On Tue, 2015-11-10 at 14:26 +0100, Joerg Roedel wrote: > From: Joerg Roedel <[email protected]> > > Not doing so is a bug and might trigger a BUG_ON in > handle_mm_fault(). So add the proper permission checks > before calling into mm code. > > Signed-off-by: Joerg Roedel <[email protected]>
> +static bool access_error(struct vm_area_struct *vma, struct
> page_req_dsc *req)
> +{
> + return !((req->rd_req && (vma->vm_flags & VM_READ)) ||
> + (req->wr_req && (vma->vm_flags & VM_WRITE)) ||
> + (req->exe_req && (vma->vm_flags & VM_EXEC)));
> +}
> +
This is a TLB fill request from the device — can it not be asking for
*all* of read, write and exec privs? And you allow it to succeed if any
*one* of the permissions that it asks for is available?
Even if we don't see read+write in the same request, the VT-d spec does
seem quite clear that we *will* see read+exec (§7.5.1.1 p7-17 of v2.3:
• Execute Requested: If the PASID Present, Read Requested and Execute
Requested fields are all 1, the request-with-PASID that encountered
the recoverable fault that resulted in this page request, requires
execute access to the page.
Also, I'm afraid my Skylake box blew up the day I sent the pull request
to Linus so I'm unable to test until I've sorted out a replacement.
Jesse should be able to though...
--
David Woodhouse Open Source Technology Centre
[email protected] Intel Corporation
smime.p7s
Description: S/MIME cryptographic signature
