cregit-Linux how code gets into the kernel

Release 4.18 mm/filemap.c

Directory: mm
/*
 *      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/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 "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_sem
 *    ->i_mmap_rwsem
 *      ->page_table_lock or pte_lock   (various, mainly in memory.c)
 *        ->i_pages lock        (arch-dependent flush_dcache_mmap_lock)
 *
 *  ->mmap_sem
 *    ->lock_page               (access_process_vm)
 *
 *  ->i_mutex                   (generic_perform_write)
 *    ->mmap_sem                (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)
 *    ->zone_lru_lock(zone)     (follow_page->mark_page_accessed)
 *    ->zone_lru_lock(zone)     (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 int page_cache_tree_insert(struct address_space *mapping, struct page *page, void **shadowp) { struct radix_tree_node *node; void **slot; int error; error = __radix_tree_create(&mapping->i_pages, page->index, 0, &node, &slot); if (error) return error; if (*slot) { void *p; p = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); if (!radix_tree_exceptional_entry(p)) return -EEXIST; mapping->nrexceptional--; if (shadowp) *shadowp = p; } __radix_tree_replace(&mapping->i_pages, node, slot, page, workingset_lookup_update(mapping)); mapping->nrpages++; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner13394.33%360.00%
Matthew Wilcox53.55%120.00%
Mel Gorman32.13%120.00%
Total141100.00%5100.00%


static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { int i, nr; /* hugetlb pages are represented by one entry in the radix tree */ nr = PageHuge(page) ? 1 : hpage_nr_pages(page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(nr != 1 && shadow, page); for (i = 0; i < nr; i++) { struct radix_tree_node *node; void **slot; __radix_tree_lookup(&mapping->i_pages, page->index + i, &node, &slot); VM_BUG_ON_PAGE(!node && nr != 1, page); radix_tree_clear_tags(&mapping->i_pages, node, slot); __radix_tree_replace(&mapping->i_pages, node, slot, shadow, workingset_lookup_update(mapping)); } 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; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner10153.44%650.00%
Kirill A. Shutemov7439.15%216.67%
Jan Kara73.70%18.33%
Matthew Wilcox42.12%216.67%
Mel Gorman31.59%18.33%
Total189100.00%12100.00%


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 = hpage_nr_pages(page); __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else { VM_BUG_ON_PAGE(PageTransHuge(page), page); } /* * 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)); }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins9737.60%15.26%
Kirill A. Shutemov5119.77%210.53%
Dan Magenheimer2610.08%210.53%
Jan Kara166.20%15.26%
Linus Torvalds155.81%15.26%
Motohiro Kosaki135.04%15.26%
Linus Torvalds (pre-git)103.88%315.79%
Michal Hocko83.10%15.26%
Tejun Heo62.33%15.26%
Mel Gorman51.94%15.26%
Christoph Lameter31.16%15.26%
JoonSoo Kim31.16%15.26%
Konstantin Khlebnikov31.16%15.26%
Johannes Weiner10.39%15.26%
Greg Thelen10.39%15.26%
Total258100.00%19100.00%

/* * 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_tree_delete(mapping, page, shadow); }

Contributors

PersonTokensPropCommitsCommitProp
Jan Kara44100.00%2100.00%
Total44100.00%2100.00%


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, HPAGE_PMD_NR); VM_BUG_ON_PAGE(page_count(page) <= 0, page); } else { put_page(page); } }

Contributors

PersonTokensPropCommitsCommitProp
Kirill A. Shutemov3844.19%233.33%
Linus Torvalds2832.56%116.67%
Linus Torvalds (pre-git)89.30%116.67%
Jan Kara78.14%116.67%
MinChan Kim55.81%116.67%
Total86100.00%6100.00%

/** * 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); }

Contributors

PersonTokensPropCommitsCommitProp
Jan Kara6394.03%150.00%
Matthew Wilcox45.97%150.00%
Total67100.00%2100.00%

EXPORT_SYMBOL(delete_from_page_cache); /* * page_cache_tree_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. * 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 and takes care to delete all corresponding tail pages from the * mapping as well. * * The function expects the i_pages lock to be held. */
static void page_cache_tree_delete_batch(struct address_space *mapping, struct pagevec *pvec) { struct radix_tree_iter iter; void **slot; int total_pages = 0; int i = 0, tail_pages = 0; struct page *page; pgoff_t start; start = pvec->pages[0]->index; radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { if (i >= pagevec_count(pvec) && !tail_pages) break; page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); if (radix_tree_exceptional_entry(page)) continue; if (!tail_pages) { /* * Some page got inserted in our range? Skip it. We * have our pages locked so they are protected from * being removed. */ if (page != pvec->pages[i]) continue; WARN_ON_ONCE(!PageLocked(page)); if (PageTransHuge(page) && !PageHuge(page)) tail_pages = HPAGE_PMD_NR - 1; page->mapping = NULL; /* * Leave page->index set: truncation lookup relies * upon it */ i++; } else { tail_pages--; } radix_tree_clear_tags(&mapping->i_pages, iter.node, slot); __radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL, workingset_lookup_update(mapping)); total_pages++; } mapping->nrpages -= total_pages; }

Contributors

PersonTokensPropCommitsCommitProp
Jan Kara20495.77%133.33%
Matthew Wilcox62.82%133.33%
Mel Gorman31.41%133.33%
Total213100.00%3100.00%


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_tree_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]); }

Contributors

PersonTokensPropCommitsCommitProp
Jan Kara12296.83%150.00%
Matthew Wilcox43.17%150.00%
Total126100.00%2100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Dmitriy Monakhov5372.60%150.00%
Jens Axboe2027.40%150.00%
Total73100.00%2100.00%

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; }

Contributors

PersonTokensPropCommitsCommitProp
Jeff Layton47100.00%1100.00%
Total47100.00%1100.00%

/** * __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. */
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_cap_writeback_dirty(mapping)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton4045.45%853.33%
Tejun Heo1618.18%16.67%
Suparna Bhattacharya1517.05%16.67%
Linus Torvalds77.95%16.67%
David Howells44.55%16.67%
Linus Torvalds (pre-git)33.41%16.67%
Hirofumi Ogawa22.27%16.67%
Nicholas Piggin11.14%16.67%
Total88100.00%15100.00%


static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); }

Contributors

PersonTokensPropCommitsCommitProp
Suparna Bhattacharya2696.30%150.00%
Hirofumi Ogawa13.70%150.00%
Total27100.00%2100.00%


int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton18100.00%1100.00%
Total18100.00%1100.00%

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); }

Contributors

PersonTokensPropCommitsCommitProp
Suparna Bhattacharya28100.00%1100.00%
Total28100.00%1100.00%

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. */
int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton18100.00%1100.00%
Total18100.00%1100.00%

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. */
bool filemap_range_has_page(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 page *page; if (end_byte < start_byte) return false; if (mapping->nrpages == 0) return false; if (!find_get_pages_range(mapping, &index, end, 1, &page)) return false; put_page(page); return true; }

