mm: pagewalk: add test_p?d callbacks

It is useful to be able to skip parts of the page table tree even when
walking without VMAs.  Add test_p?d callbacks similar to test_walk but
which are called just before a table at that level is walked.  If the
callback returns non-zero then the entire table is skipped.

Link: http://lkml.kernel.org/r/20191028135910.33253-14-steven.price@arm.com
Signed-off-by: Steven Price <steven.price@arm.com>
Tested-by: Zong Li <zong.li@sifive.com>
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: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
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: Shiraz Hashim <shashim@codeaurora.org>
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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

2 files changed, 35 insertions, 0 deletions

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 2c9725bdcf1f..84ac77620bfc 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -24,6 +24,11 @@ struct mm_walk;
  *			"do page table walk over the current vma", returning
  *			a negative value means "abort current page table walk
  *			right now" and returning 1 means "skip the current vma"
+ * @test_pmd:		similar to test_walk(), but called for every pmd.
+ * @test_pud:		similar to test_walk(), but called for every pud.
+ * @test_p4d:		similar to test_walk(), but called for every p4d.
+ *			Returning 0 means walk this part of the page tables,
+ *			returning 1 means to skip this range.
  * @pre_vma:            if set, called before starting walk on a non-null vma.
  * @post_vma:           if set, called after a walk on a non-null vma, provided
  *                      that @pre_vma and the vma walk succeeded.
@@ -49,6 +54,12 @@ struct mm_walk_ops {
 			     struct mm_walk *walk);
 	int (*test_walk)(unsigned long addr, unsigned long next,
 			struct mm_walk *walk);
+	int (*test_pmd)(unsigned long addr, unsigned long next,
+			pmd_t *pmd_start, struct mm_walk *walk);
+	int (*test_pud)(unsigned long addr, unsigned long next,
+			pud_t *pud_start, struct mm_walk *walk);
+	int (*test_p4d)(unsigned long addr, unsigned long next,
+			p4d_t *p4d_start, struct mm_walk *walk);
 	int (*pre_vma)(unsigned long start, unsigned long end,
 		       struct mm_walk *walk);
 	void (*post_vma)(struct mm_walk *walk);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index efa464cf079b..29a3a44ddf5c 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -35,6 +35,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
+	if (ops->test_pmd) {
+		err = ops->test_pmd(addr, end, pmd_offset(pud, 0UL), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	pmd = pmd_offset(pud, addr);
 	do {
 again:
@@ -86,6 +94,14 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
+	if (ops->test_pud) {
+		err = ops->test_pud(addr, end, pud_offset(p4d, 0UL), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	pud = pud_offset(p4d, addr);
 	do {
  again:
@@ -129,6 +145,14 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
+	if (ops->test_p4d) {
+		err = ops->test_p4d(addr, end, p4d_offset(pgd, 0UL), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);