mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
-----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJZXhmCAAoJEAAOaEEZVoIVpRkP/1qlYn3pq6d5Kuz84pejOmlL 5jbkS/cOmeTxeUU4+B1xG8Lx7bAk8PfSXQOADbSJGiZd0ug95tJxplFYIGJzR/tG aNMHeu/BVKKhUKORGuKR9rJKtwC839L/qao+yPBo5U3mU4L73rFWX8fxFuhSJ8HR hvkgBu3Hx6GY59CzxJ8iJzj+B+uPSFrNweAk0+0UeWkBgTzEdiGqaXBX4cHIkq/5 hMoCG+xnmwHKbCBsQ5js+YJT+HedZ4lvfjOqGxgElUyjJ7Bkt/IFYOp8TUiu193T tA4UinDjN8A7FImmIBIftrECmrAC9HIGhGZroYkMKbb8ReDR2ikE5FhKEpuAGU3a BXBgX2mPQuArvZWM7qeJCkxV9QJ0u/8Ykbyzo30iPrICyrzbEvIubeB/mDA034+Z Z0/z8C3v7826F3zP/NyaQEojUgRq30McMOIS8GMnx15HJwRsRKlzjfy9Wm4tWhl0 t3nH1jMqAZ7068s6rfh/oCwdgGOwr5o4hW/bnlITzxbjWQUOnZIe7KBxIezZJ2rv OcIwd5qE8PNtpagGj5oUbnjGOTkERAgsMfvPk5tjUNt28/qUlVs2V0aeo47dlcsh oYr8WMOIzw98Rl7Bo70mplLrqLD6nGl0LfXOyUlT4STgLWW4ksmLVuJjWIUxcO/0 yKWjj9wfYRQ0vSUqhsI5 =3Z93 -----END PGP SIGNATURE----- Merge tag 'for-linus-v4.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux Pull Writeback error handling updates from Jeff Layton: "This pile represents the bulk of the writeback error handling fixes that I have for this cycle. Some of the earlier patches in this pile may look trivial but they are prerequisites for later patches in the series. The aim of this set is to improve how we track and report writeback errors to userland. Most applications that care about data integrity will periodically call fsync/fdatasync/msync to ensure that their writes have made it to the backing store. For a very long time, we have tracked writeback errors using two flags in the address_space: AS_EIO and AS_ENOSPC. Those flags are set when a writeback error occurs (via mapping_set_error) and are cleared as a side-effect of filemap_check_errors (as you noted yesterday). This model really sucks for userland. Only the first task to call fsync (or msync or fdatasync) will see the error. Any subsequent task calling fsync on a file will get back 0 (unless another writeback error occurs in the interim). If I have several tasks writing to a file and calling fsync to ensure that their writes got stored, then I need to have them coordinate with one another. That's difficult enough, but in a world of containerized setups that coordination may even not be possible. But wait...it gets worse! The calls to filemap_check_errors can be buried pretty far down in the call stack, and there are internal callers of filemap_write_and_wait and the like that also end up clearing those errors. Many of those callers ignore the error return from that function or return it to userland at nonsensical times (e.g. truncate() or stat()). If I get back -EIO on a truncate, there is no reason to think that it was because some previous writeback failed, and a subsequent fsync() will (incorrectly) return 0. This pile aims to do three things: 1) ensure that when a writeback error occurs that that error will be reported to userland on a subsequent fsync/fdatasync/msync call, regardless of what internal callers are doing 2) report writeback errors on all file descriptions that were open at the time that the error occurred. This is a user-visible change, but I think most applications are written to assume this behavior anyway. Those that aren't are unlikely to be hurt by it. 3) document what filesystems should do when there is a writeback error. Today, there is very little consistency between them, and a lot of cargo-cult copying. We need to make it very clear what filesystems should do in this situation. To achieve this, the set adds a new data type (errseq_t) and then builds new writeback error tracking infrastructure around that. Once all of that is in place, we change the filesystems to use the new infrastructure for reporting wb errors to userland. Note that this is just the initial foray into cleaning up this mess. There is a lot of work remaining here: 1) convert the rest of the filesystems in a similar fashion. Once the initial set is in, then I think most other fs' will be fairly simple to convert. Hopefully most of those can in via individual filesystem trees. 