Contributors

PersonTokensPropCommitsCommitProp
Goldwyn Rodrigues7184.52%133.33%
Jan Kara1315.48%266.67%
Total84100.00%3100.00%

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(); } }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton6045.80%538.46%
Linus Torvalds (pre-git)2922.14%215.38%
Christoph Hellwig1813.74%17.69%
Jan Kara139.92%17.69%
Suparna Bhattacharya32.29%17.69%
Jeff Layton32.29%17.69%
Jun'ichi Nomura32.29%17.69%
Kirill A. Shutemov21.53%17.69%
Total131100.00%13100.00%

/** * 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. */
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); }

Contributors

PersonTokensPropCommitsCommitProp
Jun'ichi Nomura2477.42%114.29%
Andrew Morton412.90%342.86%
Jeff Layton13.23%114.29%
Dmitriy Monakhov13.23%114.29%
Linus Torvalds (pre-git)13.23%114.29%
Total31100.00%7100.00%

EXPORT_SYMBOL(filemap_fdatawait_range); /** * 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. */
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); }

Contributors

PersonTokensPropCommitsCommitProp
Jeff Layton2460.00%266.67%
Jun'ichi Nomura1640.00%133.33%
Total40100.00%3100.00%

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) */
int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton1456.00%120.00%
Jun'ichi Nomura624.00%120.00%
Marcelo Tosatti312.00%120.00%
Jeff Layton28.00%240.00%
Total25100.00%5100.00%

EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
static bool mapping_needs_writeback(struct address_space *mapping) { return (!dax_mapping(mapping) && mapping->nrpages) || (dax_mapping(mapping) && mapping->nrexceptional); }

Contributors

PersonTokensPropCommitsCommitProp
Ross Zwisler1954.29%133.33%
Andrew Morton1028.57%133.33%
Jeff Layton617.14%133.33%
Total35100.00%3100.00%


int filemap_write_and_wait(struct address_space *mapping) { int err = 0; if (mapping_needs_writeback(mapping)) { err = filemap_fdatawrite(mapping); /* * 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(mapping); if (!err) err = err2; } else { /* Clear any previously stored errors */ filemap_check_errors(mapping); } } else { err = filemap_check_errors(mapping); } return err; }

Contributors

PersonTokensPropCommitsCommitProp
Jeff Layton2936.25%240.00%
Hirofumi Ogawa2126.25%120.00%
Andrew Morton2025.00%120.00%
Dmitriy Monakhov1012.50%120.00%
Total80100.00%5100.00%

EXPORT_SYMBOL(filemap_write_and_wait); /** * 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). */
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); /* See comment of filemap_write_and_wait() */ 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; }

Contributors

PersonTokensPropCommitsCommitProp
Zach Brown5052.08%114.29%
Hirofumi Ogawa2222.92%114.29%
Jeff Layton1010.42%228.57%
Dmitriy Monakhov1010.42%114.29%
Ross Zwisler33.12%114.29%
Christoph Hellwig11.04%114.29%
Total96100.00%7100.00%

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); }

Contributors

PersonTokensPropCommitsCommitProp
Jeff Layton33100.00%2100.00%
Total33100.00%2100.00%

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. */
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; }

Contributors

PersonTokensPropCommitsCommitProp
Jeff Layton118100.00%2100.00%
Total118100.00%2100.00%

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. */
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; }

Contributors

PersonTokensPropCommitsCommitProp
Jeff Layton90100.00%2100.00%
Total90100.00%2100.00%

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 * @gfp_mask: allocation mode * * 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. The only way this function can fail is * memory allocation failure. */
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { int error; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK); if (!error) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *); unsigned long flags; pgoff_t offset = old->index; freepage = mapping->a_ops->freepage; get_page(new); new->mapping = mapping; new->index = offset; xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(old, NULL); error = page_cache_tree_insert(mapping, new, NULL); BUG_ON(error); /* * hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(new)) __inc_node_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(new)) __inc_node_page_state(new, NR_SHMEM); xa_unlock_irqrestore(&mapping->i_pages, flags); mem_cgroup_migrate(old, new); radix_tree_preload_end(); if (freepage) freepage(old); put_page(old); } return error; }

Contributors

PersonTokensPropCommitsCommitProp
Miklos Szeredi17477.68%17.69%
Greg Thelen104.46%17.69%
Michal Hocko94.02%17.69%
Sasha Levin94.02%17.69%
Kamezawa Hiroyuki62.68%17.69%
Johannes Weiner62.68%323.08%
Matthew Wilcox52.23%215.38%
Kirill A. Shutemov20.89%17.69%
Mel Gorman20.89%17.69%
MinChan Kim10.45%17.69%
Total224100.00%13100.00%

EXPORT_SYMBOL_GPL(replace_page_cache_page);
static int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask, void **shadowp) { int huge = PageHuge(page); struct mem_cgroup *memcg; int error; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); if (!huge) { error = mem_cgroup_try_charge(page, current->mm, gfp_mask, &memcg, false); if (error) return error; } error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK); if (error) { if (!huge) mem_cgroup_cancel_charge(page, memcg, false); return error; } get_page(page); page->mapping = mapping; page->index = offset; xa_lock_irq(&mapping->i_pages); error = page_cache_tree_insert(mapping, page, shadowp); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; /* hugetlb pages do not participate in page cache accounting. */ if (!huge) __inc_node_page_state(page, NR_FILE_PAGES); xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_commit_charge(page, memcg, false, false); trace_mm_filemap_add_to_page_cache(page); return 0; err_insert: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_cancel_charge(page, memcg, false); put_page(page); return error; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner6324.14%39.68%
Nicholas Piggin4015.33%13.23%
Kirill A. Shutemov3312.64%39.68%
Andrew Morton3212.26%516.13%
Balbir Singh228.43%39.68%
Linus Torvalds (pre-git)186.90%26.45%
Daisuke Nishimura124.60%13.23%
Hugh Dickins83.07%26.45%
Matthew Wilcox72.68%26.45%
Michal Hocko62.30%13.23%
Sasha Levin62.30%13.23%
Robert Jarzmik51.92%13.23%
Christoph Lameter31.15%13.23%
Linus Torvalds20.77%13.23%
Jan Kara10.38%13.23%
Mel Gorman10.38%13.23%
Al Viro10.38%13.23%
Badari Pulavarty10.38%13.23%
Total261100.00%31100.00%

/** * 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. */
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); }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner35100.00%1100.00%
Total35100.00%1100.00%

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. */ if (!(gfp_mask & __GFP_WRITE) && shadow && workingset_refault(shadow)) { SetPageActive(page); workingset_activation(page); } else ClearPageActive(page); lru_cache_add(page); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner5247.71%110.00%
Andrew Morton3431.19%330.00%
Rik Van Riel1211.01%220.00%
Linus Torvalds54.59%110.00%
Linus Torvalds (pre-git)32.75%110.00%
Kirill A. Shutemov21.83%110.00%
Al Viro10.92%110.00%
Total109100.00%10100.00%

