- Fix a hang condition that started triggering after the Xarray
conversion of fsdax in the v4.20 kernel. - Add a 'resource' (root-only physical base address) sysfs attribute to device-dax instances to correlate memory-blocks onlined via the kmem driver with a given device instance. -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJdMIETAAoJEB7SkWpmfYgCei0P/A6BpAftQF8bWOX8drjrBj6J WSrrhmfNPQ0+D+UejfrPUGVg7JysmFpSvfaRkp41nSpKaX6wr6M2uQrHNQl5hIYK gi5PStYMQay4lM78TrLsFFdDqYX5M6VZhpO3Xgd82bPT2GMXhwckua4ad4WYoN8Y 2ufNajZt/WxBL45VqL1FFqpPK+TKTbVihBR/3W36+NOSJnsj/IH5OlrHswsyq73v J1YkQY0IvhGR6nZdsNZZV9Faux4jsIVPFW/mh1k1QVLP1r70aJlxcCyka6lRVd4R ktYFOwtX/B39T72RPQB59Z4LOf/VC9pNaiK7hhWuGQ6XepMo5/0fkhYRslhQobll 7XOYUC01J0jreMu5pvWrZKfaoF9HQwZ1q0NrwNeagZeOgrpoNLqE8WAXUj+c5hsv x7nPY4XNmRdw2/kkyPotyuRiGkbOOxNEdK0Avhl0id78RFiv4iwMzGdTRT+E9TMb SLF0KPskqKFcyjECD/zwhR2vEbm54harVqMI4pJU0745bjx/ZEfq+AYZN1Epza3N O2XYV+uWHi6NXALm195ccGuj2uWtfLHan9OFKyhJgfDbDfIngkr7dgtgCEAKqK9q zQrLemqeN3Xw2bRldsbg/6mnwhxqyLdoXbJ9JwD1JO1xvsVdElS0/z8dh4KdLv/8 OQ2GIzgB1CyofYuyzpOI =UB+H -----END PGP SIGNATURE----- Merge tag 'dax-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull dax updates from Dan Williams: "The fruits of a bug hunt in the fsdax implementation with Willy and a small feature update for device-dax: - Fix a hang condition that started triggering after the Xarray conversion of fsdax in the v4.20 kernel. - Add a 'resource' (root-only physical base address) sysfs attribute to device-dax instances to correlate memory-blocks onlined via the kmem driver with a given device instance" * tag 'dax-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: dax: Fix missed wakeup with PMD faults device-dax: Add a 'resource' attribute
This commit is contained in:
commit
0fe49f70a0
|
@ -295,6 +295,22 @@ static ssize_t target_node_show(struct device *dev,
|
|||
}
|
||||
static DEVICE_ATTR_RO(target_node);
|
||||
|
||||
static unsigned long long dev_dax_resource(struct dev_dax *dev_dax)
|
||||
{
|
||||
struct dax_region *dax_region = dev_dax->region;
|
||||
|
||||
return dax_region->res.start;
|
||||
}
|
||||
|
||||
static ssize_t resource_show(struct device *dev,
|
||||
struct device_attribute *attr, char *buf)
|
||||
{
|
||||
struct dev_dax *dev_dax = to_dev_dax(dev);
|
||||
|
||||
return sprintf(buf, "%#llx\n", dev_dax_resource(dev_dax));
|
||||
}
|
||||
static DEVICE_ATTR_RO(resource);
|
||||
|
||||
static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
|
||||
char *buf)
|
||||
{
|
||||
|
@ -313,6 +329,8 @@ static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
|
|||
|
||||
if (a == &dev_attr_target_node.attr && dev_dax_target_node(dev_dax) < 0)
|
||||
return 0;
|
||||
if (a == &dev_attr_resource.attr)
|
||||
return 0400;
|
||||
return a->mode;
|
||||
}
|
||||
|
||||
|
@ -320,6 +338,7 @@ static struct attribute *dev_dax_attributes[] = {
|
|||
&dev_attr_modalias.attr,
|
||||
&dev_attr_size.attr,
|
||||
&dev_attr_target_node.attr,
|
||||
&dev_attr_resource.attr,
|
||||
NULL,
|
||||
};
|
||||
|
||||
|
|
53
fs/dax.c
53
fs/dax.c
|
@ -123,6 +123,15 @@ static int dax_is_empty_entry(void *entry)
|
|||
return xa_to_value(entry) & DAX_EMPTY;
|
||||
}
|
||||
|
||||
/*
|
||||
* true if the entry that was found is of a smaller order than the entry
|
||||
* we were looking for
|
||||
*/
|
||||
static bool dax_is_conflict(void *entry)
|
||||
{
|
||||
return entry == XA_RETRY_ENTRY;
|
||||
}
|
||||
|
||||
/*
|
||||
* DAX page cache entry locking
|
||||
*/
|
||||
|
@ -195,11 +204,13 @@ static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all)
|
|||
* Look up entry in page cache, wait for it to become unlocked if it
|
||||
* is a DAX entry and return it. The caller must subsequently call
|
||||
* put_unlocked_entry() if it did not lock the entry or dax_unlock_entry()
|
||||
* if it did.
|
||||
* if it did. The entry returned may have a larger order than @order.
