License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* S390 version
|
2012-07-20 09:15:04 +00:00
|
|
|
* Copyright IBM Corp. 1999
|
2005-04-16 22:20:36 +00:00
|
|
|
* Author(s): Hartmut Penner (hp@de.ibm.com)
|
|
|
|
|
* Ulrich Weigand (uweigand@de.ibm.com)
|
|
|
|
|
*
|
|
|
|
|
* Derived from "arch/i386/mm/fault.c"
|
|
|
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
|
|
|
*/
|
|
|
|
|
|
2011-01-05 11:47:28 +00:00
|
|
|
#include <linux/kernel_stat.h>
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
|
|
|
#include <linux/perf_event.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/signal.h>
|
|
|
|
|
#include <linux/sched.h>
|
2017-02-08 17:51:35 +00:00
|
|
|
#include <linux/sched/debug.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/kernel.h>
|
|
|
|
|
#include <linux/errno.h>
|
|
|
|
|
#include <linux/string.h>
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
|
#include <linux/mman.h>
|
|
|
|
|
#include <linux/mm.h>
|
2009-06-12 08:26:25 +00:00
|
|
|
#include <linux/compat.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/smp.h>
|
2007-05-08 07:27:03 +00:00
|
|
|
#include <linux/kdebug.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/init.h>
|
|
|
|
|
#include <linux/console.h>
|
2016-09-19 21:54:56 +00:00
|
|
|
#include <linux/extable.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/hardirq.h>
|
2006-09-20 13:58:39 +00:00
|
|
|
#include <linux/kprobes.h>
|
2007-04-27 14:01:44 +00:00
|
|
|
#include <linux/uaccess.h>
|
2008-04-30 11:38:46 +00:00
|
|
|
#include <linux/hugetlb.h>
|
2021-07-28 19:02:53 +00:00
|
|
|
#include <linux/kfence.h>
|
2022-02-28 10:22:12 +00:00
|
|
|
#include <asm/asm-extable.h>
|
2010-02-26 21:37:43 +00:00
|
|
|
#include <asm/asm-offsets.h>
|
2015-08-20 15:28:44 +00:00
|
|
|
#include <asm/diag.h>
|
2016-03-08 10:49:57 +00:00
|
|
|
#include <asm/gmap.h>
|
2011-05-26 07:48:24 +00:00
|
|
|
#include <asm/irq.h>
|
2008-02-09 17:24:37 +00:00
|
|
|
#include <asm/mmu_context.h>
|
2012-03-28 17:30:02 +00:00
|
|
|
#include <asm/facility.h>
|
2020-01-21 08:43:10 +00:00
|
|
|
#include <asm/uv.h>
|
2008-04-17 05:46:26 +00:00
|
|
|
#include "../kernel/entry.h"
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
#define __FAIL_ADDR_MASK -4096L
|
|
|
|
|
#define __SUBCODE_MASK 0x0600
|
|
|
|
|
#define __PF_RES_FIELD 0x8000000000000000ULL
|
|
|
|
|
|
2020-02-27 13:42:29 +00:00
|
|
|
#define VM_FAULT_BADCONTEXT ((__force vm_fault_t) 0x010000)
|
|
|
|
|
#define VM_FAULT_BADMAP ((__force vm_fault_t) 0x020000)
|
|
|
|
|
#define VM_FAULT_BADACCESS ((__force vm_fault_t) 0x040000)
|
|
|
|
|
#define VM_FAULT_SIGNAL ((__force vm_fault_t) 0x080000)
|
|
|
|
|
#define VM_FAULT_PFAULT ((__force vm_fault_t) 0x100000)
|
2009-12-07 11:51:45 +00:00
|
|
|
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
enum fault_type {
|
|
|
|
|
KERNEL_FAULT,
|
|
|
|
|
USER_FAULT,
|
|
|
|
|
GMAP_FAULT,
|
|
|
|
|
};
|
|
|
|
|
|
2012-10-30 13:49:37 +00:00
|
|
|
static unsigned long store_indication __read_mostly;
|
2010-10-25 14:10:13 +00:00
|
|
|
|
2012-10-30 13:49:37 +00:00
|
|
|
static int __init fault_init(void)
|
2010-10-25 14:10:13 +00:00
|
|
|
{
|
2012-10-30 13:49:37 +00:00
|
|
|
if (test_facility(75))
|
2010-10-25 14:10:13 +00:00
|
|
|
store_indication = 0xc00;
|
2012-10-30 13:49:37 +00:00
|
|
|
return 0;
|
2010-10-25 14:10:13 +00:00
|
|
|
}
|
2012-10-30 13:49:37 +00:00
|
|
|
early_initcall(fault_init);
|
2010-10-25 14:10:13 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
* Find out which address space caused the exception.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2019-05-17 06:49:22 +00:00
|
|
|
static enum fault_type get_fault_type(struct pt_regs *regs)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
s390/uaccess: rework uaccess code - fix locking issues
The current uaccess code uses a page table walk in some circumstances,
e.g. in case of the in atomic futex operations or if running on old
hardware which doesn't support the mvcos instruction.
However it turned out that the page table walk code does not correctly
lock page tables when accessing page table entries.
In other words: a different cpu may invalidate a page table entry while
the current cpu inspects the pte. This may lead to random data corruption.
Adding correct locking however isn't trivial for all uaccess operations.
Especially copy_in_user() is problematic since that requires to hold at
least two locks, but must be protected against ABBA deadlock when a
different cpu also performs a copy_in_user() operation.
So the solution is a different approach where we change address spaces:
User space runs in primary address mode, or access register mode within
vdso code, like it currently already does.
The kernel usually also runs in home space mode, however when accessing
user space the kernel switches to primary or secondary address mode if
the mvcos instruction is not available or if a compare-and-swap (futex)
instruction on a user space address is performed.
KVM however is special, since that requires the kernel to run in home
address space while implicitly accessing user space with the sie
instruction.
So we end up with:
User space:
- runs in primary or access register mode
- cr1 contains the user asce
- cr7 contains the user asce
- cr13 contains the kernel asce
Kernel space:
- runs in home space mode
- cr1 contains the user or kernel asce
-> the kernel asce is loaded when a uaccess requires primary or
secondary address mode
- cr7 contains the user or kernel asce, (changed with set_fs())
- cr13 contains the kernel asce
In case of uaccess the kernel changes to:
- primary space mode in case of a uaccess (copy_to_user) and uses
e.g. the mvcp instruction to access user space. However the kernel
will stay in home space mode if the mvcos instruction is available
- secondary space mode in case of futex atomic operations, so that the
instructions come from primary address space and data from secondary
space
In case of kvm the kernel runs in home space mode, but cr1 gets switched
to contain the gmap asce before the sie instruction gets executed. When
the sie instruction is finished cr1 will be switched back to contain the
user asce.
A context switch between two processes will always load the kernel asce
for the next process in cr1. So the first exit to user space is a bit
more expensive (one extra load control register instruction) than before,
however keeps the code rather simple.
In sum this means there is no need to perform any error prone page table
walks anymore when accessing user space.
The patch seems to be rather large, however it mainly removes the
the page table walk code and restores the previously deleted "standard"
uaccess code, with a couple of changes.
The uaccess without mvcos mode can be enforced with the "uaccess_primary"
kernel parameter.
