From: Steven Price <steven.price@arm.com>
To: Dave Hansen <dave.hansen@intel.com>,
linux-mm@kvack.org,
Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Mark Rutland" <Mark.Rutland@arm.com>,
"Arnd Bergmann" <arnd@arndb.de>,
"Ard Biesheuvel" <ard.biesheuvel@linaro.org>,
"Peter Zijlstra" <peterz@infradead.org>,
"Catalin Marinas" <catalin.marinas@arm.com>,
x86@kernel.org, "Will Deacon" <will.deacon@arm.com>,
linux-kernel@vger.kernel.org,
"Jérôme Glisse" <jglisse@redhat.com>,
"Ingo Molnar" <mingo@redhat.com>,
"Borislav Petkov" <bp@alien8.de>,
"Andy Lutomirski" <luto@kernel.org>,
"H. Peter Anvin" <hpa@zytor.com>,
"James Morse" <james.morse@arm.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Andrew Morton" <akpm@linux-foundation.org>,
linux-arm-kernel@lists.infradead.org, "Liang,
Kan" <kan.liang@linux.intel.com>,
"Steven Price" <steven.price@arm.com>
Subject: [RFC PATCH 1/3] mm: Add generic ptdump
Date: Wed, 17 Apr 2019 15:34:21 +0100 [thread overview]
Message-ID: <20190417143423.26665-1-steven.price@arm.com> (raw)
In-Reply-To: <3acbf061-8c97-55eb-f4b6-163a33ea4d73@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 | 19 +++++
mm/Kconfig.debug | 21 ++++++
mm/Makefile | 1 +
mm/ptdump.c | 159 +++++++++++++++++++++++++++++++++++++++++
4 files changed, 200 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..eb8e78154be3
--- /dev/null
+++ b/include/linux/ptdump.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PTDUMP_H
+#define _LINUX_PTDUMP_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 e3df921208c0..21bbf559408b 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -111,3 +111,24 @@ 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 kerenl 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 d210cc9d6f80..59d653c3250d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -99,3 +99,4 @@ obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
obj-$(CONFIG_HMM) += hmm.o
obj-$(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..c8e4c08ce206
--- /dev/null
+++ b/mm/ptdump.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mm.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_large(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_large(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_large(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_large(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 bool kasan_page_table(struct ptdump_state *st, void *pt,
+ unsigned long addr)
+{
+ if (__pa(pt) == __pa(kasan_early_shadow_pmd) ||
+ (pgtable_l5_enabled() &&
+ __pa(pt) == __pa(kasan_early_shadow_p4d)) ||
+ __pa(pt) == __pa(kasan_early_shadow_pud)) {
+ st->note_page(st, addr, 5, pte_val(kasan_early_shadow_pte[0]));
+ return true;
+ }
+ return false;
+}
+#else
+static inline bool kasan_page_table(struct ptdump_state *st, void *pt,
+ unsigned long addr)
+{
+ return false;
+}
+#endif
+
+static int ptdump_test_p4d(unsigned long addr, unsigned long next,
+ p4d_t *p4d, struct mm_walk *walk)
+{
+ struct ptdump_state *st = walk->private;
+
+ if (kasan_page_table(st, p4d, addr))
+ return 1;
+ return 0;
+}
+
+static int ptdump_test_pud(unsigned long addr, unsigned long next,
+ pud_t *pud, struct mm_walk *walk)
+{
+ struct ptdump_state *st = walk->private;
+
+ if (kasan_page_table(st, pud, addr))
+ return 1;
+ return 0;
+}
+
+static int ptdump_test_pmd(unsigned long addr, unsigned long next,
+ pmd_t *pmd, struct mm_walk *walk)
+{
+ struct ptdump_state *st = walk->private;
+
+ if (kasan_page_table(st, pmd, addr))
+ return 1;
+ return 0;
+}
+
