diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-22 18:22:53 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-22 18:22:53 -0800 |
| commit | fd7e9a88348472521d999434ee02f25735c7dadf (patch) | |
| tree | 90e6249e58d90ba9d590cfed4481c29ca36a05dc /arch | |
| parent | 5066e4a34081dd82fb625f2f382bfa29ca421a3f (diff) | |
| parent | dd0fd8bca1850ddadf5d33a9ed28f3707cd98ac7 (diff) | |
| download | op-kernel-dev-fd7e9a88348472521d999434ee02f25735c7dadf.zip op-kernel-dev-fd7e9a88348472521d999434ee02f25735c7dadf.tar.gz | |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"4.11 is going to be a relatively large release for KVM, with a little
over 200 commits and noteworthy changes for most architectures.
ARM:
- GICv3 save/restore
- cache flushing fixes
- working MSI injection for GICv3 ITS
- physical timer emulation
MIPS:
- various improvements under the hood
- support for SMP guests
- a large rewrite of MMU emulation. KVM MIPS can now use MMU
notifiers to support copy-on-write, KSM, idle page tracking,
swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
also supported, so that writes to some memory regions can be
treated as MMIO. The new MMU also paves the way for hardware
virtualization support.
PPC:
- support for POWER9 using the radix-tree MMU for host and guest
- resizable hashed page table
- bugfixes.
s390:
- expose more features to the guest
- more SIMD extensions
- instruction execution protection
- ESOP2
x86:
- improved hashing in the MMU
- faster PageLRU tracking for Intel CPUs without EPT A/D bits
- some refactoring of nested VMX entry/exit code, preparing for live
migration support of nested hypervisors
- expose yet another AVX512 CPUID bit
- host-to-guest PTP support
- refactoring of interrupt injection, with some optimizations thrown
in and some duct tape removed.
- remove lazy FPU handling
- optimizations of user-mode exits
- optimizations of vcpu_is_preempted() for KVM guests
generic:
- alternative signaling mechanism that doesn't pound on
tsk->sighand->siglock"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
x86/paravirt: Change vcp_is_preempted() arg type to long
KVM: VMX: use correct vmcs_read/write for guest segment selector/base
x86/kvm/vmx: Defer TR reload after VM exit
x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
x86/kvm/vmx: Simplify segment_base()
x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
x86/kvm/vmx: Don't fetch the TSS base from the GDT
x86/asm: Define the kernel TSS limit in a macro
kvm: fix page struct leak in handle_vmon
KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
KVM: Return an error code only as a constant in kvm_get_dirty_log()
KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
KVM: x86: remove code for lazy FPU handling
KVM: race-free exit from KVM_RUN without POSIX signals
KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
KVM: Support vCPU-based gfn->hva cache
KVM: use separate generations for each address space
...
Diffstat (limited to 'arch')
81 files changed, 5526 insertions, 2611 deletions
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index d5423ab..cc495d79 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -60,9 +60,6 @@ struct kvm_arch { /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; - /* Timer */ - struct arch_timer_kvm timer; - /* * Anything that is not used directly from assembly code goes * here. diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 74a44727..95f38dc 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -129,8 +129,7 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, - unsigned long size, - bool ipa_uncached) + unsigned long size) { /* * If we are going to insert an instruction page and the icache is @@ -150,18 +149,12 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, * and iterate over the range. */ - bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; - VM_BUG_ON(size & ~PAGE_MASK); - if (!need_flush && !icache_is_pipt()) - goto vipt_cache; - while (size) { void *va = kmap_atomic_pfn(pfn); - if (need_flush) - kvm_flush_dcache_to_poc(va, PAGE_SIZE); + kvm_flush_dcache_to_poc(va, PAGE_SIZE); if (icache_is_pipt()) __cpuc_coherent_user_range((unsigned long)va, @@ -173,7 +166,6 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, kunmap_atomic(va); } -vipt_cache: if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index af05f8e..6ebd3e6 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -181,10 +181,23 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 #define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 +#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ + (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 #define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 +#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 +#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ + (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff +#define VGIC_LEVEL_INFO_LINE_LEVEL 0 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* KVM_IRQ_LINE irq field index values */ diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index d571243..7b3670c 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -7,7 +7,7 @@ ifeq ($(plus_virt),+virt) plus_virt_def := -DREQUIRES_VIRT=1 endif -ccflags-y += -Iarch/arm/kvm +ccflags-y += -Iarch/arm/kvm -Ivirt/kvm/arm/vgic CFLAGS_arm.o := -I. $(plus_virt_def) CFLAGS_mmu.o := -I. @@ -20,7 +20,7 @@ kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vf obj-$(CONFIG_KVM_ARM_HOST) += hyp/ obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o -obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o +obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o vgic-v3-coproc.o obj-y += $(KVM)/arm/aarch32.o obj-y += $(KVM)/arm/vgic/vgic.o @@ -33,5 +33,6 @@ obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o obj-y += $(KVM)/arm/vgic/vgic-its.o +obj-y += $(KVM)/arm/vgic/vgic-debug.o obj-y += $(KVM)/irqchip.o obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 9d74464..c9a2103 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -135,7 +135,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) goto out_free_stage2_pgd; kvm_vgic_early_init(kvm); - kvm_timer_init(kvm); /* Mark the initial VMID generation invalid */ kvm->arch.vmid_gen = 0; @@ -207,6 +206,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_READONLY_MEM: case KVM_CAP_MP_STATE: + case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -301,7 +301,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return kvm_timer_should_fire(vcpu); + return kvm_timer_should_fire(vcpu_vtimer(vcpu)) || + kvm_timer_should_fire(vcpu_ptimer(vcpu)); } void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) @@ -604,6 +605,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) return ret; } + if (run->immediate_exit) + return -EINTR; + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index a5265ed..962616f 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1232,9 +1232,9 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, } static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, - unsigned long size, bool uncached) + unsigned long size) { - __coherent_cache_guest_page(vcpu, pfn, size, uncached); + __coherent_cache_guest_page(vcpu, pfn, size); } static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, @@ -1250,7 +1250,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct vm_area_struct *vma; kvm_pfn_t pfn; pgprot_t mem_type = PAGE_S2; - bool fault_ipa_uncached; bool logging_active = memslot_is_logging(memslot); unsigned long flags = 0; @@ -1337,8 +1336,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!hugetlb && !force_pte) hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); - fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT; - if (hugetlb) { pmd_t new_pmd = pfn_pmd(pfn, mem_type); new_pmd = pmd_mkhuge(new_pmd); @@ -1346,7 +1343,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, new_pmd = kvm_s2pmd_mkwrite(new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached); + coherent_cache_guest_page(vcpu, pfn, PMD_SIZE); ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -1356,7 +1353,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_pfn_dirty(pfn); mark_page_dirty(kvm, gfn); } - coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached); + coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE); ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags); } @@ -1879,15 +1876,6 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) { - /* - * Readonly memslots are not incoherent with the caches by definition, - * but in practice, they are used mostly to emulate ROMs or NOR flashes - * that the guest may consider devices and hence map as uncached. - * To prevent incoherency issues in these cases, tag all readonly - * regions as incoherent. - */ - if (slot->flags & KVM_MEM_READONLY) - slot->flags |= KVM_MEMSLOT_INCOHERENT; return 0; } diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c index 4b5e802..1da8b2d 100644 --- a/arch/arm/kvm/reset.c +++ b/arch/arm/kvm/reset.c @@ -37,6 +37,11 @@ static struct kvm_regs cortexa_regs_reset = { .usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT, }; +static const struct kvm_irq_level cortexa_ptimer_irq = { + { .irq = 30 }, + .level = 1, +}; + static const struct kvm_irq_level cortexa_vtimer_irq = { { .irq = 27 }, .level = 1, @@ -58,6 +63,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { struct kvm_regs *reset_regs; const struct kvm_irq_level *cpu_vtimer_irq; + const struct kvm_irq_level *cpu_ptimer_irq; switch (vcpu->arch.target) { case KVM_ARM_TARGET_CORTEX_A7: @@ -65,6 +71,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) reset_regs = &cortexa_regs_reset; vcpu->arch.midr = read_cpuid_id(); cpu_vtimer_irq = &cortexa_vtimer_irq; + cpu_ptimer_irq = &cortexa_ptimer_irq; break; default: return -ENODEV; @@ -77,5 +84,5 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) kvm_reset_coprocs(vcpu); /* Reset arch_timer context */ - return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq); + return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq, cpu_ptimer_irq); } diff --git a/arch/arm/kvm/vgic-v3-coproc.c b/arch/arm/kvm/vgic-v3-coproc.c new file mode 100644 index 0000000..f41abf7 --- /dev/null +++ b/arch/arm/kvm/vgic-v3-coproc.c @@ -0,0 +1,35 @@ +/* + * VGIC system registers handling functions for AArch32 mode + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include "vgic.h" + +int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, + u64 *reg) +{ + /* + * TODO: Implement for AArch32 + */ + return -ENXIO; +} + +int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id, + u64 *reg) +{ + /* + * TODO: Implement for AArch32 + */ + return -ENXIO; +} diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 443b387..f21fd38 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -70,9 +70,6 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; - - /* Timer */ - struct arch_timer_kvm timer; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 55772c1..ed12460 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -236,13 +236,11 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, - unsigned long size, - bool ipa_uncached) + unsigned long size) { void *va = page_address(pfn_to_page(pfn)); - if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) - kvm_flush_dcache_to_poc(va, size); + kvm_flush_dcache_to_poc(va, size); if (!icache_is_aliasing()) { /* PIPT */ flush_icache_range((unsigned long)va, diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 3051f86..c286035 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -201,10 +201,23 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 #define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 +#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ + (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 #define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 +#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 +#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ + (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff +#define VGIC_LEVEL_INFO_LINE_LEVEL 0 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* Device Control API on vcpu fd */ diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index d50a82a..afd51be 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -2,7 +2,7 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -Iarch/arm64/kvm +ccflags-y += -Iarch/arm64/kvm -Ivirt/kvm/arm/vgic CFLAGS_arm.o := -I. CFLAGS_mmu.o := -I. @@ -19,6 +19,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o @@ -31,6 +32,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-debug.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/irqchip.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index e95d4f6..d9e9697 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -46,6 +46,11 @@ static const struct kvm_regs default_regs_reset32 = { COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT), }; +static const struct kvm_irq_level default_ptimer_irq = { + .irq = 30, + .level = 1, +}; + static const struct kvm_irq_level default_vtimer_irq = { .irq = 27, .level = 1, @@ -104,6 +109,7 @@ int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext) int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { const struct kvm_irq_level *cpu_vtimer_irq; + const struct kvm_irq_level *cpu_ptimer_irq; const struct kvm_regs *cpu_reset; switch (vcpu->arch.target) { @@ -117,6 +123,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } cpu_vtimer_irq = &default_vtimer_irq; + cpu_ptimer_irq = &default_ptimer_irq; break; } @@ -130,5 +137,5 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) kvm_pmu_vcpu_reset(vcpu); /* Reset timer */ - return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq); + return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq, cpu_ptimer_irq); } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 87e7e66..0e26f8c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -820,6 +820,61 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } +static bool access_cntp_tval(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + u64 now = kvm_phys_timer_read(); + + if (p->is_write) + ptimer->cnt_cval = p->regval + now; + else + p->regval = ptimer->cnt_cval - now; + + return true; +} + +static bool access_cntp_ctl(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + + if (p->is_write) { + /* ISTATUS bit is read-only */ + ptimer->cnt_ctl = p->regval & ~ARCH_TIMER_CTRL_IT_STAT; + } else { + u64 now = kvm_phys_timer_read(); + + p->regval = ptimer->cnt_ctl; + /* + * Set ISTATUS bit if it's expired. + * Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is + * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit + * regardless of ENABLE bit for our implementation convenience. + */ + if (ptimer->cnt_cval <= now) + p->regval |= ARCH_TIMER_CTRL_IT_STAT; + } + + return true; +} + +static bool access_cntp_cval(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + + if (p->is_write) + ptimer->cnt_cval = p->regval; + else + p->regval = ptimer->cnt_cval; + + return true; +} + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -1029,6 +1084,16 @@ static const struct sys_reg_desc sys_reg_descs[] = { { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011), NULL, reset_unknown, TPIDRRO_EL0 }, + /* CNTP_TVAL_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b000), + access_cntp_tval }, + /* CNTP_CTL_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b001), + access_cntp_ctl }, + /* CNTP_CVAL_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b010), + access_cntp_cval }, + /* PMEVCNTRn_EL0 */ PMU_PMEVCNTR_EL0(0), PMU_PMEVCNTR_EL0(1), @@ -1795,6 +1860,17 @@ static bool index_to_params(u64 id, struct sys_reg_params *params) } } +const struct sys_reg_desc *find_reg_by_id(u64 id, + struct sys_reg_params *params, + const struct sys_reg_desc table[], + unsigned int num) +{ + if (!index_to_params(id, params)) + return NULL; + + return find_reg(params, table, num); +} + /* Decode an index value, and find the sys_reg_desc entry. */ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id) @@ -1807,11 +1883,8 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG) return NULL; - if (!index_to_params(id, ¶ms)) - return NULL; - table = get_target_table(vcpu->arch.target, true, &num); - r = find_reg(¶ms, table, num); + r = find_reg_by_id(id, ¶ms, table, num); if (!r) r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); @@ -1918,10 +1991,8 @@ static int get_invariant_sys_reg(u64 id, void __user *uaddr) struct sys_reg_params params; const struct sys_reg_desc *r; - if (!index_to_params(id, ¶ms)) - return -ENOENT; - - r = find_reg(¶ms, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)); + r = find_reg_by_id(id, ¶ms, invariant_sys_regs, + ARRAY_SIZE(invariant_sys_regs)); if (!r) return -ENOENT; @@ -1935,9 +2006,8 @@ static int set_invariant_sys_reg(u64 id, void __user *uaddr) int err; u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */ - if (!index_to_params(id, ¶ms)) - return -ENOENT; - r = find_reg(¶ms, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)); + r = find_reg_by_id(id, ¶ms, invariant_sys_regs, + ARRAY_SIZE(invariant_sys_regs)); if (!r) return -ENOENT; diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index dbbb01c..9c6ffd0 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -136,6 +136,10 @@ static inline int cmp_sys_reg(const struct sys_reg_desc *i1, return i1->Op2 - i2->Op2; } +const struct sys_reg_desc *find_reg_by_id(u64 id, + struct sys_reg_params *params, + const struct sys_reg_desc table[], + unsigned int num); #define Op0(_x) .Op0 = _x #define Op1(_x) .Op1 = _x diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c new file mode 100644 index 0000000..79f37e3 --- /dev/null +++ b/arch/arm64/kvm/vgic-sys-reg-v3.c @@ -0,0 +1,346 @@ +/* + * VGIC system registers handling functions for AArch64 mode + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include "vgic.h" +#include "sys_regs.h" + +static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u32 host_pri_bits, host_id_bits, host_seis, host_a3v, seis, a3v; + struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu; + struct vgic_vmcr vmcr; + u64 val; + + vgic_get_vmcr(vcpu, &vmcr); + if (p->is_write) { + val = p->regval; + + /* + * Disallow restoring VM state if not supported by this + * hardware. + */ + host_pri_bits = ((val & ICC_CTLR_EL1_PRI_BITS_MASK) >> + ICC_CTLR_EL1_PRI_BITS_SHIFT) + 1; + if (host_pri_bits > vgic_v3_cpu->num_pri_bits) + return false; + + vgic_v3_cpu->num_pri_bits = host_pri_bits; + + host_id_bits = (val & ICC_CTLR_EL1_ID_BITS_MASK) >> + ICC_CTLR_EL1_ID_BITS_SHIFT; + if (host_id_bits > vgic_v3_cpu->num_id_bits) + return false; + + vgic_v3_cpu->num_id_bits = host_id_bits; + + host_seis = ((kvm_vgic_global_state.ich_vtr_el2 & + ICH_VTR_SEIS_MASK) >> ICH_VTR_SEIS_SHIFT); + seis = (val & ICC_CTLR_EL1_SEIS_MASK) >> + ICC_CTLR_EL1_SEIS_SHIFT; + if (host_seis != seis) + return false; + + host_a3v = ((kvm_vgic_global_state.ich_vtr_el2 & + ICH_VTR_A3V_MASK) >> ICH_VTR_A3V_SHIFT); + a3v = (val & ICC_CTLR_EL1_A3V_MASK) >> ICC_CTLR_EL1_A3V_SHIFT; + if (host_a3v != a3v) + return false; + + /* + * Here set VMCR.CTLR in ICC_CTLR_EL1 layout. + * The vgic_set_vmcr() will convert to ICH_VMCR layout. + */ + vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK; + vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK; + vgic_set_vmcr(vcpu, &vmcr); + } else { + val = 0; + val |= (vgic_v3_cpu->num_pri_bits - 1) << + ICC_CTLR_EL1_PRI_BITS_SHIFT; + val |= vgic_v3_cpu->num_id_bits << ICC_CTLR_EL1_ID_BITS_SHIFT; + val |= ((kvm_vgic_global_state.ich_vtr_el2 & + ICH_VTR_SEIS_MASK) >> ICH_VTR_SEIS_SHIFT) << + ICC_CTLR_EL1_SEIS_SHIFT; + val |= ((kvm_vgic_global_state.ich_vtr_el2 & + ICH_VTR_A3V_MASK) >> ICH_VTR_A3V_SHIFT) << + ICC_CTLR_EL1_A3V_SHIFT; + /* + * The VMCR.CTLR value is in ICC_CTLR_EL1 layout. + * Extract it directly using ICC_CTLR_EL1 reg definitions. + */ + val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK; + val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK; + + p->regval = val; + } + + return true; +} + +static bool access_gic_pmr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct vgic_vmcr vmcr; + + vgic_get_vmcr(vcpu, &vmcr); + if (p->is_write) { + vmcr.pmr = (p->regval & ICC_PMR_EL1_MASK) >> ICC_PMR_EL1_SHIFT; + vgic_set_vmcr(vcpu, &vmcr); + } else { + p->regval = (vmcr.pmr << ICC_PMR_EL1_SHIFT) & ICC_PMR_EL1_MASK; + } + + return true; +} + +static bool access_gic_bpr0(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct vgic_vmcr vmcr; + + vgic_get_vmcr(vcpu, &vmcr); + if (p->is_write) { + vmcr.bpr = (p->regval & ICC_BPR0_EL1_MASK) >> + ICC_BPR0_EL1_SHIFT; + vgic_set_vmcr(vcpu, &vmcr); + } else { + p->regval = (vmcr.bpr << ICC_BPR0_EL1_SHIFT) & + ICC_BPR0_EL1_MASK; + } + + return true; +} + +static bool access_gic_bpr1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct vgic_vmcr vmcr; + + if (!p->is_write) + p->regval = 0; + + vgic_get_vmcr(vcpu, &vmcr); + if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) { + if (p->is_write) { + vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >> + ICC_BPR1_EL1_SHIFT; + vgic_set_vmcr(vcpu, &vmcr); + } else { + p->regval = (vmcr.abpr << ICC_BPR1_EL1_SHIFT) & + ICC_BPR1_EL1_MASK; + } + } else { + if (!p->is_write) + p->regval = min((vmcr.bpr + 1), 7U); + } + + return true; +} + +static bool access_gic_grpen0(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct vgic_vmcr vmcr; + + vgic_get_vmcr(vcpu, &vmcr); + if (p->is_write) { + vmcr.grpen0 = (p->regval & ICC_IGRPEN0_EL1_MASK) >> + ICC_IGRPEN0_EL1_SHIFT; + vgic_set_vmcr(vcpu, &vmcr); + } else { + p->regval = (vmcr.grpen0 << ICC_IGRPEN0_EL1_SHIFT) & + ICC_IGRPEN0_EL1_MASK; + } + + return true; +} + +static bool access_gic_grpen1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct vgic_vmcr vmcr; + + vgic_get_vmcr(vcpu, &vmcr); + if (p->is_write) { + vmcr.grpen1 = (p->regval & ICC_IGRPEN1_EL1_MASK) >> + ICC_IGRPEN1_EL1_SHIFT; + vgic_set_vmcr(vcpu, &vmcr); + } else { + p->regval = (vmcr.grpen1 << ICC_IGRPEN1_EL1_SHIFT) & + ICC_IGRPEN1_EL1_MASK; + } + + return true; +} + +static void vgic_v3_access_apr_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, u8 apr, u8 idx) +{ + struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; + uint32_t *ap_reg; + + if (apr) + ap_reg = &vgicv3->vgic_ap1r[idx]; + else + ap_reg = &vgicv3->vgic_ap0r[idx]; + + if (p->is_write) + *ap_reg = p->regval; + else + p->regval = *ap_reg; +} + +static bool access_gic_aprn(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r, u8 apr) +{ + struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu; + u8 idx = r->Op2 & 3; + + /* + * num_pri_bits are initialized with HW supported values. + * We can rely safely on num_pri_bits even if VM has not + * restored ICC_CTLR_EL1 before restoring APnR registers. + */ + switch (vgic_v3_cpu->num_pri_bits) { + case 7: + vgic_v3_access_apr_reg(vcpu, p, apr, idx); + break; + case 6: + if (idx > 1) + goto err; + vgic_v3_access_apr_reg(vcpu, p, apr, idx); + break; + default: + if (idx > 0) + goto err; + vgic_v3_access_apr_reg(vcpu, p, apr, idx); + } + + return true; +err: + if (!p->is_write) + p->regval = 0; + + return false; +} + +static bool access_gic_ap0r(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) + +{ + return access_gic_aprn(vcpu, p, r, 0); +} + +static bool access_gic_ap1r(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + return access_gic_aprn(vcpu, p, r, 1); +} + +static bool access_gic_sre(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; + + /* Validate SRE bit */ + if (p->is_write) { + if (!(p->regval & ICC_SRE_EL1_SRE)) + return false; + } else { + p->regval = vgicv3->vgic_sre; + } + + return true; +} +static const struct sys_reg_desc gic_v3_icc_reg_descs[] = { + /* ICC_PMR_EL1 */ + { Op0(3), Op1(0), CRn(4), CRm(6), Op2(0), access_gic_pmr }, + /* ICC_BPR0_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(8), Op2(3), access_gic_bpr0 }, + /* ICC_AP0R0_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(8), Op2(4), access_gic_ap0r }, + /* ICC_AP0R1_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(8), Op2(5), access_gic_ap0r }, + /* ICC_AP0R2_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(8), Op2(6), access_gic_ap0r }, + /* ICC_AP0R3_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(8), Op2(7), access_gic_ap0r }, + /* ICC_AP1R0_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(9), Op2(0), access_gic_ap1r }, + /* ICC_AP1R1_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(9), Op2(1), access_gic_ap1r }, + /* ICC_AP1R2_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(9), Op2(2), access_gic_ap1r }, + /* ICC_AP1R3_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(9), Op2(3), access_gic_ap1r }, + /* ICC_BPR1_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(12), Op2(3), access_gic_bpr1 }, + /* ICC_CTLR_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(12), Op2(4), access_gic_ctlr }, + /* ICC_SRE_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(12), Op2(5), access_gic_sre }, + /* ICC_IGRPEN0_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(12), Op2(6), access_gic_grpen0 }, + /* ICC_GRPEN1_EL1 */ + { Op0(3), Op1(0), CRn(12), CRm(12), Op2(7), access_gic_grpen1 }, +}; + +int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, + u64 *reg) +{ + struct sys_reg_params params; + u64 sysreg = (id & KVM_DEV_ARM_VGIC_SYSREG_MASK) | KVM_REG_SIZE_U64; + + params.regval = *reg; + params.is_write = is_write; + params.is_aarch32 = false; + params.is_32bit = false; + + if (find_reg_by_id(sysreg, ¶ms, gic_v3_icc_reg_descs, + ARRAY_SIZE(gic_v3_icc_reg_descs))) + return 0; + + return -ENXIO; +} + +int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id, + u64 *reg) +{ + struct sys_reg_params params; + const struct sys_reg_desc *r; + u64 sysreg = (id & KVM_DEV_ARM_VGIC_SYSREG_MASK) | KVM_REG_SIZE_U64; + + if (is_write) + params.regval = *reg; + params.is_write = is_write; + params.is_aarch32 = false; + params.is_32bit = false; + + r = find_reg_by_id(sysreg, ¶ms, gic_v3_icc_reg_descs, + ARRAY_SIZE(gic_v3_icc_reg_descs)); + if (!r) + return -ENXIO; + + if (!r->access(vcpu, ¶ms, r)) + return -EINVAL; + + if (!is_write) + *reg = params.regval; + + return 0; +} diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index bebec37..05e785f 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -43,6 +43,7 @@ #define KVM_REG_MIPS_CP0_ENTRYHI MIPS_CP0_64(10, 0) #define KVM_REG_MIPS_CP0_COMPARE MIPS_CP0_32(11, 0) #define KVM_REG_MIPS_CP0_STATUS MIPS_CP0_32(12, 0) +#define KVM_REG_MIPS_CP0_INTCTL MIPS_CP0_32(12, 1) #define KVM_REG_MIPS_CP0_CAUSE MIPS_CP0_32(13, 0) #define KVM_REG_MIPS_CP0_EPC MIPS_CP0_64(14, 0) #define KVM_REG_MIPS_CP0_PRID MIPS_CP0_32(15, 0) @@ -64,7 +65,7 @@ #define KVM_REG_MIPS_CP0_KSCRATCH6 MIPS_CP0_64(31, 7) -#define KVM_MAX_VCPUS 1 +#define KVM_MAX_VCPUS 8 #define KVM_USER_MEM_SLOTS 8 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 0 @@ -88,6 +89,7 @@ #define KVM_GUEST_KUSEG 0x00000000UL #define KVM_GUEST_KSEG0 0x40000000UL +#define KVM_GUEST_KSEG1 0x40000000UL #define KVM_GUEST_KSEG23 0x60000000UL #define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0xe0000000) #define KVM_GUEST_CPHYSADDR(a) ((_ACAST32_(a)) & 0x1fffffff) @@ -104,7 +106,6 @@ #define KVM_GUEST_KSEG23ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG23) #define KVM_INVALID_PAGE 0xdeadbeef -#define KVM_INVALID_INST 0xdeadbeef #define KVM_INVALID_ADDR 0xdeadbeef /* @@ -121,8 +122,6 @@ static inline bool kvm_is_error_hva(unsigned long addr) return IS_ERR_VALUE(addr); } -extern atomic_t kvm_mips_instance; - struct kvm_vm_stat { ulong remote_tlb_flush; }; @@ -156,12 +155,8 @@ struct kvm_arch_memory_slot { }; struct kvm_arch { - /* Guest GVA->HPA page table */ - unsigned long *guest_pmap; - unsigned long guest_pmap_npages; - - /* Wired host TLB used for the commpage */ - int commpage_tlb; + /* Guest physical mm */ + struct mm_struct gpa_mm; }; #define N_MIPS_COPROC_REGS 32 @@ -233,6 +228,7 @@ enum emulation_result { EMULATE_FAIL, /* can't emulate this instruction */ EMULATE_WAIT, /* WAIT instruction */ EMULATE_PRIV_FAIL, + EMULATE_EXCEPT, /* A guest exception has been generated */ }; #define mips3_paddr_to_tlbpfn(x) \ @@ -250,6 +246,7 @@ enum emulation_result { #define TLB_ASID(x) ((x).tlb_hi & KVM_ENTRYHI_ASID) #define TLB_LO_IDX(x, va) (((va) >> PAGE_SHIFT) & 1) #define TLB_IS_VALID(x, va) ((x).tlb_lo[TLB_LO_IDX(x, va)] & ENTRYLO_V) +#define TLB_IS_DIRTY(x, va) ((x).tlb_lo[TLB_LO_IDX(x, va)] & ENTRYLO_D) #define TLB_HI_VPN2_HIT(x, y) ((TLB_VPN2(x) & ~(x).tlb_mask) == \ ((y) & VPN2_MASK & ~(x).tlb_mask)) #define TLB_HI_ASID_HIT(x, y) (TLB_IS_GLOBAL(x) || \ @@ -261,6 +258,17 @@ struct kvm_mips_tlb { long tlb_lo[2]; }; +#define KVM_NR_MEM_OBJS 4 + +/* + * We don't want allocation failures within the mmu code, so we preallocate + * enough memory for a single page fault in a cache. + */ +struct kvm_mmu_memory_cache { + int nobjs; + void *objects[KVM_NR_MEM_OBJS]; +}; + #define KVM_MIPS_AUX_FPU 0x1 #define KVM_MIPS_AUX_MSA 0x2 @@ -275,6 +283,8 @@ struct kvm_vcpu_arch { unsigned long host_cp0_badvaddr; unsigned long host_cp0_epc; u32 host_cp0_cause; + u32 host_cp0_badinstr; + u32 host_cp0_badinstrp; /* GPRS */ unsigned long gprs[32]; @@ -318,20 +328,18 @@ struct kvm_vcpu_arch { /* Bitmask of pending exceptions to be cleared */ unsigned long pending_exceptions_clr; - /* Save/Restore the entryhi register when are are preempted/scheduled back in */ - unsigned long preempt_entryhi; - /* S/W Based TLB for guest */ struct kvm_mips_tlb guest_tlb[KVM_MIPS_GUEST_TLB_SIZE]; - /* Cached guest kernel/user ASIDs */ - u32 guest_user_asid[NR_CPUS]; - u32 guest_kernel_asid[NR_CPUS]; + /* Guest kernel/user [partial] mm */ struct mm_struct guest_kernel_mm, guest_user_mm; /* Guest ASID of last user mode execution */ unsigned int last_user_gasid; + /* Cache some mmu pages needed inside spinlock regions */ + struct kvm_mmu_memory_cache mmu_page_cache; + int last_sched_cpu; /* WAIT executed */ @@ -339,14 +347,15 @@ struct kvm_vcpu_arch { u8 fpu_enabled; u8 msa_enabled; - u8 kscratch_enabled; }; #define kvm_read_c0_guest_index(cop0) (cop0->reg[MIPS_CP0_TLB_INDEX][0]) #define kvm_write_c0_guest_index(cop0, val) (cop0->reg[MIPS_CP0_TLB_INDEX][0] = val) #define kvm_read_c0_guest_entrylo0(cop0) (cop0->reg[MIPS_CP0_TLB_LO0][0]) +#define kvm_write_c0_guest_entrylo0(cop0, val) (cop0->reg[MIPS_CP0_TLB_LO0][0] = (val)) #define kvm_read_c0_guest_entrylo1(cop0) (cop0->reg[MIPS_CP0_TLB_LO1][0]) +#define kvm_write_c0_guest_entrylo1(cop0, val) (cop0->reg[MIPS_CP0_TLB_LO1][0] = (val)) #define kvm_read_c0_guest_context(cop0) (cop0->reg[MIPS_CP0_TLB_CONTEXT][0]) #define kvm_write_c0_guest_context(cop0, val) (cop0->reg[MIPS_CP0_TLB_CONTEXT][0] = (val)) #define kvm_read_c0_guest_userlocal(cop0) (cop0->reg[MIPS_CP0_TLB_CONTEXT][2]) @@ -522,9 +531,17 @@ struct kvm_mips_callbacks { int (*handle_msa_fpe)(struct kvm_vcpu *vcpu); int (*handle_fpe)(struct kvm_vcpu *vcpu); int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); - int (*vm_init)(struct kvm *kvm); int (*vcpu_init)(struct kvm_vcpu *vcpu); + void (*vcpu_uninit)(struct kvm_vcpu *vcpu); int (*vcpu_setup)(struct kvm_vcpu *vcpu); + void (*flush_shadow_all)(struct kvm *kvm); + /* + * Must take care of flushing any cached GPA PTEs (e.g. guest entries in + * VZ root TLB, or T&E GVA page tables and corresponding root TLB + * mappings). + */ + void (*flush_shadow_memslot)(struct kvm *kvm, + const struct kvm_memory_slot *slot); gpa_t (*gva_to_gpa)(gva_t gva); void (*queue_timer_int)(struct kvm_vcpu *vcpu); void (*dequeue_timer_int)(struct kvm_vcpu *vcpu); @@ -542,8 +559,10 @@ struct kvm_mips_callbacks { const struct kvm_one_reg *reg, s64 *v); int (*set_one_reg)(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, s64 v); - int (*vcpu_get_regs)(struct kvm_vcpu *vcpu); - int (*vcpu_set_regs)(struct kvm_vcpu *vcpu); + int (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); + int (*vcpu_put)(struct kvm_vcpu *vcpu, int cpu); + int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); + void (*vcpu_reenter)(struct kvm_run *run, struct kvm_vcpu *vcpu); }; extern struct kvm_mips_callbacks *kvm_mips_callbacks; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks); @@ -556,6 +575,7 @@ extern int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu); /* Building of entry/exception code */ int kvm_mips_entry_setup(void); void *kvm_mips_build_vcpu_run(void *addr); +void *kvm_mips_build_tlb_refill_exception(void *addr, void *handler); void *kvm_mips_build_exception(void *addr, void *handler); void *kvm_mips_build_exit(void *addr); @@ -580,54 +600,125 @@ u32 kvm_get_user_asid(struct kvm_vcpu *vcpu); u32 kvm_get_commpage_asid (struct kvm_vcpu *vcpu); extern int kvm_mips_handle_kseg0_tlb_fault(unsigned long badbaddr, - struct kvm_vcpu *vcpu); + struct kvm_vcpu *vcpu, + bool write_fault); extern int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu); extern int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, - struct kvm_mips_tlb *tlb); + struct kvm_mips_tlb *tlb, + unsigned long gva, + bool write_fault); extern enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, u32 *opc, struct kvm_run *run, - struct kvm_vcpu *vcpu); - -extern enum emulation_result kvm_mips_handle_tlbmod(u32 cause, - u32 *opc, - struct kvm_run *run, - struct kvm_vcpu *vcpu); + struct kvm_vcpu *vcpu, + bool write_fault); extern void kvm_mips_dump_host_tlbs(void); extern void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu); -extern int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi, - unsigned long entrylo0, - unsigned long entrylo1, - int flush_dcache_mask); -extern void kvm_mips_flush_host_tlb(int skip_kseg0); -extern int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long entryhi); +extern int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long entryhi, + bool user, bool kernel); extern int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi); -extern int kvm_mips_host_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long vaddr); -extern unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu, - unsigned long gva); -extern void kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, - struct kvm_vcpu *vcpu); -extern void kvm_local_flush_tlb_all(void); -extern void kvm_mips_alloc_new_mmu_context(struct kvm_vcpu *vcpu); -extern void kvm_mips_vcpu_load(struct kvm_vcpu *vcpu, int cpu); -extern void kvm_mips_vcpu_put(struct kvm_vcpu *vcpu); + +void kvm_mips_suspend_mm(int cpu); +void kvm_mips_resume_mm(int cpu); + +/* MMU handling */ + +/** + * enum kvm_mips_flush - Types of MMU flushes. + * @KMF_USER: Flush guest user virtual memory mappings. + * Guest USeg only. + * @KMF_KERN: Flush guest kernel virtual memory mappings. + * Guest USeg and KSeg2/3. + * @KMF_GPA: Flush guest physical memory mappings. + * Also includes KSeg0 if KMF_KERN is set. + */ +enum kvm_mips_flush { + KMF_USER = 0x0, + KMF_KERN = 0x1, + KMF_GPA = 0x2, +}; +void kvm_mips_flush_gva_pt(pgd_t *pgd, enum kvm_mips_flush flags); +bool kvm_mips_flush_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn); +int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn); +pgd_t *kvm_pgd_alloc(void); +void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu); +void kvm_trap_emul_invalidate_gva(struct kvm_vcpu *vcpu, unsigned long addr, + bool user); +void kvm_trap_emul_gva_lockless_begin(struct kvm_vcpu *vcpu); +void kvm_trap_emul_gva_lockless_end(struct kvm_vcpu *vcpu); + +enum kvm_mips_fault_result { + KVM_MIPS_MAPPED = 0, + KVM_MIPS_GVA, + KVM_MIPS_GPA, + KVM_MIPS_TLB, + KVM_MIPS_TLBINV, + KVM_MIPS_TLBMOD, +}; +enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, + unsigned long gva, + bool write); + +#define KVM_ARCH_WANT_MMU_NOTIFIER +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); + +static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, + unsigned long address) +{ +} /* Emulation */ -u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu); +int kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu, u32 *out); enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause); +int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out); +int kvm_get_badinstrp(u32 *opc, struct kvm_vcpu *vcpu, u32 *out); + +/** + * kvm_is_ifetch_fault() - Find whether a TLBL exception is due to ifetch fault. + * @vcpu: Virtual CPU. + * + * Returns: Whether the TLBL exception was likely due to an instruction + * fetch fault rather than a data load fault. + */ +static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *vcpu) +{ + unsigned long badvaddr = vcpu->host_cp0_badvaddr; + unsigned long epc = msk_isa16_mode(vcpu->pc); + u32 cause = vcpu->host_cp0_cause; + + if (epc == badvaddr) + return true; + + /* + * Branches may be 32-bit or 16-bit instructions. + * This isn't exact, but we don't really support MIPS16 or microMIPS yet + * in KVM anyway. + */ + if ((cause & CAUSEF_BD) && badvaddr - epc <= 4) + return true; + + return false; +} extern enum emulation_result kvm_mips_emulate_inst(u32 cause, u32 *opc, struct kvm_run *run, struct kvm_vcpu *vcpu); +long kvm_mips_guest_exception_base(struct kvm_vcpu *vcpu); + extern enum emulation_result kvm_mips_emulate_syscall(u32 cause, u32 *opc, struct kvm_run *run, @@ -761,10 +852,6 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} -static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} -static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot) {} -static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index ddd57ad..2abf94f 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -29,9 +29,11 @@ do { \ } \ } while (0) +extern void tlbmiss_handler_setup_pgd(unsigned long); + +/* Note: This is also implemented with uasm in arch/mips/kvm/entry.c */ #define TLBMISS_HANDLER_SETUP_PGD(pgd) \ do { \ - extern void tlbmiss_handler_setup_pgd(unsigned long); \ tlbmiss_handler_setup_pgd((unsigned long)(pgd)); \ htw_set_pwbase((unsigned long)pgd); \ } while (0) @@ -97,17 +99,12 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) static inline void get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) { - extern void kvm_local_flush_tlb_all(void); unsigned long asid = asid_cache(cpu); if (!((asid += cpu_asid_inc()) & cpu_asid_mask(&cpu_data[cpu]))) { if (cpu_has_vtag_icache) flush_icache_all(); -#ifdef CONFIG_KVM - kvm_local_flush_tlb_all(); /* start new asid cycle */ -#else local_flush_tlb_all(); /* start new asid cycle */ -#endif if (!asid) /* fix version if needed */ asid = asid_first_version(cpu); } diff --git a/arch/mips/include/uapi/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h index 6985eb5..a8a0199 100644 --- a/arch/mips/include/uapi/asm/kvm.h +++ b/arch/mips/include/uapi/asm/kvm.h @@ -19,6 +19,8 @@ * Some parts derived from the x86 version of this file. */ +#define __KVM_HAVE_READONLY_MEM + /* * for KVM_GET_REGS and KVM_SET_REGS * diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 7c56d6b..6506732 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -20,7 +20,9 @@ config KVM select EXPORT_UASM select PREEMPT_NOTIFIERS select ANON_INODES + select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_MMIO + select MMU_NOTIFIER select SRCU ---help--- Support for hosting Guest kernels. diff --git a/arch/mips/kvm/dyntrans.c b/arch/mips/kvm/dyntrans.c index 010cef2..f8e7725 100644 --- a/arch/mips/kvm/dyntrans.c +++ b/arch/mips/kvm/dyntrans.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/highmem.h> #include <linux/kvm_host.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/fs.h> #include <linux/bootmem.h> @@ -29,28 +30,37 @@ static int kvm_mips_trans_replace(struct kvm_vcpu *vcpu, u32 *opc, union mips_instruction replace) { - unsigned long paddr, flags; - void *vaddr; - - if (KVM_GUEST_KSEGX((unsigned long)opc) == KVM_GUEST_KSEG0) { - paddr = kvm_mips_translate_guest_kseg0_to_hpa(vcpu, - (unsigned long)opc); - vaddr = kmap_atomic(pfn_to_page(PHYS_PFN(paddr))); - vaddr += paddr & ~PAGE_MASK; - memcpy(vaddr, (void *)&replace, sizeof(u32)); - local_flush_icache_range((unsigned long)vaddr, - (unsigned long)vaddr + 32); - kunmap_atomic(vaddr); - } else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) { - local_irq_save(flags); - memcpy((void *)opc, (void *)&replace, sizeof(u32)); - __local_flush_icache_user_range((unsigned long)opc, - (unsigned long)opc + 32); - local_irq_restore(flags); - } else { - kvm_err("%s: Invalid address: %p\n", __func__, opc); - return -EFAULT; + unsigned long vaddr = (unsigned long)opc; + int err; + +retry: + /* The GVA page table is still active so use the Linux TLB handlers */ + kvm_trap_emul_gva_lockless_begin(vcpu); + err = put_user(replace.word, opc); + kvm_trap_emul_gva_lockless_end(vcpu); + + if (unlikely(err)) { + /* + * We write protect clean pages in GVA page table so normal + * Linux TLB mod handler doesn't silently dirty the page. + * Its also possible we raced with a GVA invalidation. + * Try to force the page to become dirty. + */ + err = kvm_trap_emul_gva_fault(vcpu, vaddr, true); + if (unlikely(err)) { + kvm_info("%s: Address unwriteable: %p\n", + __func__, opc); + return -EFAULT; + } + + /* + * Try again. This will likely trigger a TLB refill, which will + * fetch the new dirty entry from the GVA page table, which + * should then succeed. + */ + goto retry; } + __local_flush_icache_user_range(vaddr, vaddr + 4); return 0; } diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index aa09374..d40cfaa 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -38,23 +38,25 @@ * Compute the return address and do emulate branch simulation, if required. * This function should be called only in branch delay slot active. */ -unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu, - unsigned long instpc) +static int kvm_compute_return_epc(struct kvm_vcpu *vcpu, unsigned long instpc, + unsigned long *out) { unsigned int dspcontrol; union mips_instruction insn; struct kvm_vcpu_arch *arch = &vcpu->arch; long epc = instpc; - long nextpc = KVM_INVALID_INST; + long nextpc; + int err; - if (epc & 3) - goto unaligned; + if (epc & 3) { + kvm_err("%s: unaligned epc\n", __func__); + return -EINVAL; + } /* Read the instruction */ - insn.word = kvm_get_inst((u32 *) epc, vcpu); - - if (insn.word == KVM_INVALID_INST) - return KVM_INVALID_INST; + err = kvm_get_badinstrp((u32 *)epc, vcpu, &insn.word); + if (err) + return err; switch (insn.i_format.opcode) { /* jr and jalr are in r_format format. */ @@ -66,6 +68,8 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu, case jr_op: nextpc = arch->gprs[insn.r_format.rs]; break; + default: + return -EINVAL; } break; @@ -114,8 +118,11 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu, nextpc = epc; break; case bposge32_op: - if (!cpu_has_dsp) - goto sigill; + if (!cpu_has_dsp) { + kvm_err("%s: DSP branch but not DSP ASE\n", + __func__); + return -EINVAL; + } dspcontrol = rddsp(0x01); @@ -125,6 +132,8 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu, epc += 8; nextpc = epc; break; + default: + return -EINVAL; } break; @@ -189,7 +198,7 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu, /* And now the FPA/cp1 branch instructions. */ case cop1_op: kvm_err("%s: unsupported cop1_op\n", __func__); - break; + return -EINVAL; #ifdef CONFIG_CPU_MIPSR6 /* R6 added the following compact branches with forbidden slots */ @@ -198,19 +207,19 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu, /* only rt == 0 isn't compact branch */ if (insn.i_format.rt != 0) goto compact_branch; - break; + return -EINVAL; case pop10_op: case pop30_op: /* only rs == rt == 0 is reserved, rest are compact branches */ if (insn.i_format.rs != 0 || insn.i_format.rt != 0) goto compact_branch; - break; + return -EINVAL; case pop66_op: case pop76_op: /* only rs == 0 isn't compact branch */ if (insn.i_format.rs != 0) goto compact_branch; - break; + return -EINVAL; compact_branch: /* * If we've hit an exception on the forbidden slot, then @@ -221,42 +230,74 @@ compact_branch: break; #else compact_branch: - /* Compact branches not supported before R6 */ - break; + /* Fall through - Compact branches not supported before R6 */ #endif + default: + return -EINVAL; } - return nextpc; - -unaligned: - kvm_err("%s: unaligned epc\n", __func__); - return nextpc; - -sigill: - kvm_err("%s: DSP branch but not DSP ASE\n", __func__); - return nextpc; + *out = nextpc; + return 0; } enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause) { - unsigned long branch_pc; - enum emulation_result er = EMULATE_DONE; + int err; if (cause & CAUSEF_BD) { - branch_pc = kvm_compute_return_epc(vcpu, vcpu->arch.pc); - if (branch_pc == KVM_INVALID_INST) { - er = EMULATE_FAIL; - } else { - vcpu->arch.pc = branch_pc; - kvm_debug("BD update_pc(): New PC: %#lx\n", - vcpu->arch.pc); - } - } else + err = kvm_compute_return_epc(vcpu, vcpu->arch.pc, + &vcpu->arch.pc); + if (err) + return EMULATE_FAIL; + } else { vcpu->arch.pc += 4; + } kvm_debug("update_pc(): New PC: %#lx\n", vcpu->arch.pc); - return er; + return EMULATE_DONE; +} + +/** + * kvm_get_badinstr() - Get bad instruction encoding. + * @opc: Guest pointer to faulting instruction. + * @vcpu: KVM VCPU information. + * + * Gets the instruction encoding of the faulting instruction, using the saved + * BadInstr register value if it exists, otherwise falling back to reading guest + * memory at @opc. + * + * Returns: The instruction encoding of the faulting instruction. + */ +int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out) +{ + if (cpu_has_badinstr) { + *out = vcpu->arch.host_cp0_badinstr; + return 0; + } else { + return kvm_get_inst(opc, vcpu, out); + } +} + +/** + * kvm_get_badinstrp() - Get bad prior instruction encoding. + * @opc: Guest pointer to prior faulting instruction. + * @vcpu: KVM VCPU information. + * + * Gets the instruction encoding of the prior faulting instruction (the branch + * containing the delay slot which faulted), using the saved BadInstrP register + * value if it exists, otherwise falling back to reading guest memory at @opc. + * + * Returns: The instruction encoding of the prior faulting instruction. + */ +int kvm_get_badinstrp(u32 *opc, struct kvm_vcpu *vcpu, u32 *out) +{ + if (cpu_has_badinstrp) { + *out = vcpu->arch.host_cp0_badinstrp; + return 0; + } else { + return kvm_get_inst(opc, vcpu, out); + } } /** @@ -856,22 +897,30 @@ enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu) static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu, struct kvm_mips_tlb *tlb) { + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; + struct mm_struct *user_mm = &vcpu->arch.guest_user_mm; int cpu, i; bool user; /* No need to flush for entries which are already invalid */ if (!((tlb->tlb_lo[0] | tlb->tlb_lo[1]) & ENTRYLO_V)) return; + /* Don't touch host kernel page tables or TLB mappings */ + if ((unsigned long)tlb->tlb_hi > 0x7fffffff) + return; /* User address space doesn't need flushing for KSeg2/3 changes */ user = tlb->tlb_hi < KVM_GUEST_KSEG0; preempt_disable(); + /* Invalidate page table entries */ + kvm_trap_emul_invalidate_gva(vcpu, tlb->tlb_hi & VPN2_MASK, user); + /* * Probe the shadow host TLB for the entry being overwritten, if one * matches, invalidate it */ - kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi); + kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi, user, true); /* Invalidate the whole ASID on other CPUs */ cpu = smp_processor_id(); @@ -879,8 +928,8 @@ static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu, if (i == cpu) continue; if (user) - vcpu->arch.guest_user_asid[i] = 0; - vcpu->arch.guest_kernel_asid[i] = 0; + cpu_context(i, user_mm) = 0; + cpu_context(i, kern_mm) = 0; } preempt_enable(); @@ -1017,7 +1066,7 @@ unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu) unsigned int mask = MIPS_CONF_M; /* KScrExist */ - mask |= (unsigned int)vcpu->arch.kscratch_enabled << 16; + mask |= 0xfc << MIPS_CONF4_KSCREXIST_SHIFT; return mask; } @@ -1056,6 +1105,7 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst, struct kvm_vcpu *vcpu) { struct mips_coproc *cop0 = vcpu->arch.cop0; + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; enum emulation_result er = EMULATE_DONE; u32 rt, rd, sel; unsigned long curr_pc; @@ -1150,14 +1200,13 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst, er = EMULATE_FAIL; break; } -#define C0_EBASE_CORE_MASK 0xff if ((rd == MIPS_CP0_PRID) && (sel == 1)) { - /* Preserve CORE number */ - kvm_change_c0_guest_ebase(cop0, - ~(C0_EBASE_CORE_MASK), + /* + * Preserve core number, and keep the exception + * base in guest KSeg0. + */ + kvm_change_c0_guest_ebase(cop0, 0x1ffff000, vcpu->arch.gprs[rt]); - kvm_err("MTCz, cop0->reg[EBASE]: %#lx\n", - kvm_read_c0_guest_ebase(cop0)); } else if (rd == MIPS_CP0_TLB_HI && sel == 0) { u32 nasid = vcpu->arch.gprs[rt] & KVM_ENTRYHI_ASID; @@ -1169,6 +1218,17 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst, nasid); /* + * Flush entries from the GVA page + * tables. + * Guest user page table will get + * flushed lazily on re-entry to guest + * user if the guest ASID actually + * changes. + */ + kvm_mips_flush_gva_pt(kern_mm->pgd, + KMF_KERN); + + /* * Regenerate/invalidate kernel MMU * context. * The user MMU context will be @@ -1178,13 +1238,10 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst, */ preempt_disable(); cpu = smp_processor_id(); - kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, - cpu, vcpu); - vcpu->arch.guest_kernel_asid[cpu] = - vcpu->arch.guest_kernel_mm.context.asid[cpu]; + get_new_mmu_context(kern_mm, cpu); for_each_possible_cpu(i) if (i != cpu) - vcpu->arch.guest_kernel_asid[i] = 0; + cpu_context(i, kern_mm) = 0; preempt_enable(); } kvm_write_c0_guest_entryhi(cop0, @@ -1639,12 +1696,56 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst, return er; } +static enum emulation_result kvm_mips_guest_cache_op(int (*fn)(unsigned long), + unsigned long curr_pc, + unsigned long addr, + struct kvm_run *run, + struct kvm_vcpu *vcpu, + u32 cause) +{ + int err; + + for (;;) { + /* Carefully attempt the cache operation */ + kvm_trap_emul_gva_lockless_begin(vcpu); + err = fn(addr); + kvm_trap_emul_gva_lockless_end(vcpu); + + if (likely(!err)) + return EMULATE_DONE; + + /* + * Try to handle the fault and retry, maybe we just raced with a + * GVA invalidation. + */ + switch (kvm_trap_emul_gva_fault(vcpu, addr, false)) { + case KVM_MIPS_GVA: + case KVM_MIPS_GPA: + /* bad virtual or physical address */ + return EMULATE_FAIL; + case KVM_MIPS_TLB: + /* no matching guest TLB */ + vcpu->arch.host_cp0_badvaddr = addr; + vcpu->arch.pc = curr_pc; + kvm_mips_emulate_tlbmiss_ld(cause, NULL, run, vcpu); + return EMULATE_EXCEPT; + case KVM_MIPS_TLBINV: + /* invalid matching guest TLB */ + vcpu->arch.host_cp0_badvaddr = addr; + vcpu->arch.pc = curr_pc; + kvm_mips_emulate_tlbinv_ld(cause, NULL, run, vcpu); + return EMULATE_EXCEPT; + default: + break; + }; + } +} + enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, u32 *opc, u32 cause, struct kvm_run *run, struct kvm_vcpu *vcpu) { - struct mips_coproc *cop0 = vcpu->arch.cop0; enum emulation_result er = EMULATE_DONE; u32 cache, op_inst, op, base; s16 offset; @@ -1701,80 +1802,16 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, goto done; } - preempt_disable(); - if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 && - kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) { - kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n", - __func__, va, vcpu, read_c0_entryhi()); - er = EMULATE_FAIL; - preempt_enable(); - goto done; - } - } else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) || - KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { - int index; - - /* If an entry already exists then skip */ - if (kvm_mips_host_tlb_lookup(vcpu, va) >= 0) - goto skip_fault; - - /* - * If address not in the guest TLB, then give the guest a fault, - * the resulting handler will do the right thing - */ - index = kvm_mips_guest_tlb_lookup(vcpu, (va & VPN2_MASK) | - (kvm_read_c0_guest_entryhi - (cop0) & KVM_ENTRYHI_ASID)); - - if (index < 0) { - vcpu->arch.host_cp0_badvaddr = va; - vcpu->arch.pc = curr_pc; - er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run, - vcpu); - preempt_enable(); - goto dont_update_pc; - } else { - struct kvm_mips_tlb *tlb = &vcpu->arch.guest_tlb[index]; - /* - * Check if the entry is valid, if not then setup a TLB - * invalid exception to the guest - */ - if (!TLB_IS_VALID(*tlb, va)) { - vcpu->arch.host_cp0_badvaddr = va; - vcpu->arch.pc = curr_pc; - er = kvm_mips_emulate_tlbinv_ld(cause, NULL, - run, vcpu); - preempt_enable(); - goto dont_update_pc; - } - /* - * We fault an entry from the guest tlb to the - * shadow host TLB - */ - if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { - kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", - __func__, va, index, vcpu, - read_c0_entryhi()); - er = EMULATE_FAIL; - preempt_enable(); - goto done; - } - } - } else { - kvm_err("INVALID CACHE INDEX/ADDRESS (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n", - cache, op, base, arch->gprs[base], offset); - er = EMULATE_FAIL; - preempt_enable(); - goto done; - - } - -skip_fault: /* XXXKYMA: Only a subset of cache ops are supported, used by Linux */ if (op_inst == Hit_Writeback_Inv_D || op_inst == Hit_Invalidate_D) { - flush_dcache_line(va); - + /* + * Perform the dcache part of icache synchronisation on the + * guest's behalf. + */ + er = kvm_mips_guest_cache_op(protected_writeback_dcache_line, + curr_pc, va, run, vcpu, cause); + if (er != EMULATE_DONE) + goto done; #ifdef CONFIG_KVM_MIPS_DYN_TRANS /* * Replace the CACHE instruction, with a SYNCI, not the same, @@ -1783,8 +1820,15 @@ skip_fault: kvm_mips_trans_cache_va(inst, opc, vcpu); #endif } else if (op_inst == Hit_Invalidate_I) { - flush_dcache_line(va); - flush_icache_line(va); + /* Perform the icache synchronisation on the guest's behalf */ + er = kvm_mips_guest_cache_op(protected_writeback_dcache_line, + curr_pc, va, run, vcpu, cause); + if (er != EMULATE_DONE) + goto done; + er = kvm_mips_guest_cache_op(protected_flush_icache_line, + curr_pc, va, run, vcpu, cause); + if (er != EMULATE_DONE) + goto done; #ifdef CONFIG_KVM_MIPS_DYN_TRANS /* Replace the CACHE instruction, with a SYNCI */ @@ -1796,17 +1840,13 @@ skip_fault: er = EMULATE_FAIL; } - preempt_enable(); done: /* Rollback PC only if emulation was unsuccessful */ if (er == EMULATE_FAIL) vcpu->arch.pc = curr_pc; - -dont_update_pc: - /* - * This is for exceptions whose emulation updates the PC, so do not - * overwrite the PC under any circumstances - */ + /* Guest exception needs guest to resume */ + if (er == EMULATE_EXCEPT) + er = EMULATE_DONE; return er; } @@ -1817,12 +1857,14 @@ enum emulation_result kvm_mips_emulate_inst(u32 cause, u32 *opc, { union mips_instruction inst; enum emulation_result er = EMULATE_DONE; + int err; /* Fetch the instruction. */ if (cause & CAUSEF_BD) opc += 1; - - inst.word = kvm_get_inst(opc, vcpu); + err = kvm_get_badinstr(opc, vcpu, &inst.word); + if (err) + return EMULATE_FAIL; switch (inst.r_format.opcode) { case cop0_op: @@ -1874,6 +1916,22 @@ unknown: return er; } +/** + * kvm_mips_guest_exception_base() - Find guest exception vector base address. + * + * Returns: The base address of the current guest exception vector, taking + * both Guest.CP0_Status.BEV and Guest.CP0_EBase into account. + */ +long kvm_mips_guest_exception_base(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + + if (kvm_read_c0_guest_status(cop0) & ST0_BEV) + return KVM_GUEST_CKSEG1ADDR(0x1fc00200); + else + return kvm_read_c0_guest_ebase(cop0) & MIPS_EBASE_BASE; +} + enum emulation_result kvm_mips_emulate_syscall(u32 cause, u32 *opc, struct kvm_run *run, @@ -1899,7 +1957,7 @@ enum emulation_result kvm_mips_emulate_syscall(u32 cause, (EXCCODE_SYS << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver SYSCALL when EXL is already set\n"); @@ -1933,13 +1991,13 @@ enum emulation_result kvm_mips_emulate_tlbmiss_ld(u32 cause, arch->pc); /* set pc to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x0; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x0; } else { kvm_debug("[EXL == 1] delivering TLB MISS @ pc %#lx\n", arch->pc); - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } kvm_change_c0_guest_cause(cop0, (0xff), @@ -1949,8 +2007,6 @@ enum emulation_result kvm_mips_emulate_tlbmiss_ld(u32 cause, kvm_write_c0_guest_badvaddr(cop0, vcpu->arch.host_cp0_badvaddr); /* XXXKYMA: is the context register used by linux??? */ kvm_write_c0_guest_entryhi(cop0, entryhi); - /* Blow away the shadow host TLBs */ - kvm_mips_flush_host_tlb(1); return EMULATE_DONE; } @@ -1978,16 +2034,14 @@ enum emulation_result kvm_mips_emulate_tlbinv_ld(u32 cause, kvm_debug("[EXL == 0] delivering TLB INV @ pc %#lx\n", arch->pc); - - /* set pc to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; - } else { kvm_debug("[EXL == 1] delivering TLB MISS @ pc %#lx\n", arch->pc); - arch->pc = KVM_GUEST_KSEG0 + 0x180; } + /* set pc to the exception entry point */ + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; + kvm_change_c0_guest_cause(cop0, (0xff), (EXCCODE_TLBL << CAUSEB_EXCCODE)); @@ -1995,8 +2049,6 @@ enum emulation_result kvm_mips_emulate_tlbinv_ld(u32 cause, kvm_write_c0_guest_badvaddr(cop0, vcpu->arch.host_cp0_badvaddr); /* XXXKYMA: is the context register used by linux??? */ kvm_write_c0_guest_entryhi(cop0, entryhi); - /* Blow away the shadow host TLBs */ - kvm_mips_flush_host_tlb(1); return EMULATE_DONE; } @@ -2025,11 +2077,11 @@ enum emulation_result kvm_mips_emulate_tlbmiss_st(u32 cause, arch->pc); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x0; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x0; } else { kvm_debug("[EXL == 1] Delivering TLB MISS @ pc %#lx\n", arch->pc); - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } kvm_change_c0_guest_cause(cop0, (0xff), @@ -2039,8 +2091,6 @@ enum emulation_result kvm_mips_emulate_tlbmiss_st(u32 cause, kvm_write_c0_guest_badvaddr(cop0, vcpu->arch.host_cp0_badvaddr); /* XXXKYMA: is the context register used by linux??? */ kvm_write_c0_guest_entryhi(cop0, entryhi); - /* Blow away the shadow host TLBs */ - kvm_mips_flush_host_tlb(1); return EMULATE_DONE; } @@ -2067,15 +2117,14 @@ enum emulation_result kvm_mips_emulate_tlbinv_st(u32 cause, kvm_debug("[EXL == 0] Delivering TLB MISS @ pc %#lx\n", arch->pc); - - /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; } else { kvm_debug("[EXL == 1] Delivering TLB MISS @ pc %#lx\n", arch->pc); - arch->pc = KVM_GUEST_KSEG0 + 0x180; } + /* Set PC to the exception entry point */ + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; + kvm_change_c0_guest_cause(cop0, (0xff), (EXCCODE_TLBS << CAUSEB_EXCCODE)); @@ -2083,41 +2132,10 @@ enum emulation_result kvm_mips_emulate_tlbinv_st(u32 cause, kvm_write_c0_guest_badvaddr(cop0, vcpu->arch.host_cp0_badvaddr); /* XXXKYMA: is the context register used by linux??? */ kvm_write_c0_guest_entryhi(cop0, entryhi); - /* Blow away the shadow host TLBs */ - kvm_mips_flush_host_tlb(1); return EMULATE_DONE; } -/* TLBMOD: store into address matching TLB with Dirty bit off */ -enum emulation_result kvm_mips_handle_tlbmod(u32 cause, u32 *opc, - struct kvm_run *run, - struct kvm_vcpu *vcpu) -{ - enum emulation_result er = EMULATE_DONE; -#ifdef DEBUG - struct mips_coproc *cop0 = vcpu->arch.cop0; - unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) | - (kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID); - int index; - - /* If address not in the guest TLB, then we are in trouble */ - index = kvm_mips_guest_tlb_lookup(vcpu, entryhi); - if (index < 0) { - /* XXXKYMA Invalidate and retry */ - kvm_mips_host_tlb_inv(vcpu, vcpu->arch.host_cp0_badvaddr); - kvm_err("%s: host got TLBMOD for %#lx but entry not present in Guest TLB\n", - __func__, entryhi); - kvm_mips_dump_guest_tlbs(vcpu); - kvm_mips_dump_host_tlbs(); - return EMULATE_FAIL; - } -#endif - - er = kvm_mips_emulate_tlbmod(cause, opc, run, vcpu); - return er; -} - enum emulation_result kvm_mips_emulate_tlbmod(u32 cause, u32 *opc, struct kvm_run *run, @@ -2140,14 +2158,13 @@ enum emulation_result kvm_mips_emulate_tlbmod(u32 cause, kvm_debug("[EXL == 0] Delivering TLB MOD @ pc %#lx\n", arch->pc); - - arch->pc = KVM_GUEST_KSEG0 + 0x180; } else { kvm_debug("[EXL == 1] Delivering TLB MOD @ pc %#lx\n", arch->pc); - arch->pc = KVM_GUEST_KSEG0 + 0x180; } + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; + kvm_change_c0_guest_cause(cop0, (0xff), (EXCCODE_MOD << CAUSEB_EXCCODE)); @@ -2155,8 +2172,6 @@ enum emulation_result kvm_mips_emulate_tlbmod(u32 cause, kvm_write_c0_guest_badvaddr(cop0, vcpu->arch.host_cp0_badvaddr); /* XXXKYMA: is the context register used by linux??? */ kvm_write_c0_guest_entryhi(cop0, entryhi); - /* Blow away the shadow host TLBs */ - kvm_mips_flush_host_tlb(1); return EMULATE_DONE; } @@ -2181,7 +2196,7 @@ enum emulation_result kvm_mips_emulate_fpu_exc(u32 cause, } - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; kvm_change_c0_guest_cause(cop0, (0xff), (EXCCODE_CPU << CAUSEB_EXCCODE)); @@ -2215,7 +2230,7 @@ enum emulation_result kvm_mips_emulate_ri_exc(u32 cause, (EXCCODE_RI << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver RI when EXL is already set\n"); @@ -2250,7 +2265,7 @@ enum emulation_result kvm_mips_emulate_bp_exc(u32 cause, (EXCCODE_BP << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver BP when EXL is already set\n"); @@ -2285,7 +2300,7 @@ enum emulation_result kvm_mips_emulate_trap_exc(u32 cause, (EXCCODE_TR << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver TRAP when EXL is already set\n"); @@ -2320,7 +2335,7 @@ enum emulation_result kvm_mips_emulate_msafpe_exc(u32 cause, (EXCCODE_MSAFPE << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver MSAFPE when EXL is already set\n"); @@ -2355,7 +2370,7 @@ enum emulation_result kvm_mips_emulate_fpe_exc(u32 cause, (EXCCODE_FPE << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver FPE when EXL is already set\n"); @@ -2390,7 +2405,7 @@ enum emulation_result kvm_mips_emulate_msadis_exc(u32 cause, (EXCCODE_MSADIS << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; } else { kvm_err("Trying to deliver MSADIS when EXL is already set\n"); @@ -2409,6 +2424,7 @@ enum emulation_result kvm_mips_handle_ri(u32 cause, u32 *opc, enum emulation_result er = EMULATE_DONE; unsigned long curr_pc; union mips_instruction inst; + int err; /* * Update PC and hold onto current PC in case there is @@ -2422,11 +2438,9 @@ enum emulation_result kvm_mips_handle_ri(u32 cause, u32 *opc, /* Fetch the instruction. */ if (cause & CAUSEF_BD) opc += 1; - - inst.word = kvm_get_inst(opc, vcpu); - - if (inst.word == KVM_INVALID_INST) { - kvm_err("%s: Cannot get inst @ %p\n", __func__, opc); + err = kvm_get_badinstr(opc, vcpu, &inst.word); + if (err) { + kvm_err("%s: Cannot get inst @ %p (%d)\n", __func__, opc, err); return EMULATE_FAIL; } @@ -2557,7 +2571,7 @@ static enum emulation_result kvm_mips_emulate_exc(u32 cause, (exccode << CAUSEB_EXCCODE)); /* Set PC to the exception entry point */ - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc = kvm_mips_guest_exception_base(vcpu) + 0x180; kvm_write_c0_guest_badvaddr(cop0, vcpu->arch.host_cp0_badvaddr); kvm_debug("Delivering EXC %d @ pc %#lx, badVaddr: %#lx\n", @@ -2670,7 +2684,8 @@ enum emulation_result kvm_mips_check_privilege(u32 cause, enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, u32 *opc, struct kvm_run *run, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, + bool write_fault) { enum emulation_result er = EMULATE_DONE; u32 exccode = (cause >> CAUSEB_EXCCODE) & 0x1f; @@ -2726,7 +2741,8 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, * OK we have a Guest TLB entry, now inject it into the * shadow host TLB */ - if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, va, + write_fault)) { kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", __func__, va, index, vcpu, read_c0_entryhi()); diff --git a/arch/mips/kvm/entry.c b/arch/mips/kvm/entry.c index e92fb19..c5b254c 100644 --- a/arch/mips/kvm/entry.c +++ b/arch/mips/kvm/entry.c @@ -12,8 +12,11 @@ */ #include <linux/kvm_host.h> +#include <linux/log2.h> +#include <asm/mmu_context.h> #include <asm/msa.h> #include <asm/setup.h> +#include <asm/tlbex.h> #include <asm/uasm.h> /* Register names */ @@ -50,6 +53,8 @@ /* Some CP0 registers */ #define C0_HWRENA 7, 0 #define C0_BADVADDR 8, 0 +#define C0_BADINSTR 8, 1 +#define C0_BADINSTRP 8, 2 #define C0_ENTRYHI 10, 0 #define C0_STATUS 12, 0 #define C0_CAUSE 13, 0 @@ -89,6 +94,21 @@ static void *kvm_mips_build_ret_from_exit(void *addr); static void *kvm_mips_build_ret_to_guest(void *addr); static void *kvm_mips_build_ret_to_host(void *addr); +/* + * The version of this function in tlbex.c uses current_cpu_type(), but for KVM + * we assume symmetry. + */ +static int c0_kscratch(void) +{ + switch (boot_cpu_type()) { + case CPU_XLP: + case CPU_XLR: + return 22; + default: + return 31; + } +} + /** * kvm_mips_entry_setup() - Perform global setup for entry code. * @@ -103,18 +123,21 @@ int kvm_mips_entry_setup(void) * We prefer to use KScratchN registers if they are available over the * defaults above, which may not work on all cores. */ - unsigned int kscratch_mask = cpu_data[0].kscratch_mask & 0xfc; + unsigned int kscratch_mask = cpu_data[0].kscratch_mask; + + if (pgd_reg != -1) + kscratch_mask &= ~BIT(pgd_reg); /* Pick a scratch register for storing VCPU */ if (kscratch_mask) { - scratch_vcpu[0] = 31; + scratch_vcpu[0] = c0_kscratch(); scratch_vcpu[1] = ffs(kscratch_mask) - 1; kscratch_mask &= ~BIT(scratch_vcpu[1]); } /* Pick a scratch register to use as a temp for saving state */ if (kscratch_mask) { - scratch_tmp[0] = 31; + scratch_tmp[0] = c0_kscratch(); scratch_tmp[1] = ffs(kscratch_mask) - 1; kscratch_mask &= ~BIT(scratch_tmp[1]); } @@ -130,7 +153,7 @@ static void kvm_mips_build_save_scratch(u32 **p, unsigned int tmp, UASM_i_SW(p, tmp, offsetof(struct pt_regs, cp0_epc), frame); /* Save the temp scratch register value in cp0_cause of stack frame */ - if (scratch_tmp[0] == 31) { + if (scratch_tmp[0] == c0_kscratch()) { UASM_i_MFC0(p, tmp, scratch_tmp[0], scratch_tmp[1]); UASM_i_SW(p, tmp, offsetof(struct pt_regs, cp0_cause), frame); } @@ -146,7 +169,7 @@ static void kvm_mips_build_restore_scratch(u32 **p, unsigned int tmp, UASM_i_LW(p, tmp, offsetof(struct pt_regs, cp0_epc), frame); UASM_i_MTC0(p, tmp, scratch_vcpu[0], scratch_vcpu[1]); - if (scratch_tmp[0] == 31) { + if (scratch_tmp[0] == c0_kscratch()) { UASM_i_LW(p, tmp, offsetof(struct pt_regs, cp0_cause), frame); UASM_i_MTC0(p, tmp, scratch_tmp[0], scratch_tmp[1]); } @@ -286,23 +309,26 @@ static void *kvm_mips_build_enter_guest(void *addr) uasm_i_andi(&p, T0, T0, KSU_USER | ST0_ERL | ST0_EXL); uasm_i_xori(&p, T0, T0, KSU_USER); uasm_il_bnez(&p, &r, T0, label_kernel_asid); - UASM_i_ADDIU(&p, T1, K1, - offsetof(struct kvm_vcpu_arch, guest_kernel_asid)); + UASM_i_ADDIU(&p, T1, K1, offsetof(struct kvm_vcpu_arch, + guest_kernel_mm.context.asid)); /* else user */ - UASM_i_ADDIU(&p, T1, K1, - offsetof(struct kvm_vcpu_arch, guest_user_asid)); + UASM_i_ADDIU(&p, T1, K1, offsetof(struct kvm_vcpu_arch, + guest_user_mm.context.asid)); uasm_l_kernel_asid(&l, p); /* t1: contains the base of the ASID array, need to get the cpu id */ /* smp_processor_id */ uasm_i_lw(&p, T2, offsetof(struct thread_info, cpu), GP); - /* x4 */ - uasm_i_sll(&p, T2, T2, 2); + /* index the ASID array */ + uasm_i_sll(&p, T2, T2, ilog2(sizeof(long))); UASM_i_ADDU(&p, T3, T1, T2); - uasm_i_lw(&p, K0, 0, T3); + UASM_i_LW(&p, K0, 0, T3); #ifdef CONFIG_MIPS_ASID_BITS_VARIABLE - /* x sizeof(struct cpuinfo_mips)/4 */ - uasm_i_addiu(&p, T3, ZERO, sizeof(struct cpuinfo_mips)/4); + /* + * reuse ASID array offset + * cpuinfo_mips is a multiple of sizeof(long) + */ + uasm_i_addiu(&p, T3, ZERO, sizeof(struct cpuinfo_mips)/sizeof(long)); uasm_i_mul(&p, T2, T2, T3); UASM_i_LA_mostly(&p, AT, (long)&cpu_data[0].asid_mask); @@ -312,7 +338,20 @@ static void *kvm_mips_build_enter_guest(void *addr) #else uasm_i_andi(&p, K0, K0, MIPS_ENTRYHI_ASID); #endif - uasm_i_mtc0(&p, K0, C0_ENTRYHI); + + /* + * Set up KVM T&E GVA pgd. + * This does roughly the same as TLBMISS_HANDLER_SETUP_PGD(): + * - call tlbmiss_handler_setup_pgd(mm->pgd) + * - but skips write into CP0_PWBase for now + */ + UASM_i_LW(&p, A0, (int)offsetof(struct mm_struct, pgd) - + (int)offsetof(struct mm_struct, context.asid), T1); + + UASM_i_LA(&p, T9, (unsigned long)tlbmiss_handler_setup_pgd); + uasm_i_jalr(&p, RA, T9); + uasm_i_mtc0(&p, K0, C0_ENTRYHI); + uasm_i_ehb(&p); /* Disable RDHWR access */ @@ -348,6 +387,80 @@ static void *kvm_mips_build_enter_guest(void *addr) } /** + * kvm_mips_build_tlb_refill_exception() - Assemble TLB refill handler. + * @addr: Address to start writing code. + * @handler: Address of common handler (within range of @addr). + * + * Assemble TLB refill exception fast path handler for guest execution. + * + * Returns: Next address after end of written function. + */ +void *kvm_mips_build_tlb_refill_exception(void *addr, void *handler) +{ + u32 *p = addr; + struct uasm_label labels[2]; + struct uasm_reloc relocs[2]; + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; + + memset(labels, 0, sizeof(labels)); + memset(relocs, 0, sizeof(relocs)); + + /* Save guest k1 into scratch register */ + UASM_i_MTC0(&p, K1, scratch_tmp[0], scratch_tmp[1]); + + /* Get the VCPU pointer from the VCPU scratch register */ + UASM_i_MFC0(&p, K1, scratch_vcpu[0], scratch_vcpu[1]); + + /* Save guest k0 into VCPU structure */ + UASM_i_SW(&p, K0, offsetof(struct kvm_vcpu, arch.gprs[K0]), K1); + + /* + * Some of the common tlbex code uses current_cpu_type(). For KVM we + * assume symmetry and just disable preemption to silence the warning. + */ + preempt_disable(); + + /* + * Now for the actual refill bit. A lot of this can be common with the + * Linux TLB refill handler, however we don't need to handle so many + * cases. We only need to handle user mode refills, and user mode runs + * with 32-bit addressing. + * + * Therefore the branch to label_vmalloc generated by build_get_pmde64() + * that isn't resolved should never actually get taken and is harmless + * to leave in place for now. + */ + +#ifdef CONFIG_64BIT + build_get_pmde64(&p, &l, &r, K0, K1); /* get pmd in K1 */ +#else + build_get_pgde32(&p, K0, K1); /* get pgd in K1 */ +#endif + + /* we don't support huge pages yet */ + + build_get_ptep(&p, K0, K1); + build_update_entries(&p, K0, K1); + build_tlb_write_entry(&p, &l, &r, tlb_random); + + preempt_enable(); + + /* Get the VCPU pointer from the VCPU scratch register again */ + UASM_i_MFC0(&p, K1, scratch_vcpu[0], scratch_vcpu[1]); + + /* Restore the guest's k0/k1 registers */ + UASM_i_LW(&p, K0, offsetof(struct kvm_vcpu, arch.gprs[K0]), K1); + uasm_i_ehb(&p); + UASM_i_MFC0(&p, K1, scratch_tmp[0], scratch_tmp[1]); + + /* Jump to guest */ + uasm_i_eret(&p); + + return p; +} + +/** * kvm_mips_build_exception() - Assemble first level guest exception handler. * @addr: Address to start writing code. * @handler: Address of common handler (within range of @addr). @@ -468,6 +581,18 @@ void *kvm_mips_build_exit(void *addr) uasm_i_mfc0(&p, K0, C0_CAUSE); uasm_i_sw(&p, K0, offsetof(struct kvm_vcpu_arch, host_cp0_cause), K1); + if (cpu_has_badinstr) { + uasm_i_mfc0(&p, K0, C0_BADINSTR); + uasm_i_sw(&p, K0, offsetof(struct kvm_vcpu_arch, + host_cp0_badinstr), K1); + } + + if (cpu_has_badinstrp) { + uasm_i_mfc0(&p, K0, C0_BADINSTRP); + uasm_i_sw(&p, K0, offsetof(struct kvm_vcpu_arch, + host_cp0_badinstrp), K1); + } + /* Now restore the host state just enough to run the handlers */ /* Switch EBASE to the one used by Linux */ diff --git a/arch/mips/kvm/interrupt.c b/arch/mips/kvm/interrupt.c index e88403b..aa0a1a0 100644 --- a/arch/mips/kvm/interrupt.c +++ b/arch/mips/kvm/interrupt.c @@ -183,10 +183,11 @@ int kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority, (exccode << CAUSEB_EXCCODE)); /* XXXSL Set PC to the interrupt exception entry point */ + arch->pc = kvm_mips_guest_exception_base(vcpu); if (kvm_read_c0_guest_cause(cop0) & CAUSEF_IV) - arch->pc = KVM_GUEST_KSEG0 + 0x200; + arch->pc += 0x200; else - arch->pc = KVM_GUEST_KSEG0 + 0x180; + arch->pc += 0x180; clear_bit(priority, &vcpu->arch.pending_exceptions); } diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 29ec9ab..ed81e5a 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -22,6 +22,7 @@ #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> +#include <asm/pgalloc.h> #include <asm/pgtable.h> #include <linux/kvm_host.h> @@ -63,18 +64,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { {NULL} }; -static int kvm_mips_reset_vcpu(struct kvm_vcpu *vcpu) -{ - int i; - - for_each_possible_cpu(i) { - vcpu->arch.guest_kernel_asid[i] = 0; - vcpu->arch.guest_user_asid[i] = 0; - } - - return 0; -} - /* * XXXKYMA: We are simulatoring a processor that has the WII bit set in * Config7, so we are "runnable" if interrupts are pending @@ -104,39 +93,12 @@ void kvm_arch_check_processor_compat(void *rtn) *(int *)rtn = 0; } -static void kvm_mips_init_tlbs(struct kvm *kvm) -{ - unsigned long wired; - - /* - * Add a wired entry to the TLB, it is used to map the commpage to - * the Guest kernel - */ - wired = read_c0_wired(); - write_c0_wired(wired + 1); - mtc0_tlbw_hazard(); - kvm->arch.commpage_tlb = wired; - - kvm_debug("[%d] commpage TLB: %d\n", smp_processor_id(), - kvm->arch.commpage_tlb); -} - -static void kvm_mips_init_vm_percpu(void *arg) -{ - struct kvm *kvm = (struct kvm *)arg; - - kvm_mips_init_tlbs(kvm); - kvm_mips_callbacks->vm_init(kvm); - -} - int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - if (atomic_inc_return(&kvm_mips_instance) == 1) { - kvm_debug("%s: 1st KVM instance, setup host TLB parameters\n", - __func__); - on_each_cpu(kvm_mips_init_vm_percpu, kvm, 1); - } + /* Allocate page table to map GPA -> RPA */ + kvm->arch.gpa_mm.pgd = kvm_pgd_alloc(); + if (!kvm->arch.gpa_mm.pgd) + return -ENOMEM; return 0; } @@ -156,13 +118,6 @@ void kvm_mips_free_vcpus(struct kvm *kvm) unsigned int i; struct kvm_vcpu *vcpu; - /* Put the pages we reserved for the guest pmap */ - for (i = 0; i < kvm->arch.guest_pmap_npages; i++) { - if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE) - kvm_release_pfn_clean(kvm->arch.guest_pmap[i]); - } - kfree(kvm->arch.guest_pmap); - kvm_for_each_vcpu(i, vcpu, kvm) { kvm_arch_vcpu_free(vcpu); } @@ -177,25 +132,17 @@ void kvm_mips_free_vcpus(struct kvm *kvm) mutex_unlock(&kvm->lock); } -static void kvm_mips_uninit_tlbs(void *arg) +static void kvm_mips_free_gpa_pt(struct kvm *kvm) { - /* Restore wired count */ - write_c0_wired(0); - mtc0_tlbw_hazard(); - /* Clear out all the TLBs */ - kvm_local_flush_tlb_all(); + /* It should always be safe to remove after flushing the whole range */ + WARN_ON(!kvm_mips_flush_gpa_pt(kvm, 0, ~0)); + pgd_free(NULL, kvm->arch.gpa_mm.pgd); } void kvm_arch_destroy_vm(struct kvm *kvm) { kvm_mips_free_vcpus(kvm); - - /* If this is the last instance, restore wired count */ - if (atomic_dec_return(&kvm_mips_instance) == 0) { - kvm_debug("%s: last KVM instance, restoring TLB parameters\n", - __func__); - on_each_cpu(kvm_mips_uninit_tlbs, NULL, 1); - } + kvm_mips_free_gpa_pt(kvm); } long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, @@ -210,6 +157,32 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, return 0; } +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + /* Flush whole GPA */ + kvm_mips_flush_gpa_pt(kvm, 0, ~0); + + /* Let implementation do the rest */ + kvm_mips_callbacks->flush_shadow_all(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + /* + * The slot has been made invalid (ready for moving or deletion), so we + * need to ensure that it can no longer be accessed by any guest VCPUs. + */ + + spin_lock(&kvm->mmu_lock); + /* Flush slot from GPA */ + kvm_mips_flush_gpa_pt(kvm, slot->base_gfn, + slot->base_gfn + slot->npages - 1); + /* Let implementation do the rest */ + kvm_mips_callbacks->flush_shadow_memslot(kvm, slot); + spin_unlock(&kvm->mmu_lock); +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, @@ -224,35 +197,32 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - unsigned long npages = 0; - int i; + int needs_flush; kvm_debug("%s: kvm: %p slot: %d, GPA: %llx, size: %llx, QVA: %llx\n", __func__, kvm, mem->slot, mem->guest_phys_addr, mem->memory_size, mem->userspace_addr); - /* Setup Guest PMAP table */ - if (!kvm->arch.guest_pmap) { - if (mem->slot == 0) - npages = mem->memory_size >> PAGE_SHIFT; - - if (npages) { - kvm->arch.guest_pmap_npages = npages; - kvm->arch.guest_pmap = - kzalloc(npages * sizeof(unsigned long), GFP_KERNEL); - - if (!kvm->arch.guest_pmap) { - kvm_err("Failed to allocate guest PMAP\n"); - return; - } - - kvm_debug("Allocated space for Guest PMAP Table (%ld pages) @ %p\n", - npages, kvm->arch.guest_pmap); - - /* Now setup the page table */ - for (i = 0; i < npages; i++) - kvm->arch.guest_pmap[i] = KVM_INVALID_PAGE; - } + /* + * If dirty page logging is enabled, write protect all pages in the slot + * ready for dirty logging. + * + * There is no need to do this in any of the following cases: + * CREATE: No dirty mappings will already exist. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot() + */ + if (change == KVM_MR_FLAGS_ONLY && + (!(old->flags & KVM_MEM_LOG_DIRTY_PAGES) && + new->flags & KVM_MEM_LOG_DIRTY_PAGES)) { + spin_lock(&kvm->mmu_lock); + /* Write protect GPA page table entries */ + needs_flush = kvm_mips_mkclean_gpa_pt(kvm, new->base_gfn, + new->base_gfn + new->npages - 1); + /* Let implementation do the rest */ + if (needs_flush) + kvm_mips_callbacks->flush_shadow_memslot(kvm, new); + spin_unlock(&kvm->mmu_lock); } } @@ -276,7 +246,7 @@ static inline void dump_handler(const char *symbol, void *start, void *end) struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { int err, size; - void *gebase, *p, *handler; + void *gebase, *p, *handler, *refill_start, *refill_end; int i; struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); @@ -329,8 +299,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) /* Build guest exception vectors dynamically in unmapped memory */ handler = gebase + 0x2000; - /* TLB Refill, EXL = 0 */ - kvm_mips_build_exception(gebase, handler); + /* TLB refill */ + refill_start = gebase; + refill_end = kvm_mips_build_tlb_refill_exception(refill_start, handler); /* General Exception Entry point */ kvm_mips_build_exception(gebase + 0x180, handler); @@ -356,6 +327,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) pr_debug("#include <asm/regdef.h>\n"); pr_debug("\n"); dump_handler("kvm_vcpu_run", vcpu->arch.vcpu_run, p); + dump_handler("kvm_tlb_refill", refill_start, refill_end); dump_handler("kvm_gen_exc", gebase + 0x180, gebase + 0x200); dump_handler("kvm_exit", gebase + 0x2000, vcpu->arch.vcpu_run); @@ -406,6 +378,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvm_mips_dump_stats(vcpu); + kvm_mmu_free_memory_caches(vcpu); kfree(vcpu->arch.guest_ebase); kfree(vcpu->arch.kseg0_commpage); kfree(vcpu); @@ -422,37 +395,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, return -ENOIOCTLCMD; } -/* Must be called with preemption disabled, just before entering guest */ -static void kvm_mips_check_asids(struct kvm_vcpu *vcpu) -{ - struct mips_coproc *cop0 = vcpu->arch.cop0; - int i, cpu = smp_processor_id(); - unsigned int gasid; - - /* - * Lazy host ASID regeneration for guest user mode. - * If the guest ASID has changed since the last guest usermode - * execution, regenerate the host ASID so as to invalidate stale TLB - * entries. - */ - if (!KVM_GUEST_KERNEL_MODE(vcpu)) { - gasid = kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID; - if (gasid != vcpu->arch.last_user_gasid) { - kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, - vcpu); - vcpu->arch.guest_user_asid[cpu] = - vcpu->arch.guest_user_mm.context.asid[cpu]; - for_each_possible_cpu(i) - if (i != cpu) - vcpu->arch.guest_user_asid[cpu] = 0; - vcpu->arch.last_user_gasid = gasid; - } - } -} - int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) { - int r = 0; + int r = -EINTR; sigset_t sigsaved; if (vcpu->sigset_active) @@ -464,31 +409,30 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu->mmio_needed = 0; } + if (run->immediate_exit) + goto out; + lose_fpu(1); local_irq_disable(); - /* Check if we have any exceptions/interrupts pending */ - kvm_mips_deliver_interrupts(vcpu, - kvm_read_c0_guest_cause(vcpu->arch.cop0)); - guest_enter_irqoff(); - - /* Disable hardware page table walking while in guest */ - htw_stop(); - trace_kvm_enter(vcpu); - kvm_mips_check_asids(vcpu); - - r = vcpu->arch.vcpu_run(run, vcpu); - trace_kvm_out(vcpu); + /* + * Make sure the read of VCPU requests in vcpu_run() callback is not + * reordered ahead of the write to vcpu->mode, or we could miss a TLB + * flush request while the requester sees the VCPU as outside of guest + * mode and not needing an IPI. + */ + smp_store_mb(vcpu->mode, IN_GUEST_MODE); - /* Re-enable HTW before enabling interrupts */ - htw_start(); + r = kvm_mips_callbacks->vcpu_run(run, vcpu); + trace_kvm_out(vcpu); guest_exit_irqoff(); local_irq_enable(); +out: if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); @@ -580,33 +524,6 @@ static u64 kvm_mips_get_one_regs[] = { KVM_REG_MIPS_LO, #endif KVM_REG_MIPS_PC, - - KVM_REG_MIPS_CP0_INDEX, - KVM_REG_MIPS_CP0_CONTEXT, - KVM_REG_MIPS_CP0_USERLOCAL, - KVM_REG_MIPS_CP0_PAGEMASK, - KVM_REG_MIPS_CP0_WIRED, - KVM_REG_MIPS_CP0_HWRENA, - KVM_REG_MIPS_CP0_BADVADDR, - KVM_REG_MIPS_CP0_COUNT, - KVM_REG_MIPS_CP0_ENTRYHI, - KVM_REG_MIPS_CP0_COMPARE, - KVM_REG_MIPS_CP0_STATUS, - KVM_REG_MIPS_CP0_CAUSE, - KVM_REG_MIPS_CP0_EPC, - KVM_REG_MIPS_CP0_PRID, - KVM_REG_MIPS_CP0_CONFIG, - KVM_REG_MIPS_CP0_CONFIG1, - KVM_REG_MIPS_CP0_CONFIG2, - KVM_REG_MIPS_CP0_CONFIG3, - KVM_REG_MIPS_CP0_CONFIG4, - KVM_REG_MIPS_CP0_CONFIG5, - KVM_REG_MIPS_CP0_CONFIG7, - KVM_REG_MIPS_CP0_ERROREPC, - - KVM_REG_MIPS_COUNT_CTL, - KVM_REG_MIPS_COUNT_RESUME, - KVM_REG_MIPS_COUNT_HZ, }; static u64 kvm_mips_get_one_regs_fpu[] = { @@ -619,15 +536,6 @@ static u64 kvm_mips_get_one_regs_msa[] = { KVM_REG_MIPS_MSA_CSR, }; -static u64 kvm_mips_get_one_regs_kscratch[] = { - KVM_REG_MIPS_CP0_KSCRATCH1, - KVM_REG_MIPS_CP0_KSCRATCH2, - KVM_REG_MIPS_CP0_KSCRATCH3, - KVM_REG_MIPS_CP0_KSCRATCH4, - KVM_REG_MIPS_CP0_KSCRATCH5, - KVM_REG_MIPS_CP0_KSCRATCH6, -}; - static unsigned long kvm_mips_num_regs(struct kvm_vcpu *vcpu) { unsigned long ret; @@ -641,7 +549,6 @@ static unsigned long kvm_mips_num_regs(struct kvm_vcpu *vcpu) } if (kvm_mips_guest_can_have_msa(&vcpu->arch)) ret += ARRAY_SIZE(kvm_mips_get_one_regs_msa) + 32; - ret += __arch_hweight8(vcpu->arch.kscratch_enabled); ret += kvm_mips_callbacks->num_regs(vcpu); return ret; @@ -694,16 +601,6 @@ static int kvm_mips_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices) } } - for (i = 0; i < 6; ++i) { - if (!(vcpu->arch.kscratch_enabled & BIT(i + 2))) - continue; - - if (copy_to_user(indices, &kvm_mips_get_one_regs_kscratch[i], - sizeof(kvm_mips_get_one_regs_kscratch[i]))) - return -EFAULT; - ++indices; - } - return kvm_mips_callbacks->copy_reg_indices(vcpu, indices); } @@ -794,95 +691,6 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, v = fpu->msacsr; break; - /* Co-processor 0 registers */ - case KVM_REG_MIPS_CP0_INDEX: - v = (long)kvm_read_c0_guest_index(cop0); - break; - case KVM_REG_MIPS_CP0_CONTEXT: - v = (long)kvm_read_c0_guest_context(cop0); - break; - case KVM_REG_MIPS_CP0_USERLOCAL: - v = (long)kvm_read_c0_guest_userlocal(cop0); - break; - case KVM_REG_MIPS_CP0_PAGEMASK: - v = (long)kvm_read_c0_guest_pagemask(cop0); - break; - case KVM_REG_MIPS_CP0_WIRED: - v = (long)kvm_read_c0_guest_wired(cop0); - break; - case KVM_REG_MIPS_CP0_HWRENA: - v = (long)kvm_read_c0_guest_hwrena(cop0); - break; - case KVM_REG_MIPS_CP0_BADVADDR: - v = (long)kvm_read_c0_guest_badvaddr(cop0); - break; - case KVM_REG_MIPS_CP0_ENTRYHI: - v = (long)kvm_read_c0_guest_entryhi(cop0); - break; - case KVM_REG_MIPS_CP0_COMPARE: - v = (long)kvm_read_c0_guest_compare(cop0); - break; - case KVM_REG_MIPS_CP0_STATUS: - v = (long)kvm_read_c0_guest_status(cop0); - break; - case KVM_REG_MIPS_CP0_CAUSE: - v = (long)kvm_read_c0_guest_cause(cop0); - break; - case KVM_REG_MIPS_CP0_EPC: - v = (long)kvm_read_c0_guest_epc(cop0); - break; - case KVM_REG_MIPS_CP0_PRID: - v = (long)kvm_read_c0_guest_prid(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG: - v = (long)kvm_read_c0_guest_config(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG1: - v = (long)kvm_read_c0_guest_config1(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG2: - v = (long)kvm_read_c0_guest_config2(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG3: - v = (long)kvm_read_c0_guest_config3(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG4: - v = (long)kvm_read_c0_guest_config4(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG5: - v = (long)kvm_read_c0_guest_config5(cop0); - break; - case KVM_REG_MIPS_CP0_CONFIG7: - v = (long)kvm_read_c0_guest_config7(cop0); - break; - case KVM_REG_MIPS_CP0_ERROREPC: - v = (long)kvm_read_c0_guest_errorepc(cop0); - break; - case KVM_REG_MIPS_CP0_KSCRATCH1 ... KVM_REG_MIPS_CP0_KSCRATCH6: - idx = reg->id - KVM_REG_MIPS_CP0_KSCRATCH1 + 2; - if (!(vcpu->arch.kscratch_enabled & BIT(idx))) - return -EINVAL; - switch (idx) { - case 2: - v = (long)kvm_read_c0_guest_kscratch1(cop0); - break; - case 3: - v = (long)kvm_read_c0_guest_kscratch2(cop0); - break; - case 4: - v = (long)kvm_read_c0_guest_kscratch3(cop0); - break; - case 5: - v = (long)kvm_read_c0_guest_kscratch4(cop0); - break; - case 6: - v = (long)kvm_read_c0_guest_kscratch5(cop0); - break; - case 7: - v = (long)kvm_read_c0_guest_kscratch6(cop0); - break; - } - break; /* registers to be handled specially */ default: ret = kvm_mips_callbacks->get_one_reg(vcpu, reg, &v); @@ -1014,68 +822,6 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, fpu->msacsr = v; break; - /* Co-processor 0 registers */ - case KVM_REG_MIPS_CP0_INDEX: - kvm_write_c0_guest_index(cop0, v); - break; - case KVM_REG_MIPS_CP0_CONTEXT: - kvm_write_c0_guest_context(cop0, v); - break; - case KVM_REG_MIPS_CP0_USERLOCAL: - kvm_write_c0_guest_userlocal(cop0, v); - break; - case KVM_REG_MIPS_CP0_PAGEMASK: - kvm_write_c0_guest_pagemask(cop0, v); - break; - case KVM_REG_MIPS_CP0_WIRED: - kvm_write_c0_guest_wired(cop0, v); - break; - case KVM_REG_MIPS_CP0_HWRENA: - kvm_write_c0_guest_hwrena(cop0, v); - break; - case KVM_REG_MIPS_CP0_BADVADDR: - kvm_write_c0_guest_badvaddr(cop0, v); - break; - case KVM_REG_MIPS_CP0_ENTRYHI: - kvm_write_c0_guest_entryhi(cop0, v); - break; - case KVM_REG_MIPS_CP0_STATUS: - kvm_write_c0_guest_status(cop0, v); - break; - case KVM_REG_MIPS_CP0_EPC: - kvm_write_c0_guest_epc(cop0, v); - break; - case KVM_REG_MIPS_CP0_PRID: - kvm_write_c0_guest_prid(cop0, v); - break; - case KVM_REG_MIPS_CP0_ERROREPC: - kvm_write_c0_guest_errorepc(cop0, v); - break; - case KVM_REG_MIPS_CP0_KSCRATCH1 ... KVM_REG_MIPS_CP0_KSCRATCH6: - idx = reg->id - KVM_REG_MIPS_CP0_KSCRATCH1 + 2; - if (!(vcpu->arch.kscratch_enabled & BIT(idx))) - return -EINVAL; - switch (idx) { - case 2: - kvm_write_c0_guest_kscratch1(cop0, v); - break; - case 3: - kvm_write_c0_guest_kscratch2(cop0, v); - break; - case 4: - kvm_write_c0_guest_kscratch3(cop0, v); - break; - case 5: - kvm_write_c0_guest_kscratch4(cop0, v); - break; - case 6: - kvm_write_c0_guest_kscratch5(cop0, v); - break; - case 7: - kvm_write_c0_guest_kscratch6(cop0, v); - break; - } - break; /* registers to be handled specially */ default: return kvm_mips_callbacks->set_one_reg(vcpu, reg, v); @@ -1144,18 +890,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, return -E2BIG; return kvm_mips_copy_reg_indices(vcpu, user_list->reg); } - case KVM_NMI: - /* Treat the NMI as a CPU reset */ - r = kvm_mips_reset_vcpu(vcpu); - break; case KVM_INTERRUPT: { struct kvm_mips_interrupt irq; - r = -EFAULT; if (copy_from_user(&irq, argp, sizeof(irq))) - goto out; - + return -EFAULT; kvm_debug("[%d] %s: irq: %d\n", vcpu->vcpu_id, __func__, irq.irq); @@ -1165,56 +905,57 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; - r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) - goto out; + return -EFAULT; r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } default: r = -ENOIOCTLCMD; } - -out: return r; } -/* Get (and clear) the dirty memory log for a memory slot. */ +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * Steps 1-4 below provide general overview of dirty page logging. See + * kvm_get_dirty_log_protect() function description for additional details. + * + * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we + * always flush the TLB (step 4) even if previous step failed and the dirty + * bitmap may be corrupt. Regardless of previous outcome the KVM logging API + * does not preclude user space subsequent dirty log read. Flushing TLB ensures + * writes will be marked dirty for next log read. + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Copy the snapshot to the userspace. + * 4. Flush TLB's if needed. + */ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - unsigned long ga, ga_end; - int is_dirty = 0; + bool is_dirty = false; int r; - unsigned long n; mutex_lock(&kvm->slots_lock); - r = kvm_get_dirty_log(kvm, log, &is_dirty); - if (r) - goto out; + r = kvm_get_dirty_log_protect(kvm, log, &is_dirty); - /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, log->slot); - ga = memslot->base_gfn << PAGE_SHIFT; - ga_end = ga + (memslot->npages << PAGE_SHIFT); - - kvm_info("%s: dirty, ga: %#lx, ga_end %#lx\n", __func__, ga, - ga_end); - - n = kvm_dirty_bitmap_bytes(memslot); - memset(memslot->dirty_bitmap, 0, n); + /* Let implementation handle TLB/GVA invalidation */ + kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); } - r = 0; -out: mutex_unlock(&kvm->slots_lock); return r; - } long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) @@ -1282,11 +1023,20 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) switch (ext) { case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: + case KVM_CAP_READONLY_MEM: + case KVM_CAP_SYNC_MMU: + case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; + case KVM_CAP_NR_VCPUS: + r = num_online_cpus(); + break; + case KVM_CAP_MAX_VCPUS: + r = KVM_MAX_VCPUS; + break; case KVM_CAP_MIPS_FPU: /* We don't handle systems with inconsistent cpu_has_fpu */ r = !!raw_cpu_has_fpu; @@ -1400,13 +1150,23 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer) int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { - kvm_mips_callbacks->vcpu_init(vcpu); + int err; + + err = kvm_mips_callbacks->vcpu_init(vcpu); + if (err) + return err; + hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup; return 0; } +void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + kvm_mips_callbacks->vcpu_uninit(vcpu); +} + int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { @@ -1440,8 +1200,11 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) u32 __user *opc = (u32 __user *) vcpu->arch.pc; unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr; enum emulation_result er = EMULATE_DONE; + u32 inst; int ret = RESUME_GUEST; + vcpu->mode = OUTSIDE_GUEST_MODE; + /* re-enable HTW before enabling interrupts */ htw_start(); @@ -1564,8 +1327,12 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) break; default: + if (cause & CAUSEF_BD) + opc += 1; + inst = 0; + kvm_get_badinstr(opc, vcpu, &inst); kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#lx\n", - exccode, opc, kvm_get_inst(opc, vcpu), badvaddr, + exccode, opc, inst, badvaddr, kvm_read_c0_guest_status(vcpu->arch.cop0)); kvm_arch_vcpu_dump_regs(vcpu); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; @@ -1593,7 +1360,15 @@ skip_emul: if (ret == RESUME_GUEST) { trace_kvm_reenter(vcpu); - kvm_mips_check_asids(vcpu); + /* + * Make sure the read of VCPU requests in vcpu_reenter() + * callback is not reordered ahead of the write to vcpu->mode, + * or we could miss a TLB flush request while the requester sees + * the VCPU as outside of guest mode and not needing an IPI. + */ + smp_store_mb(vcpu->mode, IN_GUEST_MODE); + + kvm_mips_callbacks->vcpu_reenter(run, vcpu); /* * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 3b677c8..cb0faad 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -11,86 +11,995 @@ #include <linux/highmem.h> #include <linux/kvm_host.h> +#include <linux/uaccess.h> #include <asm/mmu_context.h> +#include <asm/pgalloc.h> -static u32 kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu) +/* + * KVM_MMU_CACHE_MIN_PAGES is the number of GPA page table translation levels + * for which pages need to be cached. + */ +#if defined(__PAGETABLE_PMD_FOLDED) +#define KVM_MMU_CACHE_MIN_PAGES 1 +#else +#define KVM_MMU_CACHE_MIN_PAGES 2 +#endif + +static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, + int min, int max) { - int cpu = smp_processor_id(); + void *page; + + BUG_ON(max > KVM_NR_MEM_OBJS); + if (cache->nobjs >= min) + return 0; + while (cache->nobjs < max) { + page = (void *)__get_free_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + cache->objects[cache->nobjs++] = page; + } + return 0; +} - return vcpu->arch.guest_kernel_asid[cpu] & - cpu_asid_mask(&cpu_data[cpu]); +static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) + free_page((unsigned long)mc->objects[--mc->nobjs]); } -static u32 kvm_mips_get_user_asid(struct kvm_vcpu *vcpu) +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { - int cpu = smp_processor_id(); + void *p; - return vcpu->arch.guest_user_asid[cpu] & - cpu_asid_mask(&cpu_data[cpu]); + BUG_ON(!mc || !mc->nobjs); + p = mc->objects[--mc->nobjs]; + return p; } -static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) +void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) { - int srcu_idx, err = 0; - kvm_pfn_t pfn; + mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); +} + +/** + * kvm_pgd_init() - Initialise KVM GPA page directory. + * @page: Pointer to page directory (PGD) for KVM GPA. + * + * Initialise a KVM GPA page directory with pointers to the invalid table, i.e. + * representing no mappings. This is similar to pgd_init(), however it + * initialises all the page directory pointers, not just the ones corresponding + * to the userland address space (since it is for the guest physical address + * space rather than a virtual address space). + */ +static void kvm_pgd_init(void *page) +{ + unsigned long *p, *end; + unsigned long entry; + +#ifdef __PAGETABLE_PMD_FOLDED + entry = (unsigned long)invalid_pte_table; +#else + entry = (unsigned long)invalid_pmd_table; +#endif + + p = (unsigned long *)page; + end = p + PTRS_PER_PGD; + + do { + p[0] = entry; + p[1] = entry; + p[2] = entry; + p[3] = entry; + p[4] = entry; + p += 8; + p[-3] = entry; + p[-2] = entry; + p[-1] = entry; + } while (p != end); +} + +/** + * kvm_pgd_alloc() - Allocate and initialise a KVM GPA page directory. + * + * Allocate a blank KVM GPA page directory (PGD) for representing guest physical + * to host physical page mappings. + * + * Returns: Pointer to new KVM GPA page directory. + * NULL on allocation failure. + */ +pgd_t *kvm_pgd_alloc(void) +{ + pgd_t *ret; + + ret = (pgd_t *)__get_free_pages(GFP_KERNEL, PGD_ORDER); + if (ret) + kvm_pgd_init(ret); + + return ret; +} + +/** + * kvm_mips_walk_pgd() - Walk page table with optional allocation. + * @pgd: Page directory pointer. + * @addr: Address to index page table using. + * @cache: MMU page cache to allocate new page tables from, or NULL. + * + * Walk the page tables pointed to by @pgd to find the PTE corresponding to the + * address @addr. If page tables don't exist for @addr, they will be created + * from the MMU cache if @cache is not NULL. + * + * Returns: Pointer to pte_t corresponding to @addr. + * NULL if a page table doesn't exist for @addr and !@cache. + * NULL if a page table allocation failed. + */ +static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache, + unsigned long addr) +{ + pud_t *pud; + pmd_t *pmd; + + pgd += pgd_index(addr); + if (pgd_none(*pgd)) { + /* Not used on MIPS yet */ + BUG(); + return NULL; + } + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) { + pmd_t *new_pmd; + + if (!cache) + return NULL; + new_pmd = mmu_memory_cache_alloc(cache); + pmd_init((unsigned long)new_pmd, + (unsigned long)invalid_pte_table); + pud_populate(NULL, pud, new_pmd); + } + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + pte_t *new_pte; + + if (!cache) + return NULL; + new_pte = mmu_memory_cache_alloc(cache); + clear_page(new_pte); + pmd_populate_kernel(NULL, pmd, new_pte); + } + return pte_offset(pmd, addr); +} + +/* Caller must hold kvm->mm_lock */ +static pte_t *kvm_mips_pte_for_gpa(struct kvm *kvm, + struct kvm_mmu_memory_cache *cache, + unsigned long addr) +{ + return kvm_mips_walk_pgd(kvm->arch.gpa_mm.pgd, cache, addr); +} + +/* + * kvm_mips_flush_gpa_{pte,pmd,pud,pgd,pt}. + * Flush a range of guest physical address space from the VM's GPA page tables. + */ + +static bool kvm_mips_flush_gpa_pte(pte_t *pte, unsigned long start_gpa, + unsigned long end_gpa) +{ + int i_min = __pte_offset(start_gpa); + int i_max = __pte_offset(end_gpa); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PTE - 1); + int i; + + for (i = i_min; i <= i_max; ++i) { + if (!pte_present(pte[i])) + continue; + + set_pte(pte + i, __pte(0)); + } + return safe_to_remove; +} + +static bool kvm_mips_flush_gpa_pmd(pmd_t *pmd, unsigned long start_gpa, + unsigned long end_gpa) +{ + pte_t *pte; + unsigned long end = ~0ul; + int i_min = __pmd_offset(start_gpa); + int i_max = __pmd_offset(end_gpa); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1); + int i; + + for (i = i_min; i <= i_max; ++i, start_gpa = 0) { + if (!pmd_present(pmd[i])) + continue; + + pte = pte_offset(pmd + i, 0); + if (i == i_max) + end = end_gpa; + + if (kvm_mips_flush_gpa_pte(pte, start_gpa, end)) { + pmd_clear(pmd + i); + pte_free_kernel(NULL, pte); + } else { + safe_to_remove = false; + } + } + return safe_to_remove; +} + +static bool kvm_mips_flush_gpa_pud(pud_t *pud, unsigned long start_gpa, + unsigned long end_gpa) +{ + pmd_t *pmd; + unsigned long end = ~0ul; + int i_min = __pud_offset(start_gpa); + int i_max = __pud_offset(end_gpa); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1); + int i; + + for (i = i_min; i <= i_max; ++i, start_gpa = 0) { + if (!pud_present(pud[i])) + continue; + + pmd = pmd_offset(pud + i, 0); + if (i == i_max) + end = end_gpa; + + if (kvm_mips_flush_gpa_pmd(pmd, start_gpa, end)) { + pud_clear(pud + i); + pmd_free(NULL, pmd); + } else { + safe_to_remove = false; + } + } + return safe_to_remove; +} + +static bool kvm_mips_flush_gpa_pgd(pgd_t *pgd, unsigned long start_gpa, + unsigned long end_gpa) +{ + pud_t *pud; + unsigned long end = ~0ul; + int i_min = pgd_index(start_gpa); + int i_max = pgd_index(end_gpa); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PGD - 1); + int i; + + for (i = i_min; i <= i_max; ++i, start_gpa = 0) { + if (!pgd_present(pgd[i])) + continue; + + pud = pud_offset(pgd + i, 0); + if (i == i_max) + end = end_gpa; + + if (kvm_mips_flush_gpa_pud(pud, start_gpa, end)) { + pgd_clear(pgd + i); + pud_free(NULL, pud); + } else { + safe_to_remove = false; + } + } + return safe_to_remove; +} + +/** + * kvm_mips_flush_gpa_pt() - Flush a range of guest physical addresses. + * @kvm: KVM pointer. + * @start_gfn: Guest frame number of first page in GPA range to flush. + * @end_gfn: Guest frame number of last page in GPA range to flush. + * + * Flushes a range of GPA mappings from the GPA page tables. + * + * The caller must hold the @kvm->mmu_lock spinlock. + * + * Returns: Whether its safe to remove the top level page directory because + * all lower levels have been removed. + */ +bool kvm_mips_flush_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn) +{ + return kvm_mips_flush_gpa_pgd(kvm->arch.gpa_mm.pgd, + start_gfn << PAGE_SHIFT, + end_gfn << PAGE_SHIFT); +} + +#define BUILD_PTE_RANGE_OP(name, op) \ +static int kvm_mips_##name##_pte(pte_t *pte, unsigned long start, \ + unsigned long end) \ +{ \ + int ret = 0; \ + int i_min = __pte_offset(start); \ + int i_max = __pte_offset(end); \ + int i; \ + pte_t old, new; \ + \ + for (i = i_min; i <= i_max; ++i) { \ + if (!pte_present(pte[i])) \ + continue; \ + \ + old = pte[i]; \ + new = op(old); \ + if (pte_val(new) == pte_val(old)) \ + continue; \ + set_pte(pte + i, new); \ + ret = 1; \ + } \ + return ret; \ +} \ + \ +/* returns true if anything was done */ \ +static int kvm_mips_##name##_pmd(pmd_t *pmd, unsigned long start, \ + unsigned long end) \ +{ \ + int ret = 0; \ + pte_t *pte; \ + unsigned long cur_end = ~0ul; \ + int i_min = __pmd_offset(start); \ + int i_max = __pmd_offset(end); \ + int i; \ + \ + for (i = i_min; i <= i_max; ++i, start = 0) { \ + if (!pmd_present(pmd[i])) \ + continue; \ + \ + pte = pte_offset(pmd + i, 0); \ + if (i == i_max) \ + cur_end = end; \ + \ + ret |= kvm_mips_##name##_pte(pte, start, cur_end); \ + } \ + return ret; \ +} \ + \ +static int kvm_mips_##name##_pud(pud_t *pud, unsigned long start, \ + unsigned long end) \ +{ \ + int ret = 0; \ + pmd_t *pmd; \ + unsigned long cur_end = ~0ul; \ + int i_min = __pud_offset(start); \ + int i_max = __pud_offset(end); \ + int i; \ + \ + for (i = i_min; i <= i_max; ++i, start = 0) { \ + if (!pud_present(pud[i])) \ + continue; \ + \ + pmd = pmd_offset(pud + i, 0); \ + if (i == i_max) \ + cur_end = end; \ + \ + ret |= kvm_mips_##name##_pmd(pmd, start, cur_end); \ + } \ + return ret; \ +} \ + \ +static int kvm_mips_##name##_pgd(pgd_t *pgd, unsigned long start, \ + unsigned long end) \ +{ \ + int ret = 0; \ + pud_t *pud; \ + unsigned long cur_end = ~0ul; \ + int i_min = pgd_index(start); \ + int i_max = pgd_index(end); \ + int i; \ + \ + for (i = i_min; i <= i_max; ++i, start = 0) { \ + if (!pgd_present(pgd[i])) \ + continue; \ + \ + pud = pud_offset(pgd + i, 0); \ + if (i == i_max) \ + cur_end = end; \ + \ + ret |= kvm_mips_##name##_pud(pud, start, cur_end); \ + } \ + return ret; \ +} + +/* + * kvm_mips_mkclean_gpa_pt. + * Mark a range of guest physical address space clean (writes fault) in the VM's + * GPA page table to allow dirty page tracking. + */ - if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE) +BUILD_PTE_RANGE_OP(mkclean, pte_mkclean) + +/** + * kvm_mips_mkclean_gpa_pt() - Make a range of guest physical addresses clean. + * @kvm: KVM pointer. + * @start_gfn: Guest frame number of first page in GPA range to flush. + * @end_gfn: Guest frame number of last page in GPA range to flush. + * + * Make a range of GPA mappings clean so that guest writes will fault and + * trigger dirty page logging. + * + * The caller must hold the @kvm->mmu_lock spinlock. + * + * Returns: Whether any GPA mappings were modified, which would require + * derived mappings (GVA page tables & TLB enties) to be + * invalidated. + */ +int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn) +{ + return kvm_mips_mkclean_pgd(kvm->arch.gpa_mm.pgd, + start_gfn << PAGE_SHIFT, + end_gfn << PAGE_SHIFT); +} + +/** + * kvm_arch_mmu_enable_log_dirty_pt_masked() - write protect dirty pages + * @kvm: The KVM pointer + * @slot: The memory slot associated with mask + * @gfn_offset: The gfn offset in memory slot + * @mask: The mask of dirty pages at offset 'gfn_offset' in this memory + * slot to be write protected + * + * Walks bits set in mask write protects the associated pte's. Caller must + * acquire @kvm->mmu_lock. + */ +void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) +{ + gfn_t base_gfn = slot->base_gfn + gfn_offset; + gfn_t start = base_gfn + __ffs(mask); + gfn_t end = base_gfn + __fls(mask); + + kvm_mips_mkclean_gpa_pt(kvm, start, end); +} + +/* + * kvm_mips_mkold_gpa_pt. + * Mark a range of guest physical address space old (all accesses fault) in the + * VM's GPA page table to allow detection of commonly used pages. + */ + +BUILD_PTE_RANGE_OP(mkold, pte_mkold) + +static int kvm_mips_mkold_gpa_pt(struct kvm *kvm, gfn_t start_gfn, + gfn_t end_gfn) +{ + return kvm_mips_mkold_pgd(kvm->arch.gpa_mm.pgd, + start_gfn << PAGE_SHIFT, + end_gfn << PAGE_SHIFT); +} + +static int handle_hva_to_gpa(struct kvm *kvm, + unsigned long start, + unsigned long end, + int (*handler)(struct kvm *kvm, gfn_t gfn, + gpa_t gfn_end, + struct kvm_memory_slot *memslot, + void *data), + void *data) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int ret = 0; + + slots = kvm_memslots(kvm); + + /* we only care about the pages that the guest sees */ + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn, gfn_end; + + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; + + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. + */ + gfn = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); + + ret |= handler(kvm, gfn, gfn_end, memslot, data); + } + + return ret; +} + + +static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, + struct kvm_memory_slot *memslot, void *data) +{ + kvm_mips_flush_gpa_pt(kvm, gfn, gfn_end); + return 1; +} + +int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) +{ + unsigned long end = hva + PAGE_SIZE; + + handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); + + kvm_mips_callbacks->flush_shadow_all(kvm); + return 0; +} + +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + + kvm_mips_callbacks->flush_shadow_all(kvm); + return 0; +} + +static int kvm_set_spte_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, + struct kvm_memory_slot *memslot, void *data) +{ + gpa_t gpa = gfn << PAGE_SHIFT; + pte_t hva_pte = *(pte_t *)data; + pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa); + pte_t old_pte; + + if (!gpa_pte) + return 0; + + /* Mapping may need adjusting depending on memslot flags */ + old_pte = *gpa_pte; + if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES && !pte_dirty(old_pte)) + hva_pte = pte_mkclean(hva_pte); + else if (memslot->flags & KVM_MEM_READONLY) + hva_pte = pte_wrprotect(hva_pte); + + set_pte(gpa_pte, hva_pte); + + /* Replacing an absent or old page doesn't need flushes */ + if (!pte_present(old_pte) || !pte_young(old_pte)) return 0; + /* Pages swapped, aged, moved, or cleaned require flushes */ + return !pte_present(hva_pte) || + !pte_young(hva_pte) || + pte_pfn(old_pte) != pte_pfn(hva_pte) || + (pte_dirty(old_pte) && !pte_dirty(hva_pte)); +} + +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +{ + unsigned long end = hva + PAGE_SIZE; + int ret; + + ret = handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &pte); + if (ret) + kvm_mips_callbacks->flush_shadow_all(kvm); +} + +static int kvm_age_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, + struct kvm_memory_slot *memslot, void *data) +{ + return kvm_mips_mkold_gpa_pt(kvm, gfn, gfn_end); +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, + struct kvm_memory_slot *memslot, void *data) +{ + gpa_t gpa = gfn << PAGE_SHIFT; + pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa); + + if (!gpa_pte) + return 0; + return pte_young(*gpa_pte); +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long 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) +{ + return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); +} + +/** + * _kvm_mips_map_page_fast() - Fast path GPA fault handler. + * @vcpu: VCPU pointer. + * @gpa: Guest physical address of fault. + * @write_fault: Whether the fault was due to a write. + * @out_entry: New PTE for @gpa (written on success unless NULL). + * @out_buddy: New PTE for @gpa's buddy (written on success unless + * NULL). + * + * Perform fast path GPA fault handling, doing all that can be done without + * calling into KVM. This handles marking old pages young (for idle page + * tracking), and dirtying of clean pages (for dirty page logging). + * + * Returns: 0 on success, in which case we can update derived mappings and + * resume guest execution. + * -EFAULT on failure due to absent GPA mapping or write to + * read-only page, in which case KVM must be consulted. + */ +static int _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, + bool write_fault, + pte_t *out_entry, pte_t *out_buddy) +{ + struct kvm *kvm = vcpu->kvm; + gfn_t gfn = gpa >> PAGE_SHIFT; + pte_t *ptep; + kvm_pfn_t pfn = 0; /* silence bogus GCC warning */ + bool pfn_valid = false; + int ret = 0; + + spin_lock(&kvm->mmu_lock); + + /* Fast path - just check GPA page table for an existing entry */ + ptep = kvm_mips_pte_for_gpa(kvm, NULL, gpa); + if (!ptep || !pte_present(*ptep)) { + ret = -EFAULT; + goto out; + } + + /* Track access to pages marked old */ + if (!pte_young(*ptep)) { + set_pte(ptep, pte_mkyoung(*ptep)); + pfn = pte_pfn(*ptep); + pfn_valid = true; + /* call kvm_set_pfn_accessed() after unlock */ + } + if (write_fault && !pte_dirty(*ptep)) { + if (!pte_write(*ptep)) { + ret = -EFAULT; + goto out; + } + + /* Track dirtying of writeable pages */ + set_pte(ptep, pte_mkdirty(*ptep)); + pfn = pte_pfn(*ptep); + mark_page_dirty(kvm, gfn); + kvm_set_pfn_dirty(pfn); + } + + if (out_entry) + *out_entry = *ptep; + if (out_buddy) + *out_buddy = *ptep_buddy(ptep); + +out: + spin_unlock(&kvm->mmu_lock); + if (pfn_valid) + kvm_set_pfn_accessed(pfn); + return ret; +} + +/** + * kvm_mips_map_page() - Map a guest physical page. + * @vcpu: VCPU pointer. + * @gpa: Guest physical address of fault. + * @write_fault: Whether the fault was due to a write. + * @out_entry: New PTE for @gpa (written on success unless NULL). + * @out_buddy: New PTE for @gpa's buddy (written on success unless + * NULL). + * + * Handle GPA faults by creating a new GPA mapping (or updating an existing + * one). + * + * This takes care of marking pages young or dirty (idle/dirty page tracking), + * asking KVM for the corresponding PFN, and creating a mapping in the GPA page + * tables. Derived mappings (GVA page tables and TLBs) must be handled by the + * caller. + * + * Returns: 0 on success, in which case the caller may use the @out_entry + * and @out_buddy PTEs to update derived mappings and resume guest + * execution. + * -EFAULT if there is no memory region at @gpa or a write was + * attempted to a read-only memory region. This is usually handled + * as an MMIO access. + */ +static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa, + bool write_fault, + pte_t *out_entry, pte_t *out_buddy) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; + gfn_t gfn = gpa >> PAGE_SHIFT; + int srcu_idx, err; + kvm_pfn_t pfn; + pte_t *ptep, entry, old_pte; + bool writeable; + unsigned long prot_bits; + unsigned long mmu_seq; + + /* Try the fast path to handle old / clean pages */ srcu_idx = srcu_read_lock(&kvm->srcu); - pfn = gfn_to_pfn(kvm, gfn); + err = _kvm_mips_map_page_fast(vcpu, gpa, write_fault, out_entry, + out_buddy); + if (!err) + goto out; + /* We need a minimum of cached pages ready for page table creation */ + err = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES, + KVM_NR_MEM_OBJS); + if (err) + goto out; + +retry: + /* + * Used to check for invalidations in progress, of the pfn that is + * returned by pfn_to_pfn_prot below. + */ + mmu_seq = kvm->mmu_notifier_seq; + /* + * Ensure the read of mmu_notifier_seq isn't reordered with PTE reads in + * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't + * risk the page we get a reference to getting unmapped before we have a + * chance to grab the mmu_lock without mmu_notifier_retry() noticing. + * + * This smp_rmb() pairs with the effective smp_wmb() of the combination + * of the pte_unmap_unlock() after the PTE is zapped, and the + * spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before + * mmu_notifier_seq is incremented. + */ + smp_rmb(); + + /* Slow path - ask KVM core whether we can access this GPA */ + pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writeable); if (is_error_noslot_pfn(pfn)) { - kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn); err = -EFAULT; goto out; } - kvm->arch.guest_pmap[gfn] = pfn; + spin_lock(&kvm->mmu_lock); + /* Check if an invalidation has taken place since we got pfn */ + if (mmu_notifier_retry(kvm, mmu_seq)) { + /* + * This can happen when mappings are changed asynchronously, but + * also synchronously if a COW is triggered by + * gfn_to_pfn_prot(). + */ + spin_unlock(&kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + goto retry; + } + + /* Ensure page tables are allocated */ + ptep = kvm_mips_pte_for_gpa(kvm, memcache, gpa); + + /* Set up the PTE */ + prot_bits = _PAGE_PRESENT | __READABLE | _page_cachable_default; + if (writeable) { + prot_bits |= _PAGE_WRITE; + if (write_fault) { + prot_bits |= __WRITEABLE; + mark_page_dirty(kvm, gfn); + kvm_set_pfn_dirty(pfn); + } + } + entry = pfn_pte(pfn, __pgprot(prot_bits)); + + /* Write the PTE */ + old_pte = *ptep; + set_pte(ptep, entry); + + err = 0; + if (out_entry) + *out_entry = *ptep; + if (out_buddy) + *out_buddy = *ptep_buddy(ptep); + + spin_unlock(&kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + kvm_set_pfn_accessed(pfn); out: srcu_read_unlock(&kvm->srcu, srcu_idx); return err; } -/* Translate guest KSEG0 addresses to Host PA */ -unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu, - unsigned long gva) +static pte_t *kvm_trap_emul_pte_for_gva(struct kvm_vcpu *vcpu, + unsigned long addr) { - gfn_t gfn; - unsigned long offset = gva & ~PAGE_MASK; - struct kvm *kvm = vcpu->kvm; + struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; + pgd_t *pgdp; + int ret; + + /* We need a minimum of cached pages ready for page table creation */ + ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES, + KVM_NR_MEM_OBJS); + if (ret) + return NULL; + + if (KVM_GUEST_KERNEL_MODE(vcpu)) + pgdp = vcpu->arch.guest_kernel_mm.pgd; + else + pgdp = vcpu->arch.guest_user_mm.pgd; + + return kvm_mips_walk_pgd(pgdp, memcache, addr); +} - if (KVM_GUEST_KSEGX(gva) != KVM_GUEST_KSEG0) { - kvm_err("%s/%p: Invalid gva: %#lx\n", __func__, - __builtin_return_address(0), gva); - return KVM_INVALID_PAGE; +void kvm_trap_emul_invalidate_gva(struct kvm_vcpu *vcpu, unsigned long addr, + bool user) +{ + pgd_t *pgdp; + pte_t *ptep; + + addr &= PAGE_MASK << 1; + + pgdp = vcpu->arch.guest_kernel_mm.pgd; + ptep = kvm_mips_walk_pgd(pgdp, NULL, addr); + if (ptep) { + ptep[0] = pfn_pte(0, __pgprot(0)); + ptep[1] = pfn_pte(0, __pgprot(0)); + } + + if (user) { + pgdp = vcpu->arch.guest_user_mm.pgd; + ptep = kvm_mips_walk_pgd(pgdp, NULL, addr); + if (ptep) { + ptep[0] = pfn_pte(0, __pgprot(0)); + ptep[1] = pfn_pte(0, __pgprot(0)); + } } +} - gfn = (KVM_GUEST_CPHYSADDR(gva) >> PAGE_SHIFT); +/* + * kvm_mips_flush_gva_{pte,pmd,pud,pgd,pt}. + * Flush a range of guest physical address space from the VM's GPA page tables. + */ - if (gfn >= kvm->arch.guest_pmap_npages) { - kvm_err("%s: Invalid gfn: %#llx, GVA: %#lx\n", __func__, gfn, - gva); - return KVM_INVALID_PAGE; +static bool kvm_mips_flush_gva_pte(pte_t *pte, unsigned long start_gva, + unsigned long end_gva) +{ + int i_min = __pte_offset(start_gva); + int i_max = __pte_offset(end_gva); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PTE - 1); + int i; + + /* + * There's no freeing to do, so there's no point clearing individual + * entries unless only part of the last level page table needs flushing. + */ + if (safe_to_remove) + return true; + + for (i = i_min; i <= i_max; ++i) { + if (!pte_present(pte[i])) + continue; + + set_pte(pte + i, __pte(0)); } + return false; +} - if (kvm_mips_map_page(vcpu->kvm, gfn) < 0) - return KVM_INVALID_ADDR; +static bool kvm_mips_flush_gva_pmd(pmd_t *pmd, unsigned long start_gva, + unsigned long end_gva) +{ + pte_t *pte; + unsigned long end = ~0ul; + int i_min = __pmd_offset(start_gva); + int i_max = __pmd_offset(end_gva); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1); + int i; + + for (i = i_min; i <= i_max; ++i, start_gva = 0) { + if (!pmd_present(pmd[i])) + continue; + + pte = pte_offset(pmd + i, 0); + if (i == i_max) + end = end_gva; + + if (kvm_mips_flush_gva_pte(pte, start_gva, end)) { + pmd_clear(pmd + i); + pte_free_kernel(NULL, pte); + } else { + safe_to_remove = false; + } + } + return safe_to_remove; +} - return (kvm->arch.guest_pmap[gfn] << PAGE_SHIFT) + offset; +static bool kvm_mips_flush_gva_pud(pud_t *pud, unsigned long start_gva, + unsigned long end_gva) +{ + pmd_t *pmd; + unsigned long end = ~0ul; + int i_min = __pud_offset(start_gva); + int i_max = __pud_offset(end_gva); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1); + int i; + + for (i = i_min; i <= i_max; ++i, start_gva = 0) { + if (!pud_present(pud[i])) + continue; + + pmd = pmd_offset(pud + i, 0); + if (i == i_max) + end = end_gva; + + if (kvm_mips_flush_gva_pmd(pmd, start_gva, end)) { + pud_clear(pud + i); + pmd_free(NULL, pmd); + } else { + safe_to_remove = false; + } + } + return safe_to_remove; +} + +static bool kvm_mips_flush_gva_pgd(pgd_t *pgd, unsigned long start_gva, + unsigned long end_gva) +{ + pud_t *pud; + unsigned long end = ~0ul; + int i_min = pgd_index(start_gva); + int i_max = pgd_index(end_gva); + bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PGD - 1); + int i; + + for (i = i_min; i <= i_max; ++i, start_gva = 0) { + if (!pgd_present(pgd[i])) + continue; + + pud = pud_offset(pgd + i, 0); + if (i == i_max) + end = end_gva; + + if (kvm_mips_flush_gva_pud(pud, start_gva, end)) { + pgd_clear(pgd + i); + pud_free(NULL, pud); + } else { + safe_to_remove = false; + } + } + return safe_to_remove; +} + +void kvm_mips_flush_gva_pt(pgd_t *pgd, enum kvm_mips_flush flags) +{ + if (flags & KMF_GPA) { + /* all of guest virtual address space could be affected */ + if (flags & KMF_KERN) + /* useg, kseg0, seg2/3 */ + kvm_mips_flush_gva_pgd(pgd, 0, 0x7fffffff); + else + /* useg */ + kvm_mips_flush_gva_pgd(pgd, 0, 0x3fffffff); + } else { + /* useg */ + kvm_mips_flush_gva_pgd(pgd, 0, 0x3fffffff); + + /* kseg2/3 */ + if (flags & KMF_KERN) + kvm_mips_flush_gva_pgd(pgd, 0x60000000, 0x7fffffff); + } +} + +static pte_t kvm_mips_gpa_pte_to_gva_unmapped(pte_t pte) +{ + /* + * Don't leak writeable but clean entries from GPA page tables. We don't + * want the normal Linux tlbmod handler to handle dirtying when KVM + * accesses guest memory. + */ + if (!pte_dirty(pte)) + pte = pte_wrprotect(pte); + + return pte; +} + +static pte_t kvm_mips_gpa_pte_to_gva_mapped(pte_t pte, long entrylo) +{ + /* Guest EntryLo overrides host EntryLo */ + if (!(entrylo & ENTRYLO_D)) + pte = pte_mkclean(pte); + + return kvm_mips_gpa_pte_to_gva_unmapped(pte); } /* XXXKYMA: Must be called with interrupts disabled */ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, + bool write_fault) { - gfn_t gfn; - kvm_pfn_t pfn0, pfn1; - unsigned long vaddr = 0; - unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; - struct kvm *kvm = vcpu->kvm; - const int flush_dcache_mask = 0; - int ret; + unsigned long gpa; + pte_t pte_gpa[2], *ptep_gva; + int idx; if (KVM_GUEST_KSEGX(badvaddr) != KVM_GUEST_KSEG0) { kvm_err("%s: Invalid BadVaddr: %#lx\n", __func__, badvaddr); @@ -98,49 +1007,39 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, return -1; } - gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT); - if ((gfn | 1) >= kvm->arch.guest_pmap_npages) { - kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__, - gfn, badvaddr); - kvm_mips_dump_host_tlbs(); + /* Get the GPA page table entry */ + gpa = KVM_GUEST_CPHYSADDR(badvaddr); + idx = (badvaddr >> PAGE_SHIFT) & 1; + if (kvm_mips_map_page(vcpu, gpa, write_fault, &pte_gpa[idx], + &pte_gpa[!idx]) < 0) return -1; - } - vaddr = badvaddr & (PAGE_MASK << 1); - if (kvm_mips_map_page(vcpu->kvm, gfn) < 0) + /* Get the GVA page table entry */ + ptep_gva = kvm_trap_emul_pte_for_gva(vcpu, badvaddr & ~PAGE_SIZE); + if (!ptep_gva) { + kvm_err("No ptep for gva %lx\n", badvaddr); return -1; + } - if (kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1) < 0) - return -1; - - pfn0 = kvm->arch.guest_pmap[gfn & ~0x1]; - pfn1 = kvm->arch.guest_pmap[gfn | 0x1]; - - entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | - ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - ENTRYLO_D | ENTRYLO_V; - entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | - ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - ENTRYLO_D | ENTRYLO_V; - - preempt_disable(); - entryhi = (vaddr | kvm_mips_get_kernel_asid(vcpu)); - ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1, - flush_dcache_mask); - preempt_enable(); + /* Copy a pair of entries from GPA page table to GVA page table */ + ptep_gva[0] = kvm_mips_gpa_pte_to_gva_unmapped(pte_gpa[0]); + ptep_gva[1] = kvm_mips_gpa_pte_to_gva_unmapped(pte_gpa[1]); - return ret; + /* Invalidate this entry in the TLB, guest kernel ASID only */ + kvm_mips_host_tlb_inv(vcpu, badvaddr, false, true); + return 0; } int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, - struct kvm_mips_tlb *tlb) + struct kvm_mips_tlb *tlb, + unsigned long gva, + bool write_fault) { - unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; - kvm_pfn_t pfn0, pfn1; - gfn_t gfn0, gfn1; long tlb_lo[2]; - int ret; + pte_t pte_gpa[2], *ptep_buddy, *ptep_gva; + unsigned int idx = TLB_LO_IDX(*tlb, gva); + bool kernel = KVM_GUEST_KERNEL_MODE(vcpu); tlb_lo[0] = tlb->tlb_lo[0]; tlb_lo[1] = tlb->tlb_lo[1]; @@ -149,70 +1048,64 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, * The commpage address must not be mapped to anything else if the guest * TLB contains entries nearby, or commpage accesses will break. */ - if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) & - VPN2_MASK & (PAGE_MASK << 1))) - tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0; - - gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT; - gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT; - if (gfn0 >= kvm->arch.guest_pmap_npages || - gfn1 >= kvm->arch.guest_pmap_npages) { - kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n", - __func__, gfn0, gfn1, tlb->tlb_hi); - kvm_mips_dump_guest_tlbs(vcpu); - return -1; - } + if (!((gva ^ KVM_GUEST_COMMPAGE_ADDR) & VPN2_MASK & (PAGE_MASK << 1))) + tlb_lo[TLB_LO_IDX(*tlb, KVM_GUEST_COMMPAGE_ADDR)] = 0; - if (kvm_mips_map_page(kvm, gfn0) < 0) + /* Get the GPA page table entry */ + if (kvm_mips_map_page(vcpu, mips3_tlbpfn_to_paddr(tlb_lo[idx]), + write_fault, &pte_gpa[idx], NULL) < 0) return -1; - if (kvm_mips_map_page(kvm, gfn1) < 0) + /* And its GVA buddy's GPA page table entry if it also exists */ + pte_gpa[!idx] = pfn_pte(0, __pgprot(0)); + if (tlb_lo[!idx] & ENTRYLO_V) { + spin_lock(&kvm->mmu_lock); + ptep_buddy = kvm_mips_pte_for_gpa(kvm, NULL, + mips3_tlbpfn_to_paddr(tlb_lo[!idx])); + if (ptep_buddy) + pte_gpa[!idx] = *ptep_buddy; + spin_unlock(&kvm->mmu_lock); + } + + /* Get the GVA page table entry pair */ + ptep_gva = kvm_trap_emul_pte_for_gva(vcpu, gva & ~PAGE_SIZE); + if (!ptep_gva) { + kvm_err("No ptep for gva %lx\n", gva); return -1; + } - pfn0 = kvm->arch.guest_pmap[gfn0]; - pfn1 = kvm->arch.guest_pmap[gfn1]; + /* Copy a pair of entries from GPA page table to GVA page table */ + ptep_gva[0] = kvm_mips_gpa_pte_to_gva_mapped(pte_gpa[0], tlb_lo[0]); + ptep_gva[1] = kvm_mips_gpa_pte_to_gva_mapped(pte_gpa[1], tlb_lo[1]); - /* Get attributes from the Guest TLB */ - entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | - ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb_lo[0] & ENTRYLO_D) | - (tlb_lo[0] & ENTRYLO_V); - entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | - ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb_lo[1] & ENTRYLO_D) | - (tlb_lo[1] & ENTRYLO_V); + /* Invalidate this entry in the TLB, current guest mode ASID only */ + kvm_mips_host_tlb_inv(vcpu, gva, !kernel, kernel); kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc, tlb->tlb_lo[0], tlb->tlb_lo[1]); - preempt_disable(); - entryhi = (tlb->tlb_hi & VPN2_MASK) | (KVM_GUEST_KERNEL_MODE(vcpu) ? - kvm_mips_get_kernel_asid(vcpu) : - kvm_mips_get_user_asid(vcpu)); - ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1, - tlb->tlb_mask); - preempt_enable(); - - return ret; + return 0; } -void kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, - struct kvm_vcpu *vcpu) +int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr, + struct kvm_vcpu *vcpu) { - unsigned long asid = asid_cache(cpu); - - asid += cpu_asid_inc(); - if (!