s390/mm: do not trigger write fault when vma does not allow VM_WRITE

commit 41ac42f137080bc230b5882e3c88c392ab7f2d32 upstream.

For non-protection pXd_none() page faults in do_dat_exception(), we
call do_exception() with access == (VM_READ | VM_WRITE | VM_EXEC).
In do_exception(), vma->vm_flags is checked against that before
calling handle_mm_fault().

Since commit 92f842eac7 ("[S390] store indication fault optimization"),
we call handle_mm_fault() with FAULT_FLAG_WRITE, when recognizing that
it was a write access. However, the vma flags check is still only
checking against (VM_READ | VM_WRITE | VM_EXEC), and therefore also
calling handle_mm_fault() with FAULT_FLAG_WRITE in cases where the vma
does not allow VM_WRITE.

Fix this by changing access check in do_exception() to VM_WRITE only,
when recognizing write access.

Link: https://lkml.kernel.org/r/20220811103435.188481-3-david@redhat.com
Fixes: 92f842eac7 ("[S390] store indication fault optimization")
Cc: <stable@vger.kernel.org>
Reported-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Gerald Schaefer 2022-08-17 15:26:03 +02:00 committed by Greg Kroah-Hartman
parent c9c5501e81
commit 09602177d8

View File

@ -432,7 +432,9 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (user_mode(regs)) if (user_mode(regs))
flags |= FAULT_FLAG_USER; flags |= FAULT_FLAG_USER;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) if ((trans_exc_code & store_indication) == 0x400)
access = VM_WRITE;
if (access == VM_WRITE)
flags |= FAULT_FLAG_WRITE; flags |= FAULT_FLAG_WRITE;
down_read(&mm->mmap_sem); down_read(&mm->mmap_sem);