From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/mm/filemap.c | 1999 +++++++++++++++++++++++++++++++++-------------------------
1 files changed, 1,134 insertions(+), 865 deletions(-)
diff --git a/kernel/mm/filemap.c b/kernel/mm/filemap.c
index 9bf5437..580c1b9 100644
--- a/kernel/mm/filemap.c
+++ b/kernel/mm/filemap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/filemap.c
*
@@ -24,6 +25,7 @@
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
+#include <linux/error-injection.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
@@ -38,10 +40,17 @@
#include <linux/rmap.h>
#include <linux/delayacct.h>
#include <linux/psi.h>
+#include <linux/ramfs.h>
+#include <linux/page_idle.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/filemap.h>
+
+#undef CREATE_TRACE_POINTS
+#include <trace/hooks/mm.h>
/*
* FIXME: remove all knowledge of the buffer layer from the core VM
@@ -73,16 +82,16 @@
* ->i_mutex
* ->i_mmap_rwsem (truncate->unmap_mapping_range)
*
- * ->mmap_sem
+ * ->mmap_lock
* ->i_mmap_rwsem
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->i_pages lock (arch-dependent flush_dcache_mmap_lock)
*
- * ->mmap_sem
+ * ->mmap_lock
* ->lock_page (access_process_vm)
*
* ->i_mutex (generic_perform_write)
- * ->mmap_sem (fault_in_pages_readable->do_page_fault)
+ * ->mmap_lock (fault_in_pages_readable->do_page_fault)
*
* bdi->wb.list_lock
* sb_lock (fs/fs-writeback.c)
@@ -98,8 +107,8 @@
* ->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)
+ * ->pgdat->lru_lock (follow_page->mark_page_accessed)
+ * ->pgdat->lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->i_pages lock (page_remove_rmap->set_page_dirty)
* bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
@@ -113,60 +122,26 @@
* ->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;
-}
-
-static void page_cache_tree_delete(struct address_space *mapping,
+static void page_cache_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
- int i, nr;
+ XA_STATE(xas, &mapping->i_pages, page->index);
+ unsigned int nr = 1;
- /* hugetlb pages are represented by one entry in the radix tree */
- nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
+ mapping_set_update(&xas, mapping);
+
+ /* hugetlb pages are represented by a single entry in the xarray */
+ if (!PageHuge(page)) {
+ xas_set_order(&xas, page->index, compound_order(page));
+ nr = compound_nr(page);
+ }
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(nr != 1 && shadow, page);
- 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));
- }
+ xas_store(&xas, shadow);
+ xas_init_marks(&xas);
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
@@ -194,12 +169,10 @@
* 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)) {
- count_vm_event(PGPGOUTCLEAN);
+ if (PageUptodate(page) && PageMappedToDisk(page))
cleancache_put_page(page);
- } else {
+ else
cleancache_invalidate_page(mapping, page);
- }
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(page_mapped(page), page);
@@ -230,15 +203,16 @@
if (PageHuge(page))
return;
- nr = hpage_nr_pages(page);
+ nr = thp_nr_pages(page);
- __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+ __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr);
if (PageSwapBacked(page)) {
- __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
+ __mod_lruvec_page_state(page, NR_SHMEM, -nr);
if (PageTransHuge(page))
__dec_node_page_state(page, NR_SHMEM_THPS);
- } else {
- VM_BUG_ON_PAGE(PageTransHuge(page), page);
+ } else if (PageTransHuge(page)) {
+ __dec_node_page_state(page, NR_FILE_THPS);
+ filemap_nr_thps_dec(mapping);
}
/*
@@ -267,7 +241,7 @@
trace_mm_filemap_delete_from_page_cache(page);
unaccount_page_cache_page(mapping, page);
- page_cache_tree_delete(mapping, page, shadow);
+ page_cache_delete(mapping, page, shadow);
}
static void page_cache_free_page(struct address_space *mapping,
@@ -280,7 +254,7 @@
freepage(page);
if (PageTransHuge(page) && !PageHuge(page)) {
- page_ref_sub(page, HPAGE_PMD_NR);
+ page_ref_sub(page, thp_nr_pages(page));
VM_BUG_ON_PAGE(page_count(page) <= 0, page);
} else {
put_page(page);
@@ -310,61 +284,62 @@
EXPORT_SYMBOL(delete_from_page_cache);
/*
- * page_cache_tree_delete_batch - delete several pages from page cache
+ * page_cache_delete_batch - delete several pages from page cache
* @mapping: the mapping to which pages belong
* @pvec: pagevec with pages to delete
*
* The function walks over mapping->i_pages and removes pages passed in @pvec
- * from the mapping. The function expects @pvec to be sorted by page index.
+ * from the mapping. The function expects @pvec to be sorted by page index
+ * and is optimised for it to be dense.
* It tolerates holes in @pvec (mapping entries at those indices are not
* modified). The function expects only THP head pages to be present in the
- * @pvec and takes care to delete all corresponding tail pages from the
- * mapping as well.
+ * @pvec.
*
* The function expects the i_pages lock to be held.
*/
-static void
-page_cache_tree_delete_batch(struct address_space *mapping,
+static void page_cache_delete_batch(struct address_space *mapping,
struct pagevec *pvec)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
int total_pages = 0;
- int i = 0, tail_pages = 0;
+ int i = 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)
+ mapping_set_update(&xas, mapping);
+ xas_for_each(&xas, page, ULONG_MAX) {
+ if (i >= pagevec_count(pvec))
break;
- page = radix_tree_deref_slot_protected(slot,
- &mapping->i_pages.xa_lock);
- if (radix_tree_exceptional_entry(page))
+
+ /* A swap/dax/shadow entry got inserted? Skip it. */
+ if (xa_is_value(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--;
+ /*
+ * A page got inserted in our range? Skip it. We have our
+ * pages locked so they are protected from being removed.
+ * If we see a page whose index is higher than ours, it
+ * means our page has been removed, which shouldn't be
+ * possible because we're holding the PageLock.
+ */
+ if (page != pvec->pages[i]) {
+ VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
+ page);
+ continue;
}
- radix_tree_clear_tags(&mapping->i_pages, iter.node, slot);
- __radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL,
- workingset_lookup_update(mapping));
+
+ WARN_ON_ONCE(!PageLocked(page));
+
+ if (page->index == xas.xa_index)
+ page->mapping = NULL;
+ /* Leave page->index set: truncation lookup relies on it */
+
+ /*
+ * Move to the next page in the vector if this is a regular
+ * page or the index is of the last sub-page of this compound
+ * page.
+ */
+ if (page->index + compound_nr(page) - 1 == xas.xa_index)
+ i++;
+ xas_store(&xas, NULL);
total_pages++;
}
mapping->nrpages -= total_pages;
@@ -385,7 +360,7 @@
unaccount_page_cache_page(mapping, pvec->pages[i]);
}
- page_cache_tree_delete_batch(mapping, pvec);
+ page_cache_delete_batch(mapping, pvec);
xa_unlock_irqrestore(&mapping->i_pages, flags);
for (i = 0; i < pagevec_count(pvec); i++)
@@ -430,6 +405,8 @@
* opposed to a regular memory cleansing writeback. The difference between
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
@@ -442,7 +419,7 @@
.range_end = end,
};
- if (!mapping_cap_writeback_dirty(mapping) ||
+ if (!mapping_can_writeback(mapping) ||
!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
@@ -477,6 +454,8 @@
*
* This is a mostly non-blocking flush. Not suitable for data-integrity
* purposes - I/O may not be started against all dirty pages.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int filemap_flush(struct address_space *mapping)
{
@@ -492,24 +471,38 @@
*
* Find at least one page in the range supplied, usually used to check if
* direct writing in this range will trigger a writeback.
+ *
+ * Return: %true if at least one page exists in the specified range,
+ * %false otherwise.
