Merge tag 'folio-5.18c' of git://git.infradead.org/users/willy/pagecache

Pull folio updates from Matthew Wilcox:

 - Rewrite how munlock works to massively reduce the contention on
   i_mmap_rwsem (Hugh Dickins):

     https://lore.kernel.org/linux-mm/8e4356d-9622-a7f0-b2c-f116b5f2efea@google.com/

 - Sort out the page refcount mess for ZONE_DEVICE pages (Christoph
   Hellwig):

     https://lore.kernel.org/linux-mm/20220210072828.2930359-1-hch@lst.de/

 - Convert GUP to use folios and make pincount available for order-1
   pages. (Matthew Wilcox)

 - Convert a few more truncation functions to use folios (Matthew
   Wilcox)

 - Convert page_vma_mapped_walk to use PFNs instead of pages (Matthew
   Wilcox)

 - Convert rmap_walk to use folios (Matthew Wilcox)

 - Convert most of shrink_page_list() to use a folio (Matthew Wilcox)

 - Add support for creating large folios in readahead (Matthew Wilcox)

* tag 'folio-5.18c' of git://git.infradead.org/users/willy/pagecache: (114 commits)
  mm/damon: minor cleanup for damon_pa_young
  selftests/vm/transhuge-stress: Support file-backed PMD folios
  mm/filemap: Support VM_HUGEPAGE for file mappings
  mm/readahead: Switch to page_cache_ra_order
  mm/readahead: Align file mappings for non-DAX
  mm/readahead: Add large folio readahead
  mm: Support arbitrary THP sizes
  mm: Make large folios depend on THP
  mm: Fix READ_ONLY_THP warning
  mm/filemap: Allow large folios to be added to the page cache
  mm: Turn can_split_huge_page() into can_split_folio()
  mm/vmscan: Convert pageout() to take a folio
  mm/vmscan: Turn page_check_references() into folio_check_references()
  mm/vmscan: Account large folios correctly
  mm/vmscan: Optimise shrink_page_list for non-PMD-sized folios
  mm/vmscan: Free non-shmem folios without splitting them
  mm/rmap: Constify the rmap_walk_control argument
  mm/rmap: Convert rmap_walk() to take a folio
  mm: Turn page_anon_vma() into folio_anon_vma()
  mm/rmap: Turn page_lock_anon_vma_read() into folio_lock_anon_vma_read()
  ...

Documentation/core-api/pin_user_pages.rst

@@ -55,18 +55,18 @@ flags the caller provides. The caller is required to pass in a non-null struct
 pages* array, and the function then pins pages by incrementing each by a special
 value: GUP_PIN_COUNTING_BIAS.
 
-For huge pages (and in fact, any compound page of more than 2 pages), the
-GUP_PIN_COUNTING_BIAS scheme is not used. Instead, an exact form of pin counting
-is achieved, by using the 3rd struct page in the compound page. A new struct
-page field, hpage_pinned_refcount, has been added in order to support this.
+For compound pages, the GUP_PIN_COUNTING_BIAS scheme is not used. Instead,
+an exact form of pin counting is achieved, by using the 2nd struct page
+in the compound page. A new struct page field, compound_pincount, has
+been added in order to support this.
 
 This approach for compound pages avoids the counting upper limit problems that
 are discussed below. Those limitations would have been aggravated severely by
 huge pages, because each tail page adds a refcount to the head page. And in
-fact, testing revealed that, without a separate hpage_pinned_refcount field,
+fact, testing revealed that, without a separate compound_pincount field,
 page overflows were seen in some huge page stress tests.
 
-This also means that huge pages and compound pages (of order > 1) do not suffer
+This also means that huge pages and compound pages do not suffer
 from the false positives problem that is mentioned below.::
 
  Function
@@ -264,9 +264,9 @@ place.)
 Other diagnostics
 =================
 
-dump_page() has been enhanced slightly, to handle these new counting fields, and
-to better report on compound pages in general. Specifically, for compound pages
-with order > 1, the exact (hpage_pinned_refcount) pincount is reported.
+dump_page() has been enhanced slightly, to handle these new counting
+fields, and to better report on compound pages in general. Specifically,
+for compound pages, the exact (compound_pincount) pincount is reported.
 
 References
 ==========

arch/alpha/include/asm/pgtable.h

@@ -233,6 +233,7 @@ pmd_page_vaddr(pmd_t pmd)
 	return ((pmd_val(pmd) & _PFN_MASK) >> (32-PAGE_SHIFT)) + PAGE_OFFSET;
 }
 
+#define pmd_pfn(pmd)	(pmd_val(pmd) >> 32)
 #define pmd_page(pmd)	(pfn_to_page(pmd_val(pmd) >> 32))
 #define pud_page(pud)	(pfn_to_page(pud_val(pud) >> 32))
 

arch/arc/include/asm/hugepage.h

@@ -31,7 +31,6 @@ static inline pmd_t pte_pmd(pte_t pte)
 
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
-#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 
 #define mk_pmd(page, prot)	pte_pmd(mk_pte(page, prot))

arch/arc/include/asm/pgtable-levels.h

@@ -161,6 +161,7 @@
 #define pmd_present(x)		(pmd_val(x))
 #define pmd_clear(xp)		do { pmd_val(*(xp)) = 0; } while (0)
 #define pmd_page_vaddr(pmd)	(pmd_val(pmd) & PAGE_MASK)
+#define pmd_pfn(pmd)		((pmd_val(pmd) & PAGE_MASK) >> PAGE_SHIFT)
 #define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
 #define set_pmd(pmdp, pmd)	(*(pmdp) = pmd)
 #define pmd_pgtable(pmd)	((pgtable_t) pmd_page_vaddr(pmd))

arch/arm/include/asm/pgtable-2level.h

@@ -208,6 +208,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 }
 #define pmd_offset pmd_offset
 
+#define pmd_pfn(pmd)		(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+
 #define pmd_large(pmd)		(pmd_val(pmd) & 2)
 #define pmd_leaf(pmd)		(pmd_val(pmd) & 2)
 #define pmd_bad(pmd)		(pmd_val(pmd) & 2)

arch/arm64/mm/mmu.c

@@ -17,6 +17,7 @@
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
+#include <linux/memremap.h>
 #include <linux/memory.h>
 #include <linux/fs.h>
 #include <linux/io.h>

arch/csky/include/asm/pgtable.h

@@ -30,6 +30,7 @@
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
+#define pmd_pfn(pmd)	(pmd_phys(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)	(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
 #define pte_clear(mm, addr, ptep)	set_pte((ptep), \
 	(((unsigned int) addr >= PAGE_OFFSET) ? __pte(_PAGE_GLOBAL) : __pte(0)))

arch/hexagon/include/asm/pgtable.h

@@ -235,6 +235,11 @@ static inline int pmd_bad(pmd_t pmd)
 	return 0;
 }
 
+/*
+ * pmd_pfn - converts a PMD entry to a page frame number
+ */
+#define pmd_pfn(pmd)  (pmd_val(pmd) >> PAGE_SHIFT)
+
 /*
  * pmd_page - converts a PMD entry to a page pointer
  */

arch/ia64/include/asm/pgtable.h

@@ -267,6 +267,7 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pmd_present(pmd)		(pmd_val(pmd) != 0UL)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
 #define pmd_page_vaddr(pmd)		((unsigned long) __va(pmd_val(pmd) & _PFN_MASK))
+#define pmd_pfn(pmd)			((pmd_val(pmd) & _PFN_MASK) >> PAGE_SHIFT)
 #define pmd_page(pmd)			virt_to_page((pmd_val(pmd) + PAGE_OFFSET))
 
 #define pud_none(pud)			(!pud_val(pud))

arch/m68k/include/asm/mcf_pgtable.h

@@ -322,6 +322,7 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	(__pte((x).val))
 
+#define pmd_pfn(pmd)		(pmd_val(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
 
 #define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))

arch/m68k/include/asm/motorola_pgtable.h

@@ -147,6 +147,7 @@ static inline void pud_set(pud_t *pudp, pmd_t *pmdp)
 #define pmd_present(pmd)	(pmd_val(pmd) & _PAGE_TABLE)
 #define pmd_clear(pmdp)		({ pmd_val(*pmdp) = 0; })
 