2) convert internal waiters on writeback to use errseq_t for detecting errors instead of relying on the AS_* flags. I have some draft patches for this for ext4, but they are not quite ready for prime time yet. This was a discussion topic this year at LSF/MM too. If you're interested in the gory details, LWN has some good articles about this: https://lwn.net/Articles/718734/ https://lwn.net/Articles/724307/" * tag 'for-linus-v4.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux: btrfs: minimal conversion to errseq_t writeback error reporting on fsync xfs: minimal conversion to errseq_t writeback error reporting ext4: use errseq_t based error handling for reporting data writeback errors fs: convert __generic_file_fsync to use errseq_t based reporting block: convert to errseq_t based writeback error tracking dax: set errors in mapping when writeback fails Documentation: flesh out the section in vfs.txt on storing and reporting writeback errors mm: set both AS_EIO/AS_ENOSPC and errseq_t in mapping_set_error fs: new infrastructure for writeback error handling and reporting lib: add errseq_t type and infrastructure for handling it mm: don't TestClearPageError in __filemap_fdatawait_range mm: clear AS_EIO/AS_ENOSPC when writeback initiation fails jbd2: don't clear and reset errors after waiting on writeback buffer: set errors in mapping at the time that the error occurs fs: check for writeback errors after syncing out buffers in generic_file_fsync buffer: use mapping_set_error instead of setting the flag mm: fix mapping_set_error call in me_pagecache_dirty
635 lines
18 KiB
C
635 lines
18 KiB
C
#ifndef _LINUX_PAGEMAP_H
|
|
#define _LINUX_PAGEMAP_H
|
|
|
|
/*
|
|
* Copyright 1995 Linus Torvalds
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/list.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/hardirq.h> /* for in_interrupt() */
|
|
#include <linux/hugetlb_inline.h>
|
|
|
|
/*
|
|
* Bits in mapping->flags.
|
|
*/
|
|
enum mapping_flags {
|
|
AS_EIO = 0, /* IO error on async write */
|
|
AS_ENOSPC = 1, /* ENOSPC on async write */
|
|
AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */
|
|
AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */
|
|
AS_EXITING = 4, /* final truncate in progress */
|
|
/* writeback related tags are not used */
|
|
AS_NO_WRITEBACK_TAGS = 5,
|
|
};
|
|
|
|
/**
|
|
* mapping_set_error - record a writeback error in the address_space
|
|
* @mapping - the mapping in which an error should be set
|
|
* @error - the error to set in the mapping
|
|
*
|
|
* When writeback fails in some way, we must record that error so that
|
|
* userspace can be informed when fsync and the like are called. We endeavor
|
|
* to report errors on any file that was open at the time of the error. Some
|
|
* internal callers also need to know when writeback errors have occurred.
|
|
*
|
|
* When a writeback error occurs, most filesystems will want to call
|
|
* mapping_set_error to record the error in the mapping so that it can be
|
|
* reported when the application calls fsync(2).
