2007-10-24 04:37:24 +08:00
|
|
|
/* Generic MTRR (Memory Type Range Register) ioctls.
|
|
|
|
|
|
|
|
Copyright (C) 1997-1999 Richard Gooch
|
|
|
|
|
|
|
|
This library is free software; you can redistribute it and/or
|
|
|
|
modify it under the terms of the GNU Library General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
This library is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
Library General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Library General Public
|
|
|
|
License along with this library; if not, write to the Free
|
|
|
|
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
|
|
|
|
|
|
Richard Gooch may be reached by email at rgooch@atnf.csiro.au
|
|
|
|
The postal address is:
|
|
|
|
Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
|
|
|
|
*/
|
2008-10-23 13:26:29 +08:00
|
|
|
#ifndef _ASM_X86_MTRR_H
|
|
|
|
#define _ASM_X86_MTRR_H
|
2007-10-24 04:37:24 +08:00
|
|
|
|
2012-12-15 06:37:13 +08:00
|
|
|
#include <uapi/asm/mtrr.h>
|
x86/mtrr: Fix Xorg crashes in Qemu sessions
A Xorg failure on qemu32 was reported as a regression [1] caused by
commit 9cd25aac1f44 ("x86/mm/pat: Emulate PAT when it is disabled").
This patch fixes the Xorg crash.
Negative effects of this regression were the following two failures [2]
in Xorg on QEMU with QEMU CPU model "qemu32" (-cpu qemu32), which were
triggered by the fact that its virtual CPU does not support MTRRs.
#1. copy_process() failed in the check in reserve_pfn_range()
copy_process
copy_mm
dup_mm
dup_mmap
copy_page_range
track_pfn_copy
reserve_pfn_range
A WC map request was tracked as WC in memtype, which set a PTE as
UC (pgprot) per __cachemode2pte_tbl[]. This led to this error in
reserve_pfn_range() called from track_pfn_copy(), which obtained
a pgprot from a PTE. It converts pgprot to page_cache_mode, which
does not necessarily result in the original page_cache_mode since
__cachemode2pte_tbl[] redirects multiple types to UC.
#2. error path in copy_process() then hit WARN_ON_ONCE in
untrack_pfn().
x86/PAT: Xorg:509 map pfn expected mapping type uncached-
minus for [mem 0xfd000000-0xfdffffff], got write-combining
Call Trace:
dump_stack
warn_slowpath_common
? untrack_pfn
? untrack_pfn
warn_slowpath_null
untrack_pfn
? __kunmap_atomic
unmap_single_vma
? pagevec_move_tail_fn
unmap_vmas
exit_mmap
mmput
copy_process.part.47
_do_fork
SyS_clone
do_syscall_32_irqs_on
entry_INT80_32
These negative effects are caused by two separate bugs, but they
can be addressed in separate patches. Fixing the pat_init() issue
described below addresses the root cause, and avoids Xorg to hit
these cases.
When the CPU does not support MTRRs, MTRR does not call pat_init(),
which leaves PAT enabled without initializing PAT. This pat_init()
issue is a long-standing issue, but manifested as issue #1 (and then
hit issue #2) with the above-mentioned commit because the memtype
now tracks cache attribute with 'page_cache_mode'.
This pat_init() issue existed before the commit, but we used pgprot
in memtype. Hence, we did not have issue #1 before. But WC request
resulted in WT in effect because WC pgrot is actually WT when PAT
is not initialized. This is not how it was designed to work. When
PAT is set to disable properly, WC is converted to UC. The use of
WT can result in a system crash if the target range does not support
WT. Fortunately, nobody ran into such issue before.
To fix this pat_init() issue, PAT code has been enhanced to provide
pat_disable() interface. Call this interface when MTRRs are disabled.
By setting PAT to disable properly, PAT bypasses the memtype check,
and avoids issue #1.
[1]: https://lkml.org/lkml/2016/3/3/828
[2]: https://lkml.org/lkml/2016/3/4/775
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: elliott@hpe.com
Cc: konrad.wilk@oracle.com
Cc: paul.gortmaker@windriver.com
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1458769323-24491-5-git-send-email-toshi.kani@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-24 05:42:00 +08:00
|
|
|
#include <asm/pat.h>
|
2007-10-24 04:37:24 +08:00
|
|
|
|
|
|
|
|
2013-05-14 07:58:40 +08:00
|
|
|
/*
|
|
|
|
* The following functions are for use by other drivers that cannot use
|
|
|
|
* arch_phys_wc_add and arch_phys_wc_del.
|
|
|
|
*/
|
2007-10-24 04:37:24 +08:00
|
|
|
# ifdef CONFIG_MTRR
|
2015-05-26 16:28:10 +08:00
|
|
|
extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
|
2007-10-24 04:37:24 +08:00
|
|
|
extern void mtrr_save_fixed_ranges(void *);
|
|
|
|
extern void mtrr_save_state(void);
|
2008-03-23 16:02:52 +08:00
|
|
|
extern int mtrr_add(unsigned long base, unsigned long size,
|
|
|
|
unsigned int type, bool increment);
|
|
|
|
extern int mtrr_add_page(unsigned long base, unsigned long size,
|
|
|
|
unsigned int type, bool increment);
|
|
|
|
extern int mtrr_del(int reg, unsigned long base, unsigned long size);
|
|
|
|
extern int mtrr_del_page(int reg, unsigned long base, unsigned long size);
|
2007-10-24 04:37:24 +08:00
|
|
|
extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
|
|
|
|
extern void mtrr_ap_init(void);
|
|
|
|
extern void mtrr_bp_init(void);
|
2009-08-20 09:05:36 +08:00
|
|
|
extern void set_mtrr_aps_delayed_init(void);
|
|
|
|
extern void mtrr_aps_init(void);
|
|
|
|
extern void mtrr_bp_restore(void);
|
x86, 32-bit: trim memory not covered by wb mtrrs
On some machines, buggy BIOSes don't properly setup WB MTRRs to cover all
available RAM, meaning the last few megs (or even gigs) of memory will be
marked uncached. Since Linux tends to allocate from high memory addresses
first, this causes the machine to be unusably slow as soon as the kernel
starts really using memory (i.e. right around init time).
This patch works around the problem by scanning the MTRRs at boot and
figuring out whether the current end_pfn value (setup by early e820 code)
goes beyond the highest WB MTRR range, and if so, trimming it to match. A
fairly obnoxious KERN_WARNING is printed too, letting the user know that
not all of their memory is available due to a likely BIOS bug.
Something similar could be done on i386 if needed, but the boot ordering
would be slightly different, since the MTRR code on i386 depends on the
boot_cpu_data structure being setup.
This patch fixes a bug in the last patch that caused the code to run on
non-Intel machines (AMD machines apparently don't need it and it's untested
on other non-Intel machines, so best keep it off).
Further enhancements and fixes from:
Yinghai Lu <Yinghai.Lu@Sun.COM>
Andi Kleen <ak@suse.de>
Signed-off-by: Jesse Barnes <jesse.barnes@intel.com>
Tested-by: Justin Piszcz <jpiszcz@lucidpixels.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:33:18 +08:00
|
|
|
extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
|
2008-03-25 07:02:01 +08:00
|
|
|
extern int amd_special_default_mtrr(void);
|
2007-10-24 04:37:24 +08:00
|
|
|
# else
|
2015-05-26 16:28:10 +08:00
|
|
|
static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
|
2008-03-21 22:42:28 +08:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Return no-MTRRs:
|
|
|
|
*/
|
2015-05-26 16:28:07 +08:00
|
|
|
return MTRR_TYPE_INVALID;
|
2008-03-21 22:42:28 +08:00
|
|
|
}
|
2007-10-24 04:37:24 +08:00
|
|
|
#define mtrr_save_fixed_ranges(arg) do {} while (0)
|
|
|
|
#define mtrr_save_state() do {} while (0)
|
2008-03-23 16:02:52 +08:00
|
|
|
static inline int mtrr_add(unsigned long base, unsigned long size,
|
|
|
|
unsigned int type, bool increment)
|
2007-10-24 04:37:24 +08:00
|
|
|
{
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
2008-03-23 16:02:52 +08:00
|
|
|
static inline int mtrr_add_page(unsigned long base, unsigned long size,
|
2008-01-30 20:30:31 +08:00
|
|
|
unsigned int type, bool increment)
|
2007-10-24 04:37:24 +08:00
|
|
|
{
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
2008-03-23 16:02:52 +08:00
|
|
|
static inline int mtrr_del(int reg, unsigned long base, unsigned long size)
|
2007-10-24 04:37:24 +08:00
|
|
|
{
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
2008-03-23 16:02:52 +08:00
|
|
|
static inline int mtrr_del_page(int reg, unsigned long base, unsigned long size)
|
2007-10-24 04:37:24 +08:00
|
|
|
{
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
x86, 32-bit: trim memory not covered by wb mtrrs
On some machines, buggy BIOSes don't properly setup WB MTRRs to cover all
available RAM, meaning the last few megs (or even gigs) of memory will be
marked uncached. Since Linux tends to allocate from high memory addresses
first, this causes the machine to be unusably slow as soon as the kernel
starts really using memory (i.e. right around init time).
