linux/arch/arm/mm/dump.c
Linus Torvalds f632a8170a Driver Core and debugfs changes for 5.3-rc1
Here is the "big" driver core and debugfs changes for 5.3-rc1
 
 It's a lot of different patches, all across the tree due to some api
 changes and lots of debugfs cleanups.  Because of this, there is going
 to be some merge issues with your tree at the moment, I'll follow up
 with the expected resolutions to make it easier for you.
 
 Other than the debugfs cleanups, in this set of changes we have:
 	- bus iteration function cleanups (will cause build warnings
 	  with s390 and coresight drivers in your tree)
 	- scripts/get_abi.pl tool to display and parse Documentation/ABI
 	  entries in a simple way
 	- cleanups to Documenatation/ABI/ entries to make them parse
 	  easier due to typos and other minor things
 	- default_attrs use for some ktype users
 	- driver model documentation file conversions to .rst
 	- compressed firmware file loading
 	- deferred probe fixes
 
 All of these have been in linux-next for a while, with a bunch of merge
 issues that Stephen has been patient with me for.  Other than the merge
 issues, functionality is working properly in linux-next :)
 
 Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 -----BEGIN PGP SIGNATURE-----
 
 iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCXSgpnQ8cZ3JlZ0Brcm9h
 aC5jb20ACgkQMUfUDdst+ykcwgCfS30OR4JmwZydWGJ7zK/cHqk+KjsAnjOxjC1K
 LpRyb3zX29oChFaZkc5a
 =XrEZ
 -----END PGP SIGNATURE-----

Merge tag 'driver-core-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core and debugfs updates from Greg KH:
 "Here is the "big" driver core and debugfs changes for 5.3-rc1

  It's a lot of different patches, all across the tree due to some api
  changes and lots of debugfs cleanups.

  Other than the debugfs cleanups, in this set of changes we have:

   - bus iteration function cleanups

   - scripts/get_abi.pl tool to display and parse Documentation/ABI
     entries in a simple way

   - cleanups to Documenatation/ABI/ entries to make them parse easier
     due to typos and other minor things

   - default_attrs use for some ktype users

   - driver model documentation file conversions to .rst

   - compressed firmware file loading

   - deferred probe fixes

  All of these have been in linux-next for a while, with a bunch of
  merge issues that Stephen has been patient with me for"

* tag 'driver-core-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (102 commits)
  debugfs: make error message a bit more verbose
  orangefs: fix build warning from debugfs cleanup patch
  ubifs: fix build warning after debugfs cleanup patch
  driver: core: Allow subsystems to continue deferring probe
  drivers: base: cacheinfo: Ensure cpu hotplug work is done before Intel RDT
  arch_topology: Remove error messages on out-of-memory conditions
  lib: notifier-error-inject: no need to check return value of debugfs_create functions
  swiotlb: no need to check return value of debugfs_create functions
  ceph: no need to check return value of debugfs_create functions
  sunrpc: no need to check return value of debugfs_create functions
  ubifs: no need to check return value of debugfs_create functions
  orangefs: no need to check return value of debugfs_create functions
  nfsd: no need to check return value of debugfs_create functions
  lib: 842: no need to check return value of debugfs_create functions
  debugfs: provide pr_fmt() macro
  debugfs: log errors when something goes wrong
  drivers: s390/cio: Fix compilation warning about const qualifiers
  drivers: Add generic helper to match by of_node
  driver_find_device: Unify the match function with class_find_device()
  bus_find_device: Unify the match callback with class_find_device
  ...
2019-07-12 12:24:03 -07:00

