cregit-Linux how code gets into the kernel

Release 4.11 fs/dax.c

Directory: fs
/*
 * fs/dax.c - Direct Access filesystem code
 * Copyright (c) 2013-2014 Intel Corporation
 * Author: Matthew Wilcox <matthew.r.wilcox@intel.com>
 * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pagevec.h>
#include <linux/pmem.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
#include "internal.h"


#define CREATE_TRACE_POINTS
#include <trace/events/fs_dax.h>

/* We choose 4096 entries - same as per-zone page wait tables */

#define DAX_WAIT_TABLE_BITS 12

#define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)


static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];




static int __init init_dax_wait_table(void)
{
	int i;

	for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
		init_waitqueue_head(wait_table + i);
	return 0;
}

Contributors
PersonTokensPropCommitsCommitProp
Jan Kara35100.00%1100.00%


Total35100.00%1100.00%




fs_initcall(init_dax_wait_table);




static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
{
	struct request_queue *q = bdev->bd_queue;
	long rc = -EIO;

	dax->addr = ERR_PTR(-EIO);
	if (blk_queue_enter(q, true) != 0)
		return rc;

	rc = bdev_direct_access(bdev, dax);
	if (rc < 0) {
		dax->addr = ERR_PTR(rc);
		blk_queue_exit(q);
		return rc;
	}
	return rc;
}


Contributors
PersonTokensPropCommitsCommitProp
Dan J Williams92100.00%1100.00%


Total92100.00%1100.00%






static void dax_unmap_atomic(struct block_device *bdev,
		const struct blk_dax_ctl *dax)
{
	if (IS_ERR(dax->addr))
		return;
	blk_queue_exit(bdev->bd_queue);
}


Contributors
PersonTokensPropCommitsCommitProp
Dan J Williams34100.00%1100.00%


Total34100.00%1100.00%






static int dax_is_pmd_entry(void *entry)
{
	return (unsigned long)entry & RADIX_DAX_PMD;
}


Contributors
PersonTokensPropCommitsCommitProp
Ross Zwisler19100.00%1100.00%


Total19100.00%1100.00%






static int dax_is_pte_entry(void *entry)
{
	return !((unsigned long)entry & RADIX_DAX_PMD);
}


Contributors
PersonTokensPropCommitsCommitProp
Ross Zwisler22100.00%1100.00%


Total22100.00%1100.00%






static int dax_is_zero_entry(void *entry)
{
	return (unsigned long)entry & RADIX_DAX_HZP;
}


Contributors
PersonTokensPropCommitsCommitProp
Ross Zwisler19100.00%1100.00%


Total19100.00%1100.00%






static int dax_is_empty_entry(void *entry)
{
	return (unsigned long)entry & RADIX_DAX_EMPTY;
}


Contributors
PersonTokensPropCommitsCommitProp
Ross Zwisler19100.00%1100.00%


Total19100.00%1100.00%






struct page *read_dax_sector(struct block_device *bdev, sector_t n)
{
	struct page *page = alloc_pages(GFP_KERNEL, 0);
	struct blk_dax_ctl dax = {
		.size = PAGE_SIZE,
		.sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
        };
	long rc;

	if (!page)
		return ERR_PTR(-ENOMEM);

	rc = dax_map_atomic(bdev, &dax);
	if (rc < 0)
		return ERR_PTR(rc);
	memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
	dax_unmap_atomic(bdev, &dax);
	return page;
}


Contributors
PersonTokensPropCommitsCommitProp
Dan J Williams121100.00%1100.00%


Total121100.00%1100.00%



/*
 * DAX radix tree locking
 */

struct exceptional_entry_key {
	
struct address_space *mapping;
	
pgoff_t entry_start;
};


struct wait_exceptional_entry_queue {
	
wait_queue_t wait;
	
struct exceptional_entry_key key;
};




static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
		pgoff_t index, void *entry, struct exceptional_entry_key *key)
{
	unsigned long hash;