*/
bool filemap_range_has_page(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
- pgoff_t index = start_byte >> PAGE_SHIFT;
- pgoff_t end = end_byte >> PAGE_SHIFT;
struct page *page;
+ XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
+ pgoff_t max = end_byte >> PAGE_SHIFT;
if (end_byte < start_byte)
return false;
- if (mapping->nrpages == 0)
- return false;
+ rcu_read_lock();
+ for (;;) {
+ page = xas_find(&xas, max);
+ if (xas_retry(&xas, page))
+ continue;
+ /* Shadow entries don't count */
+ if (xa_is_value(page))
+ continue;
+ /*
+ * We don't need to try to pin this page; we're about to
+ * release the RCU lock anyway. It is enough to know that
+ * there was a page here recently.
+ */
+ break;
+ }
+ rcu_read_unlock();
- if (!find_get_pages_range(mapping, &index, end, 1, &page))
- return false;
- put_page(page);
- return true;
+ return page != NULL;
}
EXPORT_SYMBOL(filemap_range_has_page);
@@ -557,6 +550,8 @@
* Since the error status of the address space is cleared by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
+ *
+ * Return: error status of the address space.
*/
int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
loff_t end_byte)
@@ -601,6 +596,8 @@
* Since the error status of the file is advanced by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
+ *
+ * Return: error status of the address space vs. the file->f_wb_err cursor.
*/
int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
{
@@ -622,6 +619,8 @@
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
+ *
+ * Return: error status of the address space.
*/
int filemap_fdatawait_keep_errors(struct address_space *mapping)
{
@@ -630,38 +629,14 @@
}
EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
+/* Returns true if writeback might be needed or already in progress. */
static bool mapping_needs_writeback(struct address_space *mapping)
{
- return (!dax_mapping(mapping) && mapping->nrpages) ||
- (dax_mapping(mapping) && mapping->nrexceptional);
-}
+ if (dax_mapping(mapping))
+ return mapping->nrexceptional;
-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;
+ return mapping->nrpages;
}
-EXPORT_SYMBOL(filemap_write_and_wait);
/**
* filemap_write_and_wait_range - write out & wait on a file range
@@ -673,6 +648,8 @@
*
* Note that @lend is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
+ *
+ * Return: error status of the address space.
*/
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
@@ -682,7 +659,12 @@
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
- /* See comment of filemap_write_and_wait() */
+ /*
+ * Even if the above returned error, the pages may be
+ * written partially (e.g. -ENOSPC), so we wait for it.
+ * But the -EIO is special case, it may indicate the worst
+ * thing (e.g. bug) happened, so we avoid waiting for it.
+ */
if (err != -EIO) {
int err2 = filemap_fdatawait_range(mapping,
lstart, lend);
@@ -728,6 +710,8 @@
* While we handle mapping->wb_err with atomic operations, the f_wb_err
* value is protected by the f_lock since we must ensure that it reflects
* the latest value swapped in for this file descriptor.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int file_check_and_advance_wb_err(struct file *file)
{
@@ -770,6 +754,8 @@
*
* After writing out and waiting on the data, we check and advance the
* f_wb_err cursor to the latest value, and return any errors detected there.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
{
@@ -802,107 +788,135 @@
* 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.
+ * The remove + add is atomic. This function cannot fail.
+ *
+ * Return: %0
*/
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
{
- int error;
+ struct address_space *mapping = old->mapping;
+ void (*freepage)(struct page *) = mapping->a_ops->freepage;
+ pgoff_t offset = old->index;
+ XA_STATE(xas, &mapping->i_pages, offset);
+ unsigned long flags;
VM_BUG_ON_PAGE(!PageLocked(old), old);
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
- error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
- if (!error) {
- struct address_space *mapping = old->mapping;
- void (*freepage)(struct page *);
- unsigned long flags;
+ get_page(new);
+ new->mapping = mapping;
+ new->index = offset;
- pgoff_t offset = old->index;
- freepage = mapping->a_ops->freepage;
+ mem_cgroup_migrate(old, new);
- get_page(new);
- new->mapping = mapping;
- new->index = offset;
+ xas_lock_irqsave(&xas, flags);
+ xas_store(&xas, new);
- xa_lock_irqsave(&mapping->i_pages, flags);
- __delete_from_page_cache(old, NULL);
- error = page_cache_tree_insert(mapping, new, NULL);
- BUG_ON(error);
+ old->mapping = NULL;
+ /* hugetlb pages do not participate in page cache accounting. */
+ if (!PageHuge(old))
+ __dec_lruvec_page_state(old, NR_FILE_PAGES);
+ if (!PageHuge(new))
+ __inc_lruvec_page_state(new, NR_FILE_PAGES);
+ if (PageSwapBacked(old))
+ __dec_lruvec_page_state(old, NR_SHMEM);
+ if (PageSwapBacked(new))
+ __inc_lruvec_page_state(new, NR_SHMEM);
+ xas_unlock_irqrestore(&xas, flags);
+ if (freepage)
+ freepage(old);
+ put_page(old);
- /*
- * 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;
+ return 0;
}
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)
+noinline int __add_to_page_cache_locked(struct page *page,
+ struct address_space *mapping,
+ pgoff_t offset, gfp_t gfp,
+ void **shadowp)
{
+ XA_STATE(xas, &mapping->i_pages, offset);
int huge = PageHuge(page);
- struct mem_cgroup *memcg;
int error;
+ bool charged = false;
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;
- }
+ mapping_set_update(&xas, mapping);
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;
+ if (!huge) {
+ error = mem_cgroup_charge(page, current->mm, gfp);
+ if (error)
+ goto error;
+ charged = true;
+ }
- /* 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);
+ gfp &= GFP_RECLAIM_MASK;
+
+ do {
+ unsigned int order = xa_get_order(xas.xa, xas.xa_index);
+ void *entry, *old = NULL;
+
+ if (order > thp_order(page))
+ xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
+ order, gfp);
+ xas_lock_irq(&xas);
+ xas_for_each_conflict(&xas, entry) {
+ old = entry;
+ if (!xa_is_value(entry)) {
+ xas_set_err(&xas, -EEXIST);
+ goto unlock;
+ }
+ }
+
+ if (old) {
+ if (shadowp)
+ *shadowp = old;
+ /* entry may have been split before we acquired lock */
+ order = xa_get_order(xas.xa, xas.xa_index);
+ if (order > thp_order(page)) {
+ xas_split(&xas, old, order);
+ xas_reset(&xas);
+ }
+ }
+
+ xas_store(&xas, page);
+ if (xas_error(&xas))
+ goto unlock;
+
+ if (old)
+ mapping->nrexceptional--;
+ mapping->nrpages++;
+
+ /* hugetlb pages do not participate in page cache accounting */
+ if (!huge)
+ __inc_lruvec_page_state(page, NR_FILE_PAGES);
+unlock:
+ xas_unlock_irq(&xas);
+ } while (xas_nomem(&xas, gfp));
+
+ if (xas_error(&xas)) {
+ error = xas_error(&xas);
+ if (charged)
+ mem_cgroup_uncharge(page);
+ goto error;
+ }
+
trace_mm_filemap_add_to_page_cache(page);
return 0;
-err_insert:
+error:
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;
}
+ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
/**
* add_to_page_cache_locked - add a locked page to the pagecache
@@ -913,6 +927,8 @@
*
* This function is used to add a page to the pagecache. It must be locked.
* This function does not add the page to the LRU. The caller must do that.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
@@ -1001,37 +1017,89 @@
page_writeback_init();
}
-/* 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;
-};
-
+/*
+ * The page wait code treats the "wait->flags" somewhat unusually, because
+ * we have multiple different kinds of waits, not just the usual "exclusive"
+ * one.
+ *
+ * We have:
+ *
+ * (a) no special bits set:
+ *
+ * We're just waiting for the bit to be released, and when a waker
+ * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
+ * and remove it from the wait queue.
+ *
+ * Simple and straightforward.
+ *
+ * (b) WQ_FLAG_EXCLUSIVE:
+ *
+ * The waiter is waiting to get the lock, and only one waiter should
+ * be woken up to avoid any thundering herd behavior. We'll set the
+ * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
+ *
+ * This is the traditional exclusive wait.
+ *
+ * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
+ *
+ * The waiter is waiting to get the bit, and additionally wants the
+ * lock to be transferred to it for fair lock behavior. If the lock
+ * cannot be taken, we stop walking the wait queue without waking
+ * the waiter.
+ *
+ * This is the "fair lock handoff" case, and in addition to setting
+ * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
+ * that it now has the lock.
+ */
static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
{
+ unsigned int flags;
struct wait_page_key *key = arg;
struct wait_page_queue *wait_page
= container_of(wait, struct wait_page_queue, wait);
- if (wait_page->page != key->page)
- return 0;
- key->page_match = 1;
-
- if (wait_page->bit_nr != key->bit_nr)
+ if (!wake_page_match(wait_page, key))
return 0;
- /* Stop walking if it's locked */
- if (test_bit(key->bit_nr, &key->page->flags))
- return -1;
+ /*
+ * If it's a lock handoff wait, we get the bit for it, and
+ * stop walking (and do not wake it up) if we can't.
+ */
+ flags = wait->flags;
+ if (flags & WQ_FLAG_EXCLUSIVE) {
+ if (test_bit(key->bit_nr, &key->page->flags))
+ return -1;
+ if (flags & WQ_FLAG_CUSTOM) {
+ if (test_and_set_bit(key->bit_nr, &key->page->flags))
+ return -1;
+ flags |= WQ_FLAG_DONE;
+ }
+ }
- return autoremove_wake_function(wait, mode, sync, key);
+ /*
+ * We are holding the wait-queue lock, but the waiter that
+ * is waiting for this will be checking the flags without
+ * any locking.
+ *
+ * So update the flags atomically, and wake up the waiter
+ * afterwards to avoid any races. This store-release pairs
+ * with the load-acquire in wait_on_page_bit_common().
+ */
+ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
+ wake_up_state(wait->private, mode);
+
+ /*
+ * Ok, we have successfully done what we're waiting for,
+ * and we can unconditionally remove the wait entry.
+ *
+ * Note that this pairs with the "finish_wait()" in the
+ * waiter, and has to be the absolute last thing we do.
+ * After this list_del_init(&wait->entry) the wait entry
+ * might be de-allocated and the process might even have
+ * exited.
+ */
+ list_del_init_careful(&wait->entry);
+ return (flags & WQ_FLAG_EXCLUSIVE) != 0;
}
static void wake_up_page_bit(struct page *page, int bit_nr)
@@ -1095,91 +1163,250 @@
wake_up_page_bit(page, bit);
}
-static inline __sched int wait_on_page_bit_common(wait_queue_head_t *q,
- struct page *page, int bit_nr, int state, bool lock)
+/*
+ * A choice of three behaviors for wait_on_page_bit_common():
+ */
+enum behavior {
+ EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
+ * __lock_page() waiting on then setting PG_locked.
+ */
+ SHARED, /* Hold ref to page and check the bit when woken, like
+ * wait_on_page_writeback() waiting on PG_writeback.
+ */
+ DROP, /* Drop ref to page before wait, no check when woken,
+ * like put_and_wait_on_page_locked() on PG_locked.
+ */
+};
+
+/*
+ * Attempt to check (or get) the page bit, and mark us done
+ * if successful.
+ */
+static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
+ struct wait_queue_entry *wait)
{
+ if (wait->flags & WQ_FLAG_EXCLUSIVE) {
+ if (test_and_set_bit(bit_nr, &page->flags))
+ return false;
+ } else if (test_bit(bit_nr, &page->flags))
+ return false;
+
+ wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
+ return true;
+}
+
+/* How many times do we accept lock stealing from under a waiter? */
+int sysctl_page_lock_unfairness = 5;
+
+static inline __sched int wait_on_page_bit_common(wait_queue_head_t *q,
+ struct page *page, int bit_nr, int state, enum behavior behavior)
+{
+ int unfairness = sysctl_page_lock_unfairness;
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
bool thrashing = false;
+ bool delayacct = false;
unsigned long pflags;
- int ret = 0;
if (bit_nr == PG_locked &&
!PageUptodate(page) && PageWorkingset(page)) {
- if (!PageSwapBacked(page))
+ if (!PageSwapBacked(page)) {
delayacct_thrashing_start();
+ delayacct = true;
+ }
psi_memstall_enter(&pflags);
thrashing = true;
}
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);
+repeat:
+ wait->flags = 0;
+ if (behavior == EXCLUSIVE) {
+ wait->flags = WQ_FLAG_EXCLUSIVE;
+ if (--unfairness < 0)
+ wait->flags |= WQ_FLAG_CUSTOM;
+ }
- if (likely(list_empty(&wait->entry))) {
- __add_wait_queue_entry_tail(q, wait);
- SetPageWaiters(page);
- }
+ /*
+ * Do one last check whether we can get the
+ * page bit synchronously.
+ *
+ * Do the SetPageWaiters() marking before that
+ * to let any waker we _just_ missed know they
+ * need to wake us up (otherwise they'll never
+ * even go to the slow case that looks at the
+ * page queue), and add ourselves to the wait
+ * queue if we need to sleep.
+ *
+ * This part needs to be done under the queue
+ * lock to avoid races.
+ */
+ spin_lock_irq(&q->lock);
+ SetPageWaiters(page);
+ if (!trylock_page_bit_common(page, bit_nr, wait))
+ __add_wait_queue_entry_tail(q, wait);
+ spin_unlock_irq(&q->lock);
+
+ /*
+ * From now on, all the logic will be based on
+ * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
+ * see whether the page bit testing has already
+ * been done by the wake function.
+ *
+ * We can drop our reference to the page.
+ */
+ if (behavior == DROP)
+ put_page(page);
+
+ /*
+ * Note that until the "finish_wait()", or until
+ * we see the WQ_FLAG_WOKEN flag, we need to
+ * be very careful with the 'wait->flags', because
+ * we may race with a waker that sets them.
+ */
+ for (;;) {
+ unsigned int flags;
set_current_state(state);
- spin_unlock_irq(&q->lock);
+ /* Loop until we've been woken or interrupted */
+ flags = smp_load_acquire(&wait->flags);
+ if (!(flags & WQ_FLAG_WOKEN)) {
+ if (signal_pending_state(state, current))
+ break;
- if (likely(test_bit(bit_nr, &page->flags))) {
io_schedule();
+ continue;
}
- 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;
+ /* If we were non-exclusive, we're done */
+ if (behavior != EXCLUSIVE)
break;
- }
+
+ /* If the waker got the lock for us, we're done */
+ if (flags & WQ_FLAG_DONE)
+ break;
+
+ /*
+ * Otherwise, if we're getting the lock, we need to
+ * try to get it ourselves.
+ *
+ * And if that fails, we'll have to retry this all.
+ */
+ if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
+ goto repeat;
+
+ wait->flags |= WQ_FLAG_DONE;
+ break;
}
+ /*
+ * If a signal happened, this 'finish_wait()' may remove the last
+ * waiter from the wait-queues, but the PageWaiters bit will remain
+ * set. That's ok. The next wakeup will take care of it, and trying
+ * to do it here would be difficult and prone to races.
+ */
finish_wait(q, wait);
if (thrashing) {
- if (!PageSwapBacked(page))
+ if (delayacct)
delayacct_thrashing_end();
psi_memstall_leave(&pflags);
}
/*
- * 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.