453 lines
9.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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>
*/
#include <linux/debugfs.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
#include <asm/domain.h>
#include <asm/fixmap.h>
#include <asm/memory.h>
#include <asm/pgtable.h>
#include <asm/ptdump.h>
static struct addr_marker address_markers[] = {
{ MODULES_VADDR, "Modules" },
{ PAGE_OFFSET, "Kernel Mapping" },
{ 0, "vmalloc() Area" },
{ VMALLOC_END, "vmalloc() End" },
{ FIXADDR_START, "Fixmap Area" },
{ VECTORS_BASE, "Vectors" },
{ VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" },
{ -1, NULL },
};
#define pt_dump_seq_printf(m, fmt, args...) \
({ \
if (m) \
seq_printf(m, fmt, ##args); \
})
#define pt_dump_seq_puts(m, fmt) \
({ \
if (m) \
seq_printf(m, fmt); \
})
struct pg_state {
struct seq_file *seq;
const struct addr_marker *marker;
unsigned long start_address;
unsigned level;
u64 current_prot;
bool check_wx;
unsigned long wx_pages;
const char *current_domain;
};
struct prot_bits {
u64 mask;
u64 val;
const char *set;
const char *clear;
bool ro_bit;
bool nx_bit;
};
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",
.ro_bit = true,
}, {
.mask = L_PTE_XN,
.val = L_PTE_XN,
.set = "NX",
.clear = "x ",
.nx_bit = true,
}, {
.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[] = {
#ifdef CONFIG_ARM_LPAE
{
.mask = PMD_SECT_USER,
.val = PMD_SECT_USER,
.set = "USR",
}, {
.mask = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
.val = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
.set = "ro",
.clear = "RW",
.ro_bit = true,
#elif __LINUX_ARM_ARCH__ >= 6
{
.mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
.val = PMD_SECT_APX | PMD_SECT_AP_WRITE,
.set = " ro",
.ro_bit = true,
}, {
.mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
.val = PMD_SECT_AP_WRITE,
.set = " RW",
}, {
.mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
.val = PMD_SECT_AP_READ,
.set = "USR ro",
}, {
.mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
.val = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
.set = "USR RW",
#else /* ARMv4/ARMv5 */
/* These are approximate */
{
.mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
.val = 0,
.set = " ro",
.ro_bit = true,
}, {
.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",
#endif
}, {
.mask = PMD_SECT_XN,
.val = PMD_SECT_XN,
.set = "NX",
.clear = "x ",
.nx_bit = true,
}, {
.mask = PMD_SECT_S,
.val = PMD_SECT_S,
.set = "SHD",
.clear = " ",
},
};
struct pg_level {
const struct prot_bits *bits;
size_t num;
u64 mask;
const struct prot_bits *ro_bit;
const struct prot_bits *nx_bit;
};
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)
pt_dump_seq_printf(st->seq, " %s", s);
}
}
static void note_prot_wx(struct pg_state *st, unsigned long addr)
{
if (!st->check_wx)
return;
if ((st->current_prot & pg_level[st->level].ro_bit->mask) ==
pg_level[st->level].ro_bit->val)
return;
if ((st->current_prot & pg_level[st->level].nx_bit->mask) ==
pg_level[st->level].nx_bit->val)
return;
WARN_ONCE(1, "arm/mm: Found insecure W+X mapping at address %pS\n",
(void *)st->start_address);
st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
}
static void note_page(struct pg_state *st, unsigned long addr,
unsigned int level, u64 val, const char *domain)
{
static const char units[] = "KMGTPE";
u64 prot = val & pg_level[level].mask;
if (!st->level) {
st->level = level;
st->current_prot = prot;
st->current_domain = domain;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
} else if (prot != st->current_prot || level != st->level ||
domain != st->current_domain ||
addr >= st->marker[1].start_address) {
const char *unit = units;
unsigned long delta;
if (st->current_prot) {
note_prot_wx(st, addr);
pt_dump_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++;
}
pt_dump_seq_printf(st->seq, "%9lu%c", delta, *unit);
if (st->current_domain)
pt_dump_seq_printf(st->seq, " %s",
st->current_domain);
if (pg_level[st->level].bits)
dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num);
pt_dump_seq_printf(st->seq, "\n");
}
if (addr >= st->marker[1].start_address) {
st->marker++;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n",
st->marker->name);
}
st->start_address = addr;
st->current_prot = prot;
st->current_domain = domain;
st->level = level;
}
}
static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start,
const char *domain)
{
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), domain);
}
}
static const char *get_domain_name(pmd_t *pmd)
{
#ifndef CONFIG_ARM_LPAE
switch (pmd_val(*pmd) & PMD_DOMAIN_MASK) {
case PMD_DOMAIN(DOMAIN_KERNEL):
return "KERNEL ";
case PMD_DOMAIN(DOMAIN_USER):
return "USER ";
case PMD_DOMAIN(DOMAIN_IO):
return "IO ";
case PMD_DOMAIN(DOMAIN_VECTORS):
return "VECTORS";
default:
return "unknown";
}
#endif
return NULL;
}
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;
const char *domain;
for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
addr = start + i * PMD_SIZE;
domain = get_domain_name(pmd);
if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd))
note_page(st, addr, 3, pmd_val(*pmd), domain);
else
walk_pte(st, pmd, addr, domain);
if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1])) {
addr += SECTION_SIZE;
pmd++;
domain = get_domain_name(pmd);
note_page(st, addr, 3, pmd_val(*pmd), domain);
}
}
}
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), NULL);
}
}
}
static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
unsigned long start)
{
pgd_t *pgd = pgd_offset(mm, 0UL);
unsigned i;
unsigned long addr;
for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
addr = start + i * PGDIR_SIZE;
if (!pgd_none(*pgd)) {
walk_pud(st, pgd, addr);
} else {
note_page(st, addr, 1, pgd_val(*pgd), NULL);
}
}
}
void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info)
{
struct pg_state st = {
.seq = m,
.marker = info->markers,
.check_wx = false,
};
walk_pgd(&st, info->mm, info->base_addr);
note_page(&st, 0, 0, 0, NULL);
}
static void ptdump_initialize(void)
{
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;
if (pg_level[i].bits[j].ro_bit)
pg_level[i].ro_bit = &pg_level[i].bits[j];
if (pg_level[i].bits[j].nx_bit)
pg_level[i].nx_bit = &pg_level[i].bits[j];
}
address_markers[2].start_address = VMALLOC_START;
}
static struct ptdump_info kernel_ptdump_info = {
.mm = &init_mm,
.markers = address_markers,
.base_addr = 0,
};
void ptdump_check_wx(void)
{
struct pg_state st = {
.seq = NULL,
.marker = (struct addr_marker[]) {
{ 0, NULL},
{ -1, NULL},
},
.check_wx = true,
};
walk_pgd(&st, &init_mm, 0);
note_page(&st, 0, 0, 0, NULL);
if (st.wx_pages)
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
st.wx_pages);
else
pr_info("Checked W+X mappings: passed, no W+X pages found\n");
}
static int ptdump_init(void)
{
ptdump_initialize();
ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables");
return 0;
}
__initcall(ptdump_init);