blob: 43700480d897d48eb5dbdb879d9d1c5efddb8d0d [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/filemap.c
*
* Copyright (C) 1994-1999 Linus Torvalds
*/
/*
* This file handles the generic file mmap semantics used by
* most "normal" filesystems (but you don't /have/ to use this:
* the NFS filesystem used to do this differently, for example)
*/
#include <linux/export.h>
#include <linux/compiler.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/sched/signal.h>
#include <linux/uaccess.h>
#include <linux/capability.h>
#include <linux/kernel_stat.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/error-injection.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/cpuset.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
#include <linux/delayacct.h>
#include <linux/psi.h>
#include <linux/ramfs.h>
#include <linux/page_idle.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/filemap.h>
/*
* FIXME: remove all knowledge of the buffer layer from the core VM
*/
#include <linux/buffer_head.h> /* for try_to_free_buffers */
#include <asm/mman.h>
/*
* Shared mappings implemented 30.11.1994. It's not fully working yet,
* though.
*
* Shared mappings now work. 15.8.1995 Bruno.
*
* finished 'unifying' the page and buffer cache and SMP-threaded the
* page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
*
* SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
*/
/*
* Lock ordering:
*
* ->i_mmap_rwsem (truncate_pagecache)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->i_pages lock
*
* ->i_mutex
* ->i_mmap_rwsem (truncate->unmap_mapping_range)
*
* ->mmap_lock
* ->i_mmap_rwsem
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->i_pages lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_lock
* ->lock_page (access_process_vm)
*
* ->i_mutex (generic_perform_write)
* ->mmap_lock (fault_in_pages_readable->do_page_fault)
*
* bdi->wb.list_lock
* sb_lock (fs/fs-writeback.c)
* ->i_pages lock (__sync_single_inode)
*
* ->i_mmap_rwsem
* ->anon_vma.lock (vma_adjust)
*
* ->anon_vma.lock
* ->page_table_lock or pte_lock (anon_vma_prepare and various)
*
* ->page_table_lock or pte_lock
* ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->i_pages lock (try_to_unmap_one)
* ->lruvec->lru_lock (follow_page->mark_page_accessed)
* ->lruvec->lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->i_pages lock (page_remove_rmap->set_page_dirty)
* bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
* ->inode->i_lock (page_remove_rmap->set_page_dirty)
* ->memcg->move_lock (page_remove_rmap->lock_page_memcg)
* bdi.wb->list_lock (zap_pte_range->set_page_dirty)
* ->inode->i_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->__set_page_dirty_buffers)
*
* ->i_mmap_rwsem
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
static void page_cache_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
XA_STATE(xas, &mapping->i_pages, page->index);
unsigned int nr = 1;
mapping_set_update(&xas, mapping);
/* hugetlb pages are represented by a single entry in the xarray */
if (!PageHuge(page)) {
xas_set_order(&xas, page->index, compound_order(page));
nr = compound_nr(page);
}
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(nr != 1 && shadow, page);
xas_store(&xas, shadow);
xas_init_marks(&xas);
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
if (shadow) {
mapping->nrexceptional += nr;
/*
* Make sure the nrexceptional update is committed before
* the nrpages update so that final truncate racing
* with reclaim does not see both counters 0 at the
* same time and miss a shadow entry.
*/
smp_wmb();
}
mapping->nrpages -= nr;
}
static void unaccount_page_cache_page(struct address_space *mapping,
struct page *page)
{
int nr;
/*
* if we're uptodate, flush out into the cleancache, otherwise
* invalidate any existing cleancache entries. We can't leave
* stale data around in the cleancache once our page is gone
*/
if (PageUptodate(page) && PageMappedToDisk(page))
cleancache_put_page(page);
else
cleancache_invalidate_page(mapping, page);
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(page_mapped(page), page);
if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
int mapcount;
pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
dump_page(page, "still mapped when deleted");
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
mapcount = page_mapcount(page);
if (mapping_exiting(mapping) &&
page_count(page) >= mapcount + 2) {
/*
* All vmas have already been torn down, so it's
* a good bet that actually the page is unmapped,
* and we'd prefer not to leak it: if we're wrong,
* some other bad page check should catch it later.
*/
page_mapcount_reset(page);
page_ref_sub(page, mapcount);
}
}
/* hugetlb pages do not participate in page cache accounting. */
if (PageHuge(page))
return;
nr = thp_nr_pages(page);
__mod_lruvec_page_state(page, NR_FILE_PAGES, -nr);
if (PageSwapBacked(page)) {
__mod_lruvec_page_state(page, NR_SHMEM, -nr);
if (PageTransHuge(page))
__mod_lruvec_page_state(page, NR_SHMEM_THPS, -nr);
} else if (PageTransHuge(page)) {
__mod_lruvec_page_state(page, NR_FILE_THPS, -nr);
filemap_nr_thps_dec(mapping);
}
/*
* At this point page must be either written or cleaned by
* truncate. Dirty page here signals a bug and loss of
* unwritten data.
*
* This fixes dirty accounting after removing the page entirely
* but leaves PageDirty set: it has no effect for truncated
* page and anyway will be cleared before returning page into
* buddy allocator.
*/
if (WARN_ON_ONCE(PageDirty(page)))
account_page_cleaned(page, mapping, inode_to_wb(mapping->host));
}
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold the i_pages lock.
*/
void __delete_from_page_cache(struct page *page, void *shadow)
{
struct address_space *mapping = page->mapping;
trace_mm_filemap_delete_from_page_cache(page);
unaccount_page_cache_page(mapping, page);
page_cache_delete(mapping, page, shadow);
}
static void page_cache_free_page(struct address_space *mapping,
struct page *page)
{
void (*freepage)(struct page *);
freepage = mapping->a_ops->freepage;
if (freepage)
freepage(page);
if (PageTransHuge(page) && !PageHuge(page)) {
page_ref_sub(page, thp_nr_pages(page));
VM_BUG_ON_PAGE(page_count(page) <= 0, page);
} else {
put_page(page);
}
}
/**
* delete_from_page_cache - delete page from page cache
* @page: the page which the kernel is trying to remove from page cache
*
* This must be called only on pages that have been verified to be in the page
* cache and locked. It will never put the page into the free list, the caller
* has a reference on the page.
*/
void delete_from_page_cache(struct page *page)
{
struct address_space *mapping = page_mapping(page);
unsigned long flags;
BUG_ON(!PageLocked(page));
xa_lock_irqsave(&mapping->i_pages, flags);
__delete_from_page_cache(page, NULL);
xa_unlock_irqrestore(&mapping->i_pages, flags);
page_cache_free_page(mapping, page);
}
EXPORT_SYMBOL(delete_from_page_cache);
/*
* page_cache_delete_batch - delete several pages from page cache
* @mapping: the mapping to which pages belong
* @pvec: pagevec with pages to delete
*
* The function walks over mapping->i_pages and removes pages passed in @pvec
* from the mapping. The function expects @pvec to be sorted by page index
* and is optimised for it to be dense.
* It tolerates holes in @pvec (mapping entries at those indices are not
* modified). The function expects only THP head pages to be present in the
* @pvec.
*
* The function expects the i_pages lock to be held.
*/
static void page_cache_delete_batch(struct address_space *mapping,
struct pagevec *pvec)
{
XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
int total_pages = 0;
int i = 0;
struct page *page;
mapping_set_update(&xas, mapping);
xas_for_each(&xas, page, ULONG_MAX) {
if (i >= pagevec_count(pvec))
break;
/* A swap/dax/shadow entry got inserted? Skip it. */
if (xa_is_value(page))
continue;
/*
* A page got inserted in our range? Skip it. We have our
* pages locked so they are protected from being removed.
* If we see a page whose index is higher than ours, it
* means our page has been removed, which shouldn't be
* possible because we're holding the PageLock.
*/
if (page != pvec->pages[i]) {
VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
page);
continue;
}
WARN_ON_ONCE(!PageLocked(page));
if (page->index == xas.xa_index)
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies on it */
/*
* Move to the next page in the vector if this is a regular
* page or the index is of the last sub-page of this compound
* page.
