| Message ID | d4d399492b2ba09f4c551fa2261fbd22172886d8.1643698773.git-series.apopple@nvidia.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Migrate device coherent pages on get_user_pages() | expand |
Am 2022-02-01 um 02:05 schrieb Alistair Popple: > Currently any attempts to pin a device coherent page will fail. This is > because device coherent pages need to be managed by a device driver, and > pinning them would prevent a driver from migrating them off the device. > > However this is no reason to fail pinning of these pages. These are > coherent and accessible from the CPU so can be migrated just like > pinning ZONE_MOVABLE pages. So instead of failing all attempts to pin > them first try migrating them out of ZONE_DEVICE. > > Signed-off-by: Alistair Popple <apopple@nvidia.com> Thank you for working on this. I have two questions inline. Other than that, patches 1 and 2 are Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> > --- > mm/gup.c | 105 ++++++++++++++++++++++++++++++++++++++++++++++++++------ > 1 file changed, 95 insertions(+), 10 deletions(-) > > diff --git a/mm/gup.c b/mm/gup.c > index f596b93..2cbef54 100644 > --- a/mm/gup.c > +++ b/mm/gup.c > @@ -1834,6 +1834,60 @@ struct page *get_dump_page(unsigned long addr) > > #ifdef CONFIG_MIGRATION > /* > + * Migrates a device coherent page back to normal memory. Caller should have a > + * reference on page which will be copied to the new page if migration is > + * successful or dropped on failure. > + */ > +static struct page *migrate_device_page(struct page *page, > + unsigned int gup_flags) > +{ > + struct page *dpage; > + struct migrate_vma args; > + unsigned long src_pfn, dst_pfn = 0; > + > + lock_page(page); > + src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; > + args.src = &src_pfn; > + args.dst = &dst_pfn; > + args.cpages = 1; > + args.npages = 1; > + args.vma = NULL; > + migrate_vma_setup(&args); > + if (!(src_pfn & MIGRATE_PFN_MIGRATE)) > + return NULL; > + > + dpage = alloc_pages(GFP_USER | __GFP_NOWARN, 0); Don't you need to check dpage for NULL before the try_grab_page call below? > + > + /* > + * get/pin the new page now so we don't have to retry gup after > + * migrating. We already have a reference so this should never fail. > + */ > + if (WARN_ON_ONCE(!try_grab_page(dpage, gup_flags))) { > + __free_pages(dpage, 0); > + dpage = NULL; > + } > + > + if (dpage) { > + lock_page(dpage); > + dst_pfn = migrate_pfn(page_to_pfn(dpage)); > + } > + > + migrate_vma_pages(&args); > + if (src_pfn & MIGRATE_PFN_MIGRATE) > + copy_highpage(dpage, page); Can't dpage can be NULL here as well? Regards, Felix > + migrate_vma_finalize(&args); > + if (dpage && !(src_pfn & MIGRATE_PFN_MIGRATE)) { > + if (gup_flags & FOLL_PIN) > + unpin_user_page(dpage); > + else > + put_page(dpage); > + dpage = NULL; > + } > + > + return dpage; > +} > + > +/* > * Check whether all pages are pinnable, if so return number of pages. If some > * pages are not pinnable, migrate them, and unpin all pages. Return zero if > * pages were migrated, or if some pages were not successfully isolated. > @@ -1861,15 +1915,40 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, > continue; > prev_head = head; > /* > - * If we get a movable page, since we are going to be pinning > - * these entries, try to move them out if possible. > + * Device coherent pages are managed by a driver and should not > + * be pinned indefinitely as it prevents the driver moving the > + * page. So when trying to pin with FOLL_LONGTERM instead try > + * migrating page out of device memory. > */ > if (is_dev_private_or_coherent_page(head)) { > + /* > + * device private pages will get faulted in during gup > + * so it shouldn't be possible to see one here. > + */ > WARN_ON_ONCE(is_device_private_page(head)); > - ret = -EFAULT; > - goto unpin_pages; > + WARN_ON_ONCE(PageCompound(head)); > + > + /* > + * migration will fail