[RFC PATCH 03/18] fs/dax: use ptdesc in dax_pmd_load_hole

[RFC PATCH 03/18] fs/dax: use ptdesc in dax_pmd_load_hole

[alexs]

From: Alex Shi <alexs@kernel.org>

Since we have ptdesc struct now, better to use replace pgtable_t, aka
'struct page *'.
It's a prepare for return ptdesc pointer in pte_alloc_one series
function.

Signed-off-by: Alex Shi <alexs@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: nvdimm@lists.linux.dev
Cc: linux-fsdevel@vger.kernel.org
Cc: Christian Brauner <brauner@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
---
 fs/dax.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index becb4a6920c6..6f7cea248206 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1206,7 +1206,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = mapping->host;
-	pgtable_t pgtable = NULL;
+	struct ptdesc *ptdesc = NULL;
 	struct folio *zero_folio;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
@@ -1222,8 +1222,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 				  DAX_PMD | DAX_ZERO_PAGE);
 
 	if (arch_needs_pgtable_deposit()) {
-		pgtable = pte_alloc_one(vma->vm_mm);
-		if (!pgtable)
+		ptdesc = page_ptdesc(pte_alloc_one(vma->vm_mm));
+		if (!ptdesc)
 			return VM_FAULT_OOM;
 	}
 
@@ -1233,8 +1233,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 		goto fallback;
 	}
 
-	if (pgtable) {
-		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+	if (ptdesc) {
+		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, ptdesc_page(ptdesc));
 		mm_inc_nr_ptes(vma->vm_mm);
 	}
 	pmd_entry = mk_pmd(&zero_folio->page, vmf->vma->vm_page_prot);
@@ -1245,8 +1245,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	return VM_FAULT_NOPAGE;
 
 fallback:
-	if (pgtable)
-		pte_free(vma->vm_mm, pgtable);
+	if (ptdesc)
+		pte_free(vma->vm_mm, ptdesc_page(ptdesc));
 	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_folio, *entry);
 	return VM_FAULT_FALLBACK;
 }
-- 
2.43.0

[RFC PATCH 09/18] mm/pgtable: fully use ptdesc in pte_alloc_one series functions

[alexs]

From: Alex Shi <alexs@kernel.org>

Replace pgtable_t and struct page by ptdesc in pte_alloc_one series
functions.

Signed-off-by: Alex Shi <alexs@kernel.org>
Cc: linux-mm@kvack.org
Cc: linux-arch@vger.kernel.org
Cc: nvdimm@lists.linux.dev
Cc: linux-fsdevel@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: Dawei Li <dawei.li@shingroup.cn>
Cc: Vishal Moola  <vishal.moola@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Breno Leitao <leitao@debian.org>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Mike Rapoport  <rppt@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
---
 arch/arm/include/asm/pgalloc.h      |  9 ++++-----
 arch/powerpc/include/asm/pgalloc.h  |  4 ++--
 arch/s390/include/asm/pgalloc.h     |  2 +-
 arch/sparc/include/asm/pgalloc_32.h |  2 +-
 arch/sparc/include/asm/pgalloc_64.h |  2 +-
 arch/sparc/mm/init_64.c             |  2 +-
 arch/sparc/mm/srmmu.c               |  4 ++--
 arch/x86/include/asm/pgalloc.h      |  2 +-
 arch/x86/mm/pgtable.c               |  2 +-
 arch/xtensa/include/asm/pgalloc.h   | 12 ++++++------
 fs/dax.c                            |  2 +-
 include/asm-generic/pgalloc.h       |  6 +++---
 mm/huge_memory.c                    |  8 ++++----
 mm/memory.c                         |  8 ++++----
 14 files changed, 32 insertions(+), 33 deletions(-)

diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index a17f01235c29..e8501a6c3336 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -91,16 +91,15 @@ pte_alloc_one_kernel(struct mm_struct *mm)
 #define PGTABLE_HIGHMEM 0
 #endif
 
-static inline pgtable_t
-pte_alloc_one(struct mm_struct *mm)
+static inline struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 {
-	struct page *pte;
+	struct ptdesc *pte;
 
 	pte = __pte_alloc_one(mm, GFP_PGTABLE_USER | PGTABLE_HIGHMEM);
 	if (!pte)
 		return NULL;
-	if (!PageHighMem(pte))
-		clean_pte_table(page_address(pte));
+	if (!PageHighMem(ptdesc_page(pte)))
+		clean_pte_table(ptdesc_address(pte));
 	return pte;
 }
 
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 3a971e2a8c73..37512f344b37 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -27,9 +27,9 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	return (pte_t *)pte_fragment_alloc(mm, 1);
 }
 
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+static inline struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 {
-	return (pgtable_t)pte_fragment_alloc(mm, 0);
+	return (struct ptdesc *)pte_fragment_alloc(mm, 0);
 }
 
 void pte_frag_destroy(void *pte_frag);
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 7b84ef6dc4b6..771494526f6e 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -137,7 +137,7 @@ static inline void pmd_populate(struct mm_struct *mm,
  * page table entry allocation/free routines.
  */
 #define pte_alloc_one_kernel(mm) ((pte_t *)page_table_alloc(mm))
-#define pte_alloc_one(mm) ((pte_t *)page_table_alloc(mm))
+#define pte_alloc_one(mm) ((struct ptdesc *)page_table_alloc(mm))
 
 #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
 #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index 4f73e87b22a3..bc3ef54d9564 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -55,7 +55,7 @@ static inline void free_pmd_fast(pmd_t * pmd)
 void pmd_set(pmd_t *pmdp, pte_t *ptep);
 #define pmd_populate_kernel		pmd_populate
 
-pgtable_t pte_alloc_one(struct mm_struct *mm);
+struct ptdesc *pte_alloc_one(struct mm_struct *mm);
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index caa7632be4c2..285aa7958912 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -61,7 +61,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 }
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
-pgtable_t pte_alloc_one(struct mm_struct *mm);
+struct ptdesc *pte_alloc_one(struct mm_struct *mm);
 void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
 void pte_free(struct mm_struct *mm, pgtable_t ptepage);
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 53d7cb5bbffe..e1b33f996469 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2900,7 +2900,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	return pte;
 }
 
-pgtable_t pte_alloc_one(struct mm_struct *mm)
+struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 {
 	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL | __GFP_ZERO, 0);
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 9df51a62333d..60bb8628bb1f 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -346,7 +346,7 @@ pgd_t *get_pgd_fast(void)
  * Alignments up to the page size are the same for physical and virtual
  * addresses of the nocache area.
  */
-pgtable_t pte_alloc_one(struct mm_struct *mm)
+struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 {
 	pte_t *ptep;
 	struct page *page;
@@ -362,7 +362,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
 	}
 	spin_unlock(&mm->page_table_lock);
 
-	return ptep;
+	return (struct ptdesc *)ptep;
 }
 
 void pte_free(struct mm_struct *mm, pgtable_t ptep)
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dcd836b59beb..497c757b5b98 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -51,7 +51,7 @@ extern gfp_t __userpte_alloc_gfp;
 extern pgd_t *pgd_alloc(struct mm_struct *);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
-extern pgtable_t pte_alloc_one(struct mm_struct *);
+extern struct ptdesc *pte_alloc_one(struct mm_struct *);
 
 extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 93e54ba91fbf..c27d15cd01b9 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -28,7 +28,7 @@ void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
 
 gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
 
-pgtable_t pte_alloc_one(struct mm_struct *mm)
+struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 {
 	return __pte_alloc_one(mm, __userpte_alloc_gfp);
 }
diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index 7fc0f9126dd3..a9206c02956e 100644
--- a/arch/xtensa/include/asm/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
@@ -51,15 +51,15 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	return ptep;
 }
 
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+static inline struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 {
-	struct page *page;
+	struct ptdesc *ptdesc;
 
-	page = __pte_alloc_one(mm, GFP_PGTABLE_USER);
-	if (!page)
+	ptdesc = __pte_alloc_one(mm, GFP_PGTABLE_USER);
+	if (!ptdesc)
 		return NULL;
-	ptes_clear(page_address(page));
-	return page;
+	ptes_clear(ptdesc_address(ptdesc));
+	return ptdesc;
 }
 
 #endif /* CONFIG_MMU */
diff --git a/fs/dax.c b/fs/dax.c
index 6f7cea248206..51cbc08b22e7 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1222,7 +1222,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 				  DAX_PMD | DAX_ZERO_PAGE);
 
 	if (arch_needs_pgtable_deposit()) {
-		ptdesc = page_ptdesc(pte_alloc_one(vma->vm_mm));
+		ptdesc = pte_alloc_one(vma->vm_mm);
 		if (!ptdesc)
 			return VM_FAULT_OOM;
 	}
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 7c48f5fbf8aa..1a4070f8d5dd 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -63,7 +63,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
  *
  * Return: `struct page` referencing the ptdesc or %NULL on error
  */
-static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
+static inline struct ptdesc *__pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
 {
 	struct ptdesc *ptdesc;
 
@@ -75,7 +75,7 @@ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
 		return NULL;
 	}
 
-	return ptdesc_page(ptdesc);
+	return ptdesc;
 }
 #define __pte_alloc_one(...)	alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__))
 
