On Fri, May 03, 2019 at 01:47:16PM +0200, Michal Kubecek wrote:
On Tue, Apr 30, 2019 at 01:38:16PM +0200, Greg Kroah-Hartman wrote:
From: Jason Gunthorpe jgg@mellanox.com
commit 67f269b37f9b4d52c5e7f97acea26c0852e9b8a1 upstream.
When this code was consolidated the intention was that the VMA would become backed by anonymous zero pages after the zap_vma_pte - however this very subtly relied on setting the vm_ops = NULL and clearing the VM_SHARED bits to transform the VMA into an anonymous VMA. Since the vm_ops was removed this broke.
Now userspace gets a SIGBUS if it touches the vma after disassociation.
Instead of converting the VMA to anonymous provide a fault handler that puts a zero'd page into the VMA when user-space touches it after disassociation.
Cc: stable@vger.kernel.org Suggested-by: Andrea Arcangeli aarcange@redhat.com Fixes: 5f9794dc94f5 ("RDMA/ucontext: Add a core API for mmaping driver IO memory") Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
This commit breaks build on s390 and mips, please pick also commit 6a5c5d26c4c6 ("rdma: fix build errors on s390 and MIPS due to bad ZERO_PAGE use").
Oops, it's already there as 71/89, I managed to overlook it. Sorry for the noise.
Michal Kubecek