arm64: mm: Add definitions to support 5 levels of paging

Add the required types and descriptor accessors to support 5 levels of
paging in the common code. This is one of the prerequisites for
supporting 52-bit virtual addressing with 4k pages.

Note that this does not cover the code that handles kernel mappings or
the fixmap.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-76-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

4 files changed, 147 insertions, 4 deletions

diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 237224484d0f..cae8c648f462 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -60,6 +60,47 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 
+#if CONFIG_PGTABLE_LEVELS > 4
+
+static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot)
+{
+	if (pgtable_l5_enabled())
+		set_pgd(pgdp, __pgd(__phys_to_pgd_val(p4dp) | prot));
+}
+
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp)
+{
+	pgdval_t pgdval = PGD_TYPE_TABLE;
+
+	pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN;
+	__pgd_populate(pgdp, __pa(p4dp), pgdval);
+}
+
+static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	return (p4d_t *)get_zeroed_page(gfp);
+}
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!pgtable_l5_enabled())
+		return;
+	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+	free_page((unsigned long)p4d);
+}
+
+#define __p4d_free_tlb(tlb, p4d, addr)  p4d_free((tlb)->mm, p4d)
+#else
+static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot)
+{
+	BUILD_BUG();
+}
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
+
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp);
 
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 4426f48f2ae0..ef207a0d4f0d 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -26,10 +26,10 @@
 #define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
 
 /*
- * Size mapped by an entry at level n ( 0 <= n <= 3)
+ * Size mapped by an entry at level n ( -1 <= n <= 3)
  * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
  * in the final page. The maximum number of translation levels supported by
- * the architecture is 4. Hence, starting at level n, we have further
+ * the architecture is 5. Hence, starting at level n, we have further
  * ((4 - n) - 1) levels of translation excluding the offset within the page.
  * So, the total number of bits mapped by an entry at level n is :
  *
@@ -62,9 +62,16 @@
 #define PTRS_PER_PUD		(1 << (PAGE_SHIFT - 3))
 #endif
 
+#if CONFIG_PGTABLE_LEVELS > 4
+#define P4D_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(0)
+#define P4D_SIZE		(_AC(1, UL) << P4D_SHIFT)
+#define P4D_MASK		(~(P4D_SIZE-1))
+#define PTRS_PER_P4D		(1 << (PAGE_SHIFT - 3))
+#endif
+
 /*
  * PGDIR_SHIFT determines the size a top-level page table entry can map
- * (depending on the configuration, this level can be 0, 1 or 2).
+ * (depending on the configuration, this level can be -1, 0, 1 or 2).
  */
 #define PGDIR_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
 #define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
@@ -87,6 +94,15 @@
 /*
  * Hardware page table definitions.
  *
+ * Level -1 descriptor (PGD).
+ */
+#define PGD_TYPE_TABLE		(_AT(pgdval_t, 3) << 0)
+#define PGD_TABLE_BIT		(_AT(pgdval_t, 1) << 1)
+#define PGD_TYPE_MASK		(_AT(pgdval_t, 3) << 0)
+#define PGD_TABLE_PXN		(_AT(pgdval_t, 1) << 59)
+#define PGD_TABLE_UXN		(_AT(pgdval_t, 1) << 60)
+
+/*
  * Level 0 descriptor (P4D).
  */
 #define P4D_TYPE_TABLE		(_AT(p4dval_t, 3) << 0)
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
index b8f158ae2527..6d6d4065b0cb 100644
--- a/arch/arm64/include/asm/pgtable-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -36,6 +36,12 @@ typedef struct { pudval_t pud; } pud_t;
 #define __pud(x)	((pud_t) { (x) } )
 #endif
 
+#if CONFIG_PGTABLE_LEVELS > 4
+typedef struct { p4dval_t p4d; } p4d_t;
+#define p4d_val(x)	((x).p4d)
+#define __p4d(x)	((p4d_t) { (x) } )
+#endif
+
 typedef struct { pgdval_t pgd; } pgd_t;
 #define pgd_val(x)	((x).pgd)
 #define __pgd(x)	((pgd_t) { (x) } )
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 61de7b1516bc..7eb2b933ed3c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -808,7 +808,6 @@ static inline pud_t *p4d_pgtable(p4d_t p4d)
 #else
 
 #define p4d_page_paddr(p4d)	({ BUILD_BUG(); 0;})
-#define pgd_page_paddr(pgd)	({ BUILD_BUG(); 0;})
 
 /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */
 #define pud_set_fixmap(addr)		NULL
@@ -819,6 +818,87 @@ static inline pud_t *p4d_pgtable(p4d_t p4d)
 
 #endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
+#if CONFIG_PGTABLE_LEVELS > 4
+
+static __always_inline bool pgtable_l5_enabled(void)
+{
+	if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT))
+		return vabits_actual == VA_BITS;
+	return alternative_has_cap_unlikely(ARM64_HAS_VA52);
+}
+
+static inline bool mm_p4d_folded(const struct mm_struct *mm)
+{
+	return !pgtable_l5_enabled();
+}
+#define mm_p4d_folded  mm_p4d_folded
+
+#define p4d_ERROR(e)	\
+	pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e))
+
+#define pgd_none(pgd)		(pgtable_l5_enabled() && !pgd_val(pgd))
+#define pgd_bad(pgd)		(pgtable_l5_enabled() && !(pgd_val(pgd) & 2))
+#define pgd_present(pgd)	(!pgd_none(pgd))
+
+static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (in_swapper_pgdir(pgdp)) {
+		set_swapper_pgd(pgdp, __pgd(pgd_val(pgd)));
+		return;
+	}
+
+	WRITE_ONCE(*pgdp, pgd);
+	dsb(ishst);
+	isb();
+}
+
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	if (pgtable_l5_enabled())
+		set_pgd(pgdp, __pgd(0));
+}
+
+static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
+{
+	return __pgd_to_phys(pgd);
+}
+
+#define p4d_index(addr)		(((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
+
+static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr)
+{
+	return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr);
+}
+
+static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr)
+{
+	BUG_ON(!pgtable_l5_enabled());
+
+	return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t);
+}
+
+static inline
+p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr)
+{
+	if (!pgtable_l5_enabled())
+		return pgd_to_folded_p4d(pgdp, addr);
+	return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr);
+}
+#define p4d_offset_lockless p4d_offset_lockless
+
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr)
+{
+	return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr);
+}
+
+#define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd)))
+
+#else
+
+static inline bool pgtable_l5_enabled(void) { return false; }
+
+#endif  /* CONFIG_PGTABLE_LEVELS > 4 */
+
 #define pgd_ERROR(e)	\
 	pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e))