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-03-21 09:42:25 +00:00
|
|
|
unsigned long trans_exc_code;
|
|
|
|
|
|
|
|
|
|
trans_exc_code = regs->int_parm_long & 3;
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
if (likely(trans_exc_code == 0)) {
|
|
|
|
|
/* primary space exception */
|
2020-11-16 07:06:40 +00:00
|
|
|
if (user_mode(regs))
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
return USER_FAULT;
|
2020-11-16 07:06:40 +00:00
|
|
|
if (!IS_ENABLED(CONFIG_PGSTE))
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
return KERNEL_FAULT;
|
2020-11-16 07:06:40 +00:00
|
|
|
if (test_pt_regs_flag(regs, PIF_GUEST_FAULT))
|
|
|
|
|
return GMAP_FAULT;
|
|
|
|
|
return KERNEL_FAULT;
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
}
|
2020-11-16 07:06:40 +00:00
|
|
|
if (trans_exc_code == 2)
|
|
|
|
|
return USER_FAULT;
|
2019-05-27 16:40:19 +00:00
|
|
|
if (trans_exc_code == 1) {
|
|
|
|
|
/* access register mode, not used in the kernel */
|
|
|
|
|
return USER_FAULT;
|
|
|
|
|
}
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
/* home space exception -> access via kernel ASCE */
|
|
|
|
|
return KERNEL_FAULT;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
2014-04-07 08:20:40 +00:00
|
|
|
static int bad_address(void *p)
|
|
|
|
|
{
|
|
|
|
|
unsigned long dummy;
|
|
|
|
|
|
2020-06-17 07:37:55 +00:00
|
|
|
return get_kernel_nofault(dummy, (unsigned long *)p);
|
2014-04-07 08:20:40 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void dump_pagetable(unsigned long asce, unsigned long address)
|
|
|
|
|
{
|
2017-05-22 11:16:00 +00:00
|
|
|
unsigned long *table = __va(asce & _ASCE_ORIGIN);
|
2014-04-07 08:20:40 +00:00
|
|
|
|
|
|
|
|
pr_alert("AS:%016lx ", asce);
|
|
|
|
|
switch (asce & _ASCE_TYPE_MASK) {
|
|
|
|
|
case _ASCE_TYPE_REGION1:
|
2017-07-05 05:37:27 +00:00
|
|
|
table += (address & _REGION1_INDEX) >> _REGION1_SHIFT;
|
2014-04-07 08:20:40 +00:00
|
|
|
if (bad_address(table))
|
|
|
|
|
goto bad;
|
|
|
|
|
pr_cont("R1:%016lx ", *table);
|
|
|
|
|
if (*table & _REGION_ENTRY_INVALID)
|
|
|
|
|
goto out;
|
2021-12-06 17:55:21 +00:00
|
|
|
table = __va(*table & _REGION_ENTRY_ORIGIN);
|
2020-03-10 20:47:30 +00:00
|
|
|
fallthrough;
|
2014-04-07 08:20:40 +00:00
|
|
|
case _ASCE_TYPE_REGION2:
|
2017-07-05 05:37:27 +00:00
|
|
|
table += (address & _REGION2_INDEX) >> _REGION2_SHIFT;
|
2014-04-07 08:20:40 +00:00
|
|
|
if (bad_address(table))
|
|
|
|
|
goto bad;
|
|
|
|
|
pr_cont("R2:%016lx ", *table);
|
|
|
|
|
if (*table & _REGION_ENTRY_INVALID)
|
|
|
|
|
goto out;
|
2021-12-06 17:55:21 +00:00
|
|
|
table = __va(*table & _REGION_ENTRY_ORIGIN);
|
2020-03-10 20:47:30 +00:00
|
|
|
fallthrough;
|
2014-04-07 08:20:40 +00:00
|
|
|
case _ASCE_TYPE_REGION3:
|
2017-07-05 05:37:27 +00:00
|
|
|
table += (address & _REGION3_INDEX) >> _REGION3_SHIFT;
|
2014-04-07 08:20:40 +00:00
|
|
|
if (bad_address(table))
|
|
|
|
|
goto bad;
|
|
|
|
|
pr_cont("R3:%016lx ", *table);
|
|
|
|
|
if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE))
|
|
|
|
|
goto out;
|
2021-12-06 17:55:21 +00:00
|
|
|
table = __va(*table & _REGION_ENTRY_ORIGIN);
|
2020-03-10 20:47:30 +00:00
|
|
|
fallthrough;
|
2014-04-07 08:20:40 +00:00
|
|
|
case _ASCE_TYPE_SEGMENT:
|
2017-07-05 05:37:27 +00:00
|
|
|
table += (address & _SEGMENT_INDEX) >> _SEGMENT_SHIFT;
|
2014-04-07 08:20:40 +00:00
|
|
|
if (bad_address(table))
|
|
|
|
|
goto bad;
|
2015-01-05 12:29:18 +00:00
|
|
|
pr_cont("S:%016lx ", *table);
|
2014-04-07 08:20:40 +00:00
|
|
|
if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE))
|
|
|
|
|
goto out;
|
2021-12-06 17:55:21 +00:00
|
|
|
table = __va(*table & _SEGMENT_ENTRY_ORIGIN);
|
2014-04-07 08:20:40 +00:00
|
|
|
}
|
2017-07-05 05:37:27 +00:00
|
|
|
table += (address & _PAGE_INDEX) >> _PAGE_SHIFT;
|
2014-04-07 08:20:40 +00:00
|
|
|
if (bad_address(table))
|
|
|
|
|
goto bad;
|
|
|
|
|
pr_cont("P:%016lx ", *table);
|
|
|
|
|
out:
|
|
|
|
|
pr_cont("\n");
|
|
|
|
|
return;
|
|
|
|
|
bad:
|
|
|
|
|
pr_cont("BAD\n");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void dump_fault_info(struct pt_regs *regs)
|
|
|
|
|
{
|
|
|
|
|
unsigned long asce;
|
|
|
|
|
|
2016-02-24 13:27:46 +00:00
|
|
|
pr_alert("Failing address: %016lx TEID: %016lx\n",
|
|
|
|
|
regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
|
2014-04-07 08:20:40 +00:00
|
|
|
pr_alert("Fault in ");
|
|
|
|
|
switch (regs->int_parm_long & 3) {
|
|
|
|
|
case 3:
|
|
|
|
|
pr_cont("home space ");
|
|
|
|
|
break;
|
|
|
|
|
case 2:
|
|
|
|
|
pr_cont("secondary space ");
|
|
|
|
|
break;
|
|
|
|
|
case 1:
|
|
|
|
|
pr_cont("access register ");
|
|
|
|
|
break;
|
|
|
|
|
case 0:
|
|
|
|
|
pr_cont("primary space ");
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
pr_cont("mode while using ");
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
switch (get_fault_type(regs)) {
|
|
|
|
|
case USER_FAULT:
|
2014-04-07 08:20:40 +00:00
|
|
|
asce = S390_lowcore.user_asce;
|
|
|
|
|
pr_cont("user ");
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
break;
|
|
|
|
|
case GMAP_FAULT:
|
|
|
|
|
asce = ((struct gmap *) S390_lowcore.gmap)->asce;
|
|
|
|
|
pr_cont("gmap ");
|
|
|
|
|
break;
|
|
|
|
|
case KERNEL_FAULT:
|
|
|
|
|
asce = S390_lowcore.kernel_asce;
|
|
|
|
|
pr_cont("kernel ");
|
|
|
|
|
break;
|
2019-05-17 06:49:22 +00:00
|
|
|
default:
|
|
|
|
|
unreachable();
|
2014-04-07 08:20:40 +00:00
|
|
|
}
|
|
|
|
|
pr_cont("ASCE.\n");
|
|
|
|
|
dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-24 13:27:46 +00:00
|
|
|
int show_unhandled_signals = 1;
|
|
|
|
|
|
|
|
|
|
void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
|
2010-05-17 08:00:21 +00:00
|
|
|
{
|
|
|
|
|
if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
|
|
|
|
|
return;
|
|
|
|
|
if (!unhandled_signal(current, signr))
|
|
|
|
|
return;
|
|
|
|
|
if (!printk_ratelimit())
|
|
|
|
|
return;
|
2015-01-29 13:38:38 +00:00
|
|
|
printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ",
|
2014-11-19 12:31:08 +00:00
|
|
|
regs->int_code & 0xffff, regs->int_code >> 17);
|
2016-01-18 12:12:19 +00:00
|
|
|
print_vma_addr(KERN_CONT "in ", regs->psw.addr);
|
2011-12-27 10:27:18 +00:00
|
|
|
printk(KERN_CONT "\n");
|
2016-02-24 13:27:46 +00:00
|
|
|
if (is_mm_fault)
|
|
|
|
|
dump_fault_info(regs);
|
2010-05-17 08:00:21 +00:00
|
|
|
show_regs(regs);
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* Send SIGSEGV to task. This is an external routine
|
|
|
|
|
* to keep the stack usage of do_page_fault small.
