pass mm into pagewalkers

diff -puN mm/pagewalk.c~pass-mm-into-pagewalkers mm/pagewalk.c
@@ -3,14 +3,14 @@
 #include <linux/sched.h>
 
 static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			  const struct mm_walk *walk, void *private)
+			  struct mm_walk *walk)
 {
 	pte_t *pte;
 	int err = 0;
 
 	pte = pte_offset_map(pmd, addr);
 	for (;;) {
-		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, private);
+		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
 		       break;
 		addr += PAGE_SIZE;

@@ -24,7 +24,7 @@ static int walk_pte_range(pmd_t *pmd, un
 }
 
 static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
-			  const struct mm_walk *walk, void *private)
+			  struct mm_walk *walk)
 {
 	pmd_t *pmd;
 	unsigned long next;

@@ -35,15 +35,15 @@ static int walk_pmd_range(pud_t *pud, un
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd)) {
 			if (walk->pte_hole)
-				err = walk->pte_hole(addr, next, private);
+				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
 			continue;
 		}
 		if (walk->pmd_entry)
-			err = walk->pmd_entry(pmd, addr, next, private);
+			err = walk->pmd_entry(pmd, addr, next, walk);
 		if (!err && walk->pte_entry)
-			err = walk_pte_range(pmd, addr, next, walk, private);
+			err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
 	} while (pmd++, addr = next, addr != end);

@@ -52,7 +52,7 @@ static int walk_pmd_range(pud_t *pud, un
 }
 
 static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
-			  const struct mm_walk *walk, void *private)
+			  struct mm_walk *walk)
 {
 	pud_t *pud;
 	unsigned long next;

@@ -63,15 +63,15 @@ static int walk_pud_range(pgd_t *pgd, un
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud)) {
 			if (walk->pte_hole)
-				err = walk->pte_hole(addr, next, private);
+				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
 			continue;
 		}
 		if (walk->pud_entry)
-			err = walk->pud_entry(pud, addr, next, private);
+			err = walk->pud_entry(pud, addr, next, walk);
 		if (!err && (walk->pmd_entry || walk->pte_entry))
-			err = walk_pmd_range(pud, addr, next, walk, private);
+			err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
 	} while (pud++, addr = next, addr != end);

@@ -85,15 +85,15 @@ static int walk_pud_range(pgd_t *pgd, un
  * @addr: starting address
  * @end: ending address
  * @walk: set of callbacks to invoke for each level of the tree
- * @private: private data passed to the callback function
  *
  * Recursively walk the page table for the memory area in a VMA,
  * calling supplied callbacks. Callbacks are called in-order (first
  * PGD, first PUD, first PMD, first PTE, second PTE... second PMD,
  * etc.). If lower-level callbacks are omitted, walking depth is reduced.
  *
- * Each callback receives an entry pointer, the start and end of the
- * associated range, and a caller-supplied private data pointer.
+ * Each callback receives an entry pointer and the start and end of the
+ * associated range, and a copy of the original mm_walk for access to
+ * the ->private or ->mm fields.
  *
  * No locks are taken, but the bottom level iterator will map PTE
  * directories from highmem if necessary.

@@ -101,9 +101,8 @@ static int walk_pud_range(pgd_t *pgd, un
  * If any callback returns a non-zero value, the walk is aborted and
  * the return value is propagated back to the caller. Otherwise 0 is returned.
  */
-int walk_page_range(const struct mm_struct *mm,
-		    unsigned long addr, unsigned long end,
-		    const struct mm_walk *walk, void *private)
+int walk_page_range(unsigned long addr, unsigned long end,
+		    struct mm_walk *walk)
 {
 	pgd_t *pgd;
 	unsigned long next;

@@ -112,21 +111,24 @@ int walk_page_range(const struct mm_stru
 	if (addr >= end)
 		return err;
 
-	pgd = pgd_offset(mm, addr);
+	if (!walk->mm)
+		return -EINVAL;
+
+	pgd = pgd_offset(walk->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd)) {
 			if (walk->pte_hole)
-				err = walk->pte_hole(addr, next, private);
+				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
 			continue;
 		}
 		if (walk->pgd_entry)
-			err = walk->pgd_entry(pgd, addr, next, private);
+			err = walk->pgd_entry(pgd, addr, next, walk);
 		if (!err &&
 		    (walk->pud_entry || walk->pmd_entry || walk->pte_entry))
-			err = walk_pud_range(pgd, addr, next, walk, private);
+			err = walk_pud_range(pgd, addr, next, walk);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);

diff -puN include/linux/mm.h~pass-mm-into-pagewalkers include/linux/mm.h
@@ -760,16 +760,17 @@ unsigned long unmap_vmas(struct mmu_gath
  * (see walk_page_range for more details)
  */
 struct mm_walk {
-	int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, void *);
-	int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *);
-	int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *);
-	int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *);
-	int (*pte_hole)(unsigned long, unsigned long, void *);
+	int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *);
+	int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *);
+	int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
+	int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
+	int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
+	struct mm_struct *mm;
+	void *private;
 };
 
