Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: akpm@linux-foundation.org, alex@ghiti.fr, aou@eecs.berkeley.edu,
	ard.biesheuvel@linaro.org, arnd@arndb.de,
	benh@kernel.crashing.org, borntraeger@de.ibm.com, bp@alien8.de,
	catalin.marinas@arm.com, dave.hansen@linux.intel.com,
	davem@davemloft.net, gor@linux.ibm.com,
	heiko.carstens@de.ibm.com, hpa@zytor.com, james.morse@arm.com,
	jglisse@redhat.com, jhogan@kernel.org, kan.liang@linux.intel.com,
	linux-mm@kvack.org, linux@armlinux.org.uk, luto@kernel.org,
	mark.rutland@arm.com, mingo@redhat.com,
	mm-commits@vger.kernel.org, mpe@ellerman.id.au,
	paul.burton@mips.com, paul.walmsley@sifive.com, paulus@samba.org,
	peterz@infradead.org, ralf@linux-mips.org, steven.price@arm.com,
	tglx@linutronix.de, torvalds@linux-foundation.org,
	vgupta@synopsys.com, will@kernel.org, zong.li@sifive.com
Subject: [patch 42/67] mm: add generic ptdump
Date: Mon, 03 Feb 2020 17:36:20 -0800
Message-ID: <20200204013620.zbQjeC8MW%akpm@linux-foundation.org> (raw)
In-Reply-To: <20200203173311.6269a8be06a05e5a4aa08a93@linux-foundation.org>

From: Steven Price <steven.price@arm.com>
Subject: 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>
---

 include/linux/ptdump.h |   21 +++++
 mm/Kconfig.debug       |   21 +++++
 mm/Makefile            |    1 
 mm/ptdump.c            |  139 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 182 insertions(+)

--- /dev/null
+++ a/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 */
--- a/mm/Kconfig.debug~mm-add-generic-ptdump
+++ a/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.
--- a/mm/Makefile~mm-add-generic-ptdump
+++ a/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
--- /dev/null
+++ a/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);
+}
_


