/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *page;
page = find_get_page(&swapper_space, entry.val);
if (page)
INC_CACHE_INFO(find_success);
INC_CACHE_INFO(find_total);
return page;
}
int btrfs_write_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages, int mark)
{
int ret;
int err = 0;
int werr = 0;
struct page *page;
struct inode *btree_inode = root->fs_info->btree_inode;
u64 start = 0;
u64 end;
unsigned long index;
while (1) {
ret = find_first_extent_bit(dirty_pages, start, &start, &end,
mark);
if (ret)
break;
while (start <= end) {
cond_resched();
index = start >> PAGE_CACHE_SHIFT;
start = (u64)(index + 1) << PAGE_CACHE_SHIFT;
page = find_get_page(btree_inode->i_mapping, index);
if (!page)
continue;
btree_lock_page_hook(page);
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
continue;
}
if (PageWriteback(page)) {
if (PageDirty(page))
wait_on_page_writeback(page);
else {
unlock_page(page);
page_cache_release(page);
continue;
}
}
err = write_one_page(page, 0);
if (err)
werr = err;
page_cache_release(page);
}
}
if (err)
werr = err;
return werr;
}
/*
* Use the cached Readdirplus results in order to avoid a LOOKUP call
* whenever we believe that the parent directory has not changed.
*
* We assume that any file creation/rename changes the directory mtime.
* As this results in a page cache invalidation whenever it occurs,
* we don't require any other tests for cache coherency.
*/
static
int nfs_cached_lookup(struct inode *dir, struct dentry *dentry,
struct nfs_fh *fh, struct nfs_fattr *fattr)
{
nfs_readdir_descriptor_t desc;
struct nfs_server *server;
struct nfs_entry entry;
struct page *page;
unsigned long timestamp;
int res;
if (!NFS_USE_READDIRPLUS(dir))
return -ENOENT;
server = NFS_SERVER(dir);
/* Don't use readdirplus unless the cache is stable */
if ((server->flags & NFS_MOUNT_NOAC) != 0
|| nfs_caches_unstable(dir)
|| nfs_attribute_timeout(dir))
return -ENOENT;
if ((NFS_FLAGS(dir) & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA)) != 0)
return -ENOENT;
timestamp = NFS_I(dir)->readdir_timestamp;
entry.fh = fh;
entry.fattr = fattr;
desc.decode = NFS_PROTO(dir)->decode_dirent;
desc.entry = &entry;
desc.page_index = 0;
desc.plus = 1;
for(;(page = find_get_page(dir->i_mapping, desc.page_index)); desc.page_index++) {
res = -EIO;
if (PageUptodate(page)) {
void * kaddr = kmap_atomic(page, KM_USER0);
desc.ptr = kaddr;
res = find_dirent_name(&desc, page, dentry);
kunmap_atomic(kaddr, KM_USER0);
}
page_cache_release(page);
if (res == 0)
goto out_found;
if (res != -EAGAIN)
break;
}
return -ENOENT;
out_found:
fattr->timestamp = timestamp;
return 0;
}
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *found_page, *new_page = NULL;
int err;
do {
found_page = find_get_page(&swapper_space, entry.val);
if (found_page)
break;
if (!new_page) {
new_page = alloc_page_vma(gfp_mask, vma, addr);
if (!new_page)
break;
}
err = radix_tree_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
err = swapcache_prepare(entry);
if (err == -EEXIST) {
radix_tree_preload_end();
continue;
}
if (err) {
radix_tree_preload_end();
break;
}
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
lru_cache_add_anon(new_page);
swap_readpage(new_page);
return new_page;
}
radix_tree_preload_end();
ClearPageSwapBacked(new_page);
__clear_page_locked(new_page);
swapcache_free(entry, NULL);
} while (err != -ENOMEM);
if (new_page)
page_cache_release(new_page);
return found_page;
}
/*
* Locate a page of swap in physical memory, reserving swap cache space
* and reading the disk if it is not already cached.