*/
if (page->index + compound_nr(page) - 1 == xas.xa_index)
i++;
xas_store(&xas, NULL);
total_pages++;
}
mapping->nrpages -= total_pages;
}
void delete_from_page_cache_batch(struct address_space *mapping,
struct pagevec *pvec)
{
int i;
unsigned long flags;
if (!pagevec_count(pvec))
return;
xa_lock_irqsave(&mapping->i_pages, flags);
for (i = 0; i < pagevec_count(pvec); i++) {
trace_mm_filemap_delete_from_page_cache(pvec->pages[i]);
unaccount_page_cache_page(mapping, pvec->pages[i]);
}
page_cache_delete_batch(mapping, pvec);
xa_unlock_irqrestore(&mapping->i_pages, flags);
for (i = 0; i < pagevec_count(pvec); i++)
page_cache_free_page(mapping, pvec->pages[i]);
}
int filemap_check_errors(struct address_space *mapping)
{
int ret = 0;
/* Check for outstanding write errors */
if (test_bit(AS_ENOSPC, &mapping->flags) &&
test_and_clear_bit(AS_ENOSPC, &mapping->flags))
ret = -ENOSPC;
if (test_bit(AS_EIO, &mapping->flags) &&
test_and_clear_bit(AS_EIO, &mapping->flags))
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(filemap_check_errors);
static int filemap_check_and_keep_errors(struct address_space *mapping)
{
/* Check for outstanding write errors */
if (test_bit(AS_EIO, &mapping->flags))
return -EIO;
if (test_bit(AS_ENOSPC, &mapping->flags))
return -ENOSPC;
return 0;
}
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @start: offset in bytes where the range starts
* @end: offset in bytes where the range ends (inclusive)
* @sync_mode: enable synchronous operation
*
* Start writeback against all of a mapping's dirty pages that lie
* within the byte offsets <start, end> inclusive.
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* opposed to a regular memory cleansing writeback. The difference between
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
*
* Return: %0 on success, negative error code otherwise.
*/
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
{
int ret;
struct writeback_control wbc = {
.sync_mode = sync_mode,
.nr_to_write = LONG_MAX,
.range_start = start,
.range_end = end,
};
if (!mapping_can_writeback(mapping) ||
!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
wbc_attach_fdatawrite_inode(&wbc, mapping->host);
ret = do_writepages(mapping, &wbc);
wbc_detach_inode(&wbc);
return ret;
}
static inline int __filemap_fdatawrite(struct address_space *mapping,
int sync_mode)
{
return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
}
int filemap_fdatawrite(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);
int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite_range);
/**
* filemap_flush - mostly a non-blocking flush
* @mapping: target address_space
*
* This is a mostly non-blocking flush. Not suitable for data-integrity
* purposes - I/O may not be started against all dirty pages.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_flush(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);
/**
* filemap_range_has_page - check if a page exists in range.
* @mapping: address space within which to check
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Find at least one page in the range supplied, usually used to check if
* direct writing in this range will trigger a writeback.
*
* Return: %true if at least one page exists in the specified range,
* %false otherwise.
*/
bool filemap_range_has_page(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
struct page *page;
XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
pgoff_t max = end_byte >> PAGE_SHIFT;
if (end_byte < start_byte)
return false;
rcu_read_lock();
for (;;) {
page = xas_find(&xas, max);
if (xas_retry(&xas, page))
continue;
/* Shadow entries don't count */
if (xa_is_value(page))
continue;
/*
* We don't need to try to pin this page; we're about to
* release the RCU lock anyway. It is enough to know that
* there was a page here recently.
*/
break;
}
rcu_read_unlock();
return page != NULL;
}
EXPORT_SYMBOL(filemap_range_has_page);
static void __filemap_fdatawait_range(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
pgoff_t index = start_byte >> PAGE_SHIFT;
pgoff_t end = end_byte >> PAGE_SHIFT;
struct pagevec pvec;
int nr_pages;
if (end_byte < start_byte)
return;
pagevec_init(&pvec);
while (index <= end) {
unsigned i;
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
end, PAGECACHE_TAG_WRITEBACK);
if (!nr_pages)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
wait_on_page_writeback(page);
ClearPageError(page);
}
pagevec_release(&pvec);
cond_resched();
}
}
/**
* filemap_fdatawait_range - wait for writeback to complete
* @mapping: address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the given address space
* in the given range and wait for all of them. Check error status of
* the address space and return it.
*
* Since the error status of the address space is cleared by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
*
* Return: error status of the address space.
*/
int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
loff_t end_byte)
{
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return filemap_check_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range);
/**
* filemap_fdatawait_range_keep_errors - wait for writeback to complete
* @mapping: address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the given address space in the
* given range and wait for all of them. Unlike filemap_fdatawait_range(),
* this function does not clear error status of the address space.
*
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
*/
int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
/**
* file_fdatawait_range - wait for writeback to complete
* @file: file pointing to address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the address space that file
* refers to, in the given range and wait for all of them. Check error
* status of the address space vs. the file->f_wb_err cursor and return it.
*
* Since the error status of the file is advanced by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
*
* Return: error status of the address space vs. the file->f_wb_err cursor.
*/
int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
{
struct address_space *mapping = file->f_mapping;
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return file_check_and_advance_wb_err(file);
}
EXPORT_SYMBOL(file_fdatawait_range);
/**
* filemap_fdatawait_keep_errors - wait for writeback without clearing errors
* @mapping: address space structure to wait for
*
* Walk the list of under-writeback pages of the given address space
* and wait for all of them. Unlike filemap_fdatawait(), this function
* does not clear error status of the address space.
*
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
*
* Return: error status of the address space.
*/
int filemap_fdatawait_keep_errors(struct address_space *mapping)
{
__filemap_fdatawait_range(mapping, 0, LLONG_MAX);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
/* Returns true if writeback might be needed or already in progress. */
static bool mapping_needs_writeback(struct address_space *mapping)
{
if (dax_mapping(mapping))
return mapping->nrexceptional;
return mapping->nrpages;
}
/**
* filemap_write_and_wait_range - write out & wait on a file range
* @mapping: the address_space for the pages
* @lstart: offset in bytes where the range starts
* @lend: offset in bytes where the range ends (inclusive)
*
* Write out and wait upon file offsets lstart->lend, inclusive.
*
* Note that @lend is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
*
* Return: error status of the address space.
*/
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
int err = 0;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/*
* Even if the above returned error, the pages may be
* written partially (e.g. -ENOSPC), so we wait for it.
* But the -EIO is special case, it may indicate the worst
* thing (e.g. bug) happened, so we avoid waiting for it.
*/
if (err != -EIO) {
int err2 = filemap_fdatawait_range(mapping,
lstart, lend);
if (!err)
err = err2;
} else {
/* Clear any previously stored errors */
filemap_check_errors(mapping);
}
} else {
err = filemap_check_errors(mapping);
}
return err;
}
EXPORT_SYMBOL(filemap_write_and_wait_range);
void __filemap_set_wb_err(struct address_space *mapping, int err)
{
errseq_t eseq = errseq_set(&mapping->wb_err, err);
trace_filemap_set_wb_err(mapping, eseq);
}
EXPORT_SYMBOL(__filemap_set_wb_err);
/**
* file_check_and_advance_wb_err - report wb error (if any) that was previously
* and advance wb_err to current one
* @file: struct file on which the error is being reported
*
* When userland calls fsync (or something like nfsd does the equivalent), we
* want to report any writeback errors that occurred since the last fsync (or
* since the file was opened if there haven't been any).
*
* Grab the wb_err from the mapping. If it matches what we have in the file,
* then just quickly return 0. The file is all caught up.
*
* If it doesn't match, then take the mapping value, set the "seen" flag in
* it and try to swap it into place. If it works, or another task beat us
* to it with the new value, then update the f_wb_err and return the error
* portion. The error at this point must be reported via proper channels
* (a'la fsync, or NFS COMMIT operation, etc.).
*
* While we handle mapping->wb_err with atomic operations, the f_wb_err
* value is protected by the f_lock since we must ensure that it reflects
* the latest value swapped in for this file descriptor.
*
* Return: %0 on success, negative error code otherwise.
*/
int file_check_and_advance_wb_err(struct file *file)
{
int err = 0;
errseq_t old = READ_ONCE(file->f_wb_err);
struct address_space *mapping = file->f_mapping;
/* Locklessly handle the common case where nothing has changed */
if (errseq_check(&mapping->wb_err, old)) {
/* Something changed, must use slow path */
spin_lock(&file->f_lock);
old = file->f_wb_err;
err = errseq_check_and_advance(&mapping->wb_err,
&file->f_wb_err);
trace_file_check_and_advance_wb_err(file, old);
spin_unlock(&file->f_lock);
}
/*
* We're mostly using this function as a drop in replacement for
* filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
* that the legacy code would have had on these flags.
*/
clear_bit(AS_EIO, &mapping->flags);
clear_bit(AS_ENOSPC, &mapping->flags);
return err;
}
EXPORT_SYMBOL(file_check_and_advance_wb_err);
/**
* file_write_and_wait_range - write out & wait on a file range
* @file: file pointing to address_space with pages
* @lstart: offset in bytes where the range starts
* @lend: offset in bytes where the range ends (inclusive)
*
* Write out and wait upon file offsets lstart->lend, inclusive.
*
* Note that @lend is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
*
* After writing out and waiting on the data, we check and advance the
* f_wb_err cursor to the latest value, and return any errors detected there.