|
|
|
|
|
*/
|
2011-12-27 10:27:18 +00:00
|
|
|
static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2016-02-24 13:27:46 +00:00
|
|
|
report_user_fault(regs, SIGSEGV, 1);
|
2018-04-16 00:58:32 +00:00
|
|
|
force_sig_fault(SIGSEGV, si_code,
|
2019-05-23 16:04:24 +00:00
|
|
|
(void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK));
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
2011-12-27 10:27:18 +00:00
|
|
|
static noinline void do_no_context(struct pt_regs *regs)
|
2007-04-27 14:01:43 +00:00
|
|
|
{
|
2022-02-28 13:29:25 +00:00
|
|
|
if (fixup_exception(regs))
|
2007-04-27 14:01:43 +00:00
|
|
|
return;
|
|
|
|
|
/*
|
|
|
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
|
|
|
* terminate things with extreme prejudice.
|
|
|
|
|
*/
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
if (get_fault_type(regs) == KERNEL_FAULT)
|
2007-04-27 14:01:43 +00:00
|
|
|
printk(KERN_ALERT "Unable to handle kernel pointer dereference"
|
2014-04-07 08:20:40 +00:00
|
|
|
" in virtual kernel address space\n");
|
2007-04-27 14:01:43 +00:00
|
|
|
else
|
|
|
|
|
printk(KERN_ALERT "Unable to handle kernel paging request"
|
2014-04-07 08:20:40 +00:00
|
|
|
" in virtual user address space\n");
|
|
|
|
|
dump_fault_info(regs);
|
2011-12-27 10:27:18 +00:00
|
|
|
die(regs, "Oops");
|
2007-04-27 14:01:43 +00:00
|
|
|
}
|
|
|
|
|
|
2011-12-27 10:27:18 +00:00
|
|
|
static noinline void do_low_address(struct pt_regs *regs)
|
2007-04-27 14:01:43 +00:00
|
|
|
{
|
|
|
|
|
/* Low-address protection hit in kernel mode means
|
|
|
|
|
NULL pointer write access in kernel mode. */
|
|
|
|
|
if (regs->psw.mask & PSW_MASK_PSTATE) {
|
|
|
|
|
/* Low-address protection hit in user mode 'cannot happen'. */
|
2011-12-27 10:27:18 +00:00
|
|
|
die (regs, "Low-address protection");
|
2007-04-27 14:01:43 +00:00
|
|
|
}
|
|
|
|
|
|
2011-12-27 10:27:18 +00:00
|
|
|
do_no_context(regs);
|
2007-04-27 14:01:43 +00:00
|
|
|
}
|
|
|
|
|
|
2011-12-27 10:27:18 +00:00
|
|
|
static noinline void do_sigbus(struct pt_regs *regs)
|
2007-04-27 14:01:43 +00:00
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* Send a sigbus, regardless of whether we were in kernel
|
|
|
|
|
* or user mode.
|
|
|
|
|
*/
|
2018-04-16 00:58:32 +00:00
|
|
|
force_sig_fault(SIGBUS, BUS_ADRERR,
|
2019-05-23 16:04:24 +00:00
|
|
|
(void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK));
|
2007-04-27 14:01:43 +00:00
|
|
|
}
|
|
|
|
|
|
2022-08-29 12:26:56 +00:00
|
|
|
static noinline void do_fault_error(struct pt_regs *regs, vm_fault_t fault)
|
2009-12-07 11:51:45 +00:00
|
|
|
{
|
|
|
|
|
int si_code;
|
|
|
|
|
|
|
|
|
|
switch (fault) {
|
|
|
|
|
case VM_FAULT_BADACCESS:
|
|
|
|
|
case VM_FAULT_BADMAP:
|
|
|
|
|
/* Bad memory access. Check if it is kernel or user space. */
|
2012-07-27 08:31:12 +00:00
|
|
|
if (user_mode(regs)) {
|
2009-12-07 11:51:45 +00:00
|
|
|
/* User mode accesses just cause a SIGSEGV */
|
|
|
|
|
si_code = (fault == VM_FAULT_BADMAP) ?
|
|
|
|
|
SEGV_MAPERR : SEGV_ACCERR;
|
2011-12-27 10:27:18 +00:00
|
|
|
do_sigsegv(regs, si_code);
|
2016-03-22 09:54:24 +00:00
|
|
|
break;
|
2009-12-07 11:51:45 +00:00
|
|
|
}
|
2020-03-10 20:47:30 +00:00
|
|
|
fallthrough;
|
2009-12-07 11:51:45 +00:00
|
|
|
case VM_FAULT_BADCONTEXT:
|
2013-06-17 14:25:18 +00:00
|
|
|
case VM_FAULT_PFAULT:
|
2011-12-27 10:27:18 +00:00
|
|
|
do_no_context(regs);
|
2009-12-07 11:51:45 +00:00
|
|
|
break;
|
2012-07-27 06:54:20 +00:00
|
|
|
case VM_FAULT_SIGNAL:
|
|
|
|
|
if (!user_mode(regs))
|
|
|
|
|
do_no_context(regs);
|
|
|
|
|
break;
|
2009-12-07 11:51:45 +00:00
|
|
|
default: /* fault & VM_FAULT_ERROR */
|
2011-05-26 07:48:29 +00:00
|
|
|
if (fault & VM_FAULT_OOM) {
|
2012-07-27 08:31:12 +00:00
|
|
|
if (!user_mode(regs))
|
2011-12-27 10:27:18 +00:00
|
|
|
do_no_context(regs);
|
2011-05-26 07:48:29 +00:00
|
|
|
else
|
|
|
|
|
pagefault_out_of_memory();
|
vm: add VM_FAULT_SIGSEGV handling support
The core VM already knows about VM_FAULT_SIGBUS, but cannot return a
"you should SIGSEGV" error, because the SIGSEGV case was generally
handled by the caller - usually the architecture fault handler.
That results in lots of duplication - all the architecture fault
handlers end up doing very similar "look up vma, check permissions, do
retries etc" - but it generally works. However, there are cases where
the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV.
In particular, when accessing the stack guard page, libsigsegv expects a
SIGSEGV. And it usually got one, because the stack growth is handled by
that duplicated architecture fault handler.
However, when the generic VM layer started propagating the error return
from the stack expansion in commit fee7e49d4514 ("mm: propagate error
from stack expansion even for guard page"), that now exposed the
existing VM_FAULT_SIGBUS result to user space. And user space really
expected SIGSEGV, not SIGBUS.
To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those
duplicate architecture fault handlers about it. They all already have
the code to handle SIGSEGV, so it's about just tying that new return
value to the existing code, but it's all a bit annoying.
This is the mindless minimal patch to do this. A more extensive patch
would be to try to gather up the mostly shared fault handling logic into
one generic helper routine, and long-term we really should do that
cleanup.
Just from this patch, you can generally see that most architectures just
copied (directly or indirectly) the old x86 way of doing things, but in
the meantime that original x86 model has been improved to hold the VM
semaphore for shorter times etc and to handle VM_FAULT_RETRY and other
"newer" things, so it would be a good idea to bring all those
improvements to the generic case and teach other architectures about
them too.
Reported-and-tested-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Jan Engelhardt <jengelh@inai.de>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots"
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-01-29 18:51:32 +00:00
|
|
|
} else if (fault & VM_FAULT_SIGSEGV) {
|
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
|
|
|
if (!user_mode(regs))
|
|
|
|
|
do_no_context(regs);
|
|
|
|
|
else
|
|
|
|
|
do_sigsegv(regs, SEGV_MAPERR);
|
2011-05-26 07:48:29 +00:00
|
|
|
} else if (fault & VM_FAULT_SIGBUS) {
|
2009-12-07 11:51:45 +00:00
|
|
|
/* Kernel mode? Handle exceptions or die */
|
2012-07-27 08:31:12 +00:00
|
|
|
if (!user_mode(regs))
|
2011-12-27 10:27:18 +00:00
|
|
|
do_no_context(regs);
|
2010-10-25 14:10:35 +00:00
|
|
|
else
|
2011-12-27 10:27:18 +00:00
|
|
|
do_sigbus(regs);
|
2009-12-07 11:51:45 +00:00
|
|
|
} else
|
|
|
|
|
BUG();
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* This routine handles page faults. It determines the address,
|
|
|
|
|
* and the problem, and then passes it off to one of the appropriate
|
|
|
|
|
* routines.
|
|
|
|
|
*
|
2009-12-07 11:51:45 +00:00
|
|
|
* interruption code (int_code):
|
2020-07-14 05:43:26 +00:00
|
|
|
* 04 Protection -> Write-Protection (suppression)
|
2005-04-16 22:20:36 +00:00
|
|
|
* 10 Segment translation -> Not present (nullification)
|
|
|
|
|
* 11 Page translation -> Not present (nullification)
|
|
|
|
|
* 3b Region third trans. -> Not present (nullification)
|
|
|
|
|
*/
|
2018-08-17 22:44:47 +00:00
|
|
|
static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2013-06-17 14:25:18 +00:00
|
|
|
struct gmap *gmap;
|
2007-04-27 14:01:43 +00:00
|
|
|
struct task_struct *tsk;
|
|
|
|
|
struct mm_struct *mm;
|
|
|
|
|
struct vm_area_struct *vma;
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
enum fault_type type;
|
2011-12-27 10:27:18 +00:00
|
|
|
unsigned long trans_exc_code;
|
2007-04-27 14:01:43 +00:00
|
|
|
unsigned long address;
|
2011-05-26 07:48:30 +00:00
|
|
|
unsigned int flags;
|
2018-08-17 22:44:47 +00:00
|
|
|
vm_fault_t fault;
|
2021-07-28 19:02:53 +00:00
|
|
|
bool is_write;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2012-11-21 15:36:27 +00:00
|
|
|
tsk = current;
|
|
|
|
|
/*
|
|
|
|
|
* The instruction that caused the program check has
|
|
|
|
|
* been nullified. Don't signal single step via SIGTRAP.
|
|
|
|
|
*/
|
2020-11-21 10:14:56 +00:00
|
|
|
clear_thread_flag(TIF_PER_TRAP);
|
2012-11-21 15:36:27 +00:00
|
|
|
|
2019-07-16 23:28:00 +00:00
|
|
|
if (kprobe_page_fault(regs, 14))
|
2009-12-07 11:51:45 +00:00
|
|
|
return 0;
|
2006-09-20 13:58:39 +00:00
|
|
|
|
2007-04-27 14:01:43 +00:00
|
|
|
mm = tsk->mm;
|
2011-12-27 10:27:18 +00:00
|
|
|
trans_exc_code = regs->int_parm_long;
|
2021-07-28 19:02:53 +00:00
|
|
|
address = trans_exc_code & __FAIL_ADDR_MASK;
|
|
|
|
|
is_write = (trans_exc_code & store_indication) == 0x400;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Verify that the fault happened in user space, that
|
|
|
|
|
* we are not in an interrupt and that there is a
|
|
|
|
|
* user context.
|
|
|
|
|
*/
|
2009-12-07 11:51:45 +00:00
|
|
|
fault = VM_FAULT_BADCONTEXT;
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
type = get_fault_type(regs);
|
|
|
|
|
switch (type) {
|
|
|
|
|
case KERNEL_FAULT:
|
2021-07-28 19:02:53 +00:00
|
|
|
if (kfence_handle_page_fault(address, is_write, regs))
|
|
|
|
|
return 0;
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
goto out;
|
|
|
|
|
case USER_FAULT:
|
|
|
|
|
case GMAP_FAULT:
|
|
|
|
|
if (faulthandler_disabled() || !mm)
|
|
|
|
|
goto out;
|
|
|
|
|
break;
|
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2011-06-27 12:41:57 +00:00
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
2020-04-02 04:08:37 +00:00
|
|
|
flags = FAULT_FLAG_DEFAULT;
|
2013-09-12 22:13:39 +00:00
|
|
|
if (user_mode(regs))
|
|
|
|
|
flags |= FAULT_FLAG_USER;
|
2022-08-17 13:26:03 +00:00
|
|
|
if (is_write)
|
|
|
|
|
access = VM_WRITE;
|
|
|
|
|
if (access == VM_WRITE)
|
2011-05-26 07:48:30 +00:00
|
|
|
flags |= FAULT_FLAG_WRITE;
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_lock(mm);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
gmap = NULL;
|
|
|
|
|
if (IS_ENABLED(CONFIG_PGSTE) && type == GMAP_FAULT) {
|
|
|
|
|
gmap = (struct gmap *) S390_lowcore.gmap;
|
2014-04-30 14:04:25 +00:00
|
|
|
current->thread.gmap_addr = address;
|
2016-03-08 11:12:18 +00:00
|
|
|
current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE);
|
2016-03-08 11:31:52 +00:00
|
|
|
current->thread.gmap_int_code = regs->int_code & 0xffff;
|
2014-04-30 14:04:25 +00:00
|
|
|
address = __gmap_translate(gmap, address);
|
2011-07-24 08:48:20 +00:00
|
|
|
if (address == -EFAULT) {
|
|
|
|
|
fault = VM_FAULT_BADMAP;
|
|
|
|
|
goto out_up;
|
|
|
|
|
}
|
2013-06-17 14:25:18 +00:00
|
|
|
if (gmap->pfault_enabled)
|
|
|
|
|
flags |= FAULT_FLAG_RETRY_NOWAIT;
|
2011-07-24 08:48:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
retry:
|
2009-12-07 11:51:45 +00:00
|
|
|
fault = VM_FAULT_BADMAP;
|
2007-03-05 22:35:54 +00:00
|
|
|
vma = find_vma(mm, address);
|
|
|
|
|
if (!vma)
|
2009-12-07 11:51:45 +00:00
|
|
|
goto out_up;
|
2007-02-05 20:18:17 +00:00
|
|
|
|
2009-12-07 11:51:45 +00:00
|
|
|
if (unlikely(vma->vm_start > address)) {
|
|
|
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
|
|
|
goto out_up;
|
|
|
|
|
if (expand_stack(vma, address))
|
|
|
|
|
goto out_up;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
|
|
|
* we can handle it..
|
|
|
|
|
*/
|
|
|
|
|
fault = VM_FAULT_BADACCESS;
|
2009-12-07 11:51:46 +00:00
|
|
|
if (unlikely(!(vma->vm_flags & access)))
|
2009-12-07 11:51:45 +00:00
|
|
|
goto out_up;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If for any reason at all we couldn't handle the fault,
|
|
|
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
|
|
|
* the fault.
|
|
|
|
|
*/
|
2020-08-12 01:38:37 +00:00
|
|
|
fault = handle_mm_fault(vma, address, flags, regs);
|
2020-04-02 04:08:06 +00:00
|
|
|
if (fault_signal_pending(fault, regs)) {
|
2012-07-27 06:54:20 +00:00
|
|
|
fault = VM_FAULT_SIGNAL;
|
2018-07-16 08:38:57 +00:00
|
|
|
if (flags & FAULT_FLAG_RETRY_NOWAIT)
|
|
|
|
|
goto out_up;
|
2012-07-27 06:54:20 +00:00
|
|
|
goto out;
|
|
|
|
|
}
|
mm: avoid unnecessary page fault retires on shared memory types
I observed that for each of the shared file-backed page faults, we're very
likely to retry one more time for the 1st write fault upon no page. It's
because we'll need to release the mmap lock for dirty rate limit purpose
with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()).
Then after that throttling we return VM_FAULT_RETRY.
We did that probably because VM_FAULT_RETRY is the only way we can return
to the fault handler at that time telling it we've released the mmap lock.
However that's not ideal because it's very likely the fault does not need
to be retried at all since the pgtable was well installed before the
throttling, so the next continuous fault (including taking mmap read lock,
walk the pgtable, etc.) could be in most cases unnecessary.
It's not only slowing down page faults for shared file-backed, but also add
more mmap lock contention which is in most cases not needed at all.
To observe this, one could try to write to some shmem page and look at
"pgfault" value in /proc/vmstat, then we should expect 2 counts for each
shmem write simply because we retried, and vm event "pgfault" will capture
that.
To make it more efficient, add a new VM_FAULT_COMPLETED return code just to
show that we've completed the whole fault and released the lock. It's also
a hint that we should very possibly not need another fault immediately on
this page because we've just completed it.
This patch provides a ~12% perf boost on my aarch64 test VM with a simple
program sequentially dirtying 400MB shmem file being mmap()ed and these are
the time it needs:
Before: 650.980 ms (+-1.94%)
After: 569.396 ms (+-1.38%)
I believe it could help more than that.