+static int ptdump_hole(unsigned long addr, unsigned long next,
+ struct mm_walk *walk)
+{
+ struct ptdump_state *st = walk->private;
+
+ st->note_page(st, addr, -1, 0);
+
+ return 0;
+}
+
+void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm)
+{
+ struct mm_walk walk = {
+ .mm = mm,
+ .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,
+ .test_p4d = ptdump_test_p4d,
+ .test_pud = ptdump_test_pud,
+ .test_pmd = ptdump_test_pmd,
+ .pte_hole = ptdump_hole,
+ .private = st
+ };
+ const struct ptdump_range *range = st->range;
+
+ down_read(&mm->mmap_sem);
+ while (range->start != range->end) {
+ walk_page_range(range->start, range->end, &walk);
+ range++;
+ }
+ up_read(&mm->mmap_sem);
+
+ /* Flush out the last page */
+ st->note_page(st, 0, 0, 0);
+}
--
2.20.1
next prev parent reply other threads:[~2019-04-17 14:34 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-03 14:16 [PATCH v8 00/20] Convert x86 & arm64 to use generic page walk Steven Price
2019-04-03 14:16 ` [PATCH v8 01/20] arc: mm: Add p?d_large() definitions Steven Price
2019-04-03 14:16 ` [PATCH v8 02/20] arm64: " Steven Price
2019-06-11 15:36 ` Will Deacon
2019-04-03 14:16 ` [PATCH v8 03/20] mips: " Steven Price
2019-04-03 14:16 ` [PATCH v8 04/20] powerpc: " Steven Price
2019-04-03 14:16 ` [PATCH v8 05/20] KVM: PPC: Book3S HV: Remove pmd_is_leaf() Steven Price
2019-04-29 2:05 ` Paul Mackerras
2019-05-09 15:03 ` Steven Price
2019-04-03 14:16 ` [PATCH v8 06/20] riscv: mm: Add p?d_large() definitions Steven Price
2019-04-05 4:14 ` Anup Patel
2019-04-03 14:16 ` [PATCH v8 07/20] s390: " Steven Price
2019-04-03 14:16 ` [PATCH v8 08/20] sparc: " Steven Price
2019-04-03 14:16 ` [PATCH v8 09/20] x86: " Steven Price
2019-04-03 14:16 ` [PATCH v8 10/20] mm: Add generic p?d_large() macros Steven Price
2019-04-03 14:16 ` [PATCH v8 11/20] mm: pagewalk: Add p4d_entry() and pgd_entry() Steven Price
2019-04-03 14:16 ` [PATCH v8 12/20] mm: pagewalk: Allow walking without vma Steven Price
2019-04-03 14:16 ` [PATCH v8 13/20] mm: pagewalk: Add test_p?d callbacks Steven Price
2019-04-03 14:16 ` [PATCH v8 14/20] arm64: mm: Convert mm/dump.c to use walk_page_range() Steven Price
2019-04-03 14:16 ` [PATCH v8 15/20] x86: mm: Don't display pages which aren't present in debugfs Steven Price
2019-04-03 14:16 ` [PATCH v8 16/20] x86: mm: Point to struct seq_file from struct pg_state Steven Price
2019-04-03 14:16 ` [PATCH v8 17/20] x86: mm+efi: Convert ptdump_walk_pgd_level() to take a mm_struct Steven Price
2019-04-03 14:16 ` [PATCH v8 18/20] x86: mm: Convert ptdump_walk_pgd_level_debugfs() to take an mm_struct Steven Price
2019-04-03 14:16 ` [PATCH v8 19/20] x86: mm: Convert ptdump_walk_pgd_level_core() " Steven Price
2019-04-03 14:16 ` [PATCH v8 20/20] x86: mm: Convert dump_pagetables to use walk_page_range Steven Price
2019-04-10 14:56 ` [PATCH v8 00/20] Convert x86 & arm64 to use generic page walk Steven Price
2019-04-12 14:44 ` Dave Hansen
2019-04-17 14:28 ` Steven Price
2019-04-17 14:34 ` Steven Price [this message]
2019-04-17 14:34 ` [RFC PATCH 2/3] arm64: mm: Switch to using generic pt_dump Steven Price
2019-04-17 14:34 ` [RFC PATCH 3/3] x86: " Steven Price
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=20190417143423.26665-1-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@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=torvalds@linux-foundation.org \
--cc=will.deacon@arm.com \
--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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).