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); }

Contributors

PersonTokensPropCommitsCommitProp
Paul Jackson3141.33%116.67%
Mel Gorman2128.00%233.33%
Miao Xie1722.67%116.67%
Nicholas Piggin56.67%116.67%
Vlastimil Babka11.33%116.67%
Total75100.00%6100.00%

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)]; }

Contributors

PersonTokensPropCommitsCommitProp
Rik Van Riel1145.83%133.33%
Nicholas Piggin1041.67%133.33%
Rusty Russell312.50%133.33%
Total24100.00%3100.00%


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(); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin3597.22%150.00%
Linus Torvalds12.78%150.00%
Total36100.00%2100.00%

/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ struct wait_page_key { struct page *page; int bit_nr; int page_match; }; struct wait_page_queue { struct page *page; int bit_nr; wait_queue_entry_t wait; };
static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (wait_page->page != key->page) return 0; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return 0; /* Stop walking if it's locked */ if (test_bit(key->bit_nr, &key->page->flags)) return -1; return autoremove_wake_function(wait, mode, sync, key); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin10093.46%120.00%
Linus Torvalds32.80%120.00%
Rik Van Riel21.87%120.00%
Ingo Molnar10.93%120.00%
Rusty Russell10.93%120.00%
Total107100.00%5100.00%


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); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin10055.56%266.67%
Tim Chen8044.44%133.33%
Total180100.00%3100.00%


static void wake_up_page(struct page *page, int bit) { if (!PageWaiters(page)) return; wake_up_page_bit(page, bit); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin2996.67%266.67%
William Lee Irwin III13.33%133.33%
Total30100.00%3100.00%


static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, bool lock) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; int ret = 0; init_wait(wait); wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; for (;;) { spin_lock_irq(&q->lock); if (likely(list_empty(&wait->entry))) { __add_wait_queue_entry_tail(q, wait); SetPageWaiters(page); } set_current_state(state); spin_unlock_irq(&q->lock); if (likely(test_bit(bit_nr, &page->flags))) { io_schedule(); } if (lock) { if (!test_and_set_bit_lock(bit_nr, &page->flags)) break; } else { if (!test_bit(bit_nr, &page->flags)) break; } if (unlikely(signal_pending_state(state, current))) { ret = -EINTR; break; } } finish_wait(q, wait); /* * A signal could leave PageWaiters set. Clearing it here if * !waitqueue_active would be possible (by open-coding finish_wait), * but still fail to catch it in the case of wait hash collision. We * already can fail to clear wait hash collision cases, so don't * bother with signals either. */ return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin14063.93%17.69%
Linus Torvalds3114.16%215.38%
Linus Torvalds (pre-git)2310.50%17.69%
Andrew Morton115.02%323.08%
William Lee Irwin III83.65%215.38%
Rik Van Riel20.91%17.69%
Ingo Molnar20.91%215.38%
Motohiro Kosaki20.91%17.69%
Total219100.00%13100.00%


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, false); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin1851.43%150.00%
Motohiro Kosaki1748.57%150.00%
Total35100.00%2100.00%

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, false); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin2569.44%150.00%
Motohiro Kosaki1130.56%150.00%
Total36100.00%2100.00%

EXPORT_SYMBOL(wait_on_page_bit_killable); /** * 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); }

Contributors

PersonTokensPropCommitsCommitProp
David Howells5288.14%125.00%
Nicholas Piggin58.47%125.00%
Linus Torvalds11.69%125.00%
Ingo Molnar11.69%125.00%
Total59100.00%4100.00%

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 unneccssary 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); }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds2993.55%150.00%
Olof Johansson26.45%150.00%
Total31100.00%2100.00%

#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); }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds2851.85%225.00%
Nicholas Piggin1222.22%225.00%
Kirill A. Shutemov712.96%112.50%
Sasha Levin35.56%112.50%
William Lee Irwin III35.56%112.50%
Andrew Morton11.85%112.50%
Total54100.00%8100.00%

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); } if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton3568.63%444.44%
Mel Gorman917.65%111.11%
William Lee Irwin III47.84%222.22%
Miklos Szeredi23.92%111.11%
Peter Zijlstra11.96%111.11%
Total51100.00%9100.00%

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); } }

Contributors

PersonTokensPropCommitsCommitProp
Matthew Wilcox7983.16%125.00%
MinChan Kim1212.63%125.00%
Jens Axboe33.16%125.00%
Michael Christie11.05%125.00%
Total95100.00%4100.00%

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, true); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin1638.10%120.00%
Linus Torvalds (pre-git)1433.33%120.00%
Kirill A. Shutemov819.05%120.00%
William Lee Irwin III37.14%120.00%
Andrew Morton12.38%120.00%
Total42100.00%5100.00%

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, true); }

Contributors

PersonTokensPropCommitsCommitProp
Matthew Wilcox1944.19%133.33%
Nicholas Piggin1637.21%133.33%
Kirill A. Shutemov818.60%133.33%
Total43100.00%3100.00%

EXPORT_SYMBOL_GPL(__lock_page_killable); /* * Return values: * 1 - page is locked; mmap_sem is still held. * 0 - page is not locked. * mmap_sem has been released (up_read()), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_sem is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 * with the page locked and the mmap_sem unperturbed. */
int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { if (flags & FAULT_FLAG_ALLOW_RETRY) { /* * CAUTION! In this case, mmap_sem is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return 0; up_read(&mm->mmap_sem); if (flags & FAULT_FLAG_KILLABLE) wait_on_page_locked_killable(page); else wait_on_page_locked(page); return 0; } else { if (flags & FAULT_FLAG_KILLABLE) { int ret; ret = __lock_page_killable(page); if (ret) { up_read(&mm->mmap_sem); return 0; } } else __lock_page(page); return 1; } }

Contributors

PersonTokensPropCommitsCommitProp
Motohiro Kosaki5650.00%133.33%
Michel Lespinasse5044.64%133.33%
Gleb Natapov65.36%133.33%
Total112100.00%3100.00%

/** * page_cache_next_hole - find the next hole (not-present entry) * @mapping: mapping * @index: index * @max_scan: maximum range to search * * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the * lowest indexed hole. * * Returns: the index of the hole if found, otherwise returns an index * outside of the set specified (in which case 'return - index >= * max_scan' will be true). In rare cases of index wrap-around, 0 will * be returned. * * page_cache_next_hole may be called under rcu_read_lock. However, * like radix_tree_gang_lookup, this will not atomically search a * snapshot of the tree at a single point in time. For example, if a * hole is created at index 5, then subsequently a hole is created at * index 10, page_cache_next_hole covering both indexes may return 10 * if called under rcu_read_lock. */
pgoff_t page_cache_next_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { unsigned long i; for (i = 0; i < max_scan; i++) { struct page *page; page = radix_tree_lookup(&mapping->i_pages, index); if (!page || radix_tree_exceptional_entry(page)) break; index++; if (index == 0) break; } return index; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner7698.70%266.67%
Matthew Wilcox11.30%133.33%
Total77100.00%3100.00%

