From: Alistair Popple <apopple@nvidia.com> To: <akpm@linux-foundation.org>, <Felix.Kuehling@amd.com>, <linux-mm@kvack.org>, <rcampbell@nvidia.com>, <linux-ext4@vger.kernel.org>, <linux-xfs@vger.kernel.org>, Alex Sierra <alex.sierra@amd.com> Cc: <amd-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>, <hch@lst.de>, <jgg@nvidia.com>, <jglisse@redhat.com>, <willy@infradead.org> Subject: Re: [PATCH v3 00/10] Add MEMORY_DEVICE_COHERENT for coherent device memory mapping Date: Thu, 20 Jan 2022 17:33:18 +1100 [thread overview] Message-ID: <3719261.HnWzZch5t3@nvdebian> (raw) In-Reply-To: <2389959.omVpu533ic@nvdebian> On Wednesday, 12 January 2022 10:06:03 PM AEDT Alistair Popple wrote: > I have been looking at this in relation to the migration code and noticed we > have the following in try_to_migrate(): > > if (is_zone_device_page(page) && !is_device_private_page(page)) > return; > > Which if I'm understanding correctly means that migration of device coherent > pages will always fail. Given that I do wonder how hmm-tests are passing, but > I assume you must always be hitting this fast path in > migrate_vma_collect_pmd(): > > /* > * Optimize for the common case where page is only mapped once > * in one process. If we can lock the page, then we can safely > * set up a special migration page table entry now. > */ > > Meaning that try_to_migrate() never gets called from migrate_vma_unmap(). So > you will also need some changes to try_to_migrate() and possibly > try_to_migrate_one() to make this reliable. I have been running the hmm tests with the changes below. I'm pretty sure these are correct because the only zone device pages try_to_migrate_one() should be called on are device coherent/private, and coherent pages can be treated just the same as a normal pages for migration. However it would be worth checking I haven't missed anything. - Alistair --- diff --git a/mm/rmap.c b/mm/rmap.c index 163ac4e6bcee..15f56c27daab 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1806,7 +1806,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (is_zone_device_page(page)) { + if (is_device_private_page(page)) { unsigned long pfn = page_to_pfn(page); swp_entry_t entry; pte_t swp_pte; @@ -1947,7 +1947,7 @@ void try_to_migrate(struct page *page, enum ttu_flags flags) TTU_SYNC))) return; - if (is_zone_device_page(page) && !is_device_private_page(page)) + if (is_zone_device_page(page) && !is_device_page(page)) return; /*
WARNING: multiple messages have this Message-ID (diff)
From: Alistair Popple <apopple@nvidia.com> To: <akpm@linux-foundation.org>, <Felix.Kuehling@amd.com>, <linux-mm@kvack.org>, <rcampbell@nvidia.com>, <linux-ext4@vger.kernel.org>, <linux-xfs@vger.kernel.org>, Alex Sierra <alex.sierra@amd.com> Cc: amd-gfx@lists.freedesktop.org, willy@infradead.org, jglisse@redhat.com, dri-devel@lists.freedesktop.org, jgg@nvidia.com, hch@lst.de Subject: Re: [PATCH v3 00/10] Add MEMORY_DEVICE_COHERENT for coherent device memory mapping Date: Thu, 20 Jan 2022 17:33:18 +1100 [thread overview] Message-ID: <3719261.HnWzZch5t3@nvdebian> (raw) In-Reply-To: <2389959.omVpu533ic@nvdebian> On Wednesday, 12 January 2022 10:06:03 PM AEDT Alistair Popple wrote: > I have been looking at this in relation to the migration code and noticed we > have the following in try_to_migrate(): > > if (is_zone_device_page(page) && !is_device_private_page(page)) > return; > > Which if I'm understanding correctly means that migration of device coherent > pages will always fail. Given that I do wonder how hmm-tests are passing, but > I assume you must always be hitting this fast path in > migrate_vma_collect_pmd(): > > /* > * Optimize for the common case where page is only mapped once > * in one process. If we can lock the page, then we can safely > * set up a special migration page table entry now. > */ > > Meaning that try_to_migrate() never gets called from migrate_vma_unmap(). So > you will also need some changes to try_to_migrate() and possibly > try_to_migrate_one() to make this reliable. I have been running