	/*
         * If 'entry' is a PMD, align the 'index' that we use for the wait
         * queue to the start of that PMD.  This ensures that all offsets in
         * the range covered by the PMD map to the same bit lock.
         */
	if (dax_is_pmd_entry(entry))
		index &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1);

	key->mapping = mapping;
	key->entry_start = index;

	hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS);
	return wait_table + hash;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara7082.35%266.67%


Dan J Williams1517.65%133.33%


Total85100.00%3100.00%






static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
				       int sync, void *keyp)
{
	struct exceptional_entry_key *key = keyp;
	struct wait_exceptional_entry_queue *ewait =
		container_of(wait, struct wait_exceptional_entry_queue, wait);

	if (key->mapping != ewait->key.mapping ||
	    key->entry_start != ewait->key.entry_start)
		return 0;
	return autoremove_wake_function(wait, mode, sync, NULL);
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara7188.75%350.00%


Matthew Wilcox56.25%116.67%


Dan J Williams33.75%116.67%


Ross Zwisler11.25%116.67%


Total80100.00%6100.00%



/*
 * Check whether the given slot is locked. The function must be called with
 * mapping->tree_lock held
 */



static inline int slot_locked(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
	return entry & RADIX_DAX_ENTRY_LOCK;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara2972.50%266.67%


Ross Zwisler1127.50%133.33%


Total40100.00%3100.00%



/*
 * Mark the given slot is locked. The function must be called with
 * mapping->tree_lock held
 */



static inline void *lock_slot(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);

	entry |= RADIX_DAX_ENTRY_LOCK;
	radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
	return (void *)entry;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara5485.71%240.00%


Ross Zwisler711.11%240.00%


Linus Torvalds23.17%120.00%


Total63100.00%5100.00%



/*
 * Mark the given slot is unlocked. The function must be called with
 * mapping->tree_lock held
 */



static inline void *unlock_slot(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);

	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
	radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
	return (void *)entry;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara6189.71%250.00%


Linus Torvalds45.88%125.00%


Ross Zwisler34.41%125.00%


Total68100.00%4100.00%



/*
 * Lookup entry in radix tree, wait for it to become unlocked if it is
 * exceptional entry and return it. The caller must call
 * put_unlocked_mapping_entry() when he decided not to lock the entry or
 * put_locked_mapping_entry() when he locked the entry and now wants to
 * unlock it.
 *
 * The function must be called with mapping->tree_lock held.
 */



static void *get_unlocked_mapping_entry(struct address_space *mapping,
					pgoff_t index, void ***slotp)
{
	void *entry, **slot;
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

	init_wait(&ewait.wait);
	ewait.wait.func = wake_exceptional_entry_func;

	for (;;) {
		entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
					  &slot);
		if (!entry || !radix_tree_exceptional_entry(entry) ||
		    !slot_locked(mapping, slot)) {
			if (slotp)
				*slotp = slot;
			return entry;
		}

		wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
		prepare_to_wait_exclusive(wq, &ewait.wait,
					  TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(&mapping->tree_lock);
		schedule();
		finish_wait(wq, &ewait.wait);
		spin_lock_irq(&mapping->tree_lock);
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara15894.61%266.67%


Ross Zwisler95.39%133.33%


Total167100.00%3100.00%






static void dax_unlock_mapping_entry(struct address_space *mapping,
				     pgoff_t index)
{
	void *entry, **slot;

	spin_lock_irq(&mapping->tree_lock);
	entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
			 !slot_locked(mapping, slot))) {
		spin_unlock_irq(&mapping->tree_lock);
		return;
	}
	unlock_slot(mapping, slot);
	spin_unlock_irq(&mapping->tree_lock);
	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara106100.00%1100.00%


Total106100.00%1100.00%






static void put_locked_mapping_entry(struct address_space *mapping,
				     pgoff_t index, void *entry)
{
	if (!radix_tree_exceptional_entry(entry)) {
		unlock_page(entry);
		put_page(entry);
	} else {
		dax_unlock_mapping_entry(mapping, index);
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara48100.00%2100.00%


