Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Steven Price <steven.price@arm.com>
To: Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org
Cc: "Steven Price" <steven.price@arm.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Ard Biesheuvel" <ard.biesheuvel@linaro.org>,
	"Arnd Bergmann" <arnd@arndb.de>, "Borislav Petkov" <bp@alien8.de>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"James Morse" <james.morse@arm.com>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Will Deacon" <will@kernel.org>,
	x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	"Mark Rutland" <Mark.Rutland@arm.com>,
	"Liang, Kan" <kan.liang@linux.intel.com>
Subject: [PATCH v15 19/23] mm: Add generic ptdump
Date: Fri,  1 Nov 2019 14:09:38 +0000
Message-ID: <20191101140942.51554-20-steven.price@arm.com> (raw)
In-Reply-To: <20191101140942.51554-1-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            | 151 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 194 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..79e63454f1f7
--- /dev/null
+++ b/mm/ptdump.c
@@ -0,0 +1,151 @@
+// 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_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);
+}
-- 
2.20.1



  parent reply index

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-01 14:09 [PATCH v15 00/23] Generic page walk and ptdump Steven Price
2019-11-01 14:09 ` [PATCH v15 01/23] mm: Add generic p?d_leaf() macros Steven Price
2019-11-01 14:09 ` [PATCH v15 02/23] arc: mm: Add p?d_leaf() definitions Steven Price
2019-11-01 14:09 ` [PATCH v15 03/23] arm: " Steven Price
2019-11-01 14:09 ` [PATCH v15 04/23] arm64: " Steven Price
2019-11-01 14:09 ` [PATCH v15 05/23] mips: " Steven Price
2019-11-01 14:09 ` [PATCH v15 06/23] powerpc: " Steven Price
2019-11-01 14:09 ` [PATCH v15 07/23] riscv: " Steven Price
2019-11-01 14:09 ` [PATCH v15 08/23] s390: " Steven Price
2019-11-01 14:09 ` [PATCH v15 09/23] sparc: " Steven Price
2019-11-01 14:09 ` [PATCH v15 10/23] x86: " Steven Price
2019-11-01 14:09 ` [PATCH v15 11/23] mm: pagewalk: Add p4d_entry() and pgd_entry() Steven Price
2019-11-01 14:09 ` [PATCH v15 12/23] mm: pagewalk: Allow walking without vma Steven Price
2019-11-01 14:09 ` [PATCH v15 13/23] mm: pagewalk: Add test_p?d callbacks Steven Price
2019-11-01 14:09 ` [PATCH v15 14/23] mm: pagewalk: Add 'depth' parameter to pte_hole Steven Price
2019-11-01 14:09 ` [PATCH v15 15/23] x86: mm: Point to struct seq_file from struct pg_state Steven Price
2019-11-01 14:09 ` [PATCH v15 16/23] x86: mm+efi: Convert ptdump_walk_pgd_level() to take a mm_struct Steven Price
2019-11-01 14:09 ` [PATCH v15 17/23] x86: mm: Convert ptdump_walk_pgd_level_debugfs() to take an mm_struct Steven Price
2019-11-01 14:09 ` [PATCH v15 18/23] x86: mm: Convert ptdump_walk_pgd_level_core() " Steven Price
2019-11-01 14:09 ` Steven Price [this message]
2019-11-01 14:09 ` [PATCH v15 20/23] x86: mm: Convert dump_pagetables to use walk_page_range Steven Price
2019-11-01 14:09 ` [PATCH v15 21/23] arm64: mm: Convert mm/dump.c to use walk_page_range() Steven Price
2019-11-01 14:09 ` [PATCH v15 22/23] arm64: mm: Display non-present entries in ptdump Steven Price
2019-11-01 14:09 ` [PATCH v15 23/23] mm: ptdump: Reduce level numbers by 1 in note_page() Steven Price
2019-11-04 19:35 ` [PATCH v15 00/23] Generic page walk and ptdump Qian Cai
2019-11-06 13:31   ` Qian Cai
2019-11-06 15:05     ` Steven Price
2019-12-03 11:02       ` David Hildenbrand
2019-12-04 14:54         ` Qian Cai
2019-12-04 14:56           ` David Hildenbrand
2019-12-04 16:32             ` Steven Price
2019-12-04 17:51               ` Thomas Hellstrom
2019-12-05 13:15               ` Qian Cai
2019-12-05 14:32                 ` Thomas Hellstrom
2019-12-05 14:38                   ` Qian Cai

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191101140942.51554-20-steven.price@arm.com \
    --to=steven.price@arm.com \
    --cc=Mark.Rutland@arm.com \
    --cc=akpm@linux-foundation.org \
    --cc=ard.biesheuvel@linaro.org \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jglisse@redhat.com \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git