#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pagevec.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
#include <linux/rmap.h>
#include <asm/pgalloc.h>
#define CREATE_TRACE_POINTS
#include <trace/events/fs_dax.h>
#define DAX_WAIT_TABLE_BITS 12
#define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
#define PG_PMD_NR (PMD_SIZE >> PAGE_SHIFT)
static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
static int __init init_dax_wait_table(void)
{
int i;
for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
init_waitqueue_head(wait_table + i);
return 0;
}
fs_initcall(init_dax_wait_table);
#define DAX_SHIFT (4)
#define DAX_LOCKED (1UL << 0)
#define DAX_PMD (1UL << 1)
#define DAX_ZERO_PAGE (1UL << 2)
#define DAX_EMPTY (1UL << 3)
static unsigned long dax_to_pfn(void *entry)
{
return xa_to_value(entry) >> DAX_SHIFT;
}
static void *dax_make_entry(pfn_t pfn, unsigned long flags)
{
return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
}
static bool dax_is_locked(void *entry)
{
return xa_to_value(entry) & DAX_LOCKED;
}
static unsigned int dax_entry_order(void *entry)
{
if (xa_to_value(entry) & DAX_PMD)
return PMD_ORDER;
return 0;
}
static unsigned long dax_is_pmd_entry(void *entry)
{
return xa_to_value(entry) & DAX_PMD;
}
static bool dax_is_pte_entry(void *entry)
{
return !(xa_to_value(entry) & DAX_PMD);
}
static int dax_is_zero_entry(void *entry)
{
return xa_to_value(entry) & DAX_ZERO_PAGE;
}
static int dax_is_empty_entry(void *entry)
{
return xa_to_value(entry) & DAX_EMPTY;
}
static bool dax_is_conflict(void *entry)
{
return entry == XA_RETRY_ENTRY;
}
struct exceptional_entry_key {
struct xarray *xa;
pgoff_t entry_start;
};
struct wait_exceptional_entry_queue {
wait_queue_entry_t wait;
struct exceptional_entry_key key;
};
enum dax_wake_mode {
WAKE_ALL,
WAKE_NEXT,
};
static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas,
void *entry, struct exceptional_entry_key *key)
{
unsigned long hash;
unsigned long index = xas->xa_index;
if (dax_is_pmd_entry(entry))
index &= ~PG_PMD_COLOUR;
key->xa = xas->xa;
key->entry_start = index;
hash = hash_long((unsigned long)xas->xa ^ index, DAX_WAIT_TABLE_BITS);
return wait_table + hash;
}
static int wake_exceptional_entry_func(wait_queue_entry_t *wait,
unsigned int mode, int sync, void *keyp)
{
struct exceptional_entry_key *key = keyp;
struct wait_exceptional_entry_queue *ewait =
container_of(wait, struct wait_exceptional_entry_queue, wait);
if (key->xa != ewait->key.xa ||
key->entry_start != ewait->key.entry_start)
return 0;
return autoremove_wake_function(wait, mode, sync, NULL);
}
static void dax_wake_entry(struct xa_state *xas, void *entry,
enum dax_wake_mode mode)
{
struct exceptional_entry_key key;
wait_queue_head_t *wq;
wq = dax_entry_waitqueue(xas, entry, &key);
if (waitqueue_active(wq))
__wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key);
}
static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
{
void *entry;
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq;
init_wait(&ewait.wait);
ewait.wait.func = wake_exceptional_entry_func;
for (;;) {
entry = xas_find_conflict(xas);
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
return entry;
if (dax_entry_order(entry) < order)
return XA_RETRY_ENTRY;
if (!dax_is_locked(entry))
return entry;
wq = dax_entry_waitqueue(xas, entry, &ewait.key);
prepare_to_wait_exclusive(wq, &ewait.wait,
TASK_UNINTERRUPTIBLE);
xas_unlock_irq(xas);
xas_reset(xas);
schedule();
finish_wait(wq, &ewait.wait);
xas_lock_irq(xas);
}
}
static void wait_entry_unlocked(struct xa_state *xas, void *entry)
{
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq;
init_wait(&ewait.wait);
ewait.wait.func = wake_exceptional_entry_func;
wq = dax_entry_waitqueue(xas, entry, &ewait.key);
prepare_to_wait(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
xas_unlock_irq(xas);
schedule();
finish_wait(wq, &ewait.wait);
}
static void put_unlocked_entry(struct xa_state *xas, void *entry,
enum dax_wake_mode mode)
{
if (entry && !dax_is_conflict(entry))
dax_wake_entry(xas, entry, mode);
}
static void dax_unlock_entry(struct xa_state *xas, void *entry)
{
void *old;
BUG_ON(dax_is_locked(entry));
xas_reset(xas);
xas_lock_irq(xas);
old = xas_store(xas, entry);
xas_unlock_irq(xas);
BUG_ON(!dax_is_locked(old));
dax_wake_entry(xas, entry, WAKE_NEXT);
}
static void *dax_lock_entry(struct xa_state *xas, void *entry)
{
unsigned long v = xa_to_value(entry);
return xas_store(xas, xa_mk_value(v | DAX_LOCKED));
}
static unsigned long dax_entry_size(void *entry)
{
if (dax_is_zero_entry(entry))
return 0;
else if (dax_is_empty_entry(entry))
return 0;
else if (dax_is_pmd_entry(entry))
return PMD_SIZE;
else
return PAGE_SIZE;
}
static unsigned long dax_end_pfn(void *entry)
{
return dax_to_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
}
#define for_each_mapped_pfn(entry, pfn) \
for (pfn = dax_to_pfn(entry); \
pfn < dax_end_pfn(entry); pfn++)
static inline bool dax_page_is_shared(struct page *page)
{
return page->mapping == PAGE_MAPPING_DAX_SHARED;
}
static inline void dax_page_share_get(struct page *page)
{
if (page->mapping != PAGE_MAPPING_DAX_SHARED) {
if (page->mapping)
page->share = 1;
page->mapping = PAGE_MAPPING_DAX_SHARED;
}
page->share++;
}
static inline unsigned long dax_page_share_put(struct page *page)
{
return --page->share;
}
static void dax_associate_entry(void *entry, struct address_space *mapping,
struct vm_area_struct *vma, unsigned long address, bool shared)
{
unsigned long size = dax_entry_size(entry), pfn, index;
int i = 0;
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
return;
index = linear_page_index(vma, address & ~(size - 1));
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
if (shared) {
dax_page_share_get(page);
} else {
WARN_ON_ONCE(page->mapping);
page->mapping = mapping;
page->index = index + i++;
}
}
}
static void dax_disassociate_entry(void *entry, struct address_space *mapping,
bool trunc)
{
unsigned long pfn;
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
return;
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
if (dax_page_is_shared(page)) {
if (dax_page_share_put(page) > 0)
continue;
} else
WARN_ON_ONCE(page->mapping && page->mapping != mapping);
page->mapping = NULL;
page->index = 0;
}
}
static struct page *dax_busy_page(void *entry)
{
unsigned long pfn;
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
if (page_ref_count(page) > 1)
return page;
}
return NULL;
}
dax_entry_t dax_lock_page(struct page *page)
{
XA_STATE(xas, NULL, 0);
void *entry;
rcu_read_lock();
for (;;) {
struct address_space *mapping = READ_ONCE(page->mapping);
entry = NULL;
if (!mapping || !dax_mapping(mapping))
break;
entry = (void *)~0UL;
if (S_ISCHR(mapping->host->i_mode))
break;
xas.xa = &mapping->i_pages;
xas_lock_irq(&xas);
if (mapping != page->mapping) {
xas_unlock_irq(&xas);
continue;
}
xas_set(&xas, page->index);
entry = xas_load(&xas);
if (dax_is_locked(entry)) {
rcu_read_unlock();
wait_entry_unlocked(&xas, entry);
rcu_read_lock();
continue;
}
dax_lock_entry(&xas, entry);
xas_unlock_irq(&xas);
break;
}
rcu_read_unlock();
return (dax_entry_t)entry;
}
void dax_unlock_page(struct page *page, dax_entry_t cookie)
{
struct address_space *mapping = page->mapping;
XA_STATE(xas, &mapping->i_pages, page->index);
if (S_ISCHR(mapping->host->i_mode))
return;
dax_unlock_entry(&xas, (void *)cookie);
}
dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, pgoff_t index,
struct page **page)
{
XA_STATE(xas, NULL, 0);
void *entry;
rcu_read_lock();
for (;;) {
entry = NULL;
if (!dax_mapping(mapping))
break;
xas.xa = &mapping->i_pages;
xas_lock_irq(&xas);
xas_set(&xas, index);
entry = xas_load(&xas);
if (dax_is_locked(entry)) {
rcu_read_unlock();
wait_entry_unlocked(&xas, entry);
rcu_read_lock();
continue;
}
if (!entry ||
dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
entry = (void *)~0UL;
} else {
*page = pfn_to_page(dax_to_pfn(entry));
dax_lock_entry(&xas, entry);
}
xas_unlock_irq(&xas);
break;
}
rcu_read_unlock();
return (dax_entry_t)entry;
}
void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index,
dax_entry_t cookie)
{
XA_STATE(xas, &mapping->i_pages, index);
if (cookie == ~0UL)
return;
dax_unlock_entry(&xas, (void *)cookie);
}
static void *grab_mapping_entry(struct xa_state *xas,
struct address_space *mapping, unsigned int order)
{
unsigned long index = xas->xa_index;
bool pmd_downgrade;
void *entry;
retry:
pmd_downgrade = false;
xas_lock_irq(xas);
entry = get_unlocked_entry(xas, order);
if (entry) {
if (dax_is_conflict(entry))
goto fallback;
if (!xa_is_value(entry)) {
xas_set_err(xas, -EIO);
goto out_unlock;
}
if (order == 0) {
if (dax_is_pmd_entry(entry) &&
(dax_is_zero_entry(entry) ||
dax_is_empty_entry(entry))) {
pmd_downgrade = true;
}
}
}
if (pmd_downgrade) {
dax_lock_entry(xas, entry);
if (dax_is_zero_entry(entry)) {
xas_unlock_irq(xas);
unmap_mapping_pages(mapping,
xas->xa_index & ~PG_PMD_COLOUR,
PG_PMD_NR, false);
xas_reset(xas);
xas_lock_irq(xas);
}
dax_disassociate_entry(entry, mapping, false);
xas_store(xas, NULL);
dax_wake_entry(xas, entry, WAKE_ALL);
mapping->nrpages -= PG_PMD_NR;
entry = NULL;
xas_set(xas, index);
}
if (entry) {
dax_lock_entry(xas, entry);
} else {
unsigned long flags = DAX_EMPTY;
if (order > 0)
flags |= DAX_PMD;
entry = dax_make_entry(pfn_to_pfn_t(0), flags);
dax_lock_entry(xas, entry);
if (xas_error(xas))
goto out_unlock;
mapping->nrpages += 1UL << order;
}
out_unlock:
xas_unlock_irq(xas);
if (xas_nomem(xas, mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM))
goto retry;
if (xas->xa_node == XA_ERROR(-ENOMEM))
return xa_mk_internal(VM_FAULT_OOM);
if (xas_error(xas))
return xa_mk_internal(VM_FAULT_SIGBUS);
return entry;
fallback:
xas_unlock_irq(xas);
return xa_mk_internal(VM_FAULT_FALLBACK);
}
struct page *dax_layout_busy_page_range(struct address_space *mapping,
loff_t start, loff_t end)
{
void *entry;
unsigned int scanned = 0;
struct page *page = NULL;
pgoff_t start_idx = start >> PAGE_SHIFT;
pgoff_t end_idx;
XA_STATE(xas, &mapping->i_pages, start_idx);
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
return NULL;
if (!dax_mapping(mapping) || !mapping_mapped(mapping))
return NULL;
if (end == LLONG_MAX)
end_idx = ULONG_MAX;
else
end_idx = end >> PAGE_SHIFT;
unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);
xas_lock_irq(&xas);
xas_for_each(&xas, entry, end_idx) {
if (WARN_ON_ONCE(!xa_is_value(entry)))
continue;
if (unlikely(dax_is_locked(entry)))
entry = get_unlocked_entry(&xas, 0);
if (entry)
page = dax_busy_page(entry);
put_unlocked_entry(&xas, entry, WAKE_NEXT);
if (page)
break;
if (++scanned % XA_CHECK_SCHED)
continue;
xas_pause(&xas);
xas_unlock_irq(&xas);
cond_resched();
xas_lock_irq(&xas);
}
xas_unlock_irq(&xas);
return page;
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);
struct page *dax_layout_busy_page(struct address_space *mapping)
{
return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page);
static int __dax_invalidate_entry(struct address_space *mapping,
pgoff_t index, bool trunc)
{
XA_STATE(xas, &mapping->i_pages, index);
int ret = 0;
void *entry;
xas_lock_irq(&xas);
entry = get_unlocked_entry(&xas, 0);
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
goto out;
if (!trunc &&
(xas_get_mark(&xas, PAGECACHE_TAG_DIRTY) ||
xas_get_mark(&xas, PAGECACHE_TAG_TOWRITE)))
goto out;
dax_disassociate_entry(entry, mapping, trunc);
xas_store(&xas, NULL);
mapping->nrpages -= 1UL << dax_entry_order(entry);
ret = 1;
out:
put_unlocked_entry(&xas, entry, WAKE_ALL);
xas_unlock_irq(&xas);
return ret;
}
static int __dax_clear_dirty_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
XA_STATE(xas, &mapping->i_pages, start);
unsigned int scanned = 0;
void *entry;
xas_lock_irq(&xas);
xas_for_each(&xas, entry, end) {
entry = get_unlocked_entry(&xas, 0);
xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
put_unlocked_entry(&xas, entry, WAKE_NEXT);
if (++scanned % XA_CHECK_SCHED)
continue;
xas_pause(&xas);
xas_unlock_irq(&xas);
cond_resched();
xas_lock_irq(&xas);
}
xas_unlock_irq(&xas);
return 0;
}
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
int ret = __dax_invalidate_entry(mapping, index, true);
WARN_ON_ONCE(!ret);
return ret;
}
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index)
{
return __dax_invalidate_entry(mapping, index, false);
}
static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
{
return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
}
static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
{
pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos);
void *vto, *kaddr;
long rc;
int id;
id = dax_read_lock();
rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
&kaddr, NULL);
if (rc < 0) {
dax_read_unlock(id);
return rc;
}
vto = kmap_atomic(vmf->cow_page);
copy_user_page(vto, kaddr, vmf->address, vmf->cow_page);
kunmap_atomic(vto);
dax_read_unlock(id);
return 0;
}
static bool dax_fault_is_synchronous(const struct iomap_iter *iter,
struct vm_area_struct *vma)
{
return (iter->flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) &&
(iter->iomap.flags & IOMAP_F_DIRTY);
}
static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
const struct iomap_iter *iter, void *entry, pfn_t pfn,
unsigned long flags)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
void *new_entry = dax_make_entry(pfn, flags);
bool write = iter->flags & IOMAP_WRITE;
bool dirty = write && !dax_fault_is_synchronous(iter, vmf->vma);
bool shared = iter->iomap.flags & IOMAP_F_SHARED;
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
if (shared || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) {
unsigned long index = xas->xa_index;
if (dax_is_pmd_entry(entry))
unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
PG_PMD_NR, false);
else
unmap_mapping_pages(mapping, index, 1, false);
}
xas_reset(xas);
xas_lock_irq(xas);
if (shared || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
void *old;
dax_disassociate_entry(entry, mapping, false);
dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address,
shared);
old = dax_lock_entry(xas, new_entry);
WARN_ON_ONCE(old != xa_mk_value(xa_to_value(entry) |
DAX_LOCKED));
entry = new_entry;
} else {
xas_load(xas);
}
if (dirty)
xas_set_mark(xas, PAGECACHE_TAG_DIRTY);
if (write && shared)
xas_set_mark(xas, PAGECACHE_TAG_TOWRITE);
xas_unlock_irq(xas);
return entry;
}
static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
struct address_space *mapping, void *entry)
{
unsigned long pfn, index, count, end;
long ret = 0;
struct vm_area_struct *vma;
if (WARN_ON(!xa_is_value(entry)))
return -EIO;
if (unlikely(dax_is_locked(entry))) {
void *old_entry = entry;
entry = get_unlocked_entry(xas, 0);
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
goto put_unlocked;
if (dax_to_pfn(old_entry) != dax_to_pfn(entry))
goto put_unlocked;
if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
dax_is_zero_entry(entry))) {
ret = -EIO;
goto put_unlocked;
}
if (!xas_get_mark(xas, PAGECACHE_TAG_TOWRITE))
goto put_unlocked;
}
dax_lock_entry(xas, entry);
xas_clear_mark(xas, PAGECACHE_TAG_TOWRITE);
xas_unlock_irq(xas);
pfn = dax_to_pfn(entry);
count = 1UL << dax_entry_order(entry);
index = xas->xa_index & ~(count - 1);
end = index + count - 1;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, index, end) {
pfn_mkclean_range(pfn, count, index, vma);
cond_resched();
}
i_mmap_unlock_read(mapping);
dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
xas_reset(xas);
xas_lock_irq(xas);
xas_store(xas, entry);
xas_clear_mark(xas, PAGECACHE_TAG_DIRTY);
dax_wake_entry(xas, entry, WAKE_NEXT);
trace_dax_writeback_one(mapping->host, index, count);
return ret;
put_unlocked:
put_unlocked_entry(xas, entry, WAKE_NEXT);
return ret;
}
int dax_writeback_mapping_range(struct address_space *mapping,
struct dax_device *dax_dev, struct writeback_control *wbc)
{
XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT);
struct inode *inode = mapping->host;
pgoff_t end_index = wbc->range_end >> PAGE_SHIFT;
void *entry;
int ret = 0;
unsigned int scanned = 0;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
if (mapping_empty(mapping) || wbc->sync_mode != WB_SYNC_ALL)
return 0;
trace_dax_writeback_range(inode, xas.xa_index, end_index);
tag_pages_for_writeback(mapping, xas.xa_index, end_index);
xas_lock_irq(&xas);
xas_for_each_marked(&xas, entry, end_index, PAGECACHE_TAG_TOWRITE) {
ret = dax_writeback_one(&xas, dax_dev, mapping, entry);
if (ret < 0) {
mapping_set_error(mapping, ret);
break;
}
if (++scanned % XA_CHECK_SCHED)
continue;
xas_pause(&xas);
xas_unlock_irq(&xas);
cond_resched();
xas_lock_irq(&xas);
}
xas_unlock_irq(&xas);
trace_dax_writeback_range_done(inode, xas.xa_index, end_index);
return ret;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
size_t size, void **kaddr, pfn_t *pfnp)
{
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
int id, rc = 0;
long length;
id = dax_read_lock();
length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
DAX_ACCESS, kaddr, pfnp);
if (length < 0) {
rc = length;
goto out;
}
if (!pfnp)
goto out_check_addr;
rc = -EINVAL;
if (PFN_PHYS(length) < size)
goto out;
if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
goto out;
if (length > 1 && !pfn_t_devmap(*pfnp))
goto out;
rc = 0;
out_check_addr:
if (!kaddr)
goto out;
if (!*kaddr)
rc = -EFAULT;
out:
dax_read_unlock(id);
return rc;
}
static int dax_iomap_copy_around(loff_t pos, uint64_t length, size_t align_size,
const struct iomap *srcmap, void *daddr)
{
loff_t head_off = pos & (align_size - 1);
size_t size = ALIGN(head_off + length, align_size);
loff_t end = pos + length;
loff_t pg_end = round_up(end, align_size);
bool copy_all = head_off == 0 && end == pg_end;
bool zero_edge = srcmap->flags & IOMAP_F_SHARED ||
srcmap->type == IOMAP_UNWRITTEN;
void *saddr = 0;
int ret = 0;
if (!zero_edge) {
ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL);
if (ret)
return dax_mem2blk_err(ret);
}
if (copy_all) {
if (zero_edge)
memset(daddr, 0, size);
else
ret = copy_mc_to_kernel(daddr, saddr, length);
goto out;
}
if (head_off) {
if (zero_edge)
memset(daddr, 0, head_off);
else {
ret = copy_mc_to_kernel(daddr, saddr, head_off);
if (ret)
return -EIO;
}
}
if (end < pg_end) {
loff_t tail_off = head_off + length;
loff_t tail_len = pg_end - end;
if (zero_edge)
memset(daddr + tail_off, 0, tail_len);
else {
ret = copy_mc_to_kernel(daddr + tail_off,
saddr + tail_off, tail_len);
if (ret)
return -EIO;
}
}
out:
if (zero_edge)
dax_flush(srcmap->dax_dev, daddr, size);
return ret ? -EIO : 0;
}
static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf,
const struct iomap_iter *iter, void **entry)
{
struct inode *inode = iter->inode;
unsigned long vaddr = vmf->address;
pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
vm_fault_t ret;
*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE);
ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
trace_dax_load_hole(inode, vmf, ret);
return ret;
}
#ifdef CONFIG_FS_DAX_PMD
static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
const struct iomap_iter *iter, void **entry)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
unsigned long pmd_addr = vmf->address & PMD_MASK;
struct vm_area_struct *vma = vmf->vma;
struct inode *inode = mapping->host;
pgtable_t pgtable = NULL;
struct page *zero_page;
spinlock_t *ptl;
pmd_t pmd_entry;
pfn_t pfn;
zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
if (unlikely(!zero_page))
goto fallback;
pfn = page_to_pfn_t(zero_page);
*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn,
DAX_PMD | DAX_ZERO_PAGE);
if (arch_needs_pgtable_deposit()) {
pgtable = pte_alloc_one(vma->vm_mm);
if (!pgtable)
return VM_FAULT_OOM;
}
ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (!pmd_none(*(vmf->pmd))) {
spin_unlock(ptl);
goto fallback;
}
if (pgtable) {
pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
mm_inc_nr_ptes(vma->vm_mm);
}
pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
pmd_entry = pmd_mkhuge(pmd_entry);
set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
spin_unlock(ptl);
trace_dax_pmd_load_hole(inode, vmf, zero_page, *entry);
return VM_FAULT_NOPAGE;
fallback:
if (pgtable)
pte_free(vma->vm_mm, pgtable);
trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
return VM_FAULT_FALLBACK;
}
#else
static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
const struct iomap_iter *iter, void **entry)
{
return VM_FAULT_FALLBACK;
}
#endif /* CONFIG_FS_DAX_PMD */
static s64 dax_unshare_iter(struct iomap_iter *iter)
{
struct iomap *iomap = &iter->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
loff_t pos = iter->pos;
loff_t length = iomap_length(iter);
int id = 0;
s64 ret = 0;
void *daddr = NULL, *saddr = NULL;
if (!(iomap->flags & IOMAP_F_SHARED))
return length;
id = dax_read_lock();
ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL);
if (ret < 0)
goto out_unlock;
if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) {
memset(daddr, 0, length);
dax_flush(iomap->dax_dev, daddr, length);
ret = length;
goto out_unlock;
}
ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
if (ret < 0)
goto out_unlock;
if (copy_mc_to_kernel(daddr, saddr, length) == 0)
ret = length;
else
ret = -EIO;
out_unlock:
dax_read_unlock(id);
return dax_mem2blk_err(ret);
}
int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
const struct iomap_ops *ops)
{
struct iomap_iter iter = {
.inode = inode,
.pos = pos,
.len = len,
.flags = IOMAP_WRITE | IOMAP_UNSHARE | IOMAP_DAX,
};
int ret;
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.processed = dax_unshare_iter(&iter);
return ret;
}
EXPORT_SYMBOL_GPL(dax_file_unshare);
static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size)
{
const struct iomap *iomap = &iter->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
unsigned offset = offset_in_page(pos);
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
void *kaddr;
long ret;
ret = dax_direct_access(iomap->dax_dev, pgoff, 1, DAX_ACCESS, &kaddr,
NULL);
if (ret < 0)
return dax_mem2blk_err(ret);
memset(kaddr + offset, 0, size);
if (iomap->flags & IOMAP_F_SHARED)
ret = dax_iomap_copy_around(pos, size, PAGE_SIZE, srcmap,
kaddr);
else
dax_flush(iomap->dax_dev, kaddr + offset, size);
return ret;
}
static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
{
const struct iomap *iomap = &iter->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
loff_t pos = iter->pos;
u64 length = iomap_length(iter);
s64 written = 0;
if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
return length;
if (iomap->flags & IOMAP_F_SHARED)
invalidate_inode_pages2_range(iter->inode->i_mapping,
pos >> PAGE_SHIFT,
(pos + length - 1) >> PAGE_SHIFT);
do {
unsigned offset = offset_in_page(pos);
unsigned size = min_t(u64, PAGE_SIZE - offset, length);
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
long rc;
int id;
id = dax_read_lock();
if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
else
rc = dax_memzero(iter, pos, size);
dax_read_unlock(id);
if (rc < 0)
return rc;
pos += size;
length -= size;
written += size;
} while (length > 0);
if (did_zero)
*did_zero = true;
return written;
}
int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
const struct iomap_ops *ops)
{
struct iomap_iter iter = {
.inode = inode,
.pos = pos,
.len = len,
.flags = IOMAP_DAX | IOMAP_ZERO,
};
int ret;
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.processed = dax_zero_iter(&iter, did_zero);
return ret;
}
EXPORT_SYMBOL_GPL(dax_zero_range);
int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
const struct iomap_ops *ops)
{
unsigned int blocksize = i_blocksize(inode);
unsigned int off = pos & (blocksize - 1);
if (!off)
return 0;
return dax_zero_range(inode, pos, blocksize - off, did_zero, ops);
}
EXPORT_SYMBOL_GPL(dax_truncate_page);
static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
struct iov_iter *iter)
{
const struct iomap *iomap = &iomi->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iomi);
loff_t length = iomap_length(iomi);
loff_t pos = iomi->pos;
struct dax_device *dax_dev = iomap->dax_dev;
loff_t end = pos + length, done = 0;
bool write = iov_iter_rw(iter) == WRITE;
bool cow = write && iomap->flags & IOMAP_F_SHARED;
ssize_t ret = 0;
size_t xfer;
int id;
if (!write) {
end = min(end, i_size_read(iomi->inode));
if (pos >= end)
return 0;
if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
return iov_iter_zero(min(length, end - pos), iter);
}
if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED &&
!(iomap->flags & IOMAP_F_SHARED)))
return -EIO;
if (iomap->flags & IOMAP_F_NEW || cow) {
if (cow)
__dax_clear_dirty_range(iomi->inode->i_mapping,
pos >> PAGE_SHIFT,
(end - 1) >> PAGE_SHIFT);
invalidate_inode_pages2_range(iomi->inode->i_mapping,
pos >> PAGE_SHIFT,
(end - 1) >> PAGE_SHIFT);
}
id = dax_read_lock();
while (pos < end) {
unsigned offset = pos & (PAGE_SIZE - 1);
const size_t size = ALIGN(length + offset, PAGE_SIZE);
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
ssize_t map_len;
bool recovery = false;
void *kaddr;
if (fatal_signal_pending(current)) {
ret = -EINTR;
break;
}
map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
DAX_ACCESS, &kaddr, NULL);
if (map_len == -EHWPOISON && iov_iter_rw(iter) == WRITE) {
map_len = dax_direct_access(dax_dev, pgoff,
PHYS_PFN(size), DAX_RECOVERY_WRITE,
&kaddr, NULL);
if (map_len > 0)
recovery = true;
}
if (map_len < 0) {
ret = dax_mem2blk_err(map_len);
break;
}
if (cow) {
ret = dax_iomap_copy_around(pos, length, PAGE_SIZE,
srcmap, kaddr);
if (ret)
break;
}
map_len = PFN_PHYS(map_len);
kaddr += offset;
map_len -= offset;
if (map_len > end - pos)
map_len = end - pos;
if (recovery)
xfer = dax_recovery_write(dax_dev, pgoff, kaddr,
map_len, iter);
else if (write)
xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
map_len, iter);
else
xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
map_len, iter);
pos += xfer;
length -= xfer;
done += xfer;
if (xfer == 0)
ret = -EFAULT;
if (xfer < map_len)
break;
}
dax_read_unlock(id);
return done ? done : ret;
}
ssize_t
dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops)
{
struct iomap_iter iomi = {
.inode = iocb->ki_filp->f_mapping->host,
.pos = iocb->ki_pos,
.len = iov_iter_count(iter),
.flags = IOMAP_DAX,
};
loff_t done = 0;
int ret;
if (!iomi.len)
return 0;
if (iov_iter_rw(iter) == WRITE) {
lockdep_assert_held_write(&iomi.inode->i_rwsem);
iomi.flags |= IOMAP_WRITE;
} else {
lockdep_assert_held(&iomi.inode->i_rwsem);
}
if (iocb->ki_flags & IOCB_NOWAIT)
iomi.flags |= IOMAP_NOWAIT;
while ((ret = iomap_iter(&iomi, ops)) > 0)
iomi.processed = dax_iomap_iter(&iomi, iter);
done = iomi.pos - iocb->ki_pos;
iocb->ki_pos = iomi.pos;
return done ? done : ret;
}
EXPORT_SYMBOL_GPL(dax_iomap_rw);
static vm_fault_t dax_fault_return(int error)
{
if (error == 0)
return VM_FAULT_NOPAGE;
return vmf_error(error);
}
static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
{
if (WARN_ON_ONCE(!pfnp))
return VM_FAULT_SIGBUS;
*pfnp = pfn;
return VM_FAULT_NEEDDSYNC;
}
static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf,
const struct iomap_iter *iter)
{
vm_fault_t ret;
int error = 0;
switch (iter->iomap.type) {
case IOMAP_HOLE:
case IOMAP_UNWRITTEN:
clear_user_highpage(vmf->cow_page, vmf->address);
break;
case IOMAP_MAPPED:
error = copy_cow_page_dax(vmf, iter);
break;
default:
WARN_ON_ONCE(1);
error = -EIO;
break;
}
if (error)
return dax_fault_return(error);
__SetPageUptodate(vmf->cow_page);
ret = finish_fault(vmf);
if (!ret)
return VM_FAULT_DONE_COW;
return ret;
}
static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
const struct iomap_iter *iter, pfn_t *pfnp,
struct xa_state *xas, void **entry, bool pmd)
{
const struct iomap *iomap = &iter->iomap;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
size_t size = pmd ? PMD_SIZE : PAGE_SIZE;
loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT;
bool write = iter->flags & IOMAP_WRITE;
unsigned long entry_flags = pmd ? DAX_PMD : 0;
int err = 0;
pfn_t pfn;
void *kaddr;
if (!pmd && vmf->cow_page)
return dax_fault_cow_page(vmf, iter);
if (!write &&
(iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) {
if (!pmd)
return dax_load_hole(xas, vmf, iter, entry);
return dax_pmd_load_hole(xas, vmf, iter, entry);
}
if (iomap->type != IOMAP_MAPPED && !(iomap->flags & IOMAP_F_SHARED)) {
WARN_ON_ONCE(1);
return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS;
}
err = dax_iomap_direct_access(iomap, pos, size, &kaddr, &pfn);
if (err)
return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err);
*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags);
if (write && iomap->flags & IOMAP_F_SHARED) {
err = dax_iomap_copy_around(pos, size, size, srcmap, kaddr);
if (err)
return dax_fault_return(err);
}
if (dax_fault_is_synchronous(iter, vmf->vma))
return dax_fault_synchronous_pfnp(pfnp, pfn);
if (pmd)
return vmf_insert_pfn_pmd(vmf, pfn, write);
if (write)
return vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
return vmf_insert_mixed(vmf->vma, vmf->address, pfn);
}
static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
int *iomap_errp, const struct iomap_ops *ops)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
XA_STATE(xas, &mapping->i_pages, vmf->pgoff);
struct iomap_iter iter = {
.inode = mapping->host,
.pos = (loff_t)vmf->pgoff << PAGE_SHIFT,
.len = PAGE_SIZE,
.flags = IOMAP_DAX | IOMAP_FAULT,
};
vm_fault_t ret = 0;
void *entry;
int error;
trace_dax_pte_fault(iter.inode, vmf, ret);
if (iter.pos >= i_size_read(iter.inode)) {
ret = VM_FAULT_SIGBUS;
goto out;
}
if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
iter.flags |= IOMAP_WRITE;
entry = grab_mapping_entry(&xas, mapping, 0);
if (xa_is_internal(entry)) {
ret = xa_to_internal(entry);
goto out;
}
if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) {
ret = VM_FAULT_NOPAGE;
goto unlock_entry;
}
while ((error = iomap_iter(&iter, ops)) > 0) {
if (WARN_ON_ONCE(iomap_length(&iter) < PAGE_SIZE)) {
iter.processed = -EIO;
continue;
}
ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, false);
if (ret != VM_FAULT_SIGBUS &&
(iter.iomap.flags & IOMAP_F_NEW)) {
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
ret |= VM_FAULT_MAJOR;
}
if (!(ret & VM_FAULT_ERROR))
iter.processed = PAGE_SIZE;
}
if (iomap_errp)
*iomap_errp = error;
if (!ret && error)
ret = dax_fault_return(error);
unlock_entry:
dax_unlock_entry(&xas, entry);
out:
trace_dax_pte_fault_done(iter.inode, vmf, ret);
return ret;
}
#ifdef CONFIG_FS_DAX_PMD
static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
pgoff_t max_pgoff)
{
unsigned long pmd_addr = vmf->address & PMD_MASK;
bool write = vmf->flags & FAULT_FLAG_WRITE;
if ((vmf->pgoff & PG_PMD_COLOUR) !=
((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
return true;
if (write && !(vmf->vma->vm_flags & VM_SHARED))
return true;
if (pmd_addr < vmf->vma->vm_start)
return true;
if ((pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
return true;
if ((xas->xa_index | PG_PMD_COLOUR) >= max_pgoff)
return true;
return false;
}
static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
const struct iomap_ops *ops)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
struct iomap_iter iter = {
.inode = mapping->host,
.len = PMD_SIZE,
.flags = IOMAP_DAX | IOMAP_FAULT,
};
vm_fault_t ret = VM_FAULT_FALLBACK;
pgoff_t max_pgoff;
void *entry;
if (vmf->flags & FAULT_FLAG_WRITE)
iter.flags |= IOMAP_WRITE;
max_pgoff = DIV_ROUND_UP(i_size_read(iter.inode), PAGE_SIZE);
trace_dax_pmd_fault(iter.inode, vmf, max_pgoff, 0);
if (xas.xa_index >= max_pgoff) {
ret = VM_FAULT_SIGBUS;
goto out;
}
if (dax_fault_check_fallback(vmf, &xas, max_pgoff))
goto fallback;
entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
if (xa_is_internal(entry)) {
ret = xa_to_internal(entry);
goto fallback;
}
if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
!pmd_devmap(*vmf->pmd)) {
ret = 0;
goto unlock_entry;
}
iter.pos = (loff_t)xas.xa_index << PAGE_SHIFT;
while (iomap_iter(&iter, ops) > 0) {
if (iomap_length(&iter) < PMD_SIZE)
continue;
ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, true);
if (ret != VM_FAULT_FALLBACK)
iter.processed = PMD_SIZE;
}
unlock_entry:
dax_unlock_entry(&xas, entry);
fallback:
if (ret == VM_FAULT_FALLBACK) {
split_huge_pmd(vmf->vma, vmf->pmd, vmf->address);
count_vm_event(THP_FAULT_FALLBACK);
}
out:
trace_dax_pmd_fault_done(iter.inode, vmf, max_pgoff, ret);
return ret;
}
#else
static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
const struct iomap_ops *ops)
{
return VM_FAULT_FALLBACK;
}
#endif /* CONFIG_FS_DAX_PMD */
vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops)
{
if (order == 0)
return dax_iomap_pte_fault(vmf, pfnp, iomap_errp, ops);
else if (order == PMD_ORDER)
return dax_iomap_pmd_fault(vmf, pfnp, ops);
else
return VM_FAULT_FALLBACK;
}
EXPORT_SYMBOL_GPL(dax_iomap_fault);
static vm_fault_t
dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, order);
void *entry;
vm_fault_t ret;
xas_lock_irq(&xas);
entry = get_unlocked_entry(&xas, order);
if (!entry || dax_is_conflict(entry) ||
(order == 0 && !dax_is_pte_entry(entry))) {
put_unlocked_entry(&xas, entry, WAKE_NEXT);
xas_unlock_irq(&xas);
trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
VM_FAULT_NOPAGE);
return VM_FAULT_NOPAGE;
}
xas_set_mark(&xas, PAGECACHE_TAG_DIRTY);
dax_lock_entry(&xas, entry);
xas_unlock_irq(&xas);
if (order == 0)
ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
#ifdef CONFIG_FS_DAX_PMD
else if (order == PMD_ORDER)
ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
#endif
else
ret = VM_FAULT_FALLBACK;
dax_unlock_entry(&xas, entry);
trace_dax_insert_pfn_mkwrite(mapping->host, vmf, ret);
return ret;
}
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order,
pfn_t pfn)
{
int err;
loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
size_t len = PAGE_SIZE << order;
err = vfs_fsync_range(vmf->vma->vm_file, start, start + len - 1, 1);
if (err)
return VM_FAULT_SIGBUS;
return dax_insert_pfn_mkwrite(vmf, pfn, order);
}
EXPORT_SYMBOL_GPL(dax_finish_sync_fault);
static loff_t dax_range_compare_iter(struct iomap_iter *it_src,
struct iomap_iter *it_dest, u64 len, bool *same)
{
const struct iomap *smap = &it_src->iomap;
const struct iomap *dmap = &it_dest->iomap;
loff_t pos1 = it_src->pos, pos2 = it_dest->pos;
void *saddr, *daddr;
int id, ret;
len = min(len, min(smap->length, dmap->length));
if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) {
*same = true;
return len;
}
if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) {
*same = false;
return 0;
}
id = dax_read_lock();
ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE),
&saddr, NULL);
if (ret < 0)
goto out_unlock;
ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE),
&daddr, NULL);
if (ret < 0)
goto out_unlock;
*same = !memcmp(saddr, daddr, len);
if (!*same)
len = 0;
dax_read_unlock(id);
return len;
out_unlock:
dax_read_unlock(id);
return -EIO;
}
int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
struct inode *dst, loff_t dstoff, loff_t len, bool *same,
const struct iomap_ops *ops)
{
struct iomap_iter src_iter = {
.inode = src,
.pos = srcoff,
.len = len,
.flags = IOMAP_DAX,
};
struct iomap_iter dst_iter = {
.inode = dst,
.pos = dstoff,
.len = len,
.flags = IOMAP_DAX,
};
int ret, compared = 0;
while ((ret = iomap_iter(&src_iter, ops)) > 0 &&
(ret = iomap_iter(&dst_iter, ops)) > 0) {
compared = dax_range_compare_iter(&src_iter, &dst_iter,
min(src_iter.len, dst_iter.len), same);
if (compared < 0)
return ret;
src_iter.processed = dst_iter.processed = compared;
}
return ret;
}
int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags,
const struct iomap_ops *ops)
{
return __generic_remap_file_range_prep(file_in, pos_in, file_out,
pos_out, len, remap_flags, ops);
}
EXPORT_SYMBOL_GPL