powerpc: implement the new page table range API

Add set_ptes(), update_mmu_cache_range() and flush_dcache_folio().  Change
the PG_arch_1 (aka PG_dcache_dirty) flag from being per-page to per-folio.

[willy@infradead.org: re-export flush_dcache_icache_folio()]
  Link: https://lkml.kernel.org/r/ZMx1daYwvD9EM7Cv@casper.infradead.org
Link: https://lkml.kernel.org/r/20230802151406.3735276-22-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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

@@ -462,11 +462,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 		     pgprot_val(pgprot));
 }
 
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return pte_val(pte) >> PTE_RPN_SHIFT;
-}
-
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -104,6 +104,7 @@
  * and every thing below PAGE_SHIFT;
  */
 #define PTE_RPN_MASK	(((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK))
+#define PTE_RPN_SHIFT	PAGE_SHIFT
 /*
  * set of bits not changed in pmd_modify. Even though we have hash specific bits
  * in here, on radix we expect them to be zero.
@@ -569,11 +570,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 	return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE);
 }
 
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT;
-}
-
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {

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

@@ -9,13 +9,6 @@
 #endif
 
 #ifndef __ASSEMBLY__
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		       pte_t pte);
-
-
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 				 pte_t *ptep, pte_t entry, int dirty);
@@ -36,7 +29,9 @@ void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t
  * corresponding HPTE into the hash table ahead of time, instead of
  * waiting for the inevitable extra hash-table miss exception.
  */
-static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+static inline void update_mmu_cache_range(struct vm_fault *vmf,
+		struct vm_area_struct *vma, unsigned long address,
+		pte_t *ptep, unsigned int nr)
 {
 	if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE))
 		return;

arch/powerpc/include/asm/cacheflush.h

@@ -35,13 +35,19 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
  * It just marks the page as not i-cache clean.  We do the i-cache
  * flush later when the page is given to a user process, if necessary.
  */
-static inline void flush_dcache_page(struct page *page)
+static inline void flush_dcache_folio(struct folio *folio)
 {
 	if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
 		return;
 	/* avoid an atomic op if possible */
-	if (test_bit(PG_dcache_clean, &page->flags))
+	if (test_bit(PG_dcache_clean, &folio->flags))
-		clear_bit(PG_dcache_clean, &page->flags);
+		clear_bit(PG_dcache_clean, &folio->flags);
+}
+#define flush_dcache_folio flush_dcache_folio
+
+static inline void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
 }
 
 void flush_icache_range(unsigned long start, unsigned long stop);
@@ -51,7 +57,7 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long addr, int len);
 #define flush_icache_user_page flush_icache_user_page
 
-void flush_dcache_icache_page(struct page *page);
+void flush_dcache_icache_folio(struct folio *folio);
 
 /**
  * flush_dcache_range(): Write any modified data cache blocks out to memory and

arch/powerpc/include/asm/kvm_ppc.h

@@ -894,7 +894,7 @@ void kvmppc_init_lpid(unsigned long nr_lpids);
 
 static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
 {
-	struct page *page;
+	struct folio *folio;
 	/*
 	 * We can only access pages that the kernel maps
 	 * as memory. Bail out for unmapped ones.
@@ -903,10 +903,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
 		return;
 
 	/* Clear i-cache for new pages */
-	page = pfn_to_page(pfn);
+	folio = page_folio(pfn_to_page(pfn));
-	if (!test_bit(PG_dcache_clean, &page->flags)) {
+	if (!test_bit(PG_dcache_clean, &folio->flags)) {
-		flush_dcache_icache_page(page);
+		flush_dcache_icache_folio(folio);
-		set_bit(PG_dcache_clean, &page->flags);
+		set_bit(PG_dcache_clean, &folio->flags);
 	}
 }
 

arch/powerpc/include/asm/nohash/pgtable.h

@@ -101,8 +101,6 @@ static inline bool pte_access_permitted(pte_t pte, bool write)
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
 	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
 		     pgprot_val(pgprot)); }
-static inline unsigned long pte_pfn(pte_t pte)	{
-	return pte_val(pte) >> PTE_RPN_SHIFT; }
 
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_exprotect(pte_t pte)
@@ -166,12 +164,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
 }
 
