2008-02-10 06:24:09 +08:00
|
|
|
/*
|
|
|
|
|
* Hibernation support for x86-64
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* Distribute under GPLv2.
|
|
|
|
|
*
|
2008-02-10 06:24:09 +08:00
|
|
|
* Copyright 2007 Rafael J. Wysocki <rjw@sisk.pl>
|
|
|
|
|
* Copyright 2005 Andi Kleen <ak@suse.de>
|
|
|
|
|
* Copyright 2004 Pavel Machek <pavel@suse.cz>
|
|
|
|
|
*
|
2007-10-18 18:04:53 +08:00
|
|
|
* swsusp_arch_resume must not use any stack or any nonlocal variables while
|
|
|
|
|
* copying pages:
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* Its rewriting one kernel image with another. What is stack in "old"
|
|
|
|
|
* image could very well be data page in "new" image, and overwriting
|
|
|
|
|
* your own stack under you is bad idea.
|
|
|
|
|
*/
|
2008-02-10 06:24:09 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
.text
|
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
|
#include <asm/segment.h>
|
2009-02-14 03:14:01 +08:00
|
|
|
#include <asm/page_types.h>
|
2005-09-10 03:28:48 +08:00
|
|
|
#include <asm/asm-offsets.h>
|
2008-02-09 05:49:13 +08:00
|
|
|
#include <asm/processor-flags.h>
|
2016-01-22 06:49:24 +08:00
|
|
|
#include <asm/frame.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
ENTRY(swsusp_arch_suspend)
|
2016-01-22 06:49:24 +08:00
|
|
|
FRAME_BEGIN
|
2007-10-24 04:37:24 +08:00
|
|
|
movq $saved_context, %rax
|
2008-01-30 20:30:56 +08:00
|
|
|
movq %rsp, pt_regs_sp(%rax)
|
|
|
|
|
movq %rbp, pt_regs_bp(%rax)
|
|
|
|
|
movq %rsi, pt_regs_si(%rax)
|
|
|
|
|
movq %rdi, pt_regs_di(%rax)
|
|
|
|
|
movq %rbx, pt_regs_bx(%rax)
|
|
|
|
|
movq %rcx, pt_regs_cx(%rax)
|
|
|
|
|
movq %rdx, pt_regs_dx(%rax)
|
2007-10-24 04:37:24 +08:00
|
|
|
movq %r8, pt_regs_r8(%rax)
|
|
|
|
|
movq %r9, pt_regs_r9(%rax)
|
|
|
|
|
movq %r10, pt_regs_r10(%rax)
|
|
|
|
|
movq %r11, pt_regs_r11(%rax)
|
|
|
|
|
movq %r12, pt_regs_r12(%rax)
|
|
|
|
|
movq %r13, pt_regs_r13(%rax)
|
|
|
|
|
movq %r14, pt_regs_r14(%rax)
|
|
|
|
|
movq %r15, pt_regs_r15(%rax)
|
|
|
|
|
pushfq
|
2008-01-30 20:30:56 +08:00
|
|
|
popq pt_regs_flags(%rax)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-18 18:04:54 +08:00
|
|
|
/* save cr3 */
|
|
|
|
|
movq %cr3, %rax
|
|
|
|
|
movq %rax, restore_cr3(%rip)
|
2007-10-18 18:04:53 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
call swsusp_save
|
2016-01-22 06:49:24 +08:00
|
|
|
FRAME_END
|
2005-04-17 06:20:36 +08:00
|
|
|
ret
|
2016-01-22 06:49:24 +08:00
|
|
|
ENDPROC(swsusp_arch_suspend)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[PATCH] x86_64: Set up safe page tables during resume
The following patch makes swsusp avoid the possible temporary corruption
of page translation tables during resume on x86-64. This is achieved by
creating a copy of the relevant page tables that will not be modified by
swsusp and can be safely used by it on resume.
The problem is that during resume on x86-64 swsusp may temporarily
corrupt the page tables used for the direct mapping of RAM. If that
happens, a page fault occurs and cannot be handled properly, which leads
to the solid hang of the affected system. This leads to the loss of the
system's state from before suspend and may result in the loss of data or
the corruption of filesystems, so it is a serious issue. Also, it
appears to happen quite often (for me, as often as 50% of the time).
The problem is related to the fact that (at least) one of the PMD
entries used in the direct memory mapping (starting at PAGE_OFFSET)
points to a page table the physical address of which is much greater
than the physical address of the PMD entry itself. Moreover,
unfortunately, the physical address of the page table before suspend
(i.e. the one stored in the suspend image) happens to be different to
the physical address of the corresponding page table used during resume
(i.e. the one that is valid right before swsusp_arch_resume() in
arch/x86_64/kernel/suspend_asm.S is executed). Thus while the image is
restored, the "offending" PMD entry gets overwritten, so it does not
point to the right physical address any more (i.e. there's no page
table at the address pointed to by it, because it points to the address
the page table has been at during suspend). Consequently, if the PMD
entry is used later on, and it _is_ used in the process of copying the
image pages, a page fault occurs, but it cannot be handled in the normal
way and the system hangs.
