arm64: allow ID map to be extended to 52 bits

Currently, when using VA_BITS < 48, if the ID map text happens to be
placed in physical memory above VA_BITS, we increase the VA size (up to
48) and create a new table level, in order to map in the ID map text.
This is okay because the system always supports 48 bits of VA.

This patch extends the code such that if the system supports 52 bits of
VA, and the ID map text is placed that high up, then we increase the VA
size accordingly, up to 52.

One difference from the current implementation is that so far the
condition of VA_BITS < 48 has meant that the top level table is always
"full", with the maximum number of entries, and an extra table level is
always needed. Now, when VA_BITS = 48 (and using 64k pages), the top
level table is not full, and we simply need to increase the number of
entries in it, instead of creating a new table level.

Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Bob Picco <bob.picco@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: reduce arguments to __create_hyp_mappings()]
[catalin.marinas@arm.com: reworked/renamed __cpu_uses_extended_idmap_level()]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm/include/asm/kvm_mmu.h

@@ -211,6 +211,11 @@ static inline bool __kvm_cpu_uses_extended_idmap(void)
 	return false;
 }
 
+static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
+{
+	return PTRS_PER_PGD;
+}
+
 static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 				       pgd_t *hyp_pgd,
 				       pgd_t *merged_hyp_pgd,

arch/arm64/include/asm/assembler.h

@@ -344,10 +344,8 @@ alternative_endif
  * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
  */
 	.macro	tcr_set_idmap_t0sz, valreg, tmpreg
-#ifndef CONFIG_ARM64_VA_BITS_48
 	ldr_l	\tmpreg, idmap_t0sz
 	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
-#endif
 	.endm
 
 /*

arch/arm64/include/asm/kvm_mmu.h

@@ -273,7 +273,12 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
 static inline bool __kvm_cpu_uses_extended_idmap(void)
 {
-	return __cpu_uses_extended_idmap();
+	return __cpu_uses_extended_idmap_level();
+}
+
+static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
+{
+	return idmap_ptrs_per_pgd;
 }
 
 /*

arch/arm64/include/asm/mmu_context.h

@@ -63,6 +63,7 @@ static inline void cpu_set_reserved_ttbr0(void)
  * physical memory, in which case it will be smaller.
  */
 extern u64 idmap_t0sz;
+extern u64 idmap_ptrs_per_pgd;
 
 static inline bool __cpu_uses_extended_idmap(void)
 {
@@ -70,6 +71,15 @@ static inline bool __cpu_uses_extended_idmap(void)
 		unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)));
 }
 
+/*
+ * True if the extended ID map requires an extra level of translation table
+ * to be configured.
+ */
+static inline bool __cpu_uses_extended_idmap_level(void)
+{
+	return ARM64_HW_PGTABLE_LEVELS((64 - idmap_t0sz)) > CONFIG_PGTABLE_LEVELS;
+}
+
 /*
  * Set TCR.T0SZ to its default value (based on VA_BITS)
  */

arch/arm64/kernel/head.S

@@ -176,7 +176,7 @@ ENDPROC(preserve_boot_args)
  *	ptrs:	#imm pointers per table page
  *
  * Preserves:	virt
- * Corrupts:	tmp1, tmp2
+ * Corrupts:	ptrs, tmp1, tmp2
  * Returns:	tbl -> next level table page address
  */
 	.macro	create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
@@ -184,7 +184,8 @@ ENDPROC(preserve_boot_args)
 	phys_to_pte \tmp1, \tmp2
 	orr	\tmp2, \tmp2, #PMD_TYPE_TABLE	// address of next table and entry type
 	lsr	\tmp1, \virt, #\shift
-	and	\tmp1, \tmp1, #\ptrs - 1	// table index
+	sub	\ptrs, \ptrs, #1
+	and	\tmp1, \tmp1, \ptrs		// table index
 	str	\tmp2, [\tbl, \tmp1, lsl #3]
 	add	\tbl, \tbl, #PAGE_SIZE		// next level table page
 	.endm
@@ -194,15 +195,17 @@ ENDPROC(preserve_boot_args)
  * block entry in the next level (tbl) for the given virtual address.
  *
  * Preserves:	tbl, next, virt
- * Corrupts:	tmp1, tmp2
+ * Corrupts:	ptrs_per_pgd, tmp1, tmp2
  */
-	.macro	create_pgd_entry, tbl, virt, tmp1, tmp2
+	.macro	create_pgd_entry, tbl, virt, ptrs_per_pgd, tmp1, tmp2
-	create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2
+	create_table_entry \tbl, \virt, PGDIR_SHIFT, \ptrs_per_pgd, \tmp1, \tmp2
 #if SWAPPER_PGTABLE_LEVELS > 3
-	create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2
+	mov	\ptrs_per_pgd, PTRS_PER_PUD
+	create_table_entry \tbl, \virt, PUD_SHIFT, \ptrs_per_pgd, \tmp1, \tmp2
 #endif
 #if SWAPPER_PGTABLE_LEVELS > 2
-	create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
+	mov	\ptrs_per_pgd, PTRS_PER_PTE
+	create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, \ptrs_per_pgd, \tmp1, \tmp2
 #endif
 	.endm
 
@@ -266,16 +269,34 @@ __create_page_tables:
 	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
-#ifndef CONFIG_ARM64_VA_BITS_48
+	/*
+	 * VA_BITS may be too small to allow for an ID mapping to be created
+	 * that covers system RAM if that is located sufficiently high in the
+	 * physical address space. So for the ID map, use an extended virtual
+	 * range in that case, and configure an additional translation level
+	 * if needed.
+	 *
+	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
+	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
+	 * this number conveniently equals the number of leading zeroes in
+	 * the physical address of __idmap_text_end.
+	 */
+	adrp	x5, __idmap_text_end
+	clz	x5, x5
+	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
+	b.ge	1f			// .. then skip VA range extension
+
+	adr_l	x6, idmap_t0sz
+	str	x5, [x6]
+	dmb	sy
+	dc	ivac, x6		// Invalidate potentially stale cache line
+
+#if (VA_BITS < 48)
 #define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
-#define EXTRA_PTRS	(1 << (48 - EXTRA_SHIFT))
+#define EXTRA_PTRS	(1 << (PHYS_MASK_SHIFT - EXTRA_SHIFT))
 
 	/*
-	 * If VA_BITS < 48, it may be too small to allow for an ID mapping to be
+	 * If VA_BITS < 48, we have to configure an additional table level.
-	 * created that covers system RAM if that is located sufficiently high
-	 * in the physical address space. So for the ID map, use an extended
-	 * virtual range in that case, by configuring an additional translation
-	 * level.
 	 * First, we have to verify our assumption that the current value of
 	 * VA_BITS was chosen such that all translation levels are fully
 	 * utilised, and that lowering T0SZ will always result in an additional
@@ -285,27 +306,19 @@ __create_page_tables:
 #error "Mismatch between VA_BITS and page size/number of translation levels"
 #endif
 
+	mov	x4, EXTRA_PTRS
+	create_table_entry x0, x3, EXTRA_SHIFT, x4, x5, x6
+#else
 	/*
-	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
+	 * If VA_BITS == 48, we don't have to configure an additional
-	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
+	 * translation level, but the top-level table has more entries.
-	 * this number conveniently equals the number of leading zeroes in
-	 * the physical address of __idmap_text_end.
 	 */
-	adrp	x5, __idmap_text_end
+	mov	x4, #1 << (PHYS_MASK_SHIFT - PGDIR_SHIFT)
-	clz	x5, x5
+	str_l	x4, idmap_ptrs_per_pgd, x5
-	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
-	b.ge	1f			// .. then skip additional level
-
-	adr_l	x6, idmap_t0sz
-	str	x5, [x6]
-	dmb	sy
-	dc	ivac, x6		// Invalidate potentially stale cache line
-
-	create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6
-1:
 #endif
-
+1:
-	create_pgd_entry x0, x3, x5, x6
+	ldr_l	x4, idmap_ptrs_per_pgd
+	create_pgd_entry x0, x3, x4, x5, x6
 	mov	x5, x3				// __pa(__idmap_text_start)
 	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
 	create_block_map x0, x7, x3, x5, x6, x4
@@ -316,7 +329,8 @@ __create_page_tables:
 	adrp	x0, swapper_pg_dir
 	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
-	create_pgd_entry x0, x5, x3, x6
+	mov	x4, PTRS_PER_PGD
+	create_pgd_entry x0, x5, x4, x3, x6
 	adrp	x6, _end			// runtime __pa(_end)
 	adrp	x3, _text			// runtime __pa(_text)
 	sub	x6, x6, x3			// _end - _text

arch/arm64/kvm/hyp-init.S

@@ -72,24 +72,23 @@ __do_hyp_init:
 	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
-#ifndef CONFIG_ARM64_VA_BITS_48
 	/*
-	 * If we are running with VA_BITS < 48, we may be running with an extra
+	 * The ID map may be configured to use an extended virtual address
-	 * level of translation in the ID map. This is only the case if system
+	 * range. This is only the case if system RAM is out of range for the
-	 * RAM is out of range for the currently configured page size and number
+	 * currently configured page size and VA_BITS, in which case we will
-	 * of translation levels, in which case we will also need the extra
+	 * also need the extended virtual range for the HYP ID map, or we won't
-	 * level for the HYP ID map, or we won't be able to enable the EL2 MMU.
+	 * be able to enable the EL2 MMU.
 	 *
 	 * However, at EL2, there is only one TTBR register, and we can't switch
 	 * between translation tables *and* update TCR_EL2.T0SZ at the same
-	 * time. Bottom line: we need the extra level in *both* our translation
+	 * time. Bottom line: we need to use the extended range with *both* our
-	 * tables.
+	 * translation tables.
 	 *
 	 * So use the same T0SZ value we use for the ID map.
 	 */
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
-#endif
+
 	/*
 	 * Set the PS bits in TCR_EL2.
 	 */

arch/arm64/mm/mmu.c

@@ -50,6 +50,7 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);

virt/kvm/arm/mmu.c

@@ -629,14 +629,20 @@ static int __create_hyp_mappings(pgd_t *pgdp,
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	unsigned long addr, next;
+	unsigned long addr, next, ptrs_per_pgd = PTRS_PER_PGD;
 	int err = 0;
 
+	/*
+	 * If it's not the hyp_pgd, fall back to the kvm idmap layout.
+	 */
+	if (pgdp != hyp_pgd)
+		ptrs_per_pgd = __kvm_idmap_ptrs_per_pgd();
+
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	addr = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 	do {
-		pgd = pgdp + pgd_index(addr);
+		pgd = pgdp + ((addr >> PGDIR_SHIFT) & (ptrs_per_pgd - 1));
 
 		if (pgd_none(*pgd)) {
 			pud = pud_alloc_one(NULL, addr);