This patch works around the problem by scanning the MTRRs at boot and
figuring out whether the current end_pfn value (setup by early e820 code)
goes beyond the highest WB MTRR range, and if so, trimming it to match. A
fairly obnoxious KERN_WARNING is printed too, letting the user know that
not all of their memory is available due to a likely BIOS bug.
Something similar could be done on i386 if needed, but the boot ordering
would be slightly different, since the MTRR code on i386 depends on the
boot_cpu_data structure being setup.
This patch fixes a bug in the last patch that caused the code to run on
non-Intel machines (AMD machines apparently don't need it and it's untested
on other non-Intel machines, so best keep it off).
Further enhancements and fixes from:
Yinghai Lu <Yinghai.Lu@Sun.COM>
Andi Kleen <ak@suse.de>
Signed-off-by: Jesse Barnes <jesse.barnes@intel.com>
Tested-by: Justin Piszcz <jpiszcz@lucidpixels.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:33:18 +08:00
|
|
|
static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2008-03-23 16:02:52 +08:00
|
|
|
static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
|
|
|
|
{
|
|
|
|
}
|
x86/mtrr: Fix Xorg crashes in Qemu sessions
A Xorg failure on qemu32 was reported as a regression [1] caused by
commit 9cd25aac1f44 ("x86/mm/pat: Emulate PAT when it is disabled").
This patch fixes the Xorg crash.
Negative effects of this regression were the following two failures [2]
in Xorg on QEMU with QEMU CPU model "qemu32" (-cpu qemu32), which were
triggered by the fact that its virtual CPU does not support MTRRs.
#1. copy_process() failed in the check in reserve_pfn_range()
copy_process
copy_mm
dup_mm
dup_mmap
copy_page_range
track_pfn_copy
reserve_pfn_range
A WC map request was tracked as WC in memtype, which set a PTE as
UC (pgprot) per __cachemode2pte_tbl[]. This led to this error in
reserve_pfn_range() called from track_pfn_copy(), which obtained
a pgprot from a PTE. It converts pgprot to page_cache_mode, which
does not necessarily result in the original page_cache_mode since
__cachemode2pte_tbl[] redirects multiple types to UC.
#2. error path in copy_process() then hit WARN_ON_ONCE in
untrack_pfn().
x86/PAT: Xorg:509 map pfn expected mapping type uncached-
minus for [mem 0xfd000000-0xfdffffff], got write-combining
Call Trace:
dump_stack
warn_slowpath_common
? untrack_pfn
? untrack_pfn
warn_slowpath_null
untrack_pfn
? __kunmap_atomic
unmap_single_vma
? pagevec_move_tail_fn
unmap_vmas
exit_mmap
mmput
copy_process.part.47
_do_fork
SyS_clone
do_syscall_32_irqs_on
entry_INT80_32
These negative effects are caused by two separate bugs, but they
can be addressed in separate patches. Fixing the pat_init() issue
described below addresses the root cause, and avoids Xorg to hit
these cases.
