static void evict_entry(struct drm_gem_object *obj,
enum tiler_fmt fmt, struct usergart_entry *entry)
{
if (obj->dev->dev_mapping) {
struct omap_gem_object *omap_obj = to_omap_bo(obj);
int n = usergart[fmt].height;
size_t size = PAGE_SIZE * n;
loff_t off = mmap_offset(obj) +
(entry->obj_pgoff << PAGE_SHIFT);
const int m = 1 + ((omap_obj->width << fmt) / PAGE_SIZE);
if (m > 1) {
int i;
/* if stride > than PAGE_SIZE then sparse mapping: */
for (i = n; i > 0; i--) {
unmap_mapping_range(obj->dev->dev_mapping,
off, PAGE_SIZE, 1);
off += PAGE_SIZE * m;
}
} else {
unmap_mapping_range(obj->dev->dev_mapping, off, size, 1);
}
}
entry->obj = NULL;
}
void fuse_truncate(struct address_space *mapping, loff_t offset)
{
/* See vmtruncate() */
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(mapping, offset);
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
}
///////////////////////////////////////////////////////////
// DropPages
//
//
///////////////////////////////////////////////////////////
void
DropPages(
IN struct address_space* m
)
{
filemap_fdatawrite( m );
unmap_mapping_range( m, 0, 0, 1 );
truncate_inode_pages( m, 0 );
unmap_mapping_range( m, 0, 0, 1 );
}
void spu_unmap_mappings(struct spu_context *ctx)
{
if (ctx->local_store)
unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
if (ctx->mfc)
unmap_mapping_range(ctx->mfc, 0, 0x4000, 1);
if (ctx->cntl)
unmap_mapping_range(ctx->cntl, 0, 0x4000, 1);
if (ctx->signal1)
unmap_mapping_range(ctx->signal1, 0, 0x4000, 1);
if (ctx->signal2)
unmap_mapping_range(ctx->signal2, 0, 0x4000, 1);
}
/**
* truncate_pagecache - unmap and remove pagecache that has been truncated
* @inode: inode
* @newsize: new file size
*
* inode's new i_size must already be written before truncate_pagecache
* is called.
*
* This function should typically be called before the filesystem
* releases resources associated with the freed range (eg. deallocates
* blocks). This way, pagecache will always stay logically coherent
* with on-disk format, and the filesystem would not have to deal with
* situations such as writepage being called for a page that has already
* had its underlying blocks deallocated.
*/
void truncate_pagecache(struct inode *inode, loff_t newsize)
{
struct address_space *mapping = inode->i_mapping;
loff_t holebegin = round_up(newsize, PAGE_SIZE);
/*
* unmap_mapping_range is called twice, first simply for
* efficiency so that truncate_inode_pages does fewer
* single-page unmaps. However after this first call, and
* before truncate_inode_pages finishes, it is possible for
* private pages to be COWed, which remain after
* truncate_inode_pages finishes, hence the second
* unmap_mapping_range call must be made for correctness.
*/
unmap_mapping_range(mapping, holebegin, 0, 1);
truncate_inode_pages(mapping, newsize);
unmap_mapping_range(mapping, holebegin, 0, 1);
}
int truncate_inode_page(struct address_space *mapping, struct page *page)
{
if (page_mapped(page)) {
unmap_mapping_range(mapping,
(loff_t)page->index << PAGE_CACHE_SHIFT,
PAGE_CACHE_SIZE, 0);
}
return truncate_complete_page(mapping, page);
}
/**
* nfs_sync_mapping - helper to flush all mmapped dirty data to disk
*/
int nfs_sync_mapping(struct address_space *mapping)
{
int ret = 0;
if (mapping->nrpages != 0) {
unmap_mapping_range(mapping, 0, 0, 0);
ret = nfs_wb_all(mapping->host);
}
return ret;
}
void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo)
{
struct ttm_bo_device *bdev = bo->bdev;
loff_t offset = (loff_t) bo->addr_space_offset;
loff_t holelen = ((loff_t) bo->mem.num_pages) << PAGE_SHIFT;
if (!bdev->dev_mapping)
return;
unmap_mapping_range(bdev->dev_mapping, offset, holelen, 1);
ttm_mem_io_free_vm(bo);
}
static void evict_entry(struct drm_gem_object *obj,
enum tiler_fmt fmt, struct usergart_entry *entry)
{
if (obj->dev->dev_mapping) {
size_t size = PAGE_SIZE * usergart[fmt].height;
loff_t off = mmap_offset(obj) +
(entry->obj_pgoff << PAGE_SHIFT);
unmap_mapping_range(obj->dev->dev_mapping, off, size, 1);
}
entry->obj = NULL;
}
/* XXX put nice comment here. talk about __free_pte -> dirty pages and
* nopage's reference passing to the pte
*/
int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last)
{
int rc = -ENOENT;
LASSERTF(last > first, "last %llu first %llu\n", last, first);
if (mapping_mapped(mapping)) {
rc = 0;
unmap_mapping_range(mapping, first + PAGE_CACHE_SIZE - 1,
last - first + 1, 0);
}
return rc;
}
int truncate_inode_page(struct address_space *mapping, struct page *page)
{
loff_t holelen;
VM_BUG_ON_PAGE(PageTail(page), page);
holelen = PageTransHuge(page) ? HPAGE_PMD_SIZE : PAGE_SIZE;
if (page_mapped(page)) {
unmap_mapping_range(mapping,
(loff_t)page->index << PAGE_SHIFT,
holelen, 0);
}
return truncate_complete_page(mapping, page);
}
static void fuse_vmtruncate(struct _inode *inode, loff_t offset)
{
struct fuse_conn *fc = get_fuse_conn(inode);
int need_trunc;
spin_lock(&fc->lock);
need_trunc = inode->i_size > offset;
i_size_write(inode, offset);
spin_unlock(&fc->lock);
if (need_trunc) {
struct address_space *mapping = inode->i_mapping;
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(mapping, offset);
}
}
static int vvp_conf_set(const struct lu_env *env, struct cl_object *obj,
const struct cl_object_conf *conf)
{
struct ll_inode_info *lli = ll_i2info(conf->coc_inode);
if (conf->coc_opc == OBJECT_CONF_INVALIDATE) {
CDEBUG(D_VFSTRACE, DFID ": losing layout lock\n",
PFID(&lli->lli_fid));
ll_layout_version_set(lli, LL_LAYOUT_GEN_NONE);
/* Clean up page mmap for this inode.
* The reason for us to do this is that if the page has
* already been installed into memory space, the process
* can access it without interacting with lustre, so this
* page may be stale due to layout change, and the process
* will never be notified.
* This operation is expensive but mmap processes have to pay
* a price themselves.
*/
unmap_mapping_range(conf->coc_inode->i_mapping,
0, OBD_OBJECT_EOF, 0);
return 0;
}
if (conf->coc_opc != OBJECT_CONF_SET)
return 0;
if (conf->u.coc_md && conf->u.coc_md->lsm) {
CDEBUG(D_VFSTRACE, DFID ": layout version change: %u -> %u\n",
PFID(&lli->lli_fid), lli->lli_layout_gen,
conf->u.coc_md->lsm->lsm_layout_gen);
lli->lli_has_smd = lsm_has_objects(conf->u.coc_md->lsm);
ll_layout_version_set(lli, conf->u.coc_md->lsm->lsm_layout_gen);
} else {
CDEBUG(D_VFSTRACE, DFID ": layout nuked: %u.\n",
PFID(&lli->lli_fid), lli->lli_layout_gen);
lli->lli_has_smd = false;
ll_layout_version_set(lli, LL_LAYOUT_GEN_EMPTY);
}
return 0;
}
/*
* Device passthrough support
*/
static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq)
{
struct kvmppc_xive *xive = kvm->arch.xive;
if (irq >= KVMPPC_XIVE_NR_IRQS)
return -EINVAL;
/*
* Clear the ESB pages of the IRQ number being mapped (or
* unmapped) into the guest and let the the VM fault handler
* repopulate with the appropriate ESB pages (device or IC)
*/
pr_debug("clearing esb pages for girq 0x%lx\n", irq);
mutex_lock(&xive->mapping_lock);
if (xive->mapping)
unmap_mapping_range(xive->mapping,
irq * (2ull << PAGE_SHIFT),
2ull << PAGE_SHIFT, 1);
mutex_unlock(&xive->mapping_lock);
return 0;
}
void spu_unmap_mappings(struct spu_context *ctx)
{
mutex_lock(&ctx->mapping_lock);
if (ctx->local_store)
unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
if (ctx->mfc)
unmap_mapping_range(ctx->mfc, 0, SPUFS_MFC_MAP_SIZE, 1);
if (ctx->cntl)
unmap_mapping_range(ctx->cntl, 0, SPUFS_CNTL_MAP_SIZE, 1);
if (ctx->signal1)
unmap_mapping_range(ctx->signal1, 0, SPUFS_SIGNAL_MAP_SIZE, 1);
if (ctx->signal2)
unmap_mapping_range(ctx->signal2, 0, SPUFS_SIGNAL_MAP_SIZE, 1);
if (ctx->mss)
unmap_mapping_range(ctx->mss, 0, SPUFS_MSS_MAP_SIZE, 1);
if (ctx->psmap)
unmap_mapping_range(ctx->psmap, 0, SPUFS_PS_MAP_SIZE, 1);
mutex_unlock(&ctx->mapping_lock);
}
/**
* truncate_pagecache_range - unmap and remove pagecache that is hole-punched
* @inode: inode
* @lstart: offset of beginning of hole
* @lend: offset of last byte of hole
*
* This function should typically be called before the filesystem
* releases resources associated with the freed range (eg. deallocates
* blocks). This way, pagecache will always stay logically coherent
* with on-disk format, and the filesystem would not have to deal with
* situations such as writepage being called for a page that has already
* had its underlying blocks deallocated.
*/
void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
{
struct address_space *mapping = inode->i_mapping;
loff_t unmap_start = round_up(lstart, PAGE_SIZE);
loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
/*
* This rounding is currently just for example: unmap_mapping_range
* expands its hole outwards, whereas we want it to contract the hole
* inwards. However, existing callers of truncate_pagecache_range are
* doing their own page rounding first. Note that unmap_mapping_range
* allows holelen 0 for all, and we allow lend -1 for end of file.
*/
/*
* Unlike in truncate_pagecache, unmap_mapping_range is called only
* once (before truncating pagecache), and without "even_cows" flag:
* hole-punching should not remove private COWed pages from the hole.
*/
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
truncate_inode_pages_range(mapping, lstart, lend);
}
static int ocfs2_truncate_file(struct inode *inode,
struct buffer_head *di_bh,
u64 new_i_size)
{
int status = 0;
struct ocfs2_dinode *fe = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_truncate_context *tc = NULL;
mlog_entry("(inode = %llu, new_i_size = %llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)new_i_size);
unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(inode->i_mapping, new_i_size);
fe = (struct ocfs2_dinode *) di_bh->b_data;
if (!OCFS2_IS_VALID_DINODE(fe)) {
OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe);
status = -EIO;
goto bail;
}
mlog_bug_on_msg(le64_to_cpu(fe->i_size) != i_size_read(inode),
"Inode %llu, inode i_size = %lld != di "
"i_size = %llu, i_flags = 0x%x\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
i_size_read(inode),
(unsigned long long)le64_to_cpu(fe->i_size),
le32_to_cpu(fe->i_flags));
if (new_i_size > le64_to_cpu(fe->i_size)) {
mlog(0, "asked to truncate file with size (%llu) to size (%llu)!\n",
(unsigned long long)le64_to_cpu(fe->i_size),
(unsigned long long)new_i_size);
status = -EINVAL;
mlog_errno(status);
goto bail;
}
mlog(0, "inode %llu, i_size = %llu, new_i_size = %llu\n",
(unsigned long long)le64_to_cpu(fe->i_blkno),
(unsigned long long)le64_to_cpu(fe->i_size),
(unsigned long long)new_i_size);
/* lets handle the simple truncate cases before doing any more
* cluster locking. */
if (new_i_size == le64_to_cpu(fe->i_size))
goto bail;
/* This forces other nodes to sync and drop their pages. Do
* this even if we have a truncate without allocation change -
* ocfs2 cluster sizes can be much greater than page size, so
* we have to truncate them anyway. */
status = ocfs2_data_lock(inode, 1);
if (status < 0) {
mlog_errno(status);
goto bail;
}
/* alright, we're going to need to do a full blown alloc size
* change. Orphan the inode so that recovery can complete the
* truncate if necessary. This does the task of marking
* i_size. */
status = ocfs2_orphan_for_truncate(osb, inode, di_bh, new_i_size);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_data;
}
status = ocfs2_prepare_truncate(osb, inode, di_bh, &tc);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_data;
}
status = ocfs2_commit_truncate(osb, inode, di_bh, tc);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_data;
}
/* TODO: orphan dir cleanup here. */
bail_unlock_data:
ocfs2_data_unlock(inode, 1);
bail:
mlog_exit(status);
return status;
}
/**
* invalidate_inode_pages2_range - remove range of pages from an address_space
* @mapping: the address_space
* @start: the page offset 'from' which to invalidate
* @end: the page offset 'to' which to invalidate (inclusive)
*
* Any pages which are found to be mapped into pagetables are unmapped prior to
* invalidation.
*
* Returns -EBUSY if any pages could not be invalidated.
*/
int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
pgoff_t index;
int i;
int ret = 0;
int ret2 = 0;
int did_range_unmap = 0;
cleancache_invalidate_inode(mapping);
pagevec_init(&pvec, 0);
index = start;
while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
index = indices[i];
if (index > end)
break;
if (radix_tree_exceptional_entry(page)) {
clear_exceptional_entry(mapping, index, page);
continue;
}
lock_page(page);
WARN_ON(page->index != index);
if (page->mapping != mapping) {
unlock_page(page);
continue;
}
wait_on_page_writeback(page);
if (page_mapped(page)) {
if (!did_range_unmap) {
/*
* Zap the rest of the file in one hit.
*/
unmap_mapping_range(mapping,
(loff_t)index << PAGE_CACHE_SHIFT,
(loff_t)(1 + end - index)
<< PAGE_CACHE_SHIFT,
0);
did_range_unmap = 1;
} else {
/*
* Just zap this page
*/
unmap_mapping_range(mapping,
(loff_t)index << PAGE_CACHE_SHIFT,
PAGE_CACHE_SIZE, 0);
}
}
BUG_ON(page_mapped(page));
ret2 = do_launder_page(mapping, page);
if (ret2 == 0) {
if (!invalidate_complete_page2(mapping, page))
ret2 = -EBUSY;
}
if (ret2 < 0)
ret = ret2;
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
cond_resched();
index++;
}
cleancache_invalidate_inode(mapping);
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;
}
void spu_unmap_mappings(struct spu_context *ctx)
{
unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
}
