/*
* release a page and clean up its private state if it's not busy
* - return true if the page can now be released, false if not
*/
static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
_enter("{{%x:%u}[%lu],%lx},%x",
vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
gfp_flags);
/* deny if page is being written to the cache and the caller hasn't
* elected to wait */
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
if (fscache_check_page_write(vnode->cache, page)) {
if (!(gfp_flags & __GFP_WAIT)) {
_leave(" = F [cache busy]");
return 0;
}
fscache_wait_on_page_write(vnode->cache, page);
}
fscache_uncache_page(vnode->cache, page);
ClearPageFsCache(page);
}
#endif
if (PagePrivate(page)) {
if (wb) {
set_page_private(page, 0);
afs_put_writeback(wb);
}
ClearPagePrivate(page);
}
/* indicate that the page can be released */
_leave(" = T");
return 1;
}
/*
* This must be called only on pages that have
* been verified to be in the swap cache.
*/
void __delete_from_swap_cache(struct page *page)
{
struct address_space *address_space;
int i, nr = hpage_nr_pages(page);
swp_entry_t entry;
pgoff_t idx;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
VM_BUG_ON_PAGE(PageWriteback(page), page);
entry.val = page_private(page);
address_space = swap_address_space(entry);
idx = swp_offset(entry);
for (i = 0; i < nr; i++) {
radix_tree_delete(&address_space->page_tree, idx + i);
set_page_private(page + i, 0);
}
ClearPageSwapCache(page);
address_space->nrpages -= nr;
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
ADD_CACHE_INFO(del_total, nr);
}
/* Add an MFN override for a particular page */
int m2p_add_override(unsigned long mfn, struct page *page,
struct gnttab_map_grant_ref *kmap_op)
{
unsigned long flags;
unsigned long pfn;
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
int ret = 0;
pfn = page_to_pfn(page);
if (!PageHighMem(page)) {
address = (unsigned long)__va(pfn << PAGE_SHIFT);
ptep = lookup_address(address, &level);
if (WARN(ptep == NULL || level != PG_LEVEL_4K,
"m2p_add_override: pfn %lx not mapped", pfn))
return -EINVAL;
}
WARN_ON(PagePrivate(page));
SetPagePrivate(page);
set_page_private(page, mfn);
page->index = pfn_to_mfn(pfn);
if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
return -ENOMEM;
if (kmap_op != NULL) {
if (!PageHighMem(page)) {
struct multicall_space mcs =
xen_mc_entry(sizeof(*kmap_op));
MULTI_grant_table_op(mcs.mc,
GNTTABOP_map_grant_ref, kmap_op, 1);
xen_mc_issue(PARAVIRT_LAZY_MMU);
}
/* let's use dev_bus_addr to record the old mfn instead */
kmap_op->dev_bus_addr = page->index;
page->index = (unsigned long) kmap_op;
}
spin_lock_irqsave(&m2p_override_lock, flags);
list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]);
spin_unlock_irqrestore(&m2p_override_lock, flags);
/* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
* this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
* pfn so that the following mfn_to_pfn(mfn) calls will return the
* pfn from the m2p_override (the backend pfn) instead.
* We need to do this because the pages shared by the frontend
* (xen-blkfront) can be already locked (lock_page, called by
* do_read_cache_page); when the userspace backend tries to use them
* with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
* do_blockdev_direct_IO is going to try to lock the same pages
* again resulting in a deadlock.
* As a side effect get_user_pages_fast might not be safe on the
* frontend pages while they are being shared with the backend,
* because mfn_to_pfn (that ends up being called by GUPF) will
* return the backend pfn rather than the frontend pfn. */
ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
if (ret == 0 && get_phys_to_machine(pfn) == mfn)
set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
return 0;
}
/* Two pass sync: first using WB_SYNC_NONE, then WB_SYNC_ALL */
static int nfs_write_mapping(struct address_space *mapping, int how)
{
struct writeback_control wbc = {
.bdi = mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
};
return __nfs_write_mapping(mapping, &wbc, how);
}
/*
* flush the inode to disk.
*/
int nfs_wb_all(struct inode *inode)
{
return nfs_write_mapping(inode->i_mapping, 0);
}
int nfs_wb_nocommit(struct inode *inode)
{
return nfs_write_mapping(inode->i_mapping, FLUSH_NOCOMMIT);
}
int nfs_wb_page_cancel(struct inode *inode, struct page *page)
{
struct nfs_page *req;
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.bdi = page->mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
.range_end = range_end,
};
int ret = 0;
BUG_ON(!PageLocked(page));
for (;;) {
req = nfs_page_find_request(page);
if (req == NULL)
goto out;
if (test_bit(PG_CLEAN, &req->wb_flags)) {
nfs_release_request(req);
break;
}
if (nfs_lock_request_dontget(req)) {
nfs_inode_remove_request(req);
/*
* In case nfs_inode_remove_request has marked the
* page as being dirty
*/
cancel_dirty_page(page, PAGE_CACHE_SIZE);
nfs_unlock_request(req);
break;
}
ret = nfs_wait_on_request(req);
if (ret < 0)
goto out;
}
if (!PagePrivate(page))
return 0;
ret = nfs_sync_mapping_wait(page->mapping, &wbc, FLUSH_INVALIDATE);
out:
return ret;
}
static int nfs_wb_page_priority(struct inode *inode, struct page *page,
int how)
{
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.bdi = page->mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
.range_end = range_end,
};
int ret;
do {
if (clear_page_dirty_for_io(page)) {
ret = nfs_writepage_locked(page, &wbc);
if (ret < 0)
goto out_error;
} else if (!PagePrivate(page))
break;
ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
if (ret < 0)
goto out_error;
} while (PagePrivate(page));
return 0;
out_error:
__mark_inode_dirty(inode, I_DIRTY_PAGES);
return ret;
}
/*
* Write back all requests on one page - we do this before reading it.
*/
int nfs_wb_page(struct inode *inode, struct page* page)
{
return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
}
#ifdef CONFIG_MIGRATION
int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
struct page *page)
{
struct nfs_page *req;
int ret;
if (PageFsCache(page))
nfs_fscache_release_page(page, GFP_KERNEL);
req = nfs_find_and_lock_request(page);
ret = PTR_ERR(req);
if (IS_ERR(req))
goto out;
ret = migrate_page(mapping, newpage, page);
if (!req)
goto out;
if (ret)
goto out_unlock;
page_cache_get(newpage);
req->wb_page = newpage;
SetPagePrivate(newpage);
set_page_private(newpage, page_private(page));
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
out_unlock:
nfs_clear_page_tag_locked(req);
nfs_release_request(req);
out:
return ret;
}
#endif
int __init nfs_init_writepagecache(void)
{
nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
sizeof(struct nfs_write_data),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_wdata_cachep == NULL)
return -ENOMEM;
nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
nfs_wdata_cachep);
if (nfs_wdata_mempool == NULL)
return -ENOMEM;
nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
nfs_wdata_cachep);
if (nfs_commit_mempool == NULL)
return -ENOMEM;
/*
* NFS congestion size, scale with available memory.
*
* 64MB: 8192k
* 128MB: 11585k
* 256MB: 16384k
* 512MB: 23170k
* 1GB: 32768k
* 2GB: 46340k
* 4GB: 65536k
* 8GB: 92681k
* 16GB: 131072k
*
* This allows larger machines to have larger/more transfers.
* Limit the default to 256M
*/
nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
if (nfs_congestion_kb > 256*1024)
nfs_congestion_kb = 256*1024;
return 0;
}
void nfs_destroy_writepagecache(void)
{
mempool_destroy(nfs_commit_mempool);
mempool_destroy(nfs_wdata_mempool);
kmem_cache_destroy(nfs_wdata_cachep);
}
/*
* prepare to perform part of a write to a page
*/
int afs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct page *page;
struct key *key = afs_file_key(file);
unsigned long priv;
unsigned f, from = pos & (PAGE_SIZE - 1);
unsigned t, to = from + len;
pgoff_t index = pos >> PAGE_SHIFT;
int ret;
_enter("{%x:%u},{%lx},%u,%u",
vnode->fid.vid, vnode->fid.vnode, index, from, to);
/* We want to store information about how much of a page is altered in
* page->private.
*/
BUILD_BUG_ON(PAGE_SIZE > 32768 && sizeof(page->private) < 8);
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
if (!PageUptodate(page) && len != PAGE_SIZE) {
ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page);
if (ret < 0) {
unlock_page(page);
put_page(page);
_leave(" = %d [prep]", ret);
return ret;
}
SetPageUptodate(page);
}
/* page won't leak in error case: it eventually gets cleaned off LRU */
*pagep = page;
try_again:
/* See if this page is already partially written in a way that we can
* merge the new write with.
*/
t = f = 0;
if (PagePrivate(page)) {
priv = page_private(page);
f = priv & AFS_PRIV_MAX;
t = priv >> AFS_PRIV_SHIFT;
ASSERTCMP(f, <=, t);
}
if (f != t) {
if (PageWriteback(page)) {
trace_afs_page_dirty(vnode, tracepoint_string("alrdy"),
page->index, priv);
goto flush_conflicting_write;
}
/* If the file is being filled locally, allow inter-write
* spaces to be merged into writes. If it's not, only write
* back what the user gives us.
*/
if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
(to < f || from > t))
goto flush_conflicting_write;
if (from < f)
f = from;
if (to > t)
t = to;
} else {
f = from;
t = to;
}
priv = (unsigned long)t << AFS_PRIV_SHIFT;
priv |= f;
trace_afs_page_dirty(vnode, tracepoint_string("begin"),
page->index, priv);
SetPagePrivate(page);
set_page_private(page, priv);
_leave(" = 0");
return 0;
/* The previous write and this write aren't adjacent or overlapping, so
* flush the page out.
*/
flush_conflicting_write:
_debug("flush conflict");
ret = write_one_page(page);
if (ret < 0) {
_leave(" = %d", ret);
return ret;
}
ret = lock_page_killable(page);
if (ret < 0) {
_leave(" = %d", ret);
return ret;
}
goto try_again;
}