diff options
Diffstat (limited to 'arch/arm64/kvm')
-rw-r--r-- | arch/arm64/kvm/fpsimd.c | 4 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/debug-sr.c | 30 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/entry.S | 36 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/hyp-entry.S | 30 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/switch.c | 18 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/sysreg-sr.c | 78 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/tlb.c | 26 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c | 2 | ||||
-rw-r--r-- | arch/arm64/kvm/regmap.c | 9 | ||||
-rw-r--r-- | arch/arm64/kvm/sys_regs.c | 92 | ||||
-rw-r--r-- | arch/arm64/kvm/va_layout.c | 21 |
11 files changed, 218 insertions, 128 deletions
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 6e3c9c8b2df9..525010504f9d 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -112,9 +112,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1]; - /* Clean guest FP state to memory and invalidate cpu view */ - fpsimd_save(); - fpsimd_flush_cpu_state(); + fpsimd_save_and_flush_cpu_state(); if (guest_has_sve) *guest_zcr = read_sysreg_s(SYS_ZCR_EL12); diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 26781da3ad3e..0fc9872a1467 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -18,40 +18,70 @@ #define save_debug(ptr,reg,nr) \ switch (nr) { \ case 15: ptr[15] = read_debug(reg, 15); \ + /* Fall through */ \ case 14: ptr[14] = read_debug(reg, 14); \ + /* Fall through */ \ case 13: ptr[13] = read_debug(reg, 13); \ + /* Fall through */ \ case 12: ptr[12] = read_debug(reg, 12); \ + /* Fall through */ \ case 11: ptr[11] = read_debug(reg, 11); \ + /* Fall through */ \ case 10: ptr[10] = read_debug(reg, 10); \ + /* Fall through */ \ case 9: ptr[9] = read_debug(reg, 9); \ + /* Fall through */ \ case 8: ptr[8] = read_debug(reg, 8); \ + /* Fall through */ \ case 7: ptr[7] = read_debug(reg, 7); \ + /* Fall through */ \ case 6: ptr[6] = read_debug(reg, 6); \ + /* Fall through */ \ case 5: ptr[5] = read_debug(reg, 5); \ + /* Fall through */ \ case 4: ptr[4] = read_debug(reg, 4); \ + /* Fall through */ \ case 3: ptr[3] = read_debug(reg, 3); \ + /* Fall through */ \ case 2: ptr[2] = read_debug(reg, 2); \ + /* Fall through */ \ case 1: ptr[1] = read_debug(reg, 1); \ + /* Fall through */ \ default: ptr[0] = read_debug(reg, 0); \ } #define restore_debug(ptr,reg,nr) \ switch (nr) { \ case 15: write_debug(ptr[15], reg, 15); \ + /* Fall through */ \ case 14: write_debug(ptr[14], reg, 14); \ + /* Fall through */ \ case 13: write_debug(ptr[13], reg, 13); \ + /* Fall through */ \ case 12: write_debug(ptr[12], reg, 12); \ + /* Fall through */ \ case 11: write_debug(ptr[11], reg, 11); \ + /* Fall through */ \ case 10: write_debug(ptr[10], reg, 10); \ + /* Fall through */ \ case 9: write_debug(ptr[9], reg, 9); \ + /* Fall through */ \ case 8: write_debug(ptr[8], reg, 8); \ + /* Fall through */ \ case 7: write_debug(ptr[7], reg, 7); \ + /* Fall through */ \ case 6: write_debug(ptr[6], reg, 6); \ + /* Fall through */ \ case 5: write_debug(ptr[5], reg, 5); \ + /* Fall through */ \ case 4: write_debug(ptr[4], reg, 4); \ + /* Fall through */ \ case 3: write_debug(ptr[3], reg, 3); \ + /* Fall through */ \ case 2: write_debug(ptr[2], reg, 2); \ + /* Fall through */ \ case 1: write_debug(ptr[1], reg, 1); \ + /* Fall through */ \ default: write_debug(ptr[0], reg, 0); \ } diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index bd34016354ba..e5cc8d66bf53 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -6,6 +6,7 @@ #include <linux/linkage.h> +#include <asm/alternative.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/fpsimdmacros.h> @@ -52,6 +53,20 @@ ENTRY(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Now the host state is stored if we have a pending RAS SError it must + // affect the host. If any asynchronous exception is pending we defer + // the guest entry. The DSB isn't necessary before v8.2 as any SError + // would be fatal. +alternative_if ARM64_HAS_RAS_EXTN + dsb nshst + isb +alternative_else_nop_endif + mrs x1, isr_el1 + cbz x1, 1f + mov x0, #ARM_EXCEPTION_IRQ + ret + +1: add x18, x0, #VCPU_CONTEXT // Macro ptrauth_switch_to_guest format: @@ -127,8 +142,8 @@ ENTRY(__guest_exit) alternative_if ARM64_HAS_RAS_EXTN // If we have the RAS extensions we can consume a pending error - // without an unmask-SError and isb. - esb + // without an unmask-SError and isb. The ESB-instruction consumed any + // pending guest error when we took the exception from the guest. mrs_s