From a78738ed1d9bf40d09109599b884508c69d188b8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 8 Oct 2021 14:58:34 +0100 Subject: KVM: arm64: Turn __KVM_HOST_SMCCC_FUNC_* into an enum (mostly) __KVM_HOST_SMCCC_FUNC_* is a royal pain, as there is a fair amount of churn around these #defines, and we avoid making it an enum only for the sake of the early init, low level code that requires __KVM_HOST_SMCCC_FUNC___kvm_hyp_init to be usable from assembly. Let's be brave and turn everything but this symbol into an enum, using a bit of arithmetic to avoid any overlap. Acked-by: Will Deacon Link: https://lore.kernel.org/r/877depq9gw.wl-maz@kernel.org Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon Link: https://lore.kernel.org/r/20211008135839.1193-2-will@kernel.org --- arch/arm64/include/asm/kvm_asm.h | 44 ++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 20 deletions(-) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index e86045ac43ba..43b5e213ae43 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -44,31 +44,35 @@ #define KVM_HOST_SMCCC_FUNC(name) KVM_HOST_SMCCC_ID(__KVM_HOST_SMCCC_FUNC_##name) #define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init 0 -#define __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run 1 -#define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context 2 -#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa 3 -#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid 4 -#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context 5 -#define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff 6 -#define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs 7 -#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config 8 -#define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr 9 -#define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr 10 -#define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs 11 -#define __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 12 -#define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs 13 -#define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs 14 -#define __KVM_HOST_SMCCC_FUNC___pkvm_init 15 -#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp 16 -#define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping 17 -#define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 -#define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 -#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 20 #ifndef __ASSEMBLY__ #include +enum __kvm_host_smccc_func { + /* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */ + __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1, + __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context, + __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa, + __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid, + __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context, + __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff, + __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs, + __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config, + __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr, + __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr, + __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs, + __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2, + __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs, + __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs, + __KVM_HOST_SMCCC_FUNC___pkvm_init, + __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, + __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping, + __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector, + __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize, + __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, +}; + #define DECLARE_KVM_VHE_SYM(sym) extern char sym[] #define DECLARE_KVM_NVHE_SYM(sym) extern char kvm_nvhe_sym(sym)[] -- cgit From 8f4566f18db5d1257fc2d5442e16274424a529c1 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Oct 2021 14:58:35 +0100 Subject: arm64: Prevent kexec and hibernation if is_protected_kvm_enabled() When pKVM is enabled, the hypervisor code at EL2 and its data structures are inaccessible to the host kernel and cannot be torn down or replaced as this would defeat the integrity properies which pKVM aims to provide. Furthermore, the ABI between the host and EL2 is flexible and private to whatever the current implementation of KVM requires and so booting a new kernel with an old EL2 component is very likely to end in disaster. In preparation for uninstalling the hyp stub calls which are relied upon to reset EL2, disable kexec and hibernation in the host when protected KVM is enabled. Cc: Marc Zyngier Cc: Quentin Perret Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211008135839.1193-3-will@kernel.org --- arch/arm64/kernel/smp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 6f6ff072acbd..44369b99a57e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -1128,5 +1128,6 @@ bool cpus_are_stuck_in_kernel(void) { bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die()); - return !!cpus_stuck_in_kernel || smp_spin_tables; + return !!cpus_stuck_in_kernel || smp_spin_tables || + is_protected_kvm_enabled(); } -- cgit From 8579a185bacaa64c65e43e251ceede2f7600f7e2 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Oct 2021 14:58:36 +0100 Subject: KVM: arm64: Reject stub hypercalls after pKVM has been initialised The stub hypercalls provide mechanisms to reset and replace the EL2 code, so uninstall them once pKVM has been initialised in order to ensure the integrity of the hypervisor code. To ensure pKVM initialisation remains functional, split cpu_hyp_reinit() into two helper functions to separate usage of the stub from usage