UPSTREAM: arm64: Add percpu vectors for EL1

commit bd09128d16fac3c34b80bd6a29088ac632e8ce09 upstream.

The Spectre-BHB workaround adds a firmware call to the vectors. This
is needed on some CPUs, but not others. To avoid the unaffected CPU in
a big/little pair from making the firmware call, create per cpu vectors.

The per-cpu vectors only apply when returning from EL0.

Systems using KPTI can use the canonical 'full-fat' vectors directly at
EL1, the trampoline exit code will switch to this_cpu_vector on exit to
EL0. Systems not using KPTI should always use this_cpu_vector.

this_cpu_vector will point at a vector in tramp_vecs or
__bp_harden_el1_vectors, depending on whether KPTI is in use.

Bug: 215557547
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ie96a6896e26d54d09143ec668a0bdfbf21fa2618

arch/arm64/include/asm/vectors.h

@@ -5,6 +5,15 @@
 #ifndef __ASM_VECTORS_H
 #define __ASM_VECTORS_H
 
+#include <linux/bug.h>
+#include <linux/percpu.h>
+
+#include <asm/fixmap.h>
+
+extern char vectors[];
+extern char tramp_vectors[];
+extern char __bp_harden_el1_vectors[];
+
 /*
  * Note: the order of this enum corresponds to two arrays in entry.S:
  * tramp_vecs and __bp_harden_el1_vectors. By default the canonical
@@ -31,4 +40,22 @@ enum arm64_bp_harden_el1_vectors {
 	EL1_VECTOR_KPTI,
 };
 
+/* The vectors to use on return from EL0. e.g. to remap the kernel */
+DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
+
+#ifndef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_VALIAS	0
+#endif
+
+static inline const char *
+arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
+{
+	if (arm64_kernel_unmapped_at_el0())
+		return (char *)TRAMP_VALIAS + SZ_2K * slot;
+
+	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);
+
+	return __bp_harden_el1_vectors + SZ_2K * slot;
+}
+
 #endif /* __ASM_VECTORS_H */

arch/arm64/kernel/cpufeature.c

@@ -65,6 +65,7 @@
 #include <linux/bsearch.h>
 #include <linux/cpumask.h>
 #include <linux/crash_dump.h>
+#include <linux/percpu.h>
 #include <linux/sort.h>
 #include <linux/stop_machine.h>
 #include <linux/sysfs.h>
@@ -72,6 +73,7 @@
 #include <linux/mm.h>
 #include <linux/cpu.h>
 #include <linux/kasan.h>
+
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -82,6 +84,7 @@
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/traps.h>
+#include <asm/vectors.h>
 #include <asm/virt.h>
 
 /* Kernel representation of AT_HWCAP and AT_HWCAP2 */
@@ -107,6 +110,8 @@ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
 bool arm64_use_ng_mappings = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
+DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
+
 /*
  * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs
  * support it?
@@ -1557,6 +1562,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 
 	int cpu = smp_processor_id();
 
+	if (__this_cpu_read(this_cpu_vector) == vectors) {
+		const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI);
+
+		__this_cpu_write(this_cpu_vector, v);
+	}
+
 	/*
 	 * We don't need to rewrite the page-tables if either we've done
 	 * it already or we have KASLR enabled and therefore have not

arch/arm64/kernel/entry.S

@@ -63,7 +63,6 @@
 	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
 .Lventry_start\@:
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
 	/*
 	 * This must be the first instruction of the EL0 vector entries. It is
@@ -78,7 +77,6 @@
 	.endif
 .Lskip_tramp_vectors_cleanup\@:
 	.endif
-#endif
 
 	sub	sp, sp, #S_FRAME_SIZE
 #ifdef CONFIG_VMAP_STACK
@@ -979,10 +977,10 @@ alternative_else_nop_endif
 	.endm
 
 	.macro tramp_exit, regsize = 64
-	adr	x30, tramp_vectors
+	tramp_data_read_var	x30, this_cpu_vector
-#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	this_cpu_offset x29
-	add	x30, x30, SZ_4K
+	ldr	x30, [x30, x29]
-#endif
+
 	msr	vbar_el1, x30
 	ldr	lr, [sp, #S_LR]
 	tramp_unmap_kernel	x29
@@ -1042,6 +1040,8 @@ __entry_tramp_data_vectors:
 __entry_tramp_data___sdei_asm_handler:
 	.quad	__sdei_asm_handler
 #endif /* CONFIG_ARM_SDE_INTERFACE */
+__entry_tramp_data_this_cpu_vector:
+	.quad	this_cpu_vector
 SYM_DATA_END(__entry_tramp_data_start)
 	.popsection				// .rodata
 #endif /* CONFIG_RANDOMIZE_BASE */

arch/arm64/kvm/hyp/vhe/switch.c

@@ -11,6 +11,7 @@
 #include <linux/kvm_host.h>
 #include <linux/types.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
 #include <uapi/linux/psci.h>
 
 #include <kvm/arm_psci.h>
@@ -26,6 +27,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>
 #include <asm/thread_info.h>
+#include <asm/vectors.h>
 
 const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
 
@@ -71,7 +73,7 @@ NOKPROBE_SYMBOL(__activate_traps);
 
 static void __deactivate_traps(struct kvm_vcpu *vcpu)
 {
-	extern char vectors[];	/* kernel exception vectors */
+	const char *host_vectors = vectors;
 
 	___deactivate_traps(vcpu);
 
@@ -85,7 +87,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
-	write_sysreg(vectors, vbar_el1);
+
+	if (!arm64_kernel_unmapped_at_el0())
+		host_vectors = __this_cpu_read(this_cpu_vector);
+	write_sysreg(host_vectors, vbar_el1);
 }
 NOKPROBE_SYMBOL(__deactivate_traps);