mm: add generic ptdump

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

Link: http://lkml.kernel.org/r/20191218162402.45610-20-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/include/linux/ptdump.h b/include/linux/ptdump.h
new file mode 100644 (file)
index 0000000..a0fb8dd
--- /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 327b3eb..0271b22 100644 (file)
--- 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 32f08e2..272e660 100644 (file)
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -109,3 +109,4 @@ obj-$(CONFIG_ZONE_DEVICE) += memremap.o
 obj-$(CONFIG_HMM_MIRROR) += hmm.o
 obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
+obj-$(CONFIG_PTDUMP_CORE) += ptdump.o

diff --git a/mm/ptdump.c b/mm/ptdump.c
new file mode 100644 (file)
index 0000000..868638b
--- /dev/null
+++ b/mm/ptdump.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pagewalk.h>
+#include <linux/ptdump.h>
+#include <linux/kasan.h>
+
+#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]));
+
+       walk->action = ACTION_CONTINUE;
+
+       return 0;
+}
+#endif
+
+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 CONFIG_PGTABLE_LEVELS > 4 && defined(CONFIG_KASAN)
+       if (pgd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_p4d)))
+               return note_kasan_page_table(walk, addr);
+#endif
+
+       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 CONFIG_PGTABLE_LEVELS > 3 && defined(CONFIG_KASAN)
+       if (p4d_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pud)))
+               return note_kasan_page_table(walk, addr);
+#endif
+
+       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 CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_KASAN)
+       if (pud_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pmd)))
+               return note_kasan_page_table(walk, addr);
+#endif
+
+       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 defined(CONFIG_KASAN)
+       if (pmd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pte)))
+               return note_kasan_page_table(walk, addr);
+#endif
+
+       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;
+}
+
+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;
+}
+
+static const 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,
+       .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_novma(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);
+}