if the page is pinned, so convert > + * the pin on the source page to a normal reference. > + */ > + if (gup_flags & FOLL_PIN) { > + get_page(head); > + unpin_user_page(head); > + } > + > + pages[i] = migrate_device_page(head, gup_flags); > + if (!pages[i]) { > + ret = -EBUSY; > + break; > + } > + continue; > } > > + /* > + * If we get a movable page, since we are going to be pinning > + * these entries, try to move them out if possible. > + */ > if (!is_pinnable_page(head)) { > if (PageHuge(head)) { > if (!isolate_huge_page(head, &movable_page_list)) > @@ -1897,16 +1976,22 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, > * If list is empty, and no isolation errors, means that all pages are > * in the correct zone. > */ > - if (list_empty(&movable_page_list) && !isolation_error_count) > + if (!ret && list_empty(&movable_page_list) && !isolation_error_count) > return nr_pages; > > -unpin_pages: > - if (gup_flags & FOLL_PIN) { > - unpin_user_pages(pages, nr_pages); > - } else { > - for (i = 0; i < nr_pages; i++) > + for (i = 0; i < nr_pages; i++) > + if (!pages[i]) > + continue; > + else if (gup_flags & FOLL_PIN) > + unpin_user_page(pages[i]); > + else > put_page(pages[i]); > + > + if (ret && !list_empty(&movable_page_list)) { > + putback_movable_pages(&movable_page_list); > + return ret; > } > + > if (!list_empty(&movable_page_list)) { > ret = migrate_pages(&movable_page_list, alloc_migration_target, > NULL, (unsigned long)&mtc, MIGRATE_SYNC,
On Wednesday, 2 February 2022 2:03:01 AM AEDT Felix Kuehling wrote: > > Am 2022-02-01 um 02:05 schrieb Alistair Popple: > > Currently any attempts to pin a device coherent page will fail. This is > > because device coherent pages need to be managed by a device driver, and > > pinning them would prevent a driver from migrating them off the device. > > > > However this is no reason to fail pinning of these pages. These are > > coherent and accessible from the CPU so can be migrated just like > > pinning ZONE_MOVABLE pages. So instead of failing all attempts to pin > > them first try migrating them out of ZONE_DEVICE. > > > > Signed-off-by: Alistair Popple <apopple@nvidia.com> > > Thank you for working on this. I have two questions inline. > > Other than that, patches 1 and 2 are > > Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> > > > > --- > > mm/gup.c | 105 ++++++++++++++++++++++++++++++++++++++++++++++++++------ > > 1 file changed, 95 insertions(+), 10 deletions(-) > > > > diff --git a/mm/gup.c b/mm/gup.c > > index f596b93..2cbef54 100644 > > --- a/mm/gup.c > > +++ b/mm/gup.c > > @@ -1834,6 +1834,60 @@ struct page *get_dump_page(unsigned long addr) > > > > #ifdef CONFIG_MIGRATION > > /* > > + * Migrates a device coherent page back to normal memory. Caller should have a > > + * reference on page which will be copied to the new page if migration is > > + * successful or dropped on failure. > > + */ > > +static struct page *migrate_device_page(struct page *page, > > + unsigned int gup_flags) > > +{ > > + struct page *dpage; > > + struct migrate_vma args; > > + unsigned long src_pfn, dst_pfn = 0; > > + > > + lock_page(page); > > + src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; > > + args.src = &src_pfn; > > + args.dst = &dst_pfn; > > + args.cpages = 1; > > + args.npages = 1; > > + args.vma = NULL; > > + migrate_vma_setup(&args); > > + if (!(src_pfn & MIGRATE_PFN_MIGRATE)) > > + return NULL; > > + > > + dpage = alloc_pages(GFP_USER | __GFP_NOWARN, 0); > > Don't you need to check dpage for NULL before the try_grab_page call below? Yes, thanks for pointing that out. Will fix for v2. > > + > > + /* > > + * get/pin the new page now so we don't have to retry gup after > > + * migrating. We already have a reference so this should never fail. > > + */ > > + if (WARN_ON_ONCE(!try_grab_page(dpage, gup_flags))) { > > + __free_pages(dpage, 0); > > + dpage = NULL; > > + } > > + > > + if (dpage) { > > + lock_page(dpage); > > + dst_pfn = migrate_pfn(page_to_pfn(dpage)); > > + } > > + > > + migrate_vma_pages(&args); > > + if (src_pfn & MIGRATE_PFN_MIGRATE) > > + copy_highpage(dpage, page); > > Can't dpage can be NULL here as well? No - migrate_vma_pages() will clear src_pfn & MIGRATE_PFN_MIGRATE if no destination page is provided in dst_pfn. > Regards, > Felix > > > > + migrate_vma_finalize(&args); > > + if (dpage && !