2005-04-17 06:20:36 +08:00
|
|
|
#ifndef _ASM_GENERIC_PGTABLE_H
|
|
|
|
#define _ASM_GENERIC_PGTABLE_H
|
|
|
|
|
2006-09-26 14:32:29 +08:00
|
|
|
#ifndef __ASSEMBLY__
|
2007-08-11 04:01:20 +08:00
|
|
|
#ifdef CONFIG_MMU
|
2006-09-26 14:32:29 +08:00
|
|
|
|
2011-02-27 13:41:35 +08:00
|
|
|
#include <linux/mm_types.h>
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
|
2011-01-14 07:46:40 +08:00
|
|
|
extern int ptep_set_access_flags(struct vm_area_struct *vma,
|
|
|
|
unsigned long address, pte_t *ptep,
|
|
|
|
pte_t entry, int dirty);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
|
|
|
|
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
|
|
|
|
unsigned long address, pmd_t *pmdp,
|
|
|
|
pmd_t entry, int dirty);
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
|
2011-01-14 07:46:40 +08:00
|
|
|
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
|
|
|
|
unsigned long address,
|
|
|
|
pte_t *ptep)
|
|
|
|
{
|
|
|
|
pte_t pte = *ptep;
|
|
|
|
int r = 1;
|
|
|
|
if (!pte_young(pte))
|
|
|
|
r = 0;
|
|
|
|
else
|
|
|
|
set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte));
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
|
|
|
|
unsigned long address,
|
|
|
|
pmd_t *pmdp)
|
|
|
|
{
|
|
|
|
pmd_t pmd = *pmdp;
|
|
|
|
int r = 1;
|
|
|
|
if (!pmd_young(pmd))
|
|
|
|
r = 0;
|
|
|
|
else
|
|
|
|
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd));
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
|
|
|
|
unsigned long address,
|
|
|
|
pmd_t *pmdp)
|
|
|
|
{
|
|
|
|
BUG();
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
|
2011-01-14 07:46:40 +08:00
|
|
|
int ptep_clear_flush_young(struct vm_area_struct *vma,
|
|
|
|
unsigned long address, pte_t *ptep);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
|
|
|
|
int pmdp_clear_flush_young(struct vm_area_struct *vma,
|
|
|
|
unsigned long address, pmd_t *pmdp);
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
|
2011-01-14 07:46:40 +08:00
|
|
|
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
|
|
|
|
unsigned long address,
|
|
|
|
pte_t *ptep)
|
|
|
|
{
|
|
|
|
pte_t pte = *ptep;
|
|
|
|
pte_clear(mm, address, ptep);
|
|
|
|
return pte;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
|
|
|
|
unsigned long address,
|
|
|
|
pmd_t *pmdp)
|
|
|
|
{
|
|
|
|
pmd_t pmd = *pmdp;
|
|
|
|
pmd_clear(mm, address, pmdp);
|
|
|
|
return pmd;
|
2005-04-17 06:20:36 +08:00
|
|
|
})
|
2011-01-14 07:46:40 +08:00
|
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
[PATCH] x86: ptep_clear optimization
Add a new accessor for PTEs, which passes the full hint from the mmu_gather
struct; this allows architectures with hardware pagetables to optimize away
atomic PTE operations when destroying an address space. Removing the
locked operation should allow better pipelining of memory access in this
loop. I measured an average savings of 30-35 cycles per zap_pte_range on
the first 500 destructions on Pentium-M, but I believe the optimization
would win more on older processors which still assert the bus lock on xchg
for an exclusive cacheline.
Update: I made some new measurements, and this saves exactly 26 cycles over
ptep_get_and_clear on Pentium M. On P4, with a PAE kernel, this saves 180
cycles per ptep_get_and_clear, for a whopping 92160 cycles savings for a
full address space destruction.
pte_clear_full is not yet used, but is provided for future optimizations
(in particular, when running inside of a hypervisor that queues page table
updates, the full hint allows us to avoid queueing unnecessary page table
update for an address space in the process of being destroyed.
