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.
Link: http://lkml.kernel.org/r/20191218162402.45610-13-steven.price@arm.com
Signed-off-by: Steven Price <steven.price@arm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
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: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
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: Zong Li <zong.li@sifive.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 690af44..d577346 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)
@@ -65,13 +65,16 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
* Check this here so we only break down trans_huge
* pages when we _need_ to
*/
- if (walk->action == ACTION_CONTINUE ||
+ if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) ||
+ walk->action == ACTION_CONTINUE ||
!(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;
+ }
err = walk_pte_range(pmd, addr, next, walk);
if (err)
@@ -93,7 +96,7 @@ 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)
@@ -111,11 +114,13 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
if (walk->action == ACTION_AGAIN)
goto again;
- if (walk->action == ACTION_CONTINUE ||
+ if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) ||
+ walk->action == ACTION_CONTINUE ||
!(ops->pmd_entry || ops->pte_entry))
continue;
- split_huge_pud(walk->vma, pud, addr);
+ if (walk->vma)
+ split_huge_pud(walk->vma, pud, addr);
if (pud_none(*pud))
goto again;
@@ -389,6 +394,25 @@ 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)
{