(asid & cpu_asid_mask(&cpu_data[cpu]))) { - if (cpu_has_vtag_icache) - flush_icache_all(); - - kvm_local_flush_tlb_all(); /* start new asid cycle */ + kvm_pfn_t pfn; + pte_t *ptep; - if (!asid) /* fix version if needed */ - asid = asid_first_version(cpu); + ptep = kvm_trap_emul_pte_for_gva(vcpu, badvaddr); + if (!ptep) { + kvm_err("No ptep for commpage %lx\n", badvaddr); + return -1; } - cpu_context(cpu, mm) = asid_cache(cpu) = asid; + pfn = PFN_DOWN(virt_to_phys(vcpu->arch.kseg0_commpage)); + /* Also set valid and dirty, so refill handler doesn't have to */ + *ptep = pte_mkyoung(pte_mkdirty(pfn_pte(pfn, PAGE_SHARED))); + + /* Invalidate this entry in the TLB, guest kernel ASID only */ + kvm_mips_host_tlb_inv(vcpu, badvaddr, false, true); + return 0; } /** @@ -235,42 +1128,13 @@ static void kvm_mips_migrate_count(struct kvm_vcpu *vcpu) /* Restore ASID once we are scheduled back after preemption */ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - unsigned long asid_mask = cpu_asid_mask(&cpu_data[cpu]); unsigned long flags; - int newasid = 0; kvm_debug("%s: vcpu %p, cpu: %d\n", __func__, vcpu, cpu); - /* Allocate new kernel and user ASIDs if needed */ - local_irq_save(flags); - if ((vcpu->arch.guest_kernel_asid[cpu] ^ asid_cache(cpu)) & - asid_version_mask(cpu)) { - kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, cpu, vcpu); - vcpu->arch.guest_kernel_asid[cpu] = - vcpu->arch.guest_kernel_mm.context.asid[cpu]; - newasid++; - - kvm_debug("[%d]: cpu_context: %#lx\n", cpu, - cpu_context(cpu, current->mm)); - kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n", - cpu, vcpu->arch.guest_kernel_asid[cpu]); - } - - if ((vcpu->arch.guest_user_asid[cpu] ^ asid_cache(cpu)) & - asid_version_mask(cpu)) { - kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu); - vcpu->arch.guest_user_asid[cpu] = - vcpu->arch.guest_user_mm.context.asid[cpu]; - newasid++; - - kvm_debug("[%d]: cpu_context: %#lx\n", cpu, - cpu_context(cpu, current->mm)); - kvm_debug("[%d]: Allocated new ASID for Guest User: %#x\n", cpu, - vcpu->arch.guest_user_asid[cpu]); - } - + vcpu->cpu = cpu; if (vcpu->arch.last_sched_cpu != cpu) { kvm_debug("[%d->%d]KVM VCPU[%d] switch\n", vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id); @@ -282,42 +1146,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_mips_migrate_count(vcpu); } - if (!newasid) { - /* - * If we preempted while the guest was executing, then reload - * the pre-empted ASID - */ - if (current->flags & PF_VCPU) { - write_c0_entryhi(vcpu->arch. - preempt_entryhi & asid_mask); - ehb(); - } - } else { - /* New ASIDs were allocated for the VM */ - - /* - * Were we in guest context? If so then the pre-empted ASID is - * no longer valid, we need to set it to what it should be based - * on the mode of the Guest (Kernel/User) - */ - if (current->flags & PF_VCPU) { - if (KVM_GUEST_KERNEL_MODE(vcpu)) - write_c0_entryhi(vcpu->arch. - guest_kernel_asid[cpu] & - asid_mask); - else - write_c0_entryhi(vcpu->arch. - guest_user_asid[cpu] & - asid_mask); - ehb(); - } - } - /* restore guest state to registers */ - kvm_mips_callbacks->vcpu_set_regs(vcpu); + kvm_mips_callbacks->vcpu_load(vcpu, cpu); local_irq_restore(flags); - } /* ASID can change if another task is scheduled during preemption */ @@ -329,75 +1161,90 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) local_irq_save(flags); cpu = smp_processor_id(); - - vcpu->arch.preempt_entryhi = read_c0_entryhi(); vcpu->arch.last_sched_cpu = cpu; + vcpu->cpu = -1; /* save guest state in registers */ - kvm_mips_callbacks->vcpu_get_regs(vcpu); - - if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) & - asid_version_mask(cpu))) { - kvm_debug("%s: Dropping MMU Context: %#lx\n", __func__, - cpu_context(cpu, current->mm)); - drop_mmu_context(current->mm, cpu); - } - write_c0_entryhi(cpu_asid(cpu, current->mm)); - ehb(); + kvm_mips_callbacks->vcpu_put(vcpu, cpu); local_irq_restore(flags); } -u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu) +/** + * kvm_trap_emul_gva_fault() - Safely attempt to handle a GVA access fault. + * @vcpu: Virtual CPU. + * @gva: Guest virtual address to be accessed. + * @write: True if write attempted (must be dirtied and made writable). + * + * Safely attempt to handle a GVA fault, mapping GVA pages if necessary, and + * dirtying the page if @write so that guest instructions can be modified. + * + * Returns: KVM_MIPS_MAPPED on success. + * KVM_MIPS_GVA if bad guest virtual address. + * KVM_MIPS_GPA if bad guest physical address. + * KVM_MIPS_TLB if guest TLB not present. + * KVM_MIPS_TLBINV if guest TLB present but not valid. + * KVM_MIPS_TLBMOD if guest TLB read only. + */ +enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, + unsigned long gva, + bool write) { struct mips_coproc *cop0 = vcpu->arch.cop0; - unsigned long paddr, flags, vpn2, asid; - unsigned long va = (unsigned long)opc; - void *vaddr; - u32 inst; + struct kvm_mips_tlb *tlb; int index; - if (KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0 || - KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { - local_irq_save(flags); - index = kvm_mips_host_tlb_lookup(vcpu, va); - if (index >= 0) { - inst = *(opc); - } else { - vpn2 = va & VPN2_MASK; - asid = kvm_read_c0_guest_entryhi(cop0) & - KVM_ENTRYHI_ASID; - index = kvm_mips_guest_tlb_lookup(vcpu, vpn2 | asid); - if (index < 0) { - kvm_err("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n", - __func__, opc, vcpu, read_c0_entryhi()); - kvm_mips_dump_host_tlbs(); - kvm_mips_dump_guest_tlbs(vcpu); - local_irq_restore(flags); - return KVM_INVALID_INST; - } - if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, - &vcpu->arch.guest_tlb[index])) { - kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n", - __func__, opc, index, vcpu, - read_c0_entryhi()); - kvm_mips_dump_guest_tlbs(vcpu); - local_irq_restore(flags); - return KVM_INVALID_INST; - } - inst = *(opc); - } - local_irq_restore(flags); - } else if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - paddr = kvm_mips_translate_guest_kseg0_to_hpa(vcpu, va); - vaddr = kmap_atomic(pfn_to_page(PHYS_PFN(paddr))); - vaddr += paddr & ~PAGE_MASK; - inst = *(u32 *)vaddr; - kunmap_atomic(vaddr); + if (KVM_GUEST_KSEGX(gva) == KVM_GUEST_KSEG0) { + if (kvm_mips_handle_kseg0_tlb_fault(gva, vcpu, write) < 0) + return KVM_MIPS_GPA; + } else if ((KVM_GUEST_KSEGX(gva) < KVM_GUEST_KSEG0) || + KVM_GUEST_KSEGX(gva) == KVM_GUEST_KSEG23) { + /* Address should be in the guest TLB */ + index = kvm_mips_guest_tlb_lookup(vcpu, (gva & VPN2_MASK) | + (kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID)); + if (index < 0) + return KVM_MIPS_TLB; + tlb = &vcpu->arch.guest_tlb[index]; + + /* Entry should be valid, and dirty for writes */ + if (!TLB_IS_VALID(*tlb, gva)) + return KVM_MIPS_TLBINV; + if (write && !TLB_IS_DIRTY(*tlb, gva)) + return KVM_MIPS_TLBMOD; + + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, gva, write)) + return KVM_MIPS_GPA; } else { - kvm_err("%s: illegal address: %p\n", __func__, opc); - return KVM_INVALID_INST; + return KVM_MIPS_GVA; } - return inst; + return KVM_MIPS_MAPPED; +} + +int kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu, u32 *out) +{ + int err; + +retry: + kvm_trap_emul_gva_lockless_begin(vcpu); + err = get_user(*out, opc); + kvm_trap_emul_gva_lockless_end(vcpu); + + if (unlikely(err)) { + /* + * Try to handle the fault, maybe we just raced with a GVA + * invalidation. + */ + err = kvm_trap_emul_gva_fault(vcpu, (unsigned long)opc, + false); + if (unlikely(err)) { + kvm_err("%s: illegal address: %p\n", + __func__, opc); + return -EFAULT; + } + + /* Hopefully it'll work now */ + goto retry; + } + return 0; } diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index 254377d..2819eb7 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -33,28 +33,20 @@ #define KVM_GUEST_PC_TLB 0 #define KVM_GUEST_SP_TLB 1 -atomic_t kvm_mips_instance; -EXPORT_SYMBOL_GPL(kvm_mips_instance); - static u32 kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu) { + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; int cpu = smp_processor_id(); - return vcpu->arch.guest_kernel_asid[cpu] & - cpu_asid_mask(&cpu_data[cpu]); + return cpu_asid(cpu, kern_mm); } static u32 kvm_mips_get_user_asid(struct kvm_vcpu *vcpu) { + struct mm_struct *user_mm = &vcpu->arch.guest_user_mm; int cpu = smp_processor_id(); - return vcpu->arch.guest_user_asid[cpu] & - cpu_asid_mask(&cpu_data[cpu]); -} - -inline u32 kvm_mips_get_commpage_asid(struct kvm_vcpu *vcpu) -{ - return vcpu->kvm->arch.commpage_tlb; + return cpu_asid(cpu, user_mm); } /* Structure defining an tlb entry data set. */ @@ -104,109 +96,6 @@ void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mips_dump_guest_tlbs); -/* XXXKYMA: Must be called with interrupts disabled */ -/* set flush_dcache_mask == 0 if no dcache flush required */ -int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi, - unsigned long entrylo0, unsigned long entrylo1, - int flush_dcache_mask) -{ - unsigned long flags; - unsigned long old_entryhi; - int idx; - - local_irq_save(flags); - - old_entryhi = read_c0_entryhi(); - write_c0_entryhi(entryhi); - mtc0_tlbw_hazard(); - - tlb_probe(); - tlb_probe_hazard(); - idx = read_c0_index(); - - if (idx > current_cpu_data.tlbsize) { - kvm_err("%s: Invalid Index: %d\n", __func__, idx); - kvm_mips_dump_host_tlbs(); - local_irq_restore(flags); - return -1; - } - - write_c0_entrylo0(entrylo0); - write_c0_entrylo1(entrylo1); - mtc0_tlbw_hazard(); - - if (idx < 0) - tlb_write_random(); - else - tlb_write_indexed(); - tlbw_use_hazard(); - - kvm_debug("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0(R): 0x%08lx, entrylo1(R): 0x%08lx\n", - vcpu->arch.pc, idx, read_c0_entryhi(), - read_c0_entrylo0(), read_c0_entrylo1()); - - /* Flush D-cache */ - if (flush_dcache_mask) { - if (entrylo0 & ENTRYLO_V) { - ++vcpu->stat.flush_dcache_exits; - flush_data_cache_page((entryhi & VPN2_MASK) & - ~flush_dcache_mask); - } - if (entrylo1 & ENTRYLO_V) { - ++vcpu->stat.flush_dcache_exits; - flush_data_cache_page(((entryhi & VPN2_MASK) & - ~flush_dcache_mask) | - (0x1 << PAGE_SHIFT)); - } - } - - /* Restore old ASID */ - write_c0_entryhi(old_entryhi); - mtc0_tlbw_hazard(); - local_irq_restore(flags); - return 0; -} -EXPORT_SYMBOL_GPL(kvm_mips_host_tlb_write); - -int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr, - struct kvm_vcpu *vcpu) -{ - kvm_pfn_t pfn; - unsigned long flags, old_entryhi = 0, vaddr = 0; - unsigned long entrylo[2] = { 0, 0 }; - unsigned int pair_idx; - - pfn = PFN_DOWN(virt_to_phys(vcpu->arch.kseg0_commpage)); - pair_idx = (badvaddr >> PAGE_SHIFT) & 1; - entrylo[pair_idx] = mips3_paddr_to_tlbpfn(pfn << PAGE_SHIFT) | - ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - ENTRYLO_D | ENTRYLO_V; - - local_irq_save(flags); - - old_entryhi = read_c0_entryhi(); - vaddr = badvaddr & (PAGE_MASK << 1); - write_c0_entryhi(vaddr | kvm_mips_get_kernel_asid(vcpu)); - write_c0_entrylo0(entrylo[0]); - write_c0_entrylo1(entrylo[1]); - write_c0_index(kvm_mips_get_commpage_asid(vcpu)); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - tlbw_use_hazard(); - - kvm_debug("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0 (R): 0x%08lx, entrylo1(R): 0x%08lx\n", - vcpu->arch.pc, read_c0_index(), read_c0_entryhi(), - read_c0_entrylo0(), read_c0_entrylo1()); - - /* Restore old ASID */ - write_c0_entryhi(old_entryhi); - mtc0_tlbw_hazard(); - local_irq_restore(flags); - - return 0; -} -EXPORT_SYMBOL_GPL(kvm_mips_handle_commpage_tlb_fault); - int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi) { int i; @@ -228,51 +117,11 @@ int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi) } EXPORT_SYMBOL_GPL(kvm_mips_guest_tlb_lookup); -int kvm_mips_host_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long vaddr) -{ - unsigned long old_entryhi, flags; - int idx; - - local_irq_save(flags); - - old_entryhi = read_c0_entryhi(); - - if (KVM_GUEST_KERNEL_MODE(vcpu)) - write_c0_entryhi((vaddr & VPN2_MASK) | - kvm_mips_get_kernel_asid(vcpu)); - else { - write_c0_entryhi((vaddr & VPN2_MASK) | - kvm_mips_get_user_asid(vcpu)); - } - - mtc0_tlbw_hazard(); - - tlb_probe(); - tlb_probe_hazard(); - idx = read_c0_index(); - - /* Restore old ASID */ - write_c0_entryhi(old_entryhi); - mtc0_tlbw_hazard(); - - local_irq_restore(flags); - - kvm_debug("Host TLB lookup, %#lx, idx: %2d\n", vaddr, idx); - - return idx; -} -EXPORT_SYMBOL_GPL(kvm_mips_host_tlb_lookup); - -int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va) +static int _kvm_mips_host_tlb_inv(unsigned long entryhi) { int idx; - unsigned long flags, old_entryhi; - - local_irq_save(flags); - - old_entryhi = read_c0_entryhi(); - write_c0_entryhi((va & VPN2_MASK) | kvm_mips_get_user_asid(vcpu)); + write_c0_entryhi(entryhi); mtc0_tlbw_hazard(); tlb_probe(); @@ -282,7 +131,7 @@ int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va) if (idx >= current_cpu_data.tlbsize) BUG(); - if (idx > 0) { + if (idx >= 0) { write_c0_entryhi(UNIQUE_ENTRYHI(idx)); write_c0_entrylo0(0); write_c0_entrylo1(0); @@ -292,93 +141,75 @@ int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va) tlbw_use_hazard(); } - write_c0_entryhi(old_entryhi); - mtc0_tlbw_hazard(); - - local_irq_restore(flags); - - if (idx > 0) - kvm_debug("%s: Invalidated entryhi %#lx @ idx %d\n", __func__, - (va & VPN2_MASK) | kvm_mips_get_user_asid(vcpu), idx); - - return 0; + return idx; } -EXPORT_SYMBOL_GPL(kvm_mips_host_tlb_inv); -void kvm_mips_flush_host_tlb(int skip_kseg0) +int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va, + bool user, bool kernel) { - unsigned long flags; - unsigned long old_entryhi, entryhi; - unsigned long old_pagemask; - int entry = 0; - int maxentry = current_cpu_data.tlbsize; + int idx_user, idx_kernel; + unsigned long flags, old_entryhi; local_irq_save(flags); old_entryhi = read_c0_entryhi(); - old_pagemask = read_c0_pagemask(); - - /* Blast 'em all away. */ - for (entry = 0; entry < maxentry; entry++) { - write_c0_index(entry); - - if (skip_kseg0) { - mtc0_tlbr_hazard(); - tlb_read(); - tlb_read_hazard(); - - entryhi = read_c0_entryhi(); - /* Don't blow away guest kernel entries */ - if (KVM_GUEST_KSEGX(entryhi) == KVM_GUEST_KSEG0) - continue; - - write_c0_pagemask(old_pagemask); - } - - /* Make sure all entries differ. */ - write_c0_entryhi(UNIQUE_ENTRYHI(entry)); - write_c0_entrylo0(0); - write_c0_entrylo1(0); - mtc0_tlbw_hazard(); - - tlb_write_indexed(); - tlbw_use_hazard(); - } + if (user) + idx_user = _kvm_mips_host_tlb_inv((va & VPN2_MASK) | + kvm_mips_get_user_asid(vcpu)); + if (kernel) + idx_kernel = _kvm_mips_host_tlb_inv((va & VPN2_MASK) | + kvm_mips_get_kernel_asid(vcpu)); write_c0_entryhi(old_entryhi); - write_c0_pagemask(old_pagemask); mtc0_tlbw_hazard(); local_irq_restore(flags); + + if (user && idx_user >= 0) + kvm_debug("%s: Invalidated guest user entryhi %#lx @ idx %d\n", + __func__, (va & VPN2_MASK) | + kvm_mips_get_user_asid(vcpu), idx_user); + if (kernel && idx_kernel >= 0) + kvm_debug("%s: Invalidated guest kernel entryhi %#lx @ idx %d\n", + __func__, (va & VPN2_MASK) | + kvm_mips_get_kernel_asid(vcpu), idx_kernel); + + return 0; } -EXPORT_SYMBOL_GPL(kvm_mips_flush_host_tlb); +EXPORT_SYMBOL_GPL(kvm_mips_host_tlb_inv); -void kvm_local_flush_tlb_all(void) +/** + * kvm_mips_suspend_mm() - Suspend the active mm. + * @cpu The CPU we're running on. + * + * Suspend the active_mm, ready for a switch to a KVM guest virtual address + * space. This is left active for the duration of guest context, including time + * with interrupts enabled, so we need to be careful not to confuse e.g. cache + * management IPIs. + * + * kvm_mips_resume_mm() should be called before context switching to a different + * process so we don't need to worry about reference counting. + * + * This needs to be in static kernel code to avoid exporting init_mm. + */ +void kvm_mips_suspend_mm(int cpu) { - unsigned long flags; - unsigned long old_ctx; - int entry = 0; - - local_irq_save(flags); - /* Save old context and create impossible VPN2 value */ - old_ctx = read_c0_entryhi(); - write_c0_entrylo0(0); - write_c0_entrylo1(0); - - /* Blast 'em all away. */ - while (entry < current_cpu_data.tlbsize) { - /* Make sure all entries differ. */ - write_c0_entryhi(UNIQUE_ENTRYHI(entry)); - write_c0_index(entry); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - tlbw_use_hazard(); - entry++; - } - write_c0_entryhi(old_ctx); - mtc0_tlbw_hazard(); + cpumask_clear_cpu(cpu, mm_cpumask(current->active_mm)); + current->active_mm = &init_mm; +} +EXPORT_SYMBOL_GPL(kvm_mips_suspend_mm); - local_irq_restore(flags); +/** + * kvm_mips_resume_mm() - Resume the current process mm. + * @cpu The CPU we're running on. + * + * Resume the mm of the current process, after a switch back from a KVM guest + * virtual address space (see kvm_mips_suspend_mm()). + */ +void kvm_mips_resume_mm(int cpu) +{ + cpumask_set_cpu(cpu, mm_cpumask(current->mm)); + current->active_mm = current->mm; } -EXPORT_SYMBOL_GPL(kvm_local_flush_tlb_all); +EXPORT_SYMBOL_GPL(kvm_mips_resume_mm); diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index 3b20441..b1fa53b 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -11,9 +11,11 @@ #include <linux/errno.h> #include <linux/err.h> -#include <linux/vmalloc.h> - #include <linux/kvm_host.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <asm/mmu_context.h> +#include <asm/pgalloc.h> #include "interrupt.h" @@ -21,9 +23,12 @@ static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva) { gpa_t gpa; gva_t kseg = KSEGX(gva); + gva_t gkseg = KVM_GUEST_KSEGX(gva); if ((kseg == CKSEG0) || (kseg == CKSEG1)) gpa = CPHYSADDR(gva); + else if (gkseg == KVM_GUEST_KSEG0) + gpa = KVM_GUEST_CPHYSADDR(gva); else { kvm_err("%s: cannot find GPA for GVA: %#lx\n", __func__, gva); kvm_mips_dump_host_tlbs(); @@ -83,48 +88,134 @@ static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu) return ret; } +static int kvm_mips_bad_load(u32 cause, u32 *opc, struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + enum emulation_result er; + union mips_instruction inst; + int err; + + /* A code fetch fault doesn't count as an MMIO */ + if (kvm_is_ifetch_fault(&vcpu->arch)) { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return RESUME_HOST; + } + + /* Fetch the instruction. */ + if (cause & CAUSEF_BD) + opc += 1; + err = kvm_get_badinstr(opc, vcpu, &inst.word); + if (err) { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return RESUME_HOST; + } + + /* Emulate the load */ + er = kvm_mips_emulate_load(inst, cause, run, vcpu); + if (er == EMULATE_FAIL) { + kvm_err("Emulate load from MMIO space failed\n"); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + } else { + run->exit_reason = KVM_EXIT_MMIO; + } + return RESUME_HOST; +} + +static int kvm_mips_bad_store(u32 cause, u32 *opc, struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + enum emulation_result er; + union mips_instruction inst; + int err; + + /* Fetch the instruction. */ + if (cause & CAUSEF_BD) + opc += 1; + err = kvm_get_badinstr(opc, vcpu, &inst.word); + if (err) { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return RESUME_HOST; + } + + /* Emulate the store */ + er = kvm_mips_emulate_store(inst, cause, run, vcpu); + if (er == EMULATE_FAIL) { + kvm_err("Emulate store to MMIO space failed\n"); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + } else { + run->exit_reason = KVM_EXIT_MMIO; + } + return RESUME_HOST; +} + +static int kvm_mips_bad_access(u32 cause, u32 *opc, struct kvm_run *run, + struct kvm_vcpu *vcpu, bool store) +{ + if (store) + return kvm_mips_bad_store(cause, opc, run, vcpu); + else + return kvm_mips_bad_load(cause, opc, run, vcpu); +} + static int kvm_trap_emul_handle_tlb_mod(struct kvm_vcpu *vcpu) { + struct mips_coproc *cop0 = vcpu->arch.cop0; struct kvm_run *run = vcpu->run; u32 __user *opc = (u32 __user *) vcpu->arch.pc; unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr; u32 cause = vcpu->arch.host_cp0_cause; - enum emulation_result er = EMULATE_DONE; - int ret = RESUME_GUEST; + struct kvm_mips_tlb *tlb; + unsigned long entryhi; + int index; if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0 || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) { - kvm_debug("USER/KSEG23 ADDR TLB MOD fault: cause %#x, PC: %p, BadVaddr: %#lx\n", - cause, opc, badvaddr); - er = kvm_mips_handle_tlbmod(cause, opc, run, vcpu); + /* + * First find the mapping in the guest TLB. If the failure to + * write was due to the guest TLB, it should be up to the guest + * to handle it. + */ + entryhi = (badvaddr & VPN2_MASK) | + (kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID); + index = kvm_mips_guest_tlb_lookup(vcpu, entryhi); - if (er == EMULATE_DONE) - ret = RESUME_GUEST; - else { + /* + * These should never happen. + * They would indicate stale host TLB entries. + */ + if (unlikely(index < 0)) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; + return RESUME_HOST; } - } else if (KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG0) { + tlb = vcpu->arch.guest_tlb + index; + if (unlikely(!TLB_IS_VALID(*tlb, badvaddr))) { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return RESUME_HOST; + } + /* - * XXXKYMA: The guest kernel does not expect to get this fault - * when we are not using HIGHMEM. Need to address this in a - * HIGHMEM kernel + * Guest entry not dirty? That would explain the TLB modified + * exception. Relay that on to the guest so it can handle it. */ - kvm_err("TLB MOD fault not handled, cause %#x, PC: %p, BadVaddr: %#lx\n", - cause, opc, badvaddr); - kvm_mips_dump_host_tlbs(); - kvm_arch_vcpu_dump_regs(vcpu); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; + if (!TLB_IS_DIRTY(*tlb, badvaddr)) { + kvm_mips_emulate_tlbmod(cause, opc, run, vcpu); + return RESUME_GUEST; + } + + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, badvaddr, + true)) + /* Not writable, needs handling as MMIO */ + return kvm_mips_bad_store(cause, opc, run, vcpu); + return RESUME_GUEST; + } else if (KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG0) { + if (kvm_mips_handle_kseg0_tlb_fault(badvaddr, vcpu, true) < 0) + /* Not writable, needs handling as MMIO */ + return kvm_mips_bad_store(cause, opc, run, vcpu); + return RESUME_GUEST; } else { - kvm_err("Illegal TLB Mod fault address , cause %#x, PC: %p, BadVaddr: %#lx\n", - cause, opc, badvaddr); - kvm_mips_dump_host_tlbs(); - kvm_arch_vcpu_dump_regs(vcpu); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; + /* host kernel addresses are all handled as MMIO */ + return kvm_mips_bad_store(cause, opc, run, vcpu); } - return ret; } static int kvm_trap_emul_handle_tlb_miss(struct kvm_vcpu *vcpu, bool store) @@ -157,7 +248,7 @@ static int kvm_trap_emul_handle_tlb_miss(struct kvm_vcpu *vcpu, bool store) * into the shadow host TLB */ - er = kvm_mips_handle_tlbmiss(cause, opc, run, vcpu); + er = kvm_mips_handle_tlbmiss(cause, opc, run, vcpu, store); if (er == EMULATE_DONE) ret = RESUME_GUEST; else { @@ -169,29 +260,15 @@ static int kvm_trap_emul_handle_tlb_miss(struct kvm_vcpu *vcpu, bool store) * All KSEG0 faults are handled by KVM, as the guest kernel does * not expect to ever get them */ - if (kvm_mips_handle_kseg0_tlb_fault - (vcpu->arch.host_cp0_badvaddr, vcpu) < 0) { - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; - } + if (kvm_mips_handle_kseg0_tlb_fault(badvaddr, vcpu, store) < 0) + ret = kvm_mips_bad_access(cause, opc, run, vcpu, store); } else if (KVM_GUEST_KERNEL_MODE(vcpu) && (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1)) { /* * With EVA we may get a TLB exception instead of an address * error when the guest performs MMIO to KSeg1 addresses. */ - kvm_debug("Emulate %s MMIO space\n", - store ? "Store to" : "Load from"); - er = kvm_mips_emulate_inst(cause, opc, run, vcpu); - if (er == EMULATE_FAIL) { - kvm_err("Emulate %s MMIO space failed\n", - store ? "Store to" : "Load from"); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; - } else { - run->exit_reason = KVM_EXIT_MMIO; - ret = RESUME_HOST; - } + ret = kvm_mips_bad_access(cause, opc, run, vcpu, store); } else { kvm_err("Illegal TLB %s fault address , cause %#x, PC: %p, BadVaddr: %#lx\n", store ? "ST" : "LD", cause, opc, badvaddr); @@ -219,21 +296,11 @@ static int kvm_trap_emul_handle_addr_err_st(struct kvm_vcpu *vcpu) u32 __user *opc = (u32 __user *) vcpu->arch.pc; unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr; u32 cause = vcpu->arch.host_cp0_cause; - enum emulation_result er = EMULATE_DONE; int ret = RESUME_GUEST; if (KVM_GUEST_KERNEL_MODE(vcpu) && (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1)) { - kvm_debug("Emulate Store to MMIO space\n"); - er = kvm_mips_emulate_inst(cause, opc, run, vcpu); - if (er == EMULATE_FAIL) { - kvm_err("Emulate Store to MMIO space failed\n"); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; - } else { - run->exit_reason = KVM_EXIT_MMIO; - ret = RESUME_HOST; - } + ret = kvm_mips_bad_store(cause, opc, run, vcpu); } else { kvm_err("Address Error (STORE): cause %#x, PC: %p, BadVaddr: %#lx\n", cause, opc, badvaddr); @@ -249,26 +316,15 @@ static int kvm_trap_emul_handle_addr_err_ld(struct kvm_vcpu *vcpu) u32 __user *opc = (u32 __user *) vcpu->arch.pc; unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr; u32 cause = vcpu->arch.host_cp0_cause; - enum emulation_result er = EMULATE_DONE; int ret = RESUME_GUEST; if (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1) { - kvm_debug("Emulate Load from MMIO space @ %#lx\n", badvaddr); - er = kvm_mips_emulate_inst(cause, opc, run, vcpu); - if (er == EMULATE_FAIL) { - kvm_err("Emulate Load from MMIO space failed\n"); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - ret = RESUME_HOST; - } else { - run->exit_reason = KVM_EXIT_MMIO; - ret = RESUME_HOST; - } + ret = kvm_mips_bad_load(cause, opc, run, vcpu); } else { kvm_err("Address Error (LOAD): cause %#x, PC: %p, BadVaddr: %#lx\n", cause, opc, badvaddr); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; ret = RESUME_HOST; - er = EMULATE_FAIL; } return ret; } @@ -428,16 +484,75 @@ static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu) return ret; } -static int kvm_trap_emul_vm_init(struct kvm *kvm) +static int kvm_trap_emul_vcpu_init(struct kvm_vcpu *vcpu) { + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; + struct mm_struct *user_mm = &vcpu->arch.guest_user_mm; + + /* + * Allocate GVA -> HPA page tables. + * MIPS doesn't use the mm_struct pointer argument. + */ + kern_mm->pgd = pgd_alloc(kern_mm); + if (!kern_mm->pgd) + return -ENOMEM; + + user_mm->pgd = pgd_alloc(user_mm); + if (!user_mm->pgd) { + pgd_free(kern_mm, kern_mm->pgd); + return -ENOMEM; + } + return 0; } -static int kvm_trap_emul_vcpu_init(struct kvm_vcpu *vcpu) +static void kvm_mips_emul_free_gva_pt(pgd_t *pgd) { - vcpu->arch.kscratch_enabled = 0xfc; + /* Don't free host kernel page tables copied from init_mm.pgd */ + const unsigned long end = 0x80000000; + unsigned long pgd_va, pud_va, pmd_va; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i, j, k; + + for (i = 0; i < USER_PTRS_PER_PGD; i++) { + if (pgd_none(pgd[i])) + continue; + + pgd_va = (unsigned long)i << PGDIR_SHIFT; + if (pgd_va >= end) + break; + pud = pud_offset(pgd + i, 0); + for (j = 0; j < PTRS_PER_PUD; j++) { + if (pud_none(pud[j])) + continue; + + pud_va = pgd_va | ((unsigned long)j << PUD_SHIFT); + if (pud_va >= end) + break; + pmd = pmd_offset(pud + j, 0); + for (k = 0; k < PTRS_PER_PMD; k++) { + if (pmd_none(pmd[k])) + continue; + + pmd_va = pud_va | (k << PMD_SHIFT); + if (pmd_va >= end) + break; + pte = pte_offset(pmd + k, 0); + pte_free_kernel(NULL, pte); + } + pmd_free(NULL, pmd); + } + pud_free(NULL, pud); + } + pgd_free(NULL, pgd); +} - return 0; +static void kvm_trap_emul_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + kvm_mips_emul_free_gva_pt(vcpu->arch.guest_kernel_mm.pgd); + kvm_mips_emul_free_gva_pt(vcpu->arch.guest_user_mm.pgd); } static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) @@ -499,6 +614,9 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) /* Set Wait IE/IXMT Ignore in Config7, IAR, AR */ kvm_write_c0_guest_config7(cop0, (MIPS_CONF7_WII) | (1 << 10)); + /* Status */ + kvm_write_c0_guest_status(cop0, ST0_BEV | ST0_ERL); + /* * Setup IntCtl defaults, compatibility mode for timer interrupts (HW5) */ @@ -508,17 +626,76 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) kvm_write_c0_guest_ebase(cop0, KVM_GUEST_KSEG0 | (vcpu_id & MIPS_EBASE_CPUNUM)); + /* Put PC at guest reset vector */ + vcpu->arch.pc = KVM_GUEST_CKSEG1ADDR(0x1fc00000); + return 0; } +static void kvm_trap_emul_flush_shadow_all(struct kvm *kvm) +{ + /* Flush GVA page tables and invalidate GVA ASIDs on all VCPUs */ + kvm_flush_remote_tlbs(kvm); +} + +static void kvm_trap_emul_flush_shadow_memslot(struct kvm *kvm, + const struct kvm_memory_slot *slot) +{ + kvm_trap_emul_flush_shadow_all(kvm); +} + +static u64 kvm_trap_emul_get_one_regs[] = { + KVM_REG_MIPS_CP0_INDEX, + KVM_REG_MIPS_CP0_ENTRYLO0, + KVM_REG_MIPS_CP0_ENTRYLO1, + KVM_REG_MIPS_CP0_CONTEXT, + KVM_REG_MIPS_CP0_USERLOCAL, + KVM_REG_MIPS_CP0_PAGEMASK, + KVM_REG_MIPS_CP0_WIRED, + KVM_REG_MIPS_CP0_HWRENA, + KVM_REG_MIPS_CP0_BADVADDR, + KVM_REG_MIPS_CP0_COUNT, + KVM_REG_MIPS_CP0_ENTRYHI, + KVM_REG_MIPS_CP0_COMPARE, + KVM_REG_MIPS_CP0_STATUS, + KVM_REG_MIPS_CP0_INTCTL, + KVM_REG_MIPS_CP0_CAUSE, + KVM_REG_MIPS_CP0_EPC, + KVM_REG_MIPS_CP0_PRID, + KVM_REG_MIPS_CP0_EBASE, + KVM_REG_MIPS_CP0_CONFIG, + KVM_REG_MIPS_CP0_CONFIG1, + KVM_REG_MIPS_CP0_CONFIG2, + KVM_REG_MIPS_CP0_CONFIG3, + KVM_REG_MIPS_CP0_CONFIG4, + KVM_REG_MIPS_CP0_CONFIG5, + KVM_REG_MIPS_CP0_CONFIG7, + KVM_REG_MIPS_CP0_ERROREPC, + KVM_REG_MIPS_CP0_KSCRATCH1, + KVM_REG_MIPS_CP0_KSCRATCH2, + KVM_REG_MIPS_CP0_KSCRATCH3, + KVM_REG_MIPS_CP0_KSCRATCH4, + KVM_REG_MIPS_CP0_KSCRATCH5, + KVM_REG_MIPS_CP0_KSCRATCH6, + + KVM_REG_MIPS_COUNT_CTL, + KVM_REG_MIPS_COUNT_RESUME, + KVM_REG_MIPS_COUNT_HZ, +}; + static unsigned long kvm_trap_emul_num_regs(struct kvm_vcpu *vcpu) { - return 0; + return ARRAY_SIZE(kvm_trap_emul_get_one_regs); } static int kvm_trap_emul_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices) { + if (copy_to_user(indices, kvm_trap_emul_get_one_regs, + sizeof(kvm_trap_emul_get_one_regs))) + return -EFAULT; + indices += ARRAY_SIZE(kvm_trap_emul_get_one_regs); + return 0; } @@ -526,7 +703,81 @@ static int kvm_trap_emul_get_one_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, s64 *v) { + struct mips_coproc *cop0 = vcpu->arch.cop0; + switch (reg->id) { + case KVM_REG_MIPS_CP0_INDEX: + *v = (long)kvm_read_c0_guest_index(cop0); + break; + case KVM_REG_MIPS_CP0_ENTRYLO0: + *v = kvm_read_c0_guest_entrylo0(cop0); + break; + case KVM_REG_MIPS_CP0_ENTRYLO1: + *v = kvm_read_c0_guest_entrylo1(cop0); + break; + case KVM_REG_MIPS_CP0_CONTEXT: + *v = (long)kvm_read_c0_guest_context(cop0); + break; + case KVM_REG_MIPS_CP0_USERLOCAL: + *v = (long)kvm_read_c0_guest_userlocal(cop0); + break; + case KVM_REG_MIPS_CP0_PAGEMASK: + *v = (long)kvm_read_c0_guest_pagemask(cop0); + break; + case KVM_REG_MIPS_CP0_WIRED: + *v = (long)kvm_read_c0_guest_wired(cop0); + break; + case KVM_REG_MIPS_CP0_HWRENA: + *v = (long)kvm_read_c0_guest_hwrena(cop0); + break; + case KVM_REG_MIPS_CP0_BADVADDR: + *v = (long)kvm_read_c0_guest_badvaddr(cop0); + break; + case KVM_REG_MIPS_CP0_ENTRYHI: + *v = (long)kvm_read_c0_guest_entryhi(cop0); + break; + case KVM_REG_MIPS_CP0_COMPARE: + *v = (long)kvm_read_c0_guest_compare(cop0); + break; + case KVM_REG_MIPS_CP0_STATUS: + *v = (long)kvm_read_c0_guest_status(cop0); + break; + case KVM_REG_MIPS_CP0_INTCTL: + *v = (long)kvm_read_c0_guest_intctl(cop0); + break; + case KVM_REG_MIPS_CP0_CAUSE: + *v = (long)kvm_read_c0_guest_cause(cop0); + break; + case KVM_REG_MIPS_CP0_EPC: + *v = (long)kvm_read_c0_guest_epc(cop0); + break; + case KVM_REG_MIPS_CP0_PRID: + *v = (long)kvm_read_c0_guest_prid(cop0); + break; + case KVM_REG_MIPS_CP0_EBASE: + *v = (long)kvm_read_c0_guest_ebase(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG: + *v = (long)kvm_read_c0_guest_config(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG1: + *v = (long)kvm_read_c0_guest_config1(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG2: + *v = (long)kvm_read_c0_guest_config2(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG3: + *v = (long)kvm_read_c0_guest_config3(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG4: + *v = (long)kvm_read_c0_guest_config4(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG5: + *v = (long)kvm_read_c0_guest_config5(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG7: + *v = (long)kvm_read_c0_guest_config7(cop0); + break; case KVM_REG_MIPS_CP0_COUNT: *v = kvm_mips_read_count(vcpu); break; @@ -539,6 +790,27 @@ static int kvm_trap_emul_get_one_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_COUNT_HZ: *v = vcpu->arch.count_hz; break; + case KVM_REG_MIPS_CP0_ERROREPC: + *v = (long)kvm_read_c0_guest_errorepc(cop0); + break; + case KVM_REG_MIPS_CP0_KSCRATCH1: + *v = (long)kvm_read_c0_guest_kscratch1(cop0); + break; + case KVM_REG_MIPS_CP0_KSCRATCH2: + *v = (long)kvm_read_c0_guest_kscratch2(cop0); + break; + case KVM_REG_MIPS_CP0_KSCRATCH3: + *v = (long)kvm_read_c0_guest_kscratch3(cop0); + break; + case KVM_REG_MIPS_CP0_KSCRATCH4: + *v = (long)kvm_read_c0_guest_kscratch4(cop0); + break; + case KVM_REG_MIPS_CP0_KSCRATCH5: + *v = (long)kvm_read_c0_guest_kscratch5(cop0); + break; + case KVM_REG_MIPS_CP0_KSCRATCH6: + *v = (long)kvm_read_c0_guest_kscratch6(cop0); + break; default: return -EINVAL; } @@ -554,6 +826,56 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, unsigned int cur, change; switch (reg->id) { + case KVM_REG_MIPS_CP0_INDEX: + kvm_write_c0_guest_index(cop0, v); + break; + case KVM_REG_MIPS_CP0_ENTRYLO0: + kvm_write_c0_guest_entrylo0(cop0, v); + break; + case KVM_REG_MIPS_CP0_ENTRYLO1: + kvm_write_c0_guest_entrylo1(cop0, v); + break; + case KVM_REG_MIPS_CP0_CONTEXT: + kvm_write_c0_guest_context(cop0, v); + break; + case KVM_REG_MIPS_CP0_USERLOCAL: + kvm_write_c0_guest_userlocal(cop0, v); + break; + case KVM_REG_MIPS_CP0_PAGEMASK: + kvm_write_c0_guest_pagemask(cop0, v); + break; + case KVM_REG_MIPS_CP0_WIRED: + kvm_write_c0_guest_wired(cop0, v); + break; + case KVM_REG_MIPS_CP0_HWRENA: + kvm_write_c0_guest_hwrena(cop0, v); + break; + case KVM_REG_MIPS_CP0_BADVADDR: + kvm_write_c0_guest_badvaddr(cop0, v); + break; + case KVM_REG_MIPS_CP0_ENTRYHI: + kvm_write_c0_guest_entryhi(cop0, v); + break; + case KVM_REG_MIPS_CP0_STATUS: + kvm_write_c0_guest_status(cop0, v); + break; + case KVM_REG_MIPS_CP0_INTCTL: + /* No VInt, so no VS, read-only for now */ + break; + case KVM_REG_MIPS_CP0_EPC: + kvm_write_c0_guest_epc(cop0, v); + break; + case KVM_REG_MIPS_CP0_PRID: + kvm_write_c0_guest_prid(cop0, v); + break; + case KVM_REG_MIPS_CP0_EBASE: + /* + * Allow core number to be written, but the exception base must + * remain in guest KSeg0. + */ + kvm_change_c0_guest_ebase(cop0, 0x1ffff000 | MIPS_EBASE_CPUNUM, + v); + break; case KVM_REG_MIPS_CP0_COUNT: kvm_mips_write_count(vcpu, v); break; @@ -618,6 +940,9 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, kvm_write_c0_guest_config5(cop0, v); } break; + case KVM_REG_MIPS_CP0_CONFIG7: + /* writes ignored */ + break; case KVM_REG_MIPS_COUNT_CTL: ret = kvm_mips_set_count_ctl(vcpu, v); break; @@ -627,24 +952,269 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_COUNT_HZ: ret = kvm_mips_set_count_hz(vcpu, v); break; + case KVM_REG_MIPS_CP0_ERROREPC: + kvm_write_c0_guest_errorepc(cop0, v); + break; + case KVM_REG_MIPS_CP0_KSCRATCH1: + kvm_write_c0_guest_kscratch1(cop0, v); + break; + case KVM_REG_MIPS_CP0_KSCRATCH2: + kvm_write_c0_guest_kscratch2(cop0, v); + break; + case KVM_REG_MIPS_CP0_KSCRATCH3: + kvm_write_c0_guest_kscratch3(cop0, v); + break; + case KVM_REG_MIPS_CP0_KSCRATCH4: + kvm_write_c0_guest_kscratch4(cop0, v); + break; + case KVM_REG_MIPS_CP0_KSCRATCH5: + kvm_write_c0_guest_kscratch5(cop0, v); + break; + case KVM_REG_MIPS_CP0_KSCRATCH6: + kvm_write_c0_guest_kscratch6(cop0, v); + break; default: return -EINVAL; } return ret; } -static int kvm_trap_emul_vcpu_get_regs(struct kvm_vcpu *vcpu) +static int kvm_trap_emul_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - kvm_lose_fpu(vcpu); + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; + struct mm_struct *user_mm = &vcpu->arch.guest_user_mm; + struct mm_struct *mm; + + /* + * Were we in guest context? If so, restore the appropriate ASID based + * on the mode of the Guest (Kernel/User). + */ + if (current->flags & PF_VCPU) { + mm = KVM_GUEST_KERNEL_MODE(vcpu) ? kern_mm : user_mm; + if ((cpu_context(cpu, mm) ^ asid_cache(cpu)) & + asid_version_mask(cpu)) + get_new_mmu_context(mm, cpu); + write_c0_entryhi(cpu_asid(cpu, mm)); + TLBMISS_HANDLER_SETUP_PGD(mm->pgd); + kvm_mips_suspend_mm(cpu); + ehb(); + } return 0; } -static int kvm_trap_emul_vcpu_set_regs(struct kvm_vcpu *vcpu) +static int kvm_trap_emul_vcpu_put(struct kvm_vcpu *vcpu, int cpu) { + kvm_lose_fpu(vcpu); + + if (current->flags & PF_VCPU) { + /* Restore normal Linux process memory map */ + if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) & + asid_version_mask(cpu))) + get_new_mmu_context(current->mm, cpu); + write_c0_entryhi(cpu_asid(cpu, current->mm)); + TLBMISS_HANDLER_SETUP_PGD(current->mm->pgd); + kvm_mips_resume_mm(cpu); + ehb(); + } + return 0; } +static void kvm_trap_emul_check_requests(struct kvm_vcpu *vcpu, int cpu, + bool reload_asid) +{ + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; + struct mm_struct *user_mm = &vcpu->arch.guest_user_mm; + struct mm_struct *mm; + int i; + + if (likely(!vcpu->requests)) + return; + + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) { + /* + * Both kernel & user GVA mappings must be invalidated. The + * caller is just about to check whether the ASID is stale + * anyway so no need to reload it here. + */ + kvm_mips_flush_gva_pt(kern_mm->pgd, KMF_GPA | KMF_KERN); + kvm_mips_flush_gva_pt(user_mm->pgd, KMF_GPA | KMF_USER); + for_each_possible_cpu(i) { + cpu_context(i, kern_mm) = 0; + cpu_context(i, user_mm) = 0; + } + + /* Generate new ASID for current mode */ + if (reload_asid) { + mm = KVM_GUEST_KERNEL_MODE(vcpu) ? kern_mm : user_mm; + get_new_mmu_context(mm, cpu); + htw_stop(); + write_c0_entryhi(cpu_asid(cpu, mm)); + TLBMISS_HANDLER_SETUP_PGD(mm->pgd); + htw_start(); + } + } +} + +/** + * kvm_trap_emul_gva_lockless_begin() - Begin lockless access to GVA space. + * @vcpu: VCPU pointer. + * + * Call before a GVA space access outside of guest mode, to ensure that + * asynchronous TLB flush requests are handled or delayed until completion of + * the GVA access (as indicated by a matching kvm_trap_emul_gva_lockless_end()). + * + * Should be called with IRQs already enabled. + */ +void kvm_trap_emul_gva_lockless_begin(struct kvm_vcpu *vcpu) +{ + /* We re-enable IRQs in kvm_trap_emul_gva_lockless_end() */ + WARN_ON_ONCE(irqs_disabled()); + + /* + * The caller is about to access the GVA space, so we set the mode to + * force TLB flush requests to send an IPI, and also disable IRQs to + * delay IPI handling until kvm_trap_emul_gva_lockless_end(). + */ + local_irq_disable(); + + /* + * Make sure the read of VCPU requests is not reordered ahead of the + * write to vcpu->mode, or we could miss a TLB flush request while + * the requester sees the VCPU as outside of guest mode and not needing + * an IPI. + */ + smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES); + + /* + * If a TLB flush has been requested (potentially while + * OUTSIDE_GUEST_MODE and assumed immediately effective), perform it + * before accessing the GVA space, and be sure to reload the ASID if + * necessary as it'll be immediately used. + * + * TLB flush requests after this check will trigger an IPI due to the + * mode change above, which will be delayed due to IRQs disabled. + */ + kvm_trap_emul_check_requests(vcpu, smp_processor_id(), true); +} + +/** + * kvm_trap_emul_gva_lockless_end() - End lockless access to GVA space. + * @vcpu: VCPU pointer. + * + * Called after a GVA space access outside of guest mode. Should have a matching + * call to kvm_trap_emul_gva_lockless_begin(). + */ +void kvm_trap_emul_gva_lockless_end(struct kvm_vcpu *vcpu) +{ + /* + * Make sure the write to vcpu->mode is not reordered in front of GVA + * accesses, or a TLB flush requester may not think it necessary to send + * an IPI. + */ + smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); + + /* + * Now that the access to GVA space is complete, its safe for pending + * TLB flush request IPIs to be handled (which indicates completion). + */ + local_irq_enable(); +} + +static void kvm_trap_emul_vcpu_reenter(struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mm_struct *kern_mm = &vcpu->arch.guest_kernel_mm; + struct mm_struct *user_mm = &vcpu->arch.guest_user_mm; + struct mm_struct *mm; + struct mips_coproc *cop0 = vcpu->arch.cop0; + int i, cpu = smp_processor_id(); + unsigned int gasid; + + /* + * No need to reload ASID, IRQs are disabled already so there's no rush, + * and we'll check if we need to regenerate below anyway before + * re-entering the guest. + */ + kvm_trap_emul_check_requests(vcpu, cpu, false); + + if (KVM_GUEST_KERNEL_MODE(vcpu)) { + mm = kern_mm; + } else { + mm = user_mm; + + /* + * Lazy host ASID regeneration / PT flush for guest user mode. + * If the guest ASID has changed since the last guest usermode + * execution, invalidate the stale TLB entries and flush GVA PT + * entries too. + */ + gasid = kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID; + if (gasid != vcpu->arch.last_user_gasid) { + kvm_mips_flush_gva_pt(user_mm->pgd, KMF_USER); + for_each_possible_cpu(i) + cpu_context(i, user_mm) = 0; + vcpu->arch.last_user_gasid = gasid; + } + } + + /* + * Check if ASID is stale. This may happen due to a TLB flush request or + * a lazy user MM invalidation. + */ + if ((cpu_context(cpu, mm) ^ asid_cache(cpu)) & + asid_version_mask(cpu)) + get_new_mmu_context(mm, cpu); +} + +static int kvm_trap_emul_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) +{ + int cpu = smp_processor_id(); + int r; + + /* Check if we have any exceptions/interrupts pending */ + kvm_mips_deliver_interrupts(vcpu, + kvm_read_c0_guest_cause(vcpu->arch.cop0)); + + kvm_trap_emul_vcpu_reenter(run, vcpu); + + /* + * We use user accessors to access guest memory, but we don't want to + * invoke Linux page faulting. + */ + pagefault_disable(); + + /* Disable hardware page table walking while in guest */ + htw_stop(); + + /* + * While in guest context we're in the guest's address space, not the + * host process address space, so we need to be careful not to confuse + * e.g. cache management IPIs. + */ + kvm_mips_suspend_mm(cpu); + + r = vcpu->arch.vcpu_run(run, vcpu); + + /* We may have migrated while handling guest exits */ + cpu = smp_processor_id(); + + /* Restore normal Linux process memory map */ + if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) & + asid_version_mask(cpu))) + get_new_mmu_context(current->mm, cpu); + write_c0_entryhi(cpu_asid(cpu, current->mm)); + TLBMISS_HANDLER_SETUP_PGD(current->mm->pgd); + kvm_mips_resume_mm(cpu); + + htw_start(); + + pagefault_enable(); + + return r; +} + static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { /* exit handlers */ .handle_cop_unusable = kvm_trap_emul_handle_cop_unusable, @@ -661,9 +1231,11 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .handle_fpe = kvm_trap_emul_handle_fpe, .handle_msa_disabled = kvm_trap_emul_handle_msa_disabled, - .vm_init = kvm_trap_emul_vm_init, .vcpu_init = kvm_trap_emul_vcpu_init, + .vcpu_uninit = kvm_trap_emul_vcpu_uninit, .vcpu_setup = kvm_trap_emul_vcpu_setup, + .flush_shadow_all = kvm_trap_emul_flush_shadow_all, + .flush_shadow_memslot = kvm_trap_emul_flush_shadow_memslot, .gva_to_gpa = kvm_trap_emul_gva_to_gpa_cb, .queue_timer_int = kvm_mips_queue_timer_int_cb, .dequeue_timer_int = kvm_mips_dequeue_timer_int_cb, @@ -675,8 +1247,10 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .copy_reg_indices = kvm_trap_emul_copy_reg_indices, .get_one_reg = kvm_trap_emul_get_one_reg, .set_one_reg = kvm_trap_emul_set_one_reg, - .vcpu_get_regs = kvm_trap_emul_vcpu_get_regs, - .vcpu_set_regs = kvm_trap_emul_vcpu_set_regs, + .vcpu_load = kvm_trap_emul_vcpu_load, + .vcpu_put = kvm_trap_emul_vcpu_put, + .vcpu_run = kvm_trap_emul_vcpu_run, + .vcpu_reenter = kvm_trap_emul_vcpu_reenter, }; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 0db010c..d9b48f5 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -22,6 +22,10 @@ #include <asm/book3s/64/mmu-hash.h> +/* Power architecture requires HPT is at least 256kiB, at most 64TiB */ +#define PPC_MIN_HPT_ORDER 18 +#define PPC_MAX_HPT_ORDER 46 + #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu) { @@ -356,6 +360,18 @@ extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); extern void kvmhv_rm_send_ipi(int cpu); +static inline unsigned long kvmppc_hpt_npte(struct kvm_hpt_info *hpt) +{ + /* HPTEs are 2**4 bytes long */ + return 1UL << (hpt->order - 4); +} + +static inline unsigned long kvmppc_hpt_mask(struct kvm_hpt_info *hpt) +{ + /* 128 (2**7) bytes in each HPTEG */ + return (1UL << (hpt->order - 7)) - 1; +} + #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index b2dbeac..7bba8f4 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -241,12 +241,24 @@ struct kvm_arch_memory_slot { #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ }; +struct kvm_hpt_info { + /* Host virtual (linear mapping) address of guest HPT */ + unsigned long virt; + /* Array of reverse mapping entries for each guest HPTE */ + struct revmap_entry *rev; + /* Guest HPT size is 2**(order) bytes */ + u32 order; + /* 1 if HPT allocated with CMA, 0 otherwise */ + int cma; +}; + +struct kvm_resize_hpt; + struct kvm_arch { unsigned int lpid; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE unsigned int tlb_sets; - unsigned long hpt_virt; - struct revmap_entry *revmap; + struct kvm_hpt_info hpt; atomic64_t mmio_update; unsigned int host_lpid; unsigned long host_lpcr; @@ -256,20 +268,17 @@ struct kvm_arch { unsigned long lpcr; unsigned long vrma_slb_v; int hpte_setup_done; - u32 hpt_order; atomic_t vcpus_running; u32 online_vcores; - unsigned long hpt_npte; - unsigned long hpt_mask; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; cpumask_t cpu_in_guest; - int hpt_cma_alloc; u8 radix; pgd_t *pgtable; u64 process_table; struct dentry *debugfs_dir; struct dentry *htab_dentry; + struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */ #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE struct mutex hpt_mutex; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 48c760f..dd11c4c 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -155,9 +155,10 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); -extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp); -extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp); -extern void kvmppc_free_hpt(struct kvm *kvm); +extern int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order); +extern void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info); +extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); +extern void kvmppc_free_hpt(struct kvm_hpt_info *info); extern long kvmppc_prepare_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem); extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, @@ -186,8 +187,8 @@ extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, unsigned long tce_value, unsigned long npages); extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba); -extern struct page *kvm_alloc_hpt(unsigned long nr_pages); -extern void kvm_release_hpt(struct page *page, unsigned long nr_pages); +extern struct page *kvm_alloc_hpt_cma(unsigned long nr_pages); +extern void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, @@ -214,6 +215,10 @@ extern void kvmppc_bookehv_exit(void); extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *); +extern long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt); +extern long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt); int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index cc0908b..4edbe4b 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -633,5 +633,7 @@ struct kvm_ppc_rmmu_info { #define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40) #define KVM_XICS_MASKED (1ULL << 41) #define KVM_XICS_PENDING (1ULL << 42) +#define KVM_XICS_PRESENTED (1ULL << 43) +#define KVM_XICS_QUEUED (1ULL << 44) #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index a2eb6d3..1992676 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -224,7 +224,8 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, ptem = kvmppc_mmu_book3s_32_get_ptem(sre, eaddr, primary); if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) { - printk(KERN_ERR "KVM: Can't copy data from 0x%lx!\n", ptegp); + printk_ratelimited(KERN_ERR + "KVM: Can't copy data from 0x%lx!\n", ptegp); goto no_page_found; } diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index b9131aa..7015357 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -265,7 +265,8 @@ do_second: goto no_page_found; if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) { - printk(KERN_ERR "KVM can't copy data from 0x%lx!\n", ptegp); + printk_ratelimited(KERN_ERR + "KVM: Can't copy data from 0x%lx!\n", ptegp); goto no_page_found; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 9df3d94..f3158fb 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -40,84 +40,101 @@ #include "trace_hv.h" -/* Power architecture requires HPT is at least 256kB */ -#define PPC_MIN_HPT_ORDER 18 +//#define DEBUG_RESIZE_HPT 1 + +#ifdef DEBUG_RESIZE_HPT +#define resize_hpt_debug(resize, ...) \ + do { \ + printk(KERN_DEBUG "RESIZE HPT %p: ", resize); \ + printk(__VA_ARGS__); \ + } while (0) +#else +#define resize_hpt_debug(resize, ...) \ + do { } while (0) +#endif static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, unsigned long *pte_idx_ret); + +struct kvm_resize_hpt { + /* These fields read-only after init */ + struct kvm *kvm; + struct work_struct work; + u32 order; + + /* These fields protected by kvm->lock */ + int error; + bool prepare_done; + + /* Private to the work thread, until prepare_done is true, + * then protected by kvm->resize_hpt_sem */ + struct kvm_hpt_info hpt; +}; + static void kvmppc_rmap_reset(struct kvm *kvm); -long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) +int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order) { unsigned long hpt = 0; - struct revmap_entry *rev; + int cma = 0; struct page *page = NULL; - long order = KVM_DEFAULT_HPT_ORDER; + struct revmap_entry *rev; + unsigned long npte; - if (htab_orderp) { - order = *htab_orderp; - if (order < PPC_MIN_HPT_ORDER) - order = PPC_MIN_HPT_ORDER; - } + if ((order < PPC_MIN_HPT_ORDER) || (order > PPC_MAX_HPT_ORDER)) + return -EINVAL; - kvm->arch.hpt_cma_alloc = 0; - page = kvm_alloc_hpt(1ul << (order - PAGE_SHIFT)); + page = kvm_alloc_hpt_cma(1ul << (order - PAGE_SHIFT)); if (page) { hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page)); memset((void *)hpt, 0, (1ul << order)); - kvm->arch.hpt_cma_alloc = 1; + cma = 1; } - /* Lastly try successively smaller sizes from the page allocator */ - /* Only do this if userspace didn't specify a size via ioctl */ - while (!hpt && order > PPC_MIN_HPT_ORDER && !htab_orderp) { - hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| - __GFP_NOWARN, order - PAGE_SHIFT); - if (!hpt) - --order; - } + if (!hpt) + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT + |__GFP_NOWARN, order - PAGE_SHIFT); if (!hpt) return -ENOMEM; - kvm->arch.hpt_virt = hpt; - kvm->arch.hpt_order = order; /* HPTEs are 2**4 bytes long */ - kvm->arch.hpt_npte = 1ul << (order - 4); - /* 128 (2**7) bytes in each HPTEG */ - kvm->arch.hpt_mask = (1ul << (order - 7)) - 1; - - atomic64_set(&kvm->arch.mmio_update, 0); + npte = 1ul << (order - 4); /* Allocate reverse map array */ - rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte); + rev = vmalloc(sizeof(struct revmap_entry) * npte); if (!rev) { - pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n"); - goto out_freehpt; + pr_err("kvmppc_allocate_hpt: Couldn't alloc reverse map array\n"); + if (cma) + kvm_free_hpt_cma(page, 1 << (order - PAGE_SHIFT)); + else + free_pages(hpt, order - PAGE_SHIFT); + return -ENOMEM; } - kvm->arch.revmap = rev; - kvm->arch.sdr1 = __pa(hpt) | (order - 18); - pr_info("KVM guest htab at %lx (order %ld), LPID %x\n", - hpt, order, kvm->arch.lpid); + info->order = order; + info->virt = hpt; + info->cma = cma; + info->rev = rev; - if (htab_orderp) - *htab_orderp = order; return 0; +} - out_freehpt: - if (kvm->arch.hpt_cma_alloc) - kvm_release_hpt(page, 1 << (order - PAGE_SHIFT)); - else - free_pages(hpt, order - PAGE_SHIFT); - return -ENOMEM; +void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info) +{ + atomic64_set(&kvm->arch.mmio_update, 0); + kvm->arch.hpt = *info; + kvm->arch.sdr1 = __pa(info->virt) | (info->order - 18); + + pr_debug("KVM guest htab at %lx (order %ld), LPID %x\n", + info->virt, (long)info->order, kvm->arch.lpid); } -long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) +long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) { long err = -EBUSY; - long order; + struct kvm_hpt_info info; if (kvm_is_radix(kvm)) return -EINVAL; @@ -132,36 +149,44 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) goto out; } } - if (kvm->arch.hpt_virt) { - order = kvm->arch.hpt_order; + if (kvm->arch.hpt.order == order) { + /* We already have a suitable HPT */ + /* Set the entire HPT to 0, i.e. invalid HPTEs */ - memset((void *)kvm->arch.hpt_virt, 0, 1ul << order); + memset((void *)kvm->arch.hpt.virt, 0, 1ul << order); /* * Reset all the reverse-mapping chains for all memslots */ kvmppc_rmap_reset(kvm); /* Ensure that each vcpu will flush its TLB on next entry. */ cpumask_setall(&kvm->arch.need_tlb_flush); - *htab_orderp = order; err = 0; - } else { - err = kvmppc_alloc_hpt(kvm, htab_orderp); - order = *htab_orderp; + goto out; } - out: + + if (kvm->arch.hpt.virt) + kvmppc_free_hpt(&kvm->arch.hpt); + + err = kvmppc_allocate_hpt(&info, order); + if (err < 0) + goto out; + kvmppc_set_hpt(kvm, &info); + +out: mutex_unlock(&kvm->lock); return err; } -void kvmppc_free_hpt(struct kvm *kvm) +void kvmppc_free_hpt(struct kvm_hpt_info *info) { - vfree(kvm->arch.revmap); - if (kvm->arch.hpt_cma_alloc) - kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt), - 1 << (kvm->arch.hpt_order - PAGE_SHIFT)); - else if (kvm->arch.hpt_virt) - free_pages(kvm->arch.hpt_virt, - kvm->arch.hpt_order - PAGE_SHIFT); + vfree(info->rev); + if (info->cma) + kvm_free_hpt_cma(virt_to_page(info->virt), + 1 << (info->order - PAGE_SHIFT)); + else if (info->virt) + free_pages(info->virt, info->order - PAGE_SHIFT); + info->virt = 0; + info->order = 0; } /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */ @@ -196,8 +221,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, if (npages > 1ul << (40 - porder)) npages = 1ul << (40 - porder); /* Can't use more than 1 HPTE per HPTEG */ - if (npages > kvm->arch.hpt_mask + 1) - npages = kvm->arch.hpt_mask + 1; + if (npages > kvmppc_hpt_mask(&kvm->arch.hpt) + 1) + npages = kvmppc_hpt_mask(&kvm->arch.hpt) + 1; hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) | HPTE_V_BOLTED | hpte0_pgsize_encoding(psize); @@ -207,7 +232,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, for (i = 0; i < npages; ++i) { addr = i << porder; /* can't use hpt_hash since va > 64 bits */ - hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask; + hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) + & kvmppc_hpt_mask(&kvm->arch.hpt); /* * We assume that the hash table is empty and no * vcpus are using it at this stage. Since we create @@ -340,11 +366,11 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, preempt_enable(); return -ENOENT; } - hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); + hptep = (__be64 *)(kvm->arch.hpt.virt + (index << 4)); v = orig_v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK; if (cpu_has_feature(CPU_FTR_ARCH_300)) v = hpte_new_to_old_v(v, be64_to_cpu(hptep[1])); - gr = kvm->arch.revmap[index].guest_rpte; + gr = kvm->arch.hpt.rev[index].guest_rpte; unlock_hpte(hptep, orig_v); preempt_enable(); @@ -485,8 +511,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } index = vcpu->arch.pgfault_index; - hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); - rev = &kvm->arch.revmap[index]; + hptep = (__be64 *)(kvm->arch.hpt.virt + (index << 4)); + rev = &kvm->arch.hpt.rev[index]; preempt_disable(); while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) cpu_relax(); @@ -745,13 +771,53 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, handler); } +/* Must be called with both HPTE and rmap locked */ +static void kvmppc_unmap_hpte(struct kvm *kvm, unsigned long i, + unsigned long *rmapp, unsigned long gfn) +{ + __be64 *hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); + struct revmap_entry *rev = kvm->arch.hpt.rev; + unsigned long j, h; + unsigned long ptel, psize, rcbits; + + j = rev[i].forw; + if (j == i) { + /* chain is now empty */ + *rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX); + } else { + /* remove i from chain */ + h = rev[i].back; + rev[h].forw = j; + rev[j].back = h; + rev[i].forw = rev[i].back = i; + *rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j; + } + + /* Now check and modify the HPTE */ + ptel = rev[i].guest_rpte; + psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel); + if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && + hpte_rpn(ptel, psize) == gfn) { + hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); + kvmppc_invalidate_hpte(kvm, hptep, i); + hptep[1] &= ~cpu_to_be64(HPTE_R_KEY_HI | HPTE_R_KEY_LO); + /* Harvest R and C */ + rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); + *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT; + if (rcbits & HPTE_R_C) + kvmppc_update_rmap_change(rmapp, psize); + if (rcbits & ~rev[i].guest_rpte) { + rev[i].guest_rpte = ptel | rcbits; + note_hpte_modification(kvm, &rev[i]); + } + } +} + static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { - struct revmap_entry *rev = kvm->arch.revmap; - unsigned long h, i, j; + unsigned long i; __be64 *hptep; - unsigned long ptel, psize, rcbits; unsigned long *rmapp; rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; @@ -768,7 +834,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, * rmap chain lock. */ i = *rmapp & KVMPPC_RMAP_INDEX; - hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) { /* unlock rmap before spinning on the HPTE lock */ unlock_rmap(rmapp); @@ -776,37 +842,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, cpu_relax(); continue; } - j = rev[i].forw; - if (j == i) { - /* chain is now empty */ - *rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX); - } else { - /* remove i from chain */ - h = rev[i].back; - rev[h].forw = j; - rev[j].back = h; - rev[i].forw = rev[i].back = i; - *rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j; - } - /* Now check and modify the HPTE */ - ptel = rev[i].guest_rpte; - psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel); - if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && - hpte_rpn(ptel, psize) == gfn) { - hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); - kvmppc_invalidate_hpte(kvm, hptep, i); - hptep[1] &= ~cpu_to_be64(HPTE_R_KEY_HI | HPTE_R_KEY_LO); - /* Harvest R and C */ - rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); - *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT; - if (rcbits & HPTE_R_C) - kvmppc_update_rmap_change(rmapp, psize); - if (rcbits & ~rev[i].guest_rpte) { - rev[i].guest_rpte = ptel | rcbits; - note_hpte_modification(kvm, &rev[i]); - } - } + kvmppc_unmap_hpte(kvm, i, rmapp, gfn); unlock_rmap(rmapp); __unlock_hpte(hptep, be64_to_cpu(hptep[0])); } @@ -860,7 +897,7 @@ void kvmppc_core_flush_memslot_hv(struct kvm *kvm, static int kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { - struct revmap_entry *rev = kvm->arch.revmap; + struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; __be64 *hptep; int ret = 0; @@ -880,7 +917,7 @@ static int kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, i = head = *rmapp & KVMPPC_RMAP_INDEX; do { - hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); j = rev[i].forw; /* If this HPTE isn't referenced, ignore it */ @@ -923,7 +960,7 @@ int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end) static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { - struct revmap_entry *rev = kvm->arch.revmap; + struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; unsigned long *hp; int ret = 1; @@ -940,7 +977,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, if (*rmapp & KVMPPC_RMAP_PRESENT) { i = head = *rmapp & KVMPPC_RMAP_INDEX; do { - hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4)); + hp = (unsigned long *)(kvm->arch.hpt.virt + (i << 4)); j = rev[i].forw; if (be64_to_cpu(hp[1]) & HPTE_R_R) goto out; @@ -980,7 +1017,7 @@ static int vcpus_running(struct kvm *kvm) */ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) { - struct revmap_entry *rev = kvm->arch.revmap; + struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; unsigned long n; unsigned long v, r; @@ -1005,7 +1042,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) i = head = *rmapp & KVMPPC_RMAP_INDEX; do { unsigned long hptep1; - hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); j = rev[i].forw; /* @@ -1172,6 +1209,363 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa, } /* + * HPT resizing + */ +static int resize_hpt_allocate(struct kvm_resize_hpt *resize) +{ + int rc; + + rc = kvmppc_allocate_hpt(&resize->hpt, resize->order); + if (rc < 0) + return rc; + + resize_hpt_debug(resize, "resize_hpt_allocate(): HPT @ 0x%lx\n", + resize->hpt.virt); + + return 0; +} + +static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, + unsigned long idx) +{ + struct kvm *kvm = resize->kvm; + struct kvm_hpt_info *old = &kvm->arch.hpt; + struct kvm_hpt_info *new = &resize->hpt; + unsigned long old_hash_mask = (1ULL << (old->order - 7)) - 1; + unsigned long new_hash_mask = (1ULL << (new->order - 7)) - 1; + __be64 *hptep, *new_hptep; + unsigned long vpte, rpte, guest_rpte; + int ret; + struct revmap_entry *rev; + unsigned long apsize, psize, avpn, pteg, hash; + unsigned long new_idx, new_pteg, replace_vpte; + + hptep = (__be64 *)(old->virt + (idx << 4)); + + /* Guest is stopped, so new HPTEs can't be added or faulted + * in, only unmapped or altered by host actions. So, it's + * safe to check this before we take the HPTE lock */ + vpte = be64_to_cpu(hptep[0]); + if (!(vpte & HPTE_V_VALID) && !(vpte & HPTE_V_ABSENT)) + return 0; /* nothing to do */ + + while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) + cpu_relax(); + + vpte = be64_to_cpu(hptep[0]); + + ret = 0; + if (!(vpte & HPTE_V_VALID) && !(vpte & HPTE_V_ABSENT)) + /* Nothing to do */ + goto out; + + /* Unmap */ + rev = &old->rev[idx]; + guest_rpte = rev->guest_rpte; + + ret = -EIO; + apsize = hpte_page_size(vpte, guest_rpte); + if (!apsize) + goto out; + + if (vpte & HPTE_V_VALID) { + unsigned long gfn = hpte_rpn(guest_rpte, apsize); + int srcu_idx = srcu_read_lock(&kvm->srcu); + struct kvm_memory_slot *memslot = + __gfn_to_memslot(kvm_memslots(kvm), gfn); + + if (memslot) { + unsigned long *rmapp; + rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; + + lock_rmap(rmapp); + kvmppc_unmap_hpte(kvm, idx, rmapp, gfn); + unlock_rmap(rmapp); + } + + srcu_read_unlock(&kvm->srcu, srcu_idx); + } + + /* Reload PTE after unmap */ + vpte = be64_to_cpu(hptep[0]); + + BUG_ON(vpte & HPTE_V_VALID); + BUG_ON(!(vpte & HPTE_V_ABSENT)); + + ret = 0; + if (!(vpte & HPTE_V_BOLTED)) + goto out; + + rpte = be64_to_cpu(hptep[1]); + psize = hpte_base_page_size(vpte, rpte); + avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23); + pteg = idx / HPTES_PER_GROUP; + if (vpte & HPTE_V_SECONDARY) + pteg = ~pteg; + + if (!(vpte & HPTE_V_1TB_SEG)) { + unsigned long offset, vsid; + + /* We only have 28 - 23 bits of offset in avpn */ + offset = (avpn & 0x1f) << 23; + vsid = avpn >> 5; + /* We can find more bits from the pteg value */ + if (psize < (1ULL << 23)) + offset |= ((vsid ^ pteg) & old_hash_mask) * psize; + + hash = vsid ^ (offset / psize); + } else { + unsigned long offset, vsid; + + /* We only have 40 - 23 bits of seg_off in avpn */ + offset = (avpn & 0x1ffff) << 23; + vsid = avpn >> 17; + if (psize < (1ULL << 23)) + offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize; + + hash = vsid ^ (vsid << 25) ^ (offset / psize); + } + + new_pteg = hash & new_hash_mask; + if (vpte & HPTE_V_SECONDARY) { + BUG_ON(~pteg != (hash & old_hash_mask)); + new_pteg = ~new_pteg; + } else { + BUG_ON(pteg != (hash & old_hash_mask)); + } + + new_idx = new_pteg * HPTES_PER_GROUP + (idx % HPTES_PER_GROUP); + new_hptep = (__be64 *)(new->virt + (new_idx << 4)); + + replace_vpte = be64_to_cpu(new_hptep[0]); + + if (replace_vpte & (HPTE_V_VALID | HPTE_V_ABSENT)) { + BUG_ON(new->order >= old->order); + + if (replace_vpte & HPTE_V_BOLTED) { + if (vpte & HPTE_V_BOLTED) + /* Bolted collision, nothing we can do */ + ret = -ENOSPC; + /* Discard the new HPTE */ + goto out; + } + + /* Discard the previous HPTE */ + } + + new_hptep[1] = cpu_to_be64(rpte); + new->rev[new_idx].guest_rpte = guest_rpte; + /* No need for a barrier, since new HPT isn't active */ + new_hptep[0] = cpu_to_be64(vpte); + unlock_hpte(new_hptep, vpte); + +out: + unlock_hpte(hptep, vpte); + return ret; +} + +static int resize_hpt_rehash(struct kvm_resize_hpt *resize) +{ + struct kvm *kvm = resize->kvm; + unsigned long i; + int rc; + + /* + * resize_hpt_rehash_hpte() doesn't handle the new-format HPTEs + * that POWER9 uses, and could well hit a BUG_ON on POWER9. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return -EIO; + for (i = 0; i < kvmppc_hpt_npte(&kvm->arch.hpt); i++) { + rc = resize_hpt_rehash_hpte(resize, i); + if (rc != 0) + return rc; + } + + return 0; +} + +static void resize_hpt_pivot(struct kvm_resize_hpt *resize) +{ + struct kvm *kvm = resize->kvm; + struct kvm_hpt_info hpt_tmp; + + /* Exchange the pending tables in the resize structure with + * the active tables */ + + resize_hpt_debug(resize, "resize_hpt_pivot()\n"); + + spin_lock(&kvm->mmu_lock); + asm volatile("ptesync" : : : "memory"); + + hpt_tmp = kvm->arch.hpt; + kvmppc_set_hpt(kvm, &resize->hpt); + resize->hpt = hpt_tmp; + + spin_unlock(&kvm->mmu_lock); + + synchronize_srcu_expedited(&kvm->srcu); + + resize_hpt_debug(resize, "resize_hpt_pivot() done\n"); +} + +static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize) +{ + BUG_ON(kvm->arch.resize_hpt != resize); + + if (!resize) + return; + + if (resize->hpt.virt) + kvmppc_free_hpt(&resize->hpt); + + kvm->arch.resize_hpt = NULL; + kfree(resize); +} + +static void resize_hpt_prepare_work(struct work_struct *work) +{ + struct kvm_resize_hpt *resize = container_of(work, + struct kvm_resize_hpt, + work); + struct kvm *kvm = resize->kvm; + int err; + + resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n", + resize->order); + + err = resize_hpt_allocate(resize); + + mutex_lock(&kvm->lock); + + resize->error = err; + resize->prepare_done = true; + + mutex_unlock(&kvm->lock); +} + +long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt) +{ + unsigned long flags = rhpt->flags; + unsigned long shift = rhpt->shift; + struct kvm_resize_hpt *resize; + int ret; + + if (flags != 0) + return -EINVAL; + + if (shift && ((shift < 18) || (shift > 46))) + return -EINVAL; + + mutex_lock(&kvm->lock); + + resize = kvm->arch.resize_hpt; + + if (resize) { + if (resize->order == shift) { + /* Suitable resize in progress */ + if (resize->prepare_done) { + ret = resize->error; + if (ret != 0) + resize_hpt_release(kvm, resize); + } else { + ret = 100; /* estimated time in ms */ + } + + goto out; + } + + /* not suitable, cancel it */ + resize_hpt_release(kvm, resize); + } + + ret = 0; + if (!shift) + goto out; /* nothing to do */ + + /* start new resize */ + + resize = kzalloc(sizeof(*resize), GFP_KERNEL); + resize->order = shift; + resize->kvm = kvm; + INIT_WORK(&resize->work, resize_hpt_prepare_work); + kvm->arch.resize_hpt = resize; + + schedule_work(&resize->work); + + ret = 100; /* estimated time in ms */ + +out: + mutex_unlock(&kvm->lock); + return ret; +} + +static void resize_hpt_boot_vcpu(void *opaque) +{ + /* Nothing to do, just force a KVM exit */ +} + +long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt) +{ + unsigned long flags = rhpt->flags; + unsigned long shift = rhpt->shift; + struct kvm_resize_hpt *resize; + long ret; + + if (flags != 0) + return -EINVAL; + + if (shift && ((shift < 18) || (shift > 46))) + return -EINVAL; + + mutex_lock(&kvm->lock); + + resize = kvm->arch.resize_hpt; + + /* This shouldn't be possible */ + ret = -EIO; + if (WARN_ON(!kvm->arch.hpte_setup_done)) + goto out_no_hpt; + + /* Stop VCPUs from running while we mess with the HPT */ + kvm->arch.hpte_setup_done = 0; + smp_mb(); + + /* Boot all CPUs out of the guest so they re-read + * hpte_setup_done */ + on_each_cpu(resize_hpt_boot_vcpu, NULL, 1); + + ret = -ENXIO; + if (!resize || (resize->order != shift)) + goto out; + + ret = -EBUSY; + if (!resize->prepare_done) + goto out; + + ret = resize->error; + if (ret != 0) + goto out; + + ret = resize_hpt_rehash(resize); + if (ret != 0) + goto out; + + resize_hpt_pivot(resize); + +out: + /* Let VCPUs run again */ + kvm->arch.hpte_setup_done = 1; + smp_mb(); +out_no_hpt: + resize_hpt_release(kvm, resize); + mutex_unlock(&kvm->lock); + return ret; +} + +/* * Functions for reading and writing the hash table via reads and * writes on a file descriptor. * @@ -1311,8 +1705,8 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, flags = ctx->flags; i = ctx->index; - hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); - revp = kvm->arch.revmap + i; + hptp = (__be64 *)(kvm->arch.hpt.virt + (i * HPTE_SIZE)); + revp = kvm->arch.hpt.rev + i; lbuf = (unsigned long __user *)buf; nb = 0; @@ -1327,7 +1721,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, /* Skip uninteresting entries, i.e. clean on not-first pass */ if (!first_pass) { - while (i < kvm->arch.hpt_npte && + while (i < kvmppc_hpt_npte(&kvm->arch.hpt) && !hpte_dirty(revp, hptp)) { ++i; hptp += 2; @@ -1337,7 +1731,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, hdr.index = i; /* Grab a series of valid entries */ - while (i < kvm->arch.hpt_npte && + while (i < kvmppc_hpt_npte(&kvm->arch.hpt) && hdr.n_valid < 0xffff && nb + HPTE_SIZE < count && record_hpte(flags, hptp, hpte, revp, 1, first_pass)) { @@ -1353,7 +1747,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, ++revp; } /* Now skip invalid entries while we can */ - while (i < kvm->arch.hpt_npte && + while (i < kvmppc_hpt_npte(&kvm->arch.hpt) && hdr.n_invalid < 0xffff && record_hpte(flags, hptp, hpte, revp, 0, first_pass)) { /* found an invalid entry */ @@ -1374,7 +1768,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, } /* Check if we've wrapped around the hash table */ - if (i >= kvm->arch.hpt_npte) { + if (i >= kvmppc_hpt_npte(&kvm->arch.hpt)) { i = 0; ctx->first_pass = 0; break; @@ -1433,11 +1827,11 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, err = -EINVAL; i = hdr.index; - if (i >= kvm->arch.hpt_npte || - i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte) + if (i >= kvmppc_hpt_npte(&kvm->arch.hpt) || + i + hdr.n_valid + hdr.n_invalid > kvmppc_hpt_npte(&kvm->arch.hpt)) break; - hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); + hptp = (__be64 *)(kvm->arch.hpt.virt + (i * HPTE_SIZE)); lbuf = (unsigned long __user *)buf; for (j = 0; j < hdr.n_valid; ++j) { __be64 hpte_v; @@ -1624,8 +2018,9 @@ static ssize_t debugfs_htab_read(struct file *file, char __user *buf, kvm = p->kvm; i = p->hpt_index; - hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); - for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) { + hptp = (__be64 *)(kvm->arch.hpt.virt + (i * HPTE_SIZE)); + for (; len != 0 && i < kvmppc_hpt_npte(&kvm->arch.hpt); + ++i, hptp += 2) { if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT))) continue; @@ -1635,7 +2030,7 @@ static ssize_t debugfs_htab_read(struct file *file, char __user *buf, cpu_relax(); v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK; hr = be64_to_cpu(hptp[1]); - gr = kvm->arch.revmap[i].guest_rpte; + gr = kvm->arch.hpt.rev[i].guest_rpte; unlock_hpte(hptp, v); preempt_enable(); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index c379ff5..491c5d8 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -171,6 +171,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, goto fail; } + ret = -ENOMEM; stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), GFP_KERNEL); if (!stt) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e4a7967..1e107ec 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -182,7 +182,8 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) ++vcpu->stat.halt_wakeup; } - if (kvmppc_ipi_thread(vcpu->arch.thread_cpu)) + cpu = READ_ONCE(vcpu->arch.thread_cpu); + if (cpu >= 0 && kvmppc_ipi_thread(cpu)) return; /* CPU points to the first thread of the core */ @@ -773,12 +774,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) } tvcpu->arch.prodded = 1; smp_mb(); - if (vcpu->arch.ceded) { - if (swait_active(&vcpu->wq)) { - swake_up(&vcpu->wq); - vcpu->stat.halt_wakeup++; - } - } + if (tvcpu->arch.ceded) + kvmppc_fast_vcpu_kick_hv(tvcpu); break; case H_CONFER: target = kvmppc_get_gpr(vcpu, 4); @@ -2665,7 +2662,8 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) int i; for_each_runnable_thread(i, vcpu, vc) { - if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) + if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded || + vcpu->arch.prodded) return 1; } @@ -2851,7 +2849,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) break; n_ceded = 0; for_each_runnable_thread(i, v, vc) { - if (!v->arch.pending_exceptions) + if (!v->arch.pending_exceptions && !v->arch.prodded) n_ceded += v->arch.ceded; else v->arch.ceded = 0; @@ -3199,12 +3197,23 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto out; /* another vcpu beat us to it */ /* Allocate hashed page table (if not done already) and reset it */ - if (!kvm->arch.hpt_virt) { - err = kvmppc_alloc_hpt(kvm, NULL); - if (err) { + if (!kvm->arch.hpt.virt) { + int order = KVM_DEFAULT_HPT_ORDER; + struct kvm_hpt_info info; + + err = kvmppc_allocate_hpt(&info, order); + /* If we get here, it means userspace didn't specify a + * size explicitly. So, try successively smaller + * sizes if the default failed. */ + while ((err == -ENOMEM) && --order >= PPC_MIN_HPT_ORDER) + err = kvmppc_allocate_hpt(&info, order); + + if (err < 0) { pr_err("KVM: Couldn't alloc HPT\n"); goto out; } + + kvmppc_set_hpt(kvm, &info); } /* Look up the memslot for guest physical address 0 */ @@ -3413,6 +3422,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.lpcr = lpcr; + /* Initialization for future HPT resizes */ + kvm->arch.resize_hpt = NULL; + /* * Work out how many sets the TLB has, for the use of * the TLB invalidation loop in book3s_hv_rmhandlers.S. @@ -3469,7 +3481,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (kvm_is_radix(kvm)) kvmppc_free_radix(kvm); else - kvmppc_free_hpt(kvm); + kvmppc_free_hpt(&kvm->arch.hpt); kvmppc_free_pimap(kvm); } @@ -3695,12 +3707,9 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, r = -EFAULT; if (get_user(htab_order, (u32 __user *)argp)) break; - r = kvmppc_alloc_reset_hpt(kvm, &htab_order); + r = kvmppc_alloc_reset_hpt(kvm, htab_order); if (r) break; - r = -EFAULT; - if (put_user(htab_order, (u32 __user *)argp)) - break; r = 0; break; } @@ -3715,6 +3724,28 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, break; } + case KVM_PPC_RESIZE_HPT_PREPARE: { + struct kvm_ppc_resize_hpt rhpt; + + r = -EFAULT; + if (copy_from_user(&rhpt, argp, sizeof(rhpt))) + break; + + r = kvm_vm_ioctl_resize_hpt_prepare(kvm, &rhpt); + break; + } + + case KVM_PPC_RESIZE_HPT_COMMIT: { + struct kvm_ppc_resize_hpt rhpt; + + r = -EFAULT; + if (copy_from_user(&rhpt, argp, sizeof(rhpt))) + break; + + r = kvm_vm_ioctl_resize_hpt_commit(kvm, &rhpt); + break; + } + default: r = -ENOTTY; } diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 2f69fbc..c42a7e6 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -52,19 +52,19 @@ static int __init early_parse_kvm_cma_resv(char *p) } early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv); -struct page *kvm_alloc_hpt(unsigned long nr_pages) +struct page *kvm_alloc_hpt_cma(unsigned long nr_pages) { VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES)); } -EXPORT_SYMBOL_GPL(kvm_alloc_hpt); +EXPORT_SYMBOL_GPL(kvm_alloc_hpt_cma); -void kvm_release_hpt(struct page *page, unsigned long nr_pages) +void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages) { cma_release(kvm_cma, page, nr_pages); } -EXPORT_SYMBOL_GPL(kvm_release_hpt); +EXPORT_SYMBOL_GPL(kvm_free_hpt_cma); /** * kvm_cma_reserve() - reserve area for kvm hash pagetable diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index b095afc..6fca970 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -86,10 +86,10 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, if (*rmap & KVMPPC_RMAP_PRESENT) { i = *rmap & KVMPPC_RMAP_INDEX; - head = &kvm->arch.revmap[i]; + head = &kvm->arch.hpt.rev[i]; if (realmode) head = real_vmalloc_addr(head); - tail = &kvm->arch.revmap[head->back]; + tail = &kvm->arch.hpt.rev[head->back]; if (realmode) tail = real_vmalloc_addr(tail); rev->forw = i; @@ -154,8 +154,8 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index, lock_rmap(rmap); head = *rmap & KVMPPC_RMAP_INDEX; - next = real_vmalloc_addr(&kvm->arch.revmap[rev->forw]); - prev = real_vmalloc_addr(&kvm->arch.revmap[rev->back]); + next = real_vmalloc_addr(&kvm->arch.hpt.rev[rev->forw]); + prev = real_vmalloc_addr(&kvm->arch.hpt.rev[rev->back]); next->back = rev->back; prev->forw = rev->forw; if (head == pte_index) { @@ -292,11 +292,11 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, /* Find and lock the HPTEG slot to use */ do_insert: - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; if (likely((flags & H_EXACT) == 0)) { pte_index &= ~7UL; - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); for (i = 0; i < 8; ++i) { if ((be64_to_cpu(*hpte) & HPTE_V_VALID) == 0 && try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID | @@ -327,7 +327,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } pte_index += i; } else { - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID | HPTE_V_ABSENT)) { /* Lock the slot and check again */ @@ -344,7 +344,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } /* Save away the guest's idea of the second HPTE dword */ - rev = &kvm->arch.revmap[pte_index]; + rev = &kvm->arch.hpt.rev[pte_index]; if (realmode) rev = real_vmalloc_addr(rev); if (rev) { @@ -469,9 +469,9 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); pte = orig_pte = be64_to_cpu(hpte[0]); @@ -487,7 +487,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, return H_NOT_FOUND; } - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); v = pte & ~HPTE_V_HVLOCK; if (v & HPTE_V_VALID) { hpte[0] &= ~cpu_to_be64(HPTE_V_VALID); @@ -557,13 +557,13 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) break; } if (req != 1 || flags == 3 || - pte_index >= kvm->arch.hpt_npte) { + pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) { /* parameter error */ args[j] = ((0xa0 | flags) << 56) + pte_index; ret = H_PARAMETER; break; } - hp = (__be64 *) (kvm->arch.hpt_virt + (pte_index << 4)); + hp = (__be64 *) (kvm->arch.hpt.virt + (pte_index << 4)); /* to avoid deadlock, don't spin except for first */ if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) { if (n) @@ -600,7 +600,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) } args[j] = ((0x80 | flags) << 56) + pte_index; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); note_hpte_modification(kvm, rev); if (!