mips: implement the new page table range API

Rename _PFN_SHIFT to PFN_PTE_SHIFT.  Convert a few places
to call set_pte() instead of set_pte_at().  Add set_ptes(),
update_mmu_cache_range(), flush_icache_pages() and flush_dcache_folio().
Change the PG_arch_1 (aka PG_dcache_dirty) flag from being per-page
to per-folio.

Link: https://lkml.kernel.org/r/20230802151406.3735276-18-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 73 insertions, 44 deletions

diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index d8d3f80f9fc0..0f389bc7cb90 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -36,12 +36,12 @@
  */
 #define PG_dcache_dirty			PG_arch_1
 
-#define Page_dcache_dirty(page)		\
-	test_bit(PG_dcache_dirty, &(page)->flags)
-#define SetPageDcacheDirty(page)	\
-	set_bit(PG_dcache_dirty, &(page)->flags)
-#define ClearPageDcacheDirty(page)	\
-	clear_bit(PG_dcache_dirty, &(page)->flags)
+#define folio_test_dcache_dirty(folio)		\
+	test_bit(PG_dcache_dirty, &(folio)->flags)
+#define folio_set_dcache_dirty(folio)	\
+	set_bit(PG_dcache_dirty, &(folio)->flags)
+#define folio_clear_dcache_dirty(folio)	\
+	clear_bit(PG_dcache_dirty, &(folio)->flags)
 
 extern void (*flush_cache_all)(void);
 extern void (*__flush_cache_all)(void);
@@ -50,15 +50,24 @@ extern void (*flush_cache_mm)(struct mm_struct *mm);
 extern void (*flush_cache_range)(struct vm_area_struct *vma,
 	unsigned long start, unsigned long end);
 extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn);
-extern void __flush_dcache_page(struct page *page);
+extern void __flush_dcache_pages(struct page *page, unsigned int nr);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+static inline void flush_dcache_folio(struct folio *folio)
+{
+	if (cpu_has_dc_aliases)
+		__flush_dcache_pages(&folio->page, folio_nr_pages(folio));
+	else if (!cpu_has_ic_fills_f_dc)
+		folio_set_dcache_dirty(folio);
+}
+#define flush_dcache_folio flush_dcache_folio
+
 static inline void flush_dcache_page(struct page *page)
 {
 	if (cpu_has_dc_aliases)
-		__flush_dcache_page(page);
+		__flush_dcache_pages(page, 1);
 	else if (!cpu_has_ic_fills_f_dc)
-		SetPageDcacheDirty(page);
+		folio_set_dcache_dirty(page_folio(page));
 }
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
@@ -73,10 +82,11 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 		__flush_anon_page(page, vmaddr);
 }
 
-static inline void flush_icache_page(struct vm_area_struct *vma,
-	struct page *page)
+static inline void flush_icache_pages(struct vm_area_struct *vma,
+		struct page *page, unsigned int nr)
 {
 }
+#define flush_icache_page(vma, page) flush_icache_pages(vma, page, 1)
 
 extern void (*flush_icache_range)(unsigned long start, unsigned long end);
 extern void (*local_flush_icache_range)(unsigned long start, unsigned long end);
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index ba0016709a1a..0e196650f4f4 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -153,7 +153,7 @@ static inline void pmd_clear(pmd_t *pmdp)
 #if defined(CONFIG_XPA)
 
 #define MAX_POSSIBLE_PHYSMEM_BITS 40
-#define pte_pfn(x)		(((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT))
+#define pte_pfn(x)		(((unsigned long)((x).pte_high >> PFN_PTE_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT))
 static inline pte_t
 pfn_pte(unsigned long pfn, pgprot_t prot)
 {
@@ -161,7 +161,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot)
 
 	pte.pte_low = (pfn >> _PAGE_PRESENT_SHIFT) |
 				(pgprot_val(prot) & ~_PFNX_MASK);
-	pte.pte_high = (pfn << _PFN_SHIFT) |
+	pte.pte_high = (pfn << PFN_PTE_SHIFT) |
 				(pgprot_val(prot) & ~_PFN_MASK);
 	return pte;
 }
@@ -184,9 +184,9 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 #else
 
 #define MAX_POSSIBLE_PHYSMEM_BITS 32
-#define pte_pfn(x)		((unsigned long)((x).pte >> _PFN_SHIFT))
-#define pfn_pte(pfn, prot)	__pte(((unsigned long long)(pfn) << _PFN_SHIFT) | pgprot_val(prot))
-#define pfn_pmd(pfn, prot)	__pmd(((unsigned long long)(pfn) << _PFN_SHIFT) | pgprot_val(prot))
+#define pte_pfn(x)		((unsigned long)((x).pte >> PFN_PTE_SHIFT))
+#define pfn_pte(pfn, prot)	__pte(((unsigned long long)(pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot)	__pmd(((unsigned long long)(pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
 #endif /* defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) */
 
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 98e24e3e7f2b..20ca48c1b606 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -298,9 +298,9 @@ static inline void pud_clear(pud_t *pudp)
 