EXPORT_SYMBOL(page_cache_next_hole); /** * page_cache_prev_hole - find the prev hole (not-present entry) * @mapping: mapping * @index: index * @max_scan: maximum range to search * * Search backwards in the range [max(index-max_scan+1, 0), index] for * the first hole. * * Returns: the index of the hole if found, otherwise returns an index * outside of the set specified (in which case 'index - return >= * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX * will be returned. * * page_cache_prev_hole may be called under rcu_read_lock. However, * like radix_tree_gang_lookup, this will not atomically search a * snapshot of the tree at a single point in time. For example, if a * hole is created at index 10, then subsequently a hole is created at * index 5, page_cache_prev_hole covering both indexes may return 5 if * called under rcu_read_lock. */
pgoff_t page_cache_prev_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { unsigned long i; for (i = 0; i < max_scan; i++) { struct page *page; page = radix_tree_lookup(&mapping->i_pages, index); if (!page || radix_tree_exceptional_entry(page)) break; index--; if (index == ULONG_MAX) break; } return index; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner7698.70%266.67%
Matthew Wilcox11.30%133.33%
Total77100.00%3100.00%

EXPORT_SYMBOL(page_cache_prev_hole); /** * find_get_entry - find and get a page cache entry * @mapping: the address_space to search * @offset: the page cache index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it 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. * * Otherwise, %NULL is returned. */
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *head, *page; rcu_read_lock(); repeat: page = NULL; pagep = radix_tree_lookup_slot(&mapping->i_pages, offset); if (pagep) { page = radix_tree_deref_slot(pagep); if (unlikely(!page)) goto out; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(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. */ goto out; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* * Has the page moved? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != *pagep)) { put_page(head); goto repeat; } } out: rcu_read_unlock(); return page; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin7143.56%213.33%
Linus Torvalds (pre-git)4024.54%426.67%
Kirill A. Shutemov3219.63%213.33%
Hugh Dickins148.59%213.33%
Johannes Weiner21.23%213.33%
Andrew Morton21.23%16.67%
Matthew Wilcox10.61%16.67%
Fengguang Wu10.61%16.67%
Total163100.00%15100.00%

EXPORT_SYMBOL(find_get_entry); /** * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search * @offset: the page cache 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. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Otherwise, %NULL is returned. * * find_lock_entry() may sleep. */
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page_mapping(page) != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); } return page; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)5358.24%942.86%
Nicholas Piggin1010.99%29.52%
Kirill A. Shutemov77.69%29.52%
Hugh Dickins66.59%14.76%
Linus Torvalds55.49%29.52%
Sasha Levin33.30%14.76%
Nikita Danilov33.30%14.76%
Johannes Weiner22.20%14.76%
Andrew Morton11.10%14.76%
Fengguang Wu11.10%14.76%
Total91100.00%21100.00%

EXPORT_SYMBOL(find_lock_entry); /** * pagecache_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * @fgp_flags: PCG flags * @gfp_mask: gfp mask to use for the page cache data page allocation * * Looks up the page cache slot at @mapping & @offset. * * PCG flags modify how the page is returned. * * @fgp_flags can be: * * - FGP_ACCESSED: the page will be marked accessed * - FGP_LOCK: Page is return locked * - FGP_CREAT: If page is not 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. Otherwise, NULL is returned. * * 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. */
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t gfp_mask) { struct page *page; repeat: page = find_get_entry(mapping, offset); if (radix_tree_exceptional_entry(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(page->index != offset, page); } if (page && (fgp_flags & FGP_ACCESSED)) mark_page_accessed(page); no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(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_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, offset, gfp_mask); if (unlikely(err)) { put_page(page); page = NULL; if (err == -EEXIST) goto repeat; } } return page; }

Contributors

PersonTokensPropCommitsCommitProp
Mel Gorman16257.04%17.14%
Linus Torvalds4014.08%214.29%
Johannes Weiner3713.03%17.14%
Andrew Morton227.75%428.57%
Nicholas Piggin103.52%17.14%
Michal Hocko51.76%17.14%
Kirill A. Shutemov31.06%17.14%
Arnaldo Carvalho de Melo20.70%17.14%
Hugh Dickins20.70%17.14%
Christoph Lameter10.35%17.14%
Total284100.00%14100.00%

EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @nr_entries: The maximum number of entries * @entries: 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 group of up to * @nr_entries entries in the mapping. The entries are placed at * @entries. find_get_entries() takes a reference against 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. * * find_get_entries() returns the number of pages and shadow entries * which were found. */
unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { void **slot; unsigned int ret = 0; struct radix_tree_iter iter; if (!nr_entries) return 0; rcu_read_lock(); radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } /* * 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. */ goto export; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* Has the page moved? */ if (unlikely(page != *slot)) { put_page(head); goto repeat; } export: indices[ret] = iter.index; entries[ret] = page; if (++ret == nr_entries) break; } rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Johannes Weiner16878.87%116.67%
Kirill A. Shutemov3215.02%233.33%
Matthew Wilcox125.63%233.33%
Ross Zwisler10.47%116.67%
Total213100.00%6100.00%

/** * 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. * * find_get_pages_range() returns 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) { struct radix_tree_iter iter; void **slot; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, *start) { struct page *head, *page; if (iter.index > end) break; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } /* * A shadow entry of a recently evicted page, * or a swap entry from shmem/tmpfs. Skip * over it. */ continue; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* Has the page moved? */ if (unlikely(page != *slot)) { put_page(head); goto repeat; } pages[ret] = page; if (++ret == nr_pages) { *start = pages[ret - 1]->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 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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin6926.64%212.50%
Jan Kara6424.71%212.50%
Andrew Morton3915.06%212.50%
Kirill A. Shutemov3212.36%212.50%
Konstantin Khlebnikov3111.97%16.25%
Hugh Dickins176.56%425.00%
Matthew Wilcox62.32%212.50%
Johannes Weiner10.39%16.25%
Total259100.00%16100.00%

/** * 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. * * find_get_pages_contig() returns 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) { struct radix_tree_iter iter; void **slot; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) { struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); /* The hole, there no reason to continue */ if (unlikely(!page)) break; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } /* * A shadow entry of a recently evicted page, * or a swap entry from shmem/tmpfs. Stop * looking for contiguous pages. */ break; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* Has the page moved? */ if (unlikely(page != *slot)) { put_page(head); goto repeat; } /* * must check mapping and index after taking the ref. * otherwise we can get both false positives and false * negatives, which is just confusing to the caller. */ if (page->mapping == NULL || page_to_pgoff(page) != iter.index) { put_page(page); break; } pages[ret] = page; if (++ret == nr_pages) break; } rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin8838.94%216.67%
Jens Axboe3917.26%18.33%
Konstantin Khlebnikov3816.81%18.33%
Kirill A. Shutemov3615.93%216.67%
Hugh Dickins146.19%325.00%
Matthew Wilcox104.42%216.67%
Johannes Weiner10.44%18.33%
Total226100.00%12100.00%

