mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 17:21:55 +07:00
d483da5bc7
It doesn't make much sense to use the atomic SetPageReserved at init time
when we are using memset to clear the memory and manipulating the page
flags via simple "&=" and "|=" operations in __init_single_page.
This patch adds a non-atomic version __SetPageReserved that can be used
during page init and shows about a 10% improvement in initialization times
on the systems I have available for testing. On those systems I saw
initialization times drop from around 35 seconds to around 32 seconds to
initialize a 3TB block of persistent memory. I believe the main advantage
of this is that it allows for more compiler optimization as the __set_bit
operation can be reordered whereas the atomic version cannot.
I tried adding a bit of documentation based on f1dd2cd13c
("mm,
memory_hotplug: do not associate hotadded memory to zones until online").
Ideally the reserved flag should be set earlier since there is a brief
window where the page is initialization via __init_single_page and we have
not set the PG_Reserved flag. I'm leaving that for a future patch set as
that will require a more significant refactor.
Link: http://lkml.kernel.org/r/20180925202018.3576.11607.stgit@localhost.localdomain
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
801 lines
24 KiB
C
801 lines
24 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Macros for manipulating and testing page->flags
|
|
*/
|
|
|
|
#ifndef PAGE_FLAGS_H
|
|
#define PAGE_FLAGS_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/mmdebug.h>
|
|
#ifndef __GENERATING_BOUNDS_H
|
|
#include <linux/mm_types.h>
|
|
#include <generated/bounds.h>
|
|
#endif /* !__GENERATING_BOUNDS_H */
|
|
|
|
/*
|
|
* Various page->flags bits:
|
|
*
|
|
* PG_reserved is set for special pages, which can never be swapped out. Some
|
|
* of them might not even exist...
|
|
*
|
|
* The PG_private bitflag is set on pagecache pages if they contain filesystem
|
|
* specific data (which is normally at page->private). It can be used by
|
|
* private allocations for its own usage.
|
|
*
|
|
* During initiation of disk I/O, PG_locked is set. This bit is set before I/O
|
|
* and cleared when writeback _starts_ or when read _completes_. PG_writeback
|
|
* is set before writeback starts and cleared when it finishes.
|
|
*
|
|
* PG_locked also pins a page in pagecache, and blocks truncation of the file
|
|
* while it is held.
|
|
*
|
|
* page_waitqueue(page) is a wait queue of all tasks waiting for the page
|
|
* to become unlocked.
|
|
*
|
|
* PG_uptodate tells whether the page's contents is valid. When a read
|
|
* completes, the page becomes uptodate, unless a disk I/O error happened.
|
|
*
|
|
* PG_referenced, PG_reclaim are used for page reclaim for anonymous and
|
|
* file-backed pagecache (see mm/vmscan.c).
|
|
*
|
|
* PG_error is set to indicate that an I/O error occurred on this page.
|
|
*
|
|
* PG_arch_1 is an architecture specific page state bit. The generic code
|
|
* guarantees that this bit is cleared for a page when it first is entered into
|
|
* the page cache.
|
|
*
|
|
* PG_hwpoison indicates that a page got corrupted in hardware and contains
|
|
* data with incorrect ECC bits that triggered a machine check. Accessing is
|
|
* not safe since it may cause another machine check. Don't touch!
|
|
*/
|
|
|
|
/*
|
|
* Don't use the *_dontuse flags. Use the macros. Otherwise you'll break
|
|
* locked- and dirty-page accounting.
|
|
*
|
|
* The page flags field is split into two parts, the main flags area
|
|
* which extends from the low bits upwards, and the fields area which
|
|
* extends from the high bits downwards.
|
|
*
|
|
* | FIELD | ... | FLAGS |
|
|
* N-1 ^ 0
|
|
* (NR_PAGEFLAGS)
|
|
*
|
|
* The fields area is reserved for fields mapping zone, node (for NUMA) and
|
|
* SPARSEMEM section (for variants of SPARSEMEM that require section ids like
|
|
* SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP).