+ * NOTE! The wait->flags weren't stable until we've done the
+ * 'finish_wait()', and we could have exited the loop above due
+ * to a signal, and had a wakeup event happen after the signal
+ * test but before the 'finish_wait()'.
+ *
+ * So only after the finish_wait() can we reliably determine
+ * if we got woken up or not, so we can now figure out the final
+ * return value based on that state without races.
+ *
+ * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
+ * waiter, but an exclusive one requires WQ_FLAG_DONE.
*/
+ if (behavior == EXCLUSIVE)
+ return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
- return ret;
+ return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
-void __sched wait_on_page_bit(struct page *page, int bit_nr)
+__sched 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);
+ wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit);
-int __sched wait_on_page_bit_killable(struct page *page, int bit_nr)
+__sched 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);
+ return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit_killable);
+
+static int __wait_on_page_locked_async(struct page *page,
+ struct wait_page_queue *wait, bool set)
+{
+ struct wait_queue_head *q = page_waitqueue(page);
+ int ret = 0;
+
+ wait->page = page;
+ wait->bit_nr = PG_locked;
+
+ spin_lock_irq(&q->lock);
+ __add_wait_queue_entry_tail(q, &wait->wait);
+ SetPageWaiters(page);
+ if (set)
+ ret = !trylock_page(page);
+ else
+ ret = PageLocked(page);
+ /*
+ * If we were succesful now, we know we're still on the
+ * waitqueue as we're still under the lock. This means it's
+ * safe to remove and return success, we know the callback
+ * isn't going to trigger.
+ */
+ if (!ret)
+ __remove_wait_queue(q, &wait->wait);
+ else
+ ret = -EIOCBQUEUED;
+ spin_unlock_irq(&q->lock);
+ return ret;
+}
+
+static int wait_on_page_locked_async(struct page *page,
+ struct wait_page_queue *wait)
+{
+ if (!PageLocked(page))
+ return 0;
+ return __wait_on_page_locked_async(compound_head(page), wait, false);
+}
+
+/**
+ * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
+ * @page: The page to wait for.
+ *
+ * The caller should hold a reference on @page. They expect the page to
+ * become unlocked relatively soon, but do not wish to hold up migration
+ * (for example) by holding the reference while waiting for the page to
+ * come unlocked. After this function returns, the caller should not
+ * dereference @page.
+ */
+void put_and_wait_on_page_locked(struct page *page)
+{
+ wait_queue_head_t *q;
+
+ page = compound_head(page);
+ q = page_waitqueue(page);
+ wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP);
+}
/**
* add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
@@ -1211,7 +1438,7 @@
* 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
+ * being cleared, but a memory barrier should be unnecessary since it is
* in the same byte as PG_locked.
*/
static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
@@ -1227,7 +1454,7 @@
* unlock_page - unlock a locked page
* @page: the page
*
- * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
+ * 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.
@@ -1266,11 +1493,19 @@
rotate_reclaimable_page(page);
}
+ /*
+ * Writeback does not hold a page reference of its own, relying
+ * on truncation to wait for the clearing of PG_writeback.
+ * But here we must make sure that the page is not freed and
+ * reused before the wake_up_page().
+ */
+ get_page(page);
if (!test_clear_page_writeback(page))
BUG();
smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
+ put_page(page);
}
EXPORT_SYMBOL(end_page_writeback);
@@ -1306,45 +1541,52 @@
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @__page: the page to lock
*/
-void __sched __lock_page(struct page *__page)
+__sched 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);
+ wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
+ EXCLUSIVE);
}
EXPORT_SYMBOL(__lock_page);
-int __sched __lock_page_killable(struct page *__page)
+__sched 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);
+ return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
+ EXCLUSIVE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
+__sched int __lock_page_async(struct page *page, struct wait_page_queue *wait)
+{
+ return __wait_on_page_locked_async(page, wait, true);
+}
+
/*
* Return values:
- * 1 - page is locked; mmap_sem is still held.
+ * 1 - page is locked; mmap_lock is still held.
* 0 - page is not locked.
- * mmap_sem has been released (up_read()), unless flags had both
+ * mmap_lock has been released (mmap_read_unlock(), unless flags had both
* FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
- * which case mmap_sem is still held.
+ * which case mmap_lock is still held.
*
* If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
- * with the page locked and the mmap_sem unperturbed.
+ * with the page locked and the mmap_lock unperturbed.
*/
-int __sched __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+__sched int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
- if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (fault_flag_allow_retry_first(flags)) {
/*
- * CAUTION! In this case, mmap_sem is not released
+ * CAUTION! In this case, mmap_lock is not released
* even though return 0.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
if (flags & FAULT_FLAG_KILLABLE)
wait_on_page_locked_killable(page);
else
@@ -1356,7 +1598,7 @@
ret = __lock_page_killable(page);
if (ret) {
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
return 0;
}
} else
@@ -1366,224 +1608,203 @@
}
/**
- * page_cache_next_hole - find the next hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
+ * page_cache_next_miss() - Find the next gap in the page cache.
+ * @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.
+ * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
+ * gap with the lowest index.
*
- * 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.
+ * This function may be called under the rcu_read_lock. However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 5, then subsequently a gap is
+ * created at index 10, page_cache_next_miss covering both indices may
+ * return 10 if called under the rcu_read_lock.
*
- * 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.
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'return - index >= max_scan' will be true).
+ * In the rare case of index wrap-around, 0 will be returned.
*/
-pgoff_t page_cache_next_hole(struct address_space *mapping,
+pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
- unsigned long i;
+ XA_STATE(xas, &mapping->i_pages, index);
- 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))
+ while (max_scan--) {
+ void *entry = xas_next(&xas);
+ if (!entry || xa_is_value(entry))
break;
- index++;
- if (index == 0)
+ if (xas.xa_index == 0)
break;
}
- return index;
+ return xas.xa_index;
}
-EXPORT_SYMBOL(page_cache_next_hole);
+EXPORT_SYMBOL(page_cache_next_miss);
/**
- * page_cache_prev_hole - find the prev hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
+ * page_cache_prev_miss() - Find the previous gap in the page cache.
+ * @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.
+ * Search the range [max(index - max_scan + 1, 0), index] for the
+ * gap with the highest index.
*
- * 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.
+ * This function may be called under the rcu_read_lock. However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 10, then subsequently a gap is
+ * created at index 5, page_cache_prev_miss() covering both indices may
+ * return 5 if called under the rcu_read_lock.
*
- * 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.
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'index - return >= max_scan' will be true).
+ * In the rare case of wrap-around, ULONG_MAX will be returned.
*/
-pgoff_t page_cache_prev_hole(struct address_space *mapping,
+pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
- unsigned long i;
+ XA_STATE(xas, &mapping->i_pages, index);
- 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))
+ while (max_scan--) {
+ void *entry = xas_prev(&xas);
+ if (!entry || xa_is_value(entry))
break;
- index--;
- if (index == ULONG_MAX)
+ if (xas.xa_index == ULONG_MAX)
break;
}
- return index;
+ return xas.xa_index;
}
-EXPORT_SYMBOL(page_cache_prev_hole);
+EXPORT_SYMBOL(page_cache_prev_miss);
/**
* find_get_entry - find and get a page cache entry
* @mapping: the address_space to search
- * @offset: the page cache index
+ * @index: 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.
+ * page cache page, the head page is returned with an increased refcount.
*
* If the slot holds a shadow entry of a previously evicted page, or a
* swap entry from shmem/tmpfs, it is returned.
*
- * Otherwise, %NULL is returned.
+ * Return: The head page or shadow entry, %NULL if nothing is found.
*/
-struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t index)
{
- void **pagep;
- struct page *head, *page;
+ XA_STATE(xas, &mapping->i_pages, index);
+ struct page *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;
- }
+ xas_reset(&xas);
+ page = xas_load(&xas);
+ if (xas_retry(&xas, page))
+ goto repeat;
+ /*
+ * A shadow entry of a recently evicted page, or a swap entry from
+ * shmem/tmpfs. Return it without attempting to raise page count.