In principle we can call create_resume_mapping() from
swsusp_arch_resume() (ie. from suspend_asm.S), but then the memory
allocations in create_resume_mapping(), resume_pud_mapping(), and
resume_pmd_mapping() must be made carefully so that we use _only_
NosaveFree pages in them (the other pages are overwritten by the loop in
swsusp_arch_resume()). Additionally, we are in atomic context at that
time, so we cannot use GFP_KERNEL. Moreover, if one of the allocations
fails, we should free all of the allocated pages, so we need to trace
them somehow.
All of this is done in the appended patch, except that the functions
populating the page tables are located in arch/x86_64/kernel/suspend.c
rather than in init.c. It may be done in a more elegan way in the
future, with the help of some swsusp patches that are in the works now.
[AK: move some externs into headers, renamed a function]
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-10 03:19:40 +08:00
|
|
|
ENTRY(restore_image)
|
2007-10-18 18:04:53 +08:00
|
|
|
/* prepare to jump to the image kernel */
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
movq restore_jump_address(%rip), %r8
|
|
|
|
|
movq restore_cr3(%rip), %r9
|
|
|
|
|
|
|
|
|
|
/* prepare to switch to temporary page tables */
|
|
|
|
|
movq temp_level4_pgt(%rip), %rax
|
|
|
|
|
movq mmu_cr4_features(%rip), %rbx
|
2007-10-18 18:04:53 +08:00
|
|
|
|
|
|
|
|
/* prepare to copy image data to their original locations */
|
2006-09-26 14:32:52 +08:00
|
|
|
movq restore_pblist(%rip), %rdx
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
|
|
|
|
|
/* jump to relocated restore code */
|
2007-10-18 18:04:53 +08:00
|
|
|
movq relocated_restore_code(%rip), %rcx
|
|
|
|
|
jmpq *%rcx
|
|
|
|
|
|
|
|
|
|
/* code below has been relocated to a safe page */
|
|
|
|
|
ENTRY(core_restore_code)
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
/* switch to temporary page tables */
|
|
|
|
|
movq $__PAGE_OFFSET, %rcx
|
|
|
|
|
subq %rcx, %rax
|
|
|
|
|
movq %rax, %cr3
|
|
|
|
|
/* flush TLB */
|
|
|
|
|
movq %rbx, %rcx
|
|
|
|
|
andq $~(X86_CR4_PGE), %rcx
|
|
|
|
|
movq %rcx, %cr4; # turn off PGE
|
|
|
|
|
movq %cr3, %rcx; # flush TLB
|
|
|
|
|
movq %rcx, %cr3;
|
|
|
|
|
movq %rbx, %cr4; # turn PGE back on
|
2015-04-13 03:45:06 +08:00
|
|
|
.Lloop:
|
2005-04-17 06:20:36 +08:00
|
|
|
testq %rdx, %rdx
|
2015-04-13 03:45:06 +08:00
|
|
|
jz .Ldone
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* get addresses from the pbe and copy the page */
|
|
|
|
|
movq pbe_address(%rdx), %rsi
|
|
|
|
|
movq pbe_orig_address(%rdx), %rdi
|
2007-10-18 18:04:53 +08:00
|
|
|
movq $(PAGE_SIZE >> 3), %rcx
|
2005-04-17 06:20:36 +08:00
|
|
|
rep
|
|
|
|
|
movsq
|
|
|
|
|
|
|
|
|
|
/* progress to the next pbe */
|
|
|
|
|
movq pbe_next(%rdx), %rdx
|
2015-04-13 03:45:06 +08:00
|
|
|
jmp .Lloop
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
|
2015-04-13 03:45:06 +08:00
|
|
|
.Ldone:
|
2007-10-18 18:04:53 +08:00
|
|
|
/* jump to the restore_registers address from the image header */
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
jmpq *%r8
|
2007-10-18 18:04:53 +08:00
|
|
|
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
/* code below belongs to the image kernel */
|
|
|
|
|
.align PAGE_SIZE
|
2007-10-18 18:04:53 +08:00
|
|
|
ENTRY(restore_registers)
|
2016-01-22 06:49:24 +08:00
|
|
|
FRAME_BEGIN
|
[PATCH] x86_64: Set up safe page tables during resume
The following patch makes swsusp avoid the possible temporary corruption
of page translation tables during resume on x86-64. This is achieved by
creating a copy of the relevant page tables that will not be modified by
swsusp and can be safely used by it on resume.
The problem is that during resume on x86-64 swsusp may temporarily
corrupt the page tables used for the direct mapping of RAM. If that
happens, a page fault occurs and cannot be handled properly, which leads
to the solid hang of the affected system. This leads to the loss of the
system's state from before suspend and may result in the loss of data or
the corruption of filesystems, so it is a serious issue. Also, it
appears to happen quite often (for me, as often as 50% of the time).
