[PATCH v5 1/5] mm/zone_device: Reinitialize large zone device private folios
Francois Dugast
francois.dugast at intel.com
Thu Jan 15 06:19:52 AEDT 2026
From: Matthew Brost <matthew.brost at intel.com>
Reinitialize metadata for large zone device private folios in
zone_device_page_init prior to creating a higher-order zone device
private folio. This step is necessary when the folio’s order changes
dynamically between zone_device_page_init calls to avoid building a
corrupt folio. As part of the metadata reinitialization, the dev_pagemap
must be passed in from the caller because the pgmap stored in the folio
page may have been overwritten with a compound head.
Cc: Zi Yan <ziy at nvidia.com>
Cc: Alistair Popple <apopple at nvidia.com>
Cc: adhavan Srinivasan <maddy at linux.ibm.com>
Cc: Nicholas Piggin <npiggin at gmail.com>
Cc: Michael Ellerman <mpe at ellerman.id.au>
Cc: "Christophe Leroy (CS GROUP)" <chleroy at kernel.org>
Cc: Felix Kuehling <Felix.Kuehling at amd.com>
Cc: Alex Deucher <alexander.deucher at amd.com>
Cc: "Christian König" <christian.koenig at amd.com>
Cc: David Airlie <airlied at gmail.com>
Cc: Simona Vetter <simona at ffwll.ch>
Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
Cc: Maxime Ripard <mripard at kernel.org>
Cc: Thomas Zimmermann <tzimmermann at suse.de>
Cc: Lyude Paul <lyude at redhat.com>
Cc: Danilo Krummrich <dakr at kernel.org>
Cc: David Hildenbrand <david at kernel.org>
Cc: Oscar Salvador <osalvador at suse.de>
Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Jason Gunthorpe <jgg at ziepe.ca>
Cc: Leon Romanovsky <leon at kernel.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes at oracle.com>
Cc: Liam R. Howlett <Liam.Howlett at oracle.com>
Cc: Vlastimil Babka <vbabka at suse.cz>
Cc: Mike Rapoport <rppt at kernel.org>
Cc: Suren Baghdasaryan <surenb at google.com>
Cc: Michal Hocko <mhocko at suse.com>
Cc: Balbir Singh <balbirs at nvidia.com>
Cc: linuxppc-dev at lists.ozlabs.org
Cc: kvm at vger.kernel.org
Cc: linux-kernel at vger.kernel.org
Cc: amd-gfx at lists.freedesktop.org
Cc: dri-devel at lists.freedesktop.org
Cc: nouveau at lists.freedesktop.org
Cc: linux-mm at kvack.org
Cc: linux-cxl at vger.kernel.org
Fixes: d245f9b4ab80 ("mm/zone_device: support large zone device private folios")
Signed-off-by: Matthew Brost <matthew.brost at intel.com>
Signed-off-by: Francois Dugast <francois.dugast at intel.com>
---
arch/powerpc/kvm/book3s_hv_uvmem.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 +-
drivers/gpu/drm/drm_pagemap.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +-
include/linux/memremap.h | 9 ++++++---
lib/test_hmm.c | 4 +++-
mm/memremap.c | 20 +++++++++++++++++++-
7 files changed, 32 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index e5000bef90f2..7cf9310de0ec 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -723,7 +723,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
dpage = pfn_to_page(uvmem_pfn);
dpage->zone_device_data = pvt;
- zone_device_page_init(dpage, 0);
+ zone_device_page_init(dpage, &kvmppc_uvmem_pgmap, 0);
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 af53e796ea1b..6ada7b4af7c6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -217,7 +217,7 @@ 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;
- zone_device_page_init(page, 0);
+ zone_device_page_init(page, page_pgmap(page), 0);
}
static void
diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index 03ee39a761a4..c497726b0147 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -201,7 +201,7 @@ static void drm_pagemap_get_devmem_page(struct page *page,
struct drm_pagemap_zdd *zdd)
{
page->zone_device_data = drm_pagemap_zdd_get(zdd);
- zone_device_page_init(page, 0);
+ zone_device_page_init(page, zdd->dpagemap->pagemap, 0);
}
/**
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 58071652679d..3d8031296eed 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -425,7 +425,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm, bool is_large)
order = ilog2(DMEM_CHUNK_NPAGES);
}
- zone_device_folio_init(folio, order);
+ zone_device_folio_init(folio, page_pgmap(folio_page(folio, 0)), order);
return page;
}
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 713ec0435b48..e3c2ccf872a8 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -224,7 +224,8 @@ static inline bool is_fsdax_page(const struct page *page)
}
#ifdef CONFIG_ZONE_DEVICE
-void zone_device_page_init(struct page *page, unsigned int order);
+void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap,
+ unsigned int order);
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);
@@ -234,9 +235,11 @@ bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
unsigned long memremap_compat_align(void);
-static inline void zone_device_folio_init(struct folio *folio, unsigned int order)
+static inline void zone_device_folio_init(struct folio *folio,
+ struct dev_pagemap *pgmap,
+ unsigned int order)
{
- zone_device_page_init(&folio->page, order);
+ zone_device_page_init(&folio->page, pgmap, order);
if (order)
folio_set_large_rmappable(folio);
}
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 8af169d3873a..455a6862ae50 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -662,7 +662,9 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror *dmirror,
goto error;
}
- zone_device_folio_init(page_folio(dpage), order);
+ zone_device_folio_init(page_folio(dpage),
+ page_pgmap(folio_page(page_folio(dpage), 0)),
+ order);
dpage->zone_device_data = rpage;
return dpage;
diff --git a/mm/memremap.c b/mm/memremap.c
index 63c6ab4fdf08..6f46ab14662b 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -477,10 +477,28 @@ void free_zone_device_folio(struct folio *folio)
}
}
-void zone_device_page_init(struct page *page, unsigned int order)
+void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap,
+ unsigned int order)
{
+ struct page *new_page = page;
+ unsigned int i;
+
VM_WARN_ON_ONCE(order > MAX_ORDER_NR_PAGES);
+ for (i = 0; i < (1UL << order); ++i, ++new_page) {
+ struct folio *new_folio = (struct folio *)new_page;
+
+ new_page->flags.f &= ~0xffUL; /* Clear possible order, page head */
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+ ((struct folio *)(new_page - 1))->_nr_pages = 0;
+#endif
+ new_folio->mapping = NULL;
+ new_folio->pgmap = pgmap; /* Also clear compound head */
+ new_folio->share = 0; /* fsdax only, unused for device private */
+ VM_WARN_ON_FOLIO(folio_ref_count(new_folio), new_folio);
+ VM_WARN_ON_FOLIO(!folio_is_zone_device(new_folio), new_folio);
+ }
+
/*
* Drivers shouldn't be allocating pages after calling
* memunmap_pages().
--
2.43.0
More information about the Linuxppc-dev
mailing list