linux/arch/x86/mm/dump_pagetables.c
H. Peter Anvin 3891a04aaf x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack
The IRET instruction, when returning to a 16-bit segment, only
restores the bottom 16 bits of the user space stack pointer.  This
causes some 16-bit software to break, but it also leaks kernel state
to user space.  We have a software workaround for that ("espfix") for
the 32-bit kernel, but it relies on a nonzero stack segment base which
is not available in 64-bit mode.

In checkin:

    b3b42ac2cb x86-64, modify_ldt: Ban 16-bit segments on 64-bit kernels

we "solved" this by forbidding 16-bit segments on 64-bit kernels, with
the logic that 16-bit support is crippled on 64-bit kernels anyway (no
V86 support), but it turns out that people are doing stuff like
running old Win16 binaries under Wine and expect it to work.

This works around this by creating percpu "ministacks", each of which
is mapped 2^16 times 64K apart.  When we detect that the return SS is
on the LDT, we copy the IRET frame to the ministack and use the
relevant alias to return to userspace.  The ministacks are mapped
readonly, so if IRET faults we promote #GP to #DF which is an IST
vector and thus has its own stack; we then do the fixup in the #DF
handler.

(Making #GP an IST exception would make the msr_safe functions unsafe
in NMI/MC context, and quite possibly have other effects.)

Special thanks to:

- Andy Lutomirski, for the suggestion of using very small stack slots
  and copy (as opposed to map) the IRET frame there, and for the
  suggestion to mark them readonly and let the fault promote to #DF.
- Konrad Wilk for paravirt fixup and testing.
- Borislav Petkov for testing help and useful comments.

Reported-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Lutomriski <amluto@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dirk Hohndel <dirk@hohndel.org>
Cc: Arjan van de Ven <arjan.van.de.ven@intel.com>
Cc: comex <comexk@gmail.com>
Cc: Alexander van Heukelum <heukelum@fastmail.fm>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: <stable@vger.kernel.org> # consider after upstream merge
2014-04-30 14:14:28 -07:00