+#define pmd_pfn(pmd)		((pmd_val(pmd) & _TABLE_MASK) >> PAGE_SHIFT)
 /*
  * m68k does not have huge pages (020/030 actually could), but generic code
  * expects pmd_page() to exists, only to then DCE it all. Provide a dummy to

arch/m68k/include/asm/sun3_pgtable.h

@@ -130,6 +130,7 @@ static inline void pte_clear (struct mm_struct *mm, unsigned long addr, pte_t *p
 ({ pte_t __pte; pte_val(__pte) = pfn | pgprot_val(pgprot); __pte; })
 
 #define pte_page(pte)		virt_to_page(__pte_page(pte))
+#define pmd_pfn(pmd)		(pmd_val(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
 
 

arch/microblaze/include/asm/pgtable.h

@@ -399,6 +399,9 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 	return ((unsigned long) (pmd_val(pmd) & PAGE_MASK));
 }
 
+/* returns pfn of the pmd entry*/
+#define pmd_pfn(pmd)	(__pa(pmd_val(pmd)) >> PAGE_SHIFT)
+
 /* returns struct *page of the pmd entry*/
 #define pmd_page(pmd)	(pfn_to_page(__pa(pmd_val(pmd)) >> PAGE_SHIFT))
 

arch/mips/include/asm/pgtable.h

@@ -86,6 +86,11 @@ extern void paging_init(void);
  */
 #define pmd_phys(pmd)		virt_to_phys((void *)pmd_val(pmd))
 
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	return pmd_val(pmd) >> _PFN_SHIFT;
+}
+
 #ifndef CONFIG_MIPS_HUGE_TLB_SUPPORT
 #define pmd_page(pmd)		(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
 #endif /* CONFIG_MIPS_HUGE_TLB_SUPPORT */
@@ -422,11 +427,6 @@ static inline int pmd_write(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_WRITE);
 }
 
-static inline unsigned long pmd_pfn(pmd_t pmd)
-{
-	return pmd_val(pmd) >> _PFN_SHIFT;
-}
-
 static inline struct page *pmd_page(pmd_t pmd)
 {
 	if (pmd_val(pmd) & _PAGE_HUGE)

arch/nds32/include/asm/pgtable.h

@@ -308,6 +308,7 @@ static inline pmd_t __mk_pmd(pte_t * ptep, unsigned long prot)
 	return pmd;
 }
 
+#define pmd_pfn(pmd)	     (pmd_val(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)        virt_to_page(__va(pmd_val(pmd)))
 
 /*

arch/nios2/include/asm/pgtable.h

@@ -235,6 +235,7 @@ static inline void pte_clear(struct mm_struct *mm,
  * and a page entry and page directory to the page they refer to.
  */
 #define pmd_phys(pmd)		virt_to_phys((void *)pmd_val(pmd))
+#define pmd_pfn(pmd)		(pmd_phys(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)		(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
 
 static inline unsigned long pmd_page_vaddr(pmd_t pmd)

arch/openrisc/include/asm/pgtable.h

@@ -361,6 +361,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 	pmd_val(*pmdp) = _KERNPG_TABLE | (unsigned long) ptep;
 }
 
+#define pmd_pfn(pmd)		(pmd_val(pmd) >> PAGE_SHIFT)
 #define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
 
 static inline unsigned long pmd_page_vaddr(pmd_t pmd)

arch/parisc/include/asm/pgtable.h

@@ -408,6 +408,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 	return ((unsigned long) __va(pmd_address(pmd)));
 }
 
+#define pmd_pfn(pmd)	(pmd_address(pmd) >> PAGE_SHIFT)
 #define __pmd_page(pmd) ((unsigned long) __va(pmd_address(pmd)))
 #define pmd_page(pmd)	virt_to_page((void *)__pmd_page(pmd))
 

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -372,8 +372,8 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
 
-#define pmd_page(pmd)		\
-	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+#define pmd_pfn(pmd)		(pmd_val(pmd) >> PAGE_SHIFT)
+#define pmd_page(pmd)		pfn_to_page(pmd_pfn(pmd))
 
 /*
  * Encode and decode a swap entry.

arch/powerpc/include/asm/mmu_context.h

@@ -21,7 +21,6 @@ extern void destroy_context(struct mm_struct *mm);
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 struct mm_iommu_table_group_mem_t;
 
-extern int isolate_lru_page(struct page *page);	/* from internal.h */
 extern bool mm_iommu_preregistered(struct mm_struct *mm);
 extern long mm_iommu_new(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries,