Re: [RFC 01/10] x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

2017-05-11 Thread Andy Lutomirski
On Thu, May 11, 2017 at 10:41 AM, Borislav Petkov wrote: >> +{ >> + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, 0); > > VM_NONE); > Fixed, although this won't have any effect. --Andy

Re: [RFC 01/10] x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

2017-05-11 Thread Andy Lutomirski
On Thu, May 11, 2017 at 10:41 AM, Borislav Petkov wrote: >> +{ >> + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, 0); > > VM_NONE); > Fixed, although this won't have any effect. --Andy

Re: [RFC 01/10] x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

2017-05-11 Thread Borislav Petkov
On Sun, May 07, 2017 at 05:38:30AM -0700, Andy Lutomirski wrote: > flush_tlb_page() was very similar to flush_tlb_mm_range() except that > it had a couple of issues: > > - It was missing an smp_mb() in the case where >current->active_mm != mm. (This is a longstanding bug reported by >

Re: [RFC 01/10] x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

2017-05-11 Thread Borislav Petkov
On Sun, May 07, 2017 at 05:38:30AM -0700, Andy Lutomirski wrote: > flush_tlb_page() was very similar to flush_tlb_mm_range() except that > it had a couple of issues: > > - It was missing an smp_mb() in the case where >current->active_mm != mm. (This is a longstanding bug reported by >

[RFC 01/10] x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

2017-05-07 Thread Andy Lutomirski
flush_tlb_page() was very similar to flush_tlb_mm_range() except that it had a couple of issues: - It was missing an smp_mb() in the case where current->active_mm != mm. (This is a longstanding bug reported by Nadav Amit.) - It was missing tracepoints and vm counter updates. The only

[RFC 01/10] x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

2017-05-07 Thread Andy Lutomirski
flush_tlb_page() was very similar to flush_tlb_mm_range() except that it had a couple of issues: - It was missing an smp_mb() in the case where current->active_mm != mm. (This is a longstanding bug reported by Nadav Amit.) - It was missing tracepoints and vm counter updates. The only