(hp0 & HPTE_V_VALID)) { @@ -657,10 +657,10 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); v = pte_v = be64_to_cpu(hpte[0]); @@ -680,7 +680,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, /* Update guest view of 2nd HPTE dword */ mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_HI | HPTE_R_KEY_LO; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); if (rev) { r = (rev->guest_rpte & ~mask) | bits; rev->guest_rpte = r; @@ -728,15 +728,15 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; if (flags & H_READ_4) { pte_index &= ~3; n = 4; } - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); for (i = 0; i < n; ++i, ++pte_index) { - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK; r = be64_to_cpu(hpte[1]); if (cpu_has_feature(CPU_FTR_ARCH_300)) { @@ -769,11 +769,11 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); v = be64_to_cpu(hpte[0]); @@ -817,11 +817,11 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); v = be64_to_cpu(hpte[0]); @@ -970,7 +970,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, somask = (1UL << 28) - 1; vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT; } - hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask; + hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvmppc_hpt_mask(&kvm->arch.hpt); avpn = slb_v & ~(somask >> 16); /* also includes B */ avpn |= (eaddr & somask) >> 16; @@ -981,7 +981,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, val |= avpn; for (;;) { - hpte = (__be64 *)(kvm->arch.hpt_virt + (hash << 7)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (hash << 7)); for (i = 0; i < 16; i += 2) { /* Read the PTE racily */ @@ -1017,7 +1017,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, if (val & HPTE_V_SECONDARY) break; val |= HPTE_V_SECONDARY; - hash = hash ^ kvm->arch.hpt_mask; + hash = hash ^ kvmppc_hpt_mask(&kvm->arch.hpt); } return -1; } @@ -1066,14 +1066,14 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, return status; /* there really was no HPTE */ return 0; /* for prot fault, HPTE disappeared */ } - hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (index << 4)); v = orig_v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK; r = be64_to_cpu(hpte[1]); if (cpu_has_feature(CPU_FTR_ARCH_300)) { v = hpte_new_to_old_v(v, r); r = hpte_new_to_old_r(r); } - rev = real_vmalloc_addr(&kvm->arch.revmap[index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[index]); gr = rev->guest_rpte; unlock_hpte(hpte, orig_v); diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 29f43ed..e78542d 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -35,7 +35,7 @@ int kvm_irq_bypass = 1; EXPORT_SYMBOL(kvm_irq_bypass); static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq); + u32 new_irq, bool check_resend); static int xics_opal_set_server(unsigned int hw_irq, int server_cpu); /* -- ICS routines -- */ @@ -44,20 +44,12 @@ static void ics_rm_check_resend(struct kvmppc_xics *xics, { int i; - arch_spin_lock(&ics->lock); - for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *state = &ics->irq_state[i]; - - if (!state->resend) - continue; - - arch_spin_unlock(&ics->lock); - icp_rm_deliver_irq(xics, icp, state->number); - arch_spin_lock(&ics->lock); + if (state->resend) + icp_rm_deliver_irq(xics, icp, state->number, true); } - arch_spin_unlock(&ics->lock); } /* -- ICP routines -- */ @@ -288,7 +280,7 @@ static bool icp_rm_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority, } static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq) + u32 new_irq, bool check_resend) { struct ics_irq_state *state; struct kvmppc_ics *ics; @@ -333,6 +325,10 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, } } + if (check_resend) + if (!state->resend) + goto out; + /* Clear the resend bit of that interrupt */ state->resend = 0; @@ -378,7 +374,9 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ if (reject && reject != XICS_IPI) { arch_spin_unlock(&ics->lock); + icp->n_reject++; new_irq = reject; + check_resend = 0; goto again; } } else { @@ -386,10 +384,16 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * We failed to deliver the interrupt we need to set the * resend map bit and mark the ICS state as needing a resend */ - set_bit(ics->icsid, icp->resend_map); state->resend = 1; /* + * Make sure when checking resend, we don't miss the resend + * if resend_map bit is seen and cleared. + */ + smp_wmb(); + set_bit(ics->icsid, icp->resend_map); + + /* * If the need_resend flag got cleared in the ICP some time * between icp_rm_try_to_deliver() atomic update and now, then * we know it might have missed the resend_map bit. So we @@ -397,7 +401,9 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ smp_mb(); if (!icp->state.need_resend) { + state->resend = 0; arch_spin_unlock(&ics->lock); + check_resend = 0; goto again; } } @@ -592,7 +598,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, /* Handle reject in real mode */ if (reject && reject != XICS_IPI) { this_icp->n_reject++; - icp_rm_deliver_irq(xics, icp, reject); + icp_rm_deliver_irq(xics, icp, reject, false); } /* Handle resends in real mode */ @@ -660,59 +666,45 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) */ if (reject && reject != XICS_IPI) { icp->n_reject++; - icp_rm_deliver_irq(xics, icp, reject); + icp_rm_deliver_irq(xics, icp, reject, false); } bail: return check_too_hard(xics, icp); } -int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +static int ics_rm_eoi(struct kvm_vcpu *vcpu, u32 irq) { struct kvmppc_xics *xics = vcpu->kvm->arch.xics; struct kvmppc_icp *icp = vcpu->arch.icp; struct kvmppc_ics *ics; struct ics_irq_state *state; - u32 irq = xirr & 0x00ffffff; u16 src; - - if (!xics || !xics->real_mode) - return H_TOO_HARD; + u32 pq_old, pq_new; /* - * ICP State: EOI + * ICS EOI handling: For LSI, if P bit is still set, we need to + * resend it. * - * Note: If EOI is incorrectly used by SW to lower the CPPR - * value (ie more favored), we do not check for rejection of - * a pending interrupt, this is a SW error and PAPR sepcifies - * that we don't have to deal with it. - * - * The sending of an EOI to the ICS is handled after the - * CPPR update - * - * ICP State: Down_CPPR which we handle - * in a separate function as it's shared with H_CPPR. + * For MSI, we move Q bit into P (and clear Q). If it is set, + * resend it. */ - icp_rm_down_cppr(xics, icp, xirr >> 24); - /* IPIs have no EOI */ - if (irq == XICS_IPI) - goto bail; - /* - * EOI handling: If the interrupt is still asserted, we need to - * resend it. We can take a lockless "peek" at the ICS state here. - * - * "Message" interrupts will never have "asserted" set - */ ics = kvmppc_xics_find_ics(xics, irq, &src); if (!ics) goto bail; + state = &ics->irq_state[src]; - /* Still asserted, resend it */ - if (state->asserted) { - icp->n_reject++; - icp_rm_deliver_irq(xics, icp, irq); - } + if (state->lsi) + pq_new = state->pq_state; + else + do { + pq_old = state->pq_state; + pq_new = pq_old >> 1; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + if (pq_new & PQ_PRESENTED) + icp_rm_deliver_irq(xics, NULL, irq, false); if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) { icp->rm_action |= XICS_RM_NOTIFY_EOI; @@ -733,10 +725,43 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) state->intr_cpu = -1; } } + bail: return check_too_hard(xics, icp); } +int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 irq = xirr & 0x00ffffff; + + if (!xics || !xics->real_mode) + return H_TOO_HARD; + + /* + * ICP State: EOI + * + * Note: If EOI is incorrectly used by SW to lower the CPPR + * value (ie more favored), we do not check for rejection of + * a pending interrupt, this is a SW error and PAPR specifies + * that we don't have to deal with it. + * + * The sending of an EOI to the ICS is handled after the + * CPPR update + * + * ICP State: Down_CPPR which we handle + * in a separate function as it's shared with H_CPPR. + */ + icp_rm_down_cppr(xics, icp, xirr >> 24); + + /* IPIs have no EOI */ + if (irq == XICS_IPI) + return check_too_hard(xics, icp); + + return ics_rm_eoi(vcpu, irq); +} + unsigned long eoi_rc; static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again) @@ -823,14 +848,33 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, { struct kvmppc_xics *xics; struct kvmppc_icp *icp; + struct kvmppc_ics *ics; + struct ics_irq_state *state; u32 irq; + u16 src; + u32 pq_old, pq_new; irq = irq_map->v_hwirq; xics = vcpu->kvm->arch.xics; icp = vcpu->arch.icp; kvmppc_rm_handle_irq_desc(irq_map->desc); - icp_rm_deliver_irq(xics, icp, irq); + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + return 2; + + state = &ics->irq_state[src]; + + /* only MSIs register bypass producers, so it must be MSI here */ + do { + pq_old = state->pq_state; + pq_new = ((pq_old << 1) & 3) | PQ_PRESENTED; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + /* Test P=1, Q=0, this is the only case where we present */ + if (pq_new == PQ_PRESENTED) + icp_rm_deliver_irq(xics, icp, irq, false); /* EOI the interrupt */ icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr, diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 1482961..d4dfc0c 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -902,6 +902,69 @@ static void kvmppc_clear_debug(struct kvm_vcpu *vcpu) } } +static int kvmppc_exit_pr_progint(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int exit_nr) +{ + enum emulation_result er; + ulong flags; + u32 last_inst; + int emul, r; + + /* + * shadow_srr1 only contains valid flags if we came here via a program + * exception. The other exceptions (emulation assist, FP unavailable, + * etc.) do not provide flags in SRR1, so use an illegal-instruction + * exception when injecting a program interrupt into the guest. + */ + if (exit_nr == BOOK3S_INTERRUPT_PROGRAM) + flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; + else + flags = SRR1_PROGILL; + + emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); + if (emul != EMULATE_DONE) + return RESUME_GUEST; + + if (kvmppc_get_msr(vcpu) & MSR_PR) { +#ifdef EXIT_DEBUG + pr_info("Userspace triggered 0x700 exception at\n 0x%lx (0x%x)\n", + kvmppc_get_pc(vcpu), last_inst); +#endif + if ((last_inst & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { + kvmppc_core_queue_program(vcpu, flags); + return RESUME_GUEST; + } + } + + vcpu->stat.emulated_inst_exits++; + er = kvmppc_emulate_instruction(run, vcpu); + switch (er) { + case EMULATE_DONE: + r = RESUME_GUEST_NV; + break; + case EMULATE_AGAIN: + r = RESUME_GUEST; + break; + case EMULATE_FAIL: + pr_crit("%s: emulation at %lx failed (%08x)\n", + __func__, kvmppc_get_pc(vcpu), last_inst); + kvmppc_core_queue_program(vcpu, flags); + r = RESUME_GUEST; + break; + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST_NV; + break; + case EMULATE_EXIT_USER: + r = RESUME_HOST_NV; + break; + default: + BUG(); + } + + return r; +} + int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int exit_nr) { @@ -1044,71 +1107,8 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, break; case BOOK3S_INTERRUPT_PROGRAM: case BOOK3S_INTERRUPT_H_EMUL_ASSIST: - { - enum emulation_result er; - ulong flags; - u32 last_inst; - int emul; - -program_interrupt: - /* - * shadow_srr1 only contains valid flags if we came here via - * a program exception. The other exceptions (emulation assist, - * FP unavailable, etc.) do not provide flags in SRR1, so use - * an illegal-instruction exception when injecting a program - * interrupt into the guest. - */ - if (exit_nr == BOOK3S_INTERRUPT_PROGRAM) - flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; - else - flags = SRR1_PROGILL; - - emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); - if (emul != EMULATE_DONE) { - r = RESUME_GUEST; - break; - } - - if (kvmppc_get_msr(vcpu) & MSR_PR) { -#ifdef EXIT_DEBUG - pr_info("Userspace triggered 0x700 exception at\n 0x%lx (0x%x)\n", - kvmppc_get_pc(vcpu), last_inst); -#endif - if ((last_inst & 0xff0007ff) != - (INS_DCBZ & 0xfffffff7)) { - kvmppc_core_queue_program(vcpu, flags); - r = RESUME_GUEST; - break; - } - } - - vcpu->stat.emulated_inst_exits++; - er = kvmppc_emulate_instruction(run, vcpu); - switch (er) { - case EMULATE_DONE: - r = RESUME_GUEST_NV; - break; - case EMULATE_AGAIN: - r = RESUME_GUEST; - break; - case EMULATE_FAIL: - printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", - __func__, kvmppc_get_pc(vcpu), last_inst); - kvmppc_core_queue_program(vcpu, flags); - r = RESUME_GUEST; - break; - case EMULATE_DO_MMIO: - run->exit_reason = KVM_EXIT_MMIO; - r = RESUME_HOST_NV; - break; - case EMULATE_EXIT_USER: - r = RESUME_HOST_NV; - break; - default: - BUG(); - } + r = kvmppc_exit_pr_progint(run, vcpu, exit_nr); break; - } case BOOK3S_INTERRUPT_SYSCALL: { u32 last_sc; @@ -1185,7 +1185,7 @@ program_interrupt: emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); if (emul == EMULATE_DONE) - goto program_interrupt; + r = kvmppc_exit_pr_progint(run, vcpu, exit_nr); else r = RESUME_GUEST; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 20dff10..e48803e 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -63,7 +63,7 @@ /* -- ICS routines -- */ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq); + u32 new_irq, bool check_resend); /* * Return value ideally indicates how the interrupt was handled, but no @@ -75,6 +75,7 @@ static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level) struct ics_irq_state *state; struct kvmppc_ics *ics; u16 src; + u32 pq_old, pq_new; XICS_DBG("ics deliver %#x (level: %d)\n", irq, level); @@ -87,25 +88,41 @@ static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level) if (!state->exists) return -EINVAL; + if (level == KVM_INTERRUPT_SET_LEVEL || level == KVM_INTERRUPT_SET) + level = 1; + else if (level == KVM_INTERRUPT_UNSET) + level = 0; /* - * We set state->asserted locklessly. This should be fine as - * we are the only setter, thus concurrent access is undefined - * to begin with. + * Take other values the same as 1, consistent with original code. + * maybe WARN here? */ - if ((level == 1 && state->lsi) || level == KVM_INTERRUPT_SET_LEVEL) - state->asserted = 1; - else if (level == 0 || level == KVM_INTERRUPT_UNSET) { - state->asserted = 0; + + if (!state->lsi && level == 0) /* noop for MSI */ return 0; - } + + do { + pq_old = state->pq_state; + if (state->lsi) { + if (level) { + if (pq_old & PQ_PRESENTED) + /* Setting already set LSI ... */ + return 0; + + pq_new = PQ_PRESENTED; + } else + pq_new = 0; + } else + pq_new = ((pq_old << 1) & 3) | PQ_PRESENTED; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + /* Test P=1, Q=0, this is the only case where we present */ + if (pq_new == PQ_PRESENTED) + icp_deliver_irq(xics, NULL, irq, false); /* Record which CPU this arrived on for passed-through interrupts */ if (state->host_irq) state->intr_cpu = raw_smp_processor_id(); - /* Attempt delivery */ - icp_deliver_irq(xics, NULL, irq); - return 0; } @@ -114,29 +131,14 @@ static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics, { int i; - unsigned long flags; - - local_irq_save(flags); - arch_spin_lock(&ics->lock); - for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *state = &ics->irq_state[i]; - - if (!state->resend) - continue; - - XICS_DBG("resend %#x prio %#x\n", state->number, - state->priority); - - arch_spin_unlock(&ics->lock); - local_irq_restore(flags); - icp_deliver_irq(xics, icp, state->number); - local_irq_save(flags); - arch_spin_lock(&ics->lock); + if (state->resend) { + XICS_DBG("resend %#x prio %#x\n", state->number, + state->priority); + icp_deliver_irq(xics, icp, state->number, true); + } } - - arch_spin_unlock(&ics->lock); - local_irq_restore(flags); } static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, @@ -155,6 +157,7 @@ static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, deliver = false; if ((state->masked_pending || state->resend) && priority != MASKED) { state->masked_pending = 0; + state->resend = 0; deliver = true; } @@ -189,7 +192,7 @@ int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority) state->masked_pending, state->resend); if (write_xive(xics, ics, state, server, priority, priority)) - icp_deliver_irq(xics, icp, irq); + icp_deliver_irq(xics, icp, irq, false); return 0; } @@ -242,7 +245,7 @@ int kvmppc_xics_int_on(struct kvm *kvm, u32 irq) if (write_xive(xics, ics, state, state->server, state->saved_priority, state->saved_priority)) - icp_deliver_irq(xics, icp, irq); + icp_deliver_irq(xics, icp, irq, false); return 0; } @@ -376,7 +379,7 @@ static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority, } static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq) + u32 new_irq, bool check_resend) { struct ics_irq_state *state; struct kvmppc_ics *ics; @@ -422,6 +425,10 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, } } + if (check_resend) + if (!state->resend) + goto out; + /* Clear the resend bit of that interrupt */ state->resend = 0; @@ -470,6 +477,7 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, arch_spin_unlock(&ics->lock); local_irq_restore(flags); new_irq = reject; + check_resend = 0; goto again; } } else { @@ -477,10 +485,16 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * We failed to deliver the interrupt we need to set the * resend map bit and mark the ICS state as needing a resend */ - set_bit(ics->icsid, icp->resend_map); state->resend = 1; /* + * Make sure when checking resend, we don't miss the resend + * if resend_map bit is seen and cleared. + */ + smp_wmb(); + set_bit(ics->icsid, icp->resend_map); + + /* * If the need_resend flag got cleared in the ICP some time * between icp_try_to_deliver() atomic update and now, then * we know it might have missed the resend_map bit. So we @@ -488,8 +502,10 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ smp_mb(); if (!icp->state.need_resend) { + state->resend = 0; arch_spin_unlock(&ics->lock); local_irq_restore(flags); + check_resend = 0; goto again; } } @@ -681,7 +697,7 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, /* Handle reject */ if (reject && reject != XICS_IPI) - icp_deliver_irq(xics, icp, reject); + icp_deliver_irq(xics, icp, reject, false); /* Handle resend */ if (resend) @@ -761,17 +777,54 @@ static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) * attempt (see comments in icp_deliver_irq). */ if (reject && reject != XICS_IPI) - icp_deliver_irq(xics, icp, reject); + icp_deliver_irq(xics, icp, reject, false); } -static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +static int ics_eoi(struct kvm_vcpu *vcpu, u32 irq) { struct kvmppc_xics *xics = vcpu->kvm->arch.xics; struct kvmppc_icp *icp = vcpu->arch.icp; struct kvmppc_ics *ics; struct ics_irq_state *state; - u32 irq = xirr & 0x00ffffff; u16 src; + u32 pq_old, pq_new; + + /* + * ICS EOI handling: For LSI, if P bit is still set, we need to + * resend it. + * + * For MSI, we move Q bit into P (and clear Q). If it is set, + * resend it. + */ + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) { + XICS_DBG("ios_eoi: IRQ 0x%06x not found !\n", irq); + return H_PARAMETER; + } + state = &ics->irq_state[src]; + + if (state->lsi) + pq_new = state->pq_state; + else + do { + pq_old = state->pq_state; + pq_new = pq_old >> 1; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + if (pq_new & PQ_PRESENTED) + icp_deliver_irq(xics, icp, irq, false); + + kvm_notify_acked_irq(vcpu->kvm, 0, irq); + + return H_SUCCESS; +} + +static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 irq = xirr & 0x00ffffff; XICS_DBG("h_eoi vcpu %d eoi %#lx\n", vcpu->vcpu_id, xirr); @@ -794,26 +847,8 @@ static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) /* IPIs have no EOI */ if (irq == XICS_IPI) return H_SUCCESS; - /* - * EOI handling: If the interrupt is still asserted, we need to - * resend it. We can take a lockless "peek" at the ICS state here. - * - * "Message" interrupts will never have "asserted" set - */ - ics = kvmppc_xics_find_ics(xics, irq, &src); - if (!ics) { - XICS_DBG("h_eoi: IRQ 0x%06x not found !\n", irq); - return H_PARAMETER; - } - state = &ics->irq_state[src]; - /* Still asserted, resend it */ - if (state->asserted) - icp_deliver_irq(xics, icp, irq); - - kvm_notify_acked_irq(vcpu->kvm, 0, irq); - - return H_SUCCESS; + return ics_eoi(vcpu, irq); } int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) @@ -832,10 +867,6 @@ int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) icp->n_rm_check_resend++; icp_check_resend(xics, icp->rm_resend_icp); } - if (icp->rm_action & XICS_RM_REJECT) { - icp->n_rm_reject++; - icp_deliver_irq(xics, icp, icp->rm_reject); - } if (icp->rm_action & XICS_RM_NOTIFY_EOI) { icp->n_rm_notify_eoi++; kvm_notify_acked_irq(vcpu->kvm, 0, icp->rm_eoied_irq); @@ -920,7 +951,7 @@ static int xics_debug_show(struct seq_file *m, void *private) int icsid, i; unsigned long flags; unsigned long t_rm_kick_vcpu, t_rm_check_resend; - unsigned long t_rm_reject, t_rm_notify_eoi; + unsigned long t_rm_notify_eoi; unsigned long t_reject, t_check_resend; if (!kvm) @@ -929,7 +960,6 @@ static int xics_debug_show(struct seq_file *m, void *private) t_rm_kick_vcpu = 0; t_rm_notify_eoi = 0; t_rm_check_resend = 0; - t_rm_reject = 0; t_check_resend = 0; t_reject = 0; @@ -952,14 +982,13 @@ static int xics_debug_show(struct seq_file *m, void *private) t_rm_kick_vcpu += icp->n_rm_kick_vcpu; t_rm_notify_eoi += icp->n_rm_notify_eoi; t_rm_check_resend += icp->n_rm_check_resend; - t_rm_reject += icp->n_rm_reject; t_check_resend += icp->n_check_resend; t_reject += icp->n_reject; } - seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu reject=%lu notify_eoi=%lu\n", + seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu notify_eoi=%lu\n", t_rm_kick_vcpu, t_rm_check_resend, - t_rm_reject, t_rm_notify_eoi); + t_rm_notify_eoi); seq_printf(m, "ICP Real Mode totals: check_resend=%lu resend=%lu\n", t_check_resend, t_reject); for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) { @@ -977,9 +1006,9 @@ static int xics_debug_show(struct seq_file *m, void *private) for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *irq = &ics->irq_state[i]; - seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x asserted %d resend %d masked pending %d\n", + seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x pq_state %d resend %d masked pending %d\n", irq->number, irq->server, irq->priority, - irq->saved_priority, irq->asserted, + irq->saved_priority, irq->pq_state, irq->resend, irq->masked_pending); } @@ -1198,10 +1227,17 @@ static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr) val |= prio << KVM_XICS_PRIORITY_SHIFT; if (irqp->lsi) { val |= KVM_XICS_LEVEL_SENSITIVE; - if (irqp->asserted) + if (irqp->pq_state & PQ_PRESENTED) val |= KVM_XICS_PENDING; } else if (irqp->masked_pending || irqp->resend) val |= KVM_XICS_PENDING; + + if (irqp->pq_state & PQ_PRESENTED) + val |= KVM_XICS_PRESENTED; + + if (irqp->pq_state & PQ_QUEUED) + val |= KVM_XICS_QUEUED; + ret = 0; } arch_spin_unlock(&ics->lock); @@ -1253,18 +1289,20 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr) irqp->resend = 0; irqp->masked_pending = 0; irqp->lsi = 0; - irqp->asserted = 0; - if (val & KVM_XICS_LEVEL_SENSITIVE) { + irqp->pq_state = 0; + if (val & KVM_XICS_LEVEL_SENSITIVE) irqp->lsi = 1; - if (val & KVM_XICS_PENDING) - irqp->asserted = 1; - } + /* If PENDING, set P in case P is not saved because of old code */ + if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING) + irqp->pq_state |= PQ_PRESENTED; + if (val & KVM_XICS_QUEUED) + irqp->pq_state |= PQ_QUEUED; irqp->exists = 1; arch_spin_unlock(&ics->lock); local_irq_restore(flags); if (val & KVM_XICS_PENDING) - icp_deliver_irq(xics, NULL, irqp->number); + icp_deliver_irq(xics, NULL, irqp->number, false); return 0; } diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 2a50320..ec5474c 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -31,16 +31,19 @@ /* Priority value to use for disabling an interrupt */ #define MASKED 0xff +#define PQ_PRESENTED 1 +#define PQ_QUEUED 2 + /* State for one irq source */ struct ics_irq_state { u32 number; u32 server; + u32 pq_state; u8 priority; u8 saved_priority; u8 resend; u8 masked_pending; u8 lsi; /* level-sensitive interrupt */ - u8 asserted; /* Only for LSI */ u8 exists; int intr_cpu; u32 host_irq; @@ -73,7 +76,6 @@ struct kvmppc_icp { */ #define XICS_RM_KICK_VCPU 0x1 #define XICS_RM_CHECK_RESEND 0x2 -#define XICS_RM_REJECT 0x4 #define XICS_RM_NOTIFY_EOI 0x8 u32 rm_action; struct kvm_vcpu *rm_kick_target; @@ -84,7 +86,6 @@ struct kvmppc_icp { /* Counters for each reason we exited real mode */ unsigned long n_rm_kick_vcpu; unsigned long n_rm_check_resend; - unsigned long n_rm_reject; unsigned long n_rm_notify_eoi; /* Counters for handling ICP processing in real mode */ unsigned long n_check_resend; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 40a5b2d..2b38d82 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -511,6 +511,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: + case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; case KVM_CAP_PPC_PAIRED_SINGLES: @@ -612,6 +613,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPAPR_MULTITCE: r = 1; break; + case KVM_CAP_SPAPR_RESIZE_HPT: + /* Disable this on POWER9 until code handles new HPTE format */ + r = !!hv_enabled && !cpu_has_feature(CPU_FTR_ARCH_300); + break; #endif case KVM_CAP_PPC_HTM: r = cpu_has_feature(CPU_FTR_TM_COMP) && @@ -1114,7 +1119,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) #endif } - r = kvmppc_vcpu_run(run, vcpu); + if (run->immediate_exit) + r = -EINTR; + else + r = kvmppc_vcpu_run(run, vcpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 4aa8a7e..4492c93 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu) ipte_unlock_simple(vcpu); } -static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, +static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar, enum gacc_mode mode) { union alet alet; @@ -465,7 +465,9 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, struct trans_exc_code_bits { unsigned long addr : 52; /* Translation-exception Address */ unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ - unsigned long : 6; + unsigned long : 2; + unsigned long b56 : 1; + unsigned long : 3; unsigned long b60 : 1; unsigned long b61 : 1; unsigned long as : 2; /* ASCE Identifier */ @@ -485,7 +487,7 @@ enum prot_type { }; static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, - ar_t ar, enum gacc_mode mode, enum prot_type prot) + u8 ar, enum gacc_mode mode, enum prot_type prot) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; struct trans_exc_code_bits *tec; @@ -497,14 +499,18 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (code) { case PGM_PROTECTION: switch (prot) { + case PROT_TYPE_LA: + tec->b56 = 1; + break; + case PROT_TYPE_KEYC: + tec->b60 = 1; + break; case PROT_TYPE_ALC: tec->b60 = 1; /* FALL THROUGH */ case PROT_TYPE_DAT: tec->b61 = 1; break; - default: /* LA and KEYC set b61 to 0, other params undefined */ - return code; } /* FALL THROUGH */ case PGM_ASCE_TYPE: @@ -539,7 +545,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, } static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, - unsigned long ga, ar_t ar, enum gacc_mode mode) + unsigned long ga, u8 ar, enum gacc_mode mode) { int rc; struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw); @@ -771,7 +777,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu, return 1; } -static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, +static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, unsigned long *pages, unsigned long nr_pages, const union asce asce, enum gacc_mode mode) { @@ -803,7 +809,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, return 0; } -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, unsigned long len, enum gacc_mode mode) { psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -877,7 +883,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * Note: The IPTE lock is not taken during this function, so the caller * has to take care of this. */ -int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long *gpa, enum gacc_mode mode) { psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -910,7 +916,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, /** * check_gva_range - test a range of guest virtual addresses for accessibility */ -int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long length, enum gacc_mode mode) { unsigned long gpa; diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 8756569..7ce47fd 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -162,11 +162,11 @@ enum gacc_mode { }; int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, - ar_t ar, unsigned long *gpa, enum gacc_mode mode); -int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + u8 ar, unsigned long *gpa, enum gacc_mode mode); +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long length, enum gacc_mode mode); -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, unsigned long len, enum gacc_mode mode); int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, @@ -218,7 +218,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * if data has been changed in guest space in case of an exception. */ static inline __must_check -int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, +int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, unsigned long len) { return access_guest(vcpu, ga, ar, data, len, GACC_STORE); @@ -238,7 +238,7 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, * data will be copied from guest space to kernel space. */ static inline __must_check -int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, +int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, unsigned long len) { return access_guest(vcpu, ga, ar, data, len, GACC_FETCH); @@ -247,10 +247,11 @@ int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, /** * read_guest_instr - copy instruction data from guest space to kernel space * @vcpu: virtual cpu + * @ga: guest address * @data: destination address in kernel space * @len: number of bytes to copy * - * Copy @len bytes from the current psw address (guest space) to @data (kernel + * Copy @len bytes from the given address (guest space) to @data (kernel * space). * * The behaviour of read_guest_instr is identical to read_guest, except that @@ -258,10 +259,10 @@ int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, * address-space mode. */ static inline __must_check -int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len) +int read_guest_instr(struct kvm_vcpu *vcpu, unsigned long ga, void *data, + unsigned long len) { - return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len, - GACC_IFETCH); + return access_guest(vcpu, ga, 0, data, len, GACC_IFETCH); } /** diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index d7c6a7f..23d9a4e 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -388,14 +388,13 @@ void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu) #define per_write_wp_event(code) \ (code & (PER_CODE_STORE | PER_CODE_STORE_REAL)) -static int debug_exit_required(struct kvm_vcpu *vcpu) +static int debug_exit_required(struct kvm_vcpu *vcpu, u8 perc, + unsigned long peraddr) { - u8 perc = vcpu->arch.sie_block->perc; struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch; struct kvm_hw_wp_info_arch *wp_info = NULL; struct kvm_hw_bp_info_arch *bp_info = NULL; unsigned long addr = vcpu->arch.sie_block->gpsw.addr; - unsigned long peraddr = vcpu->arch.sie_block->peraddr; if (guestdbg_hw_bp_enabled(vcpu)) { if (per_write_wp_event(perc) && @@ -437,36 +436,118 @@ exit_required: return 1; } +static int per_fetched_addr(struct kvm_vcpu *vcpu, unsigned long *addr) +{ + u8 exec_ilen = 0; + u16 opcode[3]; + int rc; + + if (vcpu->arch.sie_block->icptcode == ICPT_PROGI) { + /* PER address references the fetched or the execute instr */ + *addr = vcpu->arch.sie_block->peraddr; + /* + * Manually detect if we have an EXECUTE instruction. As + * instructions are always 2 byte aligned we can read the + * first two bytes unconditionally + */ + rc = read_guest_instr(vcpu, *addr, &opcode, 2); + if (rc) + return rc; + if (opcode[0] >> 8 == 0x44) + exec_ilen = 4; + if ((opcode[0] & 0xff0f) == 0xc600) + exec_ilen = 6; + } else { + /* instr was suppressed, calculate the responsible instr */ + *addr = __rewind_psw(vcpu->arch.sie_block->gpsw, + kvm_s390_get_ilen(vcpu)); + if (vcpu->arch.sie_block->icptstatus & 0x01) { + exec_ilen = (vcpu->arch.sie_block->icptstatus & 0x60) >> 4; + if (!exec_ilen) + exec_ilen = 4; + } + } + + if (exec_ilen) { + /* read the complete EXECUTE instr to detect the fetched addr */ + rc = read_guest_instr(vcpu, *addr, &opcode, exec_ilen); + if (rc) + return rc; + if (exec_ilen == 6) { + /* EXECUTE RELATIVE LONG - RIL-b format */ + s32 rl = *((s32 *) (opcode + 1)); + + /* rl is a _signed_ 32 bit value specifying halfwords */ + *addr += (u64)(s64) rl * 2; + } else { + /* EXECUTE - RX-a format */ + u32 base = (opcode[1] & 0xf000) >> 12; + u32 disp = opcode[1] & 0x0fff; + u32 index = opcode[0] & 0x000f; + + *addr = base ? vcpu->run->s.regs.gprs[base] : 0; + *addr += index ? vcpu->run->s.regs.gprs[index] : 0; + *addr += disp; + } + *addr = kvm_s390_logical_to_effective(vcpu, *addr); + } + return 0; +} + #define guest_per_enabled(vcpu) \ (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu) { + const u64 cr10 = vcpu->arch.sie_block->gcr[10]; + const u64 cr11 = vcpu->arch.sie_block->gcr[11]; const u8 ilen = kvm_s390_get_ilen(vcpu); struct kvm_s390_pgm_info pgm_info = { .code = PGM_PER, .per_code = PER_CODE_IFETCH, .per_address = __rewind_psw(vcpu->arch.sie_block->gpsw, ilen), }; + unsigned long fetched_addr; + int rc; /* * The PSW points to the next instruction, therefore the intercepted * instruction generated a PER i-fetch event. PER address therefore * points at the previous PSW address (could be an EXECUTE function). */ - return kvm_s390_inject_prog_irq(vcpu, &pgm_info); + if (!guestdbg_enabled(vcpu)) + return kvm_s390_inject_prog_irq(vcpu, &pgm_info); + + if (debug_exit_required(vcpu, pgm_info.per_code, pgm_info.per_address)) + vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING; + + if (!guest_per_enabled(vcpu) || + !(vcpu->arch.sie_block->gcr[9] & PER_EVENT_IFETCH)) + return 0; + + rc = per_fetched_addr(vcpu, &fetched_addr); + if (rc < 0) + return rc; + if (rc) + /* instruction-fetching exceptions */ + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + if (in_addr_range(fetched_addr, cr10, cr11)) + return kvm_s390_inject_prog_irq(vcpu, &pgm_info); + return 0; } -static void filter_guest_per_event(struct kvm_vcpu *vcpu) +static int filter_guest_per_event(struct kvm_vcpu *vcpu) { const u8 perc = vcpu->arch.sie_block->perc; - u64 peraddr = vcpu->arch.sie_block->peraddr; u64 addr = vcpu->arch.sie_block->gpsw.addr; u64 cr9 = vcpu->arch.sie_block->gcr[9]; u64 cr10 = vcpu->arch.sie_block->gcr[10]; u64 cr11 = vcpu->arch.sie_block->gcr[11]; /* filter all events, demanded by the guest */ u8 guest_perc = perc & (cr9 >> 24) & PER_CODE_MASK; + unsigned long fetched_addr; + int rc; if (!guest_per_enabled(vcpu)) guest_perc = 0; @@ -478,9 +559,17 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu) guest_perc &= ~PER_CODE_BRANCH; /* filter "instruction-fetching" events */ - if (guest_perc & PER_CODE_IFETCH && - !in_addr_range(peraddr, cr10, cr11)) - guest_perc &= ~PER_CODE_IFETCH; + if (guest_perc & PER_CODE_IFETCH) { + rc = per_fetched_addr(vcpu, &fetched_addr); + if (rc < 0) + return rc; + /* + * Don't inject an irq on exceptions. This would make handling + * on icpt code 8 very complex (as PSW was already rewound). + */ + if (rc || !in_addr_range(fetched_addr, cr10, cr11)) + guest_perc &= ~PER_CODE_IFETCH; + } /* All other PER events will be given to the guest */ /* TODO: Check altered address/address space */ @@ -489,6 +578,7 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu) if (!guest_perc) vcpu->arch.sie_block->iprcc &= ~PGM_PER; + return 0; } #define pssec(vcpu) (vcpu->arch.sie_block->gcr[1] & _ASCE_SPACE_SWITCH) @@ -496,14 +586,17 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu) #define old_ssec(vcpu) ((vcpu->arch.sie_block->tecmc >> 31) & 0x1) #define old_as_is_home(vcpu) !(vcpu->arch.sie_block->tecmc & 0xffff) -void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu) +int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu) { - int new_as; + int rc, new_as; - if (debug_exit_required(vcpu)) + if (debug_exit_required(vcpu, vcpu->arch.sie_block->perc, + vcpu->arch.sie_block->peraddr)) vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING; - filter_guest_per_event(vcpu); + rc = filter_guest_per_event(vcpu); + if (rc) + return rc; /* * Only RP, SAC, SACF, PT, PTI, PR, PC instructions can trigger @@ -532,4 +625,5 @@ void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu) (pssec(vcpu) || old_ssec(vcpu))) vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH; } + return 0; } diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 7a27eeb..59920f9 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -238,7 +238,9 @@ static int handle_prog(struct kvm_vcpu *vcpu) vcpu->stat.exit_program_interruption++; if (guestdbg_enabled(vcpu) && per_event(vcpu)) { - kvm_s390_handle_per_event(vcpu); + rc = kvm_s390_handle_per_event(vcpu); + if (rc) + return rc; /* the interrupt might have been filtered out completely */ if (vcpu->arch.sie_block->iprcc == 0) return 0; @@ -359,6 +361,9 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu) static int handle_operexc(struct kvm_vcpu *vcpu) { + psw_t oldpsw, newpsw; + int rc; + vcpu->stat.exit_operation_exception++; trace_kvm_s390_handle_operexc(vcpu, vcpu->arch.sie_block->ipa, vcpu->arch.sie_block->ipb); @@ -369,6 +374,24 @@ static int handle_operexc(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0) return -EOPNOTSUPP; + rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &newpsw, sizeof(psw_t)); + if (rc) + return rc; + /* + * Avoid endless loops of operation exceptions, if the pgm new + * PSW will cause a new operation exception. + * The heuristic checks if the pgm new psw is within 6 bytes before + * the faulting psw address (with same DAT, AS settings) and the + * new psw is not a wait psw and the fault was not triggered by + * problem state. + */ + oldpsw = vcpu->arch.sie_block->gpsw; + if (oldpsw.addr - newpsw.addr <= 6 && + !(newpsw.mask & PSW_MASK_WAIT) && + !(oldpsw.mask & PSW_MASK_PSTATE) && + (newpsw.mask & PSW_MASK_ASC) == (oldpsw.mask & PSW_MASK_ASC) && + (newpsw.mask & PSW_MASK_DAT) == (oldpsw.mask & PSW_MASK_DAT)) + return -EOPNOTSUPP; return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b604854..f569483 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -218,7 +218,7 @@ static void allow_cpu_feat(unsigned long nr) static inline int plo_test_bit(unsigned char nr) { register unsigned long r0 asm("0") = (unsigned long) nr | 0x100; - int cc = 3; /* subfunction not available */ + int cc; asm volatile( /* Parameter registers are ignored for "test bit" */ @@ -371,6 +371,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: + case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_S390_INJECT_IRQ: case KVM_CAP_S390_USER_SIGP: case KVM_CAP_S390_USER_STSI: @@ -443,6 +444,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; + if (kvm_is_ucontrol(kvm)) + return -EINVAL; + mutex_lock(&kvm->slots_lock); r = -EINVAL; @@ -506,6 +510,14 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) } else if (MACHINE_HAS_VX) { set_kvm_facility(kvm->arch.model.fac_mask, 129); set_kvm_facility(kvm->arch.model.fac_list, 129); + if (test_facility(134)) { + set_kvm_facility(kvm->arch.model.fac_mask, 134); + set_kvm_facility(kvm->arch.model.fac_list, 134); + } + if (test_facility(135)) { + set_kvm_facility(kvm->arch.model.fac_mask, 135); + set_kvm_facility(kvm->arch.model.fac_list, 135); + } r = 0; } else r = -EINVAL; @@ -822,6 +834,13 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) } memcpy(kvm->arch.model.fac_list, proc->fac_list, S390_ARCH_FAC_LIST_SIZE_BYTE); + VM_EVENT(kvm, 3, "SET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx", + kvm->arch.model.ibc, + kvm->arch.model.cpuid); + VM_EVENT(kvm, 3, "SET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx", + kvm->arch.model.fac_list[0], + kvm->arch.model.fac_list[1], + kvm->arch.model.fac_list[2]); } else ret = -EFAULT; kfree(proc); @@ -895,6 +914,13 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr) proc->ibc = kvm->arch.model.ibc; memcpy(&proc->fac_list, kvm->arch.model.fac_list, S390_ARCH_FAC_LIST_SIZE_BYTE); + VM_EVENT(kvm, 3, "GET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx", + kvm->arch.model.ibc, + kvm->arch.model.cpuid); + VM_EVENT(kvm, 3, "GET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx", + kvm->arch.model.fac_list[0], + kvm->arch.model.fac_list[1], + kvm->arch.model.fac_list[2]); if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc))) ret = -EFAULT; kfree(proc); @@ -918,6 +944,17 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr) S390_ARCH_FAC_LIST_SIZE_BYTE); memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list, sizeof(S390_lowcore.stfle_fac_list)); + VM_EVENT(kvm, 3, "GET: host ibc: 0x%4.4x, host cpuid: 0x%16.16llx", + kvm->arch.model.ibc, + kvm->arch.model.cpuid); + VM_EVENT(kvm, 3, "GET: host facmask: 0x%16.16llx.%16.16llx.%16.16llx", + mach->fac_mask[0], + mach->fac_mask[1], + mach->fac_mask[2]); + VM_EVENT(kvm, 3, "GET: host faclist: 0x%16.16llx.%16.16llx.