|
|
*/
|
|
enum pageflags {
|
|
PG_locked, /* Page is locked. Don't touch. */
|
|
PG_referenced,
|
|
PG_uptodate,
|
|
PG_dirty,
|
|
PG_lru,
|
|
PG_active,
|
|
PG_workingset,
|
|
PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
|
|
PG_error,
|
|
PG_slab,
|
|
PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/
|
|
PG_arch_1,
|
|
PG_reserved,
|
|
PG_private, /* If pagecache, has fs-private data */
|
|
PG_private_2, /* If pagecache, has fs aux data */
|
|
PG_writeback, /* Page is under writeback */
|
|
PG_head, /* A head page */
|
|
PG_mappedtodisk, /* Has blocks allocated on-disk */
|
|
PG_reclaim, /* To be reclaimed asap */
|
|
PG_swapbacked, /* Page is backed by RAM/swap */
|
|
PG_unevictable, /* Page is "unevictable" */
|
|
#ifdef CONFIG_MMU
|
|
PG_mlocked, /* Page is vma mlocked */
|
|
#endif
|
|
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
|
|
PG_uncached, /* Page has been mapped as uncached */
|
|
#endif
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
PG_hwpoison, /* hardware poisoned page. Don't touch */
|
|
#endif
|
|
#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
|
|
PG_young,
|
|
PG_idle,
|
|
#endif
|
|
__NR_PAGEFLAGS,
|
|
|
|
/* Filesystems */
|
|
PG_checked = PG_owner_priv_1,
|
|
|
|
/* SwapBacked */
|
|
PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */
|
|
|
|
/* Two page bits are conscripted by FS-Cache to maintain local caching
|
|
* state. These bits are set on pages belonging to the netfs's inodes
|
|
* when those inodes are being locally cached.
|
|
*/
|
|
PG_fscache = PG_private_2, /* page backed by cache */
|
|
|
|
/* XEN */
|
|
/* Pinned in Xen as a read-only pagetable page. */
|
|
PG_pinned = PG_owner_priv_1,
|
|
/* Pinned as part of domain save (see xen_mm_pin_all()). */
|
|
PG_savepinned = PG_dirty,
|
|
/* Has a grant mapping of another (foreign) domain's page. */
|
|
PG_foreign = PG_owner_priv_1,
|
|
|
|
/* SLOB */
|
|
PG_slob_free = PG_private,
|
|
|
|
/* Compound pages. Stored in first tail page's flags */
|
|
PG_double_map = PG_private_2,
|
|
|
|
/* non-lru isolated movable page */
|
|
PG_isolated = PG_reclaim,
|
|
};
|
|
|
|
#ifndef __GENERATING_BOUNDS_H
|
|
|
|
struct page; /* forward declaration */
|
|
|
|
static inline struct page *compound_head(struct page *page)
|
|
{
|
|
unsigned long head = READ_ONCE(page->compound_head);
|
|
|
|
if (unlikely(head & 1))
|
|
return (struct page *) (head - 1);
|
|
return page;
|
|
}
|
|
|
|
static __always_inline int PageTail(struct page *page)
|
|
{
|
|
return READ_ONCE(page->compound_head) & 1;
|
|
}
|
|
|
|
static __always_inline int PageCompound(struct page *page)
|
|
{
|
|
return test_bit(PG_head, &page->flags) || PageTail(page);
|
|
}
|
|
|
|
#define PAGE_POISON_PATTERN -1l
|
|
static inline int PagePoisoned(const struct page *page)
|
|
{
|
|
return page->flags == PAGE_POISON_PATTERN;
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
void page_init_poison(struct page *page, size_t size);
|
|
#else
|
|
static inline void page_init_poison(struct page *page, size_t size)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Page flags policies wrt compound pages
|
|
*
|
|
* PF_POISONED_CHECK
|
|
* check if this struct page poisoned/uninitialized
|
|
*
|
|
* PF_ANY:
|
|
* the page flag is relevant for small, head and tail pages.
|
|
*
|
|
* PF_HEAD:
|
|
* for compound page all operations related to the page flag applied to
|
|
* head page.
|
|
*
|
|
* PF_ONLY_HEAD:
|
|
* for compound page, callers only ever operate on the head page.
|
|
*
|
|
* PF_NO_TAIL:
|
|
* modifications of the page flag must be done on small or head pages,
|
|
* checks can be done on tail pages too.
|
|
*
|
|
* PF_NO_COMPOUND:
|
|
* the page flag is not relevant for compound pages.