|
|
*/
|
|
static inline void mapping_set_error(struct address_space *mapping, int error)
|
|
{
|
|
if (likely(!error))
|
|
return;
|
|
|
|
/* Record in wb_err for checkers using errseq_t based tracking */
|
|
filemap_set_wb_err(mapping, error);
|
|
|
|
/* Record it in flags for now, for legacy callers */
|
|
if (error == -ENOSPC)
|
|
set_bit(AS_ENOSPC, &mapping->flags);
|
|
else
|
|
set_bit(AS_EIO, &mapping->flags);
|
|
}
|
|
|
|
static inline void mapping_set_unevictable(struct address_space *mapping)
|
|
{
|
|
set_bit(AS_UNEVICTABLE, &mapping->flags);
|
|
}
|
|
|
|
static inline void mapping_clear_unevictable(struct address_space *mapping)
|
|
{
|
|
clear_bit(AS_UNEVICTABLE, &mapping->flags);
|
|
}
|
|
|
|
static inline int mapping_unevictable(struct address_space *mapping)
|
|
{
|
|
if (mapping)
|
|
return test_bit(AS_UNEVICTABLE, &mapping->flags);
|
|
return !!mapping;
|
|
}
|
|
|
|
static inline void mapping_set_exiting(struct address_space *mapping)
|
|
{
|
|
set_bit(AS_EXITING, &mapping->flags);
|
|
}
|
|
|
|
static inline int mapping_exiting(struct address_space *mapping)
|
|
{
|
|
return test_bit(AS_EXITING, &mapping->flags);
|
|
}
|
|
|
|
static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
|
|
{
|
|
set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
|
|
}
|
|
|
|
static inline int mapping_use_writeback_tags(struct address_space *mapping)
|
|
{
|
|
return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
|
|
}
|
|
|
|
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
|
|
{
|
|
return mapping->gfp_mask;
|
|
}
|
|
|
|
/* Restricts the given gfp_mask to what the mapping allows. */
|
|
static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
|
|
gfp_t gfp_mask)
|
|
{
|
|
return mapping_gfp_mask(mapping) & gfp_mask;
|
|
}
|
|
|
|
/*
|
|
* This is non-atomic. Only to be used before the mapping is activated.
|
|
* Probably needs a barrier...
|
|
*/
|
|
static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
|
|
{
|
|
m->gfp_mask = mask;
|
|
}
|
|
|
|
void release_pages(struct page **pages, int nr, bool cold);
|
|
|
|
/*
|
|
* speculatively take a reference to a page.
|
|
* If the page is free (_refcount == 0), then _refcount is untouched, and 0
|
|
* is returned. Otherwise, _refcount is incremented by 1 and 1 is returned.
|
|
*
|
|
* This function must be called inside the same rcu_read_lock() section as has
|
|
* been used to lookup the page in the pagecache radix-tree (or page table):
|
|
* this allows allocators to use a synchronize_rcu() to stabilize _refcount.
|
|
*
|
|
* Unless an RCU grace period has passed, the count of all pages coming out
|
|
* of the allocator must be considered unstable. page_count may return higher
|
|
* than expected, and put_page must be able to do the right thing when the
|
|
* page has been finished with, no matter what it is subsequently allocated
|
|
* for (because put_page is what is used here to drop an invalid speculative
|
|
* reference).
|
|
*
|
|
* This is the interesting part of the lockless pagecache (and lockless
|
|
* get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
|
|
* has the following pattern:
|
|
* 1. find page in radix tree
|
|
* 2. conditionally increment refcount
|
|
* 3. check the page is still in pagecache (if no, goto 1)
|
|
*
|
|
* Remove-side that cares about stability of _refcount (eg. reclaim) has the
|
|
* following (with tree_lock held for write):
|
|
* A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
|
|
* B. remove page from pagecache
|
|
* C. free the page
|
|
*
|
|
* There are 2 critical interleavings that matter:
|
|
* - 2 runs before A: in this case, A sees elevated refcount and bails out
|
|
* - A runs before 2: in this case, 2 sees zero refcount and retries;
|
|
* subsequently, B will complete and 1 will find no page, causing the
|
|
* lookup to return NULL.
|
|
*
|
|
* It is possible that between 1 and 2, the page is removed then the exact same
|
|
* page is inserted into the same position in pagecache. That's OK: the
|
|
* old find_get_page using tree_lock could equally have run before or after
|
|
* such a re-insertion, depending on order that locks are granted.
|
|
*
|
|
* Lookups racing against pagecache insertion isn't a big problem: either 1
|
|
* will find the page or it will not. Likewise, the old find_get_page could run
|
|
* either before the insertion or afterwards, depending on timing.