When the CPU does not support MTRRs, MTRR does not call pat_init(),
which leaves PAT enabled without initializing PAT. This pat_init()
issue is a long-standing issue, but manifested as issue #1 (and then
hit issue #2) with the above-mentioned commit because the memtype
now tracks cache attribute with 'page_cache_mode'.
This pat_init() issue existed before the commit, but we used pgprot
in memtype. Hence, we did not have issue #1 before. But WC request
resulted in WT in effect because WC pgrot is actually WT when PAT
is not initialized. This is not how it was designed to work. When
PAT is set to disable properly, WC is converted to UC. The use of
WT can result in a system crash if the target range does not support
WT. Fortunately, nobody ran into such issue before.
To fix this pat_init() issue, PAT code has been enhanced to provide
pat_disable() interface. Call this interface when MTRRs are disabled.
By setting PAT to disable properly, PAT bypasses the memtype check,
and avoids issue #1.
[1]: https://lkml.org/lkml/2016/3/3/828
[2]: https://lkml.org/lkml/2016/3/4/775
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: elliott@hpe.com
Cc: konrad.wilk@oracle.com
Cc: paul.gortmaker@windriver.com
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1458769323-24491-5-git-send-email-toshi.kani@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-24 05:42:00 +08:00
|
|
|
static inline void mtrr_bp_init(void)
|
|
|
|
{
|
|
|
|
pat_disable("MTRRs disabled, skipping PAT initialization too.");
|
|
|
|
}
|
2007-10-24 04:37:24 +08:00
|
|
|
|
|
|
|
#define mtrr_ap_init() do {} while (0)
|
2009-08-20 09:05:36 +08:00
|
|
|
#define set_mtrr_aps_delayed_init() do {} while (0)
|
|
|
|
#define mtrr_aps_init() do {} while (0)
|
|
|
|
#define mtrr_bp_restore() do {} while (0)
|
2007-10-24 04:37:24 +08:00
|
|
|
# endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
|
|
#include <linux/compat.h>
|
|
|
|
|
2008-03-23 16:02:52 +08:00
|
|
|
struct mtrr_sentry32 {
|
2007-10-24 04:37:24 +08:00
|
|
|
compat_ulong_t base; /* Base address */
|
|
|
|
compat_uint_t size; /* Size of region */
|
|
|
|
compat_uint_t type; /* Type of region */
|
|
|
|
};
|
|
|
|
|
2008-03-23 16:02:52 +08:00
|
|
|
struct mtrr_gentry32 {
|
2007-10-24 04:37:24 +08:00
|
|
|
compat_ulong_t regnum; /* Register number */
|
|
|
|
compat_uint_t base; /* Base address */
|
|
|
|
compat_uint_t size; /* Size of region */
|
|
|
|
compat_uint_t type; /* Type of region */
|
|
|
|
};
|
|
|
|
|
|
|
|
#define MTRR_IOCTL_BASE 'M'
|
|
|
|
|
2008-03-23 16:02:52 +08:00
|
|
|
#define MTRRIOC32_ADD_ENTRY _IOW(MTRR_IOCTL_BASE, 0, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_SET_ENTRY _IOW(MTRR_IOCTL_BASE, 1, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_DEL_ENTRY _IOW(MTRR_IOCTL_BASE, 2, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_GET_ENTRY _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry32)
|
|
|
|
#define MTRRIOC32_KILL_ENTRY _IOW(MTRR_IOCTL_BASE, 4, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 5, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 6, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 7, struct mtrr_sentry32)
|
|
|
|
#define MTRRIOC32_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry32)
|
|
|
|
#define MTRRIOC32_KILL_PAGE_ENTRY \
|
|
|
|
_IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry32)
|
2007-10-24 04:37:24 +08:00
|
|
|
#endif /* CONFIG_COMPAT */
|
|
|
|
|
2015-05-26 16:28:06 +08:00
|
|
|
/* Bit fields for enabled in struct mtrr_state_type */
|
|
|
|
#define MTRR_STATE_MTRR_FIXED_ENABLED 0x01
|
|
|
|
#define MTRR_STATE_MTRR_ENABLED 0x02
|
|
|
|
|
2008-10-23 13:26:29 +08:00
|
|
|
#endif /* _ASM_X86_MTRR_H */
|