*
* Return: %0 on success, negative error code otherwise.
*/
int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
{
int err = 0, err2;
struct address_space *mapping = file->f_mapping;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
if (err != -EIO)
__filemap_fdatawait_range(mapping, lstart, lend);
}
err2 = file_check_and_advance_wb_err(file);
if (!err)
err = err2;
return err;
}
EXPORT_SYMBOL(file_write_and_wait_range);
/**
* replace_page_cache_page - replace a pagecache page with a new one
* @old: page to be replaced
* @new: page to replace with
*
* This function replaces a page in the pagecache with a new one. On
* success it acquires the pagecache reference for the new page and
* drops it for the old page. Both the old and new pages must be
* locked. This function does not add the new page to the LRU, the
* caller must do that.
*
* The remove + add is atomic. This function cannot fail.
*/
void replace_page_cache_page(struct page *old, struct page *new)
{
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *) = mapping->a_ops->freepage;
pgoff_t offset = old->index;
XA_STATE(xas, &mapping->i_pages, offset);
unsigned long flags;
VM_BUG_ON_PAGE(!PageLocked(old), old);
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
get_page(new);
new->mapping = mapping;
new->index = offset;
mem_cgroup_migrate(old, new);
xas_lock_irqsave(&xas, flags);
xas_store(&xas, new);
old->mapping = NULL;
/* hugetlb pages do not participate in page cache accounting. */
if (!PageHuge(old))
__dec_lruvec_page_state(old, NR_FILE_PAGES);
if (!PageHuge(new))
__inc_lruvec_page_state(new, NR_FILE_PAGES);
if (PageSwapBacked(old))
__dec_lruvec_page_state(old, NR_SHMEM);
if (PageSwapBacked(new))
__inc_lruvec_page_state(new, NR_SHMEM);
xas_unlock_irqrestore(&xas, flags);
if (freepage)
freepage(old);
put_page(old);
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
noinline int __add_to_page_cache_locked(struct page *page,
struct address_space *mapping,
pgoff_t offset, gfp_t gfp,
void **shadowp)
{
XA_STATE(xas, &mapping->i_pages, offset);
int huge = PageHuge(page);
int error;
bool charged = false;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(page), page);
mapping_set_update(&xas, mapping);
get_page(page);
page->mapping = mapping;
page->index = offset;
if (!huge) {
error = mem_cgroup_charge(page, current->mm, gfp);
if (error)
goto error;
charged = true;
}
gfp &= GFP_RECLAIM_MASK;
do {
unsigned int order = xa_get_order(xas.xa, xas.xa_index);
void *entry, *old = NULL;
if (order > thp_order(page))
xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
order, gfp);
xas_lock_irq(&xas);
xas_for_each_conflict(&xas, entry) {
old = entry;
if (!xa_is_value(entry)) {
xas_set_err(&xas, -EEXIST);
goto unlock;
}
}
if (old) {
if (shadowp)
*shadowp = old;
/* entry may have been split before we acquired lock */
order = xa_get_order(xas.xa, xas.xa_index);
if (order > thp_order(page)) {
xas_split(&xas, old, order);
xas_reset(&xas);
}
}
xas_store(&xas, page);
if (xas_error(&xas))
goto unlock;
if (old)
mapping->nrexceptional--;
mapping->nrpages++;
/* hugetlb pages do not participate in page cache accounting */
if (!huge)
__inc_lruvec_page_state(page, NR_FILE_PAGES);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
if (xas_error(&xas)) {
error = xas_error(&xas);
if (charged)
mem_cgroup_uncharge(page);
goto error;
}
trace_mm_filemap_add_to_page_cache(page);
return 0;
error:
page->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
put_page(page);
return error;
}
ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
/**
* add_to_page_cache_locked - add a locked page to the pagecache
* @page: page to add
* @mapping: the page's address_space
* @offset: page index
* @gfp_mask: page allocation mode
*
* This function is used to add a page to the pagecache. It must be locked.
* This function does not add the page to the LRU. The caller must do that.
*
* Return: %0 on success, negative error code otherwise.
*/
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
return __add_to_page_cache_locked(page, mapping, offset,
gfp_mask, NULL);
}
EXPORT_SYMBOL(add_to_page_cache_locked);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
void *shadow = NULL;
int ret;
__SetPageLocked(page);
ret = __add_to_page_cache_locked(page, mapping, offset,
gfp_mask, &shadow);
if (unlikely(ret))
__ClearPageLocked(page);
else {
/*
* The page might have been evicted from cache only
* recently, in which case it should be activated like
* any other repeatedly accessed page.
* The exception is pages getting rewritten; evicting other
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
*/
WARN_ON_ONCE(PageActive(page));
if (!(gfp_mask & __GFP_WRITE) && shadow)
workingset_refault(page, shadow);
lru_cache_add(page);
}
return ret;
}
EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
#ifdef CONFIG_NUMA
struct page *__page_cache_alloc(gfp_t gfp)
{
int n;
struct page *page;
if (cpuset_do_page_mem_spread()) {
unsigned int cpuset_mems_cookie;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
n = cpuset_mem_spread_node();
page = __alloc_pages_node(n, gfp, 0);
} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
return page;
}
return alloc_pages(gfp, 0);
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
* waitqueues where the bucket discipline is to maintain all
* waiters on the same queue and wake all when any of the pages
* become available, and for the woken contexts to check to be
* sure the appropriate page became available, this saves space
* at a cost of "thundering herd" phenomena during rare hash
* collisions.
*/
#define PAGE_WAIT_TABLE_BITS 8
#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
static wait_queue_head_t *page_waitqueue(struct page *page)
{
return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
}
void __init pagecache_init(void)
{
int i;
for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
init_waitqueue_head(&page_wait_table[i]);
page_writeback_init();
}
/*
* The page wait code treats the "wait->flags" somewhat unusually, because
* we have multiple different kinds of waits, not just the usual "exclusive"
* one.
*
* We have:
*
* (a) no special bits set:
*
* We're just waiting for the bit to be released, and when a waker
* calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
* and remove it from the wait queue.
*
* Simple and straightforward.
*
* (b) WQ_FLAG_EXCLUSIVE:
*
* The waiter is waiting to get the lock, and only one waiter should
* be woken up to avoid any thundering herd behavior. We'll set the
* WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
*
* This is the traditional exclusive wait.
*
* (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
*
* The waiter is waiting to get the bit, and additionally wants the
* lock to be transferred to it for fair lock behavior. If the lock
* cannot be taken, we stop walking the wait queue without waking
* the waiter.
*
* This is the "fair lock handoff" case, and in addition to setting
* WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
* that it now has the lock.
*/
static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
{
unsigned int flags;
struct wait_page_key *key = arg;
struct wait_page_queue *wait_page
= container_of(wait, struct wait_page_queue, wait);
if (!wake_page_match(wait_page, key))
return 0;
/*
* If it's a lock handoff wait, we get the bit for it, and
* stop walking (and do not wake it up) if we can't.
*/
flags = wait->flags;
if (flags & WQ_FLAG_EXCLUSIVE) {
if (test_bit(key->bit_nr, &key->page->flags))
return -1;
if (flags & WQ_FLAG_CUSTOM) {
if (test_and_set_bit(key->bit_nr, &key->page->flags))
return -1;
flags |= WQ_FLAG_DONE;
}
}
/*
* We are holding the wait-queue lock, but the waiter that
* is waiting for this will be checking the flags without
* any locking.
*
* So update the flags atomically, and wake up the waiter
* afterwards to avoid any races. This store-release pairs
* with the load-acquire in wait_on_page_bit_common().
*/
smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
wake_up_state(wait->private, mode);
/*
* Ok, we have successfully done what we're waiting for,
* and we can unconditionally remove the wait entry.
*
* Note that this pairs with the "finish_wait()" in the
* waiter, and has to be the absolute last thing we do.
* After this list_del_init(&wait->entry) the wait entry
* might be de-allocated and the process might even have
* exited.
*/
list_del_init_careful(&wait->entry);
return (flags & WQ_FLAG_EXCLUSIVE) != 0;
}
static void wake_up_page_bit(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
struct wait_page_key key;
unsigned long flags;
wait_queue_entry_t bookmark;
key.page = page;
key.bit_nr = bit_nr;
key.page_match = 0;
bookmark.flags = 0;
bookmark.private = NULL;
bookmark.func = NULL;
INIT_LIST_HEAD(&bookmark.entry);
spin_lock_irqsave(&q->lock, flags);
__wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
while (bookmark.flags & WQ_FLAG_BOOKMARK) {
/*
* Take a breather from holding the lock,
* allow pages that finish wake up asynchronously
* to acquire the lock and remove themselves
* from wait queue
*/
spin_unlock_irqrestore(&q->lock, flags);
cpu_relax();
spin_lock_irqsave(&q->lock, flags);
__wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
}
/*
* It is possible for other pages to have collided on the waitqueue
* hash, so in that case check for a page match. That prevents a long-
* term waiter
*
* It is still possible to miss a case here, when we woke page waiters
* and removed them from the waitqueue, but there are still other
* page waiters.
*/
if (!waitqueue_active(q) || !key.page_match) {
ClearPageWaiters(page);
/*
* It's possible to miss clearing Waiters here, when we woke
* our page waiters, but the hashed waitqueue has waiters for
* other pages on it.
*
* That's okay, it's a rare case. The next waker will clear it.
*/
}
spin_unlock_irqrestore(&q->lock, flags);
}
static void wake_up_page(struct page *page, int bit)
{
if (!PageWaiters(page))
return;
wake_up_page_bit(page, bit);
}
/*
* A choice of three behaviors for wait_on_page_bit_common():
*/
enum behavior {
EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
* __lock_page() waiting on then setting PG_locked.
*/
SHARED, /* Hold ref to page and check the bit when woken, like
* wait_on_page_writeback() waiting on PG_writeback.
*/
DROP, /* Drop ref to page before wait, no check when woken,
* like put_and_wait_on_page_locked() on PG_locked.
*/
};
/*
* Attempt to check (or get) the page bit, and mark us done
* if successful.
*/
static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
struct wait_queue_entry *wait)
{
if (wait->flags & WQ_FLAG_EXCLUSIVE) {
if (test_and_set_bit(bit_nr, &page->flags))
return false;
} else if (test_bit(bit_nr, &page->flags))
return false;
wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
return true;
}
/* How many times do we accept lock stealing from under a waiter? */
int sysctl_page_lock_unfairness = 5;
static inline int wait_on_page_bit_common(wait_queue_head_t *q,
struct page *page, int bit_nr, int state, enum behavior behavior)
{
int unfairness = sysctl_page_lock_unfairness;
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
bool thrashing = false;
bool delayacct = false;
unsigned long pflags;
if (bit_nr == PG_locked &&
!PageUptodate(page) && PageWorkingset(page)) {
if (!PageSwapBacked(page)) {
delayacct_thrashing_start();
delayacct = true;
}
psi_memstall_enter(&pflags);
thrashing = true;
}
init_wait(wait);
wait->func = wake_page_function;
wait_page.page = page;
wait_page.bit_nr = bit_nr;
repeat:
wait->flags = 0;
if (behavior == EXCLUSIVE) {
wait->flags = WQ_FLAG_EXCLUSIVE;
if (--unfairness < 0)
wait->flags |= WQ_FLAG_CUSTOM;
}
/*
* Do one last check whether we can get the
* page bit synchronously.
*
* Do the SetPageWaiters() marking before that
* to let any waker we _just_ missed know they
* need to wake us up (otherwise they'll never
* even go to the slow case that looks at the
* page queue), and add ourselves to the wait
* queue if we need to sleep.
*
* This part needs to be done under the queue
* lock to avoid races.
*/
spin_lock_irq(&q->lock);
SetPageWaiters(page);
if (!trylock_page_bit_common(page, bit_nr, wait))
__add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
/*
* From now on, all the logic will be based on
* the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
* see whether the page bit testing has already
* been done by the wake function.
*
* We can drop our reference to the page.
*/
if (behavior == DROP)
put_page(page);
/*
* Note that until the "finish_wait()", or until
* we see the WQ_FLAG_WOKEN flag, we need to
* be very careful with the 'wait->flags', because
* we may race with a waker that sets them.
*/
for (;;) {
unsigned int flags;
set_current_state(state);
/* Loop until we've been woken or interrupted */
flags = smp_load_acquire(&wait->flags);
if (!(flags & WQ_FLAG_WOKEN)) {
if (signal_pending_state(state, current))
break;
io_schedule();
continue;
}
/* If we were non-exclusive, we're done */
if (behavior != EXCLUSIVE)
break;
/* If the waker got the lock for us, we're done */
if (flags & WQ_FLAG_DONE)
break;
/*
* Otherwise, if we're getting the lock, we need to
* try to get it ourselves.
*
* And if that fails, we'll have to retry this all.
*/
if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
goto repeat;
wait->flags |= WQ_FLAG_DONE;
break;
}
/*
* If a signal happened, this 'finish_wait()' may remove the last
* waiter from the wait-queues, but the PageWaiters bit will remain
* set. That's ok. The next wakeup will take care of it, and trying
* to do it here would be difficult and prone to races.
*/
finish_wait(q, wait);
if (thrashing) {
if (delayacct)
delayacct_thrashing_end();
psi_memstall_leave(&pflags);
}
/*
* NOTE! The wait->flags weren't stable until we've done the
* 'finish_wait()', and we could have exited the loop above due
* to a signal, and had a wakeup event happen after the signal
* test but before the 'finish_wait()'.
*
* So only after the finish_wait() can we reliably determine
* if we got woken up or not, so we can now figure out the final
* return value based on that state without races.
*
* Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
* waiter, but an exclusive one requires WQ_FLAG_DONE.
*/
if (behavior == EXCLUSIVE)
return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
void wait_on_page_bit(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit);
int wait_on_page_bit_killable(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit_killable);
/**
* put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
* @page: The page to wait for.
* @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc).
*
* The caller should hold a reference on @page. They expect the page to
* become unlocked relatively soon, but do not wish to hold up migration
* (for example) by holding the reference while waiting for the page to
* come unlocked. After this function returns, the caller should not
* dereference @page.
*
* Return: 0 if the page was unlocked or -EINTR if interrupted by a signal.
*/
int put_and_wait_on_page_locked(struct page *page, int state)
{
wait_queue_head_t *q;
page = compound_head(page);
q = page_waitqueue(page);
return wait_on_page_bit_common(q, page, PG_locked, state, DROP);
}
/**
* add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
* @page: Page defining the wait queue of interest
* @waiter: Waiter to add to the queue
*
* Add an arbitrary @waiter to the wait queue for the nominated @page.
*/
void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
{
wait_queue_head_t *q = page_waitqueue(page);
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__add_wait_queue_entry_tail(q, waiter);
SetPageWaiters(page);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(add_page_wait_queue);
#ifndef clear_bit_unlock_is_negative_byte
/*
* PG_waiters is the high bit in the same byte as PG_lock.
*
* On x86 (and on many other architectures), we can clear PG_lock and
* test the sign bit at the same time. But if the architecture does
* not support that special operation, we just do this all by hand
* instead.
*
* The read of PG_waiters has to be after (or concurrently with) PG_locked
* being cleared, but a memory barrier should be unnecessary since it is
* in the same byte as PG_locked.
*/
static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
{
clear_bit_unlock(nr, mem);
/* smp_mb__after_atomic(); */
return test_bit(PG_waiters, mem);
}
#endif
/**
* unlock_page - unlock a locked page
* @page: the page
*
* Unlocks the page and wakes up sleepers in wait_on_page_locked().
* Also wakes sleepers in wait_on_page_writeback() because the wakeup
* mechanism between PageLocked pages and PageWriteback pages is shared.
* But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
*
* Note that this depends on PG_waiters being the sign bit in the byte
* that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
* clear the PG_locked bit and test PG_waiters at the same time fairly
* portably (architectures that do LL/SC can test any bit, while x86 can
* test the sign bit).
*/
void unlock_page(struct page *page)
{
BUILD_BUG_ON(PG_waiters != 7);
page = compound_head(page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
wake_up_page_bit(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);
/**
* end_page_writeback - end writeback against a page
* @page: the page
*/
void end_page_writeback(struct page *page)
{
/*
* TestClearPageReclaim could be used here but it is an atomic
* operation and overkill in this particular case. Failing to
* shuffle a page marked for immediate reclaim is too mild to
* justify taking an atomic operation penalty at the end of
* ever page writeback.
*/
if (PageReclaim(page)) {
ClearPageReclaim(page);
rotate_reclaimable_page(page);
}
/*
* Writeback does not hold a page reference of its own, relying
* on truncation to wait for the clearing of PG_writeback.
* But here we must make sure that the page is not freed and
* reused before the wake_up_page().
