linux_dsm_epyc7002/arch/arm64/mm/dump.c

414 lines
9.1 KiB
C
Raw Normal View History

/*
* Copyright (c) 2014, The Linux Foundation. All rights reserved.
* 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 and arm 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/errno.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/memory.h>
#include <asm/pgtable.h>
#include <asm/pgtable-hwdef.h>
#include <asm/ptdump.h>
static const struct addr_marker address_markers[] = {
#ifdef CONFIG_KASAN
{ KASAN_SHADOW_START, "Kasan shadow start" },
{ KASAN_SHADOW_END, "Kasan shadow end" },
#endif
{ MODULES_VADDR, "Modules start" },
{ MODULES_END, "Modules end" },
{ VMALLOC_START, "vmalloc() Area" },
{ VMALLOC_END, "vmalloc() End" },
{ FIXADDR_START, "Fixmap start" },
{ FIXADDR_TOP, "Fixmap end" },
{ PCI_IO_START, "PCI I/O start" },
{ PCI_IO_END, "PCI I/O end" },
#ifdef CONFIG_SPARSEMEM_VMEMMAP
{ VMEMMAP_START, "vmemmap start" },
{ VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" },
#endif
{ PAGE_OFFSET, "Linear Mapping" },
{ -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); \
})
/*
* The page dumper groups page table entries of the same type into a single
* description. It uses pg_state to track the range information while
* iterating over the pte entries. When the continuity is broken it then
* dumps out a description of the range.
*/
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;
unsigned long uxn_pages;
};
struct prot_bits {
u64 mask;
u64 val;
const char *set;
const char *clear;
};
static const struct prot_bits pte_bits[] = {
{
.mask = PTE_VALID,
.val = PTE_VALID,
.set = " ",
.clear = "F",
}, {
.mask = PTE_USER,
.val = PTE_USER,
.set = "USR",
.clear = " ",
}, {
.mask = PTE_RDONLY,
.val = PTE_RDONLY,
.set = "ro",
.clear = "RW",
}, {
.mask = PTE_PXN,
.val = PTE_PXN,
.set = "NX",
.clear = "x ",
}, {
.mask = PTE_SHARED,
.val = PTE_SHARED,
.set = "SHD",
.clear = " ",
}, {
.mask = PTE_AF,
.val = PTE_AF,
.set = "AF",
.clear = " ",
}, {
.mask = PTE_NG,
.val = PTE_NG,
.set = "NG",
.clear = " ",
}, {
.mask = PTE_CONT,
.val = PTE_CONT,
.set = "CON",
.clear = " ",
}, {
.mask = PTE_TABLE_BIT,
.val = PTE_TABLE_BIT,
.set = " ",
.clear = "BLK",
}, {
.mask = PTE_UXN,
.val = PTE_UXN,
.set = "UXN",
}, {
.mask = PTE_ATTRINDX_MASK,
.val = PTE_ATTRINDX(MT_DEVICE_nGnRnE),
.set = "DEVICE/nGnRnE",
}, {
.mask = PTE_ATTRINDX_MASK,
.val = PTE_ATTRINDX(MT_DEVICE_nGnRE),
.set = "DEVICE/nGnRE",
}, {
.mask = PTE_ATTRINDX_MASK,
.val = PTE_ATTRINDX(MT_DEVICE_GRE),
.set = "DEVICE/GRE",
}, {
.mask = PTE_ATTRINDX_MASK,
.val = PTE_ATTRINDX(MT_NORMAL_NC),
.set = "MEM/NORMAL-NC",
}, {
.mask = PTE_ATTRINDX_MASK,
.val = PTE_ATTRINDX(MT_NORMAL),
.set = "MEM/NORMAL",
}
};
struct pg_level {
const struct prot_bits *bits;
const char *name;
size_t num;
u64 mask;
};
static struct pg_level pg_level[] = {
{
}, { /* pgd */
.name = "PGD",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
}, { /* pud */
.name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
}, { /* pmd */
.name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
.bits = pte_bits,
.num = ARRAY_SIZE(pte_bits),
}, { /* pte */
.name = "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_uxn(struct pg_state *st, unsigned long addr)
{
if (!st->check_wx)
return;
if ((st->current_prot & PTE_UXN) == PTE_UXN)
return;
WARN_ONCE(1, "arm64/mm: Found non-UXN mapping at address %p/%pS\n",
(void *)st->start_address, (void *)st->start_address);
st->uxn_pages += (addr - st->start_address) / PAGE_SIZE;
}
static void note_prot_wx(struct pg_state *st, unsigned long addr)
{
if (!st->check_wx)
return;
if ((st->current_prot & PTE_RDONLY) == PTE_RDONLY)
return;
if ((st->current_prot & PTE_PXN) == PTE_PXN)
return;
WARN_ONCE(1, "arm64/mm: Found insecure W+X mapping at address %p/%pS\n",
(void *)st->start_address, (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 level,
u64 val)
{
static const char units[] = "KMGTPE";
u64 prot = val & pg_level[level].mask;
if (!st->level) {
st->level = level;
st->current_prot = prot;
st->start_address = addr;
pt_dump_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) {
note_prot_uxn(st, addr);
note_prot_wx(st, addr);
pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx ",
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 %s", delta, *unit,
pg_level[st->level].name);
if (pg_level[st->level].bits)
dump_prot(st, pg_level[st->level].bits,
pg_level[st->level].num);
pt_dump_seq_puts(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->level = level;
}
if (addr >= st->marker[1].start_address) {
st->marker++;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
}
}
static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start)
{
pte_t *ptep = pte_offset_kernel(pmdp, 0UL);
unsigned long addr;
unsigned i;
for (i = 0; i < PTRS_PER_PTE; i++, ptep++) {
addr = start + i * PAGE_SIZE;
note_page(st, addr, 4, READ_ONCE(pte_val(*ptep)));
}
}
static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start)
{
pmd_t *pmdp = pmd_offset(pudp, 0UL);
unsigned long addr;
unsigned i;
for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) {
pmd_t pmd = READ_ONCE(*pmdp);
addr = start + i * PMD_SIZE;
if (pmd_none(pmd) || pmd_sect(pmd)) {
note_page(st, addr, 3, pmd_val(pmd));
arm64: mm: use *_sect to check for section maps The {pgd,pud,pmd}_bad family of macros have slightly fuzzy cross-architecture semantics, and seem to imply a populated entry that is not a next-level table, rather than a particular type of entry (e.g. a section map). In arm64 code, for those cases where we care about whether an entry is a section mapping, we can instead use the {pud,pmd}_sect macros to explicitly check for this case. This helps to document precisely what we care about, making the code easier to read, and allows for future relaxation of the *_bad macros to check for other "bad" entries. To that end this patch updates the table dumping and initial table setup to check for section mappings with {pud,pmd}_sect, and adds/restores BUG_ON(*_bad((*p)) checks after we've handled the *_sect and *_none cases so as to catch remaining "bad" cases. In the fault handling code, show_pte is left with *_bad checks as it only cares about whether it can walk the next level table, and this path is used for both kernel and userspace fault handling. The former case will be followed by a die() where we'll report the address that triggered the fault, which can be useful context for debugging. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Steve Capper <steve.capper@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-27 23:36:30 +07:00
} else {
BUG_ON(pmd_bad(pmd));
walk_pte(st, pmdp, addr);
arm64: mm: use *_sect to check for section maps The {pgd,pud,pmd}_bad family of macros have slightly fuzzy cross-architecture semantics, and seem to imply a populated entry that is not a next-level table, rather than a particular type of entry (e.g. a section map). In arm64 code, for those cases where we care about whether an entry is a section mapping, we can instead use the {pud,pmd}_sect macros to explicitly check for this case. This helps to document precisely what we care about, making the code easier to read, and allows for future relaxation of the *_bad macros to check for other "bad" entries. To that end this patch updates the table dumping and initial table setup to check for section mappings with {pud,pmd}_sect, and adds/restores BUG_ON(*_bad((*p)) checks after we've handled the *_sect and *_none cases so as to catch remaining "bad" cases. In the fault handling code, show_pte is left with *_bad checks as it only cares about whether it can walk the next level table, and this path is used for both kernel and userspace fault handling. The former case will be followed by a die() where we'll report the address that triggered the fault, which can be useful context for debugging. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Steve Capper <steve.capper@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-27 23:36:30 +07:00
}
}
}
static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start)
{
pud_t *pudp = pud_offset(pgdp, 0UL);
unsigned long addr;
unsigned i;
for (i = 0; i < PTRS_PER_PUD; i++, pudp++) {
pud_t pud = READ_ONCE(*pudp);
addr = start + i * PUD_SIZE;
if (pud_none(pud) || pud_sect(pud)) {
note_page(st, addr, 2, pud_val(pud));
arm64: mm: use *_sect to check for section maps The {pgd,pud,pmd}_bad family of macros have slightly fuzzy cross-architecture semantics, and seem to imply a populated entry that is not a next-level table, rather than a particular type of entry (e.g. a section map). In arm64 code, for those cases where we care about whether an entry is a section mapping, we can instead use the {pud,pmd}_sect macros to explicitly check for this case. This helps to document precisely what we care about, making the code easier to read, and allows for future relaxation of the *_bad macros to check for other "bad" entries. To that end this patch updates the table dumping and initial table setup to check for section mappings with {pud,pmd}_sect, and adds/restores BUG_ON(*_bad((*p)) checks after we've handled the *_sect and *_none cases so as to catch remaining "bad" cases. In the fault handling code, show_pte is left with *_bad checks as it only cares about whether it can walk the next level table, and this path is used for both kernel and userspace fault handling. The former case will be followed by a die() where we'll report the address that triggered the fault, which can be useful context for debugging. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Steve Capper <steve.capper@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-27 23:36:30 +07:00
} else {
BUG_ON(pud_bad(pud));
walk_pmd(st, pudp, addr);