|
|
*/
|
|
#define PF_POISONED_CHECK(page) ({ \
|
|
VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \
|
|
page; })
|
|
#define PF_ANY(page, enforce) PF_POISONED_CHECK(page)
|
|
#define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page))
|
|
#define PF_ONLY_HEAD(page, enforce) ({ \
|
|
VM_BUG_ON_PGFLAGS(PageTail(page), page); \
|
|
PF_POISONED_CHECK(page); })
|
|
#define PF_NO_TAIL(page, enforce) ({ \
|
|
VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \
|
|
PF_POISONED_CHECK(compound_head(page)); })
|
|
#define PF_NO_COMPOUND(page, enforce) ({ \
|
|
VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \
|
|
PF_POISONED_CHECK(page); })
|
|
|
|
/*
|
|
* Macros to create function definitions for page flags
|
|
*/
|
|
#define TESTPAGEFLAG(uname, lname, policy) \
|
|
static __always_inline int Page##uname(struct page *page) \
|
|
{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
|
|
|
|
#define SETPAGEFLAG(uname, lname, policy) \
|
|
static __always_inline void SetPage##uname(struct page *page) \
|
|
{ set_bit(PG_##lname, &policy(page, 1)->flags); }
|
|
|
|
#define CLEARPAGEFLAG(uname, lname, policy) \
|
|
static __always_inline void ClearPage##uname(struct page *page) \
|
|
{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
|
|
|
|
#define __SETPAGEFLAG(uname, lname, policy) \
|
|
static __always_inline void __SetPage##uname(struct page *page) \
|
|
{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
|
|
|
|
#define __CLEARPAGEFLAG(uname, lname, policy) \
|
|
static __always_inline void __ClearPage##uname(struct page *page) \
|
|
{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
|
|
|
|
#define TESTSETFLAG(uname, lname, policy) \
|
|
static __always_inline int TestSetPage##uname(struct page *page) \
|
|
{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
|
|
|
|
#define TESTCLEARFLAG(uname, lname, policy) \
|
|
static __always_inline int TestClearPage##uname(struct page *page) \
|
|
{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
|
|
|
|
#define PAGEFLAG(uname, lname, policy) \
|
|
TESTPAGEFLAG(uname, lname, policy) \
|
|
SETPAGEFLAG(uname, lname, policy) \
|
|
CLEARPAGEFLAG(uname, lname, policy)
|
|
|
|
#define __PAGEFLAG(uname, lname, policy) \
|
|
TESTPAGEFLAG(uname, lname, policy) \
|
|
__SETPAGEFLAG(uname, lname, policy) \
|
|
__CLEARPAGEFLAG(uname, lname, policy)
|
|
|
|
#define TESTSCFLAG(uname, lname, policy) \
|
|
TESTSETFLAG(uname, lname, policy) \
|
|
TESTCLEARFLAG(uname, lname, policy)
|
|
|
|
#define TESTPAGEFLAG_FALSE(uname) \
|
|
static inline int Page##uname(const struct page *page) { return 0; }
|
|
|
|
#define SETPAGEFLAG_NOOP(uname) \
|
|
static inline void SetPage##uname(struct page *page) { }
|
|
|
|
#define CLEARPAGEFLAG_NOOP(uname) \
|
|
static inline void ClearPage##uname(struct page *page) { }
|
|
|
|
#define __CLEARPAGEFLAG_NOOP(uname) \
|
|
static inline void __ClearPage##uname(struct page *page) { }
|
|
|
|
#define TESTSETFLAG_FALSE(uname) \
|
|
static inline int TestSetPage##uname(struct page *page) { return 0; }
|
|
|
|
#define TESTCLEARFLAG_FALSE(uname) \
|
|
static inline int TestClearPage##uname(struct page *page) { return 0; }
|
|
|
|
#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \
|
|
SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname)
|
|
|
|
#define TESTSCFLAG_FALSE(uname) \
|
|
TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
|
|
|
|
__PAGEFLAG(Locked, locked, PF_NO_TAIL)
|
|
PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
|
|
PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
|
|
PAGEFLAG(Referenced, referenced, PF_HEAD)
|
|
TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
|
|
__SETPAGEFLAG(Referenced, referenced, PF_HEAD)
|
|
PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
|
|
__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
|
|
PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
|
|
PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
|
|
TESTCLEARFLAG(Active, active, PF_HEAD)
|
|
PAGEFLAG(Workingset, workingset, PF_HEAD)
|
|
TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
|
|
__PAGEFLAG(Slab, slab, PF_NO_TAIL)
|
|
__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
|
|
PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
|
|
|
|
/* Xen */
|
|
PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND)
|
|
TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND)
|
|
PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND);
|
|
PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND);
|
|
|
|
PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
|
|
__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
|
|
__SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
|
|
PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
|
|
__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
|
|
__SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
|
|
|
|
/*
|
|
* Private page markings that may be used by the filesystem that owns the page
|
|
* for its own purposes.