%16.16llx", + mach->fac_list[0], + mach->fac_list[1], + mach->fac_list[2]); if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach))) ret = -EFAULT; kfree(mach); @@ -1939,6 +1976,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi) vcpu->arch.sie_block->ecb2 |= 0x08; + if (test_kvm_facility(vcpu->kvm, 130)) + vcpu->arch.sie_block->ecb2 |= 0x20; vcpu->arch.sie_block->eca = 0x1002000U; if (sclp.has_cei) vcpu->arch.sie_block->eca |= 0x80000000U; @@ -2579,7 +2618,7 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) * to look up the current opcode to get the length of the instruction * to be able to forward the PSW. */ - rc = read_guest_instr(vcpu, &opcode, 1); + rc = read_guest_instr(vcpu, vcpu->arch.sie_block->gpsw.addr, &opcode, 1); ilen = insn_length(opcode); if (rc < 0) { return rc; @@ -2761,6 +2800,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int rc; sigset_t sigsaved; + if (kvm_run->immediate_exit) + return -EINTR; + if (guestdbg_exit_pending(vcpu)) { kvm_s390_prepare_debug_exit(vcpu); return 0; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 3a4e97f..af9fa91 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -86,9 +86,7 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); } -typedef u8 __bitwise ar_t; - -static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar) +static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); @@ -101,7 +99,7 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar) static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, u64 *address1, u64 *address2, - ar_t *ar_b1, ar_t *ar_b2) + u8 *ar_b1, u8 *ar_b2) { u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; @@ -125,7 +123,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2 *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; } -static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar) +static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, u8 *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + @@ -140,7 +138,7 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2; } -static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar) +static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, u8 *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); @@ -379,7 +377,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu); void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu); int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu); -void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu); +int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu); /* support for Basic/Extended SCA handling */ static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 7945035..fb4b494 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -54,7 +54,7 @@ int kvm_s390_handle_aa(struct kvm_vcpu *vcpu) static int handle_set_clock(struct kvm_vcpu *vcpu) { int rc; - ar_t ar; + u8 ar; u64 op2, val; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) @@ -79,7 +79,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; - ar_t ar; + u8 ar; vcpu->stat.instruction_spx++; @@ -117,7 +117,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; - ar_t ar; + u8 ar; vcpu->stat.instruction_stpx++; @@ -147,7 +147,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) u16 vcpu_id = vcpu->vcpu_id; u64 ga; int rc; - ar_t ar; + u8 ar; vcpu->stat.instruction_stap++; @@ -380,7 +380,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu) u32 tpi_data[3]; int rc; u64 addr; - ar_t ar; + u8 ar; addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 3) @@ -548,7 +548,7 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) psw_compat_t new_psw; u64 addr; int rc; - ar_t ar; + u8 ar; if (gpsw->mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -575,7 +575,7 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) psw_t new_psw; u64 addr; int rc; - ar_t ar; + u8 ar; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -597,7 +597,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu) u64 stidp_data = vcpu->kvm->arch.model.cpuid; u64 operand2; int rc; - ar_t ar; + u8 ar; vcpu->stat.instruction_stidp++; @@ -644,7 +644,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) ASCEBC(mem->vm[0].cpi, 16); } -static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar, +static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, u8 ar, u8 fc, u8 sel1, u16 sel2) { vcpu->run->exit_reason = KVM_EXIT_S390_STSI; @@ -663,7 +663,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) unsigned long mem = 0; u64 operand2; int rc = 0; - ar_t ar; + u8 ar; vcpu->stat.instruction_stsi++; VCPU_EVENT(vcpu, 3, "STSI: fc: %u sel1: %u sel2: %u", fc, sel1, sel2); @@ -970,7 +970,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; - ar_t ar; + u8 ar; vcpu->stat.instruction_lctl++; @@ -1009,7 +1009,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; - ar_t ar; + u8 ar; vcpu->stat.instruction_stctl++; @@ -1043,7 +1043,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; - ar_t ar; + u8 ar; vcpu->stat.instruction_lctlg++; @@ -1081,7 +1081,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; - ar_t ar; + u8 ar; vcpu->stat.instruction_stctg++; @@ -1132,7 +1132,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu) unsigned long hva, gpa; int ret = 0, cc = 0; bool writable; - ar_t ar; + u8 ar; vcpu->stat.instruction_tprot++; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a9a9d97..38556e3 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -324,6 +324,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) /* Run-time-Instrumentation */ if (test_kvm_facility(vcpu->kvm, 64)) scb_s->ecb3 |= scb_o->ecb3 & 0x01U; + /* Instruction Execution Prevention */ + if (test_kvm_facility(vcpu->kvm, 130)) + scb_s->ecb2 |= scb_o->ecb2 & 0x20U; if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIIF)) scb_s->eca |= scb_o->eca & 0x00000001U; if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IB)) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index beb90f3..b48dc5f 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -744,7 +744,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) pgste_set_unlock(ptep, new); pte_unmap_unlock(ptep, ptl); - return 0; + return cc; } EXPORT_SYMBOL(reset_guest_reference_bit); diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index 8cc53b1..0cf802d 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -80,6 +80,8 @@ static struct facility_def facility_defs[] = { 76, /* msa extension 3 */ 77, /* msa extension 4 */ 78, /* enhanced-DAT 2 */ + 130, /* instruction-execution-protection */ + 131, /* enhanced-SOP 2 and side-effect */ -1 /* END */ } }, diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 12080d8..cb8f914 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -177,16 +177,8 @@ static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) struct desc_struct *d = get_cpu_gdt_table(cpu); tss_desc tss; - /* - * sizeof(unsigned long) coming from an extra "long" at the end - * of the iobitmap. See tss_struct definition in processor.h - * - * -1? seg base+limit should be pointing to the address of the - * last valid byte - */ set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, - IO_BITMAP_OFFSET + IO_BITMAP_BYTES + - sizeof(unsigned long) - 1); + __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } @@ -213,6 +205,54 @@ static inline void native_load_tr_desc(void) asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } +static inline void force_reload_TR(void) +{ + struct desc_struct *d = get_cpu_gdt_table(smp_processor_id()); + tss_desc tss; + + memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); + + /* + * LTR requires an available TSS, and the TSS is currently + * busy. Make it be available so that LTR will work. + */ + tss.type = DESC_TSS; + write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); + + load_TR_desc(); +} + +DECLARE_PER_CPU(bool, need_tr_refresh); + +static inline void refresh_TR(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(this_cpu_read(need_tr_refresh))) { + force_reload_TR(); + this_cpu_write(need_tr_refresh, false); + } +} + +/* + * If you do something evil that corrupts the cached TSS limit (I'm looking + * at you, VMX exits), call this function. + * + * The optimization here is that the TSS limit only matters for Linux if the + * IO bitmap is in use. If the TSS limit gets forced to its minimum value, + * everything works except that IO bitmap will be ignored and all CPL 3 IO + * instructions will #GP, which is exactly what we want for normal tasks. + */ +static inline void invalidate_tss_limit(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) + force_reload_TR(); + else + this_cpu_write(need_tr_refresh, true); +} + static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index e9cd7be..3e8c287 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -441,5 +441,6 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq); void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt); void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt); +bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a7066dc..74ef58c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -55,7 +55,6 @@ #define KVM_REQ_TRIPLE_FAULT 10 #define KVM_REQ_MMU_SYNC 11 #define KVM_REQ_CLOCK_UPDATE 12 -#define KVM_REQ_DEACTIVATE_FPU 13 #define KVM_REQ_EVENT 14 #define KVM_REQ_APF_HALT 15 #define KVM_REQ_STEAL_UPDATE 16 @@ -115,7 +114,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 -#define KVM_MMU_HASH_SHIFT 10 +#define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 @@ -208,6 +207,13 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting + * with the SVE bit in EPT PTEs. + */ +#define SPTE_SPECIAL_MASK (1ULL << 62) + /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -668,6 +674,9 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; + + /* GPA available (AMD only) */ + bool gpa_available; }; struct kvm_lpage_info { @@ -716,6 +725,12 @@ struct kvm_hv { HV_REFERENCE_TSC_PAGE tsc_ref; }; +enum kvm_irqchip_mode { + KVM_IRQCHIP_NONE, + KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ + KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -788,7 +803,7 @@ struct kvm_arch { u64 disabled_quirks; - bool irqchip_split; + enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; bool disabled_lapic_found; @@ -815,6 +830,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong max_mmu_page_hash_collisions; }; struct kvm_vcpu_stat { @@ -844,6 +860,7 @@ struct kvm_vcpu_stat { u64 hypercalls; u64 irq_injections; u64 nmi_injections; + u64 req_event; }; struct x86_instruction_info; @@ -918,8 +935,6 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); u32 (*get_pkru)(struct kvm_vcpu *vcpu); - void (*fpu_activate)(struct kvm_vcpu *vcpu); - void (*fpu_deactivate)(struct kvm_vcpu *vcpu); void (*tlb_flush)(struct kvm_vcpu *vcpu); @@ -951,7 +966,7 @@ struct kvm_x86_ops { void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); - void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); + int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*get_tdp_level)(void); u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); @@ -1050,7 +1065,8 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask); + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, + u64 acc_track_mask); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h new file mode 100644 index 0000000..f260bef --- /dev/null +++ b/arch/x86/include/asm/kvmclock.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_KVM_CLOCK_H +#define _ASM_X86_KVM_CLOCK_H + +extern struct clocksource kvm_clock; + +#endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 1eea6ca..f75fbfe 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -673,7 +673,7 @@ static __always_inline void pv_kick(int cpu) PVOP_VCALL1(pv_lock_ops.kick, cpu); } -static __always_inline bool pv_vcpu_is_preempted(int cpu) +static __always_inline bool pv_vcpu_is_preempted(long cpu) { return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index e6cfe7b..f385eca 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -304,7 +304,7 @@ struct x86_hw_tss { u16 reserved5; u16 io_bitmap_base; -} __attribute__((packed)) ____cacheline_aligned; +} __attribute__((packed)); #endif /* @@ -342,6 +342,16 @@ struct tss_struct { DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +/* + * sizeof(unsigned long) coming from an extra "long" at the end + * of the iobitmap. + * + * -1? seg base+limit should be pointing to the address of the + * last valid byte + */ +#define __KERNEL_TSS_LIMIT \ + (IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1) + #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); #endif diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index c343ab5..48a706f 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -34,7 +34,7 @@ static inline void queued_spin_unlock(struct qspinlock *lock) } #define vcpu_is_preempted vcpu_is_preempted -static inline bool vcpu_is_preempted(int cpu) +static inline bool vcpu_is_preempted(long cpu) { return pv_vcpu_is_preempted(cpu); } diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2b5b2d4..cc54b70 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -467,8 +467,16 @@ enum vmcs_field { #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull #define VMX_EPT_IPAT_BIT (1ull << 6) -#define VMX_EPT_ACCESS_BIT (1ull << 8) -#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_ACCESS_BIT (1ull << 8) +#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \ + VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) +#define VMX_EPT_MT_MASK (7ull << VMX_EPT_MT_EPTE_SHIFT) + +/* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */ +#define VMX_EPT_MISCONFIG_WX_VALUE (VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) #define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul @@ -500,6 +508,22 @@ struct vmx_msr_entry { #define ENTRY_FAIL_VMCS_LINK_PTR 4 /* + * Exit Qualifications for EPT Violations + */ +#define EPT_VIOLATION_ACC_READ_BIT 0 +#define EPT_VIOLATION_ACC_WRITE_BIT 1 +#define EPT_VIOLATION_ACC_INSTR_BIT 2 +#define EPT_VIOLATION_READABLE_BIT 3 +#define EPT_VIOLATION_WRITABLE_BIT 4 +#define EPT_VIOLATION_EXECUTABLE_BIT 5 +#define EPT_VIOLATION_ACC_READ (1 << EPT_VIOLATION_ACC_READ_BIT) +#define EPT_VIOLATION_ACC_WRITE (1 << EPT_VIOLATION_ACC_WRITE_BIT) +#define EPT_VIOLATION_ACC_INSTR (1 << EPT_VIOLATION_ACC_INSTR_BIT) +#define EPT_VIOLATION_READABLE (1 << EPT_VIOLATION_READABLE_BIT) +#define EPT_VIOLATION_WRITABLE (1 << EPT_VIOLATION_WRITABLE_BIT) +#define EPT_VIOLATION_EXECUTABLE (1 << EPT_VIOLATION_EXECUTABLE_BIT) + +/* * VM-instruction error numbers */ enum vm_instruction_error_number { diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 1421a65..cff0bb6 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -50,6 +50,15 @@ struct kvm_steal_time { __u32 pad[11]; }; +#define KVM_CLOCK_PAIRING_WALLCLOCK 0 +struct kvm_clock_pairing { + __s64 sec; + __s64 nsec; + __u64 tsc; + __u32 flags; + __u32 pad[9]; +}; + #define KVM_STEAL_ALIGNMENT_BITS 5 #define KVM_STEAL_VALID_BITS ((-1ULL << (KVM_STEAL_ALIGNMENT_BITS + 1))) #define KVM_STEAL_RESERVED_MASK (((1 << KVM_STEAL_ALIGNMENT_BITS) - 1 ) << 1) diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 210927e..99332f5 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -13,6 +13,10 @@ static char syscalls_ia32[] = { #include <asm/syscalls_32.h> }; +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#include <asm/kvm_para.h> +#endif + int main(void) { #ifdef CONFIG_PARAVIRT @@ -22,6 +26,11 @@ int main(void) BLANK(); #endif +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) + OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted); + BLANK(); +#endif + #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 589b319..b01bc8517 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <linux/bitmap.h> #include <asm/syscalls.h> +#include <asm/desc.h> /* * this changes the io permissions bitmap in the current task. @@ -45,6 +46,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) memset(bitmap, 0xff, IO_BITMAP_BYTES); t->io_bitmap_ptr = bitmap; set_thread_flag(TIF_IO_BITMAP); + + preempt_disable(); + refresh_TR(); + preempt_enable(); } /* diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 099fcba..14f65a5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -589,7 +589,8 @@ out: local_irq_restore(flags); } -__visible bool __kvm_vcpu_is_preempted(int cpu) +#ifdef CONFIG_X86_32 +__visible bool __kvm_vcpu_is_preempted(long cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); @@ -597,6 +598,29 @@ __visible bool __kvm_vcpu_is_preempted(int cpu) } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); +#else + +#include <asm/asm-offsets.h> + +extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); + +/* + * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and + * restoring to/from the stack. + */ +asm( +".pushsection .text;" +".global __raw_callee_save___kvm_vcpu_is_preempted;" +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" +"__raw_callee_save___kvm_vcpu_is_preempted:" +"movq __per_cpu_offset(,%rdi,8), %rax;" +"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" +"setne %al;" +"ret;" +".popsection"); + +#endif + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 542710b..bae6ea6 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> +#include <asm/kvmclock.h> static int kvmclock __ro_after_init = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; @@ -49,6 +50,7 @@ struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) { return hv_clock; } +EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va); /* * The wallclock is the time of day when we booted. Since then, some time may @@ -174,13 +176,14 @@ bool kvm_check_and_clear_guest_paused(void) return ret; } -static struct clocksource kvm_clock = { +struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +EXPORT_SYMBOL_GPL(kvm_clock); int kvm_register_clock(char *txt) { diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 6259327..8f2d1c9 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -20,7 +20,7 @@ bool pv_is_native_spin_unlock(void) __raw_callee_save___native_queued_spin_unlock; } -__visible bool __native_vcpu_is_preempted(int cpu) +__visible bool __native_vcpu_is_preempted(long cpu) { return false; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b615a11..7780efa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -32,6 +32,7 @@ #include <asm/mce.h> #include <asm/vm86.h> #include <asm/switch_to.h> +#include <asm/desc.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -64,6 +65,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { }; EXPORT_PER_CPU_SYMBOL(cpu_tss); +DEFINE_PER_CPU(bool, need_tr_refresh); +EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh); + /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. @@ -209,6 +213,12 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); + + /* + * Make sure that the TSS limit is correct for the CPU + * to notice the IO bitmap. + */ + refresh_TR(); } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { /* * Clear any possible leftover bits: diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index e85f6bd..1d155cc5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -123,8 +123,6 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - kvm_x86_ops->fpu_activate(vcpu); - /* * The existing code assumes virtual address is 48-bit in the canonical * address checks; exit if it is ever changed. @@ -383,7 +381,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(PKU) | 0 /*OSPKE*/; + F(AVX512VBMI) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = @@ -861,12 +859,6 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) if (!best) best = check_cpuid_limit(vcpu, function, index); - /* - * Perfmon not yet supported for L2 guest. - */ - if (is_guest_mode(vcpu) && function == 0xa) - best = NULL; - if (best) { *eax = best->eax; *ebx = best->ebx; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index cedbba0..45c7306 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -173,6 +173,7 @@ #define NearBranch ((u64)1 << 52) /* Near branches */ #define No16 ((u64)1 << 53) /* No 16 bit operand */ #define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */ +#define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -4298,7 +4299,7 @@ static const struct opcode group1[] = { }; static const struct opcode group1A[] = { - I(DstMem | SrcNone | Mov | Stack | IncSP, em_pop), N, N, N, N, N, N, N, + I(DstMem | SrcNone | Mov | Stack | IncSP | TwoMemOp, em_pop), N, N, N, N, N, N, N, }; static const struct opcode group2[] = { @@ -4336,7 +4337,7 @@ static const struct opcode group5[] = { I(SrcMemFAddr | ImplicitOps, em_call_far), I(SrcMem | NearBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps, em_jmp_far), - I(SrcMem | Stack, em_push), D(Undefined), + I(SrcMem | Stack | TwoMemOp, em_push), D(Undefined), }; static const struct opcode group6[] = { @@ -4556,8 +4557,8 @@ static const struct opcode opcode_table[256] = { /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), - I2bv(SrcSI | DstDI | Mov | String, em_mov), - F2bv(SrcSI | DstDI | String | NoWrite, em_cmp_r), + I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov), + F2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r), /* 0xA8 - 0xAF */ F2bv(DstAcc | SrcImm | NoWrite, em_test), I2bv(SrcAcc | DstDI | Mov | String, em_mov), @@ -5671,3 +5672,14 @@ void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt) { writeback_registers(ctxt); } + +bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->rep_prefix && (ctxt->d & String)) + return false; + + if (ctxt->d & TwoMemOp) + return false; + + return true; +} diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2ecd7da..f701d44 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -305,13 +305,13 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) return -ENOENT; memset(&irq, 0, sizeof(irq)); - irq.dest_id = kvm_apic_id(vcpu->arch.apic); + irq.shorthand = APIC_DEST_SELF; irq.dest_mode = APIC_DEST_PHYSICAL; irq.delivery_mode = APIC_DM_FIXED; irq.vector = vector; irq.level = 1; - ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL); + ret = kvm_irq_delivery_to_apic(vcpu->kvm, vcpu->arch.apic, &irq, NULL); trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret); return ret; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 7cc2360..73ea24d 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -598,14 +598,14 @@ static const struct kvm_io_device_ops picdev_eclr_ops = { .write = picdev_eclr_write, }; -struct kvm_pic *kvm_create_pic(struct kvm *kvm) +int kvm_pic_init(struct kvm *kvm) { struct kvm_pic *s; int ret; s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); if (!s) - return NULL; + return -ENOMEM; spin_lock_init(&s->lock); s->kvm = kvm; s->pics[0].elcr_mask = 0xf8; @@ -635,7 +635,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) mutex_unlock(&kvm->slots_lock); - return s; + kvm->arch.vpic = s; + + return 0; fail_unreg_1: kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_slave); @@ -648,13 +650,17 @@ fail_unlock: kfree(s); - return NULL; + return ret; } -void kvm_destroy_pic(struct kvm_pic *vpic) +void kvm_pic_destroy(struct kvm *kvm) { + struct kvm_pic *vpic = kvm->arch.vpic; + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + + kvm->arch.vpic = NULL; kfree(vpic); } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 035731e..40d5b2c 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -73,8 +73,8 @@ struct kvm_pic { unsigned long irq_states[PIC_NUM_PINS]; }; -struct kvm_pic *kvm_create_pic(struct kvm *kvm); -void kvm_destroy_pic(struct kvm_pic *vpic); +int kvm_pic_init(struct kvm *kvm); +void kvm_pic_destroy(struct kvm *kvm); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); @@ -93,18 +93,19 @@ static inline int pic_in_kernel(struct kvm *kvm) static inline int irqchip_split(struct kvm *kvm) { - return kvm->arch.irqchip_split; + return kvm->arch.irqchip_mode == KVM_IRQCHIP_SPLIT; } -static inline int irqchip_in_kernel(struct kvm *kvm) +static inline int irqchip_kernel(struct kvm *kvm) { - struct kvm_pic *vpic = pic_irqchip(kvm); - bool ret; + return kvm->arch.irqchip_mode == KVM_IRQCHIP_KERNEL; +} - ret = (vpic != NULL); - ret |= irqchip_split(kvm); +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + bool ret = kvm->arch.irqchip_mode != KVM_IRQCHIP_NONE; - /* Read vpic before kvm->irq_routing. */ + /* Matches with wmb after initializing kvm->irq_routing. */ smp_rmb(); return ret; } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 6c01916..b96d389 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -41,15 +41,6 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_pic *pic = pic_irqchip(kvm); - - /* - * XXX: rejecting pic routes when pic isn't in use would be better, - * but the default routing table is installed while kvm->arch.vpic is - * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE. - */ - if (!pic) - return -1; - return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); } @@ -58,10 +49,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; - - if (!ioapic) - return -1; - return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level, line_status); } @@ -297,16 +284,20 @@ int kvm_set_routing_entry(struct kvm *kvm, case KVM_IRQ_ROUTING_IRQCHIP: delta = 0; switch (ue->u.irqchip.irqchip) { - case KVM_IRQCHIP_PIC_MASTER: - e->set = kvm_set_pic_irq; - max_pin = PIC_NUM_PINS; - break; case KVM_IRQCHIP_PIC_SLAVE: + delta = 8; + /* fall through */ + case KVM_IRQCHIP_PIC_MASTER: + if (!pic_in_kernel(kvm)) + goto out; + e->set = kvm_set_pic_irq; max_pin = PIC_NUM_PINS; - delta = 8; break; case KVM_IRQCHIP_IOAPIC: + if (!ioapic_in_kernel(kvm)) + goto out; + max_pin = KVM_IOAPIC_NUM_PINS; e->set = kvm_set_ioapic_irq; break; @@ -409,7 +400,7 @@ int kvm_setup_empty_irq_routing(struct kvm *kvm) void kvm_arch_post_irq_routing_update(struct kvm *kvm) { - if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm)) + if (!irqchip_split(kvm)) return; kvm_make_scan_ioapic_request(kvm); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2f6ef51..bad6a25 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -115,6 +115,16 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + +static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) +{ + return apic->vcpu->vcpu_id; +} + static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { switch (map->mode) { @@ -159,13 +169,13 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; - u32 max_id = 255; + u32 max_id = 255; /* enough space for any xAPIC ID */ mutex_lock(&kvm->arch.apic_map_lock); kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_apic_present(vcpu)) - max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); + max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic)); new = kvm_kvzalloc(sizeof(struct kvm_apic_map) + sizeof(struct kvm_lapic *) * ((u64)max_id + 1)); @@ -179,16 +189,28 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_lapic **cluster; u16 mask; - u32 ldr, aid; + u32 ldr; + u8 xapic_id; + u32 x2apic_id; if (!kvm_apic_present(vcpu)) continue; - aid = kvm_apic_id(apic); - ldr = kvm_lapic_get_reg(apic, APIC_LDR); + xapic_id = kvm_xapic_id(apic); + x2apic_id = kvm_x2apic_id(apic); - if (aid <= new->max_apic_id) - new->phys_map[aid] = apic; + /* Hotplug hack: see kvm_apic_match_physical_addr(), ... */ + if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && + x2apic_id <= new->max_apic_id) + new->phys_map[x2apic_id] = apic; + /* + * ... xAPIC ID of VCPUs with APIC ID > 0xff will wrap-around, + * prevent them from masking VCPUs with APIC ID <= 0xff. + */ + if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) + new->phys_map[xapic_id] = apic; + + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) { new->mode |= KVM_APIC_MODE_X2APIC; @@ -250,6 +272,8 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); + WARN_ON_ONCE(id != apic->vcpu->vcpu_id); + kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); recalculate_apic_map(apic->vcpu->kvm); @@ -317,7 +341,7 @@ static int find_highest_vector(void *bitmap) vec >= 0; vec -= APIC_VECTORS_PER_REG) { reg = bitmap + REG_POS(vec); if (*reg) - return fls(*reg) - 1 + vec; + return __fls(*reg) + vec; } return -1; @@ -337,27 +361,32 @@ static u8 count_vectors(void *bitmap) return count; } -void __kvm_apic_update_irr(u32 *pir, void *regs) +int __kvm_apic_update_irr(u32 *pir, void *regs) { - u32 i, pir_val; + u32 i, vec; + u32 pir_val, irr_val; + int max_irr = -1; - for (i = 0; i <= 7; i++) { + for (i = vec = 0; i <= 7; i++, vec += 32) { pir_val = READ_ONCE(pir[i]); + irr_val = *((u32 *)(regs + APIC_IRR + i * 0x10)); if (pir_val) { - pir_val = xchg(&pir[i], 0); - *((u32 *)(regs + APIC_IRR + i * 0x10)) |= pir_val; + irr_val |= xchg(&pir[i], 0); + *((u32 *)(regs + APIC_IRR + i * 0x10)) = irr_val; } + if (irr_val) + max_irr = __fls(irr_val) + vec; } + + return max_irr; } EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); -void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) { struct kvm_lapic *apic = vcpu->arch.apic; - __kvm_apic_update_irr(pir, apic->regs); - - kvm_make_request(KVM_REQ_EVENT, vcpu); + return __kvm_apic_update_irr(pir, apic->regs); } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); @@ -377,8 +406,6 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) if (!apic->irr_pending) return -1; - if (apic->vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(apic->vcpu); result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); @@ -392,9 +419,10 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) vcpu = apic->vcpu; if (unlikely(vcpu->arch.apicv_active)) { - /* try to update RVI */ + /* need to update RVI */ apic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_x86_ops->hwapic_irr_update(vcpu, + apic_find_highest_irr(apic)); } else { apic->irr_pending = false; apic_clear_vector(vec, apic->regs + APIC_IRR); @@ -484,6 +512,7 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) */ return apic_find_highest_irr(vcpu->arch.apic); } +EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode, @@ -500,16 +529,14 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) { - - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &val, - sizeof(val)); + return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.pv_eoi.data, &val, + sizeof(val)); } static int pv_eoi_get_user(struct kvm_vcpu *vcpu, u8 *val) { - - return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, val, - sizeof(*val)); + return kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.pv_eoi.data, val, + sizeof(*val)); } static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) @@ -546,7 +573,19 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void apic_update_ppr(struct kvm_lapic *apic) +static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) +{ + int highest_irr; + if (kvm_x86_ops->sync_pir_to_irr && apic->vcpu->arch.apicv_active) + highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + else + highest_irr = apic_find_highest_irr(apic); + if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr) + return -1; + return highest_irr; +} + +static bool __apic_update_ppr(struct kvm_lapic *apic, u32 *new_ppr) { u32 tpr, isrv, ppr, old_ppr; int isr; @@ -564,13 +603,28 @@ static void apic_update_ppr(struct kvm_lapic *apic) apic_debug("vlapic %p, ppr 0x%x, isr 0x%x, isrv 0x%x", apic, ppr, isr, isrv); - if (old_ppr != ppr) { + *new_ppr = ppr; + if (old_ppr != ppr) kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr); - if (ppr < old_ppr) - kvm_make_request(KVM_REQ_EVENT, apic->vcpu); - } + + return ppr < old_ppr; +} + +static void apic_update_ppr(struct kvm_lapic *apic) +{ + u32 ppr; + + if (__apic_update_ppr(apic, &ppr) && + apic_has_interrupt_for_ppr(apic, ppr) != -1) + kvm_make_request(KVM_REQ_EVENT, apic->vcpu); } +void kvm_apic_update_ppr(struct kvm_vcpu *vcpu) +{ + apic_update_ppr(vcpu->arch.apic); +} +EXPORT_SYMBOL_GPL(kvm_apic_update_ppr); + static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) { kvm_lapic_set_reg(apic, APIC_TASKPRI, tpr); @@ -579,10 +633,8 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { - if (apic_x2apic_mode(apic)) - return mda == X2APIC_BROADCAST; - - return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST; + return mda == (apic_x2apic_mode(apic) ? + X2APIC_BROADCAST : APIC_BROADCAST); } static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) @@ -591,9 +643,18 @@ static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) return true; if (apic_x2apic_mode(apic)) - return mda == kvm_apic_id(apic); + return mda == kvm_x2apic_id(apic); - return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic)); + /* + * Hotplug hack: Make LAPIC in xAPIC mode also accept interrupts as if + * it were in x2APIC mode. Hotplugged VCPUs start in xAPIC mode and + * this allows unique addressing of VCPUs with APIC ID over 0xff. + * The 0xff condition is needed because writeable xAPIC ID. + */ + if (kvm_x2apic_id(apic) > 0xff && mda == kvm_x2apic_id(apic)) + return true; + + return mda == kvm_xapic_id(apic); } static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) @@ -610,7 +671,6 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) && (logical_id & mda & 0xffff) != 0; logical_id = GET_APIC_LOGICAL_ID(logical_id); - mda = GET_APIC_DEST_FIELD(mda); switch (kvm_lapic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: @@ -627,9 +687,9 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) /* The KVM local APIC implementation has two quirks: * - * - the xAPIC MDA stores the destination at bits 24-31, while this - * is not true of struct kvm_lapic_irq's dest_id field. This is - * just a quirk in the API and is not problematic. + * - Real hardware delivers interrupts destined to x2APIC ID > 0xff to LAPICs + * in xAPIC mode if the "destination & 0xff" matches its xAPIC ID. + * KVM doesn't do that aliasing. * * - in-kernel IOAPIC messages have to be delivered directly to * x2APIC, because the kernel does not support interrupt remapping. @@ -645,13 +705,12 @@ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, struct kvm_lapic *source, struct kvm_lapic *target) { bool ipi = source != NULL; - bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled && - !ipi && dest_id == APIC_BROADCAST && x2apic_mda) + !ipi && dest_id == APIC_BROADCAST && apic_x2apic_mode(target)) return X2APIC_BROADCAST; - return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); + return dest_id; } bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, @@ -1907,9 +1966,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; - apic_debug("%s: vcpu=%p, id=%d, base_msr=" + apic_debug("%s: vcpu=%p, id=0x%x, base_msr=" "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__, - vcpu, kvm_apic_id(apic), + vcpu, kvm_lapic_get_reg(apic, APIC_ID), vcpu->arch.apic_base, apic->base_address); } @@ -2021,17 +2080,13 @@ nomem: int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - int highest_irr; + u32 ppr; if (!apic_enabled(apic)) return -1; - apic_update_ppr(apic); - highest_irr = apic_find_highest_irr(apic); - if ((highest_irr == -1) || - ((highest_irr & 0xF0) <= kvm_lapic_get_reg(apic, APIC_PROCPRI))) - return -1; - return highest_irr; + __apic_update_ppr(apic, &ppr); + return apic_has_interrupt_for_ppr(apic, ppr); } int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) @@ -2067,6 +2122,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) { int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + u32 ppr; if (vector == -1) return -1; @@ -2078,13 +2134,23 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) * because the process would deliver it through the IDT. */ - apic_set_isr(vector, apic); - apic_update_ppr(apic); apic_clear_irr(vector, apic); - if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { - apic_clear_isr(vector, apic); + /* + * For auto-EOI interrupts, there might be another pending + * interrupt above PPR, so check whether to raise another + * KVM_REQ_EVENT. + */ apic_update_ppr(apic); + } else { + /* + * For normal interrupts, PPR has been raised and there cannot + * be a higher-priority pending interrupt---except if there was + * a concurrent interrupt injection, but that would have + * triggered KVM_REQ_EVENT already. + */ + apic_set_isr(vector, apic); + __apic_update_ppr(apic, &ppr); } return vector; @@ -2145,8 +2211,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { - if (kvm_x86_ops->apicv_post_state_restore) - kvm_x86_ops->apicv_post_state_restore(vcpu); + kvm_x86_ops->apicv_post_state_restore(vcpu); kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); kvm_x86_ops->hwapic_isr_update(vcpu, @@ -2220,8 +2285,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32))) + if (kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32))) return; apic_set_tpr(vcpu->arch.apic, data & 0xff); @@ -2273,14 +2338,14 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) max_isr = 0; data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24); - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32)); + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32)); } int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) { if (vapic_addr) { - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apic->vapic_cache, vapic_addr, sizeof(u32))) return -EINVAL; @@ -2374,7 +2439,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) vcpu->arch.pv_eoi.msr_val = data; if (!pv_eoi_enabled(vcpu)) return 0; - return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, + return kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.pv_eoi.data, addr, sizeof(u8)); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ff8039d..bcbe811 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -71,8 +71,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); -void __kvm_apic_update_irr(u32 *pir, void *regs); -void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); +int __kvm_apic_update_irr(u32 *pir, void *regs); +int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); +void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); @@ -203,17 +204,6 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } -static inline u32 kvm_apic_id(struct kvm_lapic *apic) -{ - /* To avoid a race between apic_base and following APIC_ID update when - * switching to x2apic_mode, the x2apic mode returns initial x2apic id. - */ - if (apic_x2apic_mode(apic)) - return apic->vcpu->vcpu_id; - - return kvm_lapic_get_reg(apic, APIC_ID) >> 24; -} - bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7012de4..2fd7586 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -37,6 +37,8 @@ #include <linux/srcu.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/hash.h> +#include <linux/kern_levels.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -129,6 +131,10 @@ module_param(dbg, bool, 0644); #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +/* The mask for the R/X bits in EPT PTEs */ +#define PT64_EPT_READABLE_MASK 0x1ull +#define PT64_EPT_EXECUTABLE_MASK 0x4ull + #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -178,15 +184,40 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_present_mask; +/* + * The mask/value to distinguish a PTE that has been marked not-present for + * access tracking purposes. + * The mask would be either 0 if access tracking is disabled, or + * SPTE_SPECIAL_MASK|VMX_EPT_RWX_MASK if access tracking is enabled. + */ +static u64 __read_mostly shadow_acc_track_mask; +static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; + +/* + * The mask/shift to use for saving the original R/X bits when marking the PTE + * as not-present for access tracking purposes. We do not save the W bit as the + * PTEs being access tracked also need to be dirty tracked, so the W bit will be + * restored only when a write is attempted to the page. + */ +static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK | + PT64_EPT_EXECUTABLE_MASK; +static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT; + static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) { - shadow_mmio_mask = mmio_mask; + shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static inline bool is_access_track_spte(u64 spte) +{ + /* Always false if shadow_acc_track_mask is zero. */ + return (spte & shadow_acc_track_mask) == shadow_acc_track_value; +} + /* * the low bit of the generation number is always presumed to be zero. * This disables mmio caching during memslot updates. The concept is @@ -284,17 +315,35 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) } void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask) + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, + u64 acc_track_mask) { + if (acc_track_mask != 0) + acc_track_mask |= SPTE_SPECIAL_MASK; + shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; shadow_dirty_mask = dirty_mask; shadow_nx_mask = nx_mask; shadow_x_mask = x_mask; shadow_present_mask = p_mask; + shadow_acc_track_mask = acc_track_mask; + WARN_ON(shadow_accessed_mask != 0 && shadow_acc_track_mask != 0); } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +void kvm_mmu_clear_all_pte_masks(void) +{ + shadow_user_mask = 0; + shadow_accessed_mask = 0; + shadow_dirty_mask = 0; + shadow_nx_mask = 0; + shadow_x_mask = 0; + shadow_mmio_mask = 0; + shadow_present_mask = 0; + shadow_acc_track_mask = 0; +} + static int is_cpuid_PSE36(void) { return 1; @@ -307,7 +356,7 @@ static int is_nx(struct kvm_vcpu *vcpu) static int is_shadow_present_pte(u64 pte) { - return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte); + return (pte != 0) && !is_mmio_spte(pte); } static int is_large_pte(u64 pte) @@ -324,6 +373,11 @@ static int is_last_spte(u64 pte, int level) return 0; } +static bool is_executable_pte(u64 spte) +{ + return (spte & (shadow_x_mask | shadow_nx_mask)) == shadow_x_mask; +} + static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -473,7 +527,7 @@ retry: } #endif -static bool spte_is_locklessly_modifiable(u64 spte) +static bool spte_can_locklessly_be_made_writable(u64 spte) { return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) == (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE); @@ -481,36 +535,38 @@ static bool spte_is_locklessly_modifiable(u64 spte) static bool spte_has_volatile_bits(u64 spte) { + if (!is_shadow_present_pte(spte)) + return false; + /* * Always atomically update spte if it can be updated * out of mmu-lock, it can ensure dirty bit is not lost, * also, it can help us to get a stable is_writable_pte() * to ensure tlb flush is not missed. */ - if (spte_is_locklessly_modifiable(spte)) + if (spte_can_locklessly_be_made_writable(spte) || + is_access_track_spte(spte)) return true; - if (!shadow_accessed_mask) - return false; - - if (!is_shadow_present_pte(spte)) - return false; - - if ((spte & shadow_accessed_mask) && - (!is_writable_pte(spte) || (spte & shadow_dirty_mask))) - return false; + if (shadow_accessed_mask) { + if ((spte & shadow_accessed_mask) == 0 || + (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) + return true; + } - return true; + return false; } -static bool spte_is_bit_cleared(u64 old_spte, u64 new_spte, u64 bit_mask) +static bool is_accessed_spte(u64 spte) { - return (old_spte & bit_mask) && !(new_spte & bit_mask); + return shadow_accessed_mask ? spte & shadow_accessed_mask + : !is_access_track_spte(spte); } -static bool spte_is_bit_changed(u64 old_spte, u64 new_spte, u64 bit_mask) +static bool is_dirty_spte(u64 spte) { - return (old_spte & bit_mask) != (new_spte & bit_mask); + return shadow_dirty_mask ? spte & shadow_dirty_mask + : spte & PT_WRITABLE_MASK; } /* Rules for using mmu_spte_set: @@ -525,25 +581,19 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte) __set_spte(sptep, new_spte); } -/* Rules for using mmu_spte_update: - * Update the state bits, it means the mapped pfn is not changed. - * - * Whenever we overwrite a writable spte with a read-only one we - * should flush remote TLBs. Otherwise rmap_write_protect - * will find a read-only spte, even though the writable spte - * might be cached on a CPU's TLB, the return value indicates this - * case. +/* + * Update the SPTE (excluding the PFN), but do not track changes in its + * accessed/dirty status. */ -static bool mmu_spte_update(u64 *sptep, u64 new_spte) +static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) { u64 old_spte = *sptep; - bool ret = false; WARN_ON(!is_shadow_present_pte(new_spte)); if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); - return ret; + return old_spte; } if (!spte_has_volatile_bits(old_spte)) @@ -551,45 +601,62 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) else old_spte = __update_clear_spte_slow(sptep, new_spte); + WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); + + return old_spte; +} + +/* Rules for using mmu_spte_update: + * Update the state bits, it means the mapped pfn is not changed. + * + * Whenever we overwrite a writable spte with a read-only one we + * should flush remote TLBs. Otherwise rmap_write_protect + * will find a read-only spte, even though the writable spte + * might be cached on a CPU's TLB, the return value indicates this + * case. + * + * Returns true if the TLB needs to be flushed + */ +static bool mmu_spte_update(u64 *sptep, u64 new_spte) +{ + bool flush = false; + u64 old_spte = mmu_spte_update_no_track(sptep, new_spte); + + if (!is_shadow_present_pte(old_spte)) + return false; + /* * For the spte updated out of mmu-lock is safe, since * we always atomically update it, see the comments in * spte_has_volatile_bits(). */ - if (spte_is_locklessly_modifiable(old_spte) && + if (spte_can_locklessly_be_made_writable(old_spte) && !is_writable_pte(new_spte)) - ret = true; - - if (!shadow_accessed_mask) { - /* - * We don't set page dirty when dropping non-writable spte. - * So do it now if the new spte is becoming non-writable. - */ - if (ret) - kvm_set_pfn_dirty(spte_to_pfn(old_spte)); - return ret; - } + flush = true; /* - * Flush TLB when accessed/dirty bits are changed in the page tables, + * Flush TLB when accessed/dirty states are changed in the page tables, * to guarantee consistency between TLB and page tables. */ - if (spte_is_bit_changed(old_spte, new_spte, - shadow_accessed_mask | shadow_dirty_mask)) - ret = true; - if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask)) + if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) { + flush = true; kvm_set_pfn_accessed(spte_to_pfn(old_spte)); - if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask)) + } + + if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) { + flush = true; kvm_set_pfn_dirty(spte_to_pfn(old_spte)); + } - return ret; + return flush; } /* * Rules for using mmu_spte_clear_track_bits: * It sets the sptep from present to nonpresent, and track the * state bits, it is used to clear the last level sptep. + * Returns non-zero if the PTE was previously valid. */ static int mmu_spte_clear_track_bits(u64 *sptep) { @@ -613,11 +680,12 @@ static int mmu_spte_clear_track_bits(u64 *sptep) */ WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn))); - if (!shadow_accessed_mask || old_spte & shadow_accessed_mask) + if (is_accessed_spte(old_spte)) kvm_set_pfn_accessed(pfn); - if (old_spte & (shadow_dirty_mask ? shadow_dirty_mask : - PT_WRITABLE_MASK)) + + if (is_dirty_spte(old_spte)) kvm_set_pfn_dirty(pfn); + return 1; } @@ -636,6 +704,78 @@ static u64 mmu_spte_get_lockless(u64 *sptep) return __get_spte_lockless(sptep); } +static u64 mark_spte_for_access_track(u64 spte) +{ + if (shadow_accessed_mask != 0) + return spte & ~shadow_accessed_mask; + + if (shadow_acc_track_mask == 0 || is_access_track_spte(spte)) + return spte; + + /* + * Making an Access Tracking PTE will result in removal of write access + * from the PTE. So, verify that we will be able to restore the write + * access in the fast page fault path later on. + */ + WARN_ONCE((spte & PT_WRITABLE_MASK) && + !spte_can_locklessly_be_made_writable(spte), + "kvm: Writable SPTE is not locklessly dirty-trackable\n"); + + WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask << + shadow_acc_track_saved_bits_shift), + "kvm: Access Tracking saved bit locations are not zero\n"); + + spte |= (spte & shadow_acc_track_saved_bits_mask) << + shadow_acc_track_saved_bits_shift; + spte &= ~shadow_acc_track_mask; + spte |= shadow_acc_track_value; + + return spte; +} + +/* Restore an acc-track PTE back to a regular PTE */ +static u64 restore_acc_track_spte(u64 spte) +{ + u64 new_spte = spte; + u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift) + & shadow_acc_track_saved_bits_mask; + + WARN_ON_ONCE(!is_access_track_spte(spte)); + + new_spte &= ~shadow_acc_track_mask; + new_spte &= ~(shadow_acc_track_saved_bits_mask << + shadow_acc_track_saved_bits_shift); + new_spte |= saved_bits; + + return new_spte; +} + +/* Returns the Accessed status of the PTE and resets it at the same time. */ +static bool mmu_spte_age(u64 *sptep) +{ + u64 spte = mmu_spte_get_lockless(sptep); + + if (!is_accessed_spte(spte)) + return false; + + if (shadow_accessed_mask) { + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + } else { + /* + * Capture the dirty status of the page, so that it doesn't get + * lost when the SPTE is marked for access tracking. + */ + if (is_writable_pte(spte)) + kvm_set_pfn_dirty(spte_to_pfn(spte)); + + spte = mark_spte_for_access_track(spte); + mmu_spte_update_no_track(sptep, spte); + } + + return true; +} + static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { /* @@ -1212,7 +1352,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) u64 spte = *sptep; if (!is_writable_pte(spte) && - !