The problem is related to the fact that (at least) one of the PMD
entries used in the direct memory mapping (starting at PAGE_OFFSET)
points to a page table the physical address of which is much greater
than the physical address of the PMD entry itself. Moreover,
unfortunately, the physical address of the page table before suspend
(i.e. the one stored in the suspend image) happens to be different to
the physical address of the corresponding page table used during resume
(i.e. the one that is valid right before swsusp_arch_resume() in
arch/x86_64/kernel/suspend_asm.S is executed). Thus while the image is
restored, the "offending" PMD entry gets overwritten, so it does not
point to the right physical address any more (i.e. there's no page
table at the address pointed to by it, because it points to the address
the page table has been at during suspend). Consequently, if the PMD
entry is used later on, and it _is_ used in the process of copying the
image pages, a page fault occurs, but it cannot be handled in the normal
way and the system hangs.
In principle we can call create_resume_mapping() from
swsusp_arch_resume() (ie. from suspend_asm.S), but then the memory
allocations in create_resume_mapping(), resume_pud_mapping(), and
resume_pmd_mapping() must be made carefully so that we use _only_
NosaveFree pages in them (the other pages are overwritten by the loop in
swsusp_arch_resume()). Additionally, we are in atomic context at that
time, so we cannot use GFP_KERNEL. Moreover, if one of the allocations
fails, we should free all of the allocated pages, so we need to trace
them somehow.
All of this is done in the appended patch, except that the functions
populating the page tables are located in arch/x86_64/kernel/suspend.c
rather than in init.c. It may be done in a more elegan way in the
future, with the help of some swsusp patches that are in the works now.
[AK: move some externs into headers, renamed a function]
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-10 03:19:40 +08:00
|
|
|
/* go back to the original page tables */
|
x86/power/64: Fix kernel text mapping corruption during image restoration
Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).
That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables. Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.
The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.
To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch. Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.
Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too. That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables. Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.
With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it). Update RESTORE_MAGIC
too to reflect the image header format change.
Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.
This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.
Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-01 00:11:41 +08:00
|
|
|
movq %r9, %cr3
|
2007-05-03 01:27:07 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Flush TLB, including "global" things (vmalloc) */
|
|
|
|
|
movq mmu_cr4_features(%rip), %rax
|
|
|
|
|
movq %rax, %rdx
|
2008-02-09 05:49:13 +08:00
|
|
|
andq $~(X86_CR4_PGE), %rdx
|
2005-04-17 06:20:36 +08:00
|
|
|
movq %rdx, %cr4; # turn off PGE
|
|
|
|
|
movq %cr3, %rcx; # flush TLB
|
|
|
|
|
movq %rcx, %cr3
|
|
|
|
|
movq %rax, %cr4; # turn PGE back on
|
|
|
|
|
|
2007-10-24 04:37:24 +08:00
|
|
|
/* We don't restore %rax, it must be 0 anyway */
|
|
|
|
|
movq $saved_context, %rax
|
2008-01-30 20:30:56 +08:00
|
|
|
movq pt_regs_sp(%rax), %rsp
|
|
|
|
|
movq pt_regs_bp(%rax), %rbp
|
|
|
|
|
movq pt_regs_si(%rax), %rsi
|
|
|
|
|
movq pt_regs_di(%rax), %rdi
|
|
|
|
|
movq pt_regs_bx(%rax), %rbx
|
|
|
|
|
movq pt_regs_cx(%rax), %rcx
|
|
|
|
|
movq pt_regs_dx(%rax), %rdx
|
2007-10-24 04:37:24 +08:00
|
|
|
movq pt_regs_r8(%rax), %r8
|
|
|
|
|
movq pt_regs_r9(%rax), %r9
|
|
|
|
|
movq pt_regs_r10(%rax), %r10
|
|
|
|
|
movq pt_regs_r11(%rax), %r11
|
|
|
|
|
movq pt_regs_r12(%rax), %r12
|
|
|
|
|
movq pt_regs_r13(%rax), %r13
|
|
|
|
|
movq pt_regs_r14(%rax), %r14
|
|
|
|
|
movq pt_regs_r15(%rax), %r15
|
2008-01-30 20:30:56 +08:00
|
|
|
pushq pt_regs_flags(%rax)
|
2007-10-24 04:37:24 +08:00
|
|
|
popfq
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-05-02 09:53:30 +08:00
|
|
|
/* Saved in save_processor_state. */
|
|
|
|
|
lgdt saved_context_gdt_desc(%rax)
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
xorq %rax, %rax
|
|
|
|
|
|
2007-10-18 18:04:53 +08:00
|
|
|
/* tell the hibernation core that we've just restored the memory */
|
|
|
|
|
movq %rax, in_suspend(%rip)
|
|
|
|
|
|
2016-01-22 06:49:24 +08:00
|
|
|
FRAME_END
|
2005-04-17 06:20:36 +08:00
|
|
|
ret
|
2016-01-22 06:49:24 +08:00
|
|
|
ENDPROC(restore_registers)
|