|
|
* - PG_private and PG_private_2 cause releasepage() and co to be invoked
|
|
*/
|
|
PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY)
|
|
__CLEARPAGEFLAG(Private, private, PF_ANY)
|
|
PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
|
|
PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
|
|
TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
|
|
|
|
/*
|
|
* Only test-and-set exist for PG_writeback. The unconditional operators are
|
|
* risky: they bypass page accounting.
|
|
*/
|
|
TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL)
|
|
TESTSCFLAG(Writeback, writeback, PF_NO_TAIL)
|
|
PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL)
|
|
|
|
/* PG_readahead is only used for reads; PG_reclaim is only for writes */
|
|
PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
|
|
TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL)
|
|
PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
|
|
TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND)
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
/*
|
|
* Must use a macro here due to header dependency issues. page_zone() is not
|
|
* available at this point.
|
|
*/
|
|
#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p))
|
|
#else
|
|
PAGEFLAG_FALSE(HighMem)
|
|
#endif
|
|
|
|
#ifdef CONFIG_SWAP
|
|
static __always_inline int PageSwapCache(struct page *page)
|
|
{
|
|
#ifdef CONFIG_THP_SWAP
|
|
page = compound_head(page);
|
|
#endif
|
|
return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
|
|
|
|
}
|
|
SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
|
|
CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
|
|
#else
|
|
PAGEFLAG_FALSE(SwapCache)
|
|
#endif
|
|
|
|
PAGEFLAG(Unevictable, unevictable, PF_HEAD)
|
|
__CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD)
|
|
TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD)
|
|
|
|
#ifdef CONFIG_MMU
|
|
PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
|
|
__CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
|
|
TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
|
|
#else
|
|
PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
|
|
TESTSCFLAG_FALSE(Mlocked)
|
|
#endif
|
|
|
|
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
|
|
PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
|
|
#else
|
|
PAGEFLAG_FALSE(Uncached)
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
PAGEFLAG(HWPoison, hwpoison, PF_ANY)
|
|
TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
|
|
#define __PG_HWPOISON (1UL << PG_hwpoison)
|
|
extern bool set_hwpoison_free_buddy_page(struct page *page);
|
|
#else
|
|
PAGEFLAG_FALSE(HWPoison)
|
|
static inline bool set_hwpoison_free_buddy_page(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
#define __PG_HWPOISON 0
|
|
#endif
|
|
|
|
#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
|
|
TESTPAGEFLAG(Young, young, PF_ANY)
|
|
SETPAGEFLAG(Young, young, PF_ANY)
|
|
TESTCLEARFLAG(Young, young, PF_ANY)
|
|
PAGEFLAG(Idle, idle, PF_ANY)
|
|
#endif
|
|
|
|
/*
|
|
* On an anonymous page mapped into a user virtual memory area,
|
|
* page->mapping points to its anon_vma, not to a struct address_space;
|
|
* with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h.
|
|
*
|
|
* On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
|
|
* the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON
|
|
* bit; and then page->mapping points, not to an anon_vma, but to a private
|
|
* structure which KSM associates with that merged page. See ksm.h.
|
|
*
|
|
* PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable
|
|
* page and then page->mapping points a struct address_space.
|
|
*
|
|
* Please note that, confusingly, "page_mapping" refers to the inode
|
|
* address_space which maps the page from disk; whereas "page_mapped"
|
|
* refers to user virtual address space into which the page is mapped.
|
|
*/
|
|
#define PAGE_MAPPING_ANON 0x1
|
|
#define PAGE_MAPPING_MOVABLE 0x2
|
|
#define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
|
|
#define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
|
|
|
|
static __always_inline int PageMappingFlags(struct page *page)
|
|
{
|
|
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
|
|
}
|
|
|
|
static __always_inline int PageAnon(struct page *page)
|
|
{
|
|
page = compound_head(page);
|
|
return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
|
|
}
|
|
|
|
static __always_inline int __PageMovable(struct page *page)
|
|
{
|
|
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
|
|
PAGE_MAPPING_MOVABLE;
|
|
}
|
|
|
|
#ifdef CONFIG_KSM
|
|
/*
|
|
* A KSM page is one of those write-protected "shared pages" or "merged pages"
|
|
* which KSM maps into multiple mms, wherever identical anonymous page content
|
|
* is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any
|
|
* anon_vma, but to that page's node of the stable tree.
|
|
*/
|
|
static __always_inline int PageKsm(struct page *page)
|
|
{
|
|
page = compound_head(page);
|
|
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
|
|
PAGE_MAPPING_KSM;
|
|
}
|
|
#else
|
|
TESTPAGEFLAG_FALSE(Ksm)
|
|
#endif
|
|
|
|
u64 stable_page_flags(struct page *page);
|
|
|
|
static inline int PageUptodate(struct page *page)
|
|
{
|
|
int ret;
|
|
page = compound_head(page);
|
|
ret = test_bit(PG_uptodate, &(page)->flags);
|
|
/*
|
|
* Must ensure that the data we read out of the page is loaded
|
|
* _after_ we've loaded page->flags to check for PageUptodate.
|
|
* We can skip the barrier if the page is not uptodate, because
|
|
* we wouldn't be reading anything from it.
|
|
*
|
|
* See SetPageUptodate() for the other side of the story.
|
|
*/
|
|
if (ret)
|
|
smp_rmb();
|
|
|
|
return ret;
|
|
}
|
|
|
|
static __always_inline void __SetPageUptodate(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
|
smp_wmb();
|
|
__set_bit(PG_uptodate, &page->flags);
|
|
}
|
|
|
|
static __always_inline void SetPageUptodate(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
|
/*
|
|
* Memory barrier must be issued before setting the PG_uptodate bit,
|
|
* so that all previous stores issued in order to bring the page
|
|
* uptodate are actually visible before PageUptodate becomes true.
|
|
*/
|
|
smp_wmb();
|
|
set_bit(PG_uptodate, &page->flags);
|
|
}
|
|
|
|
CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
|
|
|
|
int test_clear_page_writeback(struct page *page);
|
|
int __test_set_page_writeback(struct page *page, bool keep_write);
|
|
|
|
#define test_set_page_writeback(page) \
|
|
__test_set_page_writeback(page, false)
|
|
#define test_set_page_writeback_keepwrite(page) \
|
|
__test_set_page_writeback(page, true)
|
|
|
|
static inline void set_page_writeback(struct page *page)
|
|
{
|
|
test_set_page_writeback(page);
|
|
}
|
|
|
|
static inline void set_page_writeback_keepwrite(struct page *page)
|
|
{
|
|
test_set_page_writeback_keepwrite(page);
|
|
}
|
|
|
|
__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
|
|
|
|
static __always_inline void set_compound_head(struct page *page, struct page *head)
|
|
{
|
|
WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
|
|
}
|
|
|
|
static __always_inline void clear_compound_head(struct page *page)
|
|
{
|
|
WRITE_ONCE(page->compound_head, 0);
|
|
}
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
static inline void ClearPageCompound(struct page *page)
|
|
{
|
|
BUG_ON(!PageHead(page));
|
|
ClearPageHead(page);
|
|
}
|
|
#endif
|
|
|
|
#define PG_head_mask ((1UL << PG_head))
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
int PageHuge(struct page *page);
|
|
int PageHeadHuge(struct page *page);
|
|
bool page_huge_active(struct page *page);
|
|
#else
|
|
TESTPAGEFLAG_FALSE(Huge)
|
|
TESTPAGEFLAG_FALSE(HeadHuge)
|
|
|
|
static inline bool page_huge_active(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
/*
|
|
* PageHuge() only returns true for hugetlbfs pages, but not for
|
|
* normal or transparent huge pages.
|
|
*
|
|
* PageTransHuge() returns true for both transparent huge and
|
|
* hugetlbfs pages, but not normal pages. PageTransHuge() can only be
|
|
* called only in the core VM paths where hugetlbfs pages can't exist.
|
|
*/
|
|
static inline int PageTransHuge(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
|
return PageHead(page);
|
|
}
|
|
|
|
/*
|
|
* PageTransCompound returns true for both transparent huge pages
|
|
* and hugetlbfs pages, so it should only be called when it's known
|
|
* that hugetlbfs pages aren't involved.