This is not a huge win, but it does help a bit, and sets the stage for
further hypervisor optimization of the mm layer on all architectures.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Christoph Lameter <christoph@lameter.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-04 06:55:04 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
|
2011-01-14 07:46:40 +08:00
|
|
|
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
|
|
|
|
unsigned long address, pte_t *ptep,
|
|
|
|
int full)
|
|
|
|
{
|
|
|
|
pte_t pte;
|
|
|
|
pte = ptep_get_and_clear(mm, address, ptep);
|
|
|
|
return pte;
|
|
|
|
}
|
[PATCH] x86: ptep_clear optimization
Add a new accessor for PTEs, which passes the full hint from the mmu_gather
struct; this allows architectures with hardware pagetables to optimize away
atomic PTE operations when destroying an address space. Removing the
locked operation should allow better pipelining of memory access in this
loop. I measured an average savings of 30-35 cycles per zap_pte_range on
the first 500 destructions on Pentium-M, but I believe the optimization
would win more on older processors which still assert the bus lock on xchg
for an exclusive cacheline.
Update: I made some new measurements, and this saves exactly 26 cycles over
ptep_get_and_clear on Pentium M. On P4, with a PAE kernel, this saves 180
cycles per ptep_get_and_clear, for a whopping 92160 cycles savings for a
full address space destruction.
pte_clear_full is not yet used, but is provided for future optimizations
(in particular, when running inside of a hypervisor that queues page table
updates, the full hint allows us to avoid queueing unnecessary page table
update for an address space in the process of being destroyed.
This is not a huge win, but it does help a bit, and sets the stage for
further hypervisor optimization of the mm layer on all architectures.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Christoph Lameter <christoph@lameter.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-04 06:55:04 +08:00
|
|
|
#endif
|
|
|
|
|
2006-10-01 14:29:31 +08:00
|
|
|
/*
|
|
|
|
* Some architectures may be able to avoid expensive synchronization
|
|
|
|
* primitives when modifications are made to PTE's which are already
|
|
|
|
* not present, or in the process of an address space destruction.
|
|
|
|
*/
|
|
|
|
#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
|
2011-01-14 07:46:40 +08:00
|
|
|
static inline void pte_clear_not_present_full(struct mm_struct *mm,
|
|
|
|
unsigned long address,
|
|
|
|
pte_t *ptep,
|
|
|
|
int full)
|
|
|
|
{
|
|
|
|
pte_clear(mm, address, ptep);
|
|
|
|
}
|
[PATCH] x86: ptep_clear optimization
Add a new accessor for PTEs, which passes the full hint from the mmu_gather
struct; this allows architectures with hardware pagetables to optimize away
atomic PTE operations when destroying an address space. Removing the
locked operation should allow better pipelining of memory access in this
loop. I measured an average savings of 30-35 cycles per zap_pte_range on
the first 500 destructions on Pentium-M, but I believe the optimization
would win more on older processors which still assert the bus lock on xchg
for an exclusive cacheline.
Update: I made some new measurements, and this saves exactly 26 cycles over
ptep_get_and_clear on Pentium M. On P4, with a PAE kernel, this saves 180
cycles per ptep_get_and_clear, for a whopping 92160 cycles savings for a
full address space destruction.
pte_clear_full is not yet used, but is provided for future optimizations
(in particular, when running inside of a hypervisor that queues page table
updates, the full hint allows us to avoid queueing unnecessary page table
update for an address space in the process of being destroyed.
