Currently to map a DAX page the DAX driver calls vmf_insert_pfn. This
creates a special devmap PTE entry for the pfn but does not take a
reference on the underlying struct page for the mapping. This is
because DAX page refcounts are treated specially, as indicated by the
presence of a devmap entry.
To allow DAX page refcounts to be managed the same as normal page
refcounts introduce dax_insert_pfn. This will take a reference on the
underlying page much the same as vmf_insert_page, except it also
permits upgrading an existing mapping to be writable if
requested/possible.
Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx>
---
Updates from v1:
- Re-arrange code in insert_page_into_pte_locked() based on comments
from Jan Kara.
- Call mkdrity/mkyoung for the mkwrite case, also suggested by Jan.
---
include/linux/mm.h | 1 +-
mm/memory.c | 83 ++++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 76 insertions(+), 8 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b0ff06d..ae6d713 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3463,6 +3463,7 @@ int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
+vm_fault_t dax_insert_pfn(struct vm_fault *vmf, pfn_t pfn_t, bool write);
vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
diff --git a/mm/memory.c b/mm/memory.c
index d2785fb..368e15d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2039,19 +2039,47 @@ static int validate_page_before_insert(struct vm_area_struct *vma,
}
static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
- unsigned long addr, struct page *page, pgprot_t prot)
+ unsigned long addr, struct page *page,
+ pgprot_t prot, bool mkwrite)
{
struct folio *folio = page_folio(page);
+ pte_t entry = ptep_get(pte);
pte_t pteval;
- if (!pte_none(ptep_get(pte)))
- return -EBUSY;
+ if (!pte_none(entry)) {
+ if (!mkwrite)
+ return -EBUSY;
+
+ /*
+ * For read faults on private mappings the PFN passed in may not
+ * match the PFN we have mapped if the mapped PFN is a writeable
+ * COW page. In the mkwrite case we are creating a writable PTE
+ * for a shared mapping and we expect the PFNs to match. If they
+ * don't match, we are likely racing with block allocation and
+ * mapping invalidation so just skip the update.
+ */
+ if (pte_pfn(entry) != page_to_pfn(page)) {
+ WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry)));
+ return -EFAULT;
+ }
+ entry = maybe_mkwrite(entry, vma);
+ entry = pte_mkyoung(entry);
+ if (ptep_set_access_flags(vma, addr, pte, entry, 1))
+ update_mmu_cache(vma, addr, pte);
+ return 0;
+ }
+
/* Ok, finally just insert the thing.. */
pteval = mk_pte(page, prot);
if (unlikely(is_zero_folio(folio))) {
pteval = pte_mkspecial(pteval);
} else {
folio_get(folio);
+ entry = mk_pte(page, prot);
+ if (mkwrite) {
+ entry = pte_mkyoung(entry);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ }
inc_mm_counter(vma->vm_mm, mm_counter_file(folio));
folio_add_file_rmap_pte(folio, page, vma);
}
@@ -2060,7 +2088,7 @@ static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
}
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
- struct page *page, pgprot_t prot)
+ struct page *page, pgprot_t prot, bool mkwrite)
{
int retval;
pte_t *pte;
@@ -2073,7 +2101,8 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
pte = get_locked_pte(vma->vm_mm, addr, &ptl);
if (!pte)
goto out;
- retval = insert_page_into_pte_locked(vma, pte, addr, page, prot);
+ retval = insert_page_into_pte_locked(vma, pte, addr, page, prot,
+ mkwrite);
pte_unmap_unlock(pte, ptl);
out:
return retval;
@@ -2087,7 +2116,7 @@ static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte,
err = validate_page_before_insert(vma, page);
if (err)
return err;
- return insert_page_into_pte_locked(vma, pte, addr, page, prot);
+ return insert_page_into_pte_locked(vma, pte, addr, page, prot, false);
}
/* insert_pages() amortizes the cost of spinlock operations
@@ -2223,7 +2252,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
BUG_ON(vma->vm_flags & VM_PFNMAP);
vm_flags_set(vma, VM_MIXEDMAP);
}
- return insert_page(vma, addr, page, vma->vm_page_prot);
+ return insert_page(vma, addr, page, vma->vm_page_prot, false);
}
EXPORT_SYMBOL(vm_insert_page);
@@ -2503,7 +2532,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
* result in pfn_t_has_page() == false.
*/
page = pfn_to_page(pfn_t_to_pfn(pfn));
- err = insert_page(vma, addr, page, pgprot);
+ err = insert_page(vma, addr, page, pgprot, mkwrite);
} else {
return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
}
@@ -2516,6 +2545,44 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
return VM_FAULT_NOPAGE;
}
+vm_fault_t dax_insert_pfn(struct vm_fault *vmf, pfn_t pfn_t, bool write)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ pgprot_t pgprot = vma->vm_page_prot;
+ unsigned long pfn = pfn_t_to_pfn(pfn_t);
+ struct page *page = pfn_to_page(pfn);
+ unsigned long addr = vmf->address;
+ int err;
+
+ if (addr < vma->vm_start || addr >= vma->vm_end)
+ return VM_FAULT_SIGBUS;
+
+ track_pfn_insert(vma, &pgprot, pfn_t);
+
+ if (!pfn_modify_allowed(pfn, pgprot))
+ return VM_FAULT_SIGBUS;
+
+ /*
+ * We refcount the page normally so make sure pfn_valid is true.
+ */
+ if (!pfn_t_valid(pfn_t))
+ return VM_FAULT_SIGBUS;
+
+ WARN_ON_ONCE(pfn_t_devmap(pfn_t));
+
+ if (WARN_ON(is_zero_pfn(pfn) && write))
+ return VM_FAULT_SIGBUS;
+
+ err = insert_page(vma, addr, page, pgprot, write);
+ if (err == -ENOMEM)
+ return VM_FAULT_OOM;
+ if (err < 0 && err != -EBUSY)
+ return VM_FAULT_SIGBUS;
+
+ return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(dax_insert_pfn);
+
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn)
{
--
git-series 0.9.1