x2, SYS_DISR_EL1 str x2, [x1, #(VCPU_FAULT_DISR - VCPU_CONTEXT)] cbz x2, 1f @@ -136,8 +151,16 @@ alternative_if ARM64_HAS_RAS_EXTN orr x0, x0, #(1<<ARM_EXIT_WITH_SERROR_BIT) 1: ret alternative_else - // If we have a pending asynchronous abort, now is the - // time to find out. From your VAXorcist book, page 666: + dsb sy // Synchronize against in-flight ld/st + isb // Prevent an early read of side-effect free ISR + mrs x2, isr_el1 + tbnz x2, #8, 2f // ISR_EL1.A + ret + nop +2: +alternative_endif + // We know we have a pending asynchronous abort, now is the + // time to flush it out. From your VAXorcist book, page 666: // "Threaten me not, oh Evil one! For I speak with // the power of DEC, and I command thee to show thyself!" mrs x2, elr_el2 @@ -145,10 +168,7 @@ alternative_else mrs x4, spsr_el2 mov x5, x0 - dsb sy // Synchronize against in-flight ld/st - nop msr daifclr, #4 // Unmask aborts -alternative_endif // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask @@ -161,6 +181,8 @@ abort_guest_exit_start: .global abort_guest_exit_end abort_guest_exit_end: + msr daifset, #4 // Mask aborts + // If the exception took place, restore the EL1 exception // context so that we can report some information. // Merge the exception code with the SError pending bit. diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index b8e045615961..ffa68d5713f1 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -216,17 +216,34 @@ ENDPROC(\label) .align 11 +.macro check_preamble_length start, end +/* kvm_patch_vector_branch() generates code that jumps over the preamble. */ +.if ((\end-\start) != KVM_VECTOR_PREAMBLE) + .error "KVM vector preamble length mismatch" +.endif +.endm + .macro valid_vect target .align 7 +661: + esb stp x0, x1, [sp, #-16]! +662: b \target + +check_preamble_length 661b, 662b .endm .macro invalid_vect target .align 7 +661: b \target + nop +662: ldp x0, x1, [sp], #16 b \target + +check_preamble_length 661b, 662b .endm ENTRY(__kvm_hyp_vector) @@ -254,13 +271,14 @@ ENDPROC(__kvm_hyp_vector) #ifdef CONFIG_KVM_INDIRECT_VECTORS .macro hyp_ventry .align 7 -1: .rept 27 +1: esb + .rept 26 nop .endr /* * The default sequence is to directly branch to the KVM vectors, * using the computed offset. This applies for VHE as well as - * !ARM64_HARDEN_EL2_VECTORS. + * !ARM64_HARDEN_EL2_VECTORS. The first vector must always run the preamble. * * For ARM64_HARDEN_EL2_VECTORS configurations, this gets replaced * with: @@ -271,12 +289,13 @@ ENDPROC(__kvm_hyp_vector) * movk x0, #((addr >> 32) & 0xffff), lsl #32 * br x0 * - * Where addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + 4. + * Where: + * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE. * See kvm_patch_vector_branch for details. */ alternative_cb kvm_patch_vector_branch - b __kvm_hyp_vector + (1b - 0b) - nop + stp x0, x1, [sp, #-16]! + b __kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE) nop nop nop @@ -301,6 +320,7 @@ ENTRY(__bp_harden_hyp_vecs_end) .popsection ENTRY(__smccc_workaround_1_smc_start) + esb sub sp, sp, #(8 * 4) stp x2, x3, [sp, #(8 * 0)] stp x0, x1, [sp, #(8 * 2)] diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index b0041812bca9..bd978ad71936 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -264,7 +264,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) tmp = read_sysreg(par_el1); write_sysreg(par, par_el1); - if (unlikely(tmp & 1)) + if (unlikely(tmp & SYS_PAR_EL1_F)) return false; /* Translation failed, back to guest */ /* Convert PAR to HPFAR format */ @@ -284,7 +284,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW) return true; - far = read_sysreg_el2(far); + far = read_sysreg_el2(SYS_FAR); /* * The HPFAR can be invalid if the stage 2 fault did not @@ -401,7 +401,7 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) - vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr); + vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); /* * We're using the raw exception code in order to only process @@ -604,7 +604,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) * Naturally, we want to avoid this. */ if (system_uses_irq_prio_masking()) { - gic_write_pmr(GIC_PRIO_IRQON); + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); dsb(sy); } @@ -697,8 +697,8 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par, asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va)); __hyp_do_panic(str_va, - spsr, elr, - read_sysreg(esr_el2), read_sysreg_el2(far), + spsr, elr, + read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR), read_sysreg(hpfar_el2), par, vcpu); } @@ -713,15 +713,15 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, panic(__hyp_panic_string, spsr, elr, - read_sysreg_el2(esr), read_sysreg_el2(far), + read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR), read_sysreg(hpfar_el2), par, vcpu); } NOKPROBE_SYMBOL(__hyp_call_panic_vhe); void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) { - u64 spsr = read_sysreg_el2(spsr); - u64 elr = read_sysreg_el2(elr); + u64 spsr = read_sysreg_el2(SYS_SPSR); + u64 elr = read_sysreg_el2(SYS_ELR); u64 par = read_sysreg(par_el1); if (!has_vhe()) diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index c283f7cbc702..7ddbc849b580 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -43,33 +43,33 @@ static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) { ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1); - ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(sctlr); + ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(SYS_SCTLR); ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1); - ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(cpacr); - ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(ttbr0); - ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(ttbr1); - ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(tcr); - ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(esr); - ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(afsr0); - ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(afsr1); - ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(far); - ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(mair); - ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(vbar); - ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(contextidr); - ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(amair); - ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(cntkctl); + ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(SYS_CPACR); + ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(SYS_TTBR0); + ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(SYS_TTBR1); + ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(SYS_TCR); + ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(SYS_ESR); + ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(SYS_AFSR0); + ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(SYS_AFSR1); + ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(SYS_FAR); + ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(SYS_MAIR); + ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(SYS_VBAR); + ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(SYS_CONTEXTIDR); + ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(SYS_AMAIR); + ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(SYS_CNTKCTL); ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1); ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1); ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1); - ctxt->gp_regs.elr_el1 = read_sysreg_el1(elr); - ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr); + ctxt->gp_regs.elr_el1 = read_sysreg_el1(SYS_ELR); + ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR); } static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) { - ctxt->gp_regs.regs.pc = read_sysreg_el2(elr); - ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr); + ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR); + ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2); @@ -109,35 +109,35 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) { - write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); - write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); + write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); + write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); } static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], sctlr); - write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); - write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], cpacr); - write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], ttbr0); - write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], ttbr1); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], tcr); - write_sysreg_el1(ctxt->sys_regs[ESR_EL1], esr); - write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], afsr0); - write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], afsr1); - write_sysreg_el1(ctxt->sys_regs[FAR_EL1], far); - write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], mair); - write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], vbar); - write