From: James Morse <james.morse@xxxxxxx> 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. Reviewed-by: Catalin Marinas <catalin.marinas@xxxxxxx> Signed-off-by: James Morse <james.morse@xxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/arm64/include/asm/mmu.h | 2 +- arch/arm64/include/asm/vectors.h | 27 +++++++++++++++++++++++++++ arch/arm64/kernel/cpufeature.c | 11 +++++++++++ arch/arm64/kernel/entry.S | 16 ++++++++++------ arch/arm64/kvm/hyp/switch.c | 8 ++++++-- 5 files changed, 55 insertions(+), 9 deletions(-) --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -38,7 +38,7 @@ typedef struct { */ #define ASID(mm) ((mm)->context.id.counter & 0xffff) -static inline bool arm64_kernel_unmapped_at_el0(void) +static __always_inline bool arm64_kernel_unmapped_at_el0(void) { return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0); --- a/arch/arm64/include/asm/vectors.h +++ b/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 */ --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -20,11 +20,13 @@ #include <linux/bsearch.h> #include <linux/cpumask.h> +#include <linux/percpu.h> #include <linux/sort.h> #include <linux/stop_machine.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/cpu.h> + #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> @@ -33,6 +35,7 @@ #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/traps.h> +#include <asm/vectors.h> #include <asm/virt.h> unsigned long elf_hwcap __read_mostly; @@ -51,6 +54,8 @@ unsigned int compat_elf_hwcap2 __read_mo DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); EXPORT_SYMBOL(cpu_hwcaps); +DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors; + /* * Flag to indicate if we have computed the system wide * capabilities based on the boot time active CPUs. This @@ -963,6 +968,12 @@ kpti_install_ng_mappings(const struct ar static bool kpti_applied = false; 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); + } + if (kpti_applied) return; --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -71,7 +71,6 @@ .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 @@ -86,7 +85,6 @@ .endif .Lskip_tramp_vectors_cleanup\@: .endif -#endif sub sp, sp, #S_FRAME_SIZE #ifdef CONFIG_VMAP_STACK @@ -1033,10 +1031,14 @@ alternative_insn isb, nop, ARM64_WORKARO .endm .macro tramp_exit, regsize = 64 - adr x30, tramp_vectors -#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY - add x30, x30, SZ_4K -#endif + tramp_data_read_var x30, this_cpu_vector +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN + mrs x29, tpidr_el1 +alternative_else + mrs x29, tpidr_el2 +alternative_endif + ldr x30, [x30, x29] + msr vbar_el1, x30 ldr lr, [sp, #S_LR] tramp_unmap_kernel x29 @@ -1096,6 +1098,8 @@ __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 .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -34,6 +34,7 @@ #include <asm/debug-monitors.h> #include <asm/processor.h> #include <asm/thread_info.h> +#include <asm/vectors.h> extern struct exception_table_entry __start___kvm_ex_table; extern struct exception_table_entry __stop___kvm_ex_table; @@ -155,10 +156,13 @@ static void __hyp_text __activate_traps( static void deactivate_traps_vhe(void) { - extern char vectors[]; /* kernel exception vectors */ + const char *host_vectors = vectors; write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); 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_vhe);