|
||||
* If @order is larger than the order of the entry found in i_pages, this
|
||||
* function returns a dax_is_conflict entry.
|
||||
*
|
||||
* Must be called with the i_pages lock held.
|
||||
*/
|
||||
static void *get_unlocked_entry(struct xa_state *xas)
|
||||
static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
|
||||
{
|
||||
void *entry;
|
||||
struct wait_exceptional_entry_queue ewait;
|
||||
|
@ -210,6 +221,8 @@ static void *get_unlocked_entry(struct xa_state *xas)
|
|||
|
||||
for (;;) {
|
||||
entry = xas_find_conflict(xas);
|
||||
if (dax_entry_order(entry) < order)
|
||||
return XA_RETRY_ENTRY;
|
||||
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
|
||||
!dax_is_locked(entry))
|
||||
return entry;
|
||||
|
@ -254,7 +267,7 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry)
|
|||
static void put_unlocked_entry(struct xa_state *xas, void *entry)
|
||||
{
|
||||
/* If we were the only waiter woken, wake the next one */
|
||||
if (entry)
|
||||
if (entry && dax_is_conflict(entry))
|
||||
dax_wake_entry(xas, entry, false);
|
||||
}
|
||||
|
||||
|
@ -461,7 +474,7 @@ void dax_unlock_page(struct page *page, dax_entry_t cookie)
|
|||
* overlap with xarray value entries.
|
||||
*/
|
||||
static void *grab_mapping_entry(struct xa_state *xas,
|
||||
struct address_space *mapping, unsigned long size_flag)
|
||||
struct address_space *mapping, unsigned int order)
|
||||
{
|
||||
unsigned long index = xas->xa_index;
|
||||
bool pmd_downgrade = false; /* splitting PMD entry into PTE entries? */
|
||||
|
@ -469,20 +482,17 @@ static void *grab_mapping_entry(struct xa_state *xas,
|
|||
|
||||
retry:
|
||||
xas_lock_irq(xas);
|
||||
entry = get_unlocked_entry(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 (size_flag & DAX_PMD) {
|
||||
if (dax_is_pte_entry(entry)) {
|
||||
put_unlocked_entry(xas, entry);
|
||||
goto fallback;
|
||||
}
|
||||
} else { /* trying to grab a PTE entry */
|
||||
if (order == 0) {
|
||||
if (dax_is_pmd_entry(entry) &&
|
||||
(dax_is_zero_entry(entry) ||
|
||||
dax_is_empty_entry(entry))) {
|
||||
|
@ -523,7 +533,11 @@ retry:
|
|||
if (entry) {
|
||||
dax_lock_entry(xas, entry);
|
||||
} else {
|
||||
entry = dax_make_entry(pfn_to_pfn_t(0), size_flag | DAX_EMPTY);
|
||||
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;
|
||||
|
@ -594,7 +608,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
|
|||
if (WARN_ON_ONCE(!xa_is_value(entry)))
|
||||
continue;
|
||||
if (unlikely(dax_is_locked(entry)))
|
||||
entry = get_unlocked_entry(&xas);
|
||||
entry = get_unlocked_entry(&xas, 0);
|
||||
if (entry)
|
||||
page = dax_busy_page(entry);
|
||||
put_unlocked_entry(&xas, entry);
|
||||
|
@ -621,7 +635,7 @@ static int __dax_invalidate_entry(struct address_space *mapping,
|
|||
void *entry;
|
||||
|
||||
xas_lock_irq(&xas);
|
||||
entry = get_unlocked_entry(&xas);
|
||||
entry = get_unlocked_entry(&xas, 0);
|
||||
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
|
||||
goto out;
|
||||
if (!trunc &&
|
||||
|
@ -848,7 +862,7 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
|
|||
if (unlikely(dax_is_locked(entry))) {
|
||||
void *old_entry = entry;
|
||||
|
||||
entry = get_unlocked_entry(xas);
|
||||
entry = get_unlocked_entry(xas, 0);
|
||||
|
||||
/* Entry got punched out / reallocated? */
|
||||
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
|
||||
|
@ -1509,7 +1523,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
|
|||
* entry is already in the array, for instance), it will return
|
||||
* VM_FAULT_FALLBACK.
|
||||
*/
|
||||
entry = grab_mapping_entry(&xas, mapping, DAX_PMD);
|
||||
entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
|
||||
if (xa_is_internal(entry)) {
|
||||
result = xa_to_internal(entry);
|
||||
goto fallback;
|
||||
|
@ -1658,11 +1672,10 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
|
|||
vm_fault_t ret;
|
||||
|
||||
xas_lock_irq(&xas);
|
||||
entry = get_unlocked_entry(&xas);
|
||||
entry = get_unlocked_entry(&xas, order);
|
||||
/* Did we race with someone splitting entry or so? */
|
||||
if (!entry ||
|
||||
(order == 0 && !dax_is_pte_entry(entry)) ||
|
||||
(order == PMD_ORDER && !dax_is_pmd_entry(entry))) {
|
||||
if (!entry || dax_is_conflict(entry) ||
|
||||
(order == 0 && !dax_is_pte_entry(entry))) {
|
||||
put_unlocked_entry(&xas, entry);
|
||||
xas_unlock_irq(&xas);
|
||||
trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
|
||||
|
|
Loading…
Reference in New Issue