summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorRussell King <rmk+kernel@arm.linux.org.uk>2013-10-23 17:13:02 +0200
committerRussell King <rmk+kernel@arm.linux.org.uk>2013-12-11 10:53:13 +0100
commit1fd15b879d0075c8916e52fb9e52522827433d1f (patch)
treea9f950c9dd0eaf9de3c7d359d20bca783564630f
parentLinux 3.13-rc1 (diff)
downloadlinux-1fd15b879d0075c8916e52fb9e52522827433d1f.tar.xz
linux-1fd15b879d0075c8916e52fb9e52522827433d1f.zip
ARM: add support to dump the kernel page tables
This patch allows the kernel page tables to be dumped via a debugfs file, allowing kernel developers to check the layout of the kernel page tables and the verify the various permissions and type settings. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-rw-r--r--arch/arm/Kconfig.debug12
-rw-r--r--arch/arm/include/asm/pgtable-2level.h1
-rw-r--r--arch/arm/include/asm/pgtable-3level.h1
-rw-r--r--arch/arm/mm/Makefile1
-rw-r--r--arch/arm/mm/dump.c345
5 files changed, 360 insertions, 0 deletions
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 5765abf5ce84..0603a6a53902 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -2,6 +2,18 @@ menu "Kernel hacking"
source "lib/Kconfig.debug"
+config ARM_PTDUMP
+ bool "Export kernel pagetable layout to userspace via debugfs"
+ depends on DEBUG_KERNEL
+ select DEBUG_FS
+ ---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"
+
config STRICT_DEVMEM
bool "Filter access to /dev/mem"
depends on MMU
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 86a659a19526..dfff709fda3c 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -160,6 +160,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
return (pmd_t *)pud;
}
+#define pmd_large(pmd) (pmd_val(pmd) & 2)
#define pmd_bad(pmd) (pmd_val(pmd) & 2)
#define copy_pmd(pmdpd,pmdps) \
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 4f9503908dca..03243f7eeddf 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -142,6 +142,7 @@
PMD_TYPE_TABLE)
#define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \
PMD_TYPE_SECT)
+#define pmd_large(pmd) pmd_sect(pmd)
#define pud_clear(pudp) \
do { \
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index ecfe6e53f6e0..7f39ce2f841f 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -12,6 +12,7 @@ ifneq ($(CONFIG_MMU),y)
obj-y += nommu.o
endif
+obj-$(CONFIG_ARM_PTDUMP) += dump.o
obj-$(CONFIG_MODULES) += proc-syms.o
obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
new file mode 100644
index 000000000000..2b3a56414271
--- /dev/null
+++ b/arch/arm/mm/dump.c
@@ -0,0 +1,345 @@
+/*
+ * Debug helper to dump the current kernel pagetables of the system
+ * so that we can see what the various memory ranges are set to.
+ *
+ * Derived from x86 implementation:
+ * (C) Copyright 2008 Intel Corporation
+ *
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+
+#include <asm/fixmap.h>
+#include <asm/pgtable.h>
+
+struct addr_marker {
+ unsigned long start_address;
+ const char *name;
+};
+
+static struct addr_marker address_markers[] = {
+ { MODULES_VADDR, "Modules" },
+ { PAGE_OFFSET, "Kernel Mapping" },
+ { 0, "vmalloc() Area" },
+ { VMALLOC_END, "vmalloc() End" },
+ { FIXADDR_START, "Fixmap Area" },
+ { CONFIG_VECTORS_BASE, "Vectors" },
+ { CONFIG_VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" },
+ { -1, NULL },
+};
+
+struct pg_state {
+ struct seq_file *seq;
+ const struct addr_marker *marker;
+ unsigned long start_address;
+ unsigned level;
+ u64 current_prot;
+};
+
+struct prot_bits {
+ u64 mask;
+ u64 val;
+ const char *set;
+ const char *clear;
+};
+
+static const struct prot_bits pte_bits[] = {
+ {
+ .mask = L_PTE_USER,
+ .val = L_PTE_USER,
+ .set = "USR",
+ .clear = " ",
+ }, {
+ .mask = L_PTE_RDONLY,
+ .val = L_PTE_RDONLY,
+ .set = "ro",
+ .clear = "RW",
+ }, {
+ .mask = L_PTE_XN,
+ .val = L_PTE_XN,
+ .set = "NX",
+ .clear = "x ",
+ }, {
+ .mask = L_PTE_SHARED,
+ .val = L_PTE_SHARED,
+ .set = "SHD",
+ .clear = " ",
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_UNCACHED,
+ .set = "SO/UNCACHED",
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_BUFFERABLE,
+ .set = "MEM/BUFFERABLE/WC",
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_WRITETHROUGH,
+ .set = "MEM/CACHED/WT",
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_WRITEBACK,
+ .set = "MEM/CACHED/WBRA",
+#ifndef CONFIG_ARM_LPAE
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_MINICACHE,
+ .set = "MEM/MINICACHE",
+#endif
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_WRITEALLOC,
+ .set = "MEM/CACHED/WBWA",
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_DEV_SHARED,
+ .set = "DEV/SHARED",
+#ifndef CONFIG_ARM_LPAE
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_DEV_NONSHARED,
+ .set = "DEV/NONSHARED",
+#endif
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_DEV_WC,
+ .set = "DEV/WC",
+ }, {
+ .mask = L_PTE_MT_MASK,
+ .val = L_PTE_MT_DEV_CACHED,