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 
-#define pte_pfn(x)		((unsigned long)((x).pte >> _PFN_SHIFT))
-#define pfn_pte(pfn, prot)	__pte(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
-#define pfn_pmd(pfn, prot)	__pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
+#define pte_pfn(x)		((unsigned long)((x).pte >> PFN_PTE_SHIFT))
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot)	__pmd(((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
 
 #ifndef __PAGETABLE_PMD_FOLDED
 static inline pmd_t *pud_pgtable(pud_t pud)
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index 1c576679aa87..421e78c30253 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -182,10 +182,10 @@ enum pgtable_bits {
 #if defined(CONFIG_CPU_R3K_TLB)
 # define _CACHE_UNCACHED	(1 << _CACHE_UNCACHED_SHIFT)
 # define _CACHE_MASK		_CACHE_UNCACHED
-# define _PFN_SHIFT		PAGE_SHIFT
+# define PFN_PTE_SHIFT		PAGE_SHIFT
 #else
 # define _CACHE_MASK		(7 << _CACHE_SHIFT)
-# define _PFN_SHIFT		(PAGE_SHIFT - 12 + _CACHE_SHIFT + 3)
+# define PFN_PTE_SHIFT		(PAGE_SHIFT - 12 + _CACHE_SHIFT + 3)
 #endif
 
 #ifndef _PAGE_NO_EXEC
@@ -195,7 +195,7 @@ enum pgtable_bits {
 #define _PAGE_SILENT_READ	_PAGE_VALID
 #define _PAGE_SILENT_WRITE	_PAGE_DIRTY
 
-#define _PFN_MASK		(~((1 << (_PFN_SHIFT)) - 1))
+#define _PFN_MASK		(~((1 << (PFN_PTE_SHIFT)) - 1))
 
 /*
  * The final layouts of the PTE bits are:
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 574fa14ac8b2..cbb93a834f52 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -66,7 +66,7 @@ extern void paging_init(void);
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return pmd_val(pmd) >> _PFN_SHIFT;
+	return pmd_val(pmd) >> PFN_PTE_SHIFT;
 }
 
 #ifndef CONFIG_MIPS_HUGE_TLB_SUPPORT
@@ -105,9 +105,6 @@ do {									\
 	}								\
 } while(0)
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pteval);
-
 #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
 
 #ifdef CONFIG_XPA
@@ -157,7 +154,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 			null.pte_low = null.pte_high = _PAGE_GLOBAL;
 	}
 
-	set_pte_at(mm, addr, ptep, null);
+	set_pte(ptep, null);
 	htw_start();
 }
 #else
@@ -196,28 +193,41 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 #if !defined(CONFIG_CPU_R3K_TLB)
 	/* Preserve global status for the pair */
 	if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL)
-		set_pte_at(mm, addr, ptep, __pte(_PAGE_GLOBAL));
+		set_pte(ptep, __pte(_PAGE_GLOBAL));
 	else
 #endif
-		set_pte_at(mm, addr, ptep, __pte(0));
+		set_pte(ptep, __pte(0));
 	htw_start();
 }
 #endif
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pteval)
+static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+		pte_t *ptep, pte_t pte, unsigned int nr)
 {
+	unsigned int i;
+	bool do_sync = false;
 
-	if (!pte_present(pteval))
-		goto cache_sync_done;
+	for (i = 0; i < nr; i++) {
+		if (!pte_present(pte))
+			continue;
+		if (pte_present(ptep[i]) &&
+		    (pte_pfn(ptep[i]) == pte_pfn(pte)))
+			continue;
+		do_sync = true;
+	}
 
-	if (pte_present(*ptep) && (pte_pfn(*ptep) == pte_pfn(pteval)))
-		goto cache_sync_done;
+	if (do_sync)
+		__update_cache(addr, pte);
 
-	__update_cache(addr, pteval);
-cache_sync_done:
-	set_pte(ptep, pteval);
+	for (;;) {
+		set_pte(ptep, pte);
+		if (--nr == 0)
+			break;
+		ptep++;
+		pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+	}
 }
+#define set_ptes set_ptes
 
 /*
  * (pmds are folded into puds so this doesn't get actually called,
@@ -486,7 +496,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 					pte_t entry, int dirty)
 {
 	if (!pte_same(*ptep, entry))
-		set_pte_at(vma->vm_mm, address, ptep, entry);
+		set_pte(ptep, entry);
 	/*
 	 * update_mmu_cache will unconditionally execute, handling both
 	 * the case that the PTE changed and the spurious fault case.
@@ -568,12 +578,21 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 extern void __update_tlb(struct vm_area_struct *vma, unsigned long address,
 	pte_t pte);
 
-static inline void update_mmu_cache(struct vm_area_struct *vma,
-	unsigned long address, pte_t *ptep)
-{
-	pte_t pte = *ptep;
-	__update_tlb(vma, address, pte);
+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)
+{
+	for (;;) {
+		pte_t pte = *ptep;
+		__update_tlb(vma, address, pte);
+		if (--nr == 0)
+			break;
+		ptep++;
+		address += PAGE_SIZE;
+	}
 }
+#define update_mmu_cache(vma, address, ptep) \
+	update_mmu_cache_range(NULL, vma, address, ptep, 1)
 
 #define	__HAVE_ARCH_UPDATE_MMU_TLB
 #define update_mmu_tlb	update_mmu_cache