From c1426e4c5add09042840013dfa5565e6be6d412e Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Wed, 4 Mar 2015 11:14:34 +0100 Subject: KVM: arm/arm64: implement kvm_arch_intc_initialized On arm/arm64 the VGIC is dynamically instantiated and it is useful to expose its state, especially for irqfd setup. This patch defines __KVM_HAVE_ARCH_INTC_INITIALIZED and implements kvm_arch_intc_initialized. Signed-off-by: Eric Auger Acked-by: Christoffer Dall Reviewed-by: Andre Przywara Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm64/include/asm/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/arm64/include') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8ac3c70fe3c6..967fb1cee300 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -28,6 +28,8 @@ #include #include +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else -- cgit v1.2.3 From 174178fed338edba66ab9580af0c5d9e1a4e5019 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Wed, 4 Mar 2015 11:14:36 +0100 Subject: KVM: arm/arm64: add irqfd support This patch enables irqfd on arm/arm64. Both irqfd and resamplefd are supported. Injection is implemented in vgic.c without routing. This patch enables CONFIG_HAVE_KVM_EVENTFD and CONFIG_HAVE_KVM_IRQFD. KVM_CAP_IRQFD is now advertised. KVM_CAP_IRQFD_RESAMPLE capability automatically is advertised as soon as CONFIG_HAVE_KVM_IRQFD is set. Irqfd injection is restricted to SPI. The rationale behind not supporting PPI irqfd injection is that any device using a PPI would be a private-to-the-CPU device (timer for instance), so its state would have to be context-switched along with the VCPU and would require in-kernel wiring anyhow. It is not a relevant use case for irqfds. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- Documentation/virtual/kvm/api.txt | 6 ++++- arch/arm/include/uapi/asm/kvm.h | 3 +++ arch/arm/kvm/Kconfig | 2 ++ arch/arm/kvm/Makefile | 2 +- arch/arm/kvm/arm.c | 1 + arch/arm64/include/uapi/asm/kvm.h | 3 +++ arch/arm64/kvm/Kconfig | 2 ++ arch/arm64/kvm/Makefile | 2 +- virt/kvm/arm/vgic.c | 48 +++++++++++++++++++++++++++++++++++++++ 9 files changed, 66 insertions(+), 3 deletions(-) (limited to 'arch/arm64/include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index b112efc816f1..b265d8e50be0 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2234,7 +2234,7 @@ into the hash PTE second double word). 4.75 KVM_IRQFD Capability: KVM_CAP_IRQFD -Architectures: x86 s390 +Architectures: x86 s390 arm arm64 Type: vm ioctl Parameters: struct kvm_irqfd (in) Returns: 0 on success, -1 on error @@ -2260,6 +2260,10 @@ Note that closing the resamplefd is not sufficient to disable the irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. +On ARM/ARM64, the gsi field in the kvm_irqfd struct specifies the Shared +Peripheral Interrupt (SPI) index, such that the GIC interrupt ID is +given by gsi + 32. + 4.76 KVM_PPC_ALLOCATE_HTAB Capability: KVM_CAP_PPC_ALLOC_HTAB diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 0db25bc32864..2499867dd0d8 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -198,6 +198,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 83a448e8192b..f1f79d104309 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -28,6 +28,8 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU select MMU_NOTIFIER + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER ---help--- Support hosting virtualized guest machines. diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 60be7be4c824..a093bf125ca8 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5e893ebb9de7..cc96619f10a4 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -171,6 +171,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: + case KVM_CAP_IRQFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: case KVM_CAP_SYNC_MMU: diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 3ef77a466018..c154c0b7eb60 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -191,6 +191,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 05f56ce6ee70..5105e297ed5f 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -28,6 +28,8 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD ---help--- Support hosting virtualized guest