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		       pte_t pte);
-
 /* This low level function performs the actual PTE insertion
  * Setting the PTE depends on the MMU type and other factors. It's
  * an horrible mess that I'm not going to try to clean up now but
@@ -282,10 +274,12 @@ static inline int pud_huge(pud_t pud)
  * for the page which has just been mapped in.
  */
 #if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE)
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep, unsigned int nr);
 #else
-static inline
+static inline void update_mmu_cache_range(struct vm_fault *vmf,
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {}
+		struct vm_area_struct *vma, unsigned long address,
+		pte_t *ptep, unsigned int nr) {}
 #endif
 
 #endif /* __ASSEMBLY__ */

arch/powerpc/include/asm/pgtable.h

@@ -41,6 +41,12 @@ struct mm_struct;
 
 #ifndef __ASSEMBLY__
 
+void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		pte_t pte, unsigned int nr);
+#define set_ptes set_ptes
+#define update_mmu_cache(vma, addr, ptep) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
+
 #ifndef MAX_PTRS_PER_PGD
 #define MAX_PTRS_PER_PGD PTRS_PER_PGD
 #endif
@@ -48,6 +54,12 @@ struct mm_struct;
 /* Keep these as a macros to avoid include dependency mess */
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 #define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT;
+}
+
 /*
  * Select all bits except the pfn
  */

arch/powerpc/mm/book3s64/hash_utils.c

@@ -1307,18 +1307,19 @@ void hash__early_init_mmu_secondary(void)
  */
 unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 {
-	struct page *page;
+	struct folio *folio;
 
 	if (!pfn_valid(pte_pfn(pte)))
 		return pp;
 
-	page = pte_page(pte);
+	folio = page_folio(pte_page(pte));
 
 	/* page is dirty */
-	if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) {
+	if (!test_bit(PG_dcache_clean, &folio->flags) &&
+	    !folio_test_reserved(folio)) {
 		if (trap == INTERRUPT_INST_STORAGE) {
-			flush_dcache_icache_page(page);
+			flush_dcache_icache_folio(folio);
-			set_bit(PG_dcache_clean, &page->flags);
+			set_bit(PG_dcache_clean, &folio->flags);
 		} else
 			pp |= HPTE_R_N;
 	}

arch/powerpc/mm/cacheflush.c

@@ -148,44 +148,31 @@ static void __flush_dcache_icache(void *p)
 	invalidate_icache_range(addr, addr + PAGE_SIZE);
 }
 
-static void flush_dcache_icache_hugepage(struct page *page)
+void flush_dcache_icache_folio(struct folio *folio)
 {
-	int i;
+	unsigned int i, nr = folio_nr_pages(folio);
-	int nr = compound_nr(page);
 
-	if (!PageHighMem(page)) {
-		for (i = 0; i < nr; i++)
-			__flush_dcache_icache(lowmem_page_address(page + i));
-	} else {
-		for (i = 0; i < nr; i++) {
-			void *start = kmap_local_page(page + i);
-
-			__flush_dcache_icache(start);
-			kunmap_local(start);
-		}
-	}
-}
-
-void flush_dcache_icache_page(struct page *page)
-{
 	if (flush_coherent_icache())
 		return;
 
-	if (PageCompound(page))
+	if (!folio_test_highmem(folio)) {
-		return flush_dcache_icache_hugepage(page);
+		void *addr = folio_address(folio);
-
+		for (i = 0; i < nr; i++)
-	if (!PageHighMem(page)) {
+			__flush_dcache_icache(addr + i * PAGE_SIZE);
-		__flush_dcache_icache(lowmem_page_address(page));
 	} else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
-		void *start = kmap_local_page(page);
+		for (i = 0; i < nr; i++) {
+			void *start = kmap_local_folio(folio, i * PAGE_SIZE);
 
 			__flush_dcache_icache(start);
 			kunmap_local(start);
+		}
 	} else {
-		flush_dcache_icache_phys(page_to_phys(page));
+		unsigned long pfn = folio_pfn(folio);
+		for (i = 0; i < nr; i++)
+			flush_dcache_icache_phys((pfn + i) * PAGE_SIZE);
 	}
 }
-EXPORT_SYMBOL(flush_dcache_icache_page);
+EXPORT_SYMBOL(flush_dcache_icache_folio);
 
 void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
 {

arch/powerpc/mm/nohash/e500_hugetlbpage.c

@@ -178,7 +178,8 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
  *
  * This must always be called with the pte lock held.
  */
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep, unsigned int nr)
 {
 	if (is_vm_hugetlb_page(vma))
 		book3e_hugetlb_preload(vma, address, *ptep);

arch/powerpc/mm/pgtable.c

@@ -58,7 +58,7 @@ static inline int pte_looks_normal(pte_t pte)
 	return 0;
 }
 
-static struct page *maybe_pte_to_page(pte_t pte)
+static struct folio *maybe_pte_to_folio(pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 	struct page *page;
@@ -68,7 +68,7 @@ static struct page *maybe_pte_to_page(pte_t pte)
 	page = pfn_to_page(pfn);
 	if (PageReserved(page))
 		return NULL;
-	return page;
+	return page_folio(page);
 }
 