EXPORT_SYMBOL(find_get_pages_contig); /** * find_get_pages_range_tag - find and return pages in given range 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 pages which are tagged with * @tag. We update @index to index the next page for the traversal. */
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, int tag, unsigned int nr_pages, struct page **pages) { struct radix_tree_iter iter; void **slot; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) { struct page *head, *page; if (iter.index > end) break; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } /* * A shadow entry of a recently evicted page. * * Those entries should never be tagged, but * this tree walk is lockless and the tags are * looked up in bulk, one radix tree node at a * time, so there is a sizable window for page * reclaim to evict a page we saw tagged. * * Skip over it. */ continue; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* Has the page moved? */ if (unlikely(page != *slot)) { put_page(head); goto repeat; } pages[ret] = page; if (++ret == nr_pages) { *index = pages[ret - 1]->index + 1; goto out; } } /* * We come here when we got at @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the * iteration when there is 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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin6625.00%17.69%
Andrew Morton5520.83%215.38%
Jan Kara5219.70%17.69%
Kirill A. Shutemov3212.12%215.38%
Konstantin Khlebnikov3111.74%17.69%
Hugh Dickins166.06%323.08%
Matthew Wilcox103.79%215.38%
Johannes Weiner20.76%17.69%
Total264100.00%13100.00%

EXPORT_SYMBOL(find_get_pages_range_tag); /** * find_get_entries_tag - find and return entries that match @tag * @mapping: the address_space to search * @start: the starting page cache index * @tag: the tag index * @nr_entries: the maximum number of entries * @entries: where the resulting entries are placed * @indices: the cache indices corresponding to the entries in @entries * * Like find_get_entries, except we only return entries which are tagged with * @tag. */
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, int tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { void **slot; unsigned int ret = 0; struct radix_tree_iter iter; if (!nr_entries) return 0; rcu_read_lock(); radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) { struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } /* * 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. */ goto export; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* Has the page moved? */ if (unlikely(page != *slot)) { put_page(head); goto repeat; } export: indices[ret] = iter.index; entries[ret] = page; if (++ret == nr_entries) break; } rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Ross Zwisler17680.73%120.00%
Kirill A. Shutemov3214.68%240.00%
Matthew Wilcox104.59%240.00%
Total218100.00%5100.00%

EXPORT_SYMBOL(find_get_entries_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 *filp, struct file_ra_state *ra) { ra->ra_pages /= 4; }

Contributors

PersonTokensPropCommitsCommitProp
Fengguang Wu22100.00%1100.00%
Total22100.00%1100.00%

/** * generic_file_buffered_read - generic file read routine * @iocb: the iocb to read * @iter: data destination * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. */
static ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t written) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; loff_t *ppos = &iocb->ki_pos; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error = 0; if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; prev_offset = ra->prev_pos & (PAGE_SIZE-1); last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: if (fatal_signal_pending(current)) { error = -EINTR; goto out; } page = find_get_page(mapping, index); if (!page) { if (iocb->ki_flags & IOCB_NOWAIT) goto would_block; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } if (!PageUptodate(page)) { if (iocb->ki_flags & IOCB_NOWAIT) { put_page(page); goto would_block; } /* * See comment in do_read_cache_page on why * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ error = wait_on_page_locked_killable(page); if (unlikely(error)) goto readpage_error; if (PageUptodate(page)) goto page_ok; if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ if (unlikely(iter->type & ITER_PIPE)) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; /* Did it get truncated before we got the lock? */ if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } page_ok: /* * i_size must be checked after we know the page is 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); end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ nr = PAGE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { put_page(page); goto out; } } nr = nr - offset; /* 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 (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; prev_offset = offset; put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; if (ret < nr) { error = -EFAULT; goto out; } continue; page_not_up_to_date: /* Get exclusive access to the page ... */ error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); put_page(page); continue; } /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: /* * 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(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { put_page(page); error = 0; goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_mapping_pages got it */ unlock_page(page); put_page(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(filp, ra); error = -EIO; goto readpage_error; } unlock_page(page); } goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ put_page(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ page = page_cache_alloc(mapping); if (!page) { error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { put_page(page); if (error == -EEXIST) { error = 0; goto find_page; } goto out; } goto readpage; } would_block: error = -EAGAIN; out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds14014.30%56.76%
Andrew Morton11812.05%1317.57%
Neil Brown929.40%11.35%
Fengguang Wu747.56%56.76%
Linus Torvalds (pre-git)676.84%1418.92%
Al Viro585.92%45.41%
Nicholas Piggin575.82%45.41%
Hisashi Hifumi495.01%11.35%
Christoph Hellwig424.29%34.05%
Milosz Tanski363.68%11.35%
Oleg Nesterov343.47%22.70%
Wei Fang272.76%11.35%
Michal Hocko232.35%34.05%
Kirill A. Shutemov222.25%11.35%
Steven Pratt181.84%11.35%
Jan Kara171.74%22.70%
Mel Gorman171.74%22.70%
Zach Brown171.74%11.35%
Eryu Guan151.53%11.35%
Bart Van Assche121.23%11.35%
Miquel van Smoorenburg121.23%22.70%
Dave Hansen111.12%11.35%
Matthew Wilcox80.82%11.35%
Jeff Moyer60.61%11.35%
David Howells30.31%11.35%
Rusty Russell20.20%11.35%
Ingo Molnar20.20%11.35%
Total979100.00%74100.00%

/** * 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. */
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) goto out; /* 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) goto out; } file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } 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)) goto out; } retval = generic_file_buffered_read(iocb, iter, retval); out: return retval; }

Contributors

PersonTokensPropCommitsCommitProp
Christoph Hellwig5422.88%416.00%
Al Viro4117.37%728.00%
Goldwyn Rodrigues3615.25%14.00%
Linus Torvalds3213.56%28.00%
Nicolai Stange177.20%14.00%
Andrew Morton177.20%416.00%
Josef Bacik125.08%14.00%
Dmitriy Monakhov104.24%14.00%
Matthew Wilcox62.54%14.00%
Nicholas Piggin62.54%14.00%
Steven Whitehouse41.69%14.00%
Linus Torvalds (pre-git)10.42%14.00%
Total236100.00%25100.00%

EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU /** * page_cache_read - adds requested page to the page cache if not already there * @file: file to read * @offset: page index * @gfp_mask: memory allocation flags * * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. */
static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) { struct address_space *mapping = file->f_mapping; struct page *page; int ret; do { page = __page_cache_alloc(gfp_mask); if (!page) return -ENOMEM; ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST) ret = 0; /* losing race to add is OK */ put_page(page); } while (ret == AOP_TRUNCATED_PAGE); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Christoph Hellwig7364.60%112.50%
Zach Brown2925.66%112.50%
Michal Hocko76.19%225.00%
Andrew Morton21.77%225.00%
Kirill A. Shutemov10.88%112.50%
Fengguang Wu10.88%112.50%
Total113100.00%8100.00%

#define MMAP_LOTSAMISS (100) /* * Synchronous readahead happens when we don't even find * a page in the page cache at all. */
static void do_sync_mmap_readahead(struct vm_area_struct *vma, struct file_ra_state *ra, struct file *file, pgoff_t offset) { struct address_space *mapping = file->f_mapping; /* If we don't want any read-ahead, don't bother */ if (vma->vm_flags & VM_RAND_READ) return; if (!ra->ra_pages) return; if (vma->vm_flags & VM_SEQ_READ) { page_cache_sync_readahead(mapping, ra, file, offset, ra->ra_pages); return; } /* Avoid banging the cache line if not needed */ if (ra->mmap_miss < MMAP_LOTSAMISS * 10) ra->mmap_miss++; /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (ra->mmap_miss > MMAP_LOTSAMISS) return; /* * mmap read-around */ ra->start = max_t(long, 0, offset - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ra_submit(ra, mapping, file); }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds9563.33%112.50%
Fengguang Wu3724.67%450.00%
Joe Perches85.33%112.50%
Roman Gushchin64.00%112.50%
Andi Kleen42.67%112.50%
Total150100.00%8100.00%

/* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further.. */
static void do_async_mmap_readahead(struct vm_area_struct *vma, struct file_ra_state *ra, struct file *file, struct page *page, pgoff_t offset) { struct address_space *mapping = file->f_mapping; /* If we don't want any read-ahead, don't bother */ if (vma->vm_flags & VM_RAND_READ) return; if (ra->mmap_miss > 0) ra->mmap_miss--; if (PageReadahead(page)) page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds7891.76%133.33%
Joe Perches44.71%133.33%
Fengguang Wu33.53%133.33%
Total85100.00%3100.00%

/** * 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_sem must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because * lock_page_or_retry() returned 0. * The mmap_sem has usually been released in this case. * See __lock_page_or_retry() for the exception. * * If our return value does not have VM_FAULT_RETRY set, the mmap_sem * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. */
vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; 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. */ do_async_mmap_readahead(vmf->vma, ra, file, page, offset); } else if (!page) { /* No page in the page cache at all */ do_sync_mmap_readahead(vmf->vma, ra, file, offset); count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; retry_find: page = find_get_page(mapping, offset); if (!page) goto no_cached_page; } if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) { put_page(page); return ret | VM_FAULT_RETRY; } /* Did it get truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto retry_find; } VM_BUG_ON_PAGE(page->index != 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; /* * 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; no_cached_page: /* * We're only likely to ever get here if MADV_RANDOM is in * effect. */ error = page_cache_read(file, offset, vmf->gfp_mask); /* * The page we want has now been added to the page cache. * In the unlikely event that someone removed it in the * meantime, we'll just come back here and read it again. */ if (error >= 0) goto retry_find; /* * An error return from page_cache_read can result if the * system is low on memory, or a problem occurs while trying * to schedule I/O. */ if (error == -ENOMEM) return VM_FAULT_OOM; return VM_FAULT_SIGBUS; 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); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; /* Things didn't work out. Return zero to tell the mm layer so. */ shrink_readahead_size_eio(file, ra); return VM_FAULT_SIGBUS; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)10122.65%1527.78%
Michel Lespinasse6314.13%35.56%
Linus Torvalds5512.33%611.11%
Nicholas Piggin5311.88%47.41%
Andrew Morton368.07%814.81%
Miklos Szeredi255.61%11.85%
Fengguang Wu173.81%23.70%
Shaohua Li153.36%11.85%
David Howells143.14%11.85%
Matthew Wilcox122.69%11.85%
Kirill A. Shutemov112.47%23.70%
Zach Brown102.24%11.85%
Dave Jiang102.24%11.85%
Ying Han81.79%11.85%
Yan Zheng40.90%11.85%
Michal Hocko40.90%11.85%
Sasha Levin30.67%11.85%
Souptick Joarder20.45%11.85%
Johannes Weiner10.22%11.85%
Roman Gushchin10.22%11.85%
Steven Pratt10.22%11.85%
Total446100.00%54100.00%

EXPORT_SYMBOL(filemap_fault);
void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct radix_tree_iter iter; void **slot; struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long max_idx; struct page *head, *page; rcu_read_lock(); radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) { if (iter.index > end_pgoff) break; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) goto next; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } goto next; } head = compound_head(page); if (!page_cache_get_speculative(head)) goto repeat; /* The page was split under us? */ if (compound_head(page) != head) { put_page(head); goto repeat; } /* Has the page moved? */ if (unlikely(page != *slot)) { put_page(head); goto repeat; } if (!PageUptodate(page) || PageReadahead(page) || PageHWPoison(page)) goto skip; if (!trylock_page(page)) goto skip; if (page->mapping != mapping || !PageUptodate(page)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (page->index >= max_idx) goto unlock; if (file->f_ra.mmap_miss > 0) file->f_ra.mmap_miss--; vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) vmf->pte += iter.index - last_pgoff; last_pgoff = iter.index; if (alloc_set_pte(vmf, NULL, page)) goto unlock; unlock_page(page); goto next; unlock: unlock_page(page); skip: put_page(page); next: /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) break; if (iter.index == end_pgoff) break; } rcu_read_unlock(); }

Contributors

PersonTokensPropCommitsCommitProp
Kirill A. Shutemov35893.23%660.00%
Matthew Wilcox184.69%330.00%
Jan Kara82.08%110.00%
Total384100.00%10100.00%

EXPORT_SYMBOL(filemap_map_pages);
vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the page dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty page and writeprotect it again. */ set_page_dirty(page); wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Jan Kara9286.79%233.33%
Darrick J. Wong54.72%116.67%
Dave Jiang43.77%116.67%
Al Viro32.83%116.67%
Souptick Joarder21.89%116.67%
Total106100.00%6100.00%

const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */
int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton2446.15%228.57%
Nicholas Piggin2038.46%114.29%
Linus Torvalds (pre-git)47.69%228.57%
Jeff Moyer35.77%114.29%
Ingo Molnar11.92%114.29%
Total52100.00%7100.00%

/* * This is for filesystems which do not implement ->writepage. */
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) return -EINVAL; return generic_file_mmap(file, vma); }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton45100.00%2100.00%
Total45100.00%2100.00%

