linux-kernel - Re: [PATCH 2/3] mm/page_ref: Ensure page_ref_unfreeze is ordered against prior accesses

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 8 Jun 2017 11:34:02 +0100
From:   Will Deacon <will.deacon@....com>
To:     Vlastimil Babka <vbabka@...e.cz>
Cc:     linux-mm@...ck.org, linux-kernel@...r.kernel.org,
        mark.rutland@....com, akpm@...ux-foundation.org,
        kirill.shutemov@...ux.intel.com, Punit.Agrawal@....com,
        mgorman@...e.de, steve.capper@....com
Subject: Re: [PATCH 2/3] mm/page_ref: Ensure page_ref_unfreeze is ordered
 against prior accesses

On Thu, Jun 08, 2017 at 11:38:21AM +0200, Vlastimil Babka wrote:
> On 06/06/2017 07:58 PM, Will Deacon wrote:
> > page_ref_freeze and page_ref_unfreeze are designed to be used as a pair,
> > wrapping a critical section where struct pages can be modified without
> > having to worry about consistency for a concurrent fast-GUP.
> > 
> > Whilst page_ref_freeze has full barrier semantics due to its use of
> > atomic_cmpxchg, page_ref_unfreeze is implemented using atomic_set, which
> > doesn't provide any barrier semantics and allows the operation to be
> > reordered with respect to page modifications in the critical section.
> > 
> > This patch ensures that page_ref_unfreeze is ordered after any critical
> > section updates, by invoking smp_mb__before_atomic() prior to the
> > atomic_set.
> > 
> > Cc: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
> > Acked-by: Steve Capper <steve.capper@....com>
> > Signed-off-by: Will Deacon <will.deacon@....com>
> 
> Undecided if it's really needed. This is IMHO not the classical case
> from Documentation/core-api/atomic_ops.rst where we have to make
> modifications visible before we let others see them? Here the one who is
> freezing is doing it so others can't get their page pin and interfere
> with the freezer's work. But maybe there are some (documented or not)
> consistency guarantees to expect once you obtain the pin, that can be
> violated, or they might be added later, so it would be safer to add the
> barrier?

The problem comes if the unfreeze is reordered so that it happens before the
freezer has performed its work. For example, in
migrate_huge_page_move_mapping:


	if (!page_ref_freeze(page, expected_count)) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	newpage->index = page->index;
	newpage->mapping = page->mapping;

	get_page(newpage);

	radix_tree_replace_slot(&mapping->page_tree, pslot, newpage);

	page_ref_unfreeze(page, expected_count - 1);


then there's nothing stopping the CPU (and potentially the compiler) from
reordering the unfreeze call so that it effectively becomes:


	if (!page_ref_freeze(page, expected_count)) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	page_ref_unfreeze(page, expected_count - 1);

	newpage->index = page->index;
	newpage->mapping = page->mapping;

	get_page(newpage);

	radix_tree_replace_slot(&mapping->page_tree, pslot, newpage);


which then means that the freezer's work is carried out without the page
being frozen.

Will