|
|
*/
|
|
static inline int page_cache_get_speculative(struct page *page)
|
|
{
|
|
VM_BUG_ON(in_interrupt());
|
|
|
|
#ifdef CONFIG_TINY_RCU
|
|
# ifdef CONFIG_PREEMPT_COUNT
|
|
VM_BUG_ON(!in_atomic() && !irqs_disabled());
|
|
# endif
|
|
/*
|
|
* Preempt must be disabled here - we rely on rcu_read_lock doing
|
|
* this for us.
|
|
*
|
|
* Pagecache won't be truncated from interrupt context, so if we have
|
|
* found a page in the radix tree here, we have pinned its refcount by
|
|
* disabling preempt, and hence no need for the "speculative get" that
|
|
* SMP requires.
|
|
*/
|
|
VM_BUG_ON_PAGE(page_count(page) == 0, page);
|
|
page_ref_inc(page);
|
|
|
|
#else
|
|
if (unlikely(!get_page_unless_zero(page))) {
|
|
/*
|
|
* Either the page has been freed, or will be freed.
|
|
* In either case, retry here and the caller should
|
|
* do the right thing (see comments above).
|
|
*/
|
|
return 0;
|
|
}
|
|
#endif
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
|
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* Same as above, but add instead of inc (could just be merged)
|
|
*/
|
|
static inline int page_cache_add_speculative(struct page *page, int count)
|
|
{
|
|
VM_BUG_ON(in_interrupt());
|
|
|
|
#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
|
|
# ifdef CONFIG_PREEMPT_COUNT
|
|
VM_BUG_ON(!in_atomic() && !irqs_disabled());
|
|
# endif
|
|
VM_BUG_ON_PAGE(page_count(page) == 0, page);
|
|
page_ref_add(page, count);
|
|
|
|
#else
|
|
if (unlikely(!page_ref_add_unless(page, count, 0)))
|
|
return 0;
|
|
#endif
|
|
VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);
|
|
|
|
return 1;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern struct page *__page_cache_alloc(gfp_t gfp);
|
|
#else
|
|
static inline struct page *__page_cache_alloc(gfp_t gfp)
|
|
{
|
|
return alloc_pages(gfp, 0);
|
|
}
|
|
#endif
|
|
|
|
static inline struct page *page_cache_alloc(struct address_space *x)
|
|
{
|
|
return __page_cache_alloc(mapping_gfp_mask(x));
|
|
}
|
|
|
|
static inline struct page *page_cache_alloc_cold(struct address_space *x)
|
|
{
|
|
return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
|
|
}
|
|
|
|
static inline gfp_t readahead_gfp_mask(struct address_space *x)
|
|
{
|
|
return mapping_gfp_mask(x) |
|
|
__GFP_COLD | __GFP_NORETRY | __GFP_NOWARN;
|
|
}
|
|
|
|
typedef int filler_t(void *, struct page *);
|
|
|
|
pgoff_t page_cache_next_hole(struct address_space *mapping,
|
|
pgoff_t index, unsigned long max_scan);
|
|
pgoff_t page_cache_prev_hole(struct address_space *mapping,
|
|
pgoff_t index, unsigned long max_scan);
|
|
|
|
#define FGP_ACCESSED 0x00000001
|
|
#define FGP_LOCK 0x00000002
|
|
#define FGP_CREAT 0x00000004
|
|
#define FGP_WRITE 0x00000008
|
|
#define FGP_NOFS 0x00000010
|
|
#define FGP_NOWAIT 0x00000020
|
|
|
|
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
|
|
int fgp_flags, gfp_t cache_gfp_mask);
|
|
|
|
/**
|
|
* find_get_page - find and get a page reference
|
|
* @mapping: the address_space to search
|
|
* @offset: the page index
|
|
*
|
|
* Looks up the page cache slot at @mapping & @offset. If there is a
|
|
* page cache page, it is returned with an increased refcount.
|
|
*
|
|
* Otherwise, %NULL is returned.
|
|
*/
|
|
static inline struct page *find_get_page(struct address_space *mapping,
|
|
pgoff_t offset)
|
|
{
|
|
return pagecache_get_page(mapping, offset, 0, 0);
|
|
}
|
|
|
|
static inline struct page *find_get_page_flags(struct address_space *mapping,
|
|
pgoff_t offset, int fgp_flags)
|
|
{
|
|
return pagecache_get_page(mapping, offset, fgp_flags, 0);
|
|
}
|
|
|
|
/**
|
|
* find_lock_page - locate, pin and lock a pagecache page
|
|
* @mapping: the address_space to search
|
|
* @offset: the page index
|
|
*
|
|
* Looks up the page cache slot at @mapping & @offset. If there is a
|
|
* page cache page, it is returned locked and with an increased
|
|
* refcount.
|
|
*
|
|
* Otherwise, %NULL is returned.
|
|
*
|
|
* find_lock_page() may sleep.
|
|
*/
|
|
static inline struct page *find_lock_page(struct address_space *mapping,
|
|
pgoff_t offset)
|
|
{
|
|
return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
|
|
}
|
|
|
|
/**
|
|
* find_or_create_page - locate or add a pagecache page
|
|
* @mapping: the page's address_space
|
|
* @index: the page's index into the mapping
|
|
* @gfp_mask: page allocation mode
|
|
*
|
|
* Looks up the page cache slot at @mapping & @offset. If there is a
|
|
* page cache page, it is returned locked and with an increased
|
|
* refcount.
|
|
*
|
|
* If the page is not present, a new page is allocated using @gfp_mask
|
|
* and added to the page cache and the VM's LRU list. The page is
|
|
* returned locked and with an increased refcount.
|
|
*
|
|
* On memory exhaustion, %NULL is returned.
|
|
*
|
|
* find_or_create_page() may sleep, even if @gfp_flags specifies an
|
|
* atomic allocation!
|
|
*/
|
|
static inline struct page *find_or_create_page(struct address_space *mapping,
|
|
pgoff_t offset, gfp_t gfp_mask)
|
|
{
|
|
return pagecache_get_page(mapping, offset,
|
|
FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
|
|
gfp_mask);
|
|
}
|
|
|
|
/**
|
|
* grab_cache_page_nowait - returns locked page at given index in given cache
|
|
* @mapping: target address_space
|
|
* @index: the page index
|
|
*
|
|
* Same as grab_cache_page(), but do not wait if the page is unavailable.
|
|
* This is intended for speculative data generators, where the data can
|
|
* be regenerated if the page couldn't be grabbed. This routine should
|
|
* be safe to call while holding the lock for another page.
|
|
*
|
|
* Clear __GFP_FS when allocating the page to avoid recursion into the fs
|
|
* and deadlock against the caller's locked page.
|
|
*/
|
|
static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
|
|
pgoff_t index)
|
|
{
|
|
return pagecache_get_page(mapping, index,
|
|
FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
|
|
mapping_gfp_mask(mapping));
|
|
}
|
|
|
|
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
|
|
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
|
|
unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
|
|
unsigned int nr_entries, struct page **entries,
|
|
pgoff_t *indices);
|
|
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
|
|
unsigned int nr_pages, struct page **pages);
|
|
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
|
|
unsigned int nr_pages, struct page **pages);
|
|
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
|
|
int tag, unsigned int nr_pages, struct page **pages);
|
|
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
|
|
int tag, unsigned int nr_entries,
|
|
struct page **entries, pgoff_t *indices);
|
|
|
|
struct page *grab_cache_page_write_begin(struct address_space *mapping,
|
|
pgoff_t index, unsigned flags);
|
|
|
|
/*
|
|
* Returns locked page at given index in given cache, creating it if needed.