  parent reply index

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-04  1:33 incoming Andrew Morton
2020-02-04  1:33 ` [patch 01/67] ocfs2: fix oops when writing cloned file Andrew Morton
2020-02-04  1:33 ` [patch 02/67] mm/page_alloc.c: fix uninitialized memmaps on a partially populated last section Andrew Morton
2020-02-04  1:33 ` [patch 03/67] fs/proc/page.c: allow inspection of last section and fix end detection Andrew Morton
2020-02-04  1:33 ` [patch 04/67] mm/page_alloc.c: initialize memmap of unavailable memory directly Andrew Morton
2020-02-04  1:33 ` [patch 05/67] mm/page_alloc: fix and rework pfn handling in memmap_init_zone() Andrew Morton
2020-02-04  2:45   ` Linus Torvalds
2020-02-04  1:34 ` [patch 06/67] mm: factor out next_present_section_nr() Andrew Morton
2020-02-04  3:04   ` Linus Torvalds
2020-02-04  4:29     ` Andrew Morton
2020-02-04  8:22     ` David Hildenbrand
2020-02-04  1:34 ` [patch 07/67] mm/memmap_init: update variable name in memmap_init_zone Andrew Morton
2020-02-04  1:34 ` [patch 08/67] mm/memory_hotplug: poison memmap in remove_pfn_range_from_zone() Andrew Morton
2020-02-04  1:34 ` [patch 09/67] mm/memory_hotplug: we always have a zone in find_(smallest|biggest)_section_pfn Andrew Morton
2020-02-04  1:34 ` [patch 10/67] mm/memory_hotplug: don't check for "all holes" in shrink_zone_span() Andrew Morton
2020-02-04  1:34 ` [patch 11/67] mm/memory_hotplug: drop local variables " Andrew Morton
2020-02-04  1:34 ` [patch 12/67] mm/memory_hotplug: cleanup __remove_pages() Andrew Morton
2020-02-04  1:34 ` [patch 13/67] mm/memory_hotplug: drop valid_start/valid_end from test_pages_in_a_zone() Andrew Morton
2020-02-04  1:34 ` [patch 14/67] smp_mb__{before,after}_atomic(): update Documentation Andrew Morton
2020-02-04  1:34 ` [patch 15/67] ipc/mqueue.c: remove duplicated code Andrew Morton
2020-02-04  1:34 ` [patch 16/67] ipc/mqueue.c: update/document memory barriers Andrew Morton
2020-02-04  1:34 ` [patch 17/67] ipc/msg.c: update and document " Andrew Morton
2020-02-04  1:34 ` [patch 18/67] ipc/sem.c: document and update " Andrew Morton
2020-02-04  1:34 ` [patch 19/67] ipc/msg.c: consolidate all xxxctl_down() functions Andrew Morton
2020-02-04  1:34 ` [patch 20/67] drivers/block/null_blk_main.c: fix layout Andrew Morton
2020-02-04  1:34 ` [patch 21/67] drivers/block/null_blk_main.c: fix uninitialized var warnings Andrew Morton
2020-02-04  1:34 ` [patch 22/67] pinctrl: fix pxa2xx.c build warnings Andrew Morton
2020-02-04  1:34 ` [patch 23/67] mm: remove __krealloc Andrew Morton
2020-02-04  1:35 ` [patch 24/67] mm: add generic p?d_leaf() macros Andrew Morton
2020-02-04  1:35 ` [patch 25/67] arc: mm: add p?d_leaf() definitions Andrew Morton
2020-02-04  1:35 ` [patch 26/67] arm: " Andrew Morton
2020-02-04  1:35 ` [patch 27/67] arm64: " Andrew Morton
2020-02-04  1:35 ` [patch 28/67] mips: " Andrew Morton
2020-02-04  1:35 ` [patch 29/67] powerpc: " Andrew Morton
2020-02-04  1:35 ` [patch 30/67] riscv: " Andrew Morton
2020-02-04  1:35 ` [patch 31/67] s390: " Andrew Morton
2020-02-04  1:35 ` [patch 32/67] sparc: " Andrew Morton
2020-02-04  1:35 ` [patch 33/67] x86: " Andrew Morton
2020-02-04  1:35 ` [patch 34/67] mm: pagewalk: add p4d_entry() and pgd_entry() Andrew Morton
2020-02-04  1:35 ` [patch 35/67] mm: pagewalk: allow walking without vma Andrew Morton
2020-02-04  1:35 ` [patch 36/67] mm: pagewalk: don't lock PTEs for walk_page_range_novma() Andrew Morton
2020-02-04  1:35 ` [patch 37/67] mm: pagewalk: fix termination condition in walk_pte_range() Andrew Morton
2020-02-04  1:36 ` [patch 38/67] mm: pagewalk: add 'depth' parameter to pte_hole Andrew Morton
2020-02-04  1:36 ` [patch 39/67] x86: mm: point to struct seq_file from struct pg_state Andrew Morton
2020-02-04  1:36 ` [patch 40/67] x86: mm+efi: convert ptdump_walk_pgd_level() to take a mm_struct Andrew Morton
2020-02-04  1:36 ` [patch 41/67] x86: mm: convert ptdump_walk_pgd_level_debugfs() to take an mm_struct Andrew Morton
2020-02-04  1:36 ` Andrew Morton [this message]
2020-02-04  1:36 ` [patch 43/67] x86: mm: convert dump_pagetables to use walk_page_range Andrew Morton
2020-02-04  1:36 ` [patch 44/67] arm64: mm: convert mm/dump.c to use walk_page_range() Andrew Morton
2020-02-04  1:36 ` [patch 45/67] arm64: mm: display non-present entries in ptdump Andrew Morton
2020-02-04  1:36 ` [patch 46/67] mm: ptdump: reduce level numbers by 1 in note_page() Andrew Morton
2020-02-04  1:36 ` [patch 47/67] x86: mm: avoid allocating struct mm_struct on the stack Andrew Morton
