Re: [PATCH v2 10/26] userfaultfd: wp: add UFFDIO_COPY_MODE_WP

From: Mike Rapoport <rppt@linux.ibm.com>
To: Peter Xu <peterx@redhat.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	David Hildenbrand <david@redhat.com>,
	Hugh Dickins <hughd@google.com>, Maya Gokhale <gokhale2@llnl.gov>,
	Jerome Glisse <jglisse@redhat.com>,
	Pavel Emelyanov <xemul@virtuozzo.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Martin Cracauer <cracauer@cons.org>, Shaohua Li <shli@fb.com>,
	Marty McFadden <mcfadden8@llnl.gov>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Denis Plotnikov <dplotnikov@virtuozzo.com>,
	Mike Rapoport <rppt@linux.vnet.ibm.com>,
	Mel Gorman <mgorman@suse.de>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>
Subject: Re: [PATCH v2 10/26] userfaultfd: wp: add UFFDIO_COPY_MODE_WP
Date: Tue, 26 Feb 2019 10:28:50 +0200	[thread overview]
Message-ID: <20190226082850.GC11981@rapoport-lnx> (raw)
In-Reply-To: <20190226050942.GF13653@xz-x1>

On Tue, Feb 26, 2019 at 01:09:42PM +0800, Peter Xu wrote:
> On Mon, Feb 25, 2019 at 05:58:37PM +0200, Mike Rapoport wrote:
> > On Tue, Feb 12, 2019 at 10:56:16AM +0800, Peter Xu wrote:
> > > From: Andrea Arcangeli <aarcange@redhat.com>
> > > 
> > > This allows UFFDIO_COPY to map pages wrprotected.
> >                                        write protected please :)
> 
> Sure!
> 
> > > 
> > > Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
> > > Signed-off-by: Peter Xu <peterx@redhat.com>
> > 
> > Except for two additional nits below
> > 
> > Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
> > 
> > > ---
> > >  fs/userfaultfd.c                 |  5 +++--
> > >  include/linux/userfaultfd_k.h    |  2 +-
> > >  include/uapi/linux/userfaultfd.h | 11 +++++-----
> > >  mm/userfaultfd.c                 | 36 ++++++++++++++++++++++----------
> > >  4 files changed, 35 insertions(+), 19 deletions(-)
> > > 
> > > diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
> > > index b397bc3b954d..3092885c9d2c 100644
> > > --- a/fs/userfaultfd.c
> > > +++ b/fs/userfaultfd.c
> > > @@ -1683,11 +1683,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
> > >  	ret = -EINVAL;
> > >  	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
> > >  		goto out;
> > > -	if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
> > > +	if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
> > >  		goto out;
> > >  	if (mmget_not_zero(ctx->mm)) {
> > >  		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
> > > -				   uffdio_copy.len, &ctx->mmap_changing);
> > > +				   uffdio_copy.len, &ctx->mmap_changing,
> > > +				   uffdio_copy.mode);
> > >  		mmput(ctx->mm);
> > >  	} else {
> > >  		return -ESRCH;
> > > diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> > > index c6590c58ce28..765ce884cec0 100644
> > > --- a/include/linux/userfaultfd_k.h
> > > +++ b/include/linux/userfaultfd_k.h
> > > @@ -34,7 +34,7 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
> > > 
> > >  extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
> > >  			    unsigned long src_start, unsigned long len,
> > > -			    bool *mmap_changing);
> > > +			    bool *mmap_changing, __u64 mode);
> > >  extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
> > >  			      unsigned long dst_start,
> > >  			      unsigned long len,
> > > diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
> > > index 48f1a7c2f1f0..297cb044c03f 100644
> > > --- a/include/uapi/linux/userfaultfd.h
> > > +++ b/include/uapi/linux/userfaultfd.h
> > > @@ -203,13 +203,14 @@ struct uffdio_copy {
> > >  	__u64 dst;
> > >  	__u64 src;
> > >  	__u64 len;
> > > +#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
> > >  	/*
> > > -	 * There will be a wrprotection flag later that allows to map
> > > -	 * pages wrprotected on the fly. And such a flag will be
> > > -	 * available if the wrprotection ioctl are implemented for the
> > > -	 * range according to the uffdio_register.ioctls.
> > > +	 * UFFDIO_COPY_MODE_WP will map the page wrprotected on the
> > > +	 * fly. UFFDIO_COPY_MODE_WP is available only if the
> > > +	 * wrprotection ioctl are implemented for the range according
> > 
> >                              ^ is
> 
> Will fix.
> 
> > 
> > > +	 * to the uffdio_register.ioctls.
> > >  	 */
> > > -#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
> > > +#define UFFDIO_COPY_MODE_WP			((__u64)1<<1)
> > >  	__u64 mode;
> > > 
> > >  	/*
> > > diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> > > index d59b5a73dfb3..73a208c5c1e7 100644
> > > --- a/mm/userfaultfd.c
> > > +++ b/mm/userfaultfd.c
> > > @@ -25,7 +25,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
> > >  			    struct vm_area_struct *dst_vma,
> > >  			    unsigned long dst_addr,
> > >  			    unsigned long src_addr,
> > > -			    struct page **pagep)
> > > +			    struct page **pagep,
> > > +			    bool wp_copy)
> > >  {
> > >  	struct mem_cgroup *memcg;
> > >  	pte_t _dst_pte, *dst_pte;
> > > @@ -71,9 +72,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
> > >  	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
> > >  		goto out_release;
> > > 
> > > -	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
> > > -	if (dst_vma->vm_flags & VM_WRITE)
> > > -		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
> > > +	_dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot));
> > > +	if (dst_vma->vm_flags & VM_WRITE && !wp_copy)
> > > +		_dst_pte = pte_mkwrite(_dst_pte);
> > > 
> > >  	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
> > >  	if (dst_vma->vm_file) {
> > > @@ -399,7 +400,8 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
> > >  						unsigned long dst_addr,
> > >  						unsigned long src_addr,
> > >  						struct page **page,
> > > -						bool zeropage)
> > > +						bool zeropage,
> > > +						bool wp_copy)
> > >  {
> > >  	ssize_t err;
> > > 
> > > @@ -416,11 +418,13 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
> > >  	if (!(dst_vma->vm_flags & VM_SHARED)) {
> > >  		if (!zeropage)
> > >  			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
> > > -					       dst_addr, src_addr, page);
> > > +					       dst_addr, src_addr, page,
> > > +					       wp_copy);
> > >  		else
> > >  			err = mfill_zeropage_pte(dst_mm, dst_pmd,
> > >  						 dst_vma, dst_addr);
> > >  	} else {
> > > +		VM_WARN_ON(wp_copy); /* WP only available for anon */
> > >  		if (!zeropage)
> > >  			err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
> > >  						     dst_vma, dst_addr,
> > > @@ -438,7 +442,8 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> > >  					      unsigned long src_start,
> > >  					      unsigned long len,
> > >  					      bool zeropage,
> > > -					      bool *mmap_changing)
> > > +					      bool *mmap_changing,
> > > +					      __u64 mode)
> > >  {
> > >  	struct vm_area_struct *dst_vma;
> > >  	ssize_t err;
> > > @@ -446,6 +451,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> > >  	unsigned long src_addr, dst_addr;
> > >  	long copied;
> > >  	struct page *page;
> > > +	bool wp_copy;
> > > 
> > >  	/*>  	 * Sanitize the command parameters:
> > > @@ -502,6 +508,14 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> > >  	    dst_vma->vm_flags & VM_SHARED))
> > >  		goto out_unlock;
> > > 
> > > +	/*
> > > +	 * validate 'mode' now that we know the dst_vma: don't allow
> > > +	 * a wrprotect copy if the userfaultfd didn't register as WP.
> > > +	 */
> > > +	wp_copy = mode & UFFDIO_COPY_MODE_WP;
> > > +	if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP))
> > > +		goto out_unlock;
> 
> [1]
> 
> > > +
> > >  	/*
> > >  	 * If this is a HUGETLB vma, pass off to appropriate routine
> > >  	 */
> > 
> > I think for hugetlb we should return an error if wp_copy==true.
> > It might be worth adding wp_copy parameter to __mcopy_atomic_hugetlb() in
> > advance and return the error from there, in a hope it will also support
> > UFFD_WP some day :)
> 
> Now we should have failed even earlier if someone wants to register a
> hugetlbfs VMA with UFFD_WP because now vma_can_userfault() only allows
> anonymous memory for it:
> 
> static inline bool vma_can_userfault(struct vm_area_struct *vma,
> 				     unsigned long vm_flags)
> {
> 	/* FIXME: add WP support to hugetlbfs and shmem */
> 	return vma_is_anonymous(vma) ||
> 		((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
> 		 !(vm_flags & VM_UFFD_WP));
> }
> 
> And, as long as a VMA is not tagged with UFFD_WP, the page copy will
> fail with -EINVAL directly above at [1] when setting the wp_copy flag.
> So IMHO we should have already covered the case.
> 
> Considering these, I would think we could simply postpone the changes
> to __mcopy_atomic_hugetlb() until adding hugetlbfs support on uffd-wp.
> Mike, what do you think?

Ok, fair enough.

> Thanks!
> 
> -- 
> Peter Xu
> 

-- 
Sincerely yours,
Mike.