mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 10:29:37 +00:00
![Hugh Dickins](/assets/img/avatar_default.png)
Minchan Kim reports that when a system has many swap areas, and tmpfs swaps out to the ninth or more, shmem_getpage_gfp()'s attempts to read back the page cannot locate it, and the read fails with -ENOMEM. Whoops. Yes, I blindly followed read_swap_header()'s pte_to_swp_entry( swp_entry_to_pte()) technique for determining maximum usable swap offset, without stopping to realize that that actually depends upon the pte swap encoding shifting swap offset to the higher bits and truncating it there. Whereas our radix_tree swap encoding leaves offset in the lower bits: it's swap "type" (that is, index of swap area) that was truncated. Fix it by reducing the SWP_TYPE_SHIFT() in swapops.h, and removing the broken radix_to_swp_entry(swp_to_radix_entry()) from read_swap_header(). This does not reduce the usable size of a swap area any further, it leaves it as claimed when making the original commit: no change from 3.0 on x86_64, nor on i386 without PAE; but 3.0's 512GB is reduced to 128GB per swapfile on i386 with PAE. It's not a change I would have risked five years ago, but with x86_64 supported for ten years, I believe it's appropriate now. Hmm, and what if some architecture implements its swap pte with offset encoded below type? That would equally break the maximum usable swap offset check. Happily, they all follow the same tradition of encoding offset above type, but I'll prepare a check on that for next. Reported-and-Reviewed-and-Tested-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: stable@vger.kernel.org [3.1, 3.2, 3.3, 3.4] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
197 lines
4.9 KiB
C
197 lines
4.9 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) && !pte_file(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;
|
|
|
|
BUG_ON(pte_file(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));
|
|
BUG_ON(pte_file(__swp_entry_to_pte(arch_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, pmd_t *pmd,
|
|
unsigned long address);
|
|
#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, pmd_t *pmd,
|
|
unsigned long address) { }
|
|
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 */
|