@@ -88,7 +88,7 @@ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
  *
  * Return: `struct page` referencing the ptdesc or %NULL on error
  */
-static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm)
+static inline struct ptdesc *pte_alloc_one_noprof(struct mm_struct *mm)
 {
 	return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER);
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 236e1582d97e..6274eb7559ac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -959,7 +959,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 	}
 	folio_throttle_swaprate(folio, gfp);
 
-	ptdesc = page_ptdesc(pte_alloc_one(vma->vm_mm));
+	ptdesc = pte_alloc_one(vma->vm_mm);
 	if (unlikely(!ptdesc)) {
 		ret = VM_FAULT_OOM;
 		goto release;
@@ -1091,7 +1091,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		struct folio *zero_folio;
 		vm_fault_t ret;
 
-		ptdesc = page_ptdesc(pte_alloc_one(vma->vm_mm));
+		ptdesc = pte_alloc_one(vma->vm_mm);
 		if (unlikely(!ptdesc))
 			return VM_FAULT_OOM;
 		zero_folio = mm_get_huge_zero_folio(vma->vm_mm);
@@ -1213,7 +1213,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 		return VM_FAULT_SIGBUS;
 
 	if (arch_needs_pgtable_deposit()) {
-		ptdesc = page_ptdesc(pte_alloc_one(vma->vm_mm));
+		ptdesc = pte_alloc_one(vma->vm_mm);
 		if (!ptdesc)
 			return VM_FAULT_OOM;
 	}
@@ -1376,7 +1376,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (!vma_is_anonymous(dst_vma))
 		return 0;
 
-	ptdesc = page_ptdesc(pte_alloc_one(dst_mm));
+	ptdesc = pte_alloc_one(dst_mm);
 	if (unlikely(!ptdesc))
 		goto out;
 
diff --git a/mm/memory.c b/mm/memory.c
index 5b01d94a0b5f..37529e0a9ce2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -445,7 +445,7 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
 
 int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
 {
-	struct ptdesc *ptdesc = page_ptdesc(pte_alloc_one(mm));
+	struct ptdesc *ptdesc = pte_alloc_one(mm);
 	if (!ptdesc)
 		return -ENOMEM;
 
@@ -4647,7 +4647,7 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 	 *				# flush A, B to clear the writeback
 	 */
 	if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) {
-		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
+		vmf->prealloc_pte = ptdesc_page(pte_alloc_one(vma->vm_mm));
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 	}
@@ -4725,7 +4725,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	 * related to pte entry. Use the preallocated table for that.
 	 */
 	if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
-		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
+		vmf->prealloc_pte = ptdesc_page(pte_alloc_one(vma->vm_mm));
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 	}
@@ -5010,7 +5010,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 		      pte_off + vma_pages(vmf->vma) - vma_off) - 1;
 
 	if (pmd_none(*vmf->pmd)) {
-		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
+		vmf->prealloc_pte = ptdesc_page(pte_alloc_one(vmf->vma->vm_mm));
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 	}
-- 
2.43.0

[RFC PATCH 10/18] mm/pgtable: pass ptdesc to pte_free()

[alexs]

From: Alex Shi <alexs@kernel.org>

Now we could remove couple of page<->ptdesc converters now.

Signed-off-by: Alex Shi <alexs@kernel.org>
Cc: linux-mm@kvack.org
Cc: linux-arch@vger.kernel.org
Cc: nvdimm@lists.linux.dev
Cc: linux-fsdevel@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Vishal Moola  <vishal.moola@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Mike Rapoport  <rppt@kernel.org>
Cc: Dawei Li <dawei.li@shingroup.cn>
Cc: Hugh Dickins <hughd@google.com>
---
 arch/arm/mm/pgd.c                            |  2 +-
 arch/m68k/include/asm/motorola_pgalloc.h     |  4 ++--
 arch/powerpc/include/asm/book3s/64/pgalloc.h |  2 +-
 arch/powerpc/include/asm/pgalloc.h           |  2 +-
 arch/sparc/include/asm/pgalloc_32.h          |  2 +-
 arch/sparc/mm/srmmu.c                        |  2 +-
 fs/dax.c                                     |  2 +-
 include/asm-generic/pgalloc.h                |  4 +---
 mm/debug_vm_pgtable.c                        |  2 +-
 mm/huge_memory.c                             | 20 ++++++++++----------
 mm/memory.c                                  |  4 ++--
 mm/pgtable-generic.c                         |  2 +-
 12 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index f8e9bc58a84f..c384b734d752 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -168,7 +168,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 
 	pte = pmd_pgtable(*pmd);
 	pmd_clear(pmd);
-	pte_free(mm, pte);
+	pte_free(mm, page_ptdesc(pte));
 	mm_dec_nr_ptes(mm);
 no_pmd:
 	pud_clear(pud);
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 74a817d9387f..f6bb375971dc 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -39,9 +39,9 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
 	return get_pointer_table(TABLE_PTE);
 }
 
