/*
* invalidate part or all of a page
* - release a page and clean up its private data if offset is 0 (indicating
* the entire page)
*/
static void afs_invalidatepage(struct page *page, unsigned long offset)
{
struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
_enter("{%lu},%lu", page->index, offset);
BUG_ON(!PageLocked(page));
/* we clean up only if the entire page is being invalidated */
if (offset == 0) {
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
fscache_wait_on_page_write(vnode->cache, page);
fscache_uncache_page(vnode->cache, page);
ClearPageFsCache(page);
}
#endif
if (PagePrivate(page)) {
if (wb && !PageWriteback(page)) {
set_page_private(page, 0);
afs_put_writeback(wb);
}
if (!page_private(page))
ClearPagePrivate(page);
}
}
_leave("");
}
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 (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
_leave(" = F [cache busy]");
return 0;
}
#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;
}
/* copied from buffer.c */
static void
__clear_page_buffers(struct page *page)
{
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
}
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
(offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))
return;
if (PageDirty(page)) {
if (inode->i_ino == F2FS_META_INO(sbi))
dec_page_count(sbi, F2FS_DIRTY_META);
else if (inode->i_ino == F2FS_NODE_INO(sbi))
dec_page_count(sbi, F2FS_DIRTY_NODES);
else
inode_dec_dirty_pages(inode);
}
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
return;
ClearPagePrivate(page);
}
void fscrypt_restore_control_page(struct page *page)
{
struct fscrypt_ctx *ctx;
ctx = (struct fscrypt_ctx *)page_private(page);
set_page_private(page, (unsigned long)NULL);
ClearPagePrivate(page);
unlock_page(page);
fscrypt_release_ctx(ctx);
}
void ext4_restore_control_page(struct page *data_page)
{
struct ext4_crypto_ctx *ctx =
(struct ext4_crypto_ctx *)page_private(data_page);
set_page_private(data_page, (unsigned long)NULL);
ClearPagePrivate(data_page);
unlock_page(data_page);
ext4_release_crypto_ctx(ctx);
}
static int
__change_page_attr(struct page *page, pgprot_t prot)
{
pte_t *kpte;
unsigned long address;
struct page *kpte_page;
BUG_ON(PageHighMem(page));
address = (unsigned long)page_address(page);
kpte = lookup_address(address);
if (!kpte)
return -EINVAL;
kpte_page = virt_to_page(kpte);
if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) {
if ((pte_val(*kpte) & _PAGE_PSE) == 0) {
set_pte_atomic(kpte, mk_pte(page, prot));
} else {
pgprot_t ref_prot;
struct page *split;
ref_prot =
((address & LARGE_PAGE_MASK) < (unsigned long)&_etext)
? PAGE_KERNEL_EXEC : PAGE_KERNEL;
split = split_large_page(address, prot, ref_prot);
if (!split)
return -ENOMEM;
set_pmd_pte(kpte,address,mk_pte(split, ref_prot));
kpte_page = split;
}
page_private(kpte_page)++;
} else if ((pte_val(*kpte) & _PAGE_PSE) == 0) {
set_pte_atomic(kpte, mk_pte(page, PAGE_KERNEL));
BUG_ON(page_private(kpte_page) == 0);
page_private(kpte_page)--;
} else
BUG();
/*
* If the pte was reserved, it means it was created at boot
* time (not via split_large_page) and in turn we must not
* replace it with a largepage.
*/
if (!PageReserved(kpte_page)) {
if (cpu_has_pse && (page_private(kpte_page) == 0)) {
ClearPagePrivate(kpte_page);
list_add(&kpte_page->lru, &df_list);
revert_page(kpte_page, address);
}
}
return 0;
}
int f2fs_release_page(struct page *page, gfp_t wait)
{
/* If this is dirty page, keep PagePrivate */
if (PageDirty(page))
return 0;
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
return 0;
ClearPagePrivate(page);
return 1;
}
/**
* gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
* @nr_pages; number of pages to free
* @pages: the pages
*/
void gnttab_free_pages(int nr_pages, struct page **pages)
{
int i;
for (i = 0; i < nr_pages; i++) {
if (PagePrivate(pages[i])) {
#if BITS_PER_LONG < 64
kfree((void *)page_private(pages[i]));
#endif
ClearPagePrivate(pages[i]);
}
}
free_xenballooned_pages(nr_pages, pages);
}
/*
* release a page and cleanup its private data
*/
static int afs_file_releasepage(struct page *page, gfp_t gfp_flags)
{
_enter("{%lu},%x", page->index, gfp_flags);
#ifdef CONFIG_AFS_FSCACHE
wait_on_page_fs_misc(page);
fscache_uncache_page(AFS_FS_I(page->mapping->host)->cache, page);
ClearPagePrivate(page);
#endif
/* indicate that the page can be released */
_leave(" = 1");
return 1;
} /* end afs_file_releasepage() */
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
bool lazy = false;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
if (kmap_ops &&
!in_interrupt() &&
paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
unsigned long pfn = page_to_pfn(pages[i]);
if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) {
ret = -EINVAL;
goto out;
}
set_page_private(pages[i], INVALID_P2M_ENTRY);
WARN_ON(!PagePrivate(pages[i]));
ClearPagePrivate(pages[i]);
set_phys_to_machine(pfn, pages[i]->index);
if (kmap_ops)
ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
if (ret)
goto out;
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
/*
* Remove a write request from an inode
*/
static void nfs_inode_remove_request(struct nfs_page *req)
{
struct inode *inode = req->wb_context->path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
BUG_ON (!NFS_WBACK_BUSY(req));
spin_lock(&inode->i_lock);
set_page_private(req->wb_page, 0);
ClearPagePrivate(req->wb_page);
radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
nfsi->npages--;
if (!nfsi->npages) {
spin_unlock(&inode->i_lock);
iput(inode);
} else
spin_unlock(&inode->i_lock);
nfs_clear_request(req);
nfs_release_request(req);
}
/*
* release a page and cleanup its private data
*/
static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
struct afs_writeback *wb;
_enter("{{%x:%u}[%lu],%lx},%x",
vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
gfp_flags);
if (PagePrivate(page)) {
wb = (struct afs_writeback *) page_private(page);
ASSERT(wb != NULL);
set_page_private(page, 0);
ClearPagePrivate(page);
afs_put_writeback(wb);
}
_leave(" = 0");
return 0;
}
/*
* It only removes the dentry from the dentry page, corresponding name
* entry in name page does not need to be touched during deletion.
*/
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode)
{
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
int i;
if (f2fs_has_inline_dentry(dir))
return f2fs_delete_inline_entry(dentry, page, dir, inode);
lock_page(page);
f2fs_wait_on_page_writeback(page, DATA);
dentry_blk = page_address(page);
bit_pos = dentry - dentry_blk->dentry;
for (i = 0; i < slots; i++)
test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
/* Let's check and deallocate this dentry page */
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
0);
kunmap(page); /* kunmap - pair of f2fs_find_entry */
set_page_dirty(page);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode)
f2fs_drop_nlink(dir, inode, NULL);
if (bit_pos == NR_DENTRY_IN_BLOCK) {
truncate_hole(dir, page->index, page->index + 1);
clear_page_dirty_for_io(page);
ClearPagePrivate(page);
ClearPageUptodate(page);
inode_dec_dirty_pages(dir);
}
f2fs_put_page(page, 1);
}
/*
* release a page and cleanup its private data
*/
static int afs_file_releasepage(struct page *page, gfp_t gfp_flags)
{
struct cachefs_page *pageio;
_enter("{%lu},%x", page->index, gfp_flags);
if (PagePrivate(page)) {
#ifdef AFS_CACHING_SUPPORT
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
cachefs_uncache_page(vnode->cache, page);
#endif
pageio = (struct cachefs_page *) page_private(page);
set_page_private(page, 0);
ClearPagePrivate(page);
kfree(pageio);
}
_leave(" = 0");
return 0;
} /* end afs_file_releasepage() */
/*
* __mcopy_atomic processing for HUGETLB vmas. Note that this routine is
* called with mmap_sem held, it will release mmap_sem before returning.
*/
static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
struct vm_area_struct *dst_vma,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
bool zeropage)
{
int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED;
int vm_shared = dst_vma->vm_flags & VM_SHARED;
ssize_t err;
pte_t *dst_pte;
unsigned long src_addr, dst_addr;
long copied;
struct page *page;
struct hstate *h;
unsigned long vma_hpagesize;
pgoff_t idx;
u32 hash;
struct address_space *mapping;
/*
* There is no default zero huge page for all huge page sizes as
* supported by hugetlb. A PMD_SIZE huge pages may exist as used
* by THP. Since we can not reliably insert a zero page, this
* feature is not supported.
*/
if (zeropage) {
up_read(&dst_mm->mmap_sem);
return -EINVAL;
}
src_addr = src_start;
dst_addr = dst_start;
copied = 0;
page = NULL;
vma_hpagesize = vma_kernel_pagesize(dst_vma);
/*
* Validate alignment based on huge page size
*/
err = -EINVAL;
if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1))
goto out_unlock;
retry:
/*
* On routine entry dst_vma is set. If we had to drop mmap_sem and
* retry, dst_vma will be set to NULL and we must lookup again.
*/
if (!dst_vma) {
err = -ENOENT;
dst_vma = find_vma(dst_mm, dst_start);
if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
goto out_unlock;
/*
* Check the vma is registered in uffd, this is
* required to enforce the VM_MAYWRITE check done at
* uffd registration time.
*/
if (!dst_vma->vm_userfaultfd_ctx.ctx)
goto out_unlock;
if (dst_start < dst_vma->vm_start ||
dst_start + len > dst_vma->vm_end)
goto out_unlock;
err = -EINVAL;
if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
goto out_unlock;
vm_shared = dst_vma->vm_flags & VM_SHARED;
}
if (WARN_ON(dst_addr & (vma_hpagesize - 1) ||
(len - copied) & (vma_hpagesize - 1)))
goto out_unlock;
/*
* If not shared, ensure the dst_vma has a anon_vma.
*/
err = -ENOMEM;
if (!vm_shared) {
if (unlikely(anon_vma_prepare(dst_vma)))
goto out_unlock;
}
h = hstate_vma(dst_vma);
while (src_addr < src_start + len) {
pte_t dst_pteval;
BUG_ON(dst_addr >= dst_start + len);
VM_BUG_ON(dst_addr & ~huge_page_mask(h));
/*
* Serialize via hugetlb_fault_mutex
*/
idx = linear_page_index(dst_vma, dst_addr);
mapping = dst_vma->vm_file->f_mapping;
hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping,
idx, dst_addr);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
err = -ENOMEM;
dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h));
if (!dst_pte) {
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
goto out_unlock;
}
err = -EEXIST;
dst_pteval = huge_ptep_get(dst_pte);
if (!huge_pte_none(dst_pteval)) {
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
goto out_unlock;
}
err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma,
dst_addr, src_addr, &page);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
vm_alloc_shared = vm_shared;
cond_resched();
if (unlikely(err == -ENOENT)) {
up_read(&dst_mm->mmap_sem);
BUG_ON(!page);
err = copy_huge_page_from_user(page,
(const void __user *)src_addr,
pages_per_huge_page(h), true);
if (unlikely(err)) {
err = -EFAULT;
goto out;
}
down_read(&dst_mm->mmap_sem);
dst_vma = NULL;
goto retry;
} else
BUG_ON(page);
if (!err) {
dst_addr += vma_hpagesize;
src_addr += vma_hpagesize;
copied += vma_hpagesize;
if (fatal_signal_pending(current))
err = -EINTR;
}
if (err)
break;
}
out_unlock:
up_read(&dst_mm->mmap_sem);
out:
if (page) {
/*
* We encountered an error and are about to free a newly
* allocated huge page.
*
* Reservation handling is very subtle, and is different for
* private and shared mappings. See the routine
* restore_reserve_on_error for details. Unfortunately, we
* can not call restore_reserve_on_error now as it would
* require holding mmap_sem.
*
* If a reservation for the page existed in the reservation
* map of a private mapping, the map was modified to indicate
* the reservation was consumed when the page was allocated.
* We clear the PagePrivate flag now so that the global
* reserve count will not be incremented in free_huge_page.
* The reservation map will still indicate the reservation
* was consumed and possibly prevent later page allocation.
* This is better than leaking a global reservation. If no
* reservation existed, it is still safe to clear PagePrivate
* as no adjustments to reservation counts were made during
* allocation.
*
* The reservation map for shared mappings indicates which
* pages have reservations. When a huge page is allocated
* for an address with a reservation, no change is made to
* the reserve map. In this case PagePrivate will be set
* to indicate that the global reservation count should be
* incremented when the page is freed. This is the desired
* behavior. However, when a huge page is allocated for an
* address without a reservation a reservation entry is added
* to the reservation map, and PagePrivate will not be set.
* When the page is freed, the global reserve count will NOT
* be incremented and it will appear as though we have leaked
* reserved page. In this case, set PagePrivate so that the
* global reserve count will be incremented to match the
* reservation map entry which was created.
*
* Note that vm_alloc_shared is based on the flags of the vma
* for which the page was originally allocated. dst_vma could
* be different or NULL on error.
*/
if (vm_alloc_shared)
SetPagePrivate(page);
else
ClearPagePrivate(page);
put_page(page);
}
BUG_ON(copied < 0);
BUG_ON(err > 0);
BUG_ON(!copied && !err);
return copied ? copied : err;
}
/*
* AFS read page from file (or symlink)
*/
static int afs_file_readpage(struct file *file, struct page *page)
{
struct afs_rxfs_fetch_descriptor desc;
struct afs_vnode *vnode;
struct inode *inode;
int ret;
inode = page->mapping->host;
_enter("{%lu},%p{%lu}", inode->i_ino, page, page->index);
vnode = AFS_FS_I(inode);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (vnode->flags & AFS_VNODE_DELETED)
goto error;
#ifdef CONFIG_AFS_FSCACHE
/* is it cached? */
ret = fscache_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted (page in cache) */
case 0:
break;
/* page not yet cached */
case -ENODATA:
_debug("cache said ENODATA");
goto go_on;
/* page will not be cached */
case -ENOBUFS:
_debug("cache said ENOBUFS");
default:
go_on:
desc.fid = vnode->fid;
desc.offset = page->index << PAGE_CACHE_SHIFT;
desc.size = min((size_t) (inode->i_size - desc.offset),
(size_t) PAGE_SIZE);
desc.buffer = kmap(page);
clear_page(desc.buffer);
/* read the contents of the file from the server into the
* page */
ret = afs_vnode_fetch_data(vnode, &desc);
kunmap(page);
if (ret < 0) {
if (ret == -ENOENT) {
kdebug("got NOENT from server"
" - marking file deleted and stale");
vnode->flags |= AFS_VNODE_DELETED;
ret = -ESTALE;
}
#ifdef CONFIG_AFS_FSCACHE
fscache_uncache_page(vnode->cache, page);
ClearPagePrivate(page);
#endif
goto error;
}
SetPageUptodate(page);
/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
if (PagePrivate(page)) {
if (TestSetPageFsMisc(page))
BUG();
if (fscache_write_page(vnode->cache,
page,
afs_file_readpage_write_complete,
NULL,
GFP_KERNEL) != 0
) {
fscache_uncache_page(vnode->cache, page);
ClearPagePrivate(page);
end_page_fs_misc(page);
}
}
#endif
unlock_page(page);
}
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
_leave(" = %d", ret);
return ret;
} /* end afs_file_readpage() */
int m2p_remove_override(struct page *page, bool clear_pte)
{
unsigned long flags;
unsigned long mfn;
unsigned long pfn;
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
int ret = 0;
pfn = page_to_pfn(page);
mfn = get_phys_to_machine(pfn);
if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT))
return -EINVAL;
if (!PageHighMem(page)) {
address = (unsigned long)__va(pfn << PAGE_SHIFT);
ptep = lookup_address(address, &level);
if (WARN(ptep == NULL || level != PG_LEVEL_4K,
"m2p_remove_override: pfn %lx not mapped", pfn))
return -EINVAL;
}
spin_lock_irqsave(&m2p_override_lock, flags);
list_del(&page->lru);
spin_unlock_irqrestore(&m2p_override_lock, flags);
WARN_ON(!PagePrivate(page));
ClearPagePrivate(page);
if (clear_pte) {
struct gnttab_map_grant_ref *map_op =
(struct gnttab_map_grant_ref *) page->index;
set_phys_to_machine(pfn, map_op->dev_bus_addr);
if (!PageHighMem(page)) {
struct multicall_space mcs;
struct gnttab_unmap_grant_ref *unmap_op;
/*
* It might be that we queued all the m2p grant table
* hypercalls in a multicall, then m2p_remove_override
* get called before the multicall has actually been
* issued. In this case handle is going to -1 because
* it hasn't been modified yet.
*/
if (map_op->handle == -1)
xen_mc_flush();
/*
* Now if map_op->handle is negative it means that the
* hypercall actually returned an error.
*/
if (map_op->handle == GNTST_general_error) {
printk(KERN_WARNING "m2p_remove_override: "
"pfn %lx mfn %lx, failed to modify kernel mappings",
pfn, mfn);
return -1;
}
mcs = xen_mc_entry(
sizeof(struct gnttab_unmap_grant_ref));
unmap_op = mcs.args;
unmap_op->host_addr = map_op->host_addr;
unmap_op->handle = map_op->handle;
unmap_op->dev_bus_addr = 0;
MULTI_grant_table_op(mcs.mc,
GNTTABOP_unmap_grant_ref, unmap_op, 1);
xen_mc_issue(PARAVIRT_LAZY_MMU);
set_pte_at(&init_mm, address, ptep,
pfn_pte(pfn, PAGE_KERNEL));
__flush_tlb_single(address);
map_op->host_addr = 0;
}
} else
set_phys_to_machine(pfn, page->index);
/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
* somewhere in this domain, even before being added to the
* m2p_override (see comment above in m2p_add_override).
* If there are no other entries in the m2p_override corresponding
* to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
* the original pfn (the one shared by the frontend): the backend
* cannot do any IO on this page anymore because it has been
* unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
* the original pfn causes mfn_to_pfn(mfn) to return the frontend
* pfn again. */
mfn &= ~FOREIGN_FRAME_BIT;
ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
m2p_find_override(mfn) == NULL)
set_phys_to_machine(pfn, 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);
}
