page cache: use xa_lock
Remove the address_space ->tree_lock and use the xa_lock newly added to
the radix_tree_root. Rename the address_space ->page_tree to ->i_pages,
since we don't really care that it's a tree.
[willy@infradead.org: fix nds32, fs/dax.c]
Link: http://lkml.kernel.org/r/20180406145415.GB20605@bombadil.infradead.orgLink: http://lkml.kernel.org/r/20180313132639.17387-9-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/dax.c b/fs/dax.c
index a77394f..aaec72de 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -158,11 +158,9 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mo
}
/*
- * We do not necessarily hold the mapping->tree_lock when we call this
- * function so it is possible that 'entry' is no longer a valid item in the
- * radix tree. This is okay because all we really need to do is to find the
- * correct waitqueue where tasks might be waiting for that old 'entry' and
- * wake them.
+ * @entry may no longer be the entry at the index in the mapping.
+ * The important information it's conveying is whether the entry at
+ * this index used to be a PMD entry.
*/
static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
pgoff_t index, void *entry, bool wake_all)
@@ -174,7 +172,7 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
/*
* Checking for locked entry and prepare_to_wait_exclusive() happens
- * under mapping->tree_lock, ditto for entry handling in our callers.
+ * under the i_pages lock, ditto for entry handling in our callers.
* So at this point all tasks that could have seen our entry locked
* must be in the waitqueue and the following check will see them.
*/
@@ -183,41 +181,39 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
}
/*
- * Check whether the given slot is locked. The function must be called with
- * mapping->tree_lock held
+ * Check whether the given slot is locked. Must be called with the i_pages
+ * lock held.
*/
static inline int slot_locked(struct address_space *mapping, void **slot)
{
unsigned long entry = (unsigned long)
- radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
return entry & RADIX_DAX_ENTRY_LOCK;
}
/*
- * Mark the given slot is locked. The function must be called with
- * mapping->tree_lock held
+ * Mark the given slot as locked. Must be called with the i_pages lock held.
*/
static inline void *lock_slot(struct address_space *mapping, void **slot)
{
unsigned long entry = (unsigned long)
- radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
entry |= RADIX_DAX_ENTRY_LOCK;
- radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
+ radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
return (void *)entry;
}
/*
- * Mark the given slot is unlocked. The function must be called with
- * mapping->tree_lock held
+ * Mark the given slot as unlocked. Must be called with the i_pages lock held.
*/
static inline void *unlock_slot(struct address_space *mapping, void **slot)
{
unsigned long entry = (unsigned long)
- radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
- radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
+ radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
return (void *)entry;
}
@@ -228,7 +224,7 @@ static inline void *unlock_slot(struct address_space *mapping, void **slot)
* put_locked_mapping_entry() when he locked the entry and now wants to
* unlock it.
*
- * The function must be called with mapping->tree_lock held.
+ * Must be called with the i_pages lock held.
*/
static void *get_unlocked_mapping_entry(struct address_space *mapping,
pgoff_t index, void ***slotp)
@@ -241,7 +237,7 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
ewait.wait.func = wake_exceptional_entry_func;
for (;;) {
- entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
+ entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
&slot);
if (!entry ||
WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
@@ -254,10 +250,10 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
prepare_to_wait_exclusive(wq, &ewait.wait,
TASK_UNINTERRUPTIBLE);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
schedule();
finish_wait(wq, &ewait.wait);
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(&mapping->i_pages);
}
}
@@ -266,15 +262,15 @@ static void dax_unlock_mapping_entry(struct address_space *mapping,
{
void *entry, **slot;
- spin_lock_irq(&mapping->tree_lock);
- entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
+ xa_lock_irq(&mapping->i_pages);
+ entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
!slot_locked(mapping, slot))) {
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
return;
}
unlock_slot(mapping, slot);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}
@@ -388,7 +384,7 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
void *entry, **slot;
restart:
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(&mapping->i_pages);
entry = get_unlocked_mapping_entry(mapping, index, &slot);
if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
@@ -420,12 +416,12 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
if (pmd_downgrade) {
/*
* Make sure 'entry' remains valid while we drop
- * mapping->tree_lock.
+ * the i_pages lock.
*/
entry = lock_slot(mapping, slot);
}
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
/*
* Besides huge zero pages the only other thing that gets
* downgraded are empty entries which don't need to be
@@ -442,27 +438,27 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
put_locked_mapping_entry(mapping, index);
return ERR_PTR(err);
}
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(&mapping->i_pages);
if (!entry) {
/*
- * We needed to drop the page_tree lock while calling
+ * We needed to drop the i_pages lock while calling
* radix_tree_preload() and we didn't have an entry to
* lock. See if another thread inserted an entry at
* our index during this time.
*/
- entry = __radix_tree_lookup(&mapping->page_tree, index,
+ entry = __radix_tree_lookup(&mapping->i_pages, index,
NULL, &slot);
if (entry) {
radix_tree_preload_end();
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
goto restart;
}
}
if (pmd_downgrade) {
dax_disassociate_entry(entry, mapping, false);
- radix_tree_delete(&mapping->page_tree, index);
+ radix_tree_delete(&mapping->i_pages, index);
mapping->nrexceptional--;
dax_wake_mapping_entry_waiter(mapping, index, entry,
true);
@@ -470,11 +466,11 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
- err = __radix_tree_insert(&mapping->page_tree, index,
+ err = __radix_tree_insert(&mapping->i_pages, index,
dax_radix_order(entry), entry);
radix_tree_preload_end();
if (err) {
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
/*
* Our insertion of a DAX entry failed, most likely
* because we were inserting a PMD entry and it
@@ -487,12 +483,12 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
}
/* Good, we have inserted empty locked entry into the tree. */
mapping->nrexceptional++;
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
return entry;
}
entry = lock_slot(mapping, slot);
out_unlock:
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
return entry;
}
@@ -501,23 +497,23 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
{
int ret = 0;
void *entry;
- struct radix_tree_root *page_tree = &mapping->page_tree;
+ struct radix_tree_root *pages = &mapping->i_pages;
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(pages);
entry = get_unlocked_mapping_entry(mapping, index, NULL);
if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
goto out;
if (!trunc &&
- (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
- radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+ (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
+ radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE)))
goto out;
dax_disassociate_entry(entry, mapping, trunc);
- radix_tree_delete(page_tree, index);
+ radix_tree_delete(pages, index);
mapping->nrexceptional--;
ret = 1;
out:
put_unlocked_mapping_entry(mapping, index, entry);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(pages);
return ret;
}
/*
@@ -587,7 +583,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
void *entry, pfn_t pfn_t,
unsigned long flags, bool dirty)
{
- struct radix_tree_root *page_tree = &mapping->page_tree;
+ struct radix_tree_root *pages = &mapping->i_pages;
unsigned long pfn = pfn_t_to_pfn(pfn_t);
pgoff_t index = vmf->pgoff;
void *new_entry;
@@ -604,7 +600,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
unmap_mapping_pages(mapping, vmf->pgoff, 1, false);
}
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(pages);
new_entry = dax_radix_locked_entry(pfn, flags);
if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
dax_disassociate_entry(entry, mapping, false);
@@ -624,17 +620,17 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
void **slot;
void *ret;
- ret = __radix_tree_lookup(page_tree, index, &node, &slot);
+ ret = __radix_tree_lookup(pages, index, &node, &slot);
WARN_ON_ONCE(ret != entry);
- __radix_tree_replace(page_tree, node, slot,
+ __radix_tree_replace(pages, node, slot,
new_entry, NULL);
entry = new_entry;
}
if (dirty)
- radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
+ radix_tree_tag_set(pages, index, PAGECACHE_TAG_DIRTY);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(pages);
return entry;
}
@@ -723,7 +719,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
static int dax_writeback_one(struct dax_device *dax_dev,
struct address_space *mapping, pgoff_t index, void *entry)
{
- struct radix_tree_root *page_tree = &mapping->page_tree;
+ struct radix_tree_root *pages = &mapping->i_pages;
void *entry2, **slot;
unsigned long pfn;
long ret = 0;
@@ -736,7 +732,7 @@ static int dax_writeback_one(struct dax_device *dax_dev,
if (WARN_ON(!radix_tree_exceptional_entry(entry)))
return -EIO;
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(pages);
entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
/* Entry got punched out / reallocated? */
if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
@@ -755,7 +751,7 @@ static int dax_writeback_one(struct dax_device *dax_dev,
}
/* Another fsync thread may have already written back this entry */
- if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+ if (!radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE))
goto put_unlocked;
/* Lock the entry to serialize with page faults */
entry = lock_slot(mapping, slot);
@@ -763,11 +759,11 @@ static int dax_writeback_one(struct dax_device *dax_dev,
* We can clear the tag now but we have to be careful so that concurrent
* dax_writeback_one() calls for the same index cannot finish before we
* actually flush the caches. This is achieved as the calls will look
- * at the entry only under tree_lock and once they do that they will
- * see the entry locked and wait for it to unlock.
+ * at the entry only under the i_pages lock and once they do that
+ * they will see the entry locked and wait for it to unlock.
*/
- radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
- spin_unlock_irq(&mapping->tree_lock);
+ radix_tree_tag_clear(pages, index, PAGECACHE_TAG_TOWRITE);
+ xa_unlock_irq(pages);
/*
* Even if dax_writeback_mapping_range() was given a wbc->range_start
@@ -787,16 +783,16 @@ static int dax_writeback_one(struct dax_device *dax_dev,
* the pfn mappings are writeprotected and fault waits for mapping
* entry lock.
*/
- spin_lock_irq(&mapping->tree_lock);
- radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_lock_irq(pages);
+ radix_tree_tag_clear(pages, index, PAGECACHE_TAG_DIRTY);
+ xa_unlock_irq(pages);
trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
put_locked_mapping_entry(mapping, index);
return ret;
put_unlocked:
put_unlocked_mapping_entry(mapping, index, entry2);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(pages);
return ret;
}
@@ -1566,21 +1562,21 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf,
pgoff_t index = vmf->pgoff;
int vmf_ret, error;
- spin_lock_irq(&mapping->tree_lock);
+ xa_lock_irq(&mapping->i_pages);
entry = get_unlocked_mapping_entry(mapping, index, &slot);
/* Did we race with someone splitting entry or so? */
if (!entry ||
(pe_size == PE_SIZE_PTE && !dax_is_pte_entry(entry)) ||
(pe_size == PE_SIZE_PMD && !dax_is_pmd_entry(entry))) {
put_unlocked_mapping_entry(mapping, index, entry);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
VM_FAULT_NOPAGE);
return VM_FAULT_NOPAGE;
}
- radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
+ radix_tree_tag_set(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY);
entry = lock_slot(mapping, slot);
- spin_unlock_irq(&mapping->tree_lock);
+ xa_unlock_irq(&mapping->i_pages);
switch (pe_size) {
case PE_SIZE_PTE:
error = vm_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);