[PATCH v11 19/22] mm: Add generic ptdump

[Steven Price <steven.price@arm.com>]

Add a generic version of page table dumping that architectures can
opt-in to

Signed-off-by: Steven Price <steven.price@arm.com>
---
 include/linux/ptdump.h |  21 ++++++
 mm/Kconfig.debug       |  21 ++++++
 mm/Makefile            |   1 +
 mm/ptdump.c            | 150 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 193 insertions(+)
 create mode 100644 include/linux/ptdump.h
 create mode 100644 mm/ptdump.c

diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h
new file mode 100644
index 000000000000..a0fb8dd2be97
--- /dev/null
+++ b/include/linux/ptdump.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PTDUMP_H
+#define _LINUX_PTDUMP_H
+
+#include <linux/mm_types.h>
+
+struct ptdump_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+struct ptdump_state {
+	void (*note_page)(struct ptdump_state *st, unsigned long addr,
+			  int level, unsigned long val);
+	const struct ptdump_range *range;
+};
+
+void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm);
+
+#endif /* _LINUX_PTDUMP_H */
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 327b3ebf23bf..0271b22e063f 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -117,3 +117,24 @@ config DEBUG_RODATA_TEST
     depends on STRICT_KERNEL_RWX
     ---help---
       This option enables a testcase for the setting rodata read-only.
+
+config GENERIC_PTDUMP
+	bool
+
+config PTDUMP_CORE
+	bool
+
+config PTDUMP_DEBUGFS
+	bool "Export kernel pagetable layout to userspace via debugfs"
+	depends on DEBUG_KERNEL
+	depends on DEBUG_FS
+	depends on GENERIC_PTDUMP
+	select PTDUMP_CORE
+	help
+	  Say Y here if you want to show the kernel pagetable layout in a
+	  debugfs file. This information is only useful for kernel developers
+	  who are working in architecture specific areas of the kernel.
+	  It is probably not a good idea to enable this feature in a production
+	  kernel.
+
+	  If in doubt, say N.
diff --git a/mm/Makefile b/mm/Makefile
index d996846697ef..6e962007f186 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -107,3 +107,4 @@ obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
 obj-$(CONFIG_ZONE_DEVICE) += memremap.o
 obj-$(CONFIG_HMM_MIRROR) += hmm.o
 obj-$(CONFIG_MEMFD_CREATE) += memfd.o
+obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
diff --git a/mm/ptdump.c b/mm/ptdump.c
new file mode 100644
index 000000000000..5d349311e77e
--- /dev/null
+++ b/mm/ptdump.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pagewalk.h>
+#include <linux/ptdump.h>
+#include <linux/kasan.h>
+
+static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	pgd_t val = READ_ONCE(*pgd);
+
+	if (pgd_leaf(val))
+		st->note_page(st, addr, 1, pgd_val(val));
+
+	return 0;
+}
+
+static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	p4d_t val = READ_ONCE(*p4d);
+
+	if (p4d_leaf(val))
+		st->note_page(st, addr, 2, p4d_val(val));
+
+	return 0;
+}
+
+static int ptdump_pud_entry(pud_t *pud, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	pud_t val = READ_ONCE(*pud);
+
+	if (pud_leaf(val))
+		st->note_page(st, addr, 3, pud_val(val));
+
+	return 0;
+}
+
+static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	pmd_t val = READ_ONCE(*pmd);
+
+	if (pmd_leaf(val))
+		st->note_page(st, addr, 4, pmd_val(val));
+
+	return 0;
+}
+
+static int ptdump_pte_entry(pte_t *pte, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+
+	st->note_page(st, addr, 5, pte_val(READ_ONCE(*pte)));
+
+	return 0;
+}
+
+#ifdef CONFIG_KASAN
+/*
+ * This is an optimization for KASAN=y case. Since all kasan page tables
+ * eventually point to the kasan_early_shadow_page we could call note_page()
+ * right away without walking through lower level page tables. This saves
+ * us dozens of seconds (minutes for 5-level config) while checking for
+ * W+X mapping or reading kernel_page_tables debugfs file.
+ */
+static inline int note_kasan_page_table(struct mm_walk *walk,
+					unsigned long addr)
+{
+	struct ptdump_state *st = walk->private;
+
+	st->note_page(st, addr, 5, pte_val(kasan_early_shadow_pte[0]));
+	return 1;
+}
+
+static int ptdump_test_p4d(unsigned long addr, unsigned long next,
+			   p4d_t *p4d, struct mm_walk *walk)
+{
+#if CONFIG_PGTABLE_LEVELS > 4
+	if (p4d == lm_alias(kasan_early_shadow_p4d))
+		return note_kasan_page_table(walk, addr);
+#endif
+	return 0;
+}
+
+static int ptdump_test_pud(unsigned long addr, unsigned long next,
+			   pud_t *pud, struct mm_walk *walk)
+{
+#if CONFIG_PGTABLE_LEVELS > 3
+	if (pud == lm_alias(kasan_early_shadow_pud))
+		return note_kasan_page_table(walk, addr);
+#endif
+	return 0;
+}
+
+static int ptdump_test_pmd(unsigned long addr, unsigned long next,
+			   pmd_t *pmd, struct mm_walk *walk)
+{
+#if CONFIG_PGTABLE_LEVELS > 2
+	if (pmd == lm_alias(kasan_early_shadow_pmd))
+		return note_kasan_page_table(walk, addr);
+#endif
+	return 0;
+}
+#endif /* CONFIG_KASAN */
+
+static int ptdump_hole(unsigned long addr, unsigned long next,
+		       int depth, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+
+	st->note_page(st, addr, depth + 1, 0);
+
+	return 0;
+}
+
+const static struct mm_walk_ops ptdump_ops = {
+	.pgd_entry	= ptdump_pgd_entry,
+	.p4d_entry	= ptdump_p4d_entry,
+	.pud_entry	= ptdump_pud_entry,
+	.pmd_entry	= ptdump_pmd_entry,
+	.pte_entry	= ptdump_pte_entry,
+#ifdef CONFIG_KASAN
+	.test_p4d	= ptdump_test_p4d,
+	.test_pud	= ptdump_test_pud,
+	.test_pmd	= ptdump_test_pmd,
+#endif
+	.pte_hole	= ptdump_hole,
+};
+
+void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm)
+{
+	const struct ptdump_range *range = st->range;
+
+	down_read(&mm->mmap_sem);
+	while (range->start != range->end) {
+		walk_page_range(mm, range->start, range->end, &ptdump_ops, st);
+		range++;
+	}
+	up_read(&mm->mmap_sem);
+
+	/* Flush out the last page */
+	st->note_page(st, 0, 0, 0);
+}
-- 
2.20.1