ARC: mm: support 3 levels of page tables

ARCv2 MMU is software walked and Linux implements 2 levels of paging: pgd/pte.
Forthcoming hw will have multiple levels, so this change preps mm code
for same. It is also fun to try multi levels even on soft-walked code to
ensure generic mm code is robust to handle.

overview
________

2 levels {pgd, pte} : pmd is folded but pmd_* macros are valid and operate on pgd
3 levels {pgd, pmd, pte}:
  - pud is folded and pud_* macros point to pgd
  - pmd_* macros operate on actual pmd

code changes
____________

1. #include <asm-generic/pgtable-nopud.h>

2. Define CONFIG_PGTABLE_LEVELS 3

3a. Define PMD_SHIFT, PMD_SIZE, PMD_MASK, pmd_t
3b. Define pmd_val() which actually deals with pmd
    (pmd_offset(), pmd_index() are provided by generic code)
3c. pmd_alloc_one()/pmd_free() also provided by generic code
    (pmd_populate/pmd_free already exist)

4. Define pud_none(), pud_bad() macros based on generic pud_val() which
   internally pertains to pgd now.
4b. define pud_populate() to just setup pgd
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>

arch/arc/Kconfig

@@ -314,6 +314,10 @@ config ARC_HUGEPAGE_16M
 
 endchoice
 
+config PGTABLE_LEVELS
+	int "Number of Page table levels"
+	default 2
+
 config ARC_COMPACT_IRQ_LEVELS
 	depends on ISA_ARCOMPACT
 	bool "Setup Timer IRQ as high Priority"

arch/arc/include/asm/page.h

@@ -41,6 +41,17 @@ typedef struct {
 #define pgd_val(x)	((x).pgd)
 #define __pgd(x)	((pgd_t) { (x) })
 
+#if CONFIG_PGTABLE_LEVELS > 2
+
+typedef struct {
+	unsigned long pmd;
+} pmd_t;
+
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x)	((pmd_t) { (x) })
+
+#endif
+
 typedef struct {
 #ifdef CONFIG_ARC_HAS_PAE40
 	unsigned long long pte;

arch/arc/include/asm/pgalloc.h

@@ -70,6 +70,17 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 	return ret;
 }
 
+#if CONFIG_PGTABLE_LEVELS > 2
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
+{
+	set_pud(pudp, __pud((unsigned long)pmdp));
+}
+
+#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+
+#endif
+
 #define __pte_free_tlb(tlb, pte, addr)  pte_free((tlb)->mm, pte)
 
 #endif /* _ASM_ARC_PGALLOC_H */

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

@@ -10,6 +10,8 @@
 #ifndef _ASM_ARC_PGTABLE_LEVELS_H
 #define _ASM_ARC_PGTABLE_LEVELS_H
 
+#if CONFIG_PGTABLE_LEVELS == 2
+
 /*
  * 2 level paging setup for software walked MMUv3 (ARC700) and MMUv4 (HS)
  *
@@ -47,16 +49,38 @@
 
 #endif
 
-#define PGDIR_SIZE		BIT(PGDIR_SHIFT)	/* vaddr span, not PDG sz */
-#define PGDIR_MASK		(~(PGDIR_SIZE - 1))
+#else /* CONFIG_PGTABLE_LEVELS != 2 */
+
+/*
+ * A default 3 level paging testing setup in software walked MMU
+ *   MMUv4 (8K page): <4> : <7> : <8> : <13>
+ */
+#define PGDIR_SHIFT		28
+#if CONFIG_PGTABLE_LEVELS > 2
+#define PMD_SHIFT		21
+#endif
 
+#endif /* CONFIG_PGTABLE_LEVELS */
+
+#define PGDIR_SIZE		BIT(PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE - 1))
 #define PTRS_PER_PGD		BIT(32 - PGDIR_SHIFT)
 
-#define PTRS_PER_PTE		BIT(PGDIR_SHIFT - PAGE_SHIFT)
+#if CONFIG_PGTABLE_LEVELS > 2
+#define PMD_SIZE		BIT(PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE - 1))
+#define PTRS_PER_PMD		BIT(PGDIR_SHIFT - PMD_SHIFT)
+#endif
+
+#define PTRS_PER_PTE		BIT(PMD_SHIFT - PAGE_SHIFT)
 
 #ifndef __ASSEMBLY__
 
+#if CONFIG_PGTABLE_LEVELS > 2
+#include <asm-generic/pgtable-nopud.h>
+#else
 #include <asm-generic/pgtable-nopmd.h>
+#endif
 
