On Sat, Apr 29, 2017 at 7:18 AM, Ingo Molnar <[email protected]> wrote: > > * Dan Williams <[email protected]> wrote: > >> Kirill points out that the calls to {get,put}_dev_pagemap() can be >> removed from the mm fast path if we take a single get_dev_pagemap() >> reference to signify that the page is alive and use the final put of the >> page to drop that reference. >> >> This does require some care to make sure that any waits for the >> percpu_ref to drop to zero occur *after* devm_memremap_page_release(), >> since it now maintains its own elevated reference. >> >> Cc: Ingo Molnar <[email protected]> >> Cc: Jérôme Glisse <[email protected]> >> Cc: Andrew Morton <[email protected]> >> Reviewed-by: Logan Gunthorpe <[email protected]> >> Suggested-by: Kirill Shutemov <[email protected]> >> Tested-by: Kirill Shutemov <[email protected]> >> Signed-off-by: Dan Williams <[email protected]> > > This changelog is lacking an explanation about how this solves the crashes you > were seeing. >
Kirill? It wasn't clear to me why the conversion to generic get_user_pages_fast() caused the reference counts to be off.