|
|
*/
|
|
static inline struct page *grab_cache_page(struct address_space *mapping,
|
|
pgoff_t index)
|
|
{
|
|
return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
|
|
}
|
|
|
|
extern struct page * read_cache_page(struct address_space *mapping,
|
|
pgoff_t index, filler_t *filler, void *data);
|
|
extern struct page * read_cache_page_gfp(struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp_mask);
|
|
extern int read_cache_pages(struct address_space *mapping,
|
|
struct list_head *pages, filler_t *filler, void *data);
|
|
|
|
static inline struct page *read_mapping_page(struct address_space *mapping,
|
|
pgoff_t index, void *data)
|
|
{
|
|
filler_t *filler = (filler_t *)mapping->a_ops->readpage;
|
|
return read_cache_page(mapping, index, filler, data);
|
|
}
|
|
|
|
/*
|
|
* Get index of the page with in radix-tree
|
|
* (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
|
|
*/
|
|
static inline pgoff_t page_to_index(struct page *page)
|
|
{
|
|
pgoff_t pgoff;
|
|
|
|
if (likely(!PageTransTail(page)))
|
|
return page->index;
|
|
|
|
/*
|
|
* We don't initialize ->index for tail pages: calculate based on
|
|
* head page
|
|
*/
|
|
pgoff = compound_head(page)->index;
|
|
pgoff += page - compound_head(page);
|
|
return pgoff;
|
|
}
|
|
|
|
/*
|
|
* Get the offset in PAGE_SIZE.
|
|
* (TODO: hugepage should have ->index in PAGE_SIZE)
|
|
*/
|
|
static inline pgoff_t page_to_pgoff(struct page *page)
|
|
{
|
|
if (unlikely(PageHeadHuge(page)))
|
|
return page->index << compound_order(page);
|
|
|
|
return page_to_index(page);
|
|
}
|
|
|
|
/*
|
|
* Return byte-offset into filesystem object for page.
|
|
*/
|
|
static inline loff_t page_offset(struct page *page)
|
|
{
|
|
return ((loff_t)page->index) << PAGE_SHIFT;
|
|
}
|
|
|
|
static inline loff_t page_file_offset(struct page *page)
|
|
{
|
|
return ((loff_t)page_index(page)) << PAGE_SHIFT;
|
|
}
|
|
|
|
extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
|
|
unsigned long address);
|
|
|
|
static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
|
|
unsigned long address)
|
|
{
|
|
pgoff_t pgoff;
|
|
if (unlikely(is_vm_hugetlb_page(vma)))
|
|
return linear_hugepage_index(vma, address);
|
|
pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
|
|
pgoff += vma->vm_pgoff;
|
|
return pgoff;
|
|
}
|
|
|
|
extern void __lock_page(struct page *page);
|
|
extern int __lock_page_killable(struct page *page);
|
|
extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
|
|
unsigned int flags);
|
|
extern void unlock_page(struct page *page);
|
|
|
|
static inline int trylock_page(struct page *page)
|
|
{
|
|
page = compound_head(page);
|
|
return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
|
|
}
|
|
|
|
/*
|
|
* lock_page may only be called if we have the page's inode pinned.
|
|
*/
|
|
static inline void lock_page(struct page *page)
|
|
{
|
|
might_sleep();
|
|
if (!trylock_page(page))
|
|
__lock_page(page);
|
|
}
|
|
|
|
/*
|
|
* lock_page_killable is like lock_page but can be interrupted by fatal
|
|
* signals. It returns 0 if it locked the page and -EINTR if it was
|
|
* killed while waiting.
|
|
*/
|
|
static inline int lock_page_killable(struct page *page)
|
|
{
|
|
might_sleep();
|
|
if (!trylock_page(page))
|
|
return __lock_page_killable(page);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* lock_page_or_retry - Lock the page, unless this would block and the
|
|
* caller indicated that it can handle a retry.
|
|
*
|
|
* Return value and mmap_sem implications depend on flags; see
|
|
* __lock_page_or_retry().
|
|
*/
|
|
static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
|
|
unsigned int flags)
|
|
{
|
|
might_sleep();
|
|
return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
|
|
}
|
|
|
|
/*
|
|
* This is exported only for wait_on_page_locked/wait_on_page_writeback, etc.,
|
|
* and should not be used directly.
|
|
*/
|
|
extern void wait_on_page_bit(struct page *page, int bit_nr);
|
|
extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
|
|
|
|
/*
|
|
* Wait for a page to be unlocked.
