Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread Jerome Glisse
On Wed, Mar 21, 2018 at 05:11:10PM -0700, John Hubbard wrote: > On 03/21/2018 04:37 PM, Jerome Glisse wrote: > > On Wed, Mar 21, 2018 at 04:10:32PM -0700, John Hubbard wrote: > >> On 03/21/2018 03:46 PM, Jerome Glisse wrote: > >>> On Wed, Mar 21, 2018 at 03:16:04PM -0700, John Hubbard wrote: >

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread John Hubbard
On 03/21/2018 04:37 PM, Jerome Glisse wrote: > On Wed, Mar 21, 2018 at 04:10:32PM -0700, John Hubbard wrote: >> On 03/21/2018 03:46 PM, Jerome Glisse wrote: >>> On Wed, Mar 21, 2018 at 03:16:04PM -0700, John Hubbard wrote: On 03/21/2018 11:03 AM, Jerome Glisse wrote: > On Tue, Mar 20, 2018

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread Jerome Glisse
On Wed, Mar 21, 2018 at 04:10:32PM -0700, John Hubbard wrote: > On 03/21/2018 03:46 PM, Jerome Glisse wrote: > > On Wed, Mar 21, 2018 at 03:16:04PM -0700, John Hubbard wrote: > >> On 03/21/2018 11:03 AM, Jerome Glisse wrote: > >>> On Tue, Mar 20, 2018 at 09:14:34PM -0700, John Hubbard wrote: >

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread John Hubbard
On 03/21/2018 03:46 PM, Jerome Glisse wrote: > On Wed, Mar 21, 2018 at 03:16:04PM -0700, John Hubbard wrote: >> On 03/21/2018 11:03 AM, Jerome Glisse wrote: >>> On Tue, Mar 20, 2018 at 09:14:34PM -0700, John Hubbard wrote: On 03/19/2018 07:00 PM, jgli...@redhat.com wrote: > From: Ralph Cam

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread Jerome Glisse
On Wed, Mar 21, 2018 at 03:16:04PM -0700, John Hubbard wrote: > On 03/21/2018 11:03 AM, Jerome Glisse wrote: > > On Tue, Mar 20, 2018 at 09:14:34PM -0700, John Hubbard wrote: > >> On 03/19/2018 07:00 PM, jgli...@redhat.com wrote: > >>> From: Ralph Campbell > > > > >> Hi Jerome, > >> > >> This p

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread John Hubbard
On 03/21/2018 11:03 AM, Jerome Glisse wrote: > On Tue, Mar 20, 2018 at 09:14:34PM -0700, John Hubbard wrote: >> On 03/19/2018 07:00 PM, jgli...@redhat.com wrote: >>> From: Ralph Campbell >> Hi Jerome, >> >> This presents a deadlock problem (details below). As for solution ideas, >> Mark Hairgr

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-21 Thread Jerome Glisse
On Tue, Mar 20, 2018 at 09:14:34PM -0700, John Hubbard wrote: > On 03/19/2018 07:00 PM, jgli...@redhat.com wrote: > > From: Ralph Campbell > > > > The hmm_mirror_register() function registers a callback for when > > the CPU pagetable is modified. Normally, the device driver will > > call hmm_mirr

Re: [PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-20 Thread John Hubbard
On 03/19/2018 07:00 PM, jgli...@redhat.com wrote: > From: Ralph Campbell > > The hmm_mirror_register() function registers a callback for when > the CPU pagetable is modified. Normally, the device driver will > call hmm_mirror_unregister() when the process using the device is > finished. However,

[PATCH 03/15] mm/hmm: HMM should have a callback before MM is destroyed v2

2018-03-19 Thread jglisse
From: Ralph Campbell The hmm_mirror_register() function registers a callback for when the CPU pagetable is modified. Normally, the device driver will call hmm_mirror_unregister() when the process using the device is finished. However, if the process exits uncleanly, the struct_mm can be destroyed