|
|
*/
|
|
static inline int PageTransCompound(struct page *page)
|
|
{
|
|
return PageCompound(page);
|
|
}
|
|
|
|
/*
|
|
* PageTransCompoundMap is the same as PageTransCompound, but it also
|
|
* guarantees the primary MMU has the entire compound page mapped
|
|
* through pmd_trans_huge, which in turn guarantees the secondary MMUs
|
|
* can also map the entire compound page. This allows the secondary
|
|
* MMUs to call get_user_pages() only once for each compound page and
|
|
* to immediately map the entire compound page with a single secondary
|
|
* MMU fault. If there will be a pmd split later, the secondary MMUs
|
|
* will get an update through the MMU notifier invalidation through
|
|
* split_huge_pmd().
|
|
*
|
|
* Unlike PageTransCompound, this is safe to be called only while
|
|
* split_huge_pmd() cannot run from under us, like if protected by the
|
|
* MMU notifier, otherwise it may result in page->_mapcount < 0 false
|
|
* positives.
|
|
*/
|
|
static inline int PageTransCompoundMap(struct page *page)
|
|
{
|
|
return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0;
|
|
}
|
|
|
|
/*
|
|
* PageTransTail returns true for both transparent huge pages
|
|
* and hugetlbfs pages, so it should only be called when it's known
|
|
* that hugetlbfs pages aren't involved.
|
|
*/
|
|
static inline int PageTransTail(struct page *page)
|
|
{
|
|
return PageTail(page);
|
|
}
|
|
|
|
/*
|
|
* PageDoubleMap indicates that the compound page is mapped with PTEs as well
|
|
* as PMDs.
|
|
*
|
|
* This is required for optimization of rmap operations for THP: we can postpone
|
|
* per small page mapcount accounting (and its overhead from atomic operations)
|
|
* until the first PMD split.
|
|
*
|
|
* For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up
|
|
* by one. This reference will go away with last compound_mapcount.
|
|
*
|
|
* See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap().
|
|
*/
|
|
static inline int PageDoubleMap(struct page *page)
|
|
{
|
|
return PageHead(page) && test_bit(PG_double_map, &page[1].flags);
|
|
}
|
|
|
|
static inline void SetPageDoubleMap(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
set_bit(PG_double_map, &page[1].flags);
|
|
}
|
|
|
|
static inline void ClearPageDoubleMap(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
clear_bit(PG_double_map, &page[1].flags);
|
|
}
|
|
static inline int TestSetPageDoubleMap(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
return test_and_set_bit(PG_double_map, &page[1].flags);
|
|
}
|
|
|
|
static inline int TestClearPageDoubleMap(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
return test_and_clear_bit(PG_double_map, &page[1].flags);
|
|
}
|
|
|
|
#else
|
|
TESTPAGEFLAG_FALSE(TransHuge)
|
|
TESTPAGEFLAG_FALSE(TransCompound)
|
|
TESTPAGEFLAG_FALSE(TransCompoundMap)
|
|
TESTPAGEFLAG_FALSE(TransTail)
|
|
PAGEFLAG_FALSE(DoubleMap)
|
|
TESTSETFLAG_FALSE(DoubleMap)
|
|
TESTCLEARFLAG_FALSE(DoubleMap)
|
|
#endif
|
|
|
|
/*
|
|
* For pages that are never mapped to userspace (and aren't PageSlab),
|
|
* page_type may be used. Because it is initialised to -1, we invert the
|
|
* sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and
|
|
* __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and
|
|
* low bits so that an underflow or overflow of page_mapcount() won't be
|
|
* mistaken for a page type value.
|
|
*/
|
|
|
|
#define PAGE_TYPE_BASE 0xf0000000
|
|
/* Reserve 0x0000007f to catch underflows of page_mapcount */
|
|
#define PG_buddy 0x00000080
|
|
#define PG_balloon 0x00000100
|
|
#define PG_kmemcg 0x00000200
|
|
#define PG_table 0x00000400
|
|
|
|
#define PageType(page, flag) \
|
|
((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
|
|
|
|
#define PAGE_TYPE_OPS(uname, lname) \
|
|
static __always_inline int Page##uname(struct page *page) \
|
|
{ \
|
|
return PageType(page, PG_##lname); \
|
|
} \
|
|
static __always_inline void __SetPage##uname(struct page *page) \
|
|
{ \
|
|
VM_BUG_ON_PAGE(!PageType(page, 0), page); \
|
|
page->page_type &= ~PG_##lname; \
|
|
} \
|
|
static __always_inline void __ClearPage##uname(struct page *page) \
|
|
{ \
|
|
VM_BUG_ON_PAGE(!Page##uname(page), page); \
|
|
page->page_type |= PG_##lname; \
|
|
}
|
|
|
|
/*
|
|
* PageBuddy() indicates that the page is free and in the buddy system
|
|
* (see mm/page_alloc.c).