|
|
*
|
|
* This must be called with the caller "holding" the page,
|
|
* ie with increased "page->count" so that the page won't
|
|
* go away during the wait..
|
|
*/
|
|
static inline void wait_on_page_locked(struct page *page)
|
|
{
|
|
if (PageLocked(page))
|
|
wait_on_page_bit(compound_head(page), PG_locked);
|
|
}
|
|
|
|
static inline int wait_on_page_locked_killable(struct page *page)
|
|
{
|
|
if (!PageLocked(page))
|
|
return 0;
|
|
return wait_on_page_bit_killable(compound_head(page), PG_locked);
|
|
}
|
|
|
|
/*
|
|
* Wait for a page to complete writeback
|
|
*/
|
|
static inline void wait_on_page_writeback(struct page *page)
|
|
{
|
|
if (PageWriteback(page))
|
|
wait_on_page_bit(page, PG_writeback);
|
|
}
|
|
|
|
extern void end_page_writeback(struct page *page);
|
|
void wait_for_stable_page(struct page *page);
|
|
|
|
void page_endio(struct page *page, bool is_write, int err);
|
|
|
|
/*
|
|
* Add an arbitrary waiter to a page's wait queue
|
|
*/
|
|
extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
|
|
|
|
/*
|
|
* Fault everything in given userspace address range in.
|
|
*/
|
|
static inline int fault_in_pages_writeable(char __user *uaddr, int size)
|
|
{
|
|
char __user *end = uaddr + size - 1;
|
|
|
|
if (unlikely(size == 0))
|
|
return 0;
|
|
|
|
if (unlikely(uaddr > end))
|
|
return -EFAULT;
|
|
/*
|
|
* Writing zeroes into userspace here is OK, because we know that if
|
|
* the zero gets there, we'll be overwriting it.
|
|
*/
|
|
do {
|
|
if (unlikely(__put_user(0, uaddr) != 0))
|
|
return -EFAULT;
|
|
uaddr += PAGE_SIZE;
|
|
} while (uaddr <= end);
|
|
|
|
/* Check whether the range spilled into the next page. */
|
|
if (((unsigned long)uaddr & PAGE_MASK) ==
|
|
((unsigned long)end & PAGE_MASK))
|
|
return __put_user(0, end);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline int fault_in_pages_readable(const char __user *uaddr, int size)
|
|
{
|
|
volatile char c;
|
|
const char __user *end = uaddr + size - 1;
|
|
|
|
if (unlikely(size == 0))
|
|
return 0;
|
|
|
|
if (unlikely(uaddr > end))
|
|
return -EFAULT;
|
|
|
|
do {
|
|
if (unlikely(__get_user(c, uaddr) != 0))
|
|
return -EFAULT;
|
|
uaddr += PAGE_SIZE;
|
|
} while (uaddr <= end);
|
|
|
|
/* Check whether the range spilled into the next page. */
|
|
if (((unsigned long)uaddr & PAGE_MASK) ==
|
|
((unsigned long)end & PAGE_MASK)) {
|
|
return __get_user(c, end);
|
|
}
|
|
|
|
(void)c;
|
|
return 0;
|
|
}
|
|
|
|
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp_mask);
|
|
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp_mask);
|
|
extern void delete_from_page_cache(struct page *page);
|
|
extern void __delete_from_page_cache(struct page *page, void *shadow);
|
|
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
|
|
|
|
/*
|
|
* Like add_to_page_cache_locked, but used to add newly allocated pages:
|
|
* the page is new, so we can just run __SetPageLocked() against it.
|
|
*/
|
|
static inline int add_to_page_cache(struct page *page,
|
|
struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
|
|
{
|
|
int error;
|
|
|
|
__SetPageLocked(page);
|
|
error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
|
|
if (unlikely(error))
|
|
__ClearPageLocked(page);
|
|
return error;
|
|
}
|
|
|
|
static inline unsigned long dir_pages(struct inode *inode)
|
|
{
|
|
return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
|
|
PAGE_SHIFT;
|
|
}
|
|
|
|
#endif /* _LINUX_PAGEMAP_H */
|