From: Gerald Schaefer Date: Wed, 17 Aug 2022 13:26:03 +0000 (+0200) Subject: s390/mm: do not trigger write fault when vma does not allow VM_WRITE X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=88acf68aa1df73fab7a6c66d2679f4d76dc227fa;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git 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 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@redhat.com Fixes: 92f842eac7ee3 ("[S390] store indication fault optimization") Cc: Reported-by: David Hildenbrand Reviewed-by: Heiko Carstens Signed-off-by: Gerald Schaefer Signed-off-by: Vasily Gorbik Signed-off-by: Gerald Schaefer Signed-off-by: Greg Kroah-Hartman --- diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 40f1888bc4ab..8456e941d483 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,7 +433,9 @@ static inline int 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);