*/
get_page(page);
if (!test_clear_page_writeback(page))
BUG();
smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
put_page(page);
}
EXPORT_SYMBOL(end_page_writeback);
/*
* After completing I/O on a page, call this routine to update the page
* flags appropriately
*/
void page_endio(struct page *page, bool is_write, int err)
{
if (!is_write) {
if (!err) {
SetPageUptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(page);
}
unlock_page(page);
} else {
if (err) {
struct address_space *mapping;
SetPageError(page);
mapping = page_mapping(page);
if (mapping)
mapping_set_error(mapping, err);
}
end_page_writeback(page);
}
}
EXPORT_SYMBOL_GPL(page_endio);
/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @__page: the page to lock
*/
void __lock_page(struct page *__page)
{
struct page *page = compound_head(__page);
wait_queue_head_t *q = page_waitqueue(page);
wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
EXCLUSIVE);
}
EXPORT_SYMBOL(__lock_page);
int __lock_page_killable(struct page *__page)
{
struct page *page = compound_head(__page);
wait_queue_head_t *q = page_waitqueue(page);
return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
EXCLUSIVE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
int __lock_page_async(struct page *page, struct wait_page_queue *wait)
{
struct wait_queue_head *q = page_waitqueue(page);
int ret = 0;
wait->page = page;
wait->bit_nr = PG_locked;
spin_lock_irq(&q->lock);
__add_wait_queue_entry_tail(q, &wait->wait);
SetPageWaiters(page);
ret = !trylock_page(page);
/*
* If we were successful now, we know we're still on the
* waitqueue as we're still under the lock. This means it's
* safe to remove and return success, we know the callback
* isn't going to trigger.
*/
if (!ret)
__remove_wait_queue(q, &wait->wait);
else
ret = -EIOCBQUEUED;
spin_unlock_irq(&q->lock);
return ret;
}
/*
* Return values:
* 1 - page is locked; mmap_lock is still held.
* 0 - page is not locked.
* mmap_lock has been released (mmap_read_unlock(), unless flags had both
* FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
* which case mmap_lock is still held.
*
* If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
* with the page locked and the mmap_lock unperturbed.
*/
int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
if (fault_flag_allow_retry_first(flags)) {
/*
* CAUTION! In this case, mmap_lock is not released
* even though return 0.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
mmap_read_unlock(mm);
if (flags & FAULT_FLAG_KILLABLE)
wait_on_page_locked_killable(page);
else
wait_on_page_locked(page);
return 0;
}
if (flags & FAULT_FLAG_KILLABLE) {
int ret;
ret = __lock_page_killable(page);
if (ret) {
mmap_read_unlock(mm);
return 0;
}
} else {
__lock_page(page);
}
return 1;
}
/**
* page_cache_next_miss() - Find the next gap in the page cache.
* @mapping: Mapping.
* @index: Index.
* @max_scan: Maximum range to search.
*
* Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
* gap with the lowest index.
*
* This function may be called under the rcu_read_lock. However, this will
* not atomically search a snapshot of the cache at a single point in time.
* For example, if a gap is created at index 5, then subsequently a gap is
* created at index 10, page_cache_next_miss covering both indices may
* return 10 if called under the rcu_read_lock.
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'return - index >= max_scan' will be true).
* In the rare case of index wrap-around, 0 will be returned.
*/
pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
XA_STATE(xas, &mapping->i_pages, index);
while (max_scan--) {
void *entry = xas_next(&xas);
if (!entry || xa_is_value(entry))
break;
if (xas.xa_index == 0)
break;
}
return xas.xa_index;
}
EXPORT_SYMBOL(page_cache_next_miss);
/**
* page_cache_prev_miss() - Find the previous gap in the page cache.
* @mapping: Mapping.
* @index: Index.
* @max_scan: Maximum range to search.
*
* Search the range [max(index - max_scan + 1, 0), index] for the
* gap with the highest index.
*
* This function may be called under the rcu_read_lock. However, this will
* not atomically search a snapshot of the cache at a single point in time.
* For example, if a gap is created at index 10, then subsequently a gap is
* created at index 5, page_cache_prev_miss() covering both indices may
* return 5 if called under the rcu_read_lock.
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'index - return >= max_scan' will be true).
* In the rare case of wrap-around, ULONG_MAX will be returned.
*/
pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
XA_STATE(xas, &mapping->i_pages, index);
while (max_scan--) {
void *entry = xas_prev(&xas);
if (!entry || xa_is_value(entry))
break;
if (xas.xa_index == ULONG_MAX)
break;
}
return xas.xa_index;
}
EXPORT_SYMBOL(page_cache_prev_miss);
/*
* mapping_get_entry - Get a page cache entry.
* @mapping: the address_space to search
* @index: The page cache index.
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, the head page is returned with an increased refcount.
*
* If the slot holds a shadow entry of a previously evicted page, or a
* swap entry from shmem/tmpfs, it is returned.
*
* Return: The head page or shadow entry, %NULL if nothing is found.
*/
static struct page *mapping_get_entry(struct address_space *mapping,
pgoff_t index)
{
XA_STATE(xas, &mapping->i_pages, index);
struct page *page;
rcu_read_lock();
repeat:
xas_reset(&xas);
page = xas_load(&xas);
if (xas_retry(&xas, page))
goto repeat;
/*
* A shadow entry of a recently evicted page, or a swap entry from
* shmem/tmpfs. Return it without attempting to raise page count.
*/
if (!page || xa_is_value(page))
goto out;
if (!page_cache_get_speculative(page))
goto repeat;
/*
* Has the page moved or been split?
* This is part of the lockless pagecache protocol. See
* include/linux/pagemap.h for details.
*/
if (unlikely(page != xas_reload(&xas))) {
put_page(page);
goto repeat;
}
out:
rcu_read_unlock();
return page;
}
/**
* pagecache_get_page - Find and get a reference to a page.
* @mapping: The address_space to search.
* @index: The page index.
* @fgp_flags: %FGP flags modify how the page is returned.
* @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified.
*
* Looks up the page cache entry at @mapping & @index.
*
* @fgp_flags can be zero or more of these flags:
*
* * %FGP_ACCESSED - The page will be marked accessed.
* * %FGP_LOCK - The page is returned locked.
* * %FGP_HEAD - If the page is present and a THP, return the head page
* rather than the exact page specified by the index.
* * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it
* instead of allocating a new page to replace it.
* * %FGP_CREAT - If no page is present then 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.
* * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
* page is already in cache. If the page was allocated, unlock it before
* returning so the caller can do the same dance.
* * %FGP_WRITE - The page will be written
* * %FGP_NOFS - __GFP_FS will get cleared in gfp mask
* * %FGP_NOWAIT - Don't get blocked by page lock
*
* If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
* if the %GFP flags specified for %FGP_CREAT are atomic.
*
* If there is a page cache page, it is returned with an increased refcount.
*
* Return: The found page or %NULL otherwise.
*/
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
int fgp_flags, gfp_t gfp_mask)
{
struct page *page;
repeat:
page = mapping_get_entry(mapping, index);
if (xa_is_value(page)) {
if (fgp_flags & FGP_ENTRY)
return page;
page = NULL;
}
if (!page)
goto no_page;
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
if (!trylock_page(page)) {
put_page(page);
return NULL;
}
} else {
lock_page(page);
}
/* Has the page been truncated? */
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto repeat;
}
VM_BUG_ON_PAGE(!thp_contains(page, index), page);
}
if (fgp_flags & FGP_ACCESSED)
mark_page_accessed(page);
else if (fgp_flags & FGP_WRITE) {
/* Clear idle flag for buffer write */
if (page_is_idle(page))
clear_page_idle(page);
}
if (!(fgp_flags & FGP_HEAD))
page = find_subpage(page, index);
no_page:
if (!page && (fgp_flags & FGP_CREAT)) {
int err;
if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
gfp_mask |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp_mask &= ~__GFP_FS;
page = __page_cache_alloc(gfp_mask);
if (!page)
return NULL;
if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
fgp_flags |= FGP_LOCK;
/* Init accessed so avoid atomic mark_page_accessed later */
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
if (unlikely(err)) {
put_page(page);
page = NULL;
if (err == -EEXIST)
goto repeat;
}
/*
* add_to_page_cache_lru locks the page, and for mmap we expect
* an unlocked page.
*/
if (page && (fgp_flags & FGP_FOR_MMAP))
unlock_page(page);
}
return page;
}
EXPORT_SYMBOL(pagecache_get_page);
static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max,
xa_mark_t mark)
{
struct page *page;
retry:
if (mark == XA_PRESENT)
page = xas_find(xas, max);
else
page = xas_find_marked(xas, max, mark);
if (xas_retry(xas, page))
goto retry;
/*
* A shadow entry of a recently evicted page, a swap
* entry from shmem/tmpfs or a DAX entry. Return it
* without attempting to raise page count.
*/
if (!page || xa_is_value(page))
return page;
if (!page_cache_get_speculative(page))
goto reset;
/* Has the page moved or been split? */
if (unlikely(page != xas_reload(xas))) {
put_page(page);
goto reset;
}
return page;
reset:
xas_reset(xas);
goto retry;
}
/**
* find_get_entries - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page cache index
* @end: The final page index (inclusive).
* @pvec: Where the resulting entries are placed.
* @indices: The cache indices corresponding to the entries in @entries
*
* find_get_entries() will search for and return a batch of entries in
* the mapping. The entries are placed in @pvec. find_get_entries()
* takes a reference on any actual pages it returns.
*
* The search returns a group of mapping-contiguous page cache entries
* with ascending indexes. There may be holes in the indices due to
* not-present pages.
*
* Any shadow entries of evicted pages, or swap entries from
* shmem/tmpfs, are included in the returned array.
*
* If it finds a Transparent Huge Page, head or tail, find_get_entries()
* stops at that page: the caller is likely to have a better way to handle
* the compound page as a whole, and then skip its extent, than repeatedly
* calling find_get_entries() to return all its tails.
*
* Return: the number of pages and shadow entries which were found.
*/
unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
pgoff_t end, struct pagevec *pvec, pgoff_t *indices)
{
XA_STATE(xas, &mapping->i_pages, start);
struct page *page;
unsigned int ret = 0;
unsigned nr_entries = PAGEVEC_SIZE;
rcu_read_lock();
while ((page = find_get_entry(&xas, end, XA_PRESENT))) {
/*
* Terminate early on finding a THP, to allow the caller to
* handle it all at once; but continue if this is hugetlbfs.
*/
if (!xa_is_value(page) && PageTransHuge(page) &&
!PageHuge(page)) {
page = find_subpage(page, xas.xa_index);
nr_entries = ret + 1;
}
indices[ret] = xas.xa_index;
pvec->pages[ret] = page;
if (++ret == nr_entries)
break;
}
rcu_read_unlock();
pvec->nr = ret;
return ret;
}
/**
* find_lock_entries - Find a batch of pagecache entries.
* @mapping: The address_space to search.
* @start: The starting page cache index.
* @end: The final page index (inclusive).
* @pvec: Where the resulting entries are placed.
* @indices: The cache indices of the entries in @pvec.
*
* find_lock_entries() will return a batch of entries from @mapping.
* Swap, shadow and DAX entries are included. Pages are returned
* locked and with an incremented refcount. Pages which are locked by
* somebody else or under writeback are skipped. Only the head page of
* a THP is returned. Pages which are partially outside the range are
* not returned.
*
* The entries have ascending indexes. The indices may not be consecutive
* due to not-present entries, THP pages, pages which could not be locked
* or pages under writeback.
*
* Return: The number of entries which were found.
*/
unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
pgoff_t end, struct pagevec *pvec, pgoff_t *indices)
{
XA_STATE(xas, &mapping->i_pages, start);
struct page *page;
rcu_read_lock();
while ((page = find_get_entry(&xas, end, XA_PRESENT))) {
if (!xa_is_value(page)) {
if (page->index < start)
goto put;
VM_BUG_ON_PAGE(page->index != xas.xa_index, page);
if (page->index + thp_nr_pages(page) - 1 > end)
goto put;
if (!trylock_page(page))
goto put;
if (page->mapping != mapping || PageWriteback(page))
goto unlock;
VM_BUG_ON_PAGE(!thp_contains(page, xas.xa_index),
page);
}
indices[pvec->nr] = xas.xa_index;
if (!pagevec_add(pvec, page))
break;
goto next;
unlock:
unlock_page(page);
put:
put_page(page);
next:
if (!xa_is_value(page) && PageTransHuge(page))
xas_set(&xas, page->index + thp_nr_pages(page));
}
rcu_read_unlock();
return pagevec_count(pvec);
}
/**
* find_get_pages_range - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @nr_pages: The maximum number of pages
* @pages: Where the resulting pages are placed
*
* find_get_pages_range() will search for and return a group of up to @nr_pages
* pages in the mapping starting at index @start and up to index @end
* (inclusive). The pages are placed at @pages. find_get_pages_range() takes
* a reference against the returned pages.
*
* The search returns a group of mapping-contiguous pages with ascending
* indexes. There may be holes in the indices due to not-present pages.
* We also update @start to index the next page for the traversal.
*
* Return: the number of pages which were found. If this number is
* smaller than @nr_pages, the end of specified range has been
* reached.
*/
unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
pgoff_t end, unsigned int nr_pages,
struct page **pages)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct page *page;
unsigned ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
while ((page = find_get_entry(&xas, end, XA_PRESENT))) {
/* Skip over shadow, swap and DAX entries */
if (xa_is_value(page))
continue;
pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages) {
*start = xas.xa_index + 1;
goto out;
}
}
/*
* We come here when there is no page beyond @end. We take care to not
* overflow the index @start as it confuses some of the callers. This
* breaks the iteration when there is a page at index -1 but that is
* already broken anyway.
*/
if (end == (pgoff_t)-1)
*start = (pgoff_t)-1;
else
*start = end + 1;
out:
rcu_read_unlock();
return ret;
}
/**
* find_get_pages_contig - gang contiguous pagecache lookup
* @mapping: The address_space to search
* @index: The starting page index
* @nr_pages: The maximum number of pages
* @pages: Where the resulting pages are placed
*
* find_get_pages_contig() works exactly like find_get_pages(), except
* that the returned number of pages are guaranteed to be contiguous.
*
* Return: the number of pages which were found.
*/
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
unsigned int nr_pages, struct page **pages)
{
XA_STATE(xas, &mapping->i_pages, index);
struct page *page;
unsigned int ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
for (page = xas_load(&xas); page; page = xas_next(&xas)) {
if (xas_retry(&xas, page))
continue;
/*
* If the entry has been swapped out, we can stop looking.
* No current caller is looking for DAX entries.
*/
if (xa_is_value(page))
break;
if (!page_cache_get_speculative(page))
goto retry;
/* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto put_page;
pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages)
break;
continue;
put_page:
put_page(page);
retry:
xas_reset(&xas);
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(find_get_pages_contig);
/**
* find_get_pages_range_tag - Find and return head pages matching @tag.
* @mapping: the address_space to search
* @index: the starting page index
* @end: The final page index (inclusive)
* @tag: the tag index
* @nr_pages: the maximum number of pages
* @pages: where the resulting pages are placed
*
* Like find_get_pages(), except we only return head pages which are tagged
* with @tag. @index is updated to the index immediately after the last
* page we return, ready for the next iteration.
*
* Return: the number of pages which were found.
*/
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
struct page **pages)
{
XA_STATE(xas, &mapping->i_pages, *index);
struct page *page;
unsigned ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
while ((page = find_get_entry(&xas, end, tag))) {
/*
* Shadow entries should never be tagged, but this iteration
* is lockless so there is a window for page reclaim to evict
* a page we saw tagged. Skip over it.
*/
if (xa_is_value(page))
continue;
pages[ret] = page;
if (++ret == nr_pages) {
*index = page->index + thp_nr_pages(page);
goto out;
}
}
/*
* We come here when we got to @end. We take care to not overflow the
* index @index as it confuses some of the callers. This breaks the
* iteration when there is a page at index -1 but that is already
* broken anyway.
*/
if (end == (pgoff_t)-1)
*index = (pgoff_t)-1;
else
*index = end + 1;
out:
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(find_get_pages_range_tag);
/*
* CD/DVDs are error prone. When a medium error occurs, the driver may fail
* a _large_ part of the i/o request. Imagine the worst scenario:
*
* ---R__________________________________________B__________
* ^ reading here ^ bad block(assume 4k)
*
* read(R) => miss => readahead(R...B) => media error => frustrating retries
* => failing the whole request => read(R) => read(R+1) =>
* readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
* readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
* readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
*
* It is going insane. Fix it by quickly scaling down the readahead size.
*/
static void shrink_readahead_size_eio(struct file_ra_state *ra)
{
ra->ra_pages /= 4;
}
/*
* filemap_get_read_batch - Get a batch of pages for read
*
* Get a batch of pages which represent a contiguous range of bytes
* in the file. No tail pages will be returned. If @index is in the
* middle of a THP, the entire THP will be returned. The last page in
* the batch may have Readahead set or be not Uptodate so that the
* caller can take the appropriate action.
*/
static void filemap_get_read_batch(struct address_space *mapping,
pgoff_t index, pgoff_t max, struct pagevec *pvec)
{
XA_STATE(xas, &mapping->i_pages, index);
struct page *head;
rcu_read_lock();
for (head = xas_load(&xas); head; head = xas_next(&xas)) {
if (xas_retry(&xas, head))
continue;
if (xas.xa_index > max || xa_is_value(head))
break;
if (!page_cache_get_speculative(head))
goto retry;
/* Has the page moved or been split? */
if (unlikely(head != xas_reload(&xas)))
goto put_page;
if (!pagevec_add(pvec, head))
break;
if (!PageUptodate(head))
break;
if (PageReadahead(head))
break;
xas.xa_index = head->index + thp_nr_pages(head) - 1;
xas.xa_offset = (xas.xa_index >> xas.xa_shift) & XA_CHUNK_MASK;
continue;
put_page:
put_page(head);
retry:
xas_reset(&xas);
}
rcu_read_unlock();
}
static int filemap_read_page(struct file *file, struct address_space *mapping,
struct page *page)
{
int error;
/*
* A previous I/O error may have been due to temporary failures,
* eg. multipath errors. PG_error will be set again if readpage
* fails.