We need some special care on GUP and the s390 pgfault handler (for gmap
code before returning from pgfault), the rest changes in the page fault
handlers should be relatively straightforward.
Another thing to mention is that mm_account_fault() does take this new
fault as a generic fault to be accounted, unlike VM_FAULT_RETRY.
I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do
not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping
them as-is.
Link: https://lkml.kernel.org/r/20220530183450.42886-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vineet Gupta <vgupta@kernel.org>
Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> [arm part]
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Brian Cain <bcain@quicinc.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Richard Weinberger <richard@nod.at>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Will Deacon <will@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Chris Zankel <chris@zankel.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Rich Felker <dalias@libc.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Helge Deller <deller@gmx.de>
Cc: Yoshinori Sato <ysato@users.osdn.me>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-30 18:34:50 +00:00
|
|
|
|
|
|
|
|
/* The fault is fully completed (including releasing mmap lock) */
|
|
|
|
|
if (fault & VM_FAULT_COMPLETED) {
|
|
|
|
|
if (gmap) {
|
|
|
|
|
mmap_read_lock(mm);
|
|
|
|
|
goto out_gmap;
|
|
|
|
|
}
|
|
|
|
|
fault = 0;
|
|
|
|
|
goto out;
|
|
|
|
|
}
|
|
|
|
|
|
2009-12-07 11:51:45 +00:00
|
|
|
if (unlikely(fault & VM_FAULT_ERROR))
|
|
|
|
|
goto out_up;
|
|
|
|
|
|
2022-01-14 22:05:51 +00:00
|
|
|
if (fault & VM_FAULT_RETRY) {
|
|
|
|
|
if (IS_ENABLED(CONFIG_PGSTE) && gmap &&
|
|
|
|
|
(flags & FAULT_FLAG_RETRY_NOWAIT)) {
|
|
|
|
|
/*
|
|
|
|
|
* FAULT_FLAG_RETRY_NOWAIT has been set, mmap_lock has
|
|
|
|
|
* not been released
|
|
|
|
|
*/
|
|
|
|
|
current->thread.gmap_pfault = 1;
|
|
|
|
|
fault = VM_FAULT_PFAULT;
|
|
|
|
|
goto out_up;
|
2011-05-26 07:48:30 +00:00
|
|
|
}
|
2022-01-14 22:05:51 +00:00
|
|
|
flags &= ~FAULT_FLAG_RETRY_NOWAIT;
|
|
|
|
|
flags |= FAULT_FLAG_TRIED;
|
|
|
|
|
mmap_read_lock(mm);
|
|
|
|
|
goto retry;
|
2009-09-11 08:29:06 +00:00
|
|
|
}
|
mm: avoid unnecessary page fault retires on shared memory types
I observed that for each of the shared file-backed page faults, we're very
likely to retry one more time for the 1st write fault upon no page. It's
because we'll need to release the mmap lock for dirty rate limit purpose
with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()).
Then after that throttling we return VM_FAULT_RETRY.
We did that probably because VM_FAULT_RETRY is the only way we can return
to the fault handler at that time telling it we've released the mmap lock.
However that's not ideal because it's very likely the fault does not need
to be retried at all since the pgtable was well installed before the
throttling, so the next continuous fault (including taking mmap read lock,
walk the pgtable, etc.) could be in most cases unnecessary.
It's not only slowing down page faults for shared file-backed, but also add
more mmap lock contention which is in most cases not needed at all.
To observe this, one could try to write to some shmem page and look at
"pgfault" value in /proc/vmstat, then we should expect 2 counts for each
shmem write simply because we retried, and vm event "pgfault" will capture
that.
To make it more efficient, add a new VM_FAULT_COMPLETED return code just to
show that we've completed the whole fault and released the lock. It's also
a hint that we should very possibly not need another fault immediately on
this page because we've just completed it.
This patch provides a ~12% perf boost on my aarch64 test VM with a simple
program sequentially dirtying 400MB shmem file being mmap()ed and these are
the time it needs:
Before: 650.980 ms (+-1.94%)
After: 569.396 ms (+-1.38%)
I believe it could help more than that.
We need some special care on GUP and the s390 pgfault handler (for gmap
code before returning from pgfault), the rest changes in the page fault
handlers should be relatively straightforward.
Another thing to mention is that mm_account_fault() does take this new
fault as a generic fault to be accounted, unlike VM_FAULT_RETRY.
I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do
not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping
them as-is.
Link: https://lkml.kernel.org/r/20220530183450.42886-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vineet Gupta <vgupta@kernel.org>
Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> [arm part]
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Brian Cain <bcain@quicinc.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Richard Weinberger <richard@nod.at>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Will Deacon <will@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Chris Zankel <chris@zankel.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Rich Felker <dalias@libc.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Helge Deller <deller@gmx.de>
Cc: Yoshinori Sato <ysato@users.osdn.me>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-30 18:34:50 +00:00
|
|
|
out_gmap:
|
s390: remove all code using the access register mode
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.
An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.
Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.
The different cases:
* User copy with MVCOS for z10 and newer machines
The MVCOS instruction can copy between the primary space (aka user) and
the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
loaded in %cr1.
* User copy with MVCP/MVCS for older machines
To be able to execute the MVCP/MVCS instructions the kernel needs to
switch to primary mode. The control register %cr1 has to be set to the
kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
on set_fs(KERNEL_DS) vs set_fs(USER_DS).
* Data access in the user address space for strnlen / futex
To use "normal" instruction with data from the user address space the
secondary space mode is used. The kernel needs to switch to primary mode,
%cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
kernel ASCE, dependent on set_fs.
To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.
To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.
For CPUs with MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode, lazy | user | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
For CPUs without MVCOS:
CPU running in | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space | user | vdso |
kernel, USER_DS, normal-mode | user | vdso |
kernel, USER_DS, normal-mode lazy | kernel | user |
kernel, USER_DS, sacf-mode | kernel | user |
kernel, KERNEL_DS, normal-mode | kernel | vdso |
kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel |
kernel, KERNEL_DS, sacf-mode | kernel | kernel |
The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.
There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.
Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:
1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
with secondary space mode with set_fs(USER_DS) on machines without
MVCOS.
8) kernel address space fault via the home space ASCE
Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.
With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 10:08:22 +00:00
|
|
|
if (IS_ENABLED(CONFIG_PGSTE) && gmap) {
|
2014-04-30 14:04:25 +00:00
|
|
|
address = __gmap_link(gmap, current->thread.gmap_addr,
|
|
|
|
|
address);
|
|
|
|
|
if (address == -EFAULT) {
|
|
|
|
|
fault = VM_FAULT_BADMAP;
|
|
|
|
|
goto out_up;
|
|
|
|
|
}
|
|
|
|
|
if (address == -ENOMEM) {
|
|
|
|
|
fault = VM_FAULT_OOM;
|
|
|
|
|
goto out_up;
|
|
|
|
|
}
|
|
|
|
|
}
|
2009-12-07 11:51:45 +00:00
|
|
|
fault = 0;
|
|
|
|
|
out_up:
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2009-12-07 11:51:45 +00:00
|
|
|
out:
|
|
|
|
|
return fault;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
2014-10-22 10:42:38 +00:00
|
|
|
void do_protection_exception(struct pt_regs *regs)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2011-12-27 10:27:18 +00:00
|
|
|
unsigned long trans_exc_code;
|
2018-08-17 22:44:47 +00:00
|
|
|
int access;
|
|
|
|
|
vm_fault_t fault;
|
2009-12-07 11:51:42 +00:00
|
|
|
|
2011-12-27 10:27:18 +00:00
|
|
|
trans_exc_code = regs->int_parm_long;
|
2013-04-16 11:25:06 +00:00
|
|
|
/*
|
|
|
|
|
* Protection exceptions are suppressing, decrement psw address.
|
|
|
|
|
* The exception to this rule are aborted transactions, for these
|
|
|
|
|
* the PSW already points to the correct location.
|
|
|
|
|
*/
|
|
|
|
|
if (!(regs->int_code & 0x200))
|
|
|
|
|
regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
|
2007-04-27 14:01:43 +00:00
|
|
|
/*
|
|
|
|
|
* Check for low-address protection. This needs to be treated
|
|
|
|
|
* as a special case because the translation exception code
|
|
|
|
|
* field is not guaranteed to contain valid data in this case.
|
|
|
|
|
*/
|
2009-12-07 11:51:42 +00:00
|
|
|
if (unlikely(!(trans_exc_code & 4))) {
|
2011-12-27 10:27:18 +00:00
|
|
|
do_low_address(regs);
|
2007-04-27 14:01:43 +00:00
|
|
|
return;
|
|
|
|
|
}
|
2016-03-22 09:54:24 +00:00
|
|
|
if (unlikely(MACHINE_HAS_NX && (trans_exc_code & 0x80))) {
|
|
|
|
|
regs->int_parm_long = (trans_exc_code & ~PAGE_MASK) |
|
|
|
|
|
(regs->psw.addr & PAGE_MASK);
|
|
|
|
|
access = VM_EXEC;
|
|
|
|
|
fault = VM_FAULT_BADACCESS;
|
|
|
|
|
} else {
|
|
|
|
|
access = VM_WRITE;
|
|
|
|
|
fault = do_exception(regs, access);
|
|
|
|
|
}
|
2009-12-07 11:51:45 +00:00
|
|
|
if (unlikely(fault))
|
2022-08-29 12:26:56 +00:00
|
|
|
do_fault_error(regs, fault);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2014-10-22 10:42:38 +00:00
|
|
|
NOKPROBE_SYMBOL(do_protection_exception);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2014-10-22 10:42:38 +00:00
|
|
|
void do_dat_exception(struct pt_regs *regs)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2018-08-17 22:44:47 +00:00
|
|
|
int access;
|
|
|
|
|
vm_fault_t fault;
|
2009-12-07 11:51:45 +00:00
|
|
|
|
2020-04-10 21:33:09 +00:00
|
|
|
access = VM_ACCESS_FLAGS;
|
2011-12-27 10:27:18 +00:00
|
|
|
fault = do_exception(regs, access);
|
2009-12-07 11:51:45 +00:00
|
|
|
if (unlikely(fault))
|
2022-08-29 12:26:56 +00:00
|
|
|
do_fault_error(regs, fault);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2014-10-22 10:42:38 +00:00
|
|
|
NOKPROBE_SYMBOL(do_dat_exception);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_PFAULT
|
|
|
|
|
/*
|
|
|
|
|
* 'pfault' pseudo page faults routines.
|
|
|
|
|
*/
|
2011-01-05 11:47:39 +00:00
|
|
|
static int pfault_disable;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
static int __init nopfault(char *str)
|
|
|
|
|
{
|
|
|
|
|
pfault_disable = 1;
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
__setup("nopfault", nopfault);
|
|
|
|
|
|
2011-05-23 08:24:35 +00:00
|
|
|
struct pfault_refbk {
|
|
|
|
|
u16 refdiagc;
|
|
|
|
|
u16 reffcode;
|
|
|
|
|
u16 refdwlen;
|
|
|
|
|
u16 refversn;
|
|
|
|
|
u64 refgaddr;
|
|
|
|
|
u64 refselmk;
|
|
|
|
|
u64 refcmpmk;
|
|
|
|
|
u64 reserved;
|
|
|
|
|
} __attribute__ ((packed, aligned(8)));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2018-09-07 09:20:08 +00:00
|
|
|
static struct pfault_refbk pfault_init_refbk = {
|
|
|
|
|
.refdiagc = 0x258,
|
|
|
|
|
.reffcode = 0,
|
|
|
|
|
.refdwlen = 5,
|
|
|
|
|
.refversn = 2,
|
|
|
|
|
.refgaddr = __LC_LPP,
|
|
|
|
|
.refselmk = 1ULL << 48,
|
|
|
|
|
.refcmpmk = 1ULL << 48,
|
|
|
|
|
.reserved = __PF_RES_FIELD
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
int pfault_init(void)
|
|
|
|
|
{
|
|
|
|
|
int rc;
|
|
|
|
|
|
2011-12-27 10:27:11 +00:00
|
|
|
if (pfault_disable)
|
2005-04-16 22:20:36 +00:00
|
|
|
return -1;
|
2015-08-20 15:28:44 +00:00
|
|
|
diag_stat_inc(DIAG_STAT_X258);
|
2006-09-28 14:56:43 +00:00
|
|
|
asm volatile(
|
|
|
|
|
" diag %1,%0,0x258\n"
|
|
|
|
|
"0: j 2f\n"
|
|
|
|
|
"1: la %0,8\n"
|
2005-04-16 22:20:36 +00:00
|
|
|
"2:\n"
|
2006-09-28 14:56:43 +00:00
|
|
|
EX_TABLE(0b,1b)
|
2018-09-07 09:20:08 +00:00
|
|
|
: "=d" (rc)
|
|
|
|
|
: "a" (&pfault_init_refbk), "m" (pfault_init_refbk) : "cc");
|
2005-04-16 22:20:36 +00:00
|
|
|
return rc;
|
|
|
|
|
}
|
|
|
|
|
|
2018-09-07 09:20:08 +00:00
|
|
|
static struct pfault_refbk pfault_fini_refbk = {
|
|
|
|
|
.refdiagc = 0x258,
|
|
|
|
|
.reffcode = 1,
|
|
|
|
|
.refdwlen = 5,
|
|
|
|
|
.refversn = 2,
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
void pfault_fini(void)
|
|
|
|
|
{
|
|
|
|
|
|
2011-12-27 10:27:11 +00:00
|
|
|
if (pfault_disable)
|
2005-04-16 22:20:36 +00:00
|
|
|
return;
|
2015-08-20 15:28:44 +00:00
|
|
|
diag_stat_inc(DIAG_STAT_X258);
|
2006-09-28 14:56:43 +00:00
|
|
|
asm volatile(
|
|
|
|
|
" diag %0,0,0x258\n"
|
2016-06-10 07:57:05 +00:00
|
|
|
"0: nopr %%r7\n"
|
2006-09-28 14:56:43 +00:00
|
|
|
EX_TABLE(0b,0b)
|
2018-09-07 09:20:08 +00:00
|
|
|
: : "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) : "cc");
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
2011-05-23 08:24:34 +00:00
|
|
|
static DEFINE_SPINLOCK(pfault_lock);
|
|
|
|
|
static LIST_HEAD(pfault_list);
|
|
|
|
|
|
2016-03-22 20:42:53 +00:00
|
|
|
#define PF_COMPLETE 0x0080
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The mechanism of our pfault code: if Linux is running as guest, runs a user
|
|
|
|
|
* space process and the user space process accesses a page that the host has
|
|
|
|
|
* paged out we get a pfault interrupt.
|
|
|
|
|
*
|
|
|
|
|
* This allows us, within the guest, to schedule a different process. Without
|
|
|
|
|
* this mechanism the host would have to suspend the whole virtual cpu until
|
|
|
|
|
* the page has been paged in.
|
|
|
|
|
*
|
|
|
|
|
* So when we get such an interrupt then we set the state of the current task
|
|
|
|
|
* to uninterruptible and also set the need_resched flag. Both happens within
|
|
|
|
|
* interrupt context(!). If we later on want to return to user space we
|
|
|
|
|
* recognize the need_resched flag and then call schedule(). It's not very
|
|
|
|
|
* obvious how this works...
|
|
|
|
|
*
|
|
|
|
|
* Of course we have a lot of additional fun with the completion interrupt (->
|
|
|
|
|
* host signals that a page of a process has been paged in and the process can
|
|
|
|
|
* continue to run). This interrupt can arrive on any cpu and, since we have
|
|
|
|
|
* virtual cpus, actually appear before the interrupt that signals that a page
|
|
|
|
|
* is missing.
