fs/dax: Fix pmd vs pte conflict detection
Users reported a v5.3 performance regression and inability to establish huge page mappings. A revised version of the ndctl "dax.sh" huge page unit test identifies commit23c84eb783
"dax: Fix missed wakeup with PMD faults" as the source. Update get_unlocked_entry() to check for NULL entries before checking the entry order, otherwise NULL is misinterpreted as a present pte conflict. The 'order' check needs to happen before the locked check as an unlocked entry at the wrong order must fallback to lookup the correct order. Reported-by: Jeff Smits <jeff.smits@intel.com> Reported-by: Doug Nelson <doug.nelson@intel.com> Cc: <stable@vger.kernel.org> Fixes:23c84eb783
("dax: Fix missed wakeup with PMD faults") Reviewed-by: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Link: https://lore.kernel.org/r/157167532455.3945484.11971474077040503994.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
parent
4f5cafb5cb
commit
6370740e5f
5
fs/dax.c
5
fs/dax.c
|
@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
|
|||
|
||||
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 (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
|
||||
!dax_is_locked(entry))
|
||||
if (!dax_is_locked(entry))
|
||||
return entry;
|
||||
|
||||
wq = dax_entry_waitqueue(xas, entry, &ewait.key);
|
||||
|
|
Loading…
Reference in New Issue