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],contextidr); - write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], amair); - write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], cntkctl); + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); + write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); + write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); + write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); + write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); + write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); + write_sysreg_el1(ctxt->sys_regs[FAR_EL1], SYS_FAR); + write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], SYS_MAIR); + write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], SYS_VBAR); + write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR); + write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], SYS_AMAIR); + write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], SYS_CNTKCTL); write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); - write_sysreg_el1(ctxt->gp_regs.elr_el1, elr); - write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr); + write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); + write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); } static void __hyp_text @@ -160,8 +160,8 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t) pstate = PSR_MODE_EL2h | PSR_IL_BIT; - write_sysreg_el2(ctxt->gp_regs.regs.pc, elr); - write_sysreg_el2(pstate, spsr); + write_sysreg_el2(ctxt->gp_regs.regs.pc, SYS_ELR); + write_sysreg_el2(pstate, SYS_SPSR); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 32078b767f63..c466060b76d6 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -33,12 +33,12 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, * in the TCR_EL1 register. We also need to prevent it to * allocate IPA->PA walks, so we enable the S1 MMU... */ - val = cxt->tcr = read_sysreg_el1(tcr); + val = cxt->tcr = read_sysreg_el1(SYS_TCR); val |= TCR_EPD1_MASK | TCR_EPD0_MASK; - write_sysreg_el1(val, tcr); - val = cxt->sctlr = read_sysreg_el1(sctlr); + write_sysreg_el1(val, SYS_TCR); + val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); val |= SCTLR_ELx_M; - write_sysreg_el1(val, sctlr); + write_sysreg_el1(val, SYS_SCTLR); } /* @@ -85,8 +85,8 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) { /* Restore the registers to what they were */ - write_sysreg_el1(cxt->tcr, tcr); - write_sysreg_el1(cxt->sctlr, sctlr); + write_sysreg_el1(cxt->tcr, SYS_TCR); + write_sysreg_el1(cxt->sctlr, SYS_SCTLR); } local_irq_restore(cxt->flags); @@ -193,6 +193,18 @@ void __hyp_text __kvm_flush_vm_context(void) { dsb(ishst); __tlbi(alle1is); - asm volatile("ic ialluis" : : ); + + /* + * VIPT and PIPT caches are not affected by VMID, so no maintenance + * is necessary across a VMID rollover. + * + * VPIPT caches constrain lookup and maintenance to the active VMID, + * so we need to invalidate lines with a stale VMID to avoid an ABA + * race after multiple rollovers. + * + */ + if (icache_is_vpipt()) + asm volatile("ic ialluis"); + dsb(ish); } diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index ba2aaeb84c6c..29ee1feba4eb 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -16,7 +16,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) - return !!(read_sysreg_el2(spsr) & PSR_AA32_E_BIT); + return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT); return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE); } diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c index d66613e6ad08..a900181e3867 100644 --- a/arch/arm64/kvm/regmap.c +++ b/arch/arm64/kvm/regmap.c @@ -152,7 +152,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu) switch (spsr_idx) { case KVM_SPSR_SVC: - return read_sysreg_el1(spsr); + return read_sysreg_el1(SYS_SPSR); case KVM_SPSR_ABT: return read_sysreg(spsr_abt); case KVM_SPSR_UND: @@ -177,14 +177,19 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v) switch (spsr_idx) { case KVM_SPSR_SVC: - write_sysreg_el1(v, spsr); + write_sysreg_el1(v, SYS_SPSR); + break; case KVM_SPSR_ABT: write_sysreg(v, spsr_abt); + break; case KVM_SPSR_UND: write_sysreg(v, spsr_und); + break; case KVM_SPSR_IRQ: write_sysreg(v, spsr_irq); + break; case KVM_SPSR_FIQ: write_sysreg(v, spsr_fiq); + break; } } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index ce933f296049..2071260a275b 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -81,24 +81,24 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) */ switch (reg) { case CSSELR_EL1: return