machines. diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index c92b26abc691..b22c6360a324 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 897c849305db..c000e978c1fb 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -31,6 +31,7 @@ #include #include #include +#include /* * How the whole thing works (courtesy of Christoffer Dall): @@ -1083,6 +1084,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) u32 status = vgic_get_interrupt_status(vcpu); struct vgic_dist *dist = &vcpu->kvm->arch.vgic; bool level_pending = false; + struct kvm *kvm = vcpu->kvm; kvm_debug("STATUS = %08x\n", status); @@ -1118,6 +1120,17 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) */ vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq); + /* + * kvm_notify_acked_irq calls kvm_set_irq() + * to reset the IRQ level. Need to release the + * lock for kvm_set_irq to grab it. + */ + spin_unlock(&dist->lock); + + kvm_notify_acked_irq(kvm, 0, + vlr.irq - VGIC_NR_PRIVATE_IRQS); + spin_lock(&dist->lock); + /* Any additional pending interrupt? */ if (vgic_dist_irq_get_level(vcpu, vlr.irq)) { vgic_cpu_irq_set(vcpu, vlr.irq); @@ -1913,3 +1926,38 @@ out_free_irq: free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus()); return ret; } + +int kvm_irq_map_gsi(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *entries, + int gsi) +{ + return gsi; +} + +int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + return pin; +} + +int kvm_set_irq(struct kvm *kvm, int irq_source_id, + u32 irq, int level, bool line_status) +{ + unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS; + + trace_kvm_set_irq(irq, level, irq_source_id); + + BUG_ON(!vgic_initialized(kvm)); + + if (spi > kvm->arch.vgic.nr_irqs) + return -EINVAL; + return kvm_vgic_inject_irq(kvm, 0, spi, level); + +} + +/* MSI not implemented yet */ +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status) +{ + return 0; +} -- cgit v1.2.3 From 35307b9a5f7ebcc8d8db41c73b69c131b48ace2b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 12 Mar 2015 18:16:51 +0000 Subject: arm/arm64: KVM: Implement Stage-2 page aging Until now, KVM/arm didn't care much for page aging (who was swapping anyway?), and simply provided empty hooks to the core KVM code. With server-type systems now being available, things are quite different. This patch implements very simple support for page aging, by clearing the Access flag in the Stage-2 page tables. On access fault, the current fault handling will write the PTE or PMD again, putting the Access flag back on. It should be possible to implement a much faster handling for Access faults, but that's left for a later patch. With this in place, performance in VMs is degraded much more gracefully. Signed-off-by: Marc Zyngier Acked-by: Christoffer Dall Signed-off-by: Christoffer Dall --- arch/arm/include/asm/kvm_arm.h | 1 + arch/arm/include/asm/kvm_host.h | 13 ++------ arch/arm/kvm/mmu.c | 65 ++++++++++++++++++++++++++++++++++++++- arch/arm/kvm/trace.h | 33 ++++++++++++++++++++ arch/arm64/include/asm/esr.h | 1 + arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/include/asm/kvm_host.h | 13 ++------ 7 files changed, 104 insertions(+), 23 deletions(-) (limited to 'arch/arm64/include') diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 816db0bf2dd8..d995821f1698 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -185,6 +185,7 @@ #define HSR_COND (0xfU << HSR_COND_SHIFT) #define FSC_FAULT (0x04) +#define FSC_ACCESS (0x08) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 902a7d1441ae..d71607c16601 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -167,19 +167,10 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index ffa06e07eed2..1831aa26eef8 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1299,6 +1299,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, out_unlock: spin_unlock(&kvm->mmu_lock); + kvm_set_pfn_accessed(pfn); kvm_release_pfn_clean(pfn); return ret; } @@ -1333,7 +1334,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Check the stage-2 fault is trans. fault or write fault */ fault_status = kvm_vcpu_trap_get_fault_type(vcpu); - if (fault_status != FSC_FAULT && fault_status != FSC_PERM) { + if (fault_status != FSC_FAULT && fault_status != FSC_PERM && + fault_status != FSC_ACCESS) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), @@ -1475,6 +1477,67 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } +static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + if (pmd_young(*pmd)) { + *pmd = pmd_mkold(*pmd); + return 1; + } + + return 0; + } + + pte = pte_offset_kernel(pmd, gpa); + if (pte_none(*pte)) + return 0; + + if (pte_young(*pte)) { + *pte = pte_mkold(*pte); /* Just a page... */ + return 1; + } + + return 0; +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) /* THP, HugeTLB */ + return pmd_young(*pmd); + + pte = pte_offset_kernel(pmd, gpa); + if (!pte_none(*pte)) /* Just a page... */ + return pte_young(*pte); + + return 0; +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) +{ + trace_kvm_age_hva(start, end); + return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + trace_kvm_test_age_hva(hva); + return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); +} + void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) { mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index 6817664b46b8..c09f37faff01 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -210,6 +210,39 @@ TRACE_EVENT(kvm_set_spte_hva, TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva) ); +TRACE_EVENT(kvm_age_hva, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier age hva: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_test_age_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier test age hva: %#08lx", __entry->hva) +); + TRACE_EVENT(kvm_hvc, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 92bbae381598..70522450ca23 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -90,6 +90,7 @@ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) #define ESR_ELx_FSC_EXTABT (0x10) +#define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) #define ESR_ELx_CV (UL(1) << 24) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 94674eb7e7bb..9e5543e08955 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -187,6 +187,7 @@ /* For compatibility with fault code shared with 32-bit */ #define FSC_FAULT ESR_ELx_FSC_FAULT +#define FSC_ACCESS ESR_ELx_FSC_ACCESS #define FSC_PERM ESR_ELx_FSC_PERM /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 967fb1cee300..f0f58c9beec0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -179,19 +179,10 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { -- cgit v1.2.3 From 950324ab81bf006542f30a1d1ab3d65fcf15cbc1 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Sat, 28 Mar 2015 01:13:13 +0000 Subject: KVM: arm/arm64: rework MMIO abort handling to use KVM MMIO bus Currently we have struct kvm_exit_mmio for encapsulating MMIO abort data to be passed on from syndrome decoding all the way down to the VGIC register handlers. Now as we switch the MMIO handling to be routed through the KVM MMIO bus, it does not make sense anymore to use that structure already from the beginning. So we keep the data in local variables until we put them into the kvm_io_bus framework. Then we fill kvm_exit_mmio in the VGIC only, making it a VGIC private structure. On that way we replace the data buffer in that structure with a pointer pointing to a single location in a local variable, so we get rid of some copying on the way. With all of the virtual GIC emulation code now being registered with the kvm_io_bus, we can remove all of the old MMIO handling code and its dispatching functionality. I didn't bother to rename kvm_exit_mmio (to vgic_mmio or something), because that touches a lot of code lines without any good reason. This is based on an original patch by Nikolay. Signed-off-by: Andre Przywara Cc: Nikolay Nikolaev Reviewed-by: Marc Zyngier Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_mmio.h | 22 --------- arch/arm/kvm/mmio.c | 64 +++++++++++++++------------ arch/arm64/include/asm/kvm_mmio.h | 22 --------- include/kvm/arm_vgic.h | 6 --- virt/kvm/arm/vgic-v2-emul.c | 21 +-------- virt/kvm/arm/vgic-v3-emul.c | 35 --------------- virt/kvm/arm/vgic.c | 93 ++++----------------------------------- virt/kvm/arm/vgic.h | 13 +++--- 8 files changed, 55 insertions(+), 221 deletions(-) (limited