arm64: mm: use *_sect to check for section maps The {pgd,pud,pmd}_bad family of macros have slightly fuzzy cross-architecture semantics, and seem to imply a populated entry that is not a next-level table, rather than a particular type of entry (e.g. a section map). In arm64 code, for those cases where we care about whether an entry is a section mapping, we can instead use the {pud,pmd}_sect macros to explicitly check for this case. This helps to document precisely what we care about, making the code easier to read, and allows for future relaxation of the *_bad macros to check for other "bad" entries. To that end this patch updates the table dumping and initial table setup to check for section mappings with {pud,pmd}_sect, and adds/restores BUG_ON(*_bad((*p)) checks after we've handled the *_sect and *_none cases so as to catch remaining "bad" cases. In the fault handling code, show_pte is left with *_bad checks as it only cares about whether it can walk the next level table, and this path is used for both kernel and userspace fault handling. The former case will be followed by a die() where we'll report the address that triggered the fault, which can be useful context for debugging. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Steve Capper <steve.capper@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-27 23:36:30 +07:00
}
}
}
static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
unsigned long start)
{
pgd_t *pgdp = pgd_offset(mm, 0UL);
unsigned i;
unsigned long addr;
for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) {
pgd_t pgd = READ_ONCE(*pgdp);
addr = start + i * PGDIR_SIZE;
if (pgd_none(pgd)) {
note_page(st, addr, 1, pgd_val(pgd));
arm64: mm: use *_sect to check for section maps The {pgd,pud,pmd}_bad family of macros have slightly fuzzy cross-architecture semantics, and seem to imply a populated entry that is not a next-level table, rather than a particular type of entry (e.g. a section map). In arm64 code, for those cases where we care about whether an entry is a section mapping, we can instead use the {pud,pmd}_sect macros to explicitly check for this case. This helps to document precisely what we care about, making the code easier to read, and allows for future relaxation of the *_bad macros to check for other "bad" entries. To that end this patch updates the table dumping and initial table setup to check for section mappings with {pud,pmd}_sect, and adds/restores BUG_ON(*_bad((*p)) checks after we've handled the *_sect and *_none cases so as to catch remaining "bad" cases. In the fault handling code, show_pte is left with *_bad checks as it only cares about whether it can walk the next level table, and this path is used for both kernel and userspace fault handling. The former case will be followed by a die() where we'll report the address that triggered the fault, which can be useful context for debugging. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Steve Capper <steve.capper@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-27 23:36:30 +07:00
} else {
BUG_ON(pgd_bad(pgd));
walk_pud(st, pgdp, addr);
arm64: mm: use *_sect to check for section maps The {pgd,pud,pmd}_bad family of macros have slightly fuzzy cross-architecture semantics, and seem to imply a populated entry that is not a next-level table, rather than a particular type of entry (e.g. a section map). In arm64 code, for those cases where we care about whether an entry is a section mapping, we can instead use the {pud,pmd}_sect macros to explicitly check for this case. This helps to document precisely what we care about, making the code easier to read, and allows for future relaxation of the *_bad macros to check for other "bad" entries. To that end this patch updates the table dumping and initial table setup to check for section mappings with {pud,pmd}_sect, and adds/restores BUG_ON(*_bad((*p)) checks after we've handled the *_sect and *_none cases so as to catch remaining "bad" cases. In the fault handling code, show_pte is left with *_bad checks as it only cares about whether it can walk the next level table, and this path is used for both kernel and userspace fault handling. The former case will be followed by a die() where we'll report the address that triggered the fault, which can be useful context for debugging. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Steve Capper <steve.capper@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-27 23:36:30 +07:00
}
}
}
void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info)
{
struct pg_state st = {
.seq = m,
.marker = info->markers,
};
walk_pgd(&st, info->mm, info->base_addr);
note_page(&st, 0, 0, 0);
}
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;
}
static struct ptdump_info kernel_ptdump_info = {
.mm = &init_mm,
.markers = address_markers,
.base_addr = VA_START,
};
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, VA_START);
note_page(&st, 0, 0, 0);
if (st.wx_pages || st.uxn_pages)
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
st.wx_pages, st.uxn_pages);
else
pr_info("Checked W+X mappings: passed, no W+X pages found\n");
}
static int ptdump_init(void)
{
ptdump_initialize();
return ptdump_debugfs_register(&kernel_ptdump_info,
"kernel_page_tables");
}
device_initcall(ptdump_init);