+ .set = "DEV/CACHED",
+ },
+};
+
+static const struct prot_bits section_bits[] = {
+#ifndef CONFIG_ARM_LPAE
+ /* These are approximate */
+ {
+ .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+ .val = 0,
+ .set = " ro",
+ }, {
+ .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+ .val = PMD_SECT_AP_WRITE,
+ .set = " RW",
+ }, {
+ .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+ .val = PMD_SECT_AP_READ,
+ .set = "USR ro",
+ }, {
+ .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+ .val = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+ .set = "USR RW",
+#else
+ {
+ .mask = PMD_SECT_USER,
+ .val = PMD_SECT_USER,
+ .set = "USR",
+ }, {
+ .mask = PMD_SECT_RDONLY,
+ .val = PMD_SECT_RDONLY,
+ .set = "ro",
+ .clear = "RW",
+#endif
+ }, {
+ .mask = PMD_SECT_XN,
+ .val = PMD_SECT_XN,
+ .set = "NX",
+ .clear = "x ",
+ }, {
+ .mask = PMD_SECT_S,
+ .val = PMD_SECT_S,
+ .set = "SHD",
+ .clear = " ",
+ },
+};
+
+struct pg_level {
+ const struct prot_bits *bits;
+ size_t num;
+ u64 mask;
+};
+
+static struct pg_level pg_level[] = {
+ {
+ }, { /* pgd */
+ }, { /* pud */
+ }, { /* pmd */
+ .bits = section_bits,
+ .num = ARRAY_SIZE(section_bits),
+ }, { /* pte */
+ .bits = pte_bits,
+ .num = ARRAY_SIZE(pte_bits),
+ },
+};
+
+static void dump_prot(struct pg_state *st, const struct prot_bits *bits, size_t num)
+{
+ unsigned i;
+
+ for (i = 0; i < num; i++, bits++) {
+ const char *s;
+
+ if ((st->current_prot & bits->mask) == bits->val)
+ s = bits->set;
+ else
+ s = bits->clear;
+
+ if (s)
+ seq_printf(st->seq, " %s", s);
+ }
+}
+
+static void note_page(struct pg_state *st, unsigned long addr, unsigned level, u64 val)
+{
+ static const char units[] = "KMGTPE";
+ u64 prot = val & pg_level[level].mask;
+
+ if (addr < USER_PGTABLES_CEILING)
+ return;
+
+ if (!st->level) {
+ st->level = level;
+ st->current_prot = prot;
+ seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ } else if (prot != st->current_prot || level != st->level ||
+ addr >= st->marker[1].start_address) {
+ const char *unit = units;
+ unsigned long delta;
+
+ if (st->current_prot) {
+ seq_printf(st->seq, "0x%08lx-0x%08lx ",
+ st->start_address, addr);
+
+ delta = (addr - st->start_address) >> 10;
+ while (!(delta & 1023) && unit[1]) {
+ delta >>= 10;
+ unit++;
+ }
+ seq_printf(st->seq, "%9lu%c", delta, *unit);
+ if (pg_level[st->level].bits)
+ dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num);
+ seq_printf(st->seq, "\n");
+ }
+
+ if (addr >= st->marker[1].start_address) {
+ st->marker++;
+ seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ }
+ st->start_address = addr;
+ st->current_prot = prot;
+ st->level = level;
+ }
+}
+
+static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
+{
+ pte_t *pte = pte_offset_kernel(pmd, 0);
+ unsigned long addr;
+ unsigned i;
+
+ for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
+ addr = start + i * PAGE_SIZE;
+ note_page(st, addr, 4, pte_val(*pte));
+ }
+}
+
+static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
+{
+ pmd_t *pmd = pmd_offset(pud, 0);
+ unsigned long addr;
+ unsigned i;
+
+ for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
+ addr = start + i * PMD_SIZE;
+ if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd))
+ note_page(st, addr, 3, pmd_val(*pmd));
+ else
+ walk_pte(st, pmd, addr);
+ }
+}
+
+static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
+{
+ pud_t *pud = pud_offset(pgd, 0);
+ unsigned long addr;
+ unsigned i;
+
+ for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
+ addr = start + i * PUD_SIZE;
+ if (!pud_none(*pud)) {
+ walk_pmd(st, pud, addr);
+ } else {
+ note_page(st, addr, 2, pud_val(*pud));
+ }
+ }
+}
+
+static void walk_pgd(struct seq_file *m)
+{
+ pgd_t *pgd = swapper_pg_dir;
+ struct pg_state st;
+ unsigned long addr;
+ unsigned i, pgdoff = USER_PGTABLES_CEILING / PGDIR_SIZE;
+
+ memset(&st, 0, sizeof(st));
+ st.seq = m;
+ st.marker = address_markers;
+
+ pgd += pgdoff;
+
+ for (i = pgdoff; i < PTRS_PER_PGD; i++, pgd++) {
+ addr = i * PGDIR_SIZE;
+ if (!pgd_none(*pgd)) {
+ walk_pud(&st, pgd, addr);
+ } else {
+ note_page(&st, addr, 1, pgd_val(*pgd));
+ }
+ }
+
+ note_page(&st, 0, 0, 0);
+}
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+ walk_pgd(m);
+ return 0;
+}
+
+static int ptdump_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ptdump_show, NULL);
+}
+
+static const struct file_operations ptdump_fops = {
+ .open = ptdump_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int ptdump_init(void)
+{
+ struct dentry *pe;
+ unsigned i, j;
+
+ for (i = 0; i < ARRAY_SIZE(pg_level); i++)
+ if (pg_level[i].bits)
+ for (j = 0; j < pg_level[i].num; j++)
+ pg_level[i].mask |= pg_level[i].bits[j].mask;
+
+ address_markers[2].start_address = VMALLOC_START;
+
+ pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
+ &ptdump_fops);
+ return pe ? 0 : -ENOMEM;
+}
+__initcall(ptdump_init);