 /*
  * 1st level paging: pgd
@@ -67,9 +91,35 @@
 #define pgd_ERROR(e) \
 	pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
+#if CONFIG_PGTABLE_LEVELS > 2
+
+/* In 3 level paging, pud_* macros work on pgd */
+#define pud_none(x)		(!pud_val(x))
+#define pud_bad(x)		((pud_val(x) & ~PAGE_MASK))
+#define pud_present(x)		(pud_val(x))
+#define pud_clear(xp)		do { pud_val(*(xp)) = 0; } while (0)
+#define pud_pgtable(pud)	((pmd_t *)(pud_val(pud) & PAGE_MASK))
+#define pud_page(pud)		virt_to_page(pud_pgtable(pud))
+#define set_pud(pudp, pud)	(*(pudp) = pud)
+
 /*
- * Due to the strange way generic pgtable level folding works, in a 2 level
- * setup, pmd_val() returns pgd, so these pmd_* macros actually work on pgd
+ * 2nd level paging: pmd
+ */
+#define pmd_ERROR(e) \
+	pr_crit("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#define pmd_pfn(pmd)		((pmd_val(pmd) & PMD_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+#endif
+
+/*
+ * Due to the strange way generic pgtable level folding works, the pmd_* macros
+ *  - are valid even for 2 levels (which supposedly only has pgd - pte)
+ *  - behave differently for 2 vs. 3
+ * In 2  level paging        (pgd -> pte), pmd_* macros work on pgd
+ * In 3+ level paging (pgd -> pmd -> pte), pmd_* macros work on pmd
  */
 #define pmd_none(x)		(!pmd_val(x))
 #define pmd_bad(x)		((pmd_val(x) & ~PAGE_MASK))
@@ -80,6 +130,9 @@
 #define set_pmd(pmdp, pmd)	(*(pmdp) = pmd)
 #define pmd_pgtable(pmd)	((pgtable_t) pmd_page_vaddr(pmd))
 
+/*
+ * 3rd level paging: pte
+ */
 #define pte_ERROR(e) \
 	pr_crit("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 

arch/arc/include/asm/processor.h

@@ -93,7 +93,7 @@ extern unsigned int get_wchan(struct task_struct *p);
 #define VMALLOC_START	(PAGE_OFFSET - (CONFIG_ARC_KVADDR_SIZE << 20))
 
 /* 1 PGDIR_SIZE each for fixmap/pkmap, 2 PGDIR_SIZE gutter (see asm/highmem.h) */
-#define VMALLOC_SIZE	((CONFIG_ARC_KVADDR_SIZE << 20) - PGDIR_SIZE * 4)
+#define VMALLOC_SIZE	((CONFIG_ARC_KVADDR_SIZE << 20) - PMD_SIZE * 4)
 
 #define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
 

arch/arc/mm/fault.c

@@ -39,6 +39,8 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
 	if (!pgd_present(*pgd_k))
 		goto bad_area;
 
+	set_pgd(pgd, *pgd_k);
+
 	p4d = p4d_offset(pgd, address);
 	p4d_k = p4d_offset(pgd_k, address);
 	if (!p4d_present(*p4d_k))
@@ -49,6 +51,8 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
 	if (!pud_present(*pud_k))
 		goto bad_area;
 
+	set_pud(pud, *pud_k);
+
 	pmd = pmd_offset(pud, address);
 	pmd_k = pmd_offset(pud_k, address);
 	if (!pmd_present(*pmd_k))

arch/arc/mm/init.c

@@ -191,6 +191,7 @@ void __init mem_init(void)
 	highmem_init();
 
 	BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE);
 	BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE);
 }
 

arch/arc/mm/tlb.c

@@ -621,8 +621,8 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
 			  IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE));
 
 	n += scnprintf(buf + n, len - n,
-		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n",
-		       p_mmu->ver, p_mmu->pg_sz_k, super_pg,
+		      "MMU [v%x]\t: %dk PAGE, %s, swalk %d lvl, JTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n",
+		       p_mmu->ver, p_mmu->pg_sz_k, super_pg,  CONFIG_PGTABLE_LEVELS,
 		       p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways,
 		       p_mmu->u_dtlb, p_mmu->u_itlb,
 		       IS_AVAIL2(p_mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40));

arch/arc/mm/tlbex.S

@@ -173,6 +173,15 @@ ex_saved_reg1:
 	tst	r3, r3
 	bz	do_slow_path_pf         ; if no Page Table, do page fault
 
+#if CONFIG_PGTABLE_LEVELS > 2
+	lsr     r0, r2, PMD_SHIFT	; Bits for indexing into PMD
+	and	r0, r0, (PTRS_PER_PMD - 1)
+	ld.as	r1, [r3, r0]		; PMD entry
+	tst	r1, r1
+	bz	do_slow_path_pf
+	mov	r3, r1
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	and.f	0, r3, _PAGE_HW_SZ	; Is this Huge PMD (thp)
 	add2.nz	r1, r1, r0