diff options
Diffstat (limited to 'virt/kvm/arm')
-rw-r--r-- | virt/kvm/arm/aarch32.c | 159 | ||||
-rw-r--r-- | virt/kvm/arm/arch_timer.c | 3 | ||||
-rw-r--r-- | virt/kvm/arm/arm.c | 18 | ||||
-rw-r--r-- | virt/kvm/arm/hyp/aarch32.c | 8 | ||||
-rw-r--r-- | virt/kvm/arm/mmio.c | 6 | ||||
-rw-r--r-- | virt/kvm/arm/mmu.c | 35 | ||||
-rw-r--r-- | virt/kvm/arm/pmu.c | 3 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-its.c | 3 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio-v2.c | 10 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio-v3.c | 12 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio.c | 179 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio.h | 11 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v3.c | 6 |
13 files changed, 354 insertions, 99 deletions
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c index c4c57ba99e90..40a62a99fbf8 100644 --- a/virt/kvm/arm/aarch32.c +++ b/virt/kvm/arm/aarch32.c @@ -10,10 +10,15 @@ * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ +#include <linux/bits.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> +#define DFSR_FSC_EXTABT_LPAE 0x10 +#define DFSR_FSC_EXTABT_nLPAE 0x08 +#define DFSR_LPAE BIT(9) + /* * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. */ @@ -28,25 +33,135 @@ static const u8 return_offsets[8][2] = { [7] = { 4, 4 }, /* FIQ, unused */ }; +static bool pre_fault_synchronize(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + if (vcpu->arch.sysregs_loaded_on_cpu) { + kvm_arch_vcpu_put(vcpu); + return true; + } + + preempt_enable(); + return false; +} + +static void post_fault_synchronize(struct kvm_vcpu *vcpu, bool loaded) +{ + if (loaded) { + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + } +} + +/* + * When an exception is taken, most CPSR fields are left unchanged in the + * handler. However, some are explicitly overridden (e.g. M[4:0]). + * + * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with + * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was + * obsoleted by the ARMv7 virtualization extensions and is RES0. + * + * For the SPSR layout seen from AArch32, see: + * - ARM DDI 0406C.d, page B1-1148 + * - ARM DDI 0487E.a, page G8-6264 + * + * For the SPSR_ELx layout for AArch32 seen from AArch64, see: + * - ARM DDI 0487E.a, page C5-426 + * + * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from + * MSB to LSB. + */ +static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) +{ + u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); + unsigned long old, new; + + old = *vcpu_cpsr(vcpu); + new = 0; + + new |= (old & PSR_AA32_N_BIT); + new |= (old & PSR_AA32_Z_BIT); + new |= (old & PSR_AA32_C_BIT); + new |= (old & PSR_AA32_V_BIT); + new |= (old & PSR_AA32_Q_BIT); + + // CPSR.IT[7:0] are set to zero upon any exception + // See ARM DDI 0487E.a, section G1.12.3 + // See ARM DDI 0406C.d, section B1.8.3 + + new |= (old & PSR_AA32_DIT_BIT); + + // CPSR.SSBS is set to SCTLR.DSSBS upon any exception + // See ARM DDI 0487E.a, page G8-6244 + if (sctlr & BIT(31)) + new |= PSR_AA32_SSBS_BIT; + + // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 + // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented + // See ARM DDI 0487E.a, page G8-6246 + new |= (old & PSR_AA32_PAN_BIT); + if (!(sctlr & BIT(23))) + new |= PSR_AA32_PAN_BIT; + + // SS does not exist in AArch32, so ignore + + // CPSR.IL is set to zero upon any exception + // See ARM DDI 0487E.a, page G1-5527 + + new |= (old & PSR_AA32_GE_MASK); + + // CPSR.IT[7:0] are set to zero upon any exception + // See prior comment above + + // CPSR.E is set to SCTLR.EE upon any exception + // See ARM DDI 0487E.a, page G8-6245 + // See ARM DDI 0406C.d, page B4-1701 + if (sctlr & BIT(25)) + new |= PSR_AA32_E_BIT; + + // CPSR.A is unchanged upon an exception to Undefined, Supervisor + // CPSR.A is set upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_A_BIT); + if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) + new |= PSR_AA32_A_BIT; + + // CPSR.I is set upon any exception + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= PSR_AA32_I_BIT; + + // CPSR.F is set upon an exception to FIQ + // CPSR.F is unchanged upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_F_BIT); + if (mode == PSR_AA32_MODE_FIQ) + new |= PSR_AA32_F_BIT; + + // CPSR.T is set to SCTLR.TE upon any exception + // See ARM DDI 0487E.a, page G8-5514 + // See ARM DDI 0406C.d, page B1-1181 + if (sctlr & BIT(30)) + new |= PSR_AA32_T_BIT; + + new |= mode; + + return new; +} + static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) { - unsigned long cpsr; - unsigned long new_spsr_value = *vcpu_cpsr(vcpu); - bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT); + unsigned long spsr = *vcpu_cpsr(vcpu); + bool is_thumb = (spsr & PSR_AA32_T_BIT); u32 return_offset = return_offsets[vect_offset >> 2][is_thumb]; u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); - cpsr = mode | PSR_AA32_I_BIT; - - if (sctlr & (1 << 30)) - cpsr |= PSR_AA32_T_BIT; - if (sctlr & (1 << 25)) - cpsr |= PSR_AA32_E_BIT; - - *vcpu_cpsr(vcpu) = cpsr; + *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); /* Note: These now point to the banked copies */ - vcpu_write_spsr(vcpu, new_spsr_value); + vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr)); *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; /* Branch to exception vector */ @@ -60,7 +175,10 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) void kvm_inject_undef32(struct kvm_vcpu *vcpu) { + bool loaded = pre_fault_synchronize(vcpu); + prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4); + post_fault_synchronize(vcpu, loaded); } /* @@ -73,6 +191,9 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 vect_offset; u32 *far, *fsr; bool is_lpae; + bool loaded; + + loaded = pre_fault_synchronize(vcpu); if (is_pabt) { vect_offset = 12; @@ -84,16 +205,20 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, fsr = &vcpu_cp15(vcpu, c5_DFSR); } - prepare_fault32(vcpu, PSR_AA32_MODE_ABT | PSR_AA32_A_BIT, vect_offset); + prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset); *far = addr; /* Give the guest an IMPLEMENTATION DEFINED exception */ is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31); - if (is_lpae) - *fsr = 1 << 9 | 0x34; - else - *fsr = 0x14; + if (is_lpae) { + *fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; + } else { + /* no need to shuffle FS[4] into DFSR[10] as its 0 */ + *fsr = DFSR_FSC_EXTABT_nLPAE; + } + + post_fault_synchronize(vcpu, loaded); } void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr) diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 1be486d5d7cb..ca90c0974ae8 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -805,6 +805,7 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, switch (treg) { case TIMER_REG_TVAL: val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff; + val &= lower_32_bits(val); break; case TIMER_REG_CTL: @@ -850,7 +851,7 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, { switch (treg) { case TIMER_REG_TVAL: - timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val; + timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val; break; case TIMER_REG_CTL: diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 9b778c51af1b..d9585f6a897a 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -356,6 +356,12 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) return kvm_vgic_vcpu_init(vcpu); } +#define __ptrauth_save_key(regs, key) \ +({ \ + regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ + regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ +}) + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { int *last_ran; @@ -388,7 +394,17 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) else vcpu_set_wfe_traps(vcpu); - vcpu_ptrauth_setup_lazy(vcpu); + if (vcpu_has_ptrauth(vcpu)) { + struct kvm_cpu_context *ctxt = vcpu->arch.host_cpu_context; + + __ptrauth_save_key(ctxt->sys_regs, APIA); + __ptrauth_save_key(ctxt->sys_regs, APIB); + __ptrauth_save_key(ctxt->sys_regs, APDA); + __ptrauth_save_key(ctxt->sys_regs, APDB); + __ptrauth_save_key(ctxt->sys_regs, APGA); + + vcpu_ptrauth_disable(vcpu); + } } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c index 6af5c91337f2..f274fabb4301 100644 --- a/virt/kvm/arm/mmio.c +++ b/virt/kvm/arm/mmio.c @@ -105,6 +105,9 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) data = (data ^ mask) - mask; } + if (!vcpu->arch.mmio_decode.sixty_four) + data = data & 0xffffffff; + trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, &data); data = vcpu_data_host_to_guest(vcpu, data, len); @@ -125,6 +128,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) unsigned long rt; int access_size; bool sign_extend; + bool sixty_four; if (kvm_vcpu_dabt_iss1tw(vcpu)) { /* page table accesses IO mem: tell guest to fix its TTBR */ @@ -138,11 +142,13 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) *is_write = kvm_vcpu_dabt_iswrite(vcpu); sign_extend = kvm_vcpu_dabt_issext(vcpu); + sixty_four = kvm_vcpu_dabt_issf(vcpu); rt = kvm_vcpu_dabt_get_rd(vcpu); *len = access_size; vcpu->arch.mmio_decode.sign_extend = sign_extend; vcpu->arch.mmio_decode.rt = rt; + vcpu->arch.mmio_decode.sixty_four = sixty_four; return 0; } diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 198e5171e1f7..1f0d95c2f5f9 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -38,6 +38,11 @@ static unsigned long io_map_base; #define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0) #define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1) +static bool is_iomap(unsigned long flags) +{ + return flags & KVM_S2PTE_FLAG_IS_IOMAP; +} + static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); @@ -1194,7 +1199,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, return true; } -static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz) { pud_t *pudp; pmd_t *pmdp; @@ -1206,11 +1211,11 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) return false; if (pudp) - return kvm_s2pud_exec(pudp); + return sz <= PUD_SIZE && kvm_s2pud_exec(pudp); else if (pmdp) - return kvm_s2pmd_exec(pmdp); + return sz <= PMD_SIZE && kvm_s2pmd_exec(pmdp); else - return kvm_s2pte_exec(ptep); + return sz == PAGE_SIZE && kvm_s2pte_exec(ptep); } static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, @@ -1698,6 +1703,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = vma_kernel_pagesize(vma); if (logging_active || + (vma->vm_flags & VM_PFNMAP) || !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { force_pte = true; vma_pagesize = PAGE_SIZE; @@ -1760,6 +1766,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, writable = false; } + if (exec_fault && is_iomap(flags)) + return -ENOEXEC; + spin_lock(&kvm->mmu_lock); if (mmu_notifier_retry(kvm, mmu_seq)) goto out_unlock; @@ -1781,7 +1790,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (writable) kvm_set_pfn_dirty(pfn); - if (fault_status != FSC_PERM) + if (fault_status != FSC_PERM && !is_iomap(flags)) clean_dcache_guest_page(pfn, vma_pagesize); if (exec_fault) @@ -1796,7 +1805,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * execute permissions, and we preserve whatever we have. */ needs_exec = exec_fault || - (fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa)); + (fault_status == FSC_PERM && + stage2_is_exec(kvm, fault_ipa, vma_pagesize)); if (vma_pagesize == PUD_SIZE) { pud_t new_pud = kvm_pfn_pud(pfn, mem_type); @@ -1948,9 +1958,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) if (kvm_is_error_hva(hva) || (write_fault && !writable)) { if (is_iabt) { /* Prefetch Abort on I/O address */ - kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - ret = 1; - goto out_unlock; + ret = -ENOEXEC; + goto out; } /* @@ -1992,6 +2001,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; +out: + if (ret == -ENOEXEC) { + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + } out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; @@ -2134,7 +2148,8 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) if (!kvm->arch.pgd) return 0; trace_kvm_test_age_hva(hva); - return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); + return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE, + kvm_test_age_hva_handler, NULL); } void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c index da740764a7ee..87cde3c6701e 100644 --- a/virt/kvm/arm/pmu.c +++ b/virt/kvm/arm/pmu.c @@ -305,6 +305,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) if (val == 0) return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) + return; + enable = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) { if (!(val & BIT(i))) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 482036612adf..21a18ad58e7e 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -2265,7 +2265,8 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT); coll_id = val & KVM_ITS_CTE_ICID_MASK; - if (target_addr >= atomic_read(&kvm->online_vcpus)) + if (target_addr != COLLECTION_NOT_MAPPED && + target_addr >= atomic_read(&kvm->online_vcpus)) return -EINVAL; collection = find_collection(its, coll_id); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 5945f062d749..7b288eb391b8 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -415,18 +415,20 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = { vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, - vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_spending, + NULL, vgic_uaccess_write_spending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + NULL, vgic_uaccess_write_cpending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 936962abc38d..89f0ce81d01b 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -489,11 +489,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, @@ -562,12 +562,12 @@ static const struct vgic_register_region vgic_v3_sgibase_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index b249220025bc..e3bd622f2fe4 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -184,17 +184,6 @@ static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void) return vcpu; } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) -{ - if (is_uaccess) - return; - - irq->pending_latch = true; - vgic_irq_set_phys_active(irq, true); -} - static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && @@ -205,7 +194,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !vgic_get_mmio_requester_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -220,22 +208,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, } raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; if (irq->hw) - vgic_hw_irq_spending(vcpu, irq, is_uaccess); - else - irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) { - if (is_uaccess) - return; + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + + /* + * GICv2 SGIs are terribly broken. We can't restore + * the source of the interrupt, so just pick the vcpu + * itself as the source... + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source |= BIT(vcpu->vcpu_id); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + return 0; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ irq->pending_latch = false; /* @@ -258,7 +272,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !vgic_get_mmio_requester_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -275,7 +288,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) - vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; @@ -284,8 +297,39 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } } -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) + +/* + * If we are fiddling with an IRQ's active state, we have to make sure the IRQ + * is not queued on some running VCPU's LRs, because then the change to the + * active state can be overwritten when the VCPU's state is synced coming back + * from the guest. + * + * For shared interrupts as well as GICv3 private interrupts, we have to + * stop all the VCPUs because interrupts can be migrated while we don't hold + * the IRQ locks and we don't want to be chasing moving targets. + * + * For GICv2 private interrupts we don't have to do anything because + * userspace accesses to the VGIC state already require all VCPUs to be + * stopped, and only the VCPU itself can modify its private interrupts + * active state, which guarantees that the VCPU is not running. + */ +static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_halt_guest(vcpu->kvm); +} + +/* See vgic_access_active_prepare */ +static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_resume_guest(vcpu->kvm); +} + +static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; @@ -295,6 +339,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + /* + * Even for HW interrupts, don't evaluate the HW state as + * all the guest is interested in is the virtual state. + */ if (irq->active) value |= (1U << i); @@ -304,6 +352,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 val; + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + val = __vgic_mmio_read_active(vcpu, addr, len); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); + + return val; +} + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __vgic_mmio_read_active(vcpu, addr, len); +} + /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) @@ -355,34 +426,34 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } -/* - * If we are fiddling with an IRQ's active state, we have to make sure the IRQ - * is not queued on some running VCPU's LRs, because then the change to the - * active state can be overwritten when the VCPU's state is synced coming back - * from the guest. - * - * For shared interrupts, we have to stop all the VCPUs because interrupts can - * be migrated while we don't hold the IRQ locks and we don't want to be - * chasing moving targets. - * - * For private interrupts we don't have to do anything because userspace - * accesses to the VGIC state already require all VCPUs to be stopped, and - * only the VCPU itself can modify its private interrupts active state, which - * guarantees that the VCPU is not running. - */ -static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) { - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_halt_guest(vcpu->kvm); -} + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; -/* See vgic_change_active_prepare */ -static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_resume_guest(vcpu->kvm); + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* + * More fun with GICv2 SGIs! If we're clearing one of them + * from userspace, which source vcpu to clear? Let's not + * even think of it, and blow the whole set. + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source = 0; + + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; } static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, @@ -406,11 +477,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } @@ -443,11 +514,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h index 836f418f1ee8..71f01ef40533 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ b/virt/kvm/arm/vgic/vgic-mmio.h @@ -154,9 +154,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index a4ad431c92a9..e821fe242dbc 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -363,8 +363,8 @@ retry: int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - int last_byte_offset = -1; struct vgic_irq *irq; + gpa_t last_ptr = ~(gpa_t)0; int ret; u8 val; @@ -384,11 +384,11 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; - if (byte_offset != last_byte_offset) { + if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; - last_byte_offset = byte_offset; + last_ptr = ptr; } stored = val & (1U << bit_nr); |