-static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable)
+static inline void pte_free(struct mm_struct *mm, struct ptdesc *ptdesc)
 {
-	free_pointer_table(pgtable, TABLE_PTE);
+	free_pointer_table(ptdesc_page(ptdesc), TABLE_PTE);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable,
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index dd2cff53a111..eb7d2ca59f62 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -162,7 +162,7 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-				pgtable_t pte_page)
+				struct ptdesc *pte_page)
 {
 	*pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS);
 }
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 37512f344b37..12520521163e 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -40,7 +40,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 	pte_fragment_free((unsigned long *)pte, 1);
 }
 
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+static inline void pte_free(struct mm_struct *mm, struct ptdesc *ptepage)
 {
 	pte_fragment_free((unsigned long *)ptepage, 0);
 }
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index bc3ef54d9564..addaade56f21 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -71,7 +71,7 @@ static inline void free_pte_fast(pte_t *pte)
 
 #define pte_free_kernel(mm, pte)	free_pte_fast(pte)
 
-void pte_free(struct mm_struct * mm, pgtable_t pte);
+void pte_free(struct mm_struct *mm, struct ptdesc *pte);
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
 
 #endif /* _SPARC_PGALLOC_H */
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 60bb8628bb1f..05be7d86eda3 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -365,7 +365,7 @@ struct ptdesc *pte_alloc_one(struct mm_struct *mm)
 	return (struct ptdesc *)ptep;
 }
 
-void pte_free(struct mm_struct *mm, pgtable_t ptep)
+void pte_free(struct mm_struct *mm, struct ptdesc *ptep)
 {
 	struct page *page;
 
diff --git a/fs/dax.c b/fs/dax.c
index 51cbc08b22e7..61b9bd5200da 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1246,7 +1246,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 
 fallback:
 	if (ptdesc)
-		pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+		pte_free(vma->vm_mm, ptdesc);
 	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_folio, *entry);
 	return VM_FAULT_FALLBACK;
 }
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 1a4070f8d5dd..5f249ec9d289 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -105,10 +105,8 @@ static inline struct ptdesc *pte_alloc_one_noprof(struct mm_struct *mm)
  * @mm: the mm_struct of the current context
  * @pte_page: the `struct page` referencing the ptdesc
  */
-static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
+static inline void pte_free(struct mm_struct *mm, struct ptdesc *ptdesc)
 {
-	struct ptdesc *ptdesc = page_ptdesc(pte_page);
-
 	pagetable_pte_dtor(ptdesc);
 	pagetable_free(ptdesc);
 }
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index e4969fb54da3..f256bc816744 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -1049,7 +1049,7 @@ static void __init destroy_args(struct pgtable_debug_args *args)
 
 	/* Free page table entries */
 	if (args->start_ptep) {
-		pte_free(args->mm, args->start_ptep);
+		pte_free(args->mm, page_ptdesc(args->start_ptep));
 		mm_dec_nr_ptes(args->mm);
 	}
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6274eb7559ac..dc323453fa02 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -987,7 +987,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		if (userfaultfd_missing(vma)) {
 			spin_unlock(vmf->ptl);
 			folio_put(folio);
-			pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+			pte_free(vma->vm_mm, ptdesc);
 			ret = handle_userfault(vmf, VM_UFFD_MISSING);
 			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			return ret;
@@ -1013,7 +1013,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 	spin_unlock(vmf->ptl);
 release:
 	if (ptdesc)
-		pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+		pte_free(vma->vm_mm, ptdesc);
 	folio_put(folio);
 	return ret;
 
@@ -1096,7 +1096,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			return VM_FAULT_OOM;
 		zero_folio = mm_get_huge_zero_folio(vma->vm_mm);
 		if (unlikely(!zero_folio)) {
-			pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+			pte_free(vma->vm_mm, ptdesc);
 			count_vm_event(THP_FAULT_FALLBACK);
 			return VM_FAULT_FALLBACK;
 		}
@@ -1106,10 +1106,10 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			ret = check_stable_address_space(vma->vm_mm);
 			if (ret) {
 				spin_unlock(vmf->ptl);
-				pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+				pte_free(vma->vm_mm, ptdesc);
 			} else if (userfaultfd_missing(vma)) {
 				spin_unlock(vmf->ptl);
-				pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+				pte_free(vma->vm_mm, ptdesc);
 				ret = handle_userfault(vmf, VM_UFFD_MISSING);
 				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			} else {
@@ -1120,7 +1120,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			}
 		} else {
 			spin_unlock(vmf->ptl);
-			pte_free(vma->vm_mm, ptdesc_page(ptdesc));
+			pte_free(vma->vm_mm, ptdesc);
 		}
 		return ret;
 	}
@@ -1178,7 +1178,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 out_unlock:
 	spin_unlock(ptl);
 	if (ptdesc)
-		pte_free(mm, ptdesc_page(ptdesc));
+		pte_free(mm, ptdesc);
 }
 