(src_pfn & MIGRATE_PFN_MIGRATE)) { > > + if (gup_flags & FOLL_PIN) > > + unpin_user_page(dpage); > > + else > > + put_page(dpage); > > + dpage = NULL; > > + } > > + > > + return dpage; > > +} > > + > > +/* > > * Check whether all pages are pinnable, if so return number of pages. If some > > * pages are not pinnable, migrate them, and unpin all pages. Return zero if > > * pages were migrated, or if some pages were not successfully isolated. > > @@ -1861,15 +1915,40 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, > > continue; > > prev_head = head; > > /* > > - * If we get a movable page, since we are going to be pinning > > - * these entries, try to move them out if possible. > > + * Device coherent pages are managed by a driver and should not > > + * be pinned indefinitely as it prevents the driver moving the > > + * page. So when trying to pin with FOLL_LONGTERM instead try > > + * migrating page out of device memory. > > */ > > if (is_dev_private_or_coherent_page(head)) { > > + /* > > + * device private pages will get faulted in during gup > > + * so it shouldn't be possible to see one here. > > + */ > > WARN_ON_ONCE(is_device_private_page(head)); > > - ret = -EFAULT; > > - goto unpin_pages; > > + WARN_ON_ONCE(PageCompound(head)); > > + > > + /* > > + * migration will fail if the page is pinned, so convert > > + * the pin on the source page to a normal reference. > > + */ > > + if (gup_flags & FOLL_PIN) { > > + get_page(head); > > + unpin_user_page(head); > > + } > > + > > + pages[i] = migrate_device_page(head, gup_flags); > > + if (!pages[i]) { > > + ret = -EBUSY; > > + break; > > + } > > + continue; > > } > > > > + /* > > + * If we get a movable page, since we are going to be pinning > > + * these entries, try to move them out if possible. > > + */ > > if (!is_pinnable_page(head)) { > > if (PageHuge(head)) { > > if (!isolate_huge_page(head, &movable_page_list)) > > @@ -1897,16 +1976,22 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, > > * If list is empty, and no isolation errors, means that all pages are > > * in the correct zone. > > */ > > - if (list_empty(&movable_page_list) && !isolation_error_count) > > + if (!ret && list_empty(&movable_page_list) && !isolation_error_count) > > return nr_pages; > > > > -unpin_pages: > > - if (gup_flags & FOLL_PIN) { > > - unpin_user_pages(pages, nr_pages); > > - } else { > > - for (i = 0; i < nr_pages; i++) > > + for (i = 0; i < nr_pages; i++) > > + if (!pages[i]) > > + continue; > > + else if (gup_flags & FOLL_PIN) > > + unpin_user_page(pages[i]); > > + else > > put_page(pages[i]); > > + > > + if (ret && !list_empty(&movable_page_list)) { > > + putback_movable_pages(&movable_page_list); > > + return ret; > > } > > + > > if (!list_empty(&movable_page_list)) { > > ret = migrate_pages(&movable_page_list, alloc_migration_target, > > NULL, (unsigned long)&mtc, MIGRATE_SYNC, >
diff --git a/mm/gup.c b/mm/gup.c index f596b93..2cbef54 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1834,6 +1834,60 @@ struct page *get_dump_page(unsigned long addr) #ifdef CONFIG_MIGRATION /* + * Migrates a device coherent page back to normal memory. Caller should have a + * reference on page which will be copied to the new page if migration is + * successful or dropped on failure. + */ +static struct page *migrate_device_page(struct page *page, + unsigned int gup_flags) +{ + struct page *dpage; + struct migrate_vma args; + unsigned long src_pfn, dst_pfn = 0; + + lock_page(page); + src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; + args.src = &src_pfn; + args.dst = &dst_pfn; + args.cpages = 1; + args.npages = 1; + args.vma = NULL; + migrate_vma_setup(&args); + if (!