422 lines
10 KiB
C

/*
* Debug helper to dump the current kernel pagetables of the system
* so that we can see what the various memory ranges are set to.
*
* (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/mm.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <asm/pgtable.h>
/*
* The dumper groups pagetable entries of the same type into one, and for
* that it needs to keep some state when walking, and flush this state
* when a "break" in the continuity is found.
*/
struct pg_state {
int level;
pgprot_t current_prot;
unsigned long start_address;
unsigned long current_address;
const struct addr_marker *marker;
unsigned long lines;
bool to_dmesg;
};
struct addr_marker {
unsigned long start_address;
const char *name;
unsigned long max_lines;
};
/* indices for address_markers; keep sync'd w/ address_markers below */
enum address_markers_idx {
USER_SPACE_NR = 0,
#ifdef CONFIG_X86_64
KERNEL_SPACE_NR,
LOW_KERNEL_NR,
VMALLOC_START_NR,
VMEMMAP_START_NR,
ESPFIX_START_NR,
HIGH_KERNEL_NR,
MODULES_VADDR_NR,
MODULES_END_NR,
#else
KERNEL_SPACE_NR,
VMALLOC_START_NR,
VMALLOC_END_NR,
# ifdef CONFIG_HIGHMEM
PKMAP_BASE_NR,
# endif
FIXADDR_START_NR,
#endif
};
/* Address space markers hints */
static struct addr_marker address_markers[] = {
{ 0, "User Space" },
#ifdef CONFIG_X86_64
{ 0x8000000000000000UL, "Kernel Space" },
{ PAGE_OFFSET, "Low Kernel Mapping" },
{ VMALLOC_START, "vmalloc() Area" },
{ VMEMMAP_START, "Vmemmap" },
{ ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
{ __START_KERNEL_map, "High Kernel Mapping" },
{ MODULES_VADDR, "Modules" },
{ MODULES_END, "End Modules" },
#else
{ PAGE_OFFSET, "Kernel Mapping" },
{ 0/* VMALLOC_START */, "vmalloc() Area" },
{ 0/*VMALLOC_END*/, "vmalloc() End" },
# ifdef CONFIG_HIGHMEM
{ 0/*PKMAP_BASE*/, "Persisent kmap() Area" },
# endif
{ 0/*FIXADDR_START*/, "Fixmap Area" },
#endif
{ -1, NULL } /* End of list */
};
/* Multipliers for offsets within the PTEs */
#define PTE_LEVEL_MULT (PAGE_SIZE)
#define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
#define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT)
#define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
#define pt_dump_seq_printf(m, to_dmesg, fmt, args...) \
({ \
if (to_dmesg) \
printk(KERN_INFO fmt, ##args); \
else \
if (m) \
seq_printf(m, fmt, ##args); \
})
#define pt_dump_cont_printf(m, to_dmesg, fmt, args...) \
({ \
if (to_dmesg) \
printk(KERN_CONT fmt, ##args); \
else \
if (m) \
seq_printf(m, fmt, ##args); \
})
/*
* Print a readable form of a pgprot_t to the seq_file
*/
static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
{
pgprotval_t pr = pgprot_val(prot);
static const char * const level_name[] =
{ "cr3", "pgd", "pud", "pmd", "pte" };
if (!pgprot_val(prot)) {
/* Not present */
pt_dump_cont_printf(m, dmsg, " ");
} else {
if (pr & _PAGE_USER)
pt_dump_cont_printf(m, dmsg, "USR ");
else
pt_dump_cont_printf(m, dmsg, " ");
if (pr & _PAGE_RW)
pt_dump_cont_printf(m, dmsg, "RW ");
else
pt_dump_cont_printf(m, dmsg, "ro ");
if (pr & _PAGE_PWT)
pt_dump_cont_printf(m, dmsg, "PWT ");
else
pt_dump_cont_printf(m, dmsg, " ");
if (pr & _PAGE_PCD)
pt_dump_cont_printf(m, dmsg, "PCD ");
else
pt_dump_cont_printf(m, dmsg, " ");
/* Bit 9 has a different meaning on level 3 vs 4 */
if (level <= 3) {
if (pr & _PAGE_PSE)
pt_dump_cont_printf(m, dmsg, "PSE ");
else
pt_dump_cont_printf(m, dmsg, " ");
} else {
if (pr & _PAGE_PAT)
pt_dump_cont_printf(m, dmsg, "pat ");
else
pt_dump_cont_printf(m, dmsg, " ");
}
if (pr & _PAGE_GLOBAL)
pt_dump_cont_printf(m, dmsg, "GLB ");
else
pt_dump_cont_printf(m, dmsg, " ");
if (pr & _PAGE_NX)
pt_dump_cont_printf(m, dmsg, "NX ");
else
pt_dump_cont_printf(m, dmsg, "x ");
}
pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
}
/*
* On 64 bits, sign-extend the 48 bit address to 64 bit
*/
static unsigned long normalize_addr(unsigned long u)
{
#ifdef CONFIG_X86_64
return (signed long)(u << 16) >> 16;
#else
return u;
#endif
}
/*
* This function gets called on a break in a continuous series
* of PTE entries; the next one is different so we need to
* print what we collected so far.
*/
static void note_page(struct seq_file *m, struct pg_state *st,
pgprot_t new_prot, int level)
{
pgprotval_t prot, cur;
static const char units[] = "BKMGTPE";
/*
* If we have a "break" in the series, we need to flush the state that
* we have now. "break" is either changing perms, levels or
* address space marker.
*/
prot = pgprot_val(new_prot) & PTE_FLAGS_MASK;
cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK;
if (!st->level) {
/* First entry */
st->current_prot = new_prot;
st->level = level;
st->marker = address_markers;
st->lines = 0;
pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