 /**
@@ -1414,7 +1414,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 #endif
 
 	if (unlikely(!pmd_trans_huge(pmd))) {
-		pte_free(dst_mm, ptdesc_page(ptdesc));
+		pte_free(dst_mm, ptdesc);
 		goto out_unlock;
 	}
 	/*
@@ -1440,7 +1440,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, src_vma))) {
 		/* Page maybe pinned: split and retry the fault on PTEs. */
 		folio_put(src_folio);
-		pte_free(dst_mm, ptdesc_page(ptdesc));
+		pte_free(dst_mm, ptdesc);
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
 		__split_huge_pmd(src_vma, src_pmd, addr, false, NULL);
@@ -1830,7 +1830,7 @@ static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
 	pgtable_t pgtable;
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
-	pte_free(mm, pgtable);
+	pte_free(mm, page_ptdesc(pgtable));
 	mm_dec_nr_ptes(mm);
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 37529e0a9ce2..3014168e7296 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -451,7 +451,7 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
 
 	pmd_install(mm, pmd, (pgtable_t *)&ptdesc);
 	if (ptdesc)
-		pte_free(mm, ptdesc_page(ptdesc));
+		pte_free(mm, ptdesc);
 	return 0;
 }
 
@@ -5196,7 +5196,7 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 
 	/* preallocated pagetable is unused: free it */
 	if (vmf->prealloc_pte) {
-		pte_free(vm_mm, vmf->prealloc_pte);
+		pte_free(vm_mm, page_ptdesc(vmf->prealloc_pte));
 		vmf->prealloc_pte = NULL;
 	}
 	return ret;
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index f34a8d115f5b..92245a32656b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -241,7 +241,7 @@ static void pte_free_now(struct rcu_head *head)
 	struct ptdesc *ptdesc;
 
 	ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
-	pte_free(NULL /* mm not passed and not used */, (pgtable_t)ptdesc);
+	pte_free(NULL /* mm not passed and not used */, ptdesc);
 }
 
 void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
-- 
2.43.0

[RFC PATCH 14/18] mm/pgtable: use ptdesc in pgtable_trans_huge_deposit

[alexs]

From: Alex Shi <alexs@kernel.org>

A step to replace pgtable_t to struct ptdesc.

Signed-off-by: Alex Shi <alexs@kernel.org>
Cc: linux-mm@kvack.org
Cc: nvdimm@lists.linux.dev
Cc: linux-fsdevel@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Barry Song <baohua@kernel.org>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kinsey Ho <kinseyho@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar K.V  <aneesh.kumar@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jan Kara <jack@suse.cz>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Mike Rapoport  <rppt@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h |  6 +++---
 arch/powerpc/mm/book3s64/hash_pgtable.c      |  6 +++---
 arch/powerpc/mm/book3s64/radix_pgtable.c     |  6 +++---
 arch/s390/include/asm/pgtable.h              |  2 +-
 arch/s390/mm/pgtable.c                       |  6 +++---
 arch/sparc/include/asm/pgtable_64.h          |  2 +-
 arch/sparc/mm/tlb.c                          |  6 +++---
 fs/dax.c                                     |  2 +-
 include/linux/pgtable.h                      |  2 +-
 mm/debug_vm_pgtable.c                        |  2 +-
 mm/huge_memory.c                             | 14 +++++++-------
 mm/khugepaged.c                              |  2 +-
 mm/memory.c                                  |  2 +-
 mm/pgtable-generic.c                         |  8 ++++----
 14 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 0ee440b819d7..cf44e2440825 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1365,11 +1365,11 @@ pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma,
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 static inline void pgtable_trans_huge_deposit(struct mm_struct *mm,
-					      pmd_t *pmdp, pgtable_t pgtable)
+					      pmd_t *pmdp, struct ptdesc *ptdesc)
 {
 	if (radix_enabled())
-		return radix__pgtable_trans_huge_deposit(mm, pmdp, pgtable);
-	return hash__pgtable_trans_huge_deposit(mm, pmdp, pgtable);
+		return radix__pgtable_trans_huge_deposit(mm, pmdp, ptdesc);
+	return hash__pgtable_trans_huge_deposit(mm, pmdp, ptdesc);
 }
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c
index 35562d1f4267..8fd2c833dc3d 100644
--- a/arch/powerpc/mm/book3s64/hash_pgtable.c
+++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
@@ -265,16 +265,16 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres
  * the base page size hptes
  */
 void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				  pgtable_t pgtable)
+				      struct ptdesc *ptdesc)
 {
-	pgtable_t *pgtable_slot;
+	pte_t **pgtable_slot;
 