|
|
|
|
|
*/
|
2012-03-11 15:59:31 +00:00
|
|
|
static void pfault_interrupt(struct ext_code ext_code,
|
2010-10-25 14:10:38 +00:00
|
|
|
unsigned int param32, unsigned long param64)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
|
struct task_struct *tsk;
|
|
|
|
|
__u16 subcode;
|
2011-05-23 08:24:34 +00:00
|
|
|
pid_t pid;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
/*
|
2016-03-22 20:42:53 +00:00
|
|
|
* Get the external interruption subcode & pfault initial/completion
|
|
|
|
|
* signal bit. VM stores this in the 'cpu address' field associated
|
|
|
|
|
* with the external interrupt.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2012-03-11 15:59:31 +00:00
|
|
|
subcode = ext_code.subcode;
|
2005-04-16 22:20:36 +00:00
|
|
|
if ((subcode & 0xff00) != __SUBCODE_MASK)
|
|
|
|
|
return;
|
2013-01-02 14:18:18 +00:00
|
|
|
inc_irq_stat(IRQEXT_PFL);
|
2012-05-10 07:44:35 +00:00
|
|
|
/* Get the token (= pid of the affected task). */
|
2016-03-08 13:00:23 +00:00
|
|
|
pid = param64 & LPP_PID_MASK;
|
2012-05-10 07:44:35 +00:00
|
|
|
rcu_read_lock();
|
|
|
|
|
tsk = find_task_by_pid_ns(pid, &init_pid_ns);
|
|
|
|
|
if (tsk)
|
|
|
|
|
get_task_struct(tsk);
|
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
if (!tsk)
|
|
|
|
|
return;
|
2011-05-23 08:24:34 +00:00
|
|
|
spin_lock(&pfault_lock);
|
2016-03-22 20:42:53 +00:00
|
|
|
if (subcode & PF_COMPLETE) {
|
2005-04-16 22:20:36 +00:00
|
|
|
/* signal bit is set -> a page has been swapped in by VM */
|
2011-05-23 08:24:34 +00:00
|
|
|
if (tsk->thread.pfault_wait == 1) {
|
2005-04-16 22:20:36 +00:00
|
|
|
/* Initial interrupt was faster than the completion
|
|
|
|
|
* interrupt. pfault_wait is valid. Set pfault_wait
|
|
|
|
|
* back to zero and wake up the process. This can
|
|
|
|
|
* safely be done because the task is still sleeping
|
2005-09-03 22:58:02 +00:00
|
|
|
* and can't produce new pfaults. */
|
2005-04-16 22:20:36 +00:00
|
|
|
tsk->thread.pfault_wait = 0;
|
2011-05-23 08:24:34 +00:00
|
|
|
list_del(&tsk->thread.list);
|
2005-04-16 22:20:36 +00:00
|
|
|
wake_up_process(tsk);
|
2012-05-09 07:37:30 +00:00
|
|
|
put_task_struct(tsk);
|
2011-05-23 08:24:34 +00:00
|
|
|
} else {
|
|
|
|
|
/* Completion interrupt was faster than initial
|
|
|
|
|
* interrupt. Set pfault_wait to -1 so the initial
|
2011-11-14 10:19:01 +00:00
|
|
|
* interrupt doesn't put the task to sleep.
|
|
|
|
|
* If the task is not running, ignore the completion
|
|
|
|
|
* interrupt since it must be a leftover of a PFAULT
|
|
|
|
|
* CANCEL operation which didn't remove all pending
|
|
|
|
|
* completion interrupts. */
|
2021-06-11 08:28:12 +00:00
|
|
|
if (task_is_running(tsk))
|
2011-11-14 10:19:01 +00:00
|
|
|
tsk->thread.pfault_wait = -1;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
} else {
|
|
|
|
|
/* signal bit not set -> a real page is missing. */
|
2012-05-10 08:47:21 +00:00
|
|
|
if (WARN_ON_ONCE(tsk != current))
|
|
|
|
|
goto out;
|
2012-05-09 07:37:30 +00:00
|
|
|
if (tsk->thread.pfault_wait == 1) {
|
|
|
|
|
/* Already on the list with a reference: put to sleep */
|
2016-03-22 20:42:53 +00:00
|
|
|
goto block;
|
2012-05-09 07:37:30 +00:00
|
|
|
} else if (tsk->thread.pfault_wait == -1) {
|
2005-04-16 22:20:36 +00:00
|
|
|
/* Completion interrupt was faster than the initial
|
2011-05-23 08:24:34 +00:00
|
|
|
* interrupt (pfault_wait == -1). Set pfault_wait
|
|
|
|
|
* back to zero and exit. */
|
2005-04-16 22:20:36 +00:00
|
|
|
tsk->thread.pfault_wait = 0;
|
2011-05-23 08:24:34 +00:00
|
|
|
} else {
|
|
|
|
|
/* Initial interrupt arrived before completion
|
2012-05-09 07:37:30 +00:00
|
|
|
* interrupt. Let the task sleep.
|
|
|
|
|
* An extra task reference is needed since a different
|
|
|
|
|
* cpu may set the task state to TASK_RUNNING again
|
|
|
|
|
* before the scheduler is reached. */
|
|
|
|
|
get_task_struct(tsk);
|
2011-05-23 08:24:34 +00:00
|
|
|
tsk->thread.pfault_wait = 1;
|
|
|
|
|
list_add(&tsk->thread.list, &pfault_list);
|
2016-03-22 20:42:53 +00:00
|
|
|
block:
|
|
|
|
|
/* Since this must be a userspace fault, there
|
|
|
|
|
* is no kernel task state to trample. Rely on the
|
|
|
|
|
* return to userspace schedule() to block. */
|
|
|
|
|
__set_current_state(TASK_UNINTERRUPTIBLE);
|
2005-04-16 22:20:36 +00:00
|
|
|
set_tsk_need_resched(tsk);
|
2016-10-25 10:21:44 +00:00
|
|
|
set_preempt_need_resched();
|
2011-05-23 08:24:34 +00:00
|
|
|
}
|
|
|
|
|
}
|
2012-05-10 08:47:21 +00:00
|
|
|
out:
|
2011-05-23 08:24:34 +00:00
|
|
|
spin_unlock(&pfault_lock);
|
2012-05-10 07:44:35 +00:00
|
|
|
put_task_struct(tsk);
|
2011-05-23 08:24:34 +00:00
|
|
|
}
|
|
|
|
|
|
2016-09-06 17:04:53 +00:00
|
|
|
static int pfault_cpu_dead(unsigned int cpu)
|
2011-05-23 08:24:34 +00:00
|
|
|
{
|
|
|
|
|
struct thread_struct *thread, *next;
|
|
|
|
|
struct task_struct *tsk;
|
|
|
|
|
|
2016-09-06 17:04:53 +00:00
|
|
|
spin_lock_irq(&pfault_lock);
|
|
|
|
|
list_for_each_entry_safe(thread, next, &pfault_list, list) {
|
|
|
|
|
thread->pfault_wait = 0;
|
|
|
|
|
list_del(&thread->list);
|
|
|
|
|
tsk = container_of(thread, struct task_struct, thread);
|
|
|
|
|
wake_up_process(tsk);
|
|
|
|
|
put_task_struct(tsk);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2016-09-06 17:04:53 +00:00
|
|
|
spin_unlock_irq(&pfault_lock);
|
|
|
|
|
return 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
2011-01-05 11:47:39 +00:00
|
|
|
static int __init pfault_irq_init(void)
|
2006-12-04 14:40:40 +00:00
|
|
|
{
|
2011-01-05 11:47:39 +00:00
|
|
|
int rc;
|
2006-12-04 14:40:40 +00:00
|
|
|
|
2014-03-31 13:24:08 +00:00
|
|
|
rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
|
2011-05-23 08:24:35 +00:00
|
|
|
if (rc)
|
|
|
|
|
goto out_extint;
|
|
|
|
|
rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
|
|
|
|
|
if (rc)
|
|
|
|
|
goto out_pfault;
|
2013-09-04 11:35:45 +00:00
|
|
|
irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
|
2016-09-06 17:04:53 +00:00
|
|
|
cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead",
|
|
|
|
|
NULL, pfault_cpu_dead);
|
2011-05-23 08:24:35 +00:00
|
|
|
return 0;
|
2006-12-04 14:40:40 +00:00
|
|
|
|
2011-05-23 08:24:35 +00:00
|
|
|
out_pfault:
|
2014-03-31 13:24:08 +00:00
|
|
|
unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
|
2011-05-23 08:24:35 +00:00
|
|
|
out_extint:
|
|
|
|
|
pfault_disable = 1;
|
|
|
|
|
return rc;
|
2006-12-04 14:40:40 +00:00
|
|
|
}
|
2011-01-05 11:47:39 +00:00
|
|
|
early_initcall(pfault_irq_init);
|
|
|
|
|
|
2011-05-23 08:24:35 +00:00
|
|
|
#endif /* CONFIG_PFAULT */
|
2020-01-21 08:43:10 +00:00
|
|
|
|
|
|
|
|
#if IS_ENABLED(CONFIG_PGSTE)
|
2021-04-09 08:34:43 +00:00
|
|
|
|
2020-01-21 08:43:10 +00:00
|
|
|
void do_secure_storage_access(struct pt_regs *regs)
|
|
|
|
|
{
|
|
|
|
|
unsigned long addr = regs->int_parm_long & __FAIL_ADDR_MASK;
|
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
|
struct mm_struct *mm;
|
|
|
|
|
struct page *page;
|
2022-06-28 13:56:04 +00:00
|
|
|
struct gmap *gmap;
|
2020-01-21 08:43:10 +00:00
|
|
|
int rc;
|
|
|
|
|
|
2021-01-12 10:40:53 +00:00
|
|
|
/*
|
|
|
|
|
* bit 61 tells us if the address is valid, if it's not we
|
|
|
|
|
* have a major problem and should stop the kernel or send a
|
|
|
|
|
* SIGSEGV to the process. Unfortunately bit 61 is not
|
|
|
|
|
* reliable without the misc UV feature so we need to check
|
|
|
|
|
* for that as well.