to 'arch/arm64/include') diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h index 3f83db2f6cf0..d8e90c8cb5fa 100644 --- a/arch/arm/include/asm/kvm_mmio.h +++ b/arch/arm/include/asm/kvm_mmio.h @@ -28,28 +28,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 5d3bfc0eb3f0..974b1c606d04 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -121,12 +121,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) return 0; } -static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, - struct kvm_exit_mmio *mmio) +static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) { unsigned long rt; - int len; - bool is_write, sign_extend; + int access_size; + bool sign_extend; if (kvm_vcpu_dabt_isextabt(vcpu)) { /* cache operation on I/O addr, tell guest unsupported */ @@ -140,17 +139,15 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return 1; } - len = kvm_vcpu_dabt_get_as(vcpu); - if (unlikely(len < 0)) - return len; + access_size = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(access_size < 0)) + return access_size; - is_write = kvm_vcpu_dabt_iswrite(vcpu); + *is_write = kvm_vcpu_dabt_iswrite(vcpu); sign_extend = kvm_vcpu_dabt_issext(vcpu); rt = kvm_vcpu_dabt_get_rd(vcpu); - mmio->is_write = is_write; - mmio->phys_addr = fault_ipa; - mmio->len = len; + *len = access_size; vcpu->arch.mmio_decode.sign_extend = sign_extend; vcpu->arch.mmio_decode.rt = rt; @@ -165,20 +162,20 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa) { - struct kvm_exit_mmio mmio; unsigned long data; unsigned long rt; int ret; + bool is_write; + int len; + u8 data_buf[8]; /* - * Prepare MMIO operation. First stash it in a private - * structure that we can use for in-kernel emulation. If the - * kernel can't handle it, copy it into run->mmio and let user - * space do its magic. + * Prepare MMIO operation. First decode the syndrome data we get + * from the CPU. Then try if some in-kernel emulation feels + * responsible, otherwise let user space do its magic. */ - if (kvm_vcpu_dabt_isvalid(vcpu)) { - ret = decode_hsr(vcpu, fault_ipa, &mmio); + ret = decode_hsr(vcpu, &is_write, &len); if (ret) return ret; } else { @@ -188,21 +185,34 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, rt = vcpu->arch.mmio_decode.rt; - if (mmio.is_write) { - data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), - mmio.len); + if (is_write) { + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + mmio_write_buf(data_buf, len, data); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, mmio.len, - fault_ipa, data); - mmio_write_buf(mmio.data, mmio.len, data); + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } else { - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len, + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, fault_ipa, 0); + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } - if (vgic_handle_mmio(vcpu, run, &mmio)) + /* Now prepare kvm_run for the potential return to userland. */ + run->mmio.is_write = is_write; + run->mmio.phys_addr = fault_ipa; + run->mmio.len = len; + memcpy(run->mmio.data, data_buf, len); + + if (!ret) { + /* We handled the access successfully in the kernel. */ + kvm_handle_mmio_return(vcpu, run); return 1; + } - kvm_prepare_mmio(run, &mmio); + run->exit_reason = KVM_EXIT_MMIO; return 0; } diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h index 9f52beb7cb13..889c908ee631 100644 --- a/arch/arm64/include/asm/kvm_mmio.h +++ b/arch/arm64/include/asm/kvm_mmio.h @@ -31,28 +31,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index d6705f447c28..16ec2c8b784d 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -140,8 +140,6 @@ struct vgic_params { }; struct vgic_vm_ops { - bool (*handle_mmio)(struct kvm_vcpu *, struct kvm_run *, - struct kvm_exit_mmio *); bool (*queue_sgi)(struct kvm_vcpu *, int irq); void (*add_sgi_source)(struct kvm_vcpu *, int irq, int source); int (*init_model)(struct kvm *); @@ -313,8 +311,6 @@ struct vgic_cpu { struct kvm; struct kvm_vcpu; -struct kvm_run; -struct kvm_exit_mmio; int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write); int kvm_vgic_hyp_init(void); @@ -330,8 +326,6 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); -bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c