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 	/*
 	 * we store the pgtable in the second half of PMD
 	 */
 	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
-	*pgtable_slot = pgtable;
+	*pgtable_slot = (pte_t)ptdesc;
 	/*
 	 * expose the deposited pgtable to other cpus.
 	 * before we set the hugepage PTE at pmd level
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 3b9bb19510e3..c33e860966ad 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1478,9 +1478,9 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre
  * list_head memory area.
  */
 void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				 pgtable_t pgtable)
+				       struct ptdesc *ptdesc)
 {
-	struct list_head *lh = (struct list_head *) pgtable;
+	struct list_head *lh = (struct list_head *)ptdesc;
 
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
@@ -1489,7 +1489,7 @@ void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 		INIT_LIST_HEAD(lh);
 	else
 		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
-	pmd_huge_pte(mm, pmdp) = pgtable;
+	pmd_huge_pte(mm, pmdp) = ptdesc_page(ptdesc);
 }
 
 struct ptdesc *radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index cf0baf4bfe5c..d7b635f5e1e7 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1735,7 +1735,7 @@ pud_t pudp_xchg_direct(struct mm_struct *, unsigned long, pud_t *, pud_t);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pgtable);
+				struct ptdesc *ptdesc);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
 struct ptdesc *pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b9016ee145cb..cf1a6aeb66d4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -563,9 +563,9 @@ EXPORT_SYMBOL(pudp_xchg_direct);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pgtable)
+				struct ptdesc *ptdesc)
 {
-	struct list_head *lh = (struct list_head *) pgtable;
+	struct list_head *lh = (struct list_head *)ptdesc;
 
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
@@ -574,7 +574,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 		INIT_LIST_HEAD(lh);
 	else
 		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
-	pmd_huge_pte(mm, pmdp) = (struct ptdesc *)pgtable;
+	pmd_huge_pte(mm, pmdp) = ptdesc;
 }
 
 struct ptdesc *pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index bfefd678e220..c71be5ef8b06 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -995,7 +995,7 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pgtable);
+				struct ptdesc *ptdesc);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
 struct ptdesc *pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index bd2d3b1f6ba3..eeed4427f524 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -267,9 +267,9 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 }
 
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pgtable)
+				struct ptdesc *ptdesc)
 {
-	struct list_head *lh = (struct list_head *) pgtable;
+	struct list_head *lh = (struct list_head *)ptdesc;
 
 	assert_spin_locked(&mm->page_table_lock);
 
@@ -278,7 +278,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 		INIT_LIST_HEAD(lh);
 	else
 		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
-	pmd_huge_pte(mm, pmdp) = (struct ptdesc *)pgtable;
+	pmd_huge_pte(mm, pmdp) = ptdesc;
 }
 
 struct ptdesc *pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
diff --git a/fs/dax.c b/fs/dax.c
index 61b9bd5200da..4b4e6acb0efc 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1234,7 +1234,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	}
 
 	if (ptdesc) {
-		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, ptdesc_page(ptdesc));
+		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, ptdesc);
 		mm_inc_nr_ptes(vma->vm_mm);
 	}
 	pmd_entry = mk_pmd(&zero_folio->page, vmf->vma->vm_page_prot);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 3fa7b93580a3..9d256c548f5e 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -925,7 +925,7 @@ static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				       pgtable_t pgtable);
+				       struct ptdesc *ptdesc);
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index f256bc816744..8550eec32aba 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -225,7 +225,7 @@ static void __init pmd_advanced_tests(struct pgtable_debug_args *args)
 	/* Align the address wrt HPAGE_PMD_SIZE */
 	vaddr &= HPAGE_PMD_MASK;
 
-	pgtable_trans_huge_deposit(args->mm, args->pmdp, args->start_ptep);
+	pgtable_trans_huge_deposit(args->mm, args->pmdp, page_ptdesc(args->start_ptep));
 
 	pmd = pfn_pmd(args->pmd_pfn, args->page_prot);
 	set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4dc36910c8aa..aac67e8a8cc8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -997,7 +997,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
 		folio_add_lru_vma(folio, vma);
-		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, ptdesc_page(ptdesc));
+		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, ptdesc);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
@@ -1064,7 +1064,7 @@ static void set_huge_zero_folio(struct ptdesc *ptdesc, struct mm_struct *mm,
 		return;
 	entry = mk_pmd(&zero_folio->page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
-	pgtable_trans_huge_deposit(mm, pmd, ptdesc_page(ptdesc));
+	pgtable_trans_huge_deposit(mm, pmd, ptdesc);
 	set_pmd_at(mm, haddr, pmd, entry);
 	mm_inc_nr_ptes(mm);
 }
@@ -1167,7 +1167,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	}
 