*/
ClearPageError(page);
/* Start the actual read. The read will unlock the page. */
error = mapping->a_ops->readpage(file, page);
if (error)
return error;
error = wait_on_page_locked_killable(page);
if (error)
return error;
if (PageUptodate(page))
return 0;
if (!page->mapping) /* page truncated */
return AOP_TRUNCATED_PAGE;
shrink_readahead_size_eio(&file->f_ra);
return -EIO;
}
static bool filemap_range_uptodate(struct address_space *mapping,
loff_t pos, struct iov_iter *iter, struct page *page)
{
int count;
if (PageUptodate(page))
return true;
/* pipes can't handle partially uptodate pages */
if (iov_iter_is_pipe(iter))
return false;
if (!mapping->a_ops->is_partially_uptodate)
return false;
if (mapping->host->i_blkbits >= (PAGE_SHIFT + thp_order(page)))
return false;
count = iter->count;
if (page_offset(page) > pos) {
count -= page_offset(page) - pos;
pos = 0;
} else {
pos -= page_offset(page);
}
return mapping->a_ops->is_partially_uptodate(page, pos, count);
}
static int filemap_update_page(struct kiocb *iocb,
struct address_space *mapping, struct iov_iter *iter,
struct page *page)
{
int error;
if (!trylock_page(page)) {
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
return -EAGAIN;
if (!(iocb->ki_flags & IOCB_WAITQ)) {
put_and_wait_on_page_locked(page, TASK_KILLABLE);
return AOP_TRUNCATED_PAGE;
}
error = __lock_page_async(page, iocb->ki_waitq);
if (error)
return error;
}
if (!page->mapping)
goto truncated;
error = 0;
if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
goto unlock;
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
error = filemap_read_page(iocb->ki_filp, mapping, page);
if (error == AOP_TRUNCATED_PAGE)
put_page(page);
return error;
truncated:
unlock_page(page);
put_page(page);
return AOP_TRUNCATED_PAGE;
unlock:
unlock_page(page);
return error;
}
static int filemap_create_page(struct file *file,
struct address_space *mapping, pgoff_t index,
struct pagevec *pvec)
{
struct page *page;
int error;
page = page_cache_alloc(mapping);
if (!page)
return -ENOMEM;
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error == -EEXIST)
error = AOP_TRUNCATED_PAGE;
if (error)
goto error;
error = filemap_read_page(file, mapping, page);
if (error)
goto error;
pagevec_add(pvec, page);
return 0;
error:
put_page(page);
return error;
}
static int filemap_readahead(struct kiocb *iocb, struct file *file,
struct address_space *mapping, struct page *page,
pgoff_t last_index)
{
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
page_cache_async_readahead(mapping, &file->f_ra, file, page,
page->index, last_index - page->index);
return 0;
}
static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter,
struct pagevec *pvec)
{
struct file *filp = iocb->ki_filp;
struct address_space *mapping = filp->f_mapping;
struct file_ra_state *ra = &filp->f_ra;
pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
pgoff_t last_index;
struct page *page;
int err = 0;
last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE);
retry:
if (fatal_signal_pending(current))
return -EINTR;
filemap_get_read_batch(mapping, index, last_index, pvec);
if (!pagevec_count(pvec)) {
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
page_cache_sync_readahead(mapping, ra, filp, index,
last_index - index);
filemap_get_read_batch(mapping, index, last_index, pvec);
}
if (!pagevec_count(pvec)) {
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
return -EAGAIN;
err = filemap_create_page(filp, mapping,
iocb->ki_pos >> PAGE_SHIFT, pvec);
if (err == AOP_TRUNCATED_PAGE)
goto retry;
return err;
}
page = pvec->pages[pagevec_count(pvec) - 1];
if (PageReadahead(page)) {
err = filemap_readahead(iocb, filp, mapping, page, last_index);
if (err)
goto err;
}
if (!PageUptodate(page)) {
if ((iocb->ki_flags & IOCB_WAITQ) && pagevec_count(pvec) > 1)
iocb->ki_flags |= IOCB_NOWAIT;
err = filemap_update_page(iocb, mapping, iter, page);
if (err)
goto err;
}
return 0;
err:
if (err < 0)
put_page(page);
if (likely(--pvec->nr))
return 0;
if (err == AOP_TRUNCATED_PAGE)
goto retry;
return err;
}
/**
* filemap_read - Read data from the page cache.
* @iocb: The iocb to read.
* @iter: Destination for the data.
* @already_read: Number of bytes already read by the caller.
*
* Copies data from the page cache. If the data is not currently present,
* uses the readahead and readpage address_space operations to fetch it.
*
* Return: Total number of bytes copied, including those already read by
* the caller. If an error happens before any bytes are copied, returns
* a negative error number.
*/
ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
ssize_t already_read)
{
struct file *filp = iocb->ki_filp;
struct file_ra_state *ra = &filp->f_ra;
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct pagevec pvec;
int i, error = 0;
bool writably_mapped;
loff_t isize, end_offset;
if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes))
return 0;
if (unlikely(!iov_iter_count(iter)))
return 0;
iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
pagevec_init(&pvec);
do {
cond_resched();
/*
* If we've already successfully copied some data, then we
* can no longer safely return -EIOCBQUEUED. Hence mark
* an async read NOWAIT at that point.
*/
if ((iocb->ki_flags & IOCB_WAITQ) && already_read)
iocb->ki_flags |= IOCB_NOWAIT;
error = filemap_get_pages(iocb, iter, &pvec);
if (error < 0)
break;
/*
* i_size must be checked after we know the pages are Uptodate.
*
* Checking i_size after the check allows us to calculate
* the correct value for "nr", which means the zero-filled
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
isize = i_size_read(inode);
if (unlikely(iocb->ki_pos >= isize))
goto put_pages;
end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
/*
* Once we start copying data, we don't want to be touching any
* cachelines that might be contended:
*/
writably_mapped = mapping_writably_mapped(mapping);
/*
* When a sequential read accesses a page several times, only
* mark it as accessed the first time.
*/
if (iocb->ki_pos >> PAGE_SHIFT !=
ra->prev_pos >> PAGE_SHIFT)
mark_page_accessed(pvec.pages[0]);
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
size_t page_size = thp_size(page);
size_t offset = iocb->ki_pos & (page_size - 1);
size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos,
page_size - offset);
size_t copied;
if (end_offset < page_offset(page))
break;
if (i > 0)
mark_page_accessed(page);
/*
* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (writably_mapped) {
int j;
for (j = 0; j < thp_nr_pages(page); j++)
flush_dcache_page(page + j);
}
copied = copy_page_to_iter(page, offset, bytes, iter);
already_read += copied;
iocb->ki_pos += copied;
ra->prev_pos = iocb->ki_pos;
if (copied < bytes) {
error = -EFAULT;
break;
}
}
put_pages:
for (i = 0; i < pagevec_count(&pvec); i++)
put_page(pvec.pages[i]);
pagevec_reinit(&pvec);
} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
file_accessed(filp);
return already_read ? already_read : error;
}
EXPORT_SYMBOL_GPL(filemap_read);
/**
* generic_file_read_iter - generic filesystem read routine
* @iocb: kernel I/O control block
* @iter: destination for the data read
*
* This is the "read_iter()" routine for all filesystems
* that can use the page cache directly.
*
* The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
* be returned when no data can be read without waiting for I/O requests
* to complete; it doesn't prevent readahead.
*
* The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
* requests shall be made for the read or for readahead. When no data
* can be read, -EAGAIN shall be returned. When readahead would be
* triggered, a partial, possibly empty read shall be returned.
*
* Return:
* * number of bytes copied, even for partial reads
* * negative error code (or 0 if IOCB_NOIO) if nothing was read
*/
ssize_t
generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
size_t count = iov_iter_count(iter);
ssize_t retval = 0;
if (!count)
return 0; /* skip atime */
if (iocb->ki_flags & IOCB_DIRECT) {
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
loff_t size;
size = i_size_read(inode);
if (iocb->ki_flags & IOCB_NOWAIT) {
if (filemap_range_has_page(mapping, iocb->ki_pos,
iocb->ki_pos + count - 1))
return -EAGAIN;
} else {
retval = filemap_write_and_wait_range(mapping,
iocb->ki_pos,
iocb->ki_pos + count - 1);
if (retval < 0)
return retval;
}
file_accessed(file);
retval = mapping->a_ops->direct_IO(iocb, iter);
if (retval >= 0) {
iocb->ki_pos += retval;
count -= retval;
}
if (retval != -EIOCBQUEUED)
iov_iter_revert(iter, count - iov_iter_count(iter));
/*
* Btrfs can have a short DIO read if we encounter
* compressed extents, so if there was an error, or if
* we've already read everything we wanted to, or if
* there was a short read because we hit EOF, go ahead
* and return. Otherwise fallthrough to buffered io for
* the rest of the read. Buffered reads will not work for
* DAX files, so don't bother trying.