index 7460b376d090..13907970d11c 100644 --- a/virt/kvm/arm/vgic-v2-emul.c +++ b/virt/kvm/arm/vgic-v2-emul.c @@ -404,24 +404,6 @@ static const struct vgic_io_range vgic_dist_ranges[] = { {} }; -static bool vgic_v2_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - unsigned long base = vcpu->kvm->arch.vgic.vgic_dist_base; - - if (!is_in_range(mmio->phys_addr, mmio->len, base, - KVM_VGIC_V2_DIST_SIZE)) - return false; - - /* GICv2 does not support accesses wider than 32 bits */ - if (mmio->len > 4) { - kvm_inject_dabt(vcpu, mmio->phys_addr); - return true; - } - - return vgic_handle_mmio_range(vcpu, run, mmio, vgic_dist_ranges, base); -} - static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg) { struct kvm *kvm = vcpu->kvm; @@ -580,7 +562,6 @@ void vgic_v2_init_emulation(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - dist->vm_ops.handle_mmio = vgic_v2_handle_mmio; dist->vm_ops.queue_sgi = vgic_v2_queue_sgi; dist->vm_ops.add_sgi_source = vgic_v2_add_sgi_source; dist->vm_ops.init_model = vgic_v2_init_model; @@ -690,6 +671,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev, struct kvm_vcpu *vcpu, *tmp_vcpu; struct vgic_dist *vgic; struct kvm_exit_mmio mmio; + u32 data; offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> @@ -711,6 +693,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev, mmio.len = 4; mmio.is_write = is_write; + mmio.data = &data; if (is_write) mmio_data_write(&mmio, ~0, *reg); switch (attr->group) { diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c index eb1a797cb9c1..e9c3a7a83833 100644 --- a/virt/kvm/arm/vgic-v3-emul.c +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -708,40 +708,6 @@ static const struct vgic_io_range vgic_redist_ranges[] = { {}, }; -/* - * This function splits accesses between the distributor and the two - * redistributor parts (private/SPI). As each redistributor is accessible - * from any CPU, we have to determine the affected VCPU by taking the faulting - * address into account. We then pass this VCPU to the handler function via - * the private parameter. - */ -#define SGI_BASE_OFFSET SZ_64K -static bool vgic_v3_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - unsigned long dbase = dist->vgic_dist_base; - unsigned long rdbase = dist->vgic_redist_base; - int nrcpus = atomic_read(&vcpu->kvm->online_vcpus); - int vcpu_id; - - if (is_in_range(mmio->phys_addr, mmio->len, dbase, GIC_V3_DIST_SIZE)) { - return vgic_handle_mmio_range(vcpu, run, mmio, - vgic_v3_dist_ranges, dbase); - } - - if (!is_in_range(mmio->phys_addr, mmio->len, rdbase, - GIC_V3_REDIST_SIZE * nrcpus)) - return false; - - vcpu_id = (mmio->phys_addr - rdbase) / GIC_V3_REDIST_SIZE; - rdbase += (vcpu_id * GIC_V3_REDIST_SIZE); - mmio->private = kvm_get_vcpu(vcpu->kvm, vcpu_id); - - return vgic_handle_mmio_range(vcpu, run, mmio, vgic_redist_ranges, - rdbase); -} - static bool vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, int irq) { if (vgic_queue_irq(vcpu, 0, irq)) { @@ -861,7 +827,6 @@ void vgic_v3_init_emulation(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - dist->vm_ops.handle_mmio = vgic_v3_handle_mmio; dist->vm_ops.queue_sgi = vgic_v3_queue_sgi; dist->vm_ops.add_sgi_source = vgic_v3_add_sgi_source; dist->vm_ops.init_model = vgic_v3_init_model; diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index e968179e592f..b70174e74868 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -758,7 +758,6 @@ static bool call_range_handler(struct kvm_vcpu *vcpu, unsigned long offset, const struct vgic_io_range *range) { - u32 *data32 = (void *)mmio->data; struct kvm_exit_mmio mmio32; bool ret; @@ -775,69 +774,16 @@ static bool call_range_handler(struct kvm_vcpu *vcpu, mmio32.private = mmio->private; mmio32.phys_addr = mmio->phys_addr + 4; - if (mmio->is_write) - *(u32 *)mmio32.data = data32[1]; + mmio32.data = &((u32 *)mmio->data)[1]; ret = range->handle_mmio(vcpu, &mmio32, offset + 4); - if (!mmio->is_write) - data32[1] = *(u32 *)mmio32.data; mmio32.phys_addr = mmio->phys_addr; - if (mmio->is_write) - *(u32 *)mmio32.data = data32[0]; + mmio32.data = &((u32 *)mmio->data)[0]; ret |= range->handle_mmio(vcpu, &mmio32, offset); - if (!mmio->is_write) - data32[0] = *(u32 *)mmio32.data; return ret; } -/** - * vgic_handle_mmio_range - handle an in-kernel MMIO access - * @vcpu: pointer to the vcpu performing the access - * @run: pointer to the kvm_run structure - * @mmio: pointer to the data describing the access - * @ranges: array of MMIO ranges in a given region - * @mmio_base: base address of that region - * - * returns true if the MMIO access could be performed - */ -bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio, - const struct vgic_io_range *ranges, - unsigned long mmio_base) -{ - const struct vgic_io_range *range; - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - bool updated_state; - unsigned long offset; - - offset = mmio->phys_addr - mmio_base; - range = vgic_find_range(ranges, mmio->len, offset); - if (unlikely(!range || !range->handle_mmio)) { - pr_warn("Unhandled access %d %08llx %d\n", - mmio->is_write, mmio->phys_addr, mmio->len); - return false; - } - - spin_lock(&vcpu->kvm->arch.vgic.lock); - offset -= range->base; - if (vgic_validate_access(dist, range, offset)) { - updated_state = call_range_handler(vcpu, mmio, offset, range); - } else { - if (!mmio->is_write) - memset(mmio->data, 0, mmio->len); - updated_state = false; - } - spin_unlock(&vcpu->kvm->arch.vgic.lock); - kvm_prepare_mmio(run, mmio); - kvm_handle_mmio_return(vcpu, run); - - if (updated_state) - vgic_kick_vcpus(vcpu->kvm); - - return true; -} - /** * vgic_handle_mmio_access - handle an in-kernel MMIO access * This is called by the read/write KVM IO device wrappers below. @@ -873,23 +819,24 @@ static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu, mmio.phys_addr = addr; mmio.len = len; mmio.is_write = is_write; - if (is_write) - memcpy(mmio.data, val, len); + mmio.data = val; mmio.private = iodev->redist_vcpu; spin_lock(&dist->lock); offset -= range->base; if (vgic_validate_access(dist, range, offset)) { updated_state = call_range_handler(vcpu, &mmio, offset, range); - if (!is_write) - memcpy(val, mmio.data, len); } else { if (!is_write) memset(val, 0, len); updated_state = false; } spin_unlock(&dist->lock); - kvm_prepare_mmio(run, &mmio); + run->mmio.is_write = is_write; + run->mmio.len = len; + run->mmio.phys_addr = addr; + memcpy(run->mmio.data, val, len); + kvm_handle_mmio_return(vcpu, run); if (updated_state) @@ -898,30 +845,6 @@ static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu, return 0; } -/** - * vgic_handle_mmio - handle an in-kernel MMIO access for the GIC emulation - * @vcpu: pointer to the vcpu performing the access - * @run: pointer to the kvm_run structure - * @mmio: pointer to the data describing the access - * - * returns true if the MMIO access has been performed in kernel space, - * and false if it needs to be emulated in user space. - * Calls the actual handling routine for the selected VGIC model. - */ -bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - if (!irqchip_in_kernel(vcpu->kvm)) - return false; - - /* - * This will currently call either vgic_v2_handle_mmio() or - * vgic_v3_handle_mmio(), which in turn will call - * vgic_handle_mmio_range() defined above. - */ - return vcpu->kvm->arch.vgic.vm_ops.handle_mmio(vcpu, run, mmio); -} - static int vgic_handle_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, void *val) diff --git a/virt/kvm/arm/vgic.h b/virt/kvm/arm/vgic.h index 28fa3aaf6367..0df74cbb6200 100644 --- a/virt/kvm/arm/vgic.h +++ b/virt/kvm/arm/vgic.h @@ -59,6 +59,14 @@ void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq); void vgic_unqueue_irqs(struct kvm_vcpu *vcpu); +struct kvm_exit_mmio { + phys_addr_t phys_addr; + void *data; + u32 len; + bool is_write; + void *private; +}; + void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg, phys_addr_t offset, int mode); bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, @@ -99,11 +107,6 @@ const struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges, int len, gpa_t offset); -bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio, - const struct vgic_io_range *ranges, - unsigned long mmio_base); - bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio, phys_addr_t offset, int vcpu_id, int access); -- cgit v1.2.3