Commit 27674ef6 authored by Christoph Hellwig's avatar Christoph Hellwig Committed by Matthew Wilcox (Oracle)
Browse files

mm: remove the extra ZONE_DEVICE struct page refcount 

ZONE_DEVICE struct pages have an extra reference count that complicates
the code for put_page() and several places in the kernel that need to
check the reference count to see that a page is not being used (gup,
compaction, migration, etc.). Clean up the code so the reference count
doesn't need to be treated specially for ZONE_DEVICE pages.

Note that this excludes the special idle page wakeup for fsdax pages,
which still happens at refcount 1.  This is a separate issue and will
be sorted out later.  Given that only fsdax pages require the
notifiacation when the refcount hits 1 now, the PAGEMAP_OPS Kconfig
symbol can go away and be replaced with a FS_DAX check for this hook
in the put_page fastpath.

Based on an earlier patch from Ralph Campbell <rcampbell@nvidia.com>.

Link: https://lkml.kernel.org/r/20220210072828.2930359-8-hch@lst.de


Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarLogan Gunthorpe <logang@deltatee.com>
Reviewed-by: default avatarRalph Campbell <rcampbell@nvidia.com>
Reviewed-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Reviewed-by: default avatarDan Williams <dan.j.williams@intel.com>
Acked-by: default avatarFelix Kuehling <Felix.Kuehling@amd.com>
Tested-by: default avatar"Sierra Guiza, Alejandro (Alex)" <alex.sierra@amd.com>

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Chaitanya Kulkarni <kch@nvidia.com>
Cc: Christian Knig <christian.koenig@amd.com>
Cc: Karol Herbst <kherbst@redhat.com>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: "Pan, Xinhui" <Xinhui.Pan@amd.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarMatthew Wilcox (Oracle) <willy@infradead.org>
parent dc90f084

arch/powerpc/kvm/book3s_hv_uvmem.c

+0 −1
Original line number Diff line number Diff line
@@ -713,7 +713,6 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) 


	dpage = pfn_to_page(uvmem_pfn);

	dpage->zone_device_data = pvt;

	get_page(dpage);

	lock_page(dpage);

	return dpage;

out_clear:

drivers/gpu/drm/amd/amdkfd/kfd_migrate.c

+0 −1
Original line number Diff line number Diff line
@@ -225,7 +225,6 @@ 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;

	get_page(page);

	lock_page(page);

}

drivers/gpu/drm/nouveau/nouveau_dmem.c

+0 −1
Original line number Diff line number Diff line
@@ -326,7 +326,6 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) 
			return NULL;

	}



	get_page(page);

	lock_page(page);

	return page;

}

fs/Kconfig

+0 −1
Original line number Diff line number Diff line
@@ -48,7 +48,6 @@ config FS_DAX 
	bool "File system based Direct Access (DAX) support"

	depends on MMU

	depends on !(ARM || MIPS || SPARC)

	select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED)

	select FS_IOMAP

	select DAX

	help

include/linux/memremap.h

+5 −7
Original line number Diff line number Diff line
@@ -68,9 +68,9 @@ enum memory_type { 


struct dev_pagemap_ops {

	/*

	 * Called once the page refcount reaches 1.  (ZONE_DEVICE pages never

	 * reach 0 refcount unless there is a refcount bug. This allows the

	 * device driver to implement its own memory management.)

	 * Called once the page refcount reaches 0.  The reference count will be

	 * reset to one by the core code after the method is called to prepare

	 * for handing out the page again.

	 */

	void (*page_free)(struct page *page);
@@ -133,16 +133,14 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) 


static inline bool is_device_private_page(const struct page *page)

{

	return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&

		IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&

	return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&

		is_zone_device_page(page) &&

		page->pgmap->type == MEMORY_DEVICE_PRIVATE;

}



static inline bool is_pci_p2pdma_page(const struct page *page)

{

	return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&

		IS_ENABLED(CONFIG_PCI_P2PDMA) &&

	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&

		is_zone_device_page(page) &&

		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;

}