diff mbox series

[v3,13/25] mm/memory: Add vmf_insert_page_mkwrite()

Message ID cc2fc2971ab25e7e9f2207bb84e2ea0527174ff0.1732239628.git-series.apopple@nvidia.com (mailing list archive)
State New
Headers show
Series fs/dax: Fix ZONE_DEVICE page reference counts | expand

Commit Message

Alistair Popple Nov. 22, 2024, 1:40 a.m. UTC 
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 vmf_insert_page_mkwrite(). 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@nvidia.com>

---

Updates from v2:

 - Rename function to make not DAX specific

 - Split the insert_page_into_pte_locked() change into a separate
   patch.

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 |  2 ++
 mm/memory.c        | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 61fff5d..22c651b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3531,6 +3531,8 @@  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 vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
+			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 323662c..5e04310 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2548,6 +2548,42 @@  static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
+vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
+			bool write)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	pgprot_t pgprot = vma->vm_page_prot;
+	unsigned long pfn = page_to_pfn(page);
+	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_to_pfn_t(pfn));
+
+	if (!pfn_modify_allowed(pfn, pgprot))
+		return VM_FAULT_SIGBUS;
+
+	/*
+	 * We refcount the page normally so make sure pfn_valid is true.
+	 */
+	if (!pfn_valid(pfn))
+		return VM_FAULT_SIGBUS;
+
+	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(vmf_insert_page_mkwrite);
+
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 		pfn_t pfn)
 {