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 92f842eac7ee3 ("[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@xxxxxxxxxx
Fixes: 92f842eac7ee3 ("[S390] store indication fault optimization")
Cc: <stable@xxxxxxxxxxxxxxx>
Reported-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: Heiko Carstens <hca@xxxxxxxxxxxxx>
Signed-off-by: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
---
arch/s390/mm/fault.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 7b0bb475c166..9770381776a6 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -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;
if (user_mode(regs))
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;
down_read(&mm->mmap_sem);
--
2.34.1