Total48100.00%2100.00%



/*
 * Called when we are done with radix tree entry we looked up via
 * get_unlocked_mapping_entry() and which we didn't lock in the end.
 */



static void put_unlocked_mapping_entry(struct address_space *mapping,
				       pgoff_t index, void *entry)
{
	if (!radix_tree_exceptional_entry(entry))
		return;

	/* We have to wake up next waiter for the radix tree entry lock */
	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara39100.00%2100.00%


Total39100.00%2100.00%



/*
 * Find radix tree entry at given index. If it points to a page, return with
 * the page locked. If it points to the exceptional entry, return with the
 * radix tree entry locked. If the radix tree doesn't contain given index,
 * create empty exceptional entry for the index and return with it locked.
 *
 * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
 * either return that locked entry or will return an error.  This error will
 * happen if there are any 4k entries (either zero pages or DAX entries)
 * within the 2MiB range that we are requesting.
 *
 * We always favor 4k entries over 2MiB entries. There isn't a flow where we
 * evict 4k entries in order to 'upgrade' them to a 2MiB entry.  A 2MiB
 * insertion will fail if it finds any 4k entries already in the tree, and a
 * 4k insertion will cause an existing 2MiB entry to be unmapped and
 * downgraded to 4k entries.  This happens for both 2MiB huge zero pages as
 * well as 2MiB empty entries.
 *
 * The exception to this downgrade path is for 2MiB DAX PMD entries that have
 * real storage backing them.  We will leave these real 2MiB DAX entries in
 * the tree, and PTE writes will simply dirty the entire 2MiB DAX entry.
 *
 * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
 * persistent memory the benefit is doubtful. We can add that later if we can
 * show it helps.
 */



static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
		unsigned long size_flag)
{
	bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
	void *entry, **slot;

restart:
	spin_lock_irq(&mapping->tree_lock);
	entry = get_unlocked_mapping_entry(mapping, index, &slot);

	if (entry) {
		if (size_flag & RADIX_DAX_PMD) {
			if (!radix_tree_exceptional_entry(entry) ||
			    dax_is_pte_entry(entry)) {
				put_unlocked_mapping_entry(mapping, index,
						entry);
				entry = ERR_PTR(-EEXIST);
				goto out_unlock;
			}
		} else { /* trying to grab a PTE entry */
			if (radix_tree_exceptional_entry(entry) &&
			    dax_is_pmd_entry(entry) &&
			    (dax_is_zero_entry(entry) ||
			     dax_is_empty_entry(entry))) {
				pmd_downgrade = true;
			}
		}
	}

	/* No entry for given index? Make sure radix tree is big enough. */
	if (!entry || pmd_downgrade) {
		int err;

		if (pmd_downgrade) {
			/*
                         * Make sure 'entry' remains valid while we drop
                         * mapping->tree_lock.
                         */
			entry = lock_slot(mapping, slot);
		}

		spin_unlock_irq(&mapping->tree_lock);
		/*
                 * Besides huge zero pages the only other thing that gets
                 * downgraded are empty entries which don't need to be
                 * unmapped.
                 */
		if (pmd_downgrade && dax_is_zero_entry(entry))
			unmap_mapping_range(mapping,
				(index << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);

		err = radix_tree_preload(
				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
		if (err) {
			if (pmd_downgrade)
				put_locked_mapping_entry(mapping, index, entry);
			return ERR_PTR(err);
		}
		spin_lock_irq(&mapping->tree_lock);

		if (!entry) {
			/*
                         * We needed to drop the page_tree lock while calling
                         * radix_tree_preload() and we didn't have an entry to
                         * lock.  See if another thread inserted an entry at
                         * our index during this time.
                         */
			entry = __radix_tree_lookup(&mapping->page_tree, index,
					NULL, &slot);
			if (entry) {
				radix_tree_preload_end();
				spin_unlock_irq(&mapping->tree_lock);
				goto restart;
			}
		}

		if (pmd_downgrade) {
			radix_tree_delete(&mapping->page_tree, index);
			mapping->nrexceptional--;
			dax_wake_mapping_entry_waiter(mapping, index, entry,
					true);
		}

		entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);

		err = __radix_tree_insert(&mapping->page_tree, index,
				dax_radix_order(entry), entry);
		radix_tree_preload_end();
		if (err) {
			spin_unlock_irq(&mapping->tree_lock);
			/*
                         * Our insertion of a DAX entry failed, most likely
                         * because we were inserting a PMD entry and it
                         * collided with a PTE sized entry at a different
                         * index in the PMD range.  We haven't inserted
                         * anything into the radix tree and have no waiters to
                         * wake.
                         */
			return ERR_PTR(err);
		}
		/* Good, we have inserted empty locked entry into the tree. */
		mapping->nrexceptional++;
		spin_unlock_irq(&mapping->tree_lock);
		return entry;
	}
	/* Normal page in radix tree? */
	if (!radix_tree_exceptional_entry(entry)) {
		struct page *page = entry;

		get_page(page);
		spin_unlock_irq(&mapping->tree_lock);
		lock_page(page);
		/* Page got truncated? Retry... */
		if (unlikely(page->mapping != mapping)) {
			unlock_page(page);
			put_page(page);
			goto restart;
		}
		return page;
	}
	entry = lock_slot(mapping, slot);
 out_unlock:
	spin_unlock_irq(&mapping->tree_lock);
	return entry;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara40583.68%330.00%


Ross Zwisler6613.64%440.00%


Matthew Wilcox102.07%110.00%


Dan J Williams20.41%110.00%


Christoph Hellwig10.21%110.00%


Total484100.00%10100.00%



/*
 * We do not necessarily hold the mapping->tree_lock when we call this
 * function so it is possible that 'entry' is no longer a valid item in the
 * radix tree.  This is okay because all we really need to do is to find the
 * correct waitqueue where tasks might be waiting for that old 'entry' and
 * wake them.
 */



void dax_wake_mapping_entry_waiter(struct address_space *mapping,
		pgoff_t index, void *entry, bool wake_all)
{
	struct exceptional_entry_key key;
	wait_queue_head_t *wq;

	wq = dax_entry_waitqueue(mapping, index, entry, &key);

	/*
         * Checking for locked entry and prepare_to_wait_exclusive() happens
         * under mapping->tree_lock, ditto for entry handling in our callers.
         * So at this point all tasks that could have seen our entry locked
         * must be in the waitqueue and the following check will see them.
         */
	if (waitqueue_active(wq))
		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara4568.18%266.67%


Ross Zwisler2131.82%133.33%


Total66100.00%3100.00%






static int __dax_invalidate_mapping_entry(struct address_space *mapping,
					  pgoff_t index, bool trunc)
{
	int ret = 0;
	void *entry;
	struct radix_tree_root *page_tree = &mapping->page_tree;

	spin_lock_irq(&mapping->tree_lock);
	entry = get_unlocked_mapping_entry(mapping, index, NULL);
	if (!entry || !radix_tree_exceptional_entry(entry))
		goto out;
	if (!trunc &&
	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
		goto out;
	radix_tree_delete(page_tree, index);
	mapping->nrexceptional--;
	ret = 1;
out:
	put_unlocked_mapping_entry(mapping, index, entry);
	spin_unlock_irq(&mapping->tree_lock);
	return ret;
}

Contributors
PersonTokensPropCommitsCommitProp
Jan Kara10678.52%250.00%


Ross Zwisler2921.48%250.00%


Total135100.00%4100.00%



/*
 * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
 * entry to get unlocked before deleting it.
 */



int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	int ret = __dax_invalidate_mapping_entry(mapping, index, true);

	/*
         * This gets called from truncate / punch_hole path. As such, the caller
         * must hold locks protecting against concurrent modifications of the
         * radix tree (usually fs-private i_mmap_sem for writing). Since the
         * caller has seen exceptional entry for this index, we better find it
         * at that index as well...
         */
	WARN_ON_ONCE(!ret);
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara3497.14%150.00%


Ross Zwisler12.86%150.00%


Total35100.00%2100.00%



/*
 * Invalidate exceptional DAX entry if easily possible. This handles DAX
 * entries for invalidate_inode_pages() so we evict the entry only if we can
 * do so without blocking.
 */



int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	int ret = 0;
	void *entry, **slot;
	struct radix_tree_root *page_tree = &mapping->page_tree;

	spin_lock_irq(&mapping->tree_lock);
	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
	if (!entry || !radix_tree_exceptional_entry(entry) ||
	    slot_locked(mapping, slot))
		goto out;
	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
		goto out;
	radix_tree_delete(page_tree, index);
	mapping->nrexceptional--;
	ret = 1;
out:
	spin_unlock_irq(&mapping->tree_lock);
	if (ret)
		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara13793.84%360.00%


Ross Zwisler74.79%120.00%


Johannes Weiner21.37%120.00%


Total146100.00%5100.00%



/*
 * Invalidate exceptional DAX entry if it is clean.
 */



int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
				      pgoff_t index)
{
	return __dax_invalidate_mapping_entry(mapping, index, false);
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara23100.00%3100.00%


Total23100.00%3100.00%



/*
 * The user has performed a load from a hole in the file.  Allocating
 * a new page in the file would cause excessive storage usage for
 * workloads with sparse files.  We allocate a page cache page instead.
 * We'll kick it out of the page cache if it's ever written to,
 * otherwise it will simply fall out of the page cache under memory
 * pressure without ever having been dirtied.
 */



static int dax_load_hole(struct address_space *mapping, void **entry,
			 struct vm_fault *vmf)
{
	struct page *page;
	int ret;

	/* Hole page already exists? Return it...  */
	if (!radix_tree_exceptional_entry(*entry)) {
		page = *entry;
		goto out;
	}

	/* This will replace locked radix tree entry with a hole page */
	page = find_or_create_page(mapping, vmf->pgoff,
				   vmf->gfp_mask | __GFP_ZERO);
	if (!page)
		return VM_FAULT_OOM;
 out:
	vmf->page = page;
	ret = finish_fault(vmf);
	vmf->page = NULL;
	*entry = page;
	if (!ret) {
		/* Grab reference for PTE that is now referencing the page */
		get_page(page);
		return VM_FAULT_NOPAGE;
	}
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara10789.17%375.00%


Ross Zwisler1310.83%125.00%


Total120100.00%4100.00%






static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
		struct page *to, unsigned long vaddr)
{
	struct blk_dax_ctl dax = {
		.sector = sector,
		.size = size,
        };
	void *vto;

	if (dax_map_atomic(bdev, &dax) < 0)
		return PTR_ERR(dax.addr);
	vto = kmap_atomic(to);
	copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
	kunmap_atomic(vto);
	dax_unmap_atomic(bdev, &dax);
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Ross Zwisler6661.68%150.00%


Jan Kara4138.32%150.00%


Total107100.00%2100.00%



/*
 * By this point grab_mapping_entry() has ensured that we have a locked entry
 * of the appropriate size so we don't have to worry about downgrading PMDs to
 * PTEs.  If we happen to be trying to insert a PTE and there is a PMD
 * already in the tree, we will skip the insertion and just dirty the PMD as
 * appropriate.
 */



static void *dax_insert_mapping_entry(struct address_space *mapping,
				      struct vm_fault *vmf,
				      void *entry, sector_t sector,
				      unsigned long flags)
{
	struct radix_tree_root *page_tree = &mapping->page_tree;
	int error = 0;
	bool hole_fill = false;
	void *new_entry;
	pgoff_t index = vmf->pgoff;

	if (vmf->flags & FAULT_FLAG_WRITE)
		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	/* Replacing hole page with block mapping? */
	if (!radix_tree_exceptional_entry(entry)) {
		hole_fill = true;
		/*
                 * Unmap the page now before we remove it from page cache below.
                 * The page is locked so it cannot be faulted in again.
                 */
		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
				    PAGE_SIZE, 0);
		error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM);
		if (error)
			return ERR_PTR(error);
	} else if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_HZP)) {
		/* replacing huge zero page with PMD block mapping */
		unmap_mapping_range(mapping,
			(vmf->pgoff << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);
	}

	spin_lock_irq(&mapping->tree_lock);
	new_entry = dax_radix_locked_entry(sector, flags);

	if (hole_fill) {
		__delete_from_page_cache(entry, NULL);
		/* Drop pagecache reference */
		put_page(entry);
		error = __radix_tree_insert(page_tree, index,
				dax_radix_order(new_entry), new_entry);
		if (error) {
			new_entry = ERR_PTR(error);
			goto unlock;
		}
		mapping->nrexceptional++;
	} else if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
		/*
                 * Only swap our new entry into the radix tree if the current
                 * entry is a zero page or an empty entry.  If a normal PTE or
                 * PMD entry is already in the tree, we leave it alone.  This
                 * means that if we are trying to insert a PTE and the
                 * existing entry is a PMD, we will just leave the PMD in the
                 * tree and dirty it if necessary.
                 */
		struct radix_tree_node *node;
		void **slot;
		void *ret;

		ret = __radix_tree_lookup(page_tree, index, &node, &slot);
		WARN_ON_ONCE(ret != entry);
		__radix_tree_replace(page_tree, node, slot,
				     new_entry, NULL, NULL);
	}
	if (vmf->flags & FAULT_FLAG_WRITE)
		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
 unlock:
	spin_unlock_irq(&mapping->tree_lock);
	if (hole_fill) {
		radix_tree_preload_end();
		/*
                 * We don't need hole page anymore, it has been replaced with
                 * locked radix tree entry now.
                 */
		if (mapping->a_ops->freepage)
			mapping->a_ops->freepage(entry);
		unlock_page(entry);
		put_page(entry);
	}
	return new_entry;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara21958.71%225.00%


Ross Zwisler11330.29%225.00%


Dan J Williams154.02%112.50%


Matthew Wilcox133.49%112.50%


Linus Torvalds123.22%112.50%


Kirill A. Shutemov10.27%112.50%


Total373100.00%8100.00%





static inline unsigned long

pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
{
	unsigned long address;

	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
	return address;
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara58100.00%1100.00%


Total58100.00%1100.00%



/* Walk all mappings of a given index of a file and writeprotect them */



static void dax_mapping_entry_mkclean(struct address_space *mapping,
				      pgoff_t index, unsigned long pfn)
{
	struct vm_area_struct *vma;
	pte_t pte, *ptep = NULL;
	pmd_t *pmdp = NULL;
	spinlock_t *ptl;
	bool changed;

	i_mmap_lock_read(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
		unsigned long address;

		cond_resched();

		if (!(vma->vm_flags & VM_SHARED))
			continue;

		address = pgoff_address(index, vma);
		changed = false;
		if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
			continue;

		if (pmdp) {
#ifdef CONFIG_FS_DAX_PMD
			pmd_t pmd;

			if (pfn != pmd_pfn(*pmdp))
				goto unlock_pmd;
			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
				goto unlock_pmd;

			flush_cache_page(vma, address, pfn);
			pmd = pmdp_huge_clear_flush(vma, address, pmdp);
			pmd = pmd_wrprotect(pmd);
			pmd = pmd_mkclean(pmd);
			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
			changed = true;
unlock_pmd:
			spin_unlock(ptl);
#endif
		} else {
			if (pfn != pte_pfn(*ptep))
				goto unlock_pte;
			if (!pte_dirty(*ptep) && !pte_write(*ptep))
				goto unlock_pte;

			flush_cache_page(vma, address, pfn);
			pte = ptep_clear_flush(vma, address, ptep);
			pte = pte_wrprotect(pte);
			pte = pte_mkclean(pte);
			set_pte_at(vma->vm_mm, address, ptep, pte);
			changed = true;
unlock_pte:
			pte_unmap_unlock(ptep, ptl);
		}

		if (changed)
			mmu_notifier_invalidate_page(vma->vm_mm, address);
	}
	i_mmap_unlock_read(mapping);
}


Contributors
PersonTokensPropCommitsCommitProp
Jan Kara20862.84%150.00%


Ross Zwisler12337.16%150.00%


Total331100.00%2100.00%






static int