#else
int filemap_page_mkwrite(struct vm_fault *vmf) { return -ENOSYS; }

Contributors

PersonTokensPropCommitsCommitProp
Arnd Bergmann14100.00%1100.00%
Total14100.00%1100.00%


int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; }

Contributors

PersonTokensPropCommitsCommitProp
Christoph Hellwig19100.00%1100.00%
Total19100.00%1100.00%


int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton19100.00%1100.00%
Total19100.00%1100.00%

#endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap);
static struct page *wait_on_page_read(struct page *page) { if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { put_page(page); page = ERR_PTR(-EIO); } } return page; }

Contributors

PersonTokensPropCommitsCommitProp
Sasha Levin5398.15%150.00%
Kirill A. Shutemov11.85%150.00%
Total54100.00%2100.00%


static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data, gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for radix tree node */ return ERR_PTR(err); } filler: err = filler(data, page); if (err < 0) { put_page(page); return ERR_PTR(err); } page = wait_on_page_read(page); if (IS_ERR(page)) return page; goto out; } if (PageUptodate(page)) goto out; /* * Page is not up to date and may be locked due one of the following * case a: Page is being filled and the page lock is held * case b: Read/write error clearing the page uptodate status * case c: Truncation in progress (page locked) * case d: Reclaim in progress * * Case a, the page will be up to date when the page is unlocked. * There is no need to serialise on the page lock here as the page * is pinned so the lock gives no additional protection. Even if the * the page is truncated, the data is still valid if PageUptodate as * it's a race vs truncate race. * Case b, the page will not be up to date * Case c, the page may be truncated but in itself, the data may still * be valid after IO completes as it's a read vs truncate race. The * operation must restart if the page is not uptodate on unlock but * otherwise serialising on page lock to stabilise the mapping gives * no additional guarantees to the caller as the page lock is * released before return. * Case d, similar to truncation. If reclaim holds the page lock, it * will be a race with remove_mapping that determines if the mapping * is valid on unlock but otherwise the data is valid and there is * no need to serialise with page lock. * * As the page lock gives no additional guarantee, we optimistically * wait on the page to be unlocked and check if it's up to date and * use the page if it is. Otherwise, the page lock is required to * distinguish between the different cases. The motivation is that we * avoid spurious serialisations and wakeups when multiple processes * wait on the same page for IO to complete. */ wait_on_page_locked(page); if (PageUptodate(page)) goto out; /* Distinguish between all the cases under the safety of the lock */ lock_page(page); /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); put_page(page); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (PageUptodate(page)) { unlock_page(page); goto out; } goto filler; out: mark_page_accessed(page); return page; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)15960.69%315.79%
Mel Gorman3111.83%210.53%
Nicholas Piggin249.16%210.53%
Andrew Morton238.78%421.05%
Linus Torvalds103.82%315.79%
Sasha Levin72.67%15.26%
Kirill A. Shutemov31.15%15.26%
David Howells31.15%15.26%
Dave Kleikamp10.38%15.26%
Fengguang Wu10.38%15.26%
Total262100.00%19100.00%

/** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */
struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin3876.00%125.00%
Linus Torvalds1020.00%125.00%
Sasha Levin12.00%125.00%
Fengguang Wu12.00%125.00%
Total50100.00%4100.00%

EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. */
struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { filler_t *filler = (filler_t *)mapping->a_ops->readpage; return do_read_cache_page(mapping, index, filler, NULL, gfp); }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds2758.70%133.33%
Al Viro1123.91%133.33%
Nicholas Piggin817.39%133.33%
Total46100.00%3100.00%

EXPORT_SYMBOL(read_cache_page_gfp); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */
inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; unsigned long limit = rlimit(RLIMIT_FSIZE); loff_t pos; if (!iov_iter_count(from)) return 0; /* FIXME: this is for backwards compatibility with 2.4 */ if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); pos = iocb->ki_pos; if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) return -EINVAL; if (limit != RLIM_INFINITY) { if (iocb->ki_pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } iov_iter_truncate(from, limit - (unsigned long)pos); } /* * LFS rule */ if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS && !(file->f_flags & O_LARGEFILE))) { if (pos >= MAX_NON_LFS) return -EFBIG; iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos); } /* * Are we about to exceed the fs block limit ? * * If we have written data it becomes a short write. If we have * exceeded without writing data we send a signal and return EFBIG. * Linus frestrict idea will clean these up nicely.. */ if (unlikely(pos >= inode->i_sb->s_maxbytes)) return -EFBIG; iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos); return iov_iter_count(from); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin9339.41%17.69%
Al Viro5724.15%215.38%
Linus Torvalds3715.68%323.08%
Goldwyn Rodrigues239.75%17.69%
Andrew Morton198.05%430.77%
Linus Torvalds (pre-git)41.69%17.69%
Jiri Slaby31.27%17.69%
Total236100.00%13100.00%

EXPORT_SYMBOL(generic_write_checks);
int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin4569.23%133.33%
Andrew Morton1523.08%133.33%
Christoph Hellwig57.69%133.33%
Total65100.00%3100.00%

EXPORT_SYMBOL(pagecache_write_begin);
int pagecache_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_end(file, mapping, pos, len, copied, page, fsdata); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin5892.06%250.00%
Christoph Hellwig34.76%125.00%
Hisashi Hifumi23.17%125.00%
Total63100.00%4100.00%

EXPORT_SYMBOL(pagecache_write_end);
ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written; size_t write_len; pgoff_t end; write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ if (filemap_range_has_page(inode->i_mapping, pos, pos + iov_iter_count(from))) return -EAGAIN; } else { written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) goto out; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ if (written) { if (written == -EBUSY) return 0; goto out; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely */ if (mapping->nrpages) invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin9936.67%320.00%
Christoph Hellwig8330.74%213.33%
Goldwyn Rodrigues3613.33%16.67%
Al Viro248.89%426.67%
Hisashi Hifumi124.44%16.67%
Lukas Czerner72.59%16.67%
Namhyung Kim51.85%16.67%
Kirill A. Shutemov31.11%16.67%
Andrey Ryabinin10.37%16.67%
Total270100.00%15100.00%

EXPORT_SYMBOL(generic_file_direct_write); /* * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */
struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { struct page *page; int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; if (flags & AOP_FLAG_NOFS) fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); return page; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin4970.00%457.14%
Mel Gorman1622.86%114.29%
Darrick J. Wong57.14%228.57%
Total70100.00%7100.00%

EXPORT_SYMBOL(grab_cache_page_write_begin);
ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; unsigned int flags = 0; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ void *fsdata; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * Not only is this an optimisation, but it is also required * to check that the address is actually valid, when atomic * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) break; copied = status; cond_resched(); iov_iter_advance(i, copied); if (unlikely(copied == 0)) { /* * If we were unable to copy any data at all, we must * fall back to a single segment length write. * * If we didn't fallback here, we could livelock * because not all segments in the iov can be copied at * once without a pagefault. */ bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } pos += copied; written += copied; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); return written ? written : status; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin12541.39%833.33%
Christoph Hellwig8829.14%28.33%
Andrew Morton3110.26%625.00%
Linus Torvalds227.28%28.33%
Jan Kara154.97%14.17%
Anfei Zhou123.97%14.17%
Kirill A. Shutemov30.99%14.17%
Zach Brown30.99%14.17%
Mel Gorman20.66%14.17%
Daniel McNeil10.33%14.17%
Total302100.00%24100.00%

EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_mutex to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. */
ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; ssize_t status; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; err = file_update_time(file); if (err) goto out; if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos, endbyte; written = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; status = generic_perform_write(file, from, pos = iocb->ki_pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ if (unlikely(status < 0)) { err = status; goto out; } /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + status - 1; err = filemap_write_and_wait_range(mapping, pos, endbyte); if (err == 0) { iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return * the number of bytes which were direct-written */ } } else { written = generic_perform_write(file, from, iocb->ki_pos); if (likely(written > 0)) iocb->ki_pos += written; } out: current->backing_dev_info = NULL; return written ? written : err; }

Contributors

PersonTokensPropCommitsCommitProp
Christoph Hellwig8932.60%518.52%
Jeff Moyer6824.91%13.70%
Al Viro6724.54%414.81%
Andrew Morton176.23%518.52%
Linus Torvalds (pre-git)124.40%622.22%
Josef Bacik93.30%13.70%
Matthew Wilcox62.20%13.70%
Kirill A. Shutemov20.73%13.70%
Jan Kara10.37%13.70%
Mika Kukkonen10.37%13.70%
Linus Torvalds10.37%13.70%
Total273100.00%27100.00%

EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. */
ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton4550.00%323.08%
Al Viro2224.44%430.77%
Benjamin LaHaise1617.78%17.69%
Jan Kara33.33%17.69%
Christoph Hellwig22.22%215.38%
Badari Pulavarty11.11%17.69%
Rusty Russell11.11%17.69%
Total90100.00%13100.00%

EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page * * @page: the page which the kernel is trying to free * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page * (presumably at page->private). If the release was successful, return '1'. * Otherwise return zero. * * This may also be called if PG_fscache is set on a page, indicating that the * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). * */
int try_to_release_page(struct page *page, gfp_t gfp_mask) { struct address_space * const mapping = page->mapping; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping && mapping->a_ops->releasepage) return mapping->a_ops->releasepage(page, gfp_mask); return try_to_free_buffers(page); }

Contributors

PersonTokensPropCommitsCommitProp
David Howells70100.00%1100.00%
Total70100.00%1100.00%

EXPORT_SYMBOL(try_to_release_page);

Overall Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin163914.99%316.75%
Andrew Morton8637.89%5812.64%
Kirill A. Shutemov8487.75%112.40%
Johannes Weiner7827.15%143.05%
Jan Kara7667.01%224.79%
Linus Torvalds7236.61%296.32%
Linus Torvalds (pre-git)5755.26%5712.42%
Christoph Hellwig4944.52%204.36%
Jeff Layton3873.54%91.96%
Al Viro2932.68%235.01%
Mel Gorman2792.55%91.96%
Matthew Wilcox2432.22%91.96%
Miklos Szeredi2121.94%40.87%
Ross Zwisler2081.90%40.87%
Hugh Dickins1741.59%91.96%
Goldwyn Rodrigues1721.57%20.44%
David Howells1701.55%71.53%
Fengguang Wu1591.45%102.18%
Michel Lespinasse1131.03%30.65%
Zach Brown1091.00%20.44%
Konstantin Khlebnikov1030.94%20.44%
Motohiro Kosaki1010.92%30.65%
Neil Brown920.84%10.22%
Sasha Levin870.80%20.44%
Dmitriy Monakhov840.77%20.44%
Tim Chen800.73%10.22%
Jeff Moyer770.70%30.65%
Suparna Bhattacharya720.66%20.44%
Jens Axboe630.58%30.65%
Hisashi Hifumi630.58%30.65%
Michal Hocko620.57%61.31%
Jun'ichi Nomura510.47%10.22%
Hirofumi Ogawa510.47%20.44%
Paul Jackson430.39%10.22%
Arnaldo Carvalho de Melo360.33%10.22%
Milosz Tanski360.33%10.22%
Oleg Nesterov340.31%20.44%
Dan Magenheimer290.27%20.44%
Rik Van Riel280.26%30.65%
Wei Fang270.25%10.22%
Balbir Singh250.23%30.65%
Tejun Heo250.23%30.65%
MinChan Kim230.21%30.65%
Benjamin LaHaise220.20%20.44%
Josef Bacik210.19%20.44%
Arnd Bergmann210.19%20.44%
Steven Pratt190.17%10.22%
William Lee Irwin III190.17%20.44%
Nicolai Stange170.16%10.22%
Miao Xie170.16%10.22%
Eryu Guan150.14%10.22%
Shaohua Li150.14%10.22%
Dave Jiang150.14%10.22%
Joe Perches120.11%10.22%
Daisuke Nishimura120.11%10.22%
Miquel van Smoorenburg120.11%20.44%
Anfei Zhou120.11%10.22%
Bart Van Assche120.11%10.22%
Greg Thelen110.10%10.22%
Ingo Molnar110.10%51.09%
Robert Jarzmik110.10%10.22%
Dave Hansen110.10%10.22%
Rusty Russell100.09%30.65%
Darrick J. Wong100.09%20.44%
Evgeniy Polyakov100.09%10.22%
Randy Dunlap90.08%51.09%
Ying Han80.07%10.22%
Lukas Czerner70.06%10.22%
Christoph Lameter70.06%20.44%
Roman Gushchin70.06%20.44%
Gleb Natapov60.05%10.22%
Kamezawa Hiroyuki60.05%10.22%
Chris Mason50.05%10.22%
Namhyung Kim50.05%10.22%
Nathan Scott50.05%10.22%
Steven Whitehouse40.04%10.22%
Andi Kleen40.04%10.22%
Souptick Joarder40.04%10.22%
Yan Zheng40.04%10.22%
Jiri Slaby30.03%10.22%
Marcelo Tosatti30.03%10.22%
Mauro Carvalho Chehab30.03%10.22%
JoonSoo Kim30.03%10.22%
Stephen D. Smalley30.03%10.22%
Hiro Yoshioka30.03%10.22%
Nikita Danilov30.03%10.22%
Olof Johansson20.02%10.22%
Badari Pulavarty20.02%20.44%
Heiko Carstens20.02%10.22%
Dave Kleikamp20.02%10.22%
Vlastimil Babka10.01%10.22%
Mika Kukkonen10.01%10.22%
Paul Gortmaker10.01%10.22%
Paul Cassella10.01%10.22%
Andrey Ryabinin10.01%10.22%
Alexey Dobriyan10.01%10.22%
Daniel McNeil10.01%10.22%
Michael Christie10.01%10.22%
Peter Zijlstra10.01%10.22%
Total10935100.00%459100.00%
Directory: mm
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.