the hmm tests with the changes below. I'm pretty sure these are correct because the only zone device pages try_to_migrate_one() should be called on are device coherent/private, and coherent pages can be treated just the same as a normal pages for migration. However it would be worth checking I haven't missed anything. - Alistair --- diff --git a/mm/rmap.c b/mm/rmap.c index 163ac4e6bcee..15f56c27daab 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1806,7 +1806,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (is_zone_device_page(page)) { + if (is_device_private_page(page)) { unsigned long pfn = page_to_pfn(page); swp_entry_t entry; pte_t swp_pte; @@ -1947,7 +1947,7 @@ void try_to_migrate(struct page *page, enum ttu_flags flags) TTU_SYNC))) return; - if (is_zone_device_page(page) && !is_device_private_page(page)) + if (is_zone_device_page(page) && !is_device_page(page)) return; /*
next prev parent reply other threads:[~2022-01-20 6:33 UTC|newest] Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-01-10 22:31 [PATCH v3 00/10] Add MEMORY_DEVICE_COHERENT for coherent device memory mapping Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-10 22:31 ` [PATCH v3 01/10] mm: add zone device coherent type memory support Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-20 4:08 ` Alistair Popple 2022-01-20 4:08 ` Alistair Popple 2022-01-10 22:31 ` [PATCH v3 02/10] mm: add device coherent vma selection for memory migration Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-10 22:31 ` [PATCH v3 03/10] mm/gup: fail get_user_pages for LONGTERM dev coherent type Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-20 12:36 ` Joao Martins 2022-01-20 12:36 ` Joao Martins 2022-01-20 13:18 ` Alistair Popple 2022-01-20 13:18 ` Alistair Popple 2022-01-10 22:31 ` [PATCH v3 04/10] drm/amdkfd: add SPM support for SVM Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-10 22:31 ` [PATCH v3 05/10] drm/amdkfd: coherent type as sys mem on migration to ram Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-10 22:31 ` [PATCH v3 06/10] lib: test_hmm add ioctl to get zone device type Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-20 5:01 ` Alistair Popple 2022-01-20 5:01 ` Alistair Popple 2022-01-10 22:31 ` [PATCH v3 07/10] lib: test_hmm add module param for " Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-20 5:23 ` Alistair Popple 2022-01-20 5:23 ` Alistair Popple 2022-01-10 22:31 ` [PATCH v3 08/10] lib: add support for device coherent type in test_hmm Alex Sierra 2022-01-10 22:31 ` Alex Sierra 2022-01-20 6:00 ` Alistair Popple 2022-01-20 6:00 ` Alistair Popple 2022-01-10 22:32 ` [PATCH v3 09/10] tools: update hmm-test to support device coherent type Alex Sierra 2022-01-10 22:32 ` Alex Sierra 2022-01-20 6:14 ` Alistair Popple 2022-01-20 6:14 ` Alistair Popple 2022-01-27 3:22 ` Sierra Guiza, Alejandro (Alex) 2022-01-27 3:22 ` Sierra Guiza, Alejandro (Alex) 2022-01-10 22:32 ` [PATCH v3 10/10] tools: update test_hmm script to support SP config Alex Sierra 2022-01-10 22:32 ` Alex Sierra 2022-01-20 6:17 ` Alistair Popple 2022-01-20 6:17 ` Alistair Popple 2022-01-12 11:06 ` [PATCH v3 00/10] Add MEMORY_DEVICE_COHERENT for coherent device memory mapping Alistair Popple 2022-01-12 11:06 ` Alistair Popple 2022-01-20 6:33 ` Alistair Popple [this message] 2022-01-20 6:33 ` Alistair Popple 2022-01-12 11:16 ` David Hildenbrand 2022-01-12 11:16 ` David Hildenbrand 2022-01-12 16:08 ` Felix Kuehling 2022-01-12 16:08 ` Felix Kuehling
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=3719261.HnWzZch5t3@nvdebian \ --to=apopple@nvidia.com \ --cc=Felix.Kuehling@amd.com \ --cc=akpm@linux-foundation.org \ --cc=alex.sierra@amd.com \ --cc=amd-gfx@lists.freedesktop.org \ --cc=dri-devel@lists.freedesktop.org \ --cc=hch@lst.de \ --cc=jgg@nvidia.com \ --cc=jglisse@redhat.com \ --cc=linux-ext4@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=linux-xfs@vger.kernel.org \ --cc=rcampbell@nvidia.com \ --cc=willy@infradead.org \ /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.