mm: pagewalk: allow walking without vma

Since 48684a65b4e3: "mm: pagewalk: fix misbehavior of walk_page_range for
vma(VM_PFNMAP)", page_table_walk() will report any kernel area as a hole,
because it lacks a vma.

This means each arch has re-implemented page table walking when needed,
for example in the per-arch ptdump walker.

Remove the requirement to have a vma in the generic code and add a new
function walk_page_range_novma() which ignores the VMAs and simply walks
the page tables.

[steven.price@arm.com: v15]
  Link: http://lkml.kernel.org/r/20191101140942.51554-13-steven.price@arm.com
[steven.price@arm.com: fix boot crash]
Link: http://lkml.kernel.org/r/20191028135910.33253-13-steven.price@arm.com
Cc: Zong Li <zong.li@sifive.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Shiraz Hashim <shashim@codeaurora.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 41 insertions, 8 deletions

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 06790f23957f..2c9725bdcf1f 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -59,6 +59,7 @@ struct mm_walk_ops {
  * @ops:	operation to call during the walk
  * @mm:		mm_struct representing the target process of page table walk
  * @vma:	vma currently walked (NULL if walking outside vmas)
+ * @no_vma:	walk ignoring vmas (vma will always be NULL)
  * @private:	private data for callbacks' usage
  *
  * (see the comment on walk_page_range() for more details)
@@ -67,12 +68,16 @@ struct mm_walk {
 	const struct mm_walk_ops *ops;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
+	bool no_vma;
 	void *private;
 };
 
 int walk_page_range(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  void *private);
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private);
 int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index c089786e7a7f..efa464cf079b 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -39,7 +39,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	do {
 again:
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*pmd) || !walk->vma) {
+		if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, walk);
 			if (err)
@@ -62,9 +62,14 @@ again:
 		if (!ops->pte_entry)
 			continue;
 
-		split_huge_pmd(walk->vma, pmd, addr);
-		if (pmd_trans_unstable(pmd))
-			goto again;
+		if (walk->vma) {
+			split_huge_pmd(walk->vma, pmd, addr);
+			if (pmd_trans_unstable(pmd))
+				goto again;
+		} else if (pmd_leaf(*pmd) || !pmd_present(*pmd)) {
+			continue;
+		}
+
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
@@ -85,7 +90,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	do {
  again:
 		next = pud_addr_end(addr, end);
-		if (pud_none(*pud) || !walk->vma) {
+		if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, walk);
 			if (err)
@@ -99,9 +104,13 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 				break;
 		}
 
-		split_huge_pud(walk->vma, pud, addr);
-		if (pud_none(*pud))
-			goto again;
+		if (walk->vma) {
+			split_huge_pud(walk->vma, pud, addr);
+			if (pud_none(*pud))
+				goto again;
+		} else if (pud_leaf(*pud) || !pud_present(*pud)) {
+			continue;
+		}
 
 		if (ops->pmd_entry || ops->pte_entry)
 			err = walk_pmd_range(pud, addr, next, walk);
@@ -374,6 +383,25 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  void *private)
+{
+	struct mm_walk walk = {
+		.ops		= ops,
+		.mm		= mm,
+		.private	= private,
+		.no_vma		= true
+	};
+
+	if (start >= end || !walk.mm)
+		return -EINVAL;
+
+	lockdep_assert_held(&walk.mm->mmap_sem);
+
+	return __walk_page_range(start, end, &walk);
+}
+
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private)
 {