 	if (ptdesc) {
-		pgtable_trans_huge_deposit(mm, pmd, ptdesc_page(ptdesc));
+		pgtable_trans_huge_deposit(mm, pmd, ptdesc);
 		mm_inc_nr_ptes(mm);
 		ptdesc = NULL;
 	}
@@ -1404,7 +1404,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		}
 		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm_inc_nr_ptes(dst_mm);
-		pgtable_trans_huge_deposit(dst_mm, dst_pmd, ptdesc_page(ptdesc));
+		pgtable_trans_huge_deposit(dst_mm, dst_pmd, ptdesc);
 		if (!userfaultfd_wp(dst_vma))
 			pmd = pmd_swp_clear_uffd_wp(pmd);
 		set_pmd_at(dst_mm, addr, dst_pmd, pmd);
@@ -1449,7 +1449,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 out_zero_page:
 	mm_inc_nr_ptes(dst_mm);
-	pgtable_trans_huge_deposit(dst_mm, dst_pmd, ptdesc_page(ptdesc));
+	pgtable_trans_huge_deposit(dst_mm, dst_pmd, ptdesc);
 	pmdp_set_wrprotect(src_mm, addr, src_pmd);
 	if (!userfaultfd_wp(dst_vma))
 		pmd = pmd_clear_uffd_wp(pmd);
@@ -1962,7 +1962,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			struct ptdesc *ptdesc;
 
 			ptdesc = pgtable_trans_huge_withdraw(mm, old_pmd);
-			pgtable_trans_huge_deposit(mm, new_pmd, ptdesc_page(ptdesc));
+			pgtable_trans_huge_deposit(mm, new_pmd, ptdesc);
 		}
 		pmd = move_soft_dirty_pmd(pmd);
 		set_pmd_at(mm, new_addr, new_pmd, pmd);
@@ -2236,7 +2236,7 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm
 	set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd);
 
 	src_ptdesc = pgtable_trans_huge_withdraw(mm, src_pmd);
-	pgtable_trans_huge_deposit(mm, dst_pmd, ptdesc_page(src_ptdesc));
+	pgtable_trans_huge_deposit(mm, dst_pmd, src_ptdesc);
 unlock_ptls:
 	double_pt_unlock(src_ptl, dst_ptl);
 	if (src_anon_vma) {
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index f3b3db104615..48a54269472e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1232,7 +1232,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	BUG_ON(!pmd_none(*pmd));
 	folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
 	folio_add_lru_vma(folio, vma);
-	pgtable_trans_huge_deposit(mm, pmd, pgtable);
+	pgtable_trans_huge_deposit(mm, pmd, page_ptdesc(pgtable));
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
 	spin_unlock(pmd_ptl);
diff --git a/mm/memory.c b/mm/memory.c
index 27c2f63b7487..956cfe5f644d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4687,7 +4687,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
-	pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
+	pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, page_ptdesc(vmf->prealloc_pte));
 	/*
 	 * We are going to consume the prealloc table,
 	 * count that as nr_ptes.
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index de1ed30fea16..5e763682941d 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -163,16 +163,16 @@ pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pgtable)
+				struct ptdesc *ptdesc)
 {
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
 	/* FIFO */
 	if (!pmd_huge_pte(mm, pmdp))
-		INIT_LIST_HEAD(&pgtable->lru);
+		INIT_LIST_HEAD(&ptdesc->pt_list);
 	else
-		list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->pt_list);
-	pmd_huge_pte(mm, pmdp) = page_ptdesc(pgtable);
+		list_add(&ptdesc->pt_list, &pmd_huge_pte(mm, pmdp)->pt_list);
+	pmd_huge_pte(mm, pmdp) = ptdesc;
 }
 #endif
 
-- 
2.43.0

[RFC PATCH 16/18] mm/pgtable: pass ptdesc to pmd_install

[alexs]

From: Alex Shi <alexs@kernel.org>

A new step to replace pgtable_t by ptdesc, also a preparation to change
vmf.prealloc_pte to ptdesc too.

Signed-off-by: Alex Shi <alexs@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-fsdevel@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Wilcox  <willy@infradead.org>
---
 mm/filemap.c  | 2 +-
 mm/internal.h | 2 +-
 mm/memory.c   | 8 ++++----
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index d62150418b91..3708ef71182e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3453,7 +3453,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
 	}
 
 	if (pmd_none(*vmf->pmd) && vmf->prealloc_pte)
-		pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
+		pmd_install(mm, vmf->pmd, (struct ptdesc **)&vmf->prealloc_pte);
 
 	return false;
 }
diff --git a/mm/internal.h b/mm/internal.h
index 7a3bcc6d95e7..e4bc64d5176a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -320,7 +320,7 @@ void folio_activate(struct folio *folio);
 void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		   struct vm_area_struct *start_vma, unsigned long floor,
 		   unsigned long ceiling, bool mm_wr_locked);
-void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
+void pmd_install(struct mm_struct *mm, pmd_t *pmd, struct ptdesc **pte);
 
 struct zap_details;
 void unmap_page_range(struct mmu_gather *tlb,
diff --git a/mm/memory.c b/mm/memory.c
index cbed8824059f..79685600d23f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -418,7 +418,7 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 	} while (vma);
 }
 
-void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
+void pmd_install(struct mm_struct *mm, pmd_t *pmd, struct ptdesc **pte)
 {
 	spinlock_t *ptl = pmd_lock(mm, pmd);
 
@@ -438,7 +438,7 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
 		 * smp_rmb() barriers in page table walking code.
 		 */
 		smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
-		pmd_populate(mm, pmd, (struct ptdesc *)(*pte));
+		pmd_populate(mm, pmd, *pte);
 		*pte = NULL;
 	}
 	spin_unlock(ptl);
@@ -450,7 +450,7 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
 	if (!ptdesc)
 		return -ENOMEM;
 
-	pmd_install(mm, pmd, (pgtable_t *)&ptdesc);
+	pmd_install(mm, pmd, &ptdesc);
 	if (ptdesc)
 		pte_free(mm, ptdesc);
 	return 0;
@@ -4868,7 +4868,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		}
 
 		if (vmf->prealloc_pte)
-			pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte);
+			pmd_install(vma->vm_mm, vmf->pmd, (struct ptdesc **)&vmf->prealloc_pte);
 		else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
 			return VM_FAULT_OOM;
 	}
-- 
2.43.0

[RFC PATCH 17/18] mm: convert vmf.prealloc_pte to struct ptdesc pointer

[alexs]

From: Alex Shi <alexs@kernel.org>

vmfs.prealloc_pte is a pointer to page table memory, so converter it to
struct ptdesc pointer.

Signed-off-by: Alex Shi <alexs@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: Matthew Wilcox  <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h |  2 +-
 mm/filemap.c       |  2 +-
 mm/memory.c        | 12 ++++++------
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7424f964dff3..749d6dd311fa 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -567,7 +567,7 @@ struct vm_fault {
 					 * Protects pte page table if 'pte'
 					 * is not NULL, otherwise pmd.
 					 */
-	pgtable_t prealloc_pte;		/* Pre-allocated pte page table.
+	struct ptdesc *prealloc_pte;	/* Pre-allocated pte page table.
 					 * vm_ops->map_pages() sets up a page
 					 * table from atomic context.
 					 * do_fault_around() pre-allocates
diff --git a/mm/filemap.c b/mm/filemap.c
index 3708ef71182e..d62150418b91 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3453,7 +3453,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
 	}
 
 	if (pmd_none(*vmf->pmd) && vmf->prealloc_pte)
-		pmd_install(mm, vmf->pmd, (struct ptdesc **)&vmf->prealloc_pte);
+		pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
 
 	return false;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 79685600d23f..1a5fb17ab045 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4648,7 +4648,7 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 	 *				# flush A, B to clear the writeback
 	 */
 	if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) {
-		vmf->prealloc_pte = ptdesc_page(pte_alloc_one(vma->vm_mm));
+		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 	}
@@ -4687,7 +4687,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
-	pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, page_ptdesc(vmf->prealloc_pte));
+	pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
 	/*
 	 * We are going to consume the prealloc table,
 	 * count that as nr_ptes.
@@ -4726,7 +4726,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	 * related to pte entry. Use the preallocated table for that.
 	 */
 	if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
-		vmf->prealloc_pte = ptdesc_page(pte_alloc_one(vma->vm_mm));
+		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 	}
@@ -4868,7 +4868,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		}
 
 		if (vmf->prealloc_pte)
-			pmd_install(vma->vm_mm, vmf->pmd, (struct ptdesc **)&vmf->prealloc_pte);
+			pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte);
 		else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
 			return VM_FAULT_OOM;
 	}
@@ -5011,7 +5011,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 		      pte_off + vma_pages(vmf->vma) - vma_off) - 1;
 
 	if (pmd_none(*vmf->pmd)) {
-		vmf->prealloc_pte = ptdesc_page(pte_alloc_one(vmf->vma->vm_mm));
+		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 	}
@@ -5197,7 +5197,7 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 
 	/* preallocated pagetable is unused: free it */
 	if (vmf->prealloc_pte) {
-		pte_free(vm_mm, page_ptdesc(vmf->prealloc_pte));
+		pte_free(vm_mm, vmf->prealloc_pte);
 		vmf->prealloc_pte = NULL;
 	}
 	return ret;
-- 
2.43.0