Alistair Popple wrote:
> Previously dax pages were skipped by the pagewalk code as pud_special() or
> vm_normal_page{_pmd}() would be false for DAX pages. Now that dax pages are
> refcounted normally that is no longer the case, so add explicit checks to
> skip them.
>
> Signed-off-by: Alistair Popple <apop...@nvidia.com>
> ---
> include/linux/memremap.h | 11 +++++++++++
> mm/pagewalk.c | 12 ++++++++++--
> 2 files changed, 21 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/memremap.h b/include/linux/memremap.h
> index 4aa1519..54e8b57 100644
> --- a/include/linux/memremap.h
> +++ b/include/linux/memremap.h
> @@ -198,6 +198,17 @@ static inline bool folio_is_fsdax(const struct folio
> *folio)
> return is_fsdax_page(&folio->page);
> }
>
> +static inline bool is_devdax_page(const struct page *page)
> +{
> + return is_zone_device_page(page) &&
> + page_pgmap(page)->type == MEMORY_DEVICE_GENERIC;
> +}
> +
> +static inline bool folio_is_devdax(const struct folio *folio)
> +{
> + return is_devdax_page(&folio->page);
> +}
> +
> #ifdef CONFIG_ZONE_DEVICE
> void zone_device_page_init(struct page *page);
> void *memremap_pages(struct dev_pagemap *pgmap, int nid);
> diff --git a/mm/pagewalk.c b/mm/pagewalk.c
> index e478777..0dfb9c2 100644
> --- a/mm/pagewalk.c
> +++ b/mm/pagewalk.c
> @@ -884,6 +884,12 @@ struct folio *folio_walk_start(struct folio_walk *fw,
> * support PUD mappings in VM_PFNMAP|VM_MIXEDMAP VMAs.
> */
> page = pud_page(pud);
> +
> + if (is_devdax_page(page)) {
> + spin_unlock(ptl);
> + goto not_found;
> + }
> +
> goto found;
> }
>
> @@ -911,7 +917,8 @@ struct folio *folio_walk_start(struct folio_walk *fw,
> goto pte_table;
> } else if (pmd_present(pmd)) {
> page = vm_normal_page_pmd(vma, addr, pmd);
> - if (page) {
> + if (page && !is_devdax_page(page) &&
> + !is_fsdax_page(page)) {
It just looks awkward to say "yup, normal page, but not *that*
'normal'".
What about something like the below? Either way you can add:
Reviewed-by: Dan Williams <dan.j.willi...@intel.com>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 12d96659e8b4..4e549669166b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2471,6 +2471,27 @@ struct folio *vm_normal_folio_pmd(struct vm_area_struct
*vma,
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd);
+/* return normal pages backed by the page allocator */
+static inline struct page *vm_normal_gfp_pmd(struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd)
+{
+ struct page *page = vm_normal_page_pmd(vma, addr, pmd);
+
+ if (!is_devdax_page(page) && !is_fsdax_page(page))
+ return page;
+ return NULL;
+}
+
+static inline struct page *vm_normal_gfp_pte(struct vm_area_struct *vma,
+ unsigned long addr, pte_t pte)
+{
+ struct page *page = vm_normal_page(vma, addr, pte);
+
+ if (!is_devdax_page(page) && !is_fsdax_page(page))
+ return page;
+ return NULL;
+}
+
void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size);
void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index cca170fe5be5..54bfece05323 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -914,9 +914,8 @@ struct folio *folio_walk_start(struct folio_walk *fw,
spin_unlock(ptl);
goto pte_table;
} else if (pmd_present(pmd)) {
- page = vm_normal_page_pmd(vma, addr, pmd);
- if (page && !is_devdax_page(page) &&
- !is_fsdax_page(page)) {
+ page = vm_normal_gfp_pmd(vma, addr, pmd);
+ if (page) {
goto found;
} else if ((flags & FW_ZEROPAGE) &&
is_huge_zero_pmd(pmd)) {
@@ -949,9 +948,8 @@ struct folio *folio_walk_start(struct folio_walk *fw,
fw->pte = pte;
if (pte_present(pte)) {
- page = vm_normal_page(vma, addr, pte);
- if (page && !is_devdax_page(page) &&
- !is_fsdax_page(page))
+ page = vm_normal_gfp_pte(vma, addr, pte);
+ if (page)
goto found;
if ((flags & FW_ZEROPAGE) &&
is_zero_pfn(pte_pfn(pte))) {