of pkvm hypercalls either side of __pkvm_init on the boot CPU. Cc: Marc Zyngier Cc: Quentin Perret Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211008135839.1193-4-will@kernel.org --- arch/arm64/kvm/arm.c | 31 +++++++++++++++++++++++-------- arch/arm64/kvm/hyp/nvhe/host.S | 26 +++++++++++++++++--------- 2 files changed, 40 insertions(+), 17 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fe102cd2e518..9506cf88fa0e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1579,25 +1579,33 @@ static void cpu_set_hyp_vector(void) kvm_call_hyp_nvhe(__pkvm_cpu_set_vector, data->slot); } -static void cpu_hyp_reinit(void) +static void cpu_hyp_init_context(void) { kvm_init_host_cpu_context(&this_cpu_ptr_hyp_sym(kvm_host_data)->host_ctxt); - cpu_hyp_reset(); - - if (is_kernel_in_hyp_mode()) - kvm_timer_init_vhe(); - else + if (!is_kernel_in_hyp_mode()) cpu_init_hyp_mode(); +} +static void cpu_hyp_init_features(void) +{ cpu_set_hyp_vector(); - kvm_arm_init_debug(); + if (is_kernel_in_hyp_mode()) + kvm_timer_init_vhe(); + if (vgic_present) kvm_vgic_init_cpu_hardware(); } +static void cpu_hyp_reinit(void) +{ + cpu_hyp_reset(); + cpu_hyp_init_context(); + cpu_hyp_init_features(); +} + static void _kvm_arch_hardware_enable(void *discard) { if (!__this_cpu_read(kvm_arm_hardware_enabled)) { @@ -1788,10 +1796,17 @@ static int do_pkvm_init(u32 hyp_va_bits) int ret; preempt_disable(); - hyp_install_host_vector(); + cpu_hyp_init_context(); ret = kvm_call_hyp_nvhe(__pkvm_init, hyp_mem_base, hyp_mem_size, num_possible_cpus(), kern_hyp_va(per_cpu_base), hyp_va_bits); + cpu_hyp_init_features(); + + /* + * The stub hypercalls are now disabled, so set our local flag to + * prevent a later re-init attempt in kvm_arch_hardware_enable(). + */ + __this_cpu_write(kvm_arm_hardware_enabled, 1); preempt_enable(); return ret; diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 4b652ffb591d..0c6116d34e18 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -110,17 +110,14 @@ SYM_FUNC_START(__hyp_do_panic) b __host_enter_for_panic SYM_FUNC_END(__hyp_do_panic) -.macro host_el1_sync_vect - .align 7 -.L__vect_start\@: - stp x0, x1, [sp, #-16]! - mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT - cmp x0, #ESR_ELx_EC_HVC64 - b.ne __host_exit - +SYM_FUNC_START(__host_hvc) ldp x0, x1, [sp] // Don't fixup the stack yet + /* No stub for you, sonny Jim */ +alternative_if ARM64_KVM_PROTECTED_MODE + b __host_exit +alternative_else_nop_endif + /* Check for a stub HVC call */ cmp x0, #HVC_STUB_HCALL_NR b.hs __host_exit @@ -137,6 +134,17 @@ SYM_FUNC_END(__hyp_do_panic) ldr x5, =__kvm_handle_stub_hvc hyp_pa x5, x6 br x5 +SYM_FUNC_END(__host_hvc) + +.macro host_el1_sync_vect + .align 7 +.L__vect_start\@: + stp x0, x1, [sp, #-16]! + mrs x0, esr_el2 + lsr x0, x0, #ESR_ELx_EC_SHIFT + cmp x0, #ESR_ELx_EC_HVC64 + b.eq __host_hvc + b __host_exit .L__vect_end\@: .if ((.L__vect_end\@ - .L__vect_start\@) > 0x80) .error "host_el1_sync_vect larger than vector entry" -- cgit From 2f2e1a5069679491d18cf9021da19b40c56a17f3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Oct 2021 14:58:37 +0100 Subject: KVM: arm64: Propagate errors from __pkvm_prot_finalize hypercall If the __pkvm_prot_finalize hypercall returns an error, we WARN but fail to propagate the failure code back to kvm_arch_init(). Pass a pointer to a zero-initialised return variable so that failure to finalise the pKVM protections on a host CPU can be reported back to KVM. Cc: Marc Zyngier Cc: Quentin Perret Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211008135839.1193-5-will@kernel.org --- arch/arm64/kvm/arm.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9506cf88fa0e..13bbf35896cd 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1986,9 +1986,25 @@ out_err: return err; } -static void _kvm_host_prot_finalize(void *discard) +static void _kvm_host_prot_finalize(void *arg) { - WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize)); + int *err = arg; + + if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize))) + WRITE_ONCE(*err, -EINVAL); +} + +static int pkvm_drop_host_privileges(void) +{ + int ret = 0; + + /* + * Flip the static key upfront as that may no longer be possible + * once the host stage 2 is installed. + */ + static_branch_enable(&kvm_protected_mode_initialized); + on_each_cpu(_kvm_host_prot_finalize, &ret, 1); + return ret; } static int finalize_hyp_mode(void) @@ -2002,15 +2018,7 @@ static int finalize_hyp_mode(void) * None of other sections should ever be introspected. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); - - /* - * Flip the static key upfront as that may no longer be possible - * once the host stage 2 is installed. - */ - static_branch_enable(&kvm_protected_mode_initialized); - on_each_cpu(_kvm_host_prot_finalize, NULL, 1); - - return 0; + return pkvm_drop_host_privileges(); } struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) -- cgit From 07036cffe17ec07e8fb630d86f8ea21832d9e57d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Oct 2021 14:58:38 +0100 Subject: KVM: arm64: Prevent re-finalisation of pKVM for a given CPU __pkvm_prot_finalize() completes the deprivilege of the host when pKVM is in use by installing a stage-2 translation table for the calling CPU. Issuing the hypercall multiple times for a given CPU makes little sense, but in such a case just return early with -EPERM rather than go through the whole page-table dance again. Cc: Marc Zyngier Cc: Quentin Perret Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211008135839.1193-6-will@kernel.org --- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index bacd493a4eac..cafe17e5fa8f 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -123,6 +123,9 @@ int __pkvm_prot_finalize(void) struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu; struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); + if (params->hcr_el2 & HCR_VM) + return -EPERM; + params->vttbr = kvm_get_vttbr(mmu); params->vtcr = host_kvm.arch.vtcr; params->hcr_el2 |= HCR_VM; -- cgit From 057bed206f70d624c2eacb43ec56551950a26832 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 8 Oct 2021 14:58:39 +0100 Subject: KVM: arm64: Disable privileged hypercalls after pKVM finalisation After pKVM has been 'finalised' using the __pkvm_prot_finalize hypercall, the calling CPU will have a Stage-2 translation enabled to prevent access to memory pages owned by EL2. Although this forms a significant part of the process to deprivilege the host kernel, we also need to ensure that the hypercall interface is reduced so that the EL2 code cannot, for example, be re-initialised using a new set of vectors. Re-order the hypercalls so that only a suffix remains available after finalisation of pKVM. Cc: Marc Zyngier Cc: Quentin Perret Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211008135839.1193-7-will@kernel.org --- arch/arm64/include/asm/kvm_asm.h | 25 ++++++++++++++----------- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 37 ++++++++++++++++++++++++++----------- 2 files changed, 40 insertions(+), 22 deletions(-) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 43b5e213ae43..4654d27fd221 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -50,27 +50,30 @@ #include enum __kvm_host_smccc_func { + /* Hypercalls available only prior to pKVM finalisation */ /* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */ - __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1, + __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1, + __KVM_HOST_SMCCC_FUNC___pkvm_init, + __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping, + __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector, + __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs, + __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs, + __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config, + __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize, + + /* Hypercalls available after pKVM finalisation */ + __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, + __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, + __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run, __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context, __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa, __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid, __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context, __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff, - __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs, - __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config, __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr, __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr, - __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs, - __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2, __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs, __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs, - __KVM_HOST_SMCCC_FUNC___pkvm_init, - __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, - __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping, - __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector, - __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize, - __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, }; #define DECLARE_KVM_VHE_SYM(sym) extern char sym[] diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 2da6aa8da868..8566805ef62c 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -165,36 +165,51 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); #define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x static const hcall_t host_hcall[] = { - HANDLE_FUNC(__kvm_vcpu_run), + /* ___kvm_hyp_init */ + HANDLE_FUNC(__kvm_get_mdcr_el2), + HANDLE_FUNC(__pkvm_init), + HANDLE_FUNC(__pkvm_create_private_mapping), + HANDLE_FUNC(__pkvm_cpu_set_vector), + HANDLE_FUNC(__kvm_enable_ssbs), + HANDLE_FUNC(__vgic_v3_init_lrs), + HANDLE_FUNC(__vgic_v3_get_gic_config), + HANDLE_FUNC(__pkvm_prot_finalize), + + HANDLE_FUNC(__pkvm_host_share_hyp), HANDLE_FUNC(__kvm_adjust_pc), + HANDLE_FUNC(__kvm_vcpu_run), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid), HANDLE_FUNC(__kvm_flush_cpu_context), HANDLE_FUNC(__kvm_timer_set_cntvoff), - HANDLE_FUNC(__kvm_enable_ssbs), - HANDLE_FUNC(__vgic_v3_get_gic_config), HANDLE_FUNC(__vgic_v3_read_vmcr), HANDLE_FUNC(__vgic_v3_write_vmcr), - HANDLE_FUNC(__vgic_v3_init_lrs), - HANDLE_FUNC(__kvm_get_mdcr_el2), HANDLE_FUNC(__vgic_v3_save_aprs), HANDLE_FUNC(__vgic_v3_restore_aprs), - HANDLE_FUNC(__pkvm_init), - HANDLE_FUNC(__pkvm_cpu_set_vector), - HANDLE_FUNC(__pkvm_host_share_hyp), - HANDLE_FUNC(__pkvm_create_private_mapping), - HANDLE_FUNC(__pkvm_prot_finalize), }; static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(unsigned long, id, host_ctxt, 0); + unsigned long hcall_min = 0; hcall_t hfn; + /* + * If pKVM has been initialised then reject any calls to the + * early "privileged" hypercalls. Note that we cannot reject + * calls to __pkvm_prot_finalize for two reasons: (1) The static + * key used to determine initialisation must be toggled prior to + * finalisation and (2) finalisation is performed on a per-CPU + * basis. This is all fine, however, since __pkvm_prot_finalize + * returns -EPERM after the first call for a given CPU. + */ + if (static_branch_unlikely(&kvm_protected_mode_initialized)) + hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize; + id -= KVM_HOST_SMCCC_ID(0); - if (unlikely(id >= ARRAY_SIZE(host_hcall))) + if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall))) goto inval; hfn = host_hcall[id]; -- cgit