read_sysreg_s(SYS_CSSELR_EL1); - case SCTLR_EL1: return read_sysreg_s(sctlr_EL12); + case SCTLR_EL1: return read_sysreg_s(SYS_SCTLR_EL12); case ACTLR_EL1: return read_sysreg_s(SYS_ACTLR_EL1); - case CPACR_EL1: return read_sysreg_s(cpacr_EL12); - case TTBR0_EL1: return read_sysreg_s(ttbr0_EL12); - case TTBR1_EL1: return read_sysreg_s(ttbr1_EL12); - case TCR_EL1: return read_sysreg_s(tcr_EL12); - case ESR_EL1: return read_sysreg_s(esr_EL12); - case AFSR0_EL1: return read_sysreg_s(afsr0_EL12); - case AFSR1_EL1: return read_sysreg_s(afsr1_EL12); - case FAR_EL1: return read_sysreg_s(far_EL12); - case MAIR_EL1: return read_sysreg_s(mair_EL12); - case VBAR_EL1: return read_sysreg_s(vbar_EL12); - case CONTEXTIDR_EL1: return read_sysreg_s(contextidr_EL12); + case CPACR_EL1: return read_sysreg_s(SYS_CPACR_EL12); + case TTBR0_EL1: return read_sysreg_s(SYS_TTBR0_EL12); + case TTBR1_EL1: return read_sysreg_s(SYS_TTBR1_EL12); + case TCR_EL1: return read_sysreg_s(SYS_TCR_EL12); + case ESR_EL1: return read_sysreg_s(SYS_ESR_EL12); + case AFSR0_EL1: return read_sysreg_s(SYS_AFSR0_EL12); + case AFSR1_EL1: return read_sysreg_s(SYS_AFSR1_EL12); + case FAR_EL1: return read_sysreg_s(SYS_FAR_EL12); + case MAIR_EL1: return read_sysreg_s(SYS_MAIR_EL12); + case VBAR_EL1: return read_sysreg_s(SYS_VBAR_EL12); + case CONTEXTIDR_EL1: return read_sysreg_s(SYS_CONTEXTIDR_EL12); case TPIDR_EL0: return read_sysreg_s(SYS_TPIDR_EL0); case TPIDRRO_EL0: return read_sysreg_s(SYS_TPIDRRO_EL0); case TPIDR_EL1: return read_sysreg_s(SYS_TPIDR_EL1); - case AMAIR_EL1: return read_sysreg_s(amair_EL12); - case CNTKCTL_EL1: return read_sysreg_s(cntkctl_EL12); + case AMAIR_EL1: return read_sysreg_s(SYS_AMAIR_EL12); + case CNTKCTL_EL1: return read_sysreg_s(SYS_CNTKCTL_EL12); case PAR_EL1: return read_sysreg_s(SYS_PAR_EL1); case DACR32_EL2: return read_sysreg_s(SYS_DACR32_EL2); case IFSR32_EL2: return read_sysreg_s(SYS_IFSR32_EL2); @@ -124,24 +124,24 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) */ switch (reg) { case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); return; - case SCTLR_EL1: write_sysreg_s(val, sctlr_EL12); return; + case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); return; case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); return; - case CPACR_EL1: write_sysreg_s(val, cpacr_EL12); return; - case TTBR0_EL1: write_sysreg_s(val, ttbr0_EL12); return; - case TTBR1_EL1: write_sysreg_s(val, ttbr1_EL12); return; - case TCR_EL1: write_sysreg_s(val, tcr_EL12); return; - case ESR_EL1: write_sysreg_s(val, esr_EL12); return; - case AFSR0_EL1: write_sysreg_s(val, afsr0_EL12); return; - case AFSR1_EL1: write_sysreg_s(val, afsr1_EL12); return; - case FAR_EL1: write_sysreg_s(val, far_EL12); return; - case MAIR_EL1: write_sysreg_s(val, mair_EL12); return; - case VBAR_EL1: write_sysreg_s(val, vbar_EL12); return; - case CONTEXTIDR_EL1: write_sysreg_s(val, contextidr_EL12); return; + case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); return; + case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); return; + case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); return; + case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); return; + case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); return; + case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); return; + case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); return; + case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); return; + case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); return; + case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); return; + case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12); return; case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); return; case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); return; case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); return; - case AMAIR_EL1: write_sysreg_s(val, amair_EL12); return; - case CNTKCTL_EL1: write_sysreg_s(val, cntkctl_EL12); return; + case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); return; + case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); return; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); return; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); return; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); return; @@ -632,7 +632,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); - __vcpu_sys_reg(vcpu, PMCR_EL0) = val; + __vcpu_sys_reg(vcpu, r->reg) = val; } static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) @@ -865,12 +865,12 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (r->Op2 & 0x1) { /* accessing PMCNTENSET_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val; - kvm_pmu_enable_counter(vcpu, val); + kvm_pmu_enable_counter_mask(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); } else { /* accessing PMCNTENCLR_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val; - kvm_pmu_disable_counter(vcpu, val); + kvm_pmu_disable_counter_mask(vcpu, val); } } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask; @@ -981,13 +981,13 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ - trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \ + trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \ - trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \ + trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \ - trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \ + trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ - trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr } + trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ @@ -1540,7 +1540,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, - { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, }, + { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 }, @@ -2254,13 +2254,19 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, } static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *table, size_t num) + const struct sys_reg_desc *table, size_t num, + unsigned long *bmap) { unsigned long i; for (i = 0; i < num; i++) - if (table[i].reset) + if (table[i].reset) { + int reg = table[i].reg; + table[i].reset(vcpu, &table[i]); + if (reg > 0 && reg < NR_SYS_REGS) + set_bit(reg, bmap); + } } /** @@ -2774,18 +2780,16 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { size_t num; const struct sys_reg_desc *table; - - /* Catch someone adding a register without putting in reset entry. */ - memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs)); + DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, }; /* Generic chip reset first (so target could override). */ - reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap); table = get_target_table(vcpu->arch.target, true, &num); - reset_sys_reg_descs(vcpu, table, num); + reset_sys_reg_descs(vcpu, table, num, bmap); for (num = 1; num < NR_SYS_REGS; num++) { - if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + if (WARN(!test_bit(num, bmap), "Didn't reset __vcpu_sys_reg(%zi)\n", num)) break; } diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index 2947ab1b0fa5..2cf7d4b606c3 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -29,25 +29,25 @@ static void compute_layout(void) int kva_msb; /* Where is my RAM region? */ - hyp_va_msb = idmap_addr & BIT(VA_BITS - 1); - hyp_va_msb ^= BIT(VA_BITS - 1); + hyp_va_msb = idmap_addr & BIT(vabits_actual - 1); + hyp_va_msb ^= BIT(vabits_actual - 1); kva_msb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^ (u64)(high_memory - 1)); - if (kva_msb == (VA_BITS - 1)) { + if (kva_msb == (vabits_actual - 1)) { /* * No space in the address, let's compute the mask so - * that it covers (VA_BITS - 1) bits, and the region + * that it covers (vabits_actual - 1) bits, and the region * bit. The tag stays set to zero. */ - va_mask = BIT(VA_BITS - 1) - 1; + va_mask = BIT(vabits_actual - 1) - 1; va_mask |= hyp_va_msb; } else { /* * We do have some free bits to insert a random tag. * Hyp VAs are now created from kernel linear map VAs - * using the following formula (with V == VA_BITS): + * using the following formula (with V == vabits_actual): * * 63 ... V | V-1 | V-2 .. tag_lsb | tag_lsb - 1 .. 0 * --------------------------------------------------------- @@ -55,7 +55,7 @@ static void compute_layout(void) */ tag_lsb = kva_msb; va_mask = GENMASK_ULL(tag_lsb - 1, 0); - tag_val = get_random_long() & GENMASK_ULL(VA_BITS - 2, tag_lsb); + tag_val = get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb); tag_val |= hyp_va_msb; tag_val >>= tag_lsb; } @@ -170,11 +170,10 @@ void kvm_patch_vector_branch(struct alt_instr *alt, addr |= ((u64)origptr & GENMASK_ULL(10, 7)); /* - * Branch to the second instruction in the vectors in order to - * avoid the initial store on the stack (which we already - * perform in the hardening vectors). + * Branch over the preamble in order to avoid the initial store on + * the stack (which we already perform in the hardening vectors). */ - addr += AARCH64_INSN_SIZE; + addr += KVM_VECTOR_PREAMBLE; /* stp x0, x1, [sp, #-16]! */ insn = aarch64_insn_gen_load_store_pair(AARCH64_INSN_REG_0, |