riscv: implement the new page table range API

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

Link: https://lkml.kernel.org/r/20230802151406.3735276-23-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 33 insertions, 23 deletions

diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8091b8bf4883..0d8c92c5dfb7 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -15,20 +15,19 @@ static inline void local_flush_icache_all(void)
 
 #define PG_dcache_clean PG_arch_1
 
-static inline void flush_dcache_page(struct page *page)
+static inline void flush_dcache_folio(struct folio *folio)
 {
-	/*
-	 * HugeTLB pages are always fully mapped and only head page will be
-	 * set PG_dcache_clean (see comments in flush_icache_pte()).
-	 */
-	if (PageHuge(page))
-		page = compound_head(page);
-
-	if (test_bit(PG_dcache_clean, &page->flags))
-		clear_bit(PG_dcache_clean, &page->flags);
+	if (test_bit(PG_dcache_clean, &folio->flags))
+		clear_bit(PG_dcache_clean, &folio->flags);
 }
+#define flush_dcache_folio flush_dcache_folio
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
+static inline void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
+}
+
 /*
  * RISC-V doesn't have an instruction to flush parts of the instruction cache,
  * so instead we just flush the whole thing.
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 01e4aabc8898..ac42e9121e52 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -445,8 +445,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 
 /* Commit new configuration to MMU hardware */
-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)
 {
 	/*
 	 * The kernel assumes that TLBs don't cache invalid entries, but
@@ -455,8 +456,11 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 	 * Relying on flush_tlb_fix_spurious_fault would suffice, but
 	 * the extra traps reduce performance.  So, eagerly SFENCE.VMA.
 	 */
-	local_flush_tlb_page(address);
+	while (nr--)
+		local_flush_tlb_page(address + nr * PAGE_SIZE);
 }
+#define update_mmu_cache(vma, addr, ptep) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
 
 #define __HAVE_ARCH_UPDATE_MMU_TLB
 #define update_mmu_tlb update_mmu_cache
@@ -487,8 +491,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 
 void flush_icache_pte(pte_t pte);
 
-static inline void __set_pte_at(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep, pte_t pteval)
+static inline void __set_pte_at(pte_t *ptep, pte_t pteval)
 {
 	if (pte_present(pteval) && pte_exec(pteval))
 		flush_icache_pte(pteval);
@@ -496,17 +499,25 @@ static inline void __set_pte_at(struct mm_struct *mm,
 	set_pte(ptep, pteval);
 }
 
-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 pteval, unsigned int nr)
 {
-	page_table_check_ptes_set(mm, ptep, pteval, 1);
-	__set_pte_at(mm, addr, ptep, pteval);
+	page_table_check_ptes_set(mm, ptep, pteval, nr);
+
+	for (;;) {
+		__set_pte_at(ptep, pteval);
+		if (--nr == 0)
+			break;
+		ptep++;
+		pte_val(pteval) += 1 << _PAGE_PFN_SHIFT;
+	}
 }
+#define set_ptes set_ptes
 
 static inline void pte_clear(struct mm_struct *mm,
 	unsigned long addr, pte_t *ptep)
 {
-	__set_pte_at(mm, addr, ptep, __pte(0));
+	__set_pte_at(ptep, __pte(0));
 }
 
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
@@ -515,7 +526,7 @@ 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_at(ptep, entry);
 	/*
 	 * update_mmu_cache will unconditionally execute, handling both
 	 * the case that the PTE changed and the spurious fault case.
@@ -688,14 +699,14 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd)
 {
 	page_table_check_pmd_set(mm, pmdp, pmd);
-	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+	return __set_pte_at((pte_t *)pmdp, pmd_pte(pmd));
 }
 
 static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
 				pud_t *pudp, pud_t pud)
 {
 	page_table_check_pud_set(mm, pudp, pud);
-	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+	return __set_pte_at((pte_t *)pudp, pud_pte(pud));
 }
 
 #ifdef CONFIG_PAGE_TABLE_CHECK