1 files changed, 68 insertions, 60 deletions

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e2b705c14945..0b6e1f781d86 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1164,10 +1164,6 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 }
 #endif
 
-#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
-#define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
-#endif
-
 #ifndef __HAVE_ARCH_MOVE_PTE
 #define move_pte(pte, old_addr, new_addr)	(pte)
 #endif
@@ -1489,80 +1485,92 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
  * vmf_insert_pfn.
  */
 
-/*
- * track_pfn_remap is called when a _new_ pfn mapping is being established
- * by remap_pfn_range() for physical range indicated by pfn and size.
- */
-static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
-				  unsigned long pfn, unsigned long addr,
-				  unsigned long size)
+static inline int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size,
+		pgprot_t *prot)
 {
 	return 0;
 }
 
-/*
- * track_pfn_insert is called when a _new_ single pfn is established
- * by vmf_insert_pfn().
- */
-static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-				    pfn_t pfn)
+static inline int pfnmap_track(unsigned long pfn, unsigned long size,
+		pgprot_t *prot)
 {
+	return 0;
 }
 
-/*
- * track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page
- * tables copied during copy_page_range(). On success, stores the pfn to be
- * passed to untrack_pfn_copy().
- */
-static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
-		struct vm_area_struct *src_vma, unsigned long *pfn)
+static inline void pfnmap_untrack(unsigned long pfn, unsigned long size)
 {
-	return 0;
 }
+#else
+/**
+ * pfnmap_setup_cachemode - setup the cachemode in the pgprot for a pfn range
+ * @pfn: the start of the pfn range
+ * @size: the size of the pfn range in bytes
+ * @prot: the pgprot to modify
+ *
+ * Lookup the cachemode for the pfn range starting at @pfn with the size
+ * @size and store it in @prot, leaving other data in @prot unchanged.
+ *
+ * This allows for a hardware implementation to have fine-grained control of
+ * memory cache behavior at page level granularity. Without a hardware
+ * implementation, this function does nothing.
+ *
+ * Currently there is only one implementation for this - x86 Page Attribute
+ * Table (PAT). See Documentation/arch/x86/pat.rst for more details.
+ *
+ * This function can fail if the pfn range spans pfns that require differing
+ * cachemodes. If the pfn range was previously verified to have a single
+ * cachemode, it is sufficient to query only a single pfn. The assumption is
+ * that this is the case for drivers using the vmf_insert_pfn*() interface.
+ *
+ * Returns 0 on success and -EINVAL on error.
+ */
+int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size,
+		pgprot_t *prot);
 
-/*
- * untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during
- * copy_page_range(), but after track_pfn_copy() was already called.
+/**
+ * pfnmap_track - track a pfn range
+ * @pfn: the start of the pfn range
+ * @size: the size of the pfn range in bytes
+ * @prot: the pgprot to track
+ *
+ * Requested the pfn range to be 'tracked' by a hardware implementation and
+ * setup the cachemode in @prot similar to pfnmap_setup_cachemode().
+ *
+ * This allows for fine-grained control of memory cache behaviour at page
+ * level granularity. Tracking memory this way is persisted across VMA splits
+ * (VMA merging does not apply for VM_PFNMAP).
+ *
+ * Currently, there is only one implementation for this - x86 Page Attribute
+ * Table (PAT). See Documentation/arch/x86/pat.rst for more details.
+ *
+ * Returns 0 on success and -EINVAL on error.
  */
-static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma,
-		unsigned long pfn)
-{
-}
+int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot);
 
-/*
- * untrack_pfn is called while unmapping a pfnmap for a region.
- * untrack can be called for a specific region indicated by pfn and size or
- * can be for the entire vma (in which case pfn, size are zero).
+/**
+ * pfnmap_untrack - untrack a pfn range
+ * @pfn: the start of the pfn range
+ * @size: the size of the pfn range in bytes
+ *
+ * Untrack a pfn range previously tracked through pfnmap_track().
  */
-static inline void untrack_pfn(struct vm_area_struct *vma,
-			       unsigned long pfn, unsigned long size,
-			       bool mm_wr_locked)
-{
-}
+void pfnmap_untrack(unsigned long pfn, unsigned long size);
+#endif
 
-/*
- * untrack_pfn_clear is called in the following cases on a VM_PFNMAP VMA:
+/**
+ * pfnmap_setup_cachemode_pfn - setup the cachemode in the pgprot for a pfn
+ * @pfn: the pfn
+ * @prot: the pgprot to modify
+ *
+ * Lookup the cachemode for @pfn and store it in @prot, leaving other
+ * data in @prot unchanged.
  *
- * 1) During mremap() on the src VMA after the page tables were moved.
- * 2) During fork() on the dst VMA, immediately after duplicating the src VMA.
+ * See pfnmap_setup_cachemode() for details.
  */
-static inline void untrack_pfn_clear(struct vm_area_struct *vma)
+static inline void pfnmap_setup_cachemode_pfn(unsigned long pfn, pgprot_t *prot)
 {
+	pfnmap_setup_cachemode(pfn, PAGE_SIZE, prot);
 }
-#else
-extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
-			   unsigned long pfn, unsigned long addr,
-			   unsigned long size);
-extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-			     pfn_t pfn);
-extern int track_pfn_copy(struct vm_area_struct *dst_vma,
-		struct vm_area_struct *src_vma, unsigned long *pfn);
-extern void untrack_pfn_copy(struct vm_area_struct *dst_vma,
-		unsigned long pfn);
-extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
-			unsigned long size, bool mm_wr_locked);
-extern void untrack_pfn_clear(struct vm_area_struct *vma);
-#endif
 
 #ifdef CONFIG_MMU
 #ifdef __HAVE_COLOR_ZERO_PAGE