-int walk_page_range(const struct mm_struct *, unsigned long addr,
-		    unsigned long end, const struct mm_walk *walk,
-		    void *private);
+int walk_page_range(unsigned long addr, unsigned long end,
+		struct mm_walk *walk);
 void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,

107 lines not on this page · raw message

diff -puN fs/proc/task_mmu.c~fix-large-pages-in-pagemap fs/proc/task_mmu.c
@@ -563,24 +563,49 @@ static u64 swap_pte_to_pagemap_entry(pte
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
+static unsigned long pte_to_pagemap_entry(pte_t pte)
+{
+	unsigned long pme = 0;
+	if (is_swap_pte(pte))
+		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+	else if (pte_present(pte))
+		pme = PM_PFRAME(pte_pfn(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+	return pme;
+}
+
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
+	struct vm_area_struct *vma = find_vma(walk->mm, addr);
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
 
 	for (; addr != end; addr += PAGE_SIZE) {
 		u64 pfn = PM_NOT_PRESENT;
-		pte = pte_offset_map(pmd, addr);
-		if (is_swap_pte(*pte))
-			pfn = PM_PFRAME(swap_pte_to_pagemap_entry(*pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
-		else if (pte_present(*pte))
-			pfn = PM_PFRAME(pte_pfn(*pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-		/* unmap so we're not in atomic when we copy to userspace */
-		pte_unmap(pte);
+
+		/*
+		 * Remember that find_vma() returns the
+		 * first vma with a vm_end > addr, but
+		 * has no guarantee about addr and
+		 * vm_start.  That means we'll always
+		 * find a vma here, unless we're at
+		 * an addr higher than the highest vma.
+		 */
+		if (vma && (addr >= vma->vm_end))
+			vma = find_vma(walk->mm, addr);
+		if (vma && (vma->vm_start <= addr) &&
+		    !is_vm_hugetlb_page(vma)) {
+			pte = pte_offset_map(pmd, addr);
+			pfn = pte_to_pagemap_entry(*pte);
+			/*
+			 * unmap so we're not in atomic
+			 * when we copy to userspace
+			 */
+			pte_unmap(pte);
+		}
 		err = add_to_pagemap(addr, pfn, pm);
 		if (err)
 			return err;

diff -puN fs/proc/task_mmu.c~fix-large-pages-in-pagemap fs/proc/task_mmu.c
@@ -563,24 +563,48 @@ static u64 swap_pte_to_pagemap_entry(pte
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
+static unsigned long pte_to_pagemap_entry(pte_t pte)
+{
+	unsigned long pme = 0;
+	if (is_swap_pte(pte))
+		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+	else if (pte_present(pte))
+		pme = PM_PFRAME(pte_pfn(pte))
+			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+	return pme;
+}
+
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
+	struct vm_area_struct *vma;
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
 
+	/* find the first VMA at or above 'addr' */
+       	vma = find_vma(walk->mm, addr);
 	for (; addr != end; addr += PAGE_SIZE) {
 		u64 pfn = PM_NOT_PRESENT;
-		pte = pte_offset_map(pmd, addr);
-		if (is_swap_pte(*pte))
-			pfn = PM_PFRAME(swap_pte_to_pagemap_entry(*pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
-		else if (pte_present(*pte))
-			pfn = PM_PFRAME(pte_pfn(*pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-		/* unmap so we're not in atomic when we copy to userspace */
-		pte_unmap(pte);
+
+		/* check to see if we've left 'vma' behind
+		 * and need a new, higher one */
+		if (vma && (addr >= vma->vm_end))
+			vma = find_vma(walk->mm, addr);
+
+		/* check that 'vma' actually covers this address,
+		 * and that it isn't a huge page vma */
+		if (vma && (vma->vm_start <= addr) &&
+		    !is_vm_hugetlb_page(vma)) {
+			pte = pte_offset_map(pmd, addr);
+			pfn = pte_to_pagemap_entry(*pte);
+			/*
+			 * unmap so we're not in atomic
+			 * when we copy to userspace
+			 */
+			pte_unmap(pte);
+		}
 		err = add_to_pagemap(addr, pfn, pm);
 		if (err)
 			return err;