2020-02-04  1:36 ` [patch 48/67] powerpc/mmu_gather: enable RCU_TABLE_FREE even for !SMP case Andrew Morton
2020-02-04  1:36 ` [patch 49/67] mm/mmu_gather: invalidate TLB correctly on batch allocation failure and flush Andrew Morton
2020-02-04  1:36 ` [patch 50/67] asm-generic/tlb: avoid potential double flush Andrew Morton
2020-02-04  1:36 ` [patch 51/67] asm-gemeric/tlb: remove stray function declarations Andrew Morton
2020-02-04  1:36 ` [patch 52/67] asm-generic/tlb: add missing CONFIG symbol Andrew Morton
2020-02-04  1:37 ` [patch 53/67] asm-generic/tlb: rename HAVE_RCU_TABLE_FREE Andrew Morton
2020-02-04  1:37 ` [patch 54/67] asm-generic/tlb: rename HAVE_MMU_GATHER_PAGE_SIZE Andrew Morton
2020-02-04  1:37 ` [patch 55/67] asm-generic/tlb: rename HAVE_MMU_GATHER_NO_GATHER Andrew Morton
2020-02-04  1:37 ` [patch 56/67] asm-generic/tlb: provide MMU_GATHER_TABLE_FREE Andrew Morton
2020-02-04  1:37 ` [patch 57/67] proc: decouple proc from VFS with "struct proc_ops" Andrew Morton
2020-02-04  1:37 ` [patch 58/67] proc: convert everything to " Andrew Morton
2020-02-04  1:37 ` [patch 59/67] lib/string: add strnchrnul() Andrew Morton
2020-02-04  1:37 ` [patch 60/67] bitops: more BITS_TO_* macros Andrew Morton
2020-02-04  1:37 ` [patch 61/67] lib: add test for bitmap_parse() Andrew Morton
2020-02-04  1:37 ` [patch 62/67] lib: make bitmap_parse_user a wrapper on bitmap_parse Andrew Morton
2020-02-04  1:37 ` [patch 63/67] lib: rework bitmap_parse() Andrew Morton
2020-02-04  1:37 ` [patch 64/67] lib: new testcases for bitmap_parse{_user} Andrew Morton
2020-02-04  1:37 ` [patch 65/67] include/linux/cpumask.h: don't calculate length of the input string Andrew Morton
2020-02-04  1:37 ` [patch 66/67] treewide: remove redundant IS_ERR() before error code check Andrew Morton
2020-02-04  1:37 ` [patch 67/67] ARM: dma-api: fix max_pfn off-by-one error in __dma_supported() Andrew Morton
2020-02-04  2:27 ` incoming Linus Torvalds
2020-02-04  2:46   ` incoming Andrew Morton
2020-02-04  3:11     ` incoming Linus Torvalds
2020-02-14  6:26 ` mmotm 2020-02-13-22-26 uploaded Andrew Morton
2020-02-14 16:29   ` mmotm 2020-02-13-22-26 uploaded (mm/hugetlb.c) Randy Dunlap
2020-02-14 17:18     ` Mike Kravetz
2020-02-14 20:51       ` Mina Almasry
     [not found]       ` <20200214204544.231482-1-almasrymina@google.com>
2020-02-14 21:00         ` [PATCH] hugetlb: fix CONFIG_CGROUP_HUGETLB ifdefs Mina Almasry
2020-02-15  1:17           ` Randy Dunlap
2020-02-15  1:56             ` Randy Dunlap
2020-02-16 20:40               ` Mina Almasry
2020-02-16 21:03                 ` Mina Almasry
2020-02-17  2:48                   ` Randy Dunlap
2020-02-17  2:57                     ` [PATCH] hugetlb: fix <linux/hugetlb_cgroup.h> structs Randy Dunlap
2020-02-17  3:53               ` [PATCH] hugetlb: fix CONFIG_CGROUP_HUGETLB ifdefs Stephen Rothwell
2020-02-14 16:49   ` mmotm 2020-02-13-22-26 uploaded (mm/migrate.c, hugetlb_cgroup.h) Randy Dunlap
2020-02-25  3:53 ` mmotm 2020-02-24-19-53 uploaded Andrew Morton
2020-02-25  6:16   ` mmotm 2020-02-24-19-53 uploaded (init/main.c: initrd*) Randy Dunlap
2020-02-25  6:18     ` Randy Dunlap
2020-02-25  6:21       ` Randy Dunlap
2020-02-25 16:41   ` mmotm 2020-02-24-19-53 uploaded (drivers/platform/x86/intel_pmc_core.c) Randy Dunlap
2020-02-25 17:01   ` mmotm 2020-02-24-19-53 uploaded (objtool warning) Randy Dunlap
2020-02-27 21:52     ` Josh Poimboeuf

Reply instructions:

You may reply publicly 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=20200204013620.zbQjeC8MW%akpm@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=alex@ghiti.fr \
    --cc=aou@eecs.berkeley.edu \
    --cc=ard.biesheuvel@linaro.org \
    --cc=arnd@arndb.de \
    --cc=benh@kernel.crashing.org \
    --cc=borntraeger@de.ibm.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=davem@davemloft.net \
    --cc=gor@linux.ibm.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jglisse@redhat.com \
    --cc=jhogan@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-mm@kvack.org \
    --cc=linux@armlinux.org.uk \
    --cc=luto@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=mm-commits@vger.kernel.org \
    --cc=mpe@ellerman.id.au \
    --cc=paul.burton@mips.com \
    --cc=paul.walmsley@sifive.com \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=ralf@linux-mips.org \
    --cc=steven.price@arm.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=vgupta@synopsys.com \
    --cc=will@kernel.org \
    --cc=zong.li@sifive.com \
    /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