+ */
+ if (!page || xa_is_value(page))
+ goto out;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- goto repeat;
+ if (!page_cache_get_speculative(page))
+ 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;
- }
+ /*
+ * Has the page moved or been split?
+ * This is part of the lockless pagecache protocol. See
+ * include/linux/pagemap.h for details.
+ */
+ if (unlikely(page != xas_reload(&xas))) {
+ put_page(page);
+ goto repeat;
}
out:
rcu_read_unlock();
return page;
}
-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
+ * find_lock_entry - Locate and lock a page cache entry.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
*
- * Looks up the page cache slot at @mapping & @offset. If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * Looks up the page at @mapping & @index. If there is a page in the
+ * cache, the head page 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.
+ * Context: May sleep.
+ * Return: The head page or shadow entry, %NULL if nothing is found.
*/
-struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index)
{
struct page *page;
repeat:
- page = find_get_entry(mapping, offset);
- if (page && !radix_tree_exception(page)) {
+ page = find_get_entry(mapping, index);
+ if (page && !xa_is_value(page)) {
lock_page(page);
/* Has the page been truncated? */
- if (unlikely(page_mapping(page) != mapping)) {
+ if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto repeat;
}
- VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
+ VM_BUG_ON_PAGE(!thp_contains(page, index), page);
}
return page;
}
-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
+ * pagecache_get_page - Find and get a reference to a page.
+ * @mapping: The address_space to search.
+ * @index: The page index.
+ * @fgp_flags: %FGP flags modify how the page is returned.
+ * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified.
*
- * Looks up the page cache slot at @mapping & @offset.
+ * Looks up the page cache entry at @mapping & @index.
*
- * PCG flags modify how the page is returned.
+ * @fgp_flags can be zero or more of these flags:
*
- * @fgp_flags can be:
+ * * %FGP_ACCESSED - The page will be marked accessed.
+ * * %FGP_LOCK - The page is returned locked.
+ * * %FGP_HEAD - If the page is present and a THP, return the head page
+ * rather than the exact page specified by the index.
+ * * %FGP_CREAT - If no page is present then a new page is allocated using
+ * @gfp_mask and added to the page cache and the VM's LRU list.
+ * The page is returned locked and with an increased refcount.
+ * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
+ * page is already in cache. If the page was allocated, unlock it before
+ * returning so the caller can do the same dance.
+ * * %FGP_WRITE - The page will be written
+ * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask
+ * * %FGP_NOWAIT - Don't get blocked by page lock
*
- * - 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.
- * - FGP_FOR_MMAP: Similar to FGP_CREAT, only we want to allow the caller to do
- * its own locking dance if the page is already in cache, or unlock the page
- * before returning if we had to add the page to pagecache.
- *
- * 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 %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
+ * if the %GFP flags specified for %FGP_CREAT are atomic.
*
* If there is a page cache page, it is returned with an increased refcount.
+ *
+ * Return: The found page or %NULL otherwise.
*/
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
- int fgp_flags, gfp_t gfp_mask)
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp_mask)
{
struct page *page;
repeat:
- page = find_get_entry(mapping, offset);
- if (radix_tree_exceptional_entry(page))
+ page = find_get_entry(mapping, index);
+ if (xa_is_value(page))
page = NULL;
+
+ trace_android_vh_pagecache_get_page(mapping, index, fgp_flags,
+ gfp_mask, page);
if (!page)
goto no_page;
@@ -1603,16 +1824,23 @@
put_page(page);
goto repeat;
}
- VM_BUG_ON_PAGE(page->index != offset, page);
+ VM_BUG_ON_PAGE(!thp_contains(page, index), page);
}
- if (page && (fgp_flags & FGP_ACCESSED))
+ if (fgp_flags & FGP_ACCESSED)
mark_page_accessed(page);
+ else if (fgp_flags & FGP_WRITE) {
+ /* Clear idle flag for buffer write */
+ if (page_is_idle(page))
+ clear_page_idle(page);
+ }
+ if (!(fgp_flags & FGP_HEAD))
+ page = find_subpage(page, index);
no_page:
if (!page && (fgp_flags & FGP_CREAT)) {
int err;
- if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+ if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
gfp_mask |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp_mask &= ~__GFP_FS;
@@ -1628,7 +1856,7 @@
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
- err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
+ err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
if (unlikely(err)) {
put_page(page);
page = NULL;
@@ -1668,60 +1896,61 @@
* 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.
+ * If it finds a Transparent Huge Page, head or tail, find_get_entries()
+ * stops at that page: the caller is likely to have a better way to handle
+ * the compound page as a whole, and then skip its extent, than repeatedly
+ * calling find_get_entries() to return all its tails.
+ *
+ * Return: the number of pages and shadow entries which were found.
*/
unsigned find_get_entries(struct address_space *mapping,
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices)
{
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, start);
+ struct page *page;
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))
+ xas_for_each(&xas, page, ULONG_MAX) {
+ if (xas_retry(&xas, 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.
- */
+ /*
+ * A shadow entry of a recently evicted page, a swap
+ * entry from shmem/tmpfs or a DAX entry. Return it
+ * without attempting to raise page count.
+ */
+ if (xa_is_value(page))
goto export;
- }
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- goto repeat;
+ if (!page_cache_get_speculative(page))
+ goto retry;
- /* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
- /* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
+ /*
+ * Terminate early on finding a THP, to allow the caller to
+ * handle it all at once; but continue if this is hugetlbfs.
+ */
+ if (PageTransHuge(page) && !PageHuge(page)) {
+ page = find_subpage(page, xas.xa_index);
+ nr_entries = ret + 1;
}
export:
- indices[ret] = iter.index;
+ indices[ret] = xas.xa_index;
entries[ret] = page;
if (++ret == nr_entries)
break;
+ continue;
+put_page:
+ put_page(page);
+retry:
+ xas_reset(&xas);
}
rcu_read_unlock();
return ret;
@@ -1744,72 +1973,52 @@
* 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
+ * Return: the number of pages which were found. If this number is
+ * smaller than @nr_pages, the end of specified range has been
* reached.
*/
unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
pgoff_t end, unsigned int nr_pages,
struct page **pages)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, *start);
+ struct page *page;
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))
+ xas_for_each(&xas, page, end) {
+ if (xas_retry(&xas, page))
+ continue;
+ /* Skip over shadow, swap and DAX entries */
+ if (xa_is_value(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;
- }
+ if (!page_cache_get_speculative(page))
+ goto retry;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- goto repeat;
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
- /* 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;
+ pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages) {
- *start = pages[ret - 1]->index + 1;
+ *start = xas.xa_index + 1;
goto out;
}
+ continue;
+put_page:
+ put_page(page);
+retry:
+ xas_reset(&xas);
}
/*
* 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
+ * breaks the iteration when there is a page at index -1 but that is
* already broken anyway.
*/
if (end == (pgoff_t)-1)
@@ -1832,69 +2041,44 @@
* 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.
+ * Return: the number of pages which were found.
*/
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
unsigned int nr_pages, struct page **pages)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, index);
+ struct page *page;
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;
- }
-
+ for (page = xas_load(&xas); page; page = xas_next(&xas)) {
+ if (xas_retry(&xas, page))
+ continue;
/*
- * 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 the entry has been swapped out, we can stop looking.
+ * No current caller is looking for DAX entries.
*/
- if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
- put_page(page);
+ if (xa_is_value(page))
break;
- }
- pages[ret] = page;
+ if (!page_cache_get_speculative(page))
+ goto retry;
+
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
+
+ pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages)
break;
+ continue;
+put_page:
+ put_page(page);
+retry:
+ xas_reset(&xas);
}
rcu_read_unlock();
return ret;
@@ -1912,76 +2096,56 @@
*
* 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.
