mm/swap: add swp_offset_pfn() to fetch PFN from swap entry

We've got a bunch of special swap entries that stores PFN inside the swap
offset fields.  To fetch the PFN, normally the user just calls
swp_offset() assuming that'll be the PFN.

Add a helper swp_offset_pfn() to fetch the PFN instead, fetching only the
max possible length of a PFN on the host, meanwhile doing proper check
with MAX_PHYSMEM_BITS to make sure the swap offsets can actually store the
PFNs properly always using the BUILD_BUG_ON() in is_pfn_swap_entry().

One reason to do so is we never tried to sanitize whether swap offset can
really fit for storing PFN.  At the meantime, this patch also prepares us
with the future possibility to store more information inside the swp
offset field, so assuming "swp_offset(entry)" to be the PFN will not stand
any more very soon.

Replace many of the swp_offset() callers to use swp_offset_pfn() where
proper.  Note that many of the existing users are not candidates for the
replacement, e.g.:

  (1) When the swap entry is not a pfn swap entry at all, or,
  (2) when we wanna keep the whole swp_offset but only change the swp type.

For the latter, it can happen when fork() triggered on a write-migration
swap entry pte, we may want to only change the migration type from
write->read but keep the rest, so it's not "fetching PFN" but "changing
swap type only".  They're left aside so that when there're more
information within the swp offset they'll be carried over naturally in
those cases.

Since at it, dropping hwpoison_entry_to_pfn() because that's exactly what
the new swp_offset_pfn() is about.

Link: https://lkml.kernel.org/r/20220811161331.37055-4-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arm64/mm/hugetlbpage.c

@@ -245,7 +245,7 @@ static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
 {
 	VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
 
-	return page_folio(pfn_to_page(swp_offset(entry)));
+	return page_folio(pfn_to_page(swp_offset_pfn(entry)));
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,

fs/proc/task_mmu.c

@@ -1418,9 +1418,19 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		if (pte_swp_uffd_wp(pte))
 			flags |= PM_UFFD_WP;
 		entry = pte_to_swp_entry(pte);
-		if (pm->show_pfn)
+		if (pm->show_pfn) {
+			pgoff_t offset;
+			/*
+			 * For PFN swap offsets, keeping the offset field
+			 * to be PFN only to be compatible with old smaps.
+			 */
+			if (is_pfn_swap_entry(entry))
+				offset = swp_offset_pfn(entry);
+			else
+				offset = swp_offset(entry);
 			frame = swp_type(entry) |
-				(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+			    (offset << MAX_SWAPFILES_SHIFT);
+		}
 		flags |= PM_SWAP;
 		migration = is_migration_entry(entry);
 		if (is_pfn_swap_entry(entry))
@@ -1477,7 +1487,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			unsigned long offset;
 
 			if (pm->show_pfn) {
-				offset = swp_offset(entry) +
+				if (is_pfn_swap_entry(entry))
+					offset = swp_offset_pfn(entry);
+				else
+					offset = swp_offset(entry);
+				offset = offset +
 					((addr & ~PMD_MASK) >> PAGE_SHIFT);
 				frame = swp_type(entry) |
 					(offset << MAX_SWAPFILES_SHIFT);

include/linux/swapops.h

@@ -23,6 +23,20 @@
 #define SWP_TYPE_SHIFT	(BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
 #define SWP_OFFSET_MASK	((1UL << SWP_TYPE_SHIFT) - 1)
 
+/*
+ * Definitions only for PFN swap entries (see is_pfn_swap_entry()).  To
+ * store PFN, we only need SWP_PFN_BITS bits.  Each of the pfn swap entries
+ * can use the extra bits to store other information besides PFN.
+ */
+#ifdef MAX_PHYSMEM_BITS
+#define SWP_PFN_BITS			(MAX_PHYSMEM_BITS - PAGE_SHIFT)
+#else  /* MAX_PHYSMEM_BITS */
+#define SWP_PFN_BITS			(BITS_PER_LONG - PAGE_SHIFT)
+#endif	/* MAX_PHYSMEM_BITS */
+#define SWP_PFN_MASK			(BIT(SWP_PFN_BITS) - 1)
+
+static inline bool is_pfn_swap_entry(swp_entry_t entry);
+
 /* Clear all flags but only keep swp_entry_t related information */
 static inline pte_t pte_swp_clear_flags(pte_t pte)
 {
@@ -64,6 +78,17 @@ static inline pgoff_t swp_offset(swp_entry_t entry)
 	return entry.val & SWP_OFFSET_MASK;
 }
 
+/*
+ * This should only be called upon a pfn swap entry to get the PFN stored
+ * in the swap entry.  Please refers to is_pfn_swap_entry() for definition
+ * of pfn swap entry.
+ */
+static inline unsigned long swp_offset_pfn(swp_entry_t entry)
+{
+	VM_BUG_ON(!is_pfn_swap_entry(entry));
+	return swp_offset(entry) & SWP_PFN_MASK;
+}
+
 /* check whether a pte points to a swap entry */
 static inline int is_swap_pte(pte_t pte)
 {
@@ -369,7 +394,7 @@ static inline int pte_none_mostly(pte_t pte)
 
 static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
 {
-	struct page *p = pfn_to_page(swp_offset(entry));
+	struct page *p = pfn_to_page(swp_offset_pfn(entry));
 
 	/*
 	 * Any use of migration entries may only occur while the
@@ -387,6 +412,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
  */
 static inline bool is_pfn_swap_entry(swp_entry_t entry)
 {
+	/* Make sure the swp offset can always store the needed fields */
+	BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS);
+
 	return is_migration_entry(entry) || is_device_private_entry(entry) ||
 	       is_device_exclusive_entry(entry);
 }
@@ -475,11 +503,6 @@ static inline int is_hwpoison_entry(swp_entry_t entry)
 	return swp_type(entry) == SWP_HWPOISON;
 }
 
-static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry)
-{
-	return swp_offset(entry);
-}
-
 static inline void num_poisoned_pages_inc(void)
 {
 	atomic_long_inc(&num_poisoned_pages);

mm/hmm.c

@@ -253,7 +253,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
-			*hmm_pfn = swp_offset(entry) | cpu_flags;
+			*hmm_pfn = swp_offset_pfn(entry) | cpu_flags;
 			return 0;
 		}
 

mm/memory-failure.c

@@ -635,7 +635,7 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift,
 		swp_entry_t swp = pte_to_swp_entry(pte);
 
 		if (is_hwpoison_entry(swp))
-			pfn = hwpoison_entry_to_pfn(swp);
+			pfn = swp_offset_pfn(swp);
 	}
 
 	if (!pfn || pfn != poisoned_pfn)

mm/page_vma_mapped.c

@@ -86,7 +86,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 		    !is_device_exclusive_entry(entry))
 			return false;
 
-		pfn = swp_offset(entry);
+		pfn = swp_offset_pfn(entry);
 	} else if (is_swap_pte(*pvmw->pte)) {
 		swp_entry_t entry;
 
@@ -96,7 +96,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 		    !is_device_exclusive_entry(entry))
 			return false;
 
-		pfn = swp_offset(entry);
+		pfn = swp_offset_pfn(entry);
 	} else {
 		if (!pte_present(*pvmw->pte))
 			return false;
@@ -221,7 +221,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 					return not_found(pvmw);
 				entry = pmd_to_swp_entry(pmde);
 				if (!is_migration_entry(entry) ||
-				    !check_pmd(swp_offset(entry), pvmw))
+				    !check_pmd(swp_offset_pfn(entry), pvmw))
 					return not_found(pvmw);
 				return true;
 			}