arm64: handle 52-bit addresses in TTBR

The top 4 bits of a 52-bit physical address are positioned at bits 2..5
in the TTBR registers. Introduce a couple of macros to move the bits
there, and change all TTBR writers to use them.

Leave TTBR0 PAN code unchanged, to avoid complicating it. A system with
52-bit PA will have PAN anyway (because it's ARMv8.1 or later), and a
system without 52-bit PA can only use up to 48-bit PAs. A later patch in
this series will add a kconfig dependency to ensure PAN is configured.

In addition, when using 52-bit PA there is a special alignment
requirement on the top-level table. We don't currently have any VA_BITS
configuration that would violate the requirement, but one could be added
in the future, so add a compile-time BUG_ON to check for it.
Tested-by: NSuzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: NSuzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: NMarc Zyngier <marc.zyngier@arm.com>
Tested-by: NBob Picco <bob.picco@oracle.com>
Reviewed-by: NBob Picco <bob.picco@oracle.com>
Signed-off-by: NKristina Martsenko <kristina.martsenko@arm.com>
[catalin.marinas@arm.com: added TTBR_BADD_MASK_52 comment]
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>

arch/arm/include/asm/kvm_mmu.h

@@ -221,6 +221,8 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return 8;
 }
 
+#define kvm_phys_to_vttbr(addr)		(addr)
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */

arch/arm64/include/asm/assembler.h

@@ -530,4 +530,20 @@ alternative_else_nop_endif
 #endif
 	.endm
 
+/*
+ * Arrange a physical address in a TTBR register, taking care of 52-bit
+ * addresses.
+ *
+ * 	phys:	physical address, preserved
+ * 	ttbr:	returns the TTBR value
+ */
+	.macro	phys_to_ttbr, phys, ttbr
+#ifdef CONFIG_ARM64_PA_BITS_52
+	orr	\ttbr, \phys, \phys, lsr #46
+	and	\ttbr, \ttbr, #TTBR_BADDR_MASK_52
+#else
+	mov	\ttbr, \phys
+#endif
+	.endm
+
 #endif	/* __ASM_ASSEMBLER_H */

arch/arm64/include/asm/kvm_mmu.h

@@ -309,5 +309,7 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
+#define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */

arch/arm64/include/asm/mmu_context.h

@@ -51,7 +51,7 @@ static inline void contextidr_thread_switch(struct task_struct *next)
  */
 static inline void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbr = __pa_symbol(empty_zero_page);
+	unsigned long ttbr = phys_to_ttbr(__pa_symbol(empty_zero_page));
 
 	write_sysreg(ttbr, ttbr0_el1);
 	isb();

arch/arm64/include/asm/pgtable-hwdef.h

@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_HWDEF_H
 #define __ASM_PGTABLE_HWDEF_H
 
+#include <asm/memory.h>
+
 /*
  * Number of page-table levels required to address 'va_bits' wide
  * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
@@ -279,4 +281,15 @@
 #define TCR_HA			(UL(1) << 39)
 #define TCR_HD			(UL(1) << 40)
 
+/*
+ * TTBR.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+/*
+ * This should be GENMASK_ULL(47, 2).
+ * TTBR_ELx[1] is RES0 in this configuration.
+ */
+#define TTBR_BADDR_MASK_52	(((UL(1) << 46) - 1) << 2)
+#endif
+
 #endif

arch/arm64/include/asm/pgtable.h

@@ -733,6 +733,12 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 #define kc_vaddr_to_offset(v)	((v) & ~VA_START)
 #define kc_offset_to_vaddr(o)	((o) | VA_START)
 
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
+#else
+#define phys_to_ttbr(addr)	(addr)
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */

arch/arm64/kernel/head.S

@@ -679,8 +679,10 @@ ENTRY(__enable_mmu)
 	update_early_cpu_boot_status 0, x1, x2
 	adrp	x1, idmap_pg_dir
 	adrp	x2, swapper_pg_dir
-	msr	ttbr0_el1, x1			// load TTBR0
-	msr	ttbr1_el1, x2			// load TTBR1
+	phys_to_ttbr x1, x3
+	phys_to_ttbr x2, x4
+	msr	ttbr0_el1, x3			// load TTBR0
+	msr	ttbr1_el1, x4			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
 	isb

arch/arm64/kernel/hibernate-asm.S

@@ -33,12 +33,14 @@
  * Even switching to our copied tables will cause a changed output address at
  * each stage of the walk.
  */
-.macro break_before_make_ttbr_switch zero_page, page_table
-	msr	ttbr1_el1, \zero_page
+.macro break_before_make_ttbr_switch zero_page, page_table, tmp
+	phys_to_ttbr \zero_page, \tmp
+	msr	ttbr1_el1, \tmp
 	isb
 	tlbi	vmalle1
 	dsb	nsh
-	msr	ttbr1_el1, \page_table
+	phys_to_ttbr \page_table, \tmp
+	msr	ttbr1_el1, \tmp
 	isb
 .endm
 
@@ -78,7 +80,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
 	 */
-	break_before_make_ttbr_switch	x5, x0
+	break_before_make_ttbr_switch	x5, x0, x6
 
 	mov	x21, x1
 	mov	x30, x2
@@ -109,7 +111,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	dsb	ish		/* wait for PoU cleaning to finish */
 
 	/* switch to the restored kernels page tables */
-	break_before_make_ttbr_switch	x25, x21
+	break_before_make_ttbr_switch	x25, x21, x6
 
 	ic	ialluis
 	dsb	ish

arch/arm64/kernel/hibernate.c

@@ -264,7 +264,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	 */
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+	write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1);
 	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);

arch/arm64/kvm/hyp-init.S

@@ -63,7 +63,8 @@ __do_hyp_init:
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.lo	__kvm_handle_stub_hvc
 
-	msr	ttbr0_el2, x0
+	phys_to_ttbr x0, x4
+	msr	ttbr0_el2, x4
 
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK

arch/arm64/mm/pgd.c

@@ -49,6 +49,14 @@ void __init pgd_cache_init(void)
 	if (PGD_SIZE == PAGE_SIZE)
 		return;
 
+#ifdef CONFIG_ARM64_PA_BITS_52
+	/*
+	 * With 52-bit physical addresses, the architecture requires the
+	 * top-level table to be aligned to at least 64 bytes.
+	 */
+	BUILD_BUG_ON(PGD_SIZE < 64);
+#endif
+
 	/*
 	 * Naturally aligned pgds required by the architecture.
 	 */

arch/arm64/mm/proc.S

@@ -138,10 +138,11 @@ ENDPROC(cpu_do_resume)
  *	- pgd_phys - physical address of new TTB
  */
 ENTRY(cpu_do_switch_mm)
-	pre_ttbr0_update_workaround x0, x2, x3
+	phys_to_ttbr x0, x2
+	pre_ttbr0_update_workaround x2, x3, x4
 	mmid	x1, x1				// get mm->context.id
-	bfi	x0, x1, #48, #16		// set the ASID
-	msr	ttbr0_el1, x0			// set TTBR0
+	bfi	x2, x1, #48, #16		// set the ASID
+	msr	ttbr0_el1, x2			// set TTBR0
 	isb
 	post_ttbr0_update_workaround
 	ret
@@ -158,14 +159,16 @@ ENTRY(idmap_cpu_replace_ttbr1)
 	save_and_disable_daif flags=x2
 
 	adrp	x1, empty_zero_page
-	msr	ttbr1_el1, x1
+	phys_to_ttbr x1, x3
+	msr	ttbr1_el1, x3
 	isb
 
 	tlbi	vmalle1
 	dsb	nsh
 	isb
 
-	msr	ttbr1_el1, x0
+	phys_to_ttbr x0, x3
+	msr	ttbr1_el1, x3
 	isb
 
 	restore_daif x2

virt/kvm/arm/arm.c

@@ -509,7 +509,7 @@ static void update_vttbr(struct kvm *kvm)
 	pgd_phys = virt_to_phys(kvm->arch.pgd);
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
-	kvm->arch.vttbr = pgd_phys | vmid;
+	kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
 }