Re: [RFC] slub memory quarantine

2015-03-03 Thread Christoph Lameter
On Tue, 3 Mar 2015, Andrey Ryabinin wrote: > On 03/03/2015 12:10 PM, Dmitry Vyukov wrote: > > Please hold on with this. > > Dmitry Chernenkov is working on a quarantine that works with both slub > > and slab, does not cause spurious OOMs and does not depend on > > slub-debug which has

Re: [RFC] slub memory quarantine

2015-03-03 Thread Andrey Ryabinin
On 03/03/2015 12:10 PM, Dmitry Vyukov wrote: > Please hold on with this. > Dmitry Chernenkov is working on a quarantine that works with both slub > and slab, does not cause spurious OOMs and does not depend on > slub-debug which has unacceptable performance (acquires global lock). I think that

Re: [RFC] slub memory quarantine

2015-03-03 Thread Dmitry Vyukov
Please hold on with this. Dmitry Chernenkov is working on a quarantine that works with both slub and slab, does not cause spurious OOMs and does not depend on slub-debug which has unacceptable performance (acquires global lock). Me or Dmitry C will send an email to kasan-...@googlegroups.com to

[RFC] slub memory quarantine

2015-03-03 Thread Andrey Ryabinin
Hi. One of the main problems in detecting use after free bugs is memory reuse. Freed could be quickly reallocated. Neither KASan nor slub poisoning could detect use after free after reallocation. Memory quarantine is aimed to solve this problem by delaying as much as possible actual freeing of

Re: [RFC] slub memory quarantine

2015-03-03 Thread Andrey Ryabinin
On 03/03/2015 12:10 PM, Dmitry Vyukov wrote: Please hold on with this. Dmitry Chernenkov is working on a quarantine that works with both slub and slab, does not cause spurious OOMs and does not depend on slub-debug which has unacceptable performance (acquires global lock). I think that it's a

Re: [RFC] slub memory quarantine

2015-03-03 Thread Christoph Lameter
On Tue, 3 Mar 2015, Andrey Ryabinin wrote: On 03/03/2015 12:10 PM, Dmitry Vyukov wrote: Please hold on with this. Dmitry Chernenkov is working on a quarantine that works with both slub and slab, does not cause spurious OOMs and does not depend on slub-debug which has unacceptable

[RFC] slub memory quarantine

2015-03-03 Thread Andrey Ryabinin
Hi. One of the main problems in detecting use after free bugs is memory reuse. Freed could be quickly reallocated. Neither KASan nor slub poisoning could detect use after free after reallocation. Memory quarantine is aimed to solve this problem by delaying as much as possible actual freeing of

Re: [RFC] slub memory quarantine

2015-03-03 Thread Dmitry Vyukov
Please hold on with this. Dmitry Chernenkov is working on a quarantine that works with both slub and slab, does not cause spurious OOMs and does not depend on slub-debug which has unacceptable performance (acquires global lock). Me or Dmitry C will send an email to kasan-...@googlegroups.com to