mm/gup: continue VM_FAULT_RETRY processing even for pre-faults
When get_user_pages*() is called with pages = NULL, the processing of VM_FAULT_RETRY terminates early without actually retrying to fault-in all the pages. If the pages in the requested range belong to a VMA that has userfaultfd registered, handle_userfault() returns VM_FAULT_RETRY *after* user space has populated the page, but for the gup pre-fault case there's no actual retry and the caller will get no pages although they are present. This issue was uncovered when running post-copy memory restore in CRIU afterd9c9ce34ed
("x86/fpu: Fault-in user stack if copy_fpstate_to_sigframe() fails"). After this change, the copying of FPU state to the sigframe switched from copy_to_user() variants which caused a real page fault to get_user_pages() with pages parameter set to NULL. In post-copy mode of CRIU, the destination memory is managed with userfaultfd and lack of the retry for pre-fault case in get_user_pages() causes a crash of the restored process. Making the pre-fault behavior of get_user_pages() the same as the "normal" one fixes the issue. Link: http://lkml.kernel.org/r/1557844195-18882-1-git-send-email-rppt@linux.ibm.com Fixes:d9c9ce34ed
("x86/fpu: Fault-in user stack if copy_fpstate_to_sigframe() fails") Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Tested-by: Andrei Vagin <avagin@gmail.com> [https://travis-ci.org/avagin/linux/builds/533184940] Tested-by: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Borislav Petkov <bp@suse.de> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
b9fba67b38
commit
df17277b2a
11
mm/gup.c
11
mm/gup.c
|
@ -1042,10 +1042,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
|
|||
BUG_ON(ret >= nr_pages);
|
||||
}
|
||||
|
||||
if (!pages)
|
||||
/* If it's a prefault don't insist harder */
|
||||
return ret;
|
||||
|
||||
if (ret > 0) {
|
||||
nr_pages -= ret;
|
||||
pages_done += ret;
|
||||
|
@ -1061,7 +1057,11 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
|
|||
pages_done = ret;
|
||||
break;
|
||||
}
|
||||
/* VM_FAULT_RETRY triggered, so seek to the faulting offset */
|
||||
/*
|
||||
* VM_FAULT_RETRY triggered, so seek to the faulting offset.
|
||||
* For the prefault case (!pages) we only update counts.
|
||||
*/
|
||||
if (likely(pages))
|
||||
pages += ret;
|
||||
start += ret << PAGE_SHIFT;
|
||||
|
||||
|
@ -1085,6 +1085,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
|
|||
pages_done++;
|
||||
if (!nr_pages)
|
||||
break;
|
||||
if (likely(pages))
|
||||
pages++;
|
||||
start += PAGE_SIZE;
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue