From: Alistair Popple Date: Wed, 28 Sep 2022 12:01:16 +0000 (+1000) Subject: mm: free device private pages have zero refcount X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=ef233450898f8893dafa193a9f3211fa077a3d05;p=linux.git mm: free device private pages have zero refcount Since 27674ef6c73f ("mm: remove the extra ZONE_DEVICE struct page refcount") device private pages have no longer had an extra reference count when the page is in use. However before handing them back to the owning device driver we add an extra reference count such that free pages have a reference count of one. This makes it difficult to tell if a page is free or not because both free and in use pages will have a non-zero refcount. Instead we should return pages to the drivers page allocator with a zero reference count. Kernel code can then safely use kernel functions such as get_page_unless_zero(). Link: https://lkml.kernel.org/r/cf70cf6f8c0bdb8aaebdbfb0d790aea4c683c3c6.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: Felix Kuehling Cc: Jason Gunthorpe Cc: Michael Ellerman Cc: Alex Deucher Cc: Christian König Cc: Ben Skeggs Cc: Lyude Paul Cc: Ralph Campbell Cc: Alex Sierra Cc: John Hubbard Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Matthew Wilcox Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 965c9e9e500bc..e2f11f9c3f2aa 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -718,7 +718,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - lock_page(dpage); + zone_device_page_init(dpage); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 776448bd9fe4a..97a684568ae01 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - lock_page(page); + zone_device_page_init(page); } static void diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 16356611b5b95..b092988266a6a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -326,7 +326,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) return NULL; } - lock_page(page); + zone_device_page_init(page); return page; } diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b5..7fcaf3180a5b6 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index e566166b55712..bc2b949911653 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -627,8 +627,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) goto error; } + zone_device_page_init(dpage); dpage->zone_device_data = rpage; - lock_page(dpage); return dpage; error: diff --git a/mm/memremap.c b/mm/memremap.c index 25029a474d30b..1c2c038f34109 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -505,8 +505,17 @@ void free_zone_device_page(struct page *page) /* * Reset the page count to 1 to prepare for handing out the page again. */ + if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && + page->pgmap->type != MEMORY_DEVICE_COHERENT) + set_page_count(page, 1); +} + +void zone_device_page_init(struct page *page) +{ set_page_count(page, 1); + lock_page(page); } +EXPORT_SYMBOL_GPL(zone_device_page_init); #ifdef CONFIG_FS_DAX bool __put_devmap_managed_page_refs(struct page *page, int refs) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 12b6184cbbed6..059f6946832fa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6819,6 +6819,14 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + + /* + * ZONE_DEVICE pages are released directly to the driver page allocator + * which will set the page count to 1 when allocating the page. + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_COHERENT) + set_page_count(page, 0); } /*