|
|
*/
|
|
PAGE_TYPE_OPS(Buddy, buddy)
|
|
|
|
/*
|
|
* PageBalloon() is true for pages that are on the balloon page list
|
|
* (see mm/balloon_compaction.c).
|
|
*/
|
|
PAGE_TYPE_OPS(Balloon, balloon)
|
|
|
|
/*
|
|
* If kmemcg is enabled, the buddy allocator will set PageKmemcg() on
|
|
* pages allocated with __GFP_ACCOUNT. It gets cleared on page free.
|
|
*/
|
|
PAGE_TYPE_OPS(Kmemcg, kmemcg)
|
|
|
|
/*
|
|
* Marks pages in use as page tables.
|
|
*/
|
|
PAGE_TYPE_OPS(Table, table)
|
|
|
|
extern bool is_free_buddy_page(struct page *page);
|
|
|
|
__PAGEFLAG(Isolated, isolated, PF_ANY);
|
|
|
|
/*
|
|
* If network-based swap is enabled, sl*b must keep track of whether pages
|
|
* were allocated from pfmemalloc reserves.
|
|
*/
|
|
static inline int PageSlabPfmemalloc(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
|
return PageActive(page);
|
|
}
|
|
|
|
static inline void SetPageSlabPfmemalloc(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
|
SetPageActive(page);
|
|
}
|
|
|
|
static inline void __ClearPageSlabPfmemalloc(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
|
__ClearPageActive(page);
|
|
}
|
|
|
|
static inline void ClearPageSlabPfmemalloc(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
|
ClearPageActive(page);
|
|
}
|
|
|
|
#ifdef CONFIG_MMU
|
|
#define __PG_MLOCKED (1UL << PG_mlocked)
|
|
#else
|
|
#define __PG_MLOCKED 0
|
|
#endif
|
|
|
|
/*
|
|
* Flags checked when a page is freed. Pages being freed should not have
|
|
* these flags set. It they are, there is a problem.
|
|
*/
|
|
#define PAGE_FLAGS_CHECK_AT_FREE \
|
|
(1UL << PG_lru | 1UL << PG_locked | \
|
|
1UL << PG_private | 1UL << PG_private_2 | \
|
|
1UL << PG_writeback | 1UL << PG_reserved | \
|
|
1UL << PG_slab | 1UL << PG_active | \
|
|
1UL << PG_unevictable | __PG_MLOCKED)
|
|
|
|
/*
|
|
* Flags checked when a page is prepped for return by the page allocator.
|
|
* Pages being prepped should not have these flags set. It they are set,
|
|
* there has been a kernel bug or struct page corruption.
|
|
*
|
|
* __PG_HWPOISON is exceptional because it needs to be kept beyond page's
|
|
* alloc-free cycle to prevent from reusing the page.
|
|
*/
|
|
#define PAGE_FLAGS_CHECK_AT_PREP \
|
|
(((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
|
|
|
|
#define PAGE_FLAGS_PRIVATE \
|
|
(1UL << PG_private | 1UL << PG_private_2)
|
|
/**
|
|
* page_has_private - Determine if page has private stuff
|
|
* @page: The page to be checked
|
|
*
|
|
* Determine if a page has private stuff, indicating that release routines
|
|
* should be invoked upon it.
|
|
*/
|
|
static inline int page_has_private(struct page *page)
|
|
{
|
|
return !!(page->flags & PAGE_FLAGS_PRIVATE);
|
|
}
|
|
|
|
#undef PF_ANY
|
|
#undef PF_HEAD
|
|
#undef PF_ONLY_HEAD
|
|
#undef PF_NO_TAIL
|
|
#undef PF_NO_COMPOUND
|
|
#endif /* !__GENERATING_BOUNDS_H */
|
|
|
|
#endif /* PAGE_FLAGS_H */
|