This is not a huge win, but it does help a bit, and sets the stage for
further hypervisor optimization of the mm layer on all architectures.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Christoph Lameter <christoph@lameter.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-04 06:55:04 +08:00
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
|
2011-01-14 07:46:40 +08:00
|
|
|
extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
|
|
|
|
unsigned long address,
|
|
|
|
pte_t *ptep);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
|
|
|
|
extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
|
|
|
|
unsigned long address,
|
|
|
|
pmd_t *pmdp);
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
|
2005-11-07 16:59:43 +08:00
|
|
|
struct mm_struct;
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
|
|
|
|
{
|
|
|
|
pte_t old_pte = *ptep;
|
|
|
|
set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2011-01-14 07:46:40 +08:00
|
|
|
#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
|
|
|
|
unsigned long address, pmd_t *pmdp)
|
|
|
|
{
|
|
|
|
pmd_t old_pmd = *pmdp;
|
|
|
|
set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
|
|
|
|
}
|
|
|
|
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
|
|
|
|
unsigned long address, pmd_t *pmdp)
|
|
|
|
{
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
|
2011-01-17 05:10:39 +08:00
|
|
|
extern pmd_t pmdp_splitting_flush(struct vm_area_struct *vma,
|
|
|
|
unsigned long address,
|
|
|
|
pmd_t *pmdp);
|
2011-01-14 07:46:40 +08:00
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTE_SAME
|
2011-01-14 07:46:40 +08:00
|
|
|
static inline int pte_same(pte_t pte_a, pte_t pte_b)
|
|
|
|
{
|
|
|
|
return pte_val(pte_a) == pte_val(pte_b);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PMD_SAME
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
|
|
|
|
{
|
|
|
|
return pmd_val(pmd_a) == pmd_val(pmd_b);
|
|
|
|
}
|
|
|
|
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
|
|
|
|
{
|
|
|
|
BUG();
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
2011-05-23 16:24:39 +08:00
|
|
|
#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
|
|
|
|
#define page_test_and_clear_dirty(pfn, mapped) (0)
|
2007-04-27 22:01:57 +08:00
|
|
|
#endif
|
|
|
|
|
2011-05-23 16:24:39 +08:00
|
|
|
#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
|
2005-06-22 08:15:13 +08:00
|
|
|
#define pte_maybe_dirty(pte) pte_dirty(pte)
|
|
|
|
#else
|
|
|
|
#define pte_maybe_dirty(pte) (1)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
|
2011-05-23 16:24:39 +08:00
|
|
|
#define page_test_and_clear_young(pfn) (0)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
|
|
|
|
#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr)
|
|
|
|
#endif
|
|
|
|
|
2006-06-02 08:47:25 +08:00
|
|
|
#ifndef __HAVE_ARCH_MOVE_PTE
|
2005-09-28 12:45:18 +08:00
|
|
|
#define move_pte(pte, prot, old_addr, new_addr) (pte)
|
|
|
|
#endif
|
|
|
|
|
x86, mm: Avoid unnecessary TLB flush
In x86, access and dirty bits are set automatically by CPU when CPU accesses
memory. When we go into the code path of below flush_tlb_fix_spurious_fault(),
we already set dirty bit for pte and don't need flush tlb. This might mean
tlb entry in some CPUs hasn't dirty bit set, but this doesn't matter. When
the CPUs do page write, they will automatically check the bit and no software
involved.
On the other hand, flush tlb in below position is harmful. Test creates CPU
number of threads, each thread writes to a same but random address in same vma
range and we measure the total time. Under a 4 socket system, original time is
1.96s, while with the patch, the time is 0.8s. Under a 2 socket system, there is
20% time cut too. perf shows a lot of time are taking to send ipi/handle ipi for
tlb flush.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
LKML-Reference: <20100816011655.GA362@sli10-desk.sh.intel.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andrea Archangeli <aarcange@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-16 09:16:55 +08:00
|
|
|
#ifndef flush_tlb_fix_spurious_fault
|
|
|
|
#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
|
|
|
|
#endif
|
|
|
|
|
2009-06-23 19:51:19 +08:00
|
|
|
#ifndef pgprot_noncached
|
|
|
|
#define pgprot_noncached(prot) (prot)
|
|
|
|
#endif
|
|
|
|
|
2008-12-19 03:41:32 +08:00
|
|
|
#ifndef pgprot_writecombine
|
|
|
|
#define pgprot_writecombine pgprot_noncached
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2005-04-20 04:29:17 +08:00
|
|
|
* When walking page tables, get the address of the next boundary,
|
|
|
|
* or the end address of the range if that comes earlier. Although no
|
|
|
|
* vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#define pgd_addr_end(addr, end) \
|
|
|
|
({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \
|
|
|
|
(__boundary - 1 < (end) - 1)? __boundary: (end); \
|
|
|
|
})
|
|
|
|
|
|
|
|
#ifndef pud_addr_end
|
|
|
|
#define pud_addr_end(addr, end) \
|
|
|
|
({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \
|
|
|
|
(__boundary - 1 < (end) - 1)? __boundary: (end); \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef pmd_addr_end
|
|
|
|
#define pmd_addr_end(addr, end) \
|
|
|
|
({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \
|
|
|
|
(__boundary - 1 < (end) - 1)? __boundary: (end); \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When walking page tables, we usually want to skip any p?d_none entries;
|
|
|
|
* and any p?d_bad entries - reporting the error before resetting to none.