st->marker->name);
} else if (prot != cur || level != st->level ||
st->current_address >= st->marker[1].start_address) {
const char *unit = units;
unsigned long delta;
int width = sizeof(unsigned long) * 2;
/*
* Now print the actual finished series
*/
if (!st->marker->max_lines ||
st->lines < st->marker->max_lines) {
pt_dump_seq_printf(m, st->to_dmesg,
"0x%0*lx-0x%0*lx ",
width, st->start_address,
width, st->current_address);
delta = st->current_address - st->start_address;
while (!(delta & 1023) && unit[1]) {
delta >>= 10;
unit++;
}
pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ",
delta, *unit);
printk_prot(m, st->current_prot, st->level,
st->to_dmesg);
}
st->lines++;
/*
* We print markers for special areas of address space,
* such as the start of vmalloc space etc.
* This helps in the interpretation.
*/
if (st->current_address >= st->marker[1].start_address) {
if (st->marker->max_lines &&
st->lines > st->marker->max_lines) {
unsigned long nskip =
st->lines - st->marker->max_lines;
pt_dump_seq_printf(m, st->to_dmesg,
"... %lu entr%s skipped ... \n",
nskip,
nskip == 1 ? "y" : "ies");
}
st->marker++;
st->lines = 0;
pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
st->marker->name);
}
st->start_address = st->current_address;
st->current_prot = new_prot;
st->level = level;
}
}
static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
unsigned long P)
{
int i;
pte_t *start;
start = (pte_t *) pmd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PTE; i++) {
pgprot_t prot = pte_pgprot(*start);
st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
note_page(m, st, prot, 4);
start++;
}
}
#if PTRS_PER_PMD > 1
static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
unsigned long P)
{
int i;
pmd_t *start;
start = (pmd_t *) pud_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PMD; i++) {
st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
if (!pmd_none(*start)) {
pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK;
if (pmd_large(*start) || !pmd_present(*start))
note_page(m, st, __pgprot(prot), 3);
else
walk_pte_level(m, st, *start,
P + i * PMD_LEVEL_MULT);
} else
note_page(m, st, __pgprot(0), 3);
start++;
}
}
#else
#define walk_pmd_level(m,s,a,p) walk_pte_level(m,s,__pmd(pud_val(a)),p)
#define pud_large(a) pmd_large(__pmd(pud_val(a)))
#define pud_none(a) pmd_none(__pmd(pud_val(a)))
#endif
#if PTRS_PER_PUD > 1
static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
unsigned long P)
{
int i;
pud_t *start;
start = (pud_t *) pgd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PUD; i++) {
st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
if (!pud_none(*start)) {
pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK;
if (pud_large(*start) || !pud_present(*start))
note_page(m, st, __pgprot(prot), 2);
else
walk_pmd_level(m, st, *start,
P + i * PUD_LEVEL_MULT);
} else
note_page(m, st, __pgprot(0), 2);
start++;
}
}
#else
#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(pgd_val(a)),p)
#define pgd_large(a) pud_large(__pud(pgd_val(a)))
#define pgd_none(a) pud_none(__pud(pgd_val(a)))
#endif
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
{
#ifdef CONFIG_X86_64
pgd_t *start = (pgd_t *) &init_level4_pgt;
#else
pgd_t *start = swapper_pg_dir;
#endif
int i;
struct pg_state st = {};
if (pgd) {
start = pgd;
st.to_dmesg = true;
}
for (i = 0; i < PTRS_PER_PGD; i++) {
st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
if (!pgd_none(*start)) {
pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK;
if (pgd_large(*start) || !pgd_present(*start))
note_page(m, &st, __pgprot(prot), 1);
else
walk_pud_level(m, &st, *start,
i * PGD_LEVEL_MULT);
} else
note_page(m, &st, __pgprot(0), 1);
start++;
}
/* Flush out the last page */
st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT);
note_page(m, &st, __pgprot(0), 0);
}
static int ptdump_show(struct seq_file *m, void *v)
{
ptdump_walk_pgd_level(m, NULL);
return 0;
}
static int ptdump_open(struct inode *inode, struct file *filp)
{
return single_open(filp, ptdump_show, NULL);
}
static const struct file_operations ptdump_fops = {
.open = ptdump_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int pt_dump_init(void)
{
struct dentry *pe;
#ifdef CONFIG_X86_32
/* Not a compile-time constant on x86-32 */
address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
# ifdef CONFIG_HIGHMEM
address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
# endif
address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
#endif
pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL,
&ptdump_fops);
if (!pe)
return -ENOMEM;
return 0;
}
__initcall(pt_dump_init);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables");