summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-11-24 18:44:01 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-11-24 18:44:01 -0800
commite2125dac22f2c9c66c412cd8e049a7305af59f73 (patch)
tree8584af248ee592622bd6e8a7f9cee0b041b784cc /fs
parente195ca6cb6f21633e56322d5aa11ed59cdb22fb2 (diff)
parentfffc9a260e38acec3187515738122a3ecb24ac90 (diff)
Merge tag 'xarray-4.20-rc4' of git://git.infradead.org/users/willy/linux-dax
Pull XArray updates from Matthew Wilcox: "We found some bugs in the DAX conversion to XArray (and one bug which predated the XArray conversion). There were a couple of bugs in some of the higher-level functions, which aren't actually being called in today's kernel, but surfaced as a result of converting existing radix tree & IDR users over to the XArray. Some of the other changes to how the higher-level APIs work were also motivated by converting various users; again, they're not in use in today's kernel, so changing them has a low probability of introducing a bug. Dan can still trigger a bug in the DAX code with hot-offline/online, and we're working on tracking that down" * tag 'xarray-4.20-rc4' of git://git.infradead.org/users/willy/linux-dax: XArray tests: Add missing locking dax: Avoid losing wakeup in dax_lock_mapping_entry dax: Fix huge page faults dax: Fix dax_unlock_mapping_entry for PMD pages dax: Reinstate RCU protection of inode dax: Make sure the unlocking entry isn't locked dax: Remove optimisation from dax_lock_mapping_entry XArray tests: Correct some 64-bit assumptions XArray: Correct xa_store_range XArray: Fix Documentation XArray: Handle NULL pointers differently for allocation XArray: Unify xa_store and __xa_store XArray: Add xa_store_bh() and xa_store_irq() XArray: Turn xa_erase into an exported function XArray: Unify xa_cmpxchg and __xa_cmpxchg XArray: Regularise xa_reserve nilfs2: Use xa_erase_irq XArray: Export __xa_foo to non-GPL modules XArray: Fix xa_for_each with a single element at 0
Diffstat (limited to 'fs')
-rw-r--r--fs/dax.c60
-rw-r--r--fs/nilfs2/btnode.c4
2 files changed, 36 insertions, 28 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 616e36ea6aaa..9bcce89ea18e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -98,12 +98,6 @@ static void *dax_make_entry(pfn_t pfn, unsigned long flags)
return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
}
-static void *dax_make_page_entry(struct page *page)
-{
- pfn_t pfn = page_to_pfn_t(page);
- return dax_make_entry(pfn, PageHead(page) ? DAX_PMD : 0);
-}
-
static bool dax_is_locked(void *entry)
{
return xa_to_value(entry) & DAX_LOCKED;
@@ -116,12 +110,12 @@ static unsigned int dax_entry_order(void *entry)
return 0;
}
-static int dax_is_pmd_entry(void *entry)
+static unsigned long dax_is_pmd_entry(void *entry)
{
return xa_to_value(entry) & DAX_PMD;
}
-static int dax_is_pte_entry(void *entry)
+static bool dax_is_pte_entry(void *entry)
{
return !(xa_to_value(entry) & DAX_PMD);
}
@@ -222,9 +216,8 @@ static void *get_unlocked_entry(struct xa_state *xas)
ewait.wait.func = wake_exceptional_entry_func;
for (;;) {
- entry = xas_load(xas);
- if (!entry || xa_is_internal(entry) ||
- WARN_ON_ONCE(!xa_is_value(entry)) ||
+ entry = xas_find_conflict(xas);
+ if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
!dax_is_locked(entry))
return entry;
@@ -255,6 +248,7 @@ 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);
@@ -352,16 +346,27 @@ static struct page *dax_busy_page(void *entry)
return NULL;
}
+/*
+ * dax_lock_mapping_entry - Lock the DAX entry corresponding to a page
+ * @page: The page whose entry we want to lock
+ *
+ * Context: Process context.
+ * Return: %true if the entry was locked or does not need to be locked.
+ */
bool dax_lock_mapping_entry(struct page *page)
{
XA_STATE(xas, NULL, 0);
void *entry;
+ bool locked;
+ /* Ensure page->mapping isn't freed while we look at it */
+ rcu_read_lock();
for (;;) {
struct address_space *mapping = READ_ONCE(page->mapping);
+ locked = false;
if (!dax_mapping(mapping))
- return false;
+ break;
/*
* In the device-dax case there's no need to lock, a
@@ -370,8 +375,9 @@ bool dax_lock_mapping_entry(struct page *page)
* otherwise we would not have a valid pfn_to_page()
* translation.
*/
+ locked = true;
if (S_ISCHR(mapping->host->i_mode))
- return true;
+ break;
xas.xa = &mapping->i_pages;
xas_lock_irq(&xas);
@@ -382,28 +388,35 @@ bool dax_lock_mapping_entry(struct page *page)
xas_set(&xas, page->index);
entry = xas_load(&xas);
if (dax_is_locked(entry)) {
+ rcu_read_unlock();
entry = get_unlocked_entry(&xas);
- /* Did the page move while we slept? */
- if (dax_to_pfn(entry) != page_to_pfn(page)) {
- xas_unlock_irq(&xas);
- continue;
- }
+ xas_unlock_irq(&xas);
+ put_unlocked_entry(&xas, entry);
+ rcu_read_lock();
+ continue;
}
dax_lock_entry(&xas, entry);
xas_unlock_irq(&xas);
- return true;
+ break;
}
+ rcu_read_unlock();
+ return locked;
}
void dax_unlock_mapping_entry(struct page *page)
{
struct address_space *mapping = page->mapping;
XA_STATE(xas, &mapping->i_pages, page->index);
+ void *entry;
if (S_ISCHR(mapping->host->i_mode))
return;
- dax_unlock_entry(&xas, dax_make_page_entry(page));
+ rcu_read_lock();
+ entry = xas_load(&xas);
+ rcu_read_unlock();
+ entry = dax_make_entry(page_to_pfn_t(page), dax_is_pmd_entry(entry));
+ dax_unlock_entry(&xas, entry);
}
/*
@@ -445,11 +458,9 @@ static void *grab_mapping_entry(struct xa_state *xas,
retry:
xas_lock_irq(xas);
entry = get_unlocked_entry(xas);
- if (xa_is_internal(entry))
- goto fallback;
if (entry) {
- if (WARN_ON_ONCE(!xa_is_value(entry))) {
+ if (!xa_is_value(entry)) {
xas_set_err(xas, EIO);
goto out_unlock;
}
@@ -1628,8 +1639,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
/* Did we race with someone splitting entry or so? */
if (!entry ||
(order == 0 && !dax_is_pte_entry(entry)) ||
- (order == PMD_ORDER && (xa_is_internal(entry) ||
- !dax_is_pmd_entry(entry)))) {
+ (order == PMD_ORDER && !dax_is_pmd_entry(entry))) {
put_unlocked_entry(&xas, entry);
xas_unlock_irq(&xas);
trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index de99db518571..f2129a5d9f23 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -266,9 +266,7 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
return;
if (nbh == NULL) { /* blocksize == pagesize */
- xa_lock_irq(&btnc->i_pages);
- __xa_erase(&btnc->i_pages, newkey);
- xa_unlock_irq(&btnc->i_pages);
+ xa_erase_irq(&btnc->i_pages, newkey);
unlock_page(ctxt->bh->b_page);
} else
brelse(nbh);