(src_pfn & MIGRATE_PFN_MIGRATE)) + return NULL; + + dpage = alloc_pages(GFP_USER | __GFP_NOWARN, 0); + + /* + * get/pin the new page now so we don't have to retry gup after + * migrating. We already have a reference so this should never fail. + */ + if (WARN_ON_ONCE(!try_grab_page(dpage, gup_flags))) { + __free_pages(dpage, 0); + dpage = NULL; + } + + if (dpage) { + lock_page(dpage); + dst_pfn = migrate_pfn(page_to_pfn(dpage)); + } + + migrate_vma_pages(&args); + if (src_pfn & MIGRATE_PFN_MIGRATE) + copy_highpage(dpage, page); + migrate_vma_finalize(&args); + if (dpage && !(src_pfn & MIGRATE_PFN_MIGRATE)) { + if (gup_flags & FOLL_PIN) + unpin_user_page(dpage); + else + put_page(dpage); + dpage = NULL; + } + + return dpage; +} + +/* * Check whether all pages are pinnable, if so return number of pages. If some * pages are not pinnable, migrate them, and unpin all pages. Return zero if * pages were migrated, or if some pages were not successfully isolated. @@ -1861,15 +1915,40 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, continue; prev_head = head; /* - * If we get a movable page, since we are going to be pinning - * these entries, try to move them out if possible. + * Device coherent pages are managed by a driver and should not + * be pinned indefinitely as it prevents the driver moving the + * page. So when trying to pin with FOLL_LONGTERM instead try + * migrating page out of device memory. */ if (is_dev_private_or_coherent_page(head)) { + /* + * device private pages will get faulted in during gup + * so it shouldn't be possible to see one here. + */ WARN_ON_ONCE(is_device_private_page(head)); - ret = -EFAULT; - goto unpin_pages; + WARN_ON_ONCE(PageCompound(head)); + + /* + * migration will fail if the page is pinned, so convert + * the pin on the source page to a normal reference. + */ + if (gup_flags & FOLL_PIN) { + get_page(head); + unpin_user_page(head); + } + + pages[i] = migrate_device_page(head, gup_flags); + if (!pages[i]) { + ret = -EBUSY; + break; + } + continue; } + /* + * If we get a movable page, since we are going to be pinning + * these entries, try to move them out if possible. + */ if (!is_pinnable_page(head)) { if (PageHuge(head)) { if (!isolate_huge_page(head, &movable_page_list)) @@ -1897,16 +1976,22 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, * If list is empty, and no isolation errors, means that all pages are * in the correct zone. */ - if (list_empty(&movable_page_list) && !isolation_error_count) + if (!ret && list_empty(&movable_page_list) && !isolation_error_count) return nr_pages; -unpin_pages: - if (gup_flags & FOLL_PIN) { - unpin_user_pages(pages, nr_pages); - } else { - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) + if (!pages[i]) + continue; + else if (gup_flags & FOLL_PIN) + unpin_user_page(pages[i]); + else put_page(pages[i]); + + if (ret && !list_empty(&movable_page_list)) { + putback_movable_pages(&movable_page_list); + return ret; } + if (!list_empty(&movable_page_list)) { ret = migrate_pages(&movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC,
Currently any attempts to pin a device coherent page will fail. This is because device coherent pages need to be managed by a device driver, and pinning them would prevent a driver from migrating them off the device. However this is no reason to fail pinning of these pages. These are coherent and accessible from the CPU so can be migrated just like pinning ZONE_MOVABLE pages. So instead of failing all attempts to pin them first try migrating them out of ZONE_DEVICE. Signed-off-by: Alistair Popple <apopple@nvidia.com> --- mm/gup.c | 105 ++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 95 insertions(+), 10 deletions(-)