|
|
|
|
|
*/
|
|
|
|
|
if (test_bit_inv(BIT_UV_FEAT_MISC, &uv_info.uv_feature_indications) &&
|
|
|
|
|
!test_bit_inv(61, ®s->int_parm_long)) {
|
|
|
|
|
/*
|
|
|
|
|
* When this happens, userspace did something that it
|
|
|
|
|
* was not supposed to do, e.g. branching into secure
|
|
|
|
|
* memory. Trigger a segmentation fault.
|
|
|
|
|
*/
|
|
|
|
|
if (user_mode(regs)) {
|
|
|
|
|
send_sig(SIGSEGV, current, 0);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The kernel should never run into this case and we
|
|
|
|
|
* have no way out of this situation.
|
|
|
|
|
*/
|
|
|
|
|
panic("Unexpected PGM 0x3d with TEID bit 61=0");
|
|
|
|
|
}
|
|
|
|
|
|
2020-01-21 08:43:10 +00:00
|
|
|
switch (get_fault_type(regs)) {
|
2022-06-28 13:56:04 +00:00
|
|
|
case GMAP_FAULT:
|
|
|
|
|
mm = current->mm;
|
|
|
|
|
gmap = (struct gmap *)S390_lowcore.gmap;
|
|
|
|
|
mmap_read_lock(mm);
|
|
|
|
|
addr = __gmap_translate(gmap, addr);
|
|
|
|
|
mmap_read_unlock(mm);
|
|
|
|
|
if (IS_ERR_VALUE(addr)) {
|
2022-08-29 12:26:56 +00:00
|
|
|
do_fault_error(regs, VM_FAULT_BADMAP);
|
2022-06-28 13:56:04 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
fallthrough;
|
2020-01-21 08:43:10 +00:00
|
|
|
case USER_FAULT:
|
|
|
|
|
mm = current->mm;
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_lock(mm);
|
2020-01-21 08:43:10 +00:00
|
|
|
vma = find_vma(mm, addr);
|
|
|
|
|
if (!vma) {
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2022-08-29 12:26:56 +00:00
|
|
|
do_fault_error(regs, VM_FAULT_BADMAP);
|
2020-01-21 08:43:10 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET);
|
|
|
|
|
if (IS_ERR_OR_NULL(page)) {
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2020-01-21 08:43:10 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
if (arch_make_page_accessible(page))
|
|
|
|
|
send_sig(SIGSEGV, current, 0);
|
|
|
|
|
put_page(page);
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2020-01-21 08:43:10 +00:00
|
|
|
break;
|
|
|
|
|
case KERNEL_FAULT:
|
|
|
|
|
page = phys_to_page(addr);
|
Revert "mm/gup: remove try_get_page(), call try_get_compound_head() directly"
This reverts commit 9857a17f206ff374aea78bccfb687f145368be2e.
That commit was completely broken, and I should have caught on to it
earlier. But happily, the kernel test robot noticed the breakage fairly
quickly.
The breakage is because "try_get_page()" is about avoiding the page
reference count overflow case, but is otherwise the exact same as a
plain "get_page()".
In contrast, "try_get_compound_head()" is an entirely different beast,
and uses __page_cache_add_speculative() because it's not just about the
page reference count, but also about possibly racing with the underlying
page going away.
So all the commentary about how
"try_get_page() has fallen a little behind in terms of maintenance,
try_get_compound_head() handles speculative page references more
thoroughly"
was just completely wrong: yes, try_get_compound_head() handles
speculative page references, but the point is that try_get_page() does
not, and must not.
So there's no lack of maintainance - there are fundamentally different
semantics.
A speculative page reference would be entirely wrong in "get_page()",
and it's entirely wrong in "try_get_page()". It's not about
speculation, it's purely about "uhhuh, you can't get this page because
you've tried to increment the reference count too much already".
The reason the kernel test robot noticed this bug was that it hit the
VM_BUG_ON() in __page_cache_add_speculative(), which is all about
verifying that the context of any speculative page access is correct.
But since that isn't what try_get_page() is all about, the VM_BUG_ON()
tests things that are not correct to test for try_get_page().
Reported-by: kernel test robot <oliver.sang@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-07 18:03:45 +00:00
|
|
|
if (unlikely(!try_get_page(page)))
|
2020-01-21 08:43:10 +00:00
|
|
|
break;
|
|
|
|
|
rc = arch_make_page_accessible(page);
|
|
|
|
|
put_page(page);
|
|
|
|
|
if (rc)
|
|
|
|
|
BUG();
|
|
|
|
|
break;
|
|
|
|
|
default:
|
2022-08-29 12:26:56 +00:00
|
|
|
do_fault_error(regs, VM_FAULT_BADMAP);
|
2020-01-21 08:43:10 +00:00
|
|
|
WARN_ON_ONCE(1);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
NOKPROBE_SYMBOL(do_secure_storage_access);
|
|
|
|
|
|
|
|
|
|
void do_non_secure_storage_access(struct pt_regs *regs)
|
|
|
|
|
{
|
|
|
|
|
unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK;
|
|
|
|
|
struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
|
|
|
|
|
|
|
|
|
|
if (get_fault_type(regs) != GMAP_FAULT) {
|
2022-08-29 12:26:56 +00:00
|
|
|
do_fault_error(regs, VM_FAULT_BADMAP);
|
2020-01-21 08:43:10 +00:00
|
|
|
WARN_ON_ONCE(1);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (gmap_convert_to_secure(gmap, gaddr) == -EINVAL)
|
|
|
|
|
send_sig(SIGSEGV, current, 0);
|
|
|
|
|
}
|
|
|
|
|
NOKPROBE_SYMBOL(do_non_secure_storage_access);
|
|
|
|
|
|
2020-09-08 13:05:04 +00:00
|
|
|
void do_secure_storage_violation(struct pt_regs *regs)
|
|
|
|
|
{
|
2022-06-28 13:56:03 +00:00
|
|
|
unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK;
|
|
|
|
|
struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If the VM has been rebooted, its address space might still contain
|
|
|
|
|
* secure pages from the previous boot.
|
|
|
|
|
* Clear the page so it can be reused.
|
|
|
|
|
*/
|
|
|
|
|
if (!gmap_destroy_page(gmap, gaddr))
|
|
|
|
|
return;
|
2020-09-08 13:05:04 +00:00
|
|
|
/*
|
|
|
|
|
* Either KVM messed up the secure guest mapping or the same
|
|
|
|
|
* page is mapped into multiple secure guests.
|
|
|
|
|
*
|
|
|
|
|
* This exception is only triggered when a guest 2 is running
|
|
|
|
|
* and can therefore never occur in kernel context.
|
|
|
|
|
*/
|
|
|
|
|
printk_ratelimited(KERN_WARNING
|
|
|
|
|
"Secure storage violation in task: %s, pid %d\n",
|
|
|
|
|
current->comm, current->pid);
|
|
|
|
|
send_sig(SIGSEGV, current, 0);
|
|
|
|
|
}
|
|
|
|
|
|
2021-04-09 08:34:43 +00:00
|
|
|
#endif /* CONFIG_PGSTE */
|
