From: Balbir Singh <bsingharora@gmail.com> To: "Jérôme Glisse" <jglisse@redhat.com>, akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: John Hubbard <jhubbard@nvidia.com>, Dan Williams <dan.j.williams@intel.com>, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>, David Nellans <dnellans@nvidia.com>, Evgeny Baskakov <ebaskakov@nvidia.com>, Mark Hairgrove <mhairgrove@nvidia.com>, Sherry Cheung <SCheung@nvidia.com>, Subhash Gutti <sgutti@nvidia.com> Subject: Re: [HMM 14/16] mm/hmm/devmem: device memory hotplug using ZONE_DEVICE Date: Fri, 07 Apr 2017 11:37:34 +1000 [thread overview] Message-ID: <1491529054.12351.16.camel@gmail.com> (raw) In-Reply-To: <20170405204026.3940-15-jglisse@redhat.com> On Wed, 2017-04-05 at 16:40 -0400, Jérôme Glisse wrote: > This introduce a simple struct and associated helpers for device driver > to use when hotpluging un-addressable device memory as ZONE_DEVICE. It > will find a unuse physical address range and trigger memory hotplug for > it which allocates and initialize struct page for the device memory. > > Signed-off-by: Jérôme Glisse <jglisse@redhat.com> > Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> > Signed-off-by: John Hubbard <jhubbard@nvidia.com> > Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> > Signed-off-by: Sherry Cheung <SCheung@nvidia.com> > Signed-off-by: Subhash Gutti <sgutti@nvidia.com> > --- > include/linux/hmm.h | 114 +++++++++++++++ > mm/Kconfig | 9 ++ > mm/hmm.c | 398 ++++++++++++++++++++++++++++++++++++++++++++++++++++ > 3 files changed, 521 insertions(+) > > +/* > + * To add (hotplug) device memory, HMM assumes that there is no real resource > + * that reserves a range in the physical address space (this is intended to be > + * use by unaddressable device memory). It will reserve a physical range big > + * enough and allocate struct page for it. I've found that the implementation of this is quite non-portable, in that starting from iomem_resource.end+1-size (which is effectively -size) on my platform (powerpc) does not give expected results. It could be that additional changes are needed to arch_add_memory() to support this use case. > + > + size = ALIGN(size, SECTION_SIZE); > + addr = (iomem_resource.end + 1ULL) - size; Why don't we allocate_resource() with the right constraints and get a new unused region? Thanks, Balbir
WARNING: multiple messages have this Message-ID (diff)
From: Balbir Singh <bsingharora@gmail.com> To: "Jérôme Glisse" <jglisse@redhat.com>, akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: John Hubbard <jhubbard@nvidia.com>, Dan Williams <dan.j.williams@intel.com>, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>, David Nellans <dnellans@nvidia.com>, Evgeny Baskakov <ebaskakov@nvidia.com>, Mark Hairgrove <mhairgrove@nvidia.com>, Sherry Cheung <SCheung@nvidia.com>, Subhash Gutti <sgutti@nvidia.com> Subject: Re: [HMM 14/16] mm/hmm/devmem: device memory hotplug using ZONE_DEVICE Date: Fri, 07 Apr 2017 11:37:34 +1000 [thread overview] Message-ID: <1491529054.12351.16.camel@gmail.com> (raw) In-Reply-To: <20170405204026.3940-15-jglisse@redhat.com> On Wed, 2017-04-05 at 16:40 -0400, JA(C)rA'me Glisse wrote: > This introduce a simple struct and associated helpers for device driver > to use when hotpluging un-addressable device memory as ZONE_DEVICE. It > will find a unuse physical address range and trigger memory hotplug for > it which allocates and initialize struct page for the device memory. > > Signed-off-by: JA(C)rA'me Glisse <jglisse@redhat.com> > Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> > Signed-off-by: John Hubbard <jhubbard@nvidia.com> > Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> > Signed-off-by: Sherry Cheung <SCheung@nvidia.com> > Signed-off-by: Subhash Gutti <sgutti@nvidia.com> > --- > include/linux/hmm.h | 114 +++++++++++++++ > mm/Kconfig | 9 ++ > mm/hmm.c | 398 ++++++++++++++++++++++++++++++++++++++++++++++++++++ > 3 files changed, 521 insertions(+) > > +/* > + * To add (hotplug) device memory, HMM assumes that there is no real resource > + * that reserves a range in the physical address space (this is intended to be > + * use by unaddressable device memory). It will reserve a physical range big > + * enough and allocate struct page for it. I've found that the implementation of this is quite non-portable, in that starting from iomem_resource.end+1-size (which is effectively -size) on my platform (powerpc) does not give expected results. It could be that additional changes are needed to arch_add_memory() to support this use case. > + > + size = ALIGN(size, SECTION_SIZE); > + addr = (iomem_resource.end + 1ULL) - size; Why don't we allocate_resource() with the right constraints and get a new unused region? Thanks, Balbir -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2017-04-07 1:38 UTC|newest] Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-04-05 20:40 [HMM 00/16] HMM (Heterogeneous Memory Management) v19 Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 01/16] mm/memory/hotplug: add memory type parameter to arch_add/remove_memory Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-06 9:45 ` Anshuman Khandual 2017-04-06 9:45 ` Anshuman Khandual 2017-04-06 13:58 ` Jerome Glisse 2017-04-06 13:58 ` Jerome Glisse 2017-04-07 12:13 ` Michal Hocko 2017-04-07 12:13 ` Michal Hocko 2017-04-07 14:32 ` Jerome Glisse 2017-04-07 14:32 ` Jerome Glisse 2017-04-07 14:45 ` Michal Hocko 2017-04-07 14:45 ` Michal Hocko 2017-04-07 14:57 ` Jerome Glisse 2017-04-07 14:57 ` Jerome Glisse 2017-04-07 15:11 ` Michal Hocko 2017-04-07 15:11 ` Michal Hocko 2017-04-07 16:10 ` Jerome Glisse 2017-04-07 16:10 ` Jerome Glisse 2017-04-07 16:37 ` Michal Hocko 2017-04-07 16:37 ` Michal Hocko 2017-04-07 17:10 ` Jerome Glisse 2017-04-07 17:10 ` Jerome Glisse 2017-04-07 17:59 ` Michal Hocko 2017-04-07 17:59 ` Michal Hocko 2017-04-07 18:27 ` Jerome Glisse 2017-04-07 18:27 ` Jerome Glisse 2017-04-05 20:40 ` [HMM 02/16] mm/put_page: move ZONE_DEVICE page reference decrement v2 Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 03/16] mm/unaddressable-memory: new type of ZONE_DEVICE for unaddressable memory Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 04/16] mm/ZONE_DEVICE/x86: add support for un-addressable device memory Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 05/16] mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 06/16] mm/migrate: new memory migration helper for use with device memory v4 Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 07/16] mm/migrate: migrate_vma() unmap page from vma while collecting pages Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 08/16] mm/hmm: heterogeneous memory management (HMM for short) Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 09/16] mm/hmm/mirror: mirror process address space on device with HMM helpers Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 10/16] mm/hmm/mirror: helper to snapshot CPU page table v2 Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-10 8:35 ` Michal Hocko 2017-04-10 8:35 ` Michal Hocko 2017-04-10 8:43 ` Michal Hocko 2017-04-10 8:43 ` Michal Hocko 2017-04-10 22:10 ` Andrew Morton 2017-04-10 22:10 ` Andrew Morton 2017-04-11 1:33 ` Jerome Glisse 2017-04-11 1:33 ` Jerome Glisse 2017-04-11 20:33 ` Andrew Morton 2017-04-11 20:33 ` Andrew Morton 2017-04-05 20:40 ` [HMM 11/16] mm/hmm/mirror: device page fault handler Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 12/16] mm/migrate: support un-addressable ZONE_DEVICE page in migration Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 13/16] mm/migrate: allow migrate_vma() to alloc new page on empty entry Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 14/16] mm/hmm/devmem: device memory hotplug using ZONE_DEVICE Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-06 21:22 ` Jerome Glisse 2017-04-06 21:22 ` Jerome Glisse 2017-04-07 1:37 ` Balbir Singh [this message] 2017-04-07 1:37 ` Balbir Singh 2017-04-07 2:02 ` Jerome Glisse 2017-04-07 2:02 ` Jerome Glisse 2017-04-07 16:26 ` Jerome Glisse 2017-04-07 16:26 ` Jerome Glisse 2017-04-10 4:31 ` Balbir Singh 2017-04-10 4:31 ` Balbir Singh 2017-04-05 20:40 ` [HMM 15/16] mm/hmm/devmem: dummy HMM device for ZONE_DEVICE memory v2 Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-05 20:40 ` [HMM 16/16] hmm: heterogeneous memory management documentation Jérôme Glisse 2017-04-05 20:40 ` Jérôme Glisse 2017-04-06 3:22 ` [HMM 00/16] HMM (Heterogeneous Memory Management) v19 Figo.zhang 2017-04-06 4:59 ` Jerome Glisse 2017-04-06 4:59 ` Jerome Glisse
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1491529054.12351.16.camel@gmail.com \ --to=bsingharora@gmail.com \ --cc=SCheung@nvidia.com \ --cc=akpm@linux-foundation.org \ --cc=dan.j.williams@intel.com \ --cc=dnellans@nvidia.com \ --cc=ebaskakov@nvidia.com \ --cc=jglisse@redhat.com \ --cc=jhubbard@nvidia.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mhairgrove@nvidia.com \ --cc=n-horiguchi@ah.jp.nec.com \ --cc=sgutti@nvidia.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.