* A failure return means that either the page allocation failed or that
* the swap entry is no longer in use.
*/
struct page *read_swap_cache_async(swp_entry_t entry,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *found_page, *new_page = NULL;
int err;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(&swapper_space, entry.val);
if (found_page)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
if (!new_page)
break; /* Out of memory */
}
/*
* Associate the page with swap entry in the swap cache.
* May fail (-ENOENT) if swap entry has been freed since
* our caller observed it. May fail (-EEXIST) if there
* is already a page associated with this entry in the
* swap cache: added by a racing read_swap_cache_async,
* or by try_to_swap_out (or shmem_writepage) re-using
* the just freed swap entry for an existing page.
* May fail (-ENOMEM) if radix-tree node allocation failed.
*/
err = add_to_swap_cache(new_page, entry);
if (!err) {
/*
* Initiate read into locked page and return.
*/
lru_cache_add_active(new_page);
swap_readpage(NULL, new_page);
return new_page;
}
} while (err != -ENOENT && err != -ENOMEM);
if (new_page)
page_cache_release(new_page);
return found_page;
}
/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *page;
page = find_get_page(swap_address_space(entry), swp_offset(entry));
if (page && likely(!PageTransCompound(page))) {
INC_CACHE_INFO(find_success);
if (TestClearPageReadahead(page))
atomic_inc(&swapin_readahead_hits);
}
INC_CACHE_INFO(find_total);
return page;
}
/*
* Later we can get more picky about what "in core" means precisely.
* For now, simply check to see if the page is in the page cache,
* and is up to date; i.e. that no page-in operation would be required
* at this time if an application were to map and access this page.
*/
static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
{
unsigned char present = 0;
struct page *page;
/*
* When tmpfs swaps out a page from a file, any process mapping that
* file will not get a swp_entry_t in its pte, but rather it is like
* any other file mapping (ie. marked !present and faulted in with
* tmpfs's .fault). So swapped out tmpfs mappings are tested here.
<<<<<<< HEAD
=======
<<<<<<< HEAD
>>>>>>> ae1773bb70f3d7cf73324ce8fba787e01d8fa9f2
*/
page = find_get_page(mapping, pgoff);
#ifdef CONFIG_SWAP
/* shmem/tmpfs may return swap: account for swapcache page too. */
if (radix_tree_exceptional_entry(page)) {
swp_entry_t swap = radix_to_swp_entry(page);
page = find_get_page(&swapper_space, swap.val);
}
#endif
<<<<<<< HEAD
/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *page;
page = find_get_page(swap_address_space(entry), entry.val);
if (page) {
INC_CACHE_INFO(find_success);
if (TestClearPageReadahead(page))
atomic_inc(&swapin_readahead_hits);
}
INC_CACHE_INFO(find_total);
return page;
}
/*
* Later we can get more picky about what "in core" means precisely.
* For now, simply check to see if the page is in the page cache,
* and is up to date; i.e. that no page-in operation would be required
* at this time if an application were to map and access this page.
*/
static unsigned char mincore_page(struct vm_area_struct * vma,
unsigned long pgoff)
{
unsigned char present = 0;
struct address_space * as = vma->vm_file->f_mapping;
struct page * page;
page = find_get_page(as, pgoff);
if (page) {
present = PageUptodate(page);
page_cache_release(page);
}
return present;
}
void do_generic_file_read(struct file *filp,unsigned int *ppos,
read_descriptor_t *desc,int dumm){
struct address_space *mapping = filp->f_dentry->d_inode->i_mapping;
struct inode *inode = mapping->host;
unsigned long index = *ppos >> PAGE_CACHE_SHIFT;
unsigned long offset = *ppos & ~PAGE_CACHE_SHIFT;
for(;;){
struct page *page = find_get_page(mapping,index);
unsigned long end_index = inode->i_size >> PAGE_CACHE_SHIFT;
if(index > end_index) break;
unsigned long nr,ret;
nr = PAGE_CACHE_SIZE;
nr = nr - offset;
mapping->a_ops->readpage(filp,page);
}
}
/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *found;
found = find_get_page(&swapper_space, entry.val);
/*
* Unsafe to assert PageSwapCache and mapping on page found:
* if SMP nothing prevents swapoff from deleting this page from
* the swap cache at this moment. find_lock_page would prevent
* that, but no need to change: we _have_ got the right page.
*/
INC_CACHE_INFO(find_total);
if (found)
INC_CACHE_INFO(find_success);
return found;
}
/*
* Later we can get more picky about what "in core" means precisely.
* For now, simply check to see if the page is in the page cache,
* and is up to date; i.e. that no page-in operation would be required
* at this time if an application were to map and access this page.
*/
static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
{
unsigned char present = 0;
struct page *page;
/*
* When tmpfs swaps out a page from a file, any process mapping that
* file will not get a swp_entry_t in its pte, but rather it is like
* any other file mapping (ie. marked !present and faulted in with
* tmpfs's .fault). So swapped out tmpfs mappings are tested here.
*
* However when tmpfs moves the page from pagecache and into swapcache,
* it is still in core, but the find_get_page below won't find it.
* No big deal, but make a note of it.
*/
page = find_get_page(mapping, pgoff);
if (page) {
present = PageUptodate(page);
page_cache_release(page);
}
return present;
}
struct page *find_data_page(struct inode *inode, pgoff_t index)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
page = find_get_page(mapping, index);
if (page && PageUptodate(page))
return page;
f2fs_put_page(page, 0);
page = get_read_data_page(inode, index, READ_SYNC);
if (IS_ERR(page))
return page;
if (PageUptodate(page))
return page;
wait_on_page_locked(page);
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 0);
return ERR_PTR(-EIO);
}
return page;
}
/*
* Locate a page of swap in physical memory, reserving swap cache space
* and reading the disk if it is not already cached.
* A failure return means that either the page allocation failed or that
* the swap entry is no longer in use.
*/
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *found_page, *new_page = NULL;
int err;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(&swapper_space, entry.val);
if (found_page)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page_vma(gfp_mask, vma, addr);
if (!new_page)
break; /* Out of memory */
}
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) { /* seems racy */
radix_tree_preload_end();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
/*
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
swap_readpage(new_page);
return new_page;
}
radix_tree_preload_end();
ClearPageSwapBacked(new_page);
__clear_page_locked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry, NULL);
} while (err != -ENOMEM);
if (new_page)
page_cache_release(new_page);
return found_page;
}
struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated)
{
struct page *found_page, *new_page = NULL;
struct address_space *swapper_space = swap_address_space(entry);
int err;
*new_page_allocated = false;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(swapper_space, entry.val);
if (found_page)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page_vma(gfp_mask, vma, addr);
if (!new_page)
break; /* Out of memory */
}
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) {
radix_tree_preload_end();
/*
* We might race against get_swap_page() and stumble
* across a SWAP_HAS_CACHE swap_map entry whose page
* has not been brought into the swapcache yet, while
* the other end is scheduled away waiting on discard
* I/O completion at scan_swap_map().
*
* In order to avoid turning this transitory state
* into a permanent loop around this -EEXIST case
* if !CONFIG_PREEMPT and the I/O completion happens
* to be waiting on the CPU waitqueue where we are now
* busy looping, we just conditionally invoke the
* scheduler here, if there are some more important
* tasks to run.
*/
cond_resched();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__SetPageLocked(new_page);
__SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
/*
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
*new_page_allocated = true;
return new_page;
}
radix_tree_preload_end();
__ClearPageLocked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry);
} while (err != -ENOMEM);
if (new_page)
put_page(new_page);
return found_page;
}
static int tux3_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
struct sb *sb = tux_sb(inode->i_sb);
struct page *clone, *page = vmf->page;
void *ptr;
int ret;
sb_start_pagefault(inode->i_sb);
retry:
down_read(&tux_inode(inode)->truncate_lock);
lock_page(page);
if (page->mapping != mapping(inode)) {
unlock_page(page);
ret = VM_FAULT_NOPAGE;
goto out;
}
/*
* page fault can be happened while holding change_begin/end()
* (e.g. copy of user data between ->write_begin and
* ->write_end for write(2)).
*
* So, we use nested version here.
*/
change_begin_atomic_nested(sb, &ptr);
/*
* FIXME: Caller releases vmf->page (old_page) unconditionally.
* So, this takes additional refcount to workaround it.
*/
if (vmf->page == page)
page_cache_get(page);
clone = pagefork_for_blockdirty(page, tux3_get_current_delta());
if (IS_ERR(clone)) {
/* Someone did page fork */
pgoff_t index = page->index;
change_end_atomic_nested(sb, ptr);
unlock_page(page);
page_cache_release(page);
up_read(&tux_inode(inode)->truncate_lock);
switch (PTR_ERR(clone)) {
case -EAGAIN:
page = find_get_page(inode->i_mapping, index);
assert(page);
goto retry;
case -ENOMEM:
ret = VM_FAULT_OOM;
break;
default:
ret = VM_FAULT_SIGBUS;
break;
}
goto out;
}
file_update_time(vma->vm_file);
/* Assign buffers to dirty */
if (!page_has_buffers(clone))
create_empty_buffers(clone, sb->blocksize, 0);
/*
* We mark the page dirty already here so that when freeze is in
* progress, we are guaranteed that writeback during freezing will
* see the dirty page and writeprotect it again.
*/
tux3_set_page_dirty(clone);
#if 1
/* FIXME: Caller doesn't see the changed vmf->page */
vmf->page = clone;
change_end_atomic_nested(sb, ptr);
/* FIXME: caller doesn't know about pagefork */
unlock_page(clone);
page_cache_release(clone);
ret = 0;
// ret = VM_FAULT_LOCKED;
#endif
out:
up_read(&tux_inode(inode)->truncate_lock);
sb_end_pagefault(inode->i_sb);
return ret;
}
static int copy_user_bh(struct page *to, struct inode *inode,
struct buffer_head *bh, unsigned long vaddr)
{
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
struct block_device *bdev = bh->b_bdev;
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;
}
#define NO_SECTOR -1
#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
sector_t sector, bool pmd_entry, bool dirty)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
pgoff_t pmd_index = DAX_PMD_INDEX(index);
int type, error = 0;
void *entry;
WARN_ON_ONCE(pmd_entry && !dirty);
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
spin_lock_irq(&mapping->tree_lock);
entry = radix_tree_lookup(page_tree, pmd_index);
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) {
index = pmd_index;
goto dirty;
}
entry = radix_tree_lookup(page_tree, index);
if (entry) {
type = RADIX_DAX_TYPE(entry);
if (WARN_ON_ONCE(type != RADIX_DAX_PTE &&
type != RADIX_DAX_PMD)) {
error = -EIO;
goto unlock;
}
if (!pmd_entry || type == RADIX_DAX_PMD)
goto dirty;
/*
* We only insert dirty PMD entries into the radix tree. This
* means we don't need to worry about removing a dirty PTE
* entry and inserting a clean PMD entry, thus reducing the
* range we would flush with a follow-up fsync/msync call.
*/
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
}
if (sector == NO_SECTOR) {
/*
* This can happen during correct operation if our pfn_mkwrite
* fault raced against a hole punch operation. If this
* happens the pte that was hole punched will have been
* unmapped and the radix tree entry will have been removed by
* the time we are called, but the call will still happen. We
* will return all the way up to wp_pfn_shared(), where the
* pte_same() check will fail, eventually causing page fault
* to be retried by the CPU.
*/
goto unlock;
}
error = radix_tree_insert(page_tree, index,
RADIX_DAX_ENTRY(sector, pmd_entry));
if (error)
goto unlock;
mapping->nrexceptional++;
dirty:
if (dirty)
radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
unlock:
spin_unlock_irq(&mapping->tree_lock);
return error;
}
static int dax_writeback_one(struct block_device *bdev,
struct address_space *mapping, pgoff_t index, void *entry)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
int type = RADIX_DAX_TYPE(entry);
struct radix_tree_node *node;
struct blk_dax_ctl dax;
void **slot;
int ret = 0;
spin_lock_irq(&mapping->tree_lock);
/*
* Regular page slots are stabilized by the page lock even
* without the tree itself locked. These unlocked entries
* need verification under the tree lock.
*/
if (!__radix_tree_lookup(page_tree, index, &node, &slot))
goto unlock;
if (*slot != entry)
goto unlock;
/* another fsync thread may have already written back this entry */
if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
goto unlock;
if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
ret = -EIO;
goto unlock;
}
dax.sector = RADIX_DAX_SECTOR(entry);
dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
spin_unlock_irq(&mapping->tree_lock);
/*
* We cannot hold tree_lock while calling dax_map_atomic() because it
* eventually calls cond_resched().
*/
ret = dax_map_atomic(bdev, &dax);
if (ret < 0)
return ret;
if (WARN_ON_ONCE(ret < dax.size)) {
ret = -EIO;
goto unmap;
}
wb_cache_pmem(dax.addr, dax.size);
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
spin_unlock_irq(&mapping->tree_lock);
unmap:
dax_unmap_atomic(bdev, &dax);
return ret;
unlock:
spin_unlock_irq(&mapping->tree_lock);
return ret;
}
/*
* Flush the mapping to the persistent domain within the byte range of [start,
* end]. This is required by data integrity operations to ensure file data is
* on persistent storage prior to completion of the operation.
*/
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
pgoff_t start_index, end_index, pmd_index;
pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
bool done = false;
int i, ret = 0;
void *entry;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
return 0;
start_index = wbc->range_start >> PAGE_SHIFT;
end_index = wbc->range_end >> PAGE_SHIFT;
pmd_index = DAX_PMD_INDEX(start_index);
rcu_read_lock();
entry = radix_tree_lookup(&mapping->page_tree, pmd_index);
rcu_read_unlock();
/* see if the start of our range is covered by a PMD entry */
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
start_index = pmd_index;
tag_pages_for_writeback(mapping, start_index, end_index);
pagevec_init(&pvec, 0);
while (!done) {
pvec.nr = find_get_entries_tag(mapping, start_index,
PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
pvec.pages, indices);
if (pvec.nr == 0)
break;
for (i = 0; i < pvec.nr; i++) {
if (indices[i] > end_index) {
done = true;
break;
}
ret = dax_writeback_one(bdev, mapping, indices[i],
pvec.pages[i]);
if (ret < 0)
return ret;
}
}
wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
unsigned long vaddr = (unsigned long)vmf->virtual_address;
struct address_space *mapping = inode->i_mapping;
struct block_device *bdev = bh->b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
pgoff_t size;
int error;
i_mmap_lock_read(mapping);
/*
* Check truncate didn't happen while we were allocating a block.
* If it did, this block may or may not be still allocated to the
* file. We can't tell the filesystem to free it because we can't
* take i_mutex here. In the worst case, the file still has blocks
* allocated past the end of the file.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (unlikely(vmf->pgoff >= size)) {
error = -EIO;
goto out;
}
if (dax_map_atomic(bdev, &dax) < 0) {
error = PTR_ERR(dax.addr);
goto out;
}
if (buffer_unwritten(bh) || buffer_new(bh)) {
clear_pmem(dax.addr, PAGE_SIZE);
wmb_pmem();
}
dax_unmap_atomic(bdev, &dax);
error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
vmf->flags & FAULT_FLAG_WRITE);
if (error)
goto out;
error = vm_insert_mixed(vma, vaddr, dax.pfn);
out:
i_mmap_unlock_read(mapping);
return error;
}
/**
* __dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
* @complete_unwritten: The filesystem method used to convert unwritten blocks
* to written so the data written to them is exposed. This is required for
* required by write faults for filesystems that will return unwritten
* extent mappings from @get_block, but it is optional for reads as
* dax_insert_mapping() will always zero unwritten blocks. If the fs does
* not support unwritten extents, the it should pass NULL.
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files. __dax_fault() assumes the caller has done all
* the necessary locking for the page fault to proceed successfully.
*/
int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct page *page;
struct buffer_head bh;
unsigned long vaddr = (unsigned long)vmf->virtual_address;
unsigned blkbits = inode->i_blkbits;
sector_t block;
pgoff_t size;
int error;
int major = 0;
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
memset(&bh, 0, sizeof(bh));
block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
repeat:
page = find_get_page(mapping, vmf->pgoff);
if (page) {
if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
put_page(page);
return VM_FAULT_RETRY;
}
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto repeat;
}
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (unlikely(vmf->pgoff >= size)) {
/*
* We have a struct page covering a hole in the file
* from a read fault and we've raced with a truncate
*/
error = -EIO;
goto unlock_page;
}
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
goto unlock_page;
if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
if (vmf->flags & FAULT_FLAG_WRITE) {
error = get_block(inode, block, &bh, 1);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
major = VM_FAULT_MAJOR;
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO;
if (error)
goto unlock_page;
} else {
return dax_load_hole(mapping, page, vmf);
}
}
if (vmf->cow_page) {
struct page *new_page = vmf->cow_page;
if (buffer_written(&bh))
error = copy_user_bh(new_page, inode, &bh, vaddr);
else
clear_user_highpage(new_page, vaddr);
if (error)
goto unlock_page;
vmf->page = page;
if (!page) {
i_mmap_lock_read(mapping);
/* Check we didn't race with truncate */
size = (i_size_read(inode) + PAGE_SIZE - 1) >>
PAGE_SHIFT;
if (vmf->pgoff >= size) {
i_mmap_unlock_read(mapping);
error = -EIO;
goto out;
}
}
return VM_FAULT_LOCKED;
}
/* Check we didn't race with a read fault installing a new page */
if (!page && major)
page = find_lock_page(mapping, vmf->pgoff);
if (page) {
unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
PAGE_SIZE, 0);
delete_from_page_cache(page);
unlock_page(page);
put_page(page);
page = NULL;
}
/*
* If we successfully insert the new mapping over an unwritten extent,
* we need to ensure we convert the unwritten extent. If there is an
* error inserting the mapping, the filesystem needs to leave it as
* unwritten to prevent exposure of the stale underlying data to
* userspace, but we still need to call the completion function so
* the private resources on the mapping buffer can be released. We
* indicate what the callback should do via the uptodate variable, same
* as for normal BH based IO completions.
*/
error = dax_insert_mapping(inode, &bh, vma, vmf);
if (buffer_unwritten(&bh)) {
if (complete_unwritten)
complete_unwritten(&bh, !error);
else
WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
}
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
/* -EBUSY is fine, somebody else faulted on the same PTE */
if ((error < 0) && (error != -EBUSY))
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
unlock_page:
if (page) {
unlock_page(page);
put_page(page);
}
goto out;
}
/*
* zswap_get_swap_cache_page
*
* This is an adaption of read_swap_cache_async()
*
* This function tries to find a page with the given swap entry
* in the swapper_space address space (the swap cache). If the page
* is found, it is returned in retpage. Otherwise, a page is allocated,
* added to the swap cache, and returned in retpage.
*
* If success, the swap cache page is returned in retpage
* Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
* Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
* the new page is added to swapcache and locked
* Returns ZSWAP_SWAPCACHE_FAIL on error
*/
static int zswap_get_swap_cache_page(swp_entry_t entry,
struct page **retpage)
{
struct page *found_page, *new_page = NULL;
struct address_space *swapper_space = swap_address_space(entry);
int err;
*retpage = NULL;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(swapper_space, entry.val);
if (found_page)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page(GFP_KERNEL);
if (!new_page)
break; /* Out of memory */
}
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_preload(GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) { /* seems racy */
radix_tree_preload_end();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
lru_cache_add_anon(new_page);
*retpage = new_page;
return ZSWAP_SWAPCACHE_NEW;
}
radix_tree_preload_end();
ClearPageSwapBacked(new_page);
__clear_page_locked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry, NULL);
} while (err != -ENOMEM);
if (new_page)
page_cache_release(new_page);
if (!found_page)
return ZSWAP_SWAPCACHE_FAIL;
*retpage = found_page;
return ZSWAP_SWAPCACHE_EXIST;
}
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages;
struct page *pages[PIPE_BUFFERS];
struct partial_page partial[PIPE_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
size_t total_len;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
};
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (nr_pages > PIPE_BUFFERS)
nr_pages = PIPE_BUFFERS;
/*
* Initiate read-ahead on this page range. however, don't call into
* read-ahead if this is a non-zero offset (we are likely doing small
* chunk splice and the page is already there) for a single page.
*/
if (!loff || nr_pages > 1)
page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);
/*
* Now fill in the holes:
*/
error = 0;
total_len = 0;
/*
* Lookup the (hopefully) full range of pages we need.
*/
spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
/*
* If find_get_pages_contig() returned fewer pages than we needed,
* allocate the rest.
*/
index += spd.nr_pages;
while (spd.nr_pages < nr_pages) {
/*
* Page could be there, find_get_pages_contig() breaks on
* the first hole.
*/
page = find_get_page(mapping, index);
if (!page) {
/*
* Make sure the read-ahead engine is notified
* about this failure.
*/
handle_ra_miss(mapping, &in->f_ra, index);
/*
* page didn't exist, allocate one.
*/
page = page_cache_alloc_cold(mapping);
if (!page)
break;
error = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL);
if (unlikely(error)) {
page_cache_release(page);
if (error == -EEXIST)
continue;
break;
}
/*
* add_to_page_cache() locks the page, unlock it
* to avoid convoluting the logic below even more.
*/
unlock_page(page);
}
pages[spd.nr_pages++] = page;
index++;
}
/*
* Now loop over the map and see if we need to start IO on any
* pages, fill in the partial map, etc.
*/
index = *ppos >> PAGE_CACHE_SHIFT;
nr_pages = spd.nr_pages;
spd.nr_pages = 0;
for (page_nr = 0; page_nr < nr_pages; page_nr++) {
unsigned int this_len;
if (!len)
break;
/*
* this_len is the max we'll use from this page
*/
this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
page = pages[page_nr];
/*
* If the page isn't uptodate, we may need to start io on it
*/
if (!PageUptodate(page)) {
/*
* If in nonblock mode then dont block on waiting
* for an in-flight io page
*/
if (flags & SPLICE_F_NONBLOCK)
break;
lock_page(page);
/*
* page was truncated, stop here. if this isn't the
* first page, we'll just complete what we already
* added
*/
if (!page->mapping) {
unlock_page(page);
break;
}
/*
* page was already under io and is now done, great
*/
if (PageUptodate(page)) {
unlock_page(page);
goto fill_it;
}
/*
* need to read in the page
*/
error = mapping->a_ops->readpage(in, page);
if (unlikely(error)) {
/*
* We really should re-lookup the page here,
* but it complicates things a lot. Instead
* lets just do what we already stored, and
* we'll get it the next time we are called.
*/
if (error == AOP_TRUNCATED_PAGE)
error = 0;
break;
}
/*
* i_size must be checked after ->readpage().
*/
isize = i_size_read(mapping->host);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index))
break;
/*
* if this is the last page, see if we need to shrink
* the length and stop
*/
if (end_index == index) {
loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK);
if (total_len + loff > isize)
break;
/*
* force quit after adding this page
*/
len = this_len;
this_len = min(this_len, loff);
loff = 0;
}
}
fill_it:
partial[page_nr].offset = loff;
partial[page_nr].len = this_len;
len -= this_len;
total_len += this_len;
loff = 0;
spd.nr_pages++;
index++;
}
/*
* Release any pages at the end, if we quit early. 'i' is how far
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
page_cache_release(pages[page_nr++]);
if (spd.nr_pages)
return splice_to_pipe(pipe, &spd);
return error;
}
#ifdef CONFIG_SWAP
/* shmem/tmpfs may return swap: account for swapcache page too. */
if (radix_tree_exceptional_entry(page)) {
swp_entry_t swap = radix_to_swp_entry(page);
page = find_get_page(&swapper_space, swap.val);
}
#endif
<<<<<<< HEAD
=======
=======
*
* However when tmpfs moves the page from pagecache and into swapcache,
* it is still in core, but the find_get_page below won't find it.
* No big deal, but make a note of it.
*/
page = find_get_page(mapping, pgoff);
>>>>>>> 58a75b6a81be54a8b491263ca1af243e9d8617b9
>>>>>>> ae1773bb70f3d7cf73324ce8fba787e01d8fa9f2
if (page) {
present = PageUptodate(page);
page_cache_release(page);
}
return present;
}
static void mincore_unmapped_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
unsigned char *vec)
{
unsigned long nr = (end - addr) >> PAGE_SHIFT;
struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated)
{
struct page *found_page, *new_page = NULL;
struct address_space *swapper_space = swap_address_space(entry);
int err;
*new_page_allocated = false;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(swapper_space, swp_offset(entry));
if (found_page)
break;
/*
* Just skip read ahead for unused swap slot.
* During swap_off when swap_slot_cache is disabled,
* we have to handle the race between putting
* swap entry in swap cache and marking swap slot
* as SWAP_HAS_CACHE. That's done in later part of code or
* else swap_off will be aborted if we return NULL.
*/
if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page_vma(gfp_mask, vma, addr);
if (!new_page)
break; /* Out of memory */
}
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) {
radix_tree_preload_end();
/*
* We might race against get_swap_page() and stumble
* across a SWAP_HAS_CACHE swap_map entry whose page
* has not been brought into the swapcache yet.
*/
cond_resched();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__SetPageLocked(new_page);
__SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
/*
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
*new_page_allocated = true;
return new_page;
}
radix_tree_preload_end();
__ClearPageLocked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
put_swap_page(new_page, entry);
} while (err != -ENOMEM);
if (new_page)
put_page(new_page);
return found_page;
}
/*
* zcache_get_swap_cache_page
*
* This is an adaption of read_swap_cache_async()
*
* If success, page is returned in retpage
* Returns 0 if page was already in the swap cache, page is not locked
* Returns 1 if the new page needs to be populated, page is locked
*/
static int zcache_get_swap_cache_page(int type, pgoff_t offset,
struct page *new_page)
{
struct page *found_page;
swp_entry_t entry = swp_entry(type, offset);
int err;
BUG_ON(new_page == NULL);
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(&swapper_space, entry.val);
if (found_page)
return 0;
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_preload(GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) { /* seems racy */
radix_tree_preload_end();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
lru_cache_add_anon(new_page);
return 1;
}
radix_tree_preload_end();
ClearPageSwapBacked(new_page);
__clear_page_locked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry, NULL);
/* FIXME: is it possible to get here without err==-ENOMEM?
* If not, we can dispense with the do loop, use goto retry */
} while (err != -ENOMEM);
return -ENOMEM;
}