*/
if (retval < 0 || !count || iocb->ki_pos >= size ||
IS_DAX(inode))
return retval;
}
return filemap_read(iocb, iter, retval);
}
EXPORT_SYMBOL(generic_file_read_iter);
static inline loff_t page_seek_hole_data(struct xa_state *xas,
struct address_space *mapping, struct page *page,
loff_t start, loff_t end, bool seek_data)
{
const struct address_space_operations *ops = mapping->a_ops;
size_t offset, bsz = i_blocksize(mapping->host);
if (xa_is_value(page) || PageUptodate(page))
return seek_data ? start : end;
if (!ops->is_partially_uptodate)
return seek_data ? end : start;
xas_pause(xas);
rcu_read_unlock();
lock_page(page);
if (unlikely(page->mapping != mapping))
goto unlock;
offset = offset_in_thp(page, start) & ~(bsz - 1);
do {
if (ops->is_partially_uptodate(page, offset, bsz) == seek_data)
break;
start = (start + bsz) & ~(bsz - 1);
offset += bsz;
} while (offset < thp_size(page));
unlock:
unlock_page(page);
rcu_read_lock();
return start;
}
static inline
unsigned int seek_page_size(struct xa_state *xas, struct page *page)
{
if (xa_is_value(page))
return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index);
return thp_size(page);
}
/**
* mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache.
* @mapping: Address space to search.
* @start: First byte to consider.
* @end: Limit of search (exclusive).
* @whence: Either SEEK_HOLE or SEEK_DATA.
*
* If the page cache knows which blocks contain holes and which blocks
* contain data, your filesystem can use this function to implement
* SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are
* entirely memory-based such as tmpfs, and filesystems which support
* unwritten extents.
*
* Return: The requested offset on successs, or -ENXIO if @whence specifies
* SEEK_DATA and there is no data after @start. There is an implicit hole
* after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start
* and @end contain data.
*/
loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
loff_t end, int whence)
{
XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT);
pgoff_t max = (end - 1) / PAGE_SIZE;
bool seek_data = (whence == SEEK_DATA);
struct page *page;
if (end <= start)
return -ENXIO;
rcu_read_lock();
while ((page = find_get_entry(&xas, max, XA_PRESENT))) {
loff_t pos = xas.xa_index * PAGE_SIZE;
if (start < pos) {
if (!seek_data)
goto unlock;
start = pos;
}
pos += seek_page_size(&xas, page);
start = page_seek_hole_data(&xas, mapping, page, start, pos,
seek_data);
if (start < pos)
goto unlock;
if (!xa_is_value(page))
put_page(page);
}
rcu_read_unlock();
if (seek_data)
return -ENXIO;
goto out;
unlock:
rcu_read_unlock();
if (!xa_is_value(page))
put_page(page);
out:
if (start > end)
return end;
return start;
}
#ifdef CONFIG_MMU
#define MMAP_LOTSAMISS (100)
/*
* lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock
* @vmf - the vm_fault for this fault.
* @page - the page to lock.
* @fpin - the pointer to the file we may pin (or is already pinned).
*
* This works similar to lock_page_or_retry in that it can drop the mmap_lock.
* It differs in that it actually returns the page locked if it returns 1 and 0
* if it couldn't lock the page. If we did have to drop the mmap_lock then fpin
* will point to the pinned file and needs to be fput()'ed at a later point.
*/
static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
struct file **fpin)
{
if (trylock_page(page))
return 1;
/*
* NOTE! This will make us return with VM_FAULT_RETRY, but with
* the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT
* is supposed to work. We have way too many special cases..
*/
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_KILLABLE) {
if (__lock_page_killable(page)) {
/*
* We didn't have the right flags to drop the mmap_lock,
* but all fault_handlers only check for fatal signals
* if we return VM_FAULT_RETRY, so we need to drop the
* mmap_lock here and return 0 if we don't have a fpin.
*/
if (*fpin == NULL)
mmap_read_unlock(vmf->vma->vm_mm);
return 0;
}
} else
__lock_page(page);
return 1;
}
/*
* Synchronous readahead happens when we don't even find a page in the page
* cache at all. We don't want to perform IO under the mmap sem, so if we have
* to drop the mmap sem we return the file that was pinned in order for us to do
* that. If we didn't pin a file then we return NULL. The file that is
* returned needs to be fput()'ed when we're done with it.
*/
static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
struct file *fpin = NULL;
unsigned int mmap_miss;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ)
return fpin;
if (!ra->ra_pages)
return fpin;
if (vmf->vma->vm_flags & VM_SEQ_READ) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_sync_ra(&ractl, ra, ra->ra_pages);
return fpin;
}
/* Avoid banging the cache line if not needed */
mmap_miss = READ_ONCE(ra->mmap_miss);
if (mmap_miss < MMAP_LOTSAMISS * 10)
WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
if (mmap_miss > MMAP_LOTSAMISS)
return fpin;
/*
* mmap read-around
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
ractl._index = ra->start;
do_page_cache_ra(&ractl, ra->size, ra->async_size);
return fpin;
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
* so we want to possibly extend the readahead further. We return the file that
* was pinned if we have to drop the mmap_lock in order to do IO.
*/
static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
struct page *page)
{
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
struct file *fpin = NULL;
unsigned int mmap_miss;
pgoff_t offset = vmf->pgoff;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
return fpin;
mmap_miss = READ_ONCE(ra->mmap_miss);
if (mmap_miss)
WRITE_ONCE(ra->mmap_miss, --mmap_miss);
if (PageReadahead(page)) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_async_readahead(mapping, ra, file,
page, offset, ra->ra_pages);
}
return fpin;
}
/**
* filemap_fault - read in file data for page fault handling
* @vmf: struct vm_fault containing details of the fault
*
* filemap_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* The goto's are kind of ugly, but this streamlines the normal case of having
* it in the page cache, and handles the special cases reasonably without
* having a lot of duplicated code.
*
* vma->vm_mm->mmap_lock must be held on entry.
*
* If our return value has VM_FAULT_RETRY set, it's because the mmap_lock
* may be dropped before doing I/O or by lock_page_maybe_drop_mmap().
*
* If our return value does not have VM_FAULT_RETRY set, the mmap_lock
* has not been released.
*
* We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
*
* Return: bitwise-OR of %VM_FAULT_ codes.
*/
vm_fault_t filemap_fault(struct vm_fault *vmf)
{
int error;
struct file *file = vmf->vma->vm_file;
struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
pgoff_t max_off;
struct page *page;
vm_fault_t ret = 0;
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off))
return VM_FAULT_SIGBUS;
/*
* Do we have something in the page cache already?
*/
page = find_get_page(mapping, offset);
if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
/*
* We found the page, so try async readahead before
* waiting for the lock.
*/
fpin = do_async_mmap_readahead(vmf, page);
} else if (!page) {
/* No page in the page cache at all */
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
fpin = do_sync_mmap_readahead(vmf);
retry_find:
page = pagecache_get_page(mapping, offset,
FGP_CREAT|FGP_FOR_MMAP,
vmf->gfp_mask);
if (!page) {
if (fpin)
goto out_retry;
return VM_FAULT_OOM;
}
}
if (!lock_page_maybe_drop_mmap(vmf, page, &fpin))
goto out_retry;
/* Did it get truncated? */
if (unlikely(compound_head(page)->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto retry_find;
}
VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
/*
* We have a locked page in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error.
*/
if (unlikely(!PageUptodate(page)))
goto page_not_uptodate;
/*
* We've made it this far and we had to drop our mmap_lock, now is the
* time to return to the upper layer and have it re-find the vma and
* redo the fault.
*/
if (fpin) {
unlock_page(page);
goto out_retry;
}
/*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off)) {
unlock_page(page);
put_page(page);
return VM_FAULT_SIGBUS;
}
vmf->page = page;
return ret | VM_FAULT_LOCKED;
page_not_uptodate:
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
* because there really aren't any performance issues here
* and we need to check for errors.
*/
ClearPageError(page);
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
error = mapping->a_ops->readpage(file, page);
if (!error) {
wait_on_page_locked(page);
if (!PageUptodate(page))
error = -EIO;
}
if (fpin)
goto out_retry;