+ *
+ * Return: the number of pages which were found.
*/
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
- pgoff_t end, int tag, unsigned int nr_pages,
+ pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
struct page **pages)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, *index);
+ struct page *page;
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))
+ xas_for_each_marked(&xas, page, end, tag) {
+ if (xas_retry(&xas, page))
+ continue;
+ /*
+ * Shadow entries should never be tagged, but this iteration
+ * is lockless so there is a window for page reclaim to evict
+ * a page we saw tagged. Skip over it.
+ */
+ if (xa_is_value(page))
continue;
- 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;
- }
+ if (!page_cache_get_speculative(page))
+ goto retry;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- goto repeat;
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
- /* 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;
+ pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages) {
- *index = pages[ret - 1]->index + 1;
+ *index = xas.xa_index + 1;
goto out;
}
+ continue;
+put_page:
+ put_page(page);
+retry:
+ xas_reset(&xas);
}
/*
- * We come here when we got at @end. We take care to not overflow the
+ * We come here when we got to @end. We take care to not overflow the
* index @index as it confuses some of the callers. This breaks the
- * iteration when there is page at index -1 but that is already broken
- * anyway.
+ * iteration when there is a page at index -1 but that is already
+ * broken anyway.
*/
if (end == (pgoff_t)-1)
*index = (pgoff_t)-1;
@@ -1993,76 +2157,6 @@
return ret;
}
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;
-}
-EXPORT_SYMBOL(find_get_entries_tag);
/*
* CD/DVDs are error prone. When a medium error occurs, the driver may fail
@@ -2079,8 +2173,7 @@
*
* 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)
+static void shrink_readahead_size_eio(struct file_ra_state *ra)
{
ra->ra_pages /= 4;
}
@@ -2096,8 +2189,12 @@
*
* This is really ugly. But the goto's actually try to clarify some
* of the logic when it comes to error handling etc.
+ *
+ * Return:
+ * * total number of bytes copied, including those the were already @written
+ * * negative error code if nothing was copied
*/
-static ssize_t generic_file_buffered_read(struct kiocb *iocb,
+ssize_t generic_file_buffered_read(struct kiocb *iocb,
struct iov_iter *iter, ssize_t written)
{
struct file *filp = iocb->ki_filp;
@@ -2114,6 +2211,9 @@
if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
return 0;
+ if (unlikely(!iov_iter_count(iter)))
+ return 0;
+
iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
index = *ppos >> PAGE_SHIFT;
@@ -2121,6 +2221,14 @@
prev_offset = ra->prev_pos & (PAGE_SIZE-1);
last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
offset = *ppos & ~PAGE_MASK;
+
+ /*
+ * If we've already successfully copied some data, then we
+ * can no longer safely return -EIOCBQUEUED. Hence mark
+ * an async read NOWAIT at that point.
+ */
+ if (written && (iocb->ki_flags & IOCB_WAITQ))
+ iocb->ki_flags |= IOCB_NOWAIT;
for (;;) {
struct page *page;
@@ -2137,7 +2245,7 @@
page = find_get_page(mapping, index);
if (!page) {
- if (iocb->ki_flags & IOCB_NOWAIT)
+ if (iocb->ki_flags & IOCB_NOIO)
goto would_block;
page_cache_sync_readahead(mapping,
ra, filp,
@@ -2147,22 +2255,34 @@
goto no_cached_page;
}
if (PageReadahead(page)) {
+ if (iocb->ki_flags & IOCB_NOIO) {
+ put_page(page);
+ goto out;
+ }
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 (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
+ error = wait_on_page_locked_async(page,
+ iocb->ki_waitq);
+ } else {
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ put_page(page);
+ goto would_block;
+ }
+ error = wait_on_page_locked_killable(page);
+ }
if (unlikely(error))
goto readpage_error;
if (PageUptodate(page))
@@ -2172,7 +2292,7 @@
!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))
+ if (unlikely(iov_iter_is_pipe(iter)))
goto page_not_up_to_date;
if (!trylock_page(page))
goto page_not_up_to_date;
@@ -2250,7 +2370,15 @@
page_not_up_to_date:
/* Get exclusive access to the page ... */
- error = lock_page_killable(page);
+ if (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
+ error = lock_page_async(page, iocb->ki_waitq);
+ } else {
+ error = lock_page_killable(page);
+ }
if (unlikely(error))
goto readpage_error;
@@ -2269,6 +2397,11 @@
}
readpage:
+ if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) {
+ unlock_page(page);
+ put_page(page);
+ goto would_block;
+ }
/*
* A previous I/O error may have been due to temporary
* failures, eg. multipath errors.
@@ -2288,7 +2421,16 @@
}
if (!PageUptodate(page)) {
- error = lock_page_killable(page);
+ if (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
+ error = lock_page_async(page, iocb->ki_waitq);
+ } else {
+ error = lock_page_killable(page);
+ }
+
if (unlikely(error))
goto readpage_error;
if (!PageUptodate(page)) {
@@ -2301,7 +2443,7 @@
goto find_page;
}
unlock_page(page);
- shrink_readahead_size_eio(filp, ra);
+ shrink_readahead_size_eio(ra);
error = -EIO;
goto readpage_error;
}
@@ -2349,6 +2491,7 @@
file_accessed(filp);
return written ? written : error;
}
+EXPORT_SYMBOL_GPL(generic_file_buffered_read);
/**
* generic_file_read_iter - generic filesystem read routine
@@ -2357,6 +2500,19 @@
*
* This is the "read_iter()" routine for all filesystems
* that can use the page cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
+ * be returned when no data can be read without waiting for I/O requests
+ * to complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
+ * requests shall be made for the read or for readahead. When no data
+ * can be read, -EAGAIN shall be returned. When readahead would be
+ * triggered, a partial, possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
*/
ssize_t
generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
@@ -2417,36 +2573,15 @@
#ifdef CONFIG_MMU
#define MMAP_LOTSAMISS (100)
-static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
- struct file *fpin)
-{
- int flags = vmf->flags;
-
- if (fpin)
- return fpin;
-
- /*
- * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
- * anything, so we only pin the file and drop the mmap_sem if only
- * FAULT_FLAG_ALLOW_RETRY is set.
- */
- if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
- FAULT_FLAG_ALLOW_RETRY) {
- fpin = get_file(vmf->vma->vm_file);
- up_read(&vmf->vma->vm_mm->mmap_sem);
- }
- return fpin;
-}
-
/*
- * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem
+ * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock
* @vmf - the vm_fault for this fault.
* @page - the page to lock.
* @fpin - the pointer to the file we may pin (or is already pinned).
*
- * This works similar to lock_page_or_retry in that it can drop the mmap_sem.
+ * This works similar to lock_page_or_retry in that it can drop the mmap_lock.
* It differs in that it actually returns the page locked if it returns 1 and 0
- * if it couldn't lock the page. If we did have to drop the mmap_sem then fpin
+ * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin
* will point to the pinned file and needs to be fput()'ed at a later point.
*/
static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
@@ -2457,7 +2592,7 @@
/*
* NOTE! This will make us return with VM_FAULT_RETRY, but with
- * the mmap_sem still held. That's how FAULT_FLAG_RETRY_NOWAIT
+ * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT
* is supposed to work. We have way too many special cases..
*/
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
@@ -2467,13 +2602,13 @@
if (vmf->flags & FAULT_FLAG_KILLABLE) {
if (__lock_page_killable(page)) {
/*
- * We didn't have the right flags to drop the mmap_sem,
+ * We didn't have the right flags to drop the mmap_lock,
* but all fault_handlers only check for fatal signals
* if we return VM_FAULT_RETRY, so we need to drop the
- * mmap_sem here and return 0 if we don't have a fpin.
+ * mmap_lock here and return 0 if we don't have a fpin.
*/
if (*fpin == NULL)
- up_read(&vmf->vma->vm_mm->mmap_sem);
+ mmap_read_unlock(vmf->vma->vm_mm);
return 0;
}
} else
@@ -2494,8 +2629,9 @@
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
+ DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
struct file *fpin = NULL;
- pgoff_t offset = vmf->pgoff;
+ unsigned int mmap_miss;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ)
@@ -2505,37 +2641,40 @@
if (vmf->vma->vm_flags & VM_SEQ_READ) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- page_cache_sync_readahead(mapping, ra, file, offset,
- ra->ra_pages);
+ page_cache_sync_ra(&ractl, ra, ra->ra_pages);
return fpin;
}
/* Avoid banging the cache line if not needed */
- if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
- ra->mmap_miss++;
+ mmap_miss = READ_ONCE(ra->mmap_miss);
+ if (mmap_miss < MMAP_LOTSAMISS * 10)
+ WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
- if (ra->mmap_miss > MMAP_LOTSAMISS)
+ if (mmap_miss > MMAP_LOTSAMISS)
return fpin;
/*
* mmap read-around
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
+ ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
- ra_submit(ra, mapping, file);
+ trace_android_vh_tune_mmap_readaround(ra->ra_pages, vmf->pgoff,
+ &ra->start, &ra->size, &ra->async_size);
+ ractl._index = ra->start;
+ do_page_cache_ra(&ractl, ra->size, ra->async_size);
return fpin;
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
* so we want to possibly extend the readahead further. We return the file that
- * was pinned if we have to drop the mmap_sem in order to do IO.
+ * was pinned if we have to drop the mmap_lock in order to do IO.
*/
static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
struct page *page)
@@ -2544,13 +2683,15 @@
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
struct file *fpin = NULL;
+ unsigned int mmap_miss;
pgoff_t offset = vmf->pgoff;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
return fpin;
- if (ra->mmap_miss > 0)
- ra->mmap_miss--;
+ mmap_miss = READ_ONCE(ra->mmap_miss);
+ if (mmap_miss)
+ WRITE_ONCE(ra->mmap_miss, --mmap_miss);
if (PageReadahead(page)) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_async_readahead(mapping, ra, file,
@@ -2570,17 +2711,19 @@
* 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 FAULT_FLAG_SPECULATIVE is set, this function runs with elevated vma
+ * refcount and with mmap lock not held.
+ * Otherwise, vma->vm_mm->mmap_lock 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 has VM_FAULT_RETRY set, it's because the mmap_lock
+ * may be dropped before doing I/O or by lock_page_maybe_drop_mmap().
*
- * If our return value does not have VM_FAULT_RETRY set, the mmap_sem
+ * If our return value does not have VM_FAULT_RETRY set, the mmap_lock
* has not been released.
*
* We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
+ *
+ * Return: bitwise-OR of %VM_FAULT_ codes.
*/
vm_fault_t filemap_fault(struct vm_fault *vmf)
{
@@ -2592,12 +2735,65 @@
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
pgoff_t max_off;
- struct page *page;
+ struct page *page = NULL;
vm_fault_t ret = 0;
+ bool retry = false;
+
+ if (vmf->flags & FAULT_FLAG_SPECULATIVE) {
+ page = find_get_page(mapping, offset);
+ if (unlikely(!page))
+ return VM_FAULT_RETRY;
+
+ if (unlikely(PageReadahead(page)))
+ goto page_put;
+
+ if (!trylock_page(page))
+ goto page_put;
+
+ if (unlikely(compound_head(page)->mapping != mapping))
+ goto page_unlock;
+ VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
+ if (unlikely(!PageUptodate(page)))
+ goto page_unlock;
+
+ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+ if (unlikely(offset >= max_off))
+ goto page_unlock;
+
+ /*
+ * Update readahead mmap_miss statistic.
+ *
+ * Note that we are not sure if finish_fault() will
+ * manage to complete the transaction. If it fails,
+ * we'll come back to filemap_fault() non-speculative
+ * case which will update mmap_miss a second time.
+ * This is not ideal, we would prefer to guarantee the
+ * update will happen exactly once.
+ */
+ if (!(vmf->vma->vm_flags & VM_RAND_READ) && ra->ra_pages) {
+ unsigned int mmap_miss = READ_ONCE(ra->mmap_miss);
+ if (mmap_miss)
+ WRITE_ONCE(ra->mmap_miss, --mmap_miss);
+ }
+
+ vmf->page = page;
+ return VM_FAULT_LOCKED;
+page_unlock:
+ unlock_page(page);
+page_put:
+ put_page(page);
+ return VM_FAULT_RETRY;
+ }
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off))
return VM_FAULT_SIGBUS;
+
+ trace_android_vh_filemap_fault_get_page(vmf, &page, &retry);
+ if (unlikely(retry))
+ goto out_retry;
+ if (unlikely(page))
+ goto page_ok;
/*
* Do we have something in the page cache already?
@@ -2630,12 +2826,12 @@
goto out_retry;
/* Did it get truncated? */
- if (unlikely(page->mapping != mapping)) {
+ if (unlikely(compound_head(page)->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto retry_find;
}
- VM_BUG_ON_PAGE(page->index != offset, page);
+ VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
/*
* We have a locked page in the page cache, now we need to check
@@ -2645,7 +2841,7 @@
goto page_not_uptodate;
/*
- * We've made it this far and we had to drop our mmap_sem, now is the
+ * We've made it this far and we had to drop our mmap_lock, now is the
* time to return to the upper layer and have it re-find the vma and
* redo the fault.
*/
@@ -2654,6 +2850,7 @@
goto out_retry;
}
+page_ok:
/*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
@@ -2690,104 +2887,197 @@
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);
+ shrink_readahead_size_eio(ra);
return VM_FAULT_SIGBUS;
out_retry:
/*
- * We dropped the mmap_sem, we need to return to the fault handler to
+ * We dropped the mmap_lock, we need to return to the fault handler to
* re-find the vma and come back and find our hopefully still populated
* page.
*/
- if (page)
+ if (page) {
+ trace_android_vh_filemap_fault_cache_page(vmf, page);
put_page(page);
+ }
if (fpin)
fput(fpin);
return ret | VM_FAULT_RETRY;
}
EXPORT_SYMBOL(filemap_fault);
-void filemap_map_pages(struct vm_fault *vmf,
- pgoff_t start_pgoff, pgoff_t end_pgoff)
+static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
{
- 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;
+ struct mm_struct *mm = vmf->vma->vm_mm;
+
+ /* Huge page is mapped? No need to proceed. */
+ if (pmd_trans_huge(*vmf->pmd)) {
+ unlock_page(page);
+ put_page(page);
+ return true;
+ }
+
+ if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
+ vm_fault_t ret = do_set_pmd(vmf, page);
+ if (!ret) {
+ /* The page is mapped successfully, reference consumed. */
+ unlock_page(page);
+ return true;
+ }
+ }
+
+ if (pmd_none(*vmf->pmd)) {
+ vmf->ptl = pmd_lock(mm, vmf->pmd);
+ if (likely(pmd_none(*vmf->pmd))) {
+ mm_inc_nr_ptes(mm);
+ pmd_populate(mm, vmf->pmd, vmf->prealloc_pte);
+ vmf->prealloc_pte = NULL;
+ }
+ spin_unlock(vmf->ptl);
+ }
+
+ /* See comment in handle_pte_fault() */
+ if (pmd_devmap_trans_unstable(vmf->pmd)) {
+ unlock_page(page);
+ put_page(page);
+ return true;
+ }
+
+ return false;
+}
+
+static struct page *next_uptodate_page(struct page *page,
+ struct address_space *mapping,
+ struct xa_state *xas, pgoff_t end_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))
+ do {
+ if (!page)
+ return NULL;
+ if (xas_retry(xas, page))
+ continue;
+ if (xa_is_value(page))
+ continue;
+ if (PageLocked(page))
+ continue;
+ if (!page_cache_get_speculative(page))
+ continue;
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(xas)))
+ goto skip;
+ if (!PageUptodate(page) || PageReadahead(page))
+ goto skip;
+ if (PageHWPoison(page))
goto skip;
if (!trylock_page(page))
goto skip;
-
- if (page->mapping != mapping || !PageUptodate(page))
+ if (page->mapping != mapping)
goto unlock;
-
+ if (!PageUptodate(page))
+ goto unlock;
max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
- if (page->index >= max_idx)
+ if (xas->xa_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;
+ return page;
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;
+ } while ((page = xas_next_entry(xas, end_pgoff)) != NULL);
+
+ return NULL;
+}
+
+static inline struct page *first_map_page(struct address_space *mapping,
+ struct xa_state *xas,
+ pgoff_t end_pgoff)
+{
+ return next_uptodate_page(xas_find(xas, end_pgoff),
+ mapping, xas, end_pgoff);
+}
+
+static inline struct page *next_map_page(struct address_space *mapping,
+ struct xa_state *xas,
+ pgoff_t end_pgoff)
+{
+ return next_uptodate_page(xas_next_entry(xas, end_pgoff),
+ mapping, xas, end_pgoff);
+}
+
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+bool filemap_allow_speculation(void)
+{
+ return true;
+}
+EXPORT_SYMBOL_GPL(filemap_allow_speculation);
+#endif
+
+vm_fault_t filemap_map_pages(struct vm_fault *vmf,
+ pgoff_t start_pgoff, pgoff_t end_pgoff)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
+ pgoff_t last_pgoff = start_pgoff;
+ unsigned long addr;
+ XA_STATE(xas, &mapping->i_pages, start_pgoff);
+ struct page *head, *page;
+ unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
+ vm_fault_t ret = (vmf->flags & FAULT_FLAG_SPECULATIVE) ?
+ VM_FAULT_RETRY : 0;
+
+ rcu_read_lock();
+ head = first_map_page(mapping, &xas, end_pgoff);
+ if (!head)
+ goto out;
+
+ if (!(vmf->flags & FAULT_FLAG_SPECULATIVE) &&
+ filemap_map_pmd(vmf, head)) {
+ ret = VM_FAULT_NOPAGE;
+ goto out;
}
+
+ addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ if (!pte_map_lock_addr(vmf, addr)) {
+ unlock_page(head);
+ put_page(head);
+ goto out;
+ }
+
+ do {
+ page = find_subpage(head, xas.xa_index);
+ if (PageHWPoison(page))
+ goto unlock;
+
+ if (mmap_miss > 0)
+ mmap_miss--;
+
+ addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
+ vmf->pte += xas.xa_index - last_pgoff;
+ last_pgoff = xas.xa_index;
+
+ if (!pte_none(*vmf->pte))
+ goto unlock;
+
+ /* We're about to handle the fault */
+ if (vmf->address == addr)
+ ret = VM_FAULT_NOPAGE;
+
+ do_set_pte(vmf, page, addr);
+ /* no need to invalidate: a not-present page won't be cached */
+ update_mmu_cache(vma, addr, vmf->pte);
+ unlock_page(head);
+ continue;
+unlock:
+ unlock_page(head);
+ put_page(head);
+ } while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL);
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+out:
rcu_read_unlock();
+ WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
+ return ret;
}
EXPORT_SYMBOL(filemap_map_pages);
@@ -2821,6 +3111,9 @@
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = filemap_page_mkwrite,
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+ .allow_speculation = filemap_allow_speculation,
+#endif
};
/* This is used for a general mmap of a disk file */
@@ -2846,9 +3139,9 @@
return generic_file_mmap(file, vma);
}
#else
-int filemap_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
{
- return -ENOSYS;
+ return VM_FAULT_SIGBUS;
}
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
@@ -2895,7 +3188,7 @@
put_page(page);
if (err == -EEXIST)
goto repeat;
- /* Presumably ENOMEM for radix tree node */
+ /* Presumably ENOMEM for xarray node */
return ERR_PTR(err);
}
@@ -2919,7 +3212,7 @@
goto out;
/*
- * Page is not up to date and may be locked due one of the following
+ * Page is not up to date and may be locked due to 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)
@@ -2928,7 +3221,7 @@
* 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
+ * 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
@@ -2994,13 +3287,16 @@
* not set, try to fill the page and wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
+ *
+ * Return: up to date page on success, ERR_PTR() on failure.
*/
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));
+ return do_read_cache_page(mapping, index, filler, data,
+ mapping_gfp_mask(mapping));
}
EXPORT_SYMBOL(read_cache_page);
@@ -3014,6 +3310,8 @@
* any new page allocations done using the specified allocation flags.
*
* If the page does not get brought uptodate, return -EIO.
+ *
+ * Return: up to date page on success, ERR_PTR() on failure.
*/
struct page *read_cache_page_gfp(struct address_space *mapping,
pgoff_t index,
@@ -3022,68 +3320,6 @@
return do_read_cache_page(mapping, index, NULL, NULL, gfp);
}
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 (IS_SWAPFILE(inode))
- return -ETXTBSY;
-
- 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);
-}
-EXPORT_SYMBOL(generic_write_checks);
int pagecache_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
@@ -3106,6 +3342,27 @@
}
EXPORT_SYMBOL(pagecache_write_end);
+/*
+ * Warn about a page cache invalidation failure during a direct I/O write.
+ */
+void dio_warn_stale_pagecache(struct file *filp)
+{
+ static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
+ char pathname[128];
+ struct inode *inode = file_inode(filp);
+ char *path;
+
+ errseq_set(&inode->i_mapping->wb_err, -EIO);
+ if (__ratelimit(&_rs)) {
+ path = file_path(filp, pathname, sizeof(pathname));
+ if (IS_ERR(path))
+ path = "(unknown)";
+ pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
+ pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
+ current->comm);
+ }
+}
+
ssize_t
generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
@@ -3123,7 +3380,7 @@
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)))
+ pos + write_len - 1))
return -EAGAIN;
} else {
written = filemap_write_and_wait_range(mapping, pos,
@@ -3163,11 +3420,15 @@
* 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
+ * them by removing it completely.
+ *
+ * Noticeable example is a blkdev_direct_IO().
+ *
+ * Skip invalidation for async writes or if mapping has no pages.
*/
- if (mapping->nrpages)
- invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
+ if (written > 0 && mapping->nrpages &&
+ invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end))
+ dio_warn_stale_pagecache(file);
if (written > 0) {
pos += written;
@@ -3220,7 +3481,7 @@
unsigned long offset; /* Offset into pagecache page */
unsigned long bytes; /* Bytes to write to page */
size_t copied; /* Bytes copied from user */
- void *fsdata;
+ void *fsdata = NULL;
offset = (pos & (PAGE_SIZE - 1));
bytes = min_t(unsigned long, PAGE_SIZE - offset,
@@ -3306,6 +3567,10 @@
* 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.
+ *
+ * Return:
+ * * number of bytes written, even for truncated writes
+ * * negative error code if no data has been written at all
*/
ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
@@ -3390,6 +3655,10 @@
* 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.
+ * Return:
+ * * negative error code if no data has been written at all of
+ * vfs_fsync_range() failed for a synchronous write
+ * * number of bytes written, even for truncated writes
*/
ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
@@ -3416,8 +3685,7 @@
* @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.
+ * (presumably at page->private).
*
* This may also be called if PG_fscache is set on a page, indicating that the
* page is known to the local caching routines.
@@ -3425,6 +3693,7 @@
* 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).
*
+ * Return: %1 if the release was successful, otherwise return zero.
*/
int try_to_release_page(struct page *page, gfp_t gfp_mask)
{
--
Gitblit v1.6.2