|
|
|
|
* Do the tests inline, but report and clear the bad entry in mm/memory.c.
|
|
|
|
*/
|
|
|
|
void pgd_clear_bad(pgd_t *);
|
|
|
|
void pud_clear_bad(pud_t *);
|
|
|
|
void pmd_clear_bad(pmd_t *);
|
|
|
|
|
|
|
|
static inline int pgd_none_or_clear_bad(pgd_t *pgd)
|
|
|
|
{
|
|
|
|
if (pgd_none(*pgd))
|
|
|
|
return 1;
|
|
|
|
if (unlikely(pgd_bad(*pgd))) {
|
|
|
|
pgd_clear_bad(pgd);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int pud_none_or_clear_bad(pud_t *pud)
|
|
|
|
{
|
|
|
|
if (pud_none(*pud))
|
|
|
|
return 1;
|
|
|
|
if (unlikely(pud_bad(*pud))) {
|
|
|
|
pud_clear_bad(pud);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int pmd_none_or_clear_bad(pmd_t *pmd)
|
|
|
|
{
|
|
|
|
if (pmd_none(*pmd))
|
|
|
|
return 1;
|
|
|
|
if (unlikely(pmd_bad(*pmd))) {
|
|
|
|
pmd_clear_bad(pmd);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
2007-08-11 04:01:20 +08:00
|
|
|
|
mm: add a ptep_modify_prot transaction abstraction
This patch adds an API for doing read-modify-write updates to a pte's
protection bits which may race against hardware updates to the pte.
After reading the pte, the hardware may asynchonously set the accessed
or dirty bits on a pte, which would be lost when writing back the
modified pte value.
The existing technique to handle this race is to use
ptep_get_and_clear() atomically fetch the old pte value and clear it
in memory. This has the effect of marking the pte as non-present,
which will prevent the hardware from updating its state. When the new
value is written back, the pte will be present again, and the hardware
can resume updating the access/dirty flags.
When running in a virtualized environment, pagetable updates are
relatively expensive, since they generally involve some trap into the
hypervisor. To mitigate the cost of these updates, we tend to batch
them.
However, because of the atomic nature of ptep_get_and_clear(), it is
inherently non-batchable. This new interface allows batching by
giving the underlying implementation enough information to open a
transaction between the read and write phases:
ptep_modify_prot_start() returns the current pte value, and puts the
pte entry into a state where either the hardware will not update the
pte, or if it does, the updates will be preserved on commit.
ptep_modify_prot_commit() writes back the updated pte, makes sure that
any hardware updates made since ptep_modify_prot_start() are
preserved.
ptep_modify_prot_start() and _commit() must be exactly paired, and
used while holding the appropriate pte lock. They do not protect
against other software updates of the pte in any way.
The current implementations of ptep_modify_prot_start and _commit are
functionally unchanged from before: _start() uses ptep_get_and_clear()
fetch the pte and zero the entry, preventing any hardware updates.
_commit() simply writes the new pte value back knowing that the
hardware has not updated the pte in the meantime.
The only current user of this interface is mprotect
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-06-16 19:30:00 +08:00
|
|
|
static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
|
|
|
|
unsigned long addr,
|
|
|
|
pte_t *ptep)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Get the current pte state, but zero it out to make it
|
|
|
|
* non-present, preventing the hardware from asynchronously
|
|
|
|
* updating it.
|
|
|
|
*/
|
|
|
|
return ptep_get_and_clear(mm, addr, ptep);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
|
|
|
|
unsigned long addr,
|
|
|
|
pte_t *ptep, pte_t pte)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The pte is non-present, so there's no hardware state to
|
|
|
|
* preserve.
|
|
|
|
*/
|
|
|
|
set_pte_at(mm, addr, ptep, pte);
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
|
|
|
|
/*
|
|
|
|
* Start a pte protection read-modify-write transaction, which
|
|
|
|
* protects against asynchronous hardware modifications to the pte.
|
|
|
|
* The intention is not to prevent the hardware from making pte
|
|
|
|
* updates, but to prevent any updates it may make from being lost.
|
|
|
|
*
|
|
|
|
* This does not protect against other software modifications of the
|
|
|
|
* pte; the appropriate pte lock must be held over the transation.
|
|
|
|
*
|
|
|
|
* Note that this interface is intended to be batchable, meaning that
|
|
|
|
* ptep_modify_prot_commit may not actually update the pte, but merely
|
|
|
|
* queue the update to be done at some later time. The update must be
|
|
|
|
* actually committed before the pte lock is released, however.
|
|
|
|
*/
|
|
|
|
static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
|
|
|
|
unsigned long addr,
|
|
|
|
pte_t *ptep)
|
|
|
|
{
|
|
|
|
return __ptep_modify_prot_start(mm, addr, ptep);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Commit an update to a pte, leaving any hardware-controlled bits in
|
|
|
|
* the PTE unmodified.
|
|
|
|
*/
|
|
|
|
static inline void ptep_modify_prot_commit(struct mm_struct *mm,
|
|
|
|
unsigned long addr,
|
|
|
|
pte_t *ptep, pte_t pte)
|
|
|
|
{
|
|
|
|
__ptep_modify_prot_commit(mm, addr, ptep, pte);
|
|
|
|
}
|
|
|
|
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
|
2008-07-16 04:28:46 +08:00
|
|
|
#endif /* CONFIG_MMU */
|
mm: add a ptep_modify_prot transaction abstraction
This patch adds an API for doing read-modify-write updates to a pte's
protection bits which may race against hardware updates to the pte.
After reading the pte, the hardware may asynchonously set the accessed
or dirty bits on a pte, which would be lost when writing back the
modified pte value.
The existing technique to handle this race is to use
ptep_get_and_clear() atomically fetch the old pte value and clear it
in memory. This has the effect of marking the pte as non-present,
which will prevent the hardware from updating its state. When the new
value is written back, the pte will be present again, and the hardware
can resume updating the access/dirty flags.
When running in a virtualized environment, pagetable updates are
relatively expensive, since they generally involve some trap into the
hypervisor. To mitigate the cost of these updates, we tend to batch
them.
However, because of the atomic nature of ptep_get_and_clear(), it is
inherently non-batchable. This new interface allows batching by
giving the underlying implementation enough information to open a
transaction between the read and write phases:
ptep_modify_prot_start() returns the current pte value, and puts the
pte entry into a state where either the hardware will not update the
pte, or if it does, the updates will be preserved on commit.
ptep_modify_prot_commit() writes back the updated pte, makes sure that
any hardware updates made since ptep_modify_prot_start() are
preserved.
ptep_modify_prot_start() and _commit() must be exactly paired, and
used while holding the appropriate pte lock. They do not protect
against other software updates of the pte in any way.
The current implementations of ptep_modify_prot_start and _commit are
functionally unchanged from before: _start() uses ptep_get_and_clear()
fetch the pte and zero the entry, preventing any hardware updates.
_commit() simply writes the new pte value back knowing that the
hardware has not updated the pte in the meantime.
The only current user of this interface is mprotect
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-06-16 19:30:00 +08:00
|
|
|
|
2007-08-11 04:01:20 +08:00
|
|
|
/*
|
|
|
|
* A facility to provide lazy MMU batching. This allows PTE updates and
|
|
|
|
* page invalidations to be delayed until a call to leave lazy MMU mode
|
|
|
|
* is issued. Some architectures may benefit from doing this, and it is
|
|
|
|
* beneficial for both shadow and direct mode hypervisors, which may batch
|
|
|
|
* the PTE updates which happen during this window. Note that using this
|
|
|
|
* interface requires that read hazards be removed from the code. A read
|
|
|
|
* hazard could result in the direct mode hypervisor case, since the actual
|
|
|
|
* write to the page tables may not yet have taken place, so reads though
|
|
|
|
* a raw PTE pointer after it has been modified are not guaranteed to be
|
|
|
|
* up to date. This mode can only be entered and left under the protection of
|
|
|
|
* the page table locks for all page tables which may be modified. In the UP
|
|
|
|
* case, this is required so that preemption is disabled, and in the SMP case,
|
|
|
|
* it must synchronize the delayed page table writes properly on other CPUs.
|
|
|
|
*/
|
|
|
|
#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
|
|
|
|
#define arch_enter_lazy_mmu_mode() do {} while (0)
|
|
|
|
#define arch_leave_lazy_mmu_mode() do {} while (0)
|
|
|
|
#define arch_flush_lazy_mmu_mode() do {} while (0)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
2009-02-18 15:24:03 +08:00
|
|
|
* A facility to provide batching of the reload of page tables and
|
|
|
|
* other process state with the actual context switch code for
|
|
|
|
* paravirtualized guests. By convention, only one of the batched
|
|
|
|
* update (lazy) modes (CPU, MMU) should be active at any given time,
|
|
|
|
* entry should never be nested, and entry and exits should always be
|
|
|
|
* paired. This is for sanity of maintaining and reasoning about the
|
|
|
|
* kernel code. In this case, the exit (end of the context switch) is
|
|
|
|
* in architecture-specific code, and so doesn't need a generic
|
|
|
|
* definition.
|
2007-08-11 04:01:20 +08:00
|
|
|
*/
|
2009-02-18 15:24:03 +08:00
|
|
|
#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
|
2009-02-19 03:18:57 +08:00
|
|
|
#define arch_start_context_switch(prev) do {} while (0)
|
2007-08-11 04:01:20 +08:00
|
|
|
#endif
|
|
|
|
|
2008-12-20 05:47:29 +08:00
|
|
|
#ifndef __HAVE_PFNMAP_TRACKING
|
|
|
|
/*
|
|
|
|
* Interface that can be used by architecture code to keep track of
|
|
|
|
* memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
|
|
|
|
*
|
|
|
|
* track_pfn_vma_new is called when a _new_ pfn mapping is being established
|
|
|
|
* for physical range indicated by pfn and size.
|
|
|
|
*/
|
2009-01-10 08:13:11 +08:00
|
|
|
static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
|
2008-12-20 05:47:29 +08:00
|
|
|
unsigned long pfn, unsigned long size)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Interface that can be used by architecture code to keep track of
|
|
|
|
* memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
|
|
|
|
*
|
|
|
|
* track_pfn_vma_copy is called when vma that is covering the pfnmap gets
|
|
|
|
* copied through copy_page_range().
|
|
|
|
*/
|
|
|
|
static inline int track_pfn_vma_copy(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Interface that can be used by architecture code to keep track of
|
|
|
|
* memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
|
|
|
|
*
|
|
|
|
* untrack_pfn_vma is called while unmapping a pfnmap for a region.
|
|
|
|
* untrack can be called for a specific region indicated by pfn and size or
|
|
|
|
* can be for the entire vma (in which case size can be zero).
|
|
|
|
*/
|
|
|
|
static inline void untrack_pfn_vma(struct vm_area_struct *vma,
|
|
|
|
unsigned long pfn, unsigned long size)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#else
|
2009-01-10 08:13:11 +08:00
|
|
|
extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
|
2008-12-20 05:47:29 +08:00
|
|
|
unsigned long pfn, unsigned long size);
|
|
|
|
extern int track_pfn_vma_copy(struct vm_area_struct *vma);
|
|
|
|
extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
|
|
|
|
unsigned long size);
|
|
|
|
#endif
|
|
|
|
|
2011-01-14 07:46:40 +08:00
|
|
|
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
static inline int pmd_trans_huge(pmd_t pmd)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
static inline int pmd_trans_splitting(pmd_t pmd)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2011-01-14 07:46:40 +08:00
|
|
|
#ifndef __HAVE_ARCH_PMD_WRITE
|
|
|
|
static inline int pmd_write(pmd_t pmd)
|
|
|
|
{
|
|
|
|
BUG();
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* __HAVE_ARCH_PMD_WRITE */
|
2011-01-14 07:46:40 +08:00
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
|
|
|
|
#endif /* _ASM_GENERIC_PGTABLE_H */
|