 #ifdef CONFIG_PPC_BOOK3S
@@ -84,12 +84,12 @@ static pte_t set_pte_filter_hash(pte_t pte)
 	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
 	if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
 				       cpu_has_feature(CPU_FTR_NOEXECUTE))) {
-		struct page *pg = maybe_pte_to_page(pte);
+		struct folio *folio = maybe_pte_to_folio(pte);
-		if (!pg)
+		if (!folio)
 			return pte;
-		if (!test_bit(PG_dcache_clean, &pg->flags)) {
+		if (!test_bit(PG_dcache_clean, &folio->flags)) {
-			flush_dcache_icache_page(pg);
+			flush_dcache_icache_folio(folio);
-			set_bit(PG_dcache_clean, &pg->flags);
+			set_bit(PG_dcache_clean, &folio->flags);
 		}
 	}
 	return pte;
@@ -107,7 +107,7 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
  */
 static inline pte_t set_pte_filter(pte_t pte)
 {
-	struct page *pg;
+	struct folio *folio;
 
 	if (radix_enabled())
 		return pte;
@@ -120,18 +120,18 @@ static inline pte_t set_pte_filter(pte_t pte)
 		return pte;
 
 	/* If you set _PAGE_EXEC on weird pages you're on your own */
-	pg = maybe_pte_to_page(pte);
+	folio = maybe_pte_to_folio(pte);
-	if (unlikely(!pg))
+	if (unlikely(!folio))
 		return pte;
 
 	/* If the page clean, we move on */
-	if (test_bit(PG_dcache_clean, &pg->flags))
+	if (test_bit(PG_dcache_clean, &folio->flags))
 		return pte;
 
 	/* If it's an exec fault, we flush the cache and make it clean */
 	if (is_exec_fault()) {
-		flush_dcache_icache_page(pg);
+		flush_dcache_icache_folio(folio);
-		set_bit(PG_dcache_clean, &pg->flags);
+		set_bit(PG_dcache_clean, &folio->flags);
 		return pte;
 	}
 
@@ -142,7 +142,7 @@ static inline pte_t set_pte_filter(pte_t pte)
 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 				     int dirty)
 {
-	struct page *pg;
+	struct folio *folio;
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
 		return pte;
@@ -168,17 +168,17 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 #endif /* CONFIG_DEBUG_VM */
 
 	/* If you set _PAGE_EXEC on weird pages you're on your own */
-	pg = maybe_pte_to_page(pte);
+	folio = maybe_pte_to_folio(pte);
-	if (unlikely(!pg))
+	if (unlikely(!folio))
 		goto bail;
 
 	/* If the page is already clean, we move on */
-	if (test_bit(PG_dcache_clean, &pg->flags))
+	if (test_bit(PG_dcache_clean, &folio->flags))
 		goto bail;
 
 	/* Clean the page and set PG_dcache_clean */
-	flush_dcache_icache_page(pg);
+	flush_dcache_icache_folio(folio);
-	set_bit(PG_dcache_clean, &pg->flags);
+	set_bit(PG_dcache_clean, &folio->flags);
 
  bail:
 	return pte_mkexec(pte);
@@ -187,8 +187,8 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 /*
  * set_pte stores a linux PTE into the linux page table.
  */
-void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		pte_t pte)
+		pte_t pte, unsigned int nr)
 {
 	/*
 	 * Make sure hardware valid bit is not set. We don't do
@@ -203,7 +203,16 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	pte = set_pte_filter(pte);
 
 	/* Perform the setting of the PTE */
+	arch_enter_lazy_mmu_mode();
+	for (;;) {
 		__set_pte_at(mm, addr, ptep, pte, 0);
+		if (--nr == 0)
+			break;
+		ptep++;
+		pte = __pte(pte_val(pte) + (1UL << PTE_RPN_SHIFT));
+		addr += PAGE_SIZE;
+	}
+	arch_leave_lazy_mmu_mode();
 }
 
 void unmap_kernel_page(unsigned long va)