kernel-ark/include/linux/swapops.h
Mel Gorman 21d9ee3eda mm: remove remaining references to NUMA hinting bits and helpers
This patch removes the NUMA PTE bits and associated helpers.  As a
side-effect it increases the maximum possible swap space on x86-64.

One potential source of problems is races between the marking of PTEs
PROT_NONE, NUMA hinting faults and migration.  It must be guaranteed that
a PTE being protected is not faulted in parallel, seen as a pte_none and
corrupting memory.  The base case is safe but transhuge has problems in
the past due to an different migration mechanism and a dependance on page
lock to serialise migrations and warrants a closer look.

task_work hinting update			parallel fault
------------------------			--------------
change_pmd_range
  change_huge_pmd
    __pmd_trans_huge_lock
      pmdp_get_and_clear
						__handle_mm_fault
						pmd_none
						  do_huge_pmd_anonymous_page
						  read? pmd_lock blocks until hinting complete, fail !pmd_none test
						  write? __do_huge_pmd_anonymous_page acquires pmd_lock, checks pmd_none
      pmd_modify
      set_pmd_at

task_work hinting update			parallel migration
------------------------			------------------
change_pmd_range
  change_huge_pmd
    __pmd_trans_huge_lock
      pmdp_get_and_clear
						__handle_mm_fault
						  do_huge_pmd_numa_page
						    migrate_misplaced_transhuge_page
						    pmd_lock waits for updates to complete, recheck pmd_same
      pmd_modify
      set_pmd_at

Both of those are safe and the case where a transhuge page is inserted
during a protection update is unchanged.  The case where two processes try
migrating at the same time is unchanged by this series so should still be
ok.  I could not find a case where we are accidentally depending on the
PTE not being cleared and flushed.  If one is missed, it'll manifest as
corruption problems that start triggering shortly after this series is
merged and only happen when NUMA balancing is enabled.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 18:54:08 -08:00

206 lines
5.2 KiB
C

#ifndef _LINUX_SWAPOPS_H
#define _LINUX_SWAPOPS_H
#include <linux/radix-tree.h>
#include <linux/bug.h>
/*
* swapcache pages are stored in the swapper_space radix tree. We want to
* get good packing density in that tree, so the index should be dense in
* the low-order bits.
*
* We arrange the `type' and `offset' fields so that `type' is at the seven
* high-order bits of the swp_entry_t and `offset' is right-aligned in the
* remaining bits. Although `type' itself needs only five bits, we allow for
* shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry().
*
* swp_entry_t's are *never* stored anywhere in their arch-dependent format.
*/
#define SWP_TYPE_SHIFT(e) ((sizeof(e.val) * 8) - \
(MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT))
#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1)
/*
* Store a type+offset into a swp_entry_t in an arch-independent format
*/
static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
{
swp_entry_t ret;
ret.val = (type << SWP_TYPE_SHIFT(ret)) |
(offset & SWP_OFFSET_MASK(ret));
return ret;
}
/*
* Extract the `type' field from a swp_entry_t. The swp_entry_t is in
* arch-independent format
*/
static inline unsigned swp_type(swp_entry_t entry)
{
return (entry.val >> SWP_TYPE_SHIFT(entry));
}
/*
* Extract the `offset' field from a swp_entry_t. The swp_entry_t is in
* arch-independent format
*/
static inline pgoff_t swp_offset(swp_entry_t entry)
{
return entry.val & SWP_OFFSET_MASK(entry);
}
#ifdef CONFIG_MMU
/* check whether a pte points to a swap entry */
static inline int is_swap_pte(pte_t pte)
{
return !pte_none(pte) && !pte_present(pte);
}
#endif
/*
* Convert the arch-dependent pte representation of a swp_entry_t into an
* arch-independent swp_entry_t.
*/
static inline swp_entry_t pte_to_swp_entry(pte_t pte)
{
swp_entry_t arch_entry;
if (pte_swp_soft_dirty(pte))
pte = pte_swp_clear_soft_dirty(pte);
arch_entry = __pte_to_swp_entry(pte);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
/*
* Convert the arch-independent representation of a swp_entry_t into the
* arch-dependent pte representation.
*/
static inline pte_t swp_entry_to_pte(swp_entry_t entry)
{
swp_entry_t arch_entry;
arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
return __swp_entry_to_pte(arch_entry);
}
static inline swp_entry_t radix_to_swp_entry(void *arg)
{
swp_entry_t entry;
entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
return entry;
}
static inline void *swp_to_radix_entry(swp_entry_t entry)
{
unsigned long value;
value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT;
return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY);
}
#ifdef CONFIG_MIGRATION
static inline swp_entry_t make_migration_entry(struct page *page, int write)
{
BUG_ON(!PageLocked(page));
return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ,
page_to_pfn(page));
}
static inline int is_migration_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
swp_type(entry) == SWP_MIGRATION_WRITE);
}
static inline int is_write_migration_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
}
static inline struct page *migration_entry_to_page(swp_entry_t entry)
{
struct page *p = pfn_to_page(swp_offset(entry));
/*
* Any use of migration entries may only occur while the
* corresponding page is locked
*/
BUG_ON(!PageLocked(p));
return p;
}
static inline void make_migration_entry_read(swp_entry_t *entry)
{
*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
}
extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
spinlock_t *ptl);
extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address);
extern void migration_entry_wait_huge(struct vm_area_struct *vma,
struct mm_struct *mm, pte_t *pte);
#else
#define make_migration_entry(page, write) swp_entry(0, 0)
static inline int is_migration_entry(swp_entry_t swp)
{
return 0;
}
#define migration_entry_to_page(swp) NULL
static inline void make_migration_entry_read(swp_entry_t *entryp) { }
static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
spinlock_t *ptl) { }
static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address) { }
static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
struct mm_struct *mm, pte_t *pte) { }
static inline int is_write_migration_entry(swp_entry_t entry)
{
return 0;
}
#endif
#ifdef CONFIG_MEMORY_FAILURE
/*
* Support for hardware poisoned pages
*/
static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
BUG_ON(!PageLocked(page));
return swp_entry(SWP_HWPOISON, page_to_pfn(page));
}
static inline int is_hwpoison_entry(swp_entry_t entry)
{
return swp_type(entry) == SWP_HWPOISON;
}
#else
static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
return swp_entry(0, 0);
}
static inline int is_hwpoison_entry(swp_entry_t swp)
{
return 0;
}
#endif
#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
static inline int non_swap_entry(swp_entry_t entry)
{
return swp_type(entry) >= MAX_SWAPFILES;
}
#else
static inline int non_swap_entry(swp_entry_t entry)
{
return 0;
}
#endif
#endif /* _LINUX_SWAPOPS_H */