(pt_protect && spte_is_locklessly_modifiable(spte))) + !(pt_protect && spte_can_locklessly_be_made_writable(spte))) return false; rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); @@ -1420,7 +1560,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, restart: for_each_rmap_spte(rmap_head, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); + sptep, *sptep, gfn, level); need_flush = 1; @@ -1433,7 +1573,8 @@ restart: new_spte &= ~PT_WRITABLE_MASK; new_spte &= ~SPTE_HOST_WRITEABLE; - new_spte &= ~shadow_accessed_mask; + + new_spte = mark_spte_for_access_track(new_spte); mmu_spte_clear_track_bits(sptep); mmu_spte_set(sptep, new_spte); @@ -1595,15 +1736,8 @@ static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct rmap_iterator uninitialized_var(iter); int young = 0; - BUG_ON(!shadow_accessed_mask); - - for_each_rmap_spte(rmap_head, &iter, sptep) { - if (*sptep & shadow_accessed_mask) { - young = 1; - clear_bit((ffs(shadow_accessed_mask) - 1), - (unsigned long *)sptep); - } - } + for_each_rmap_spte(rmap_head, &iter, sptep) + young |= mmu_spte_age(sptep); trace_kvm_age_page(gfn, level, slot, young); return young; @@ -1615,24 +1749,20 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, { u64 *sptep; struct rmap_iterator iter; - int young = 0; /* - * If there's no access bit in the secondary pte set by the - * hardware it's up to gup-fast/gup to set the access bit in - * the primary pte or in the page structure. + * If there's no access bit in the secondary pte set by the hardware and + * fast access tracking is also not enabled, it's up to gup-fast/gup to + * set the access bit in the primary pte or in the page structure. */ - if (!shadow_accessed_mask) + if (!shadow_accessed_mask && !shadow_acc_track_mask) goto out; - for_each_rmap_spte(rmap_head, &iter, sptep) { - if (*sptep & shadow_accessed_mask) { - young = 1; - break; - } - } + for_each_rmap_spte(rmap_head, &iter, sptep) + if (is_accessed_spte(*sptep)) + return 1; out: - return young; + return 0; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -1660,7 +1790,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) * This has some overhead, but not as much as the cost of swapping * out actively used pages or breaking up actively used hugepages. */ - if (!shadow_accessed_mask) + if (!shadow_accessed_mask && !shadow_acc_track_mask) return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); @@ -1713,7 +1843,7 @@ static void kvm_mmu_free_page(struct kvm_mmu_page *sp) static unsigned kvm_page_table_hashfn(gfn_t gfn) { - return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1); + return hash_64(gfn, KVM_MMU_HASH_SHIFT); } static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu, @@ -1904,17 +2034,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, * since it has been deleted from active_mmu_pages but still can be found * at hast list. * - * for_each_gfn_valid_sp() has skipped that kind of pages. + * for_each_valid_sp() has skipped that kind of pages. */ -#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ +#define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if ((_sp)->gfn != (_gfn) || is_obsolete_sp((_kvm), (_sp)) \ - || (_sp)->role.invalid) {} else + if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) { \ + } else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ - for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ - if ((_sp)->role.direct) {} else + for_each_valid_sp(_kvm, _sp, _gfn) \ + if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else /* @sp->gfn should be write-protected at the call site */ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -2116,6 +2246,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; bool need_sync = false; bool flush = false; + int collisions = 0; LIST_HEAD(invalid_list); role = vcpu->arch.mmu.base_role; @@ -2130,7 +2261,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - for_each_gfn_valid_sp(vcpu->kvm, sp, gfn) { + for_each_valid_sp(vcpu->kvm, sp, gfn) { + if (sp->gfn != gfn) { + collisions++; + continue; + } + if (!need_sync && sp->unsync) need_sync = true; @@ -2153,7 +2289,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); - return sp; + goto out; } ++vcpu->kvm->stat.mmu_cache_miss; @@ -2183,6 +2319,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, trace_kvm_mmu_get_page(sp, true); kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); +out: + if (collisions > vcpu->kvm->stat.max_mmu_page_hash_collisions) + vcpu->kvm->stat.max_mmu_page_hash_collisions = collisions; return sp; } @@ -2583,6 +2722,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= shadow_dirty_mask; } + if (speculative) + spte = mark_spte_for_access_track(spte); + set_pte: if (mmu_spte_update(sptep, spte)) kvm_flush_remote_tlbs(vcpu->kvm); @@ -2636,7 +2778,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", is_large_pte(*sptep)? "2MB" : "4kB", - *sptep & PT_PRESENT_MASK ?"RW":"R", gfn, + *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn, *sptep, sptep); if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; @@ -2869,33 +3011,43 @@ static bool page_fault_can_be_fast(u32 error_code) if (unlikely(error_code & PFERR_RSVD_MASK)) return false; + /* See if the page fault is due to an NX violation */ + if (unlikely(((error_code & (PFERR_FETCH_MASK | PFERR_PRESENT_MASK)) + == (PFERR_FETCH_MASK | PFERR_PRESENT_MASK)))) + return false; + /* - * #PF can be fast only if the shadow page table is present and it - * is caused by write-protect, that means we just need change the - * W bit of the spte which can be done out of mmu-lock. + * #PF can be fast if: + * 1. The shadow page table entry is not present, which could mean that + * the fault is potentially caused by access tracking (if enabled). + * 2. The shadow page table entry is present and the fault + * is caused by write-protect, that means we just need change the W + * bit of the spte which can be done out of mmu-lock. + * + * However, if access tracking is disabled we know that a non-present + * page must be a genuine page fault where we have to create a new SPTE. + * So, if access tracking is disabled, we return true only for write + * accesses to a present page. */ - if (!(error_code & PFERR_PRESENT_MASK) || - !(error_code & PFERR_WRITE_MASK)) - return false; - return true; + return shadow_acc_track_mask != 0 || + ((error_code & (PFERR_WRITE_MASK | PFERR_PRESENT_MASK)) + == (PFERR_WRITE_MASK | PFERR_PRESENT_MASK)); } +/* + * Returns true if the SPTE was fixed successfully. Otherwise, + * someone else modified the SPTE from its original value. + */ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *sptep, u64 spte) + u64 *sptep, u64 old_spte, u64 new_spte) { gfn_t gfn; WARN_ON(!sp->role.direct); /* - * The gfn of direct spte is stable since it is calculated - * by sp->gfn. - */ - gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); - - /* * Theoretically we could also set dirty bit (and flush TLB) here in * order to eliminate unnecessary PML logging. See comments in * set_spte. But fast_page_fault is very unlikely to happen with PML @@ -2907,12 +3059,33 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * * Compare with set_spte where instead shadow_dirty_mask is set. */ - if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) + if (cmpxchg64(sptep, old_spte, new_spte) != old_spte) + return false; + + if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) { + /* + * The gfn of direct spte is stable since it is + * calculated by sp->gfn. + */ + gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); kvm_vcpu_mark_page_dirty(vcpu, gfn); + } return true; } +static bool is_access_allowed(u32 fault_err_code, u64 spte) +{ + if (fault_err_code & PFERR_FETCH_MASK) + return is_executable_pte(spte); + + if (fault_err_code & PFERR_WRITE_MASK) + return is_writable_pte(spte); + + /* Fault was on Read access */ + return spte & PT_PRESENT_MASK; +} + /* * Return value: * - true: let the vcpu to access on the same address again. @@ -2923,8 +3096,9 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; - bool ret = false; + bool fault_handled = false; u64 spte = 0ull; + uint retry_count = 0; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return false; @@ -2933,66 +3107,93 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, return false; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) - if (!is_shadow_present_pte(spte) || iterator.level < level) + + do { + u64 new_spte; + + for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + if (!is_shadow_present_pte(spte) || + iterator.level < level) + break; + + sp = page_header(__pa(iterator.sptep)); + if (!is_last_spte(spte, sp->role.level)) break; - /* - * If the mapping has been changed, let the vcpu fault on the - * same address again. - */ - if (!is_shadow_present_pte(spte)) { - ret = true; - goto exit; - } + /* + * Check whether the memory access that caused the fault would + * still cause it if it were to be performed right now. If not, + * then this is a spurious fault caused by TLB lazily flushed, + * or some other CPU has already fixed the PTE after the + * current CPU took the fault. + * + * Need not check the access of upper level table entries since + * they are always ACC_ALL. + */ + if (is_access_allowed(error_code, spte)) { + fault_handled = true; + break; + } - sp = page_header(__pa(iterator.sptep)); - if (!is_last_spte(spte, sp->role.level)) - goto exit; + new_spte = spte; - /* - * Check if it is a spurious fault caused by TLB lazily flushed. - * - * Need not check the access of upper level table entries since - * they are always ACC_ALL. - */ - if (is_writable_pte(spte)) { - ret = true; - goto exit; - } + if (is_access_track_spte(spte)) + new_spte = restore_acc_track_spte(new_spte); - /* - * Currently, to simplify the code, only the spte write-protected - * by dirty-log can be fast fixed. - */ - if (!spte_is_locklessly_modifiable(spte)) - goto exit; + /* + * Currently, to simplify the code, write-protection can + * be removed in the fast path only if the SPTE was + * write-protected for dirty-logging or access tracking. + */ + if ((error_code & PFERR_WRITE_MASK) && + spte_can_locklessly_be_made_writable(spte)) + { + new_spte |= PT_WRITABLE_MASK; - /* - * Do not fix write-permission on the large spte since we only dirty - * the first page into the dirty-bitmap in fast_pf_fix_direct_spte() - * that means other pages are missed if its slot is dirty-logged. - * - * Instead, we let the slow page fault path create a normal spte to - * fix the access. - * - * See the comments in kvm_arch_commit_memory_region(). - */ - if (sp->role.level > PT_PAGE_TABLE_LEVEL) - goto exit; + /* + * Do not fix write-permission on the large spte. Since + * we only dirty the first page into the dirty-bitmap in + * fast_pf_fix_direct_spte(), other pages are missed + * if its slot has dirty logging enabled. + * + * Instead, we let the slow page fault path create a + * normal spte to fix the access. + * + * See the comments in kvm_arch_commit_memory_region(). + */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + break; + } + + /* Verify that the fault can be handled in the fast path */ + if (new_spte == spte || + !is_access_allowed(error_code, new_spte)) + break; + + /* + * Currently, fast page fault only works for direct mapping + * since the gfn is not stable for indirect shadow page. See + * Documentation/virtual/kvm/locking.txt to get more detail. + */ + fault_handled = fast_pf_fix_direct_spte(vcpu, sp, + iterator.sptep, spte, + new_spte); + if (fault_handled) + break; + + if (++retry_count > 4) { + printk_once(KERN_WARNING + "kvm: Fast #PF retrying more than 4 times.\n"); + break; + } + + } while (true); - /* - * Currently, fast page fault only works for direct mapping since - * the gfn is not stable for indirect shadow page. - * See Documentation/virtual/kvm/locking.txt to get more detail. - */ - ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte); -exit: trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, - spte, ret); + spte, fault_handled); walk_shadow_page_lockless_end(vcpu); - return ret; + return fault_handled; } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, @@ -5063,6 +5264,8 @@ static void mmu_destroy_caches(void) int kvm_mmu_module_init(void) { + kvm_mmu_clear_all_pte_masks(); + pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, 0, NULL); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 08a4d3a..d1efe2c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -971,8 +971,8 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) * a particular vCPU. */ #define SVM_VM_DATA_HASH_BITS 8 -DECLARE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); -static spinlock_t svm_vm_data_hash_lock; +static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); +static DEFINE_SPINLOCK(svm_vm_data_hash_lock); /* Note: * This function is called from IOMMU driver to notify @@ -1077,8 +1077,6 @@ static __init int svm_hardware_setup(void) } else { pr_info("AVIC enabled\n"); - hash_init(svm_vm_data_hash); - spin_lock_init(&svm_vm_data_hash_lock); amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); } } @@ -1159,7 +1157,6 @@ static void init_vmcb(struct vcpu_svm *svm) struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; - svm->vcpu.fpu_active = 1; svm->vcpu.arch.hflags = 0; set_cr_intercept(svm, INTERCEPT_CR0_READ); @@ -1901,15 +1898,12 @@ static void update_cr0_intercept(struct vcpu_svm *svm) ulong gcr0 = svm->vcpu.arch.cr0; u64 *hcr0 = &svm->vmcb->save.cr0; - if (!svm->vcpu.fpu_active) - *hcr0 |= SVM_CR0_SELECTIVE_MASK; - else - *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) - | (gcr0 & SVM_CR0_SELECTIVE_MASK); + *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) + | (gcr0 & SVM_CR0_SELECTIVE_MASK); mark_dirty(svm->vmcb, VMCB_CR); - if (gcr0 == *hcr0 && svm->vcpu.fpu_active) { + if (gcr0 == *hcr0) { clr_cr_intercept(svm, INTERCEPT_CR0_READ); clr_cr_intercept(svm, INTERCEPT_CR0_WRITE); } else { @@ -1940,8 +1934,6 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!npt_enabled) cr0 |= X86_CR0_PG | X86_CR0_WP; - if (!vcpu->fpu_active) - cr0 |= X86_CR0_TS; /* * re-enable caching here because the QEMU bios * does not do it - this results in some delay at @@ -2160,22 +2152,6 @@ static int ac_interception(struct vcpu_svm *svm) return 1; } -static void svm_fpu_activate(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - clr_exception_intercept(svm, NM_VECTOR); - - svm->vcpu.fpu_active = 1; - update_cr0_intercept(svm); -} - -static int nm_interception(struct vcpu_svm *svm) -{ - svm_fpu_activate(&svm->vcpu); - return 1; -} - static bool is_erratum_383(void) { int err, i; @@ -2573,9 +2549,6 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) if (!npt_enabled && svm->apf_reason == 0) return NESTED_EXIT_HOST; break; - case SVM_EXIT_EXCP_BASE + NM_VECTOR: - nm_interception(svm); - break; default: break; } @@ -4020,7 +3993,6 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, - [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, [SVM_EXIT_INTR] = intr_interception, @@ -4182,6 +4154,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + vcpu->arch.gpa_available = (exit_code == SVM_EXIT_NPF); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -4357,11 +4331,6 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - return; -} - static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { kvm_lapic_set_irr(vec, vcpu->arch.apic); @@ -5077,14 +5046,6 @@ static bool svm_has_wbinvd_exit(void) return true; } -static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - set_exception_intercept(svm, NM_VECTOR); - update_cr0_intercept(svm); -} - #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -5345,9 +5306,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_pkru = svm_get_pkru, - .fpu_activate = svm_fpu_activate, - .fpu_deactivate = svm_fpu_deactivate, - .tlb_flush = svm_flush_tlb, .run = svm_vcpu_run, @@ -5371,7 +5329,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_enable_apicv = svm_get_enable_apicv, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, - .sync_pir_to_irr = svm_sync_pir_to_irr, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, .apicv_post_state_restore = avic_post_state_restore, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a236dec..ef4ba71 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1856,7 +1856,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); + (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -1865,8 +1865,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = ~0; if (enable_ept) eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ - if (vcpu->fpu_active) - eb &= ~(1u << NM_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass @@ -1992,19 +1990,6 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, m->host[i].value = host_val; } -static void reload_tss(void) -{ - /* - * VT restores TR but not its size. Useless. - */ - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); - struct desc_struct *descs; - - descs = (void *)gdt->address; - descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ - load_TR_desc(); -} - static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { u64 guest_efer = vmx->vcpu.arch.efer; @@ -2059,41 +2044,36 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) } } +#ifdef CONFIG_X86_32 +/* + * On 32-bit kernels, VM exits still load the FS and GS bases from the + * VMCS rather than the segment table. KVM uses this helper to figure + * out the current bases to poke them into the VMCS before entry. + */ static unsigned long segment_base(u16 selector) { struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *d; - unsigned long table_base; + struct desc_struct *table; unsigned long v; - if (!(selector & ~3)) + if (!(selector & ~SEGMENT_RPL_MASK)) return 0; - table_base = gdt->address; + table = (struct desc_struct *)gdt->address; - if (selector & 4) { /* from ldt */ + if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); - if (!(ldt_selector & ~3)) + if (!(ldt_selector & ~SEGMENT_RPL_MASK)) return 0; - table_base = segment_base(ldt_selector); + table = (struct desc_struct *)segment_base(ldt_selector); } - d = (struct desc_struct *)(table_base + (selector & ~7)); - v = get_desc_base(d); -#ifdef CONFIG_X86_64 - if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; -#endif + v = get_desc_base(&table[selector >> 3]); return v; } - -static inline unsigned long kvm_read_tr_base(void) -{ - u16 tr; - asm("str %0" : "=g"(tr)); - return segment_base(tr); -} +#endif static void vmx_save_host_state(struct kvm_vcpu *vcpu) { @@ -2179,7 +2159,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(es, vmx->host_state.es_sel); } #endif - reload_tss(); + invalidate_tss_limit(); #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif @@ -2294,10 +2274,19 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* * Linux uses per-cpu TSS and GDT, so set these when switching - * processors. + * processors. See 22.2.4. */ - vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ - vmcs_writel(HOST_GDTR_BASE, gdt->address); /* 22.2.4 */ + vmcs_writel(HOST_TR_BASE, + (unsigned long)this_cpu_ptr(&cpu_tss)); + vmcs_writel(HOST_GDTR_BASE, gdt->address); + + /* + * VM exits change the host TR limit to 0x67 after a VM + * exit. This is okay, since 0x67 covers everything except + * the IO bitmap and have have code to handle the IO bitmap + * being lost after a VM exit. + */ + BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67); rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -2340,25 +2329,6 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) } } -static void vmx_fpu_activate(struct kvm_vcpu *vcpu) -{ - ulong cr0; - - if (vcpu->fpu_active) - return; - vcpu->fpu_active = 1; - cr0 = vmcs_readl(GUEST_CR0); - cr0 &= ~(X86_CR0_TS | X86_CR0_MP); - cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP); - vmcs_writel(GUEST_CR0, cr0); - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; - if (is_guest_mode(vcpu)) - vcpu->arch.cr0_guest_owned_bits &= - ~get_vmcs12(vcpu)->cr0_guest_host_mask; - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); -} - static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); /* @@ -2377,33 +2347,6 @@ static inline unsigned long nested_read_cr4(struct vmcs12 *fields) (fields->cr4_read_shadow & fields->cr4_guest_host_mask); } -static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) -{ - /* Note that there is no vcpu->fpu_active = 0 here. The caller must - * set this *before* calling this function. - */ - vmx_decache_cr0_guest_bits(vcpu); - vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP); - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = 0; - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - if (is_guest_mode(vcpu)) { - /* - * L1's specified read shadow might not contain the TS bit, - * so now that we turned on shadowing of this bit, we need to - * set this bit of the shadow. Like in nested_vmx_run we need - * nested_read_cr0(vmcs12), but vmcs12->guest_cr0 is not yet - * up-to-date here because we just decached cr0.TS (and we'll - * only update vmcs12->guest_cr0 on nested exit). - */ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) | - (vcpu->arch.cr0 & X86_CR0_TS); - vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12)); - } else - vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); -} - static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags, save_rflags; @@ -3962,7 +3905,7 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) } vmcs_write16(sf->selector, var.selector); - vmcs_write32(sf->base, var.base); + vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } @@ -4232,9 +4175,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (enable_ept) ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); - if (!vcpu->fpu_active) - hw_cr0 |= X86_CR0_TS | X86_CR0_MP; - vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; @@ -4953,7 +4893,7 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } -static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; @@ -4964,19 +4904,15 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmx->nested.pi_pending) { vmx->nested.pi_pending = false; if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return 0; + return; max_irr = find_last_bit( (unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr == 256) - return 0; + return; vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4987,7 +4923,6 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } - return 0; } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -5056,26 +4991,12 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_pir(vector, &vmx->pi_desc)) return; - r = pi_test_and_set_on(&vmx->pi_desc); - kvm_make_request(KVM_REQ_EVENT, vcpu); - if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu)) - kvm_vcpu_kick(vcpu); -} - -static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!pi_test_on(&vmx->pi_desc)) + /* If a previous notification has sent the IPI, nothing to do. */ + if (pi_test_and_set_on(&vmx->pi_desc)) return; - pi_clear_on(&vmx->pi_desc); - /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. - * But on x86 this is just a compiler barrier anyway. - */ - smp_mb__after_atomic(); - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + kvm_vcpu_kick(vcpu); } /* @@ -5236,10 +5157,8 @@ static void ept_set_mmio_spte_mask(void) /* * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). - * Also, magic bits (0x3ull << 62) is set to quickly identify mmio - * spte. */ - kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull); + kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE); } #define VMX_XSS_EXIT_BITMAP 0 @@ -5342,7 +5261,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl); - vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); + vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; + vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); + set_cr4_guest_host_mask(vmx); if (vmx_xsaves_supported()) @@ -5446,7 +5367,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); - vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); vpid_sync_context(vmx->vpid); @@ -5480,26 +5401,20 @@ static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_INTR_PENDING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - if (!cpu_has_virtual_nmis() || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { enable_irq_window(vcpu); return; } - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_NMI_PENDING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -5725,11 +5640,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (is_nmi(intr_info)) return 1; /* already handled by vmx_vcpu_run() */ - if (is_no_device(intr_info)) { - vmx_fpu_activate(vcpu); - return 1; - } - if (is_invalid_opcode(intr_info)) { if (is_guest_mode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -5919,22 +5829,6 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) return kvm_set_cr4(vcpu, val); } -/* called to set cr0 as appropriate for clts instruction exit. */ -static void handle_clts(struct kvm_vcpu *vcpu) -{ - if (is_guest_mode(vcpu)) { - /* - * We get here when L2 did CLTS, and L1 didn't shadow CR0.TS - * but we did (!fpu_active). We need to keep GUEST_CR0.TS on, - * just pretend it's off (also in arch.cr0 for fpu_activate). - */ - vmcs_writel(CR0_READ_SHADOW, - vmcs_readl(CR0_READ_SHADOW) & ~X86_CR0_TS); - vcpu->arch.cr0 &= ~X86_CR0_TS; - } else - vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); -} - static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; @@ -5980,9 +5874,9 @@ static int handle_cr(struct kvm_vcpu *vcpu) } break; case 2: /* clts */ - handle_clts(vcpu); + WARN_ONCE(1, "Guest should always own CR0.TS"); + vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - vmx_fpu_activate(vcpu); return kvm_skip_emulated_instruction(vcpu); case 1: /*mov from cr*/ switch (cr) { @@ -6152,18 +6046,14 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_apic_update_ppr(vcpu); return 1; } static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - /* clear pending irq */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_INTR_PENDING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -6374,15 +6264,22 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - /* it is a read fault? */ - error_code = (exit_qualification << 2) & PFERR_USER_MASK; - /* it is a write fault? */ - error_code |= exit_qualification & PFERR_WRITE_MASK; - /* It is a fetch fault? */ - error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK; - /* ept page table is present? */ - error_code |= (exit_qualification & 0x38) != 0; - + /* Is it a read fault? */ + error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) + ? PFERR_USER_MASK : 0; + /* Is it a write fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) + ? PFERR_WRITE_MASK : 0; + /* Is it a fetch fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) + ? PFERR_FETCH_MASK : 0; + /* ept page table entry is present? */ + error_code |= (exit_qualification & + (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE | + EPT_VIOLATION_EXECUTABLE)) + ? PFERR_PRESENT_MASK : 0; + + vcpu->arch.gpa_available = true; vcpu->arch.exit_qualification = exit_qualification; return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -6400,6 +6297,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) } ret = handle_mmio_page_fault(vcpu, gpa, true); + vcpu->arch.gpa_available = true; if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -6421,12 +6319,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - /* clear pending NMI */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_NMI_PENDING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -6572,6 +6466,19 @@ static void wakeup_handler(void) spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); } +void vmx_enable_tdp(void) +{ + kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, + enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull, + enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK, + cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, + enable_ept_ad_bits ? 0ull : VMX_EPT_RWX_MASK); + + ept_set_mmio_spte_mask(); + kvm_enable_tdp(); +} + static __init int hardware_setup(void) { int r = -ENOMEM, i, msr; @@ -6651,8 +6558,10 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; - if (!cpu_has_vmx_apicv()) + if (!cpu_has_vmx_apicv()) { enable_apicv = 0; + kvm_x86_ops->sync_pir_to_irr = NULL; + } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; @@ -6697,16 +6606,9 @@ static __init int hardware_setup(void) /* SELF-IPI */ vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) { - kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, - (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, - (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK, - cpu_has_vmx_ept_execute_only() ? - 0ull : VMX_EPT_READABLE_MASK); - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); - } else + if (enable_ept) + vmx_enable_tdp(); + else kvm_disable_tdp(); update_ple_window_actual_max(); @@ -7085,13 +6987,18 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, } page = nested_get_page(vcpu, vmptr); - if (page == NULL || - *(u32 *)kmap(page) != VMCS12_REVISION) { + if (page == NULL) { nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); return kvm_skip_emulated_instruction(vcpu); } kunmap(page); + nested_release_page_clean(page); vmx->nested.vmxon_ptr = vmptr; break; case EXIT_REASON_VMCLEAR: @@ -7129,6 +7036,53 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, return 0; } +static int enter_vmx_operation(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs *shadow_vmcs; + + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); + if (!vmx->nested.cached_vmcs12) + goto out_cached_vmcs12; + + if (enable_shadow_vmcs) { + shadow_vmcs = alloc_vmcs(); + if (!shadow_vmcs) + goto out_shadow_vmcs; + /* mark vmcs as shadow */ + shadow_vmcs->revision_id |= (1u << 31); + /* init shadow vmcs */ + vmcs_clear(shadow_vmcs); + vmx->vmcs01.shadow_vmcs = shadow_vmcs; + } + + INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); + vmx->nested.vmcs02_num = 0; + + hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + + vmx->nested.vmxon = true; + return 0; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; +} + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -7139,9 +7093,9 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, */ static int handle_vmon(struct kvm_vcpu *vcpu) { + int ret; struct kvm_segment cs; struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; @@ -7168,9 +7122,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) - return 1; - if (vmx->nested.vmxon) { nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); return kvm_skip_emulated_instruction(vcpu); @@ -7182,48 +7133,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } - - vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); - if (!vmx->nested.cached_vmcs12) - goto out_cached_vmcs12; - - if (enable_shadow_vmcs) { - shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) - goto out_shadow_vmcs; - /* mark vmcs as shadow */ - shadow_vmcs->revision_id |= (1u << 31); - /* init shadow vmcs */ - vmcs_clear(shadow_vmcs); - vmx->vmcs01.shadow_vmcs = shadow_vmcs; - } - - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); - vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; - - vmx->nested.vmxon = true; + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + return 1; + + ret = enter_vmx_operation(vcpu); + if (ret) + return ret; nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); - -out_shadow_vmcs: - kfree(vmx->nested.cached_vmcs12); - -out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); - -out_msr_bitmap: - return -ENOMEM; } /* @@ -7672,6 +7590,18 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } +static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) +{ + vmx->nested.current_vmptr = vmptr; + if (enable_shadow_vmcs) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); + vmcs_write64(VMCS_LINK_POINTER, + __pa(vmx->vmcs01.shadow_vmcs)); + vmx->nested.sync_shadow_vmcs = true; + } +} + /* Emulate the VMPTRLD instruction */ static int handle_vmptrld(struct kvm_vcpu *vcpu) { @@ -7702,7 +7632,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) } nested_release_vmcs12(vmx); - vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; /* @@ -7711,14 +7640,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) */ memcpy(vmx->nested.cached_vmcs12, vmx->nested.current_vmcs12, VMCS12_SIZE); - - if (enable_shadow_vmcs) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, - __pa(vmx->vmcs01.shadow_vmcs)); - vmx->nested.sync_shadow_vmcs = true; - } + set_current_vmptr(vmx, vmptr); } nested_vmx_succeed(vcpu); @@ -8191,8 +8113,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: - if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return false; return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); @@ -8350,7 +8270,7 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(sel), + name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); @@ -8514,6 +8434,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 vectoring_info = vmx->idt_vectoring_info; trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + vcpu->arch.gpa_available = false; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more @@ -8732,6 +8653,27 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } +static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int max_irr; + + WARN_ON(!vcpu->arch.apicv_active); + if (pi_test_on(&vmx->pi_desc)) { + pi_clear_on(&vmx->pi_desc); + /* + * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * But on x86 this is just a compiler barrier anyway. + */ + smp_mb__after_atomic(); + max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + } else { + max_irr = kvm_lapic_find_highest_irr(vcpu); + } + vmx_hwapic_irr_update(vcpu, max_irr); + return max_irr; +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -8743,6 +8685,14 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } +static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + pi_clear_on(&vmx->pi_desc); + memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); +} + static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9588,17 +9538,16 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, kvm_inject_page_fault(vcpu, fault); } -static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, +static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12); + +static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); + u64 hpa; if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - if (!PAGE_ALIGNED(vmcs12->apic_access_addr) || - vmcs12->apic_access_addr >> maxphyaddr) - return false; - /* * Translate L1 physical address to host physical * address for vmcs02. Keep the page pinned, so this @@ -9609,59 +9558,80 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, nested_release_page(vmx->nested.apic_access_page); vmx->nested.apic_access_page = nested_get_page(vcpu, vmcs12->apic_access_addr); + /* + * If translation failed, no matter: This feature asks + * to exit when accessing the given address, and if it + * can never be accessed, this feature won't do + * anything anyway. + */ + if (vmx->nested.apic_access_page) { + hpa = page_to_phys(vmx->nested.apic_access_page); + vmcs_write64(APIC_ACCESS_ADDR, hpa); + } else { + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + } + } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && + cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + kvm_vcpu_reload_apic_access_page(vcpu); } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { - if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) || - vmcs12->virtual_apic_page_addr >> maxphyaddr) - return false; - if (vmx->nested.virtual_apic_page) /* shouldn't happen */ nested_release_page(vmx->nested.virtual_apic_page); vmx->nested.virtual_apic_page = nested_get_page(vcpu, vmcs12->virtual_apic_page_addr); /* - * Failing the vm entry is _not_ what the processor does - * but it's basically the only possibility we have. - * We could still enter the guest if CR8 load exits are - * enabled, CR8 store exits are enabled, and virtualize APIC - * access is disabled; in this case the processor would never - * use the TPR shadow and we could simply clear the bit from - * the execution control. But such a configuration is useless, - * so let's keep the code simple. + * If translation failed, VM entry will fail because + * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull. + * Failing the vm entry is _not_ what the processor + * does but it's basically the only possibility we + * have. We could still enter the guest if CR8 load + * exits are enabled, CR8 store exits are enabled, and + * virtualize APIC access is disabled; in this case + * the processor would never use the TPR shadow and we + * could simply clear the bit from the execution + * control. But such a configuration is useless, so + * let's keep the code simple. */ - if (!vmx->nested.virtual_apic_page) - return false; + if (vmx->nested.virtual_apic_page) { + hpa = page_to_phys(vmx->nested.virtual_apic_page); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa); + } } if (nested_cpu_has_posted_intr(vmcs12)) { - if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) || - vmcs12->posted_intr_desc_addr >> maxphyaddr) - return false; - if (vmx->nested.pi_desc_page) { /* shouldn't happen */ kunmap(vmx->nested.pi_desc_page); nested_release_page(vmx->nested.pi_desc_page); } vmx->nested.pi_desc_page = nested_get_page(vcpu, vmcs12->posted_intr_desc_addr); - if (!vmx->nested.pi_desc_page) - return false; - vmx->nested.pi_desc = (struct pi_desc *)kmap(vmx->nested.pi_desc_page); if (!vmx->nested.pi_desc) { nested_release_page_clean(vmx->nested.pi_desc_page); - return false; + return; } vmx->nested.pi_desc = (struct pi_desc *)((void *)vmx->nested.pi_desc + (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); + vmcs_write64(POSTED_INTR_DESC_ADDR, + page_to_phys(vmx->nested.pi_desc_page) + + (unsigned long)(vmcs12->posted_intr_desc_addr & + (PAGE_SIZE - 1))); } - - return true; + if (cpu_has_vmx_msr_bitmap() && + nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; + else + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); } static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) @@ -9730,11 +9700,6 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, return false; } msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9982,7 +9947,7 @@ static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) * is assigned to entry_failure_code on failure. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, - unsigned long *entry_failure_code) + u32 *entry_failure_code) { if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) { if (!nested_cr3_valid(vcpu, cr3)) { @@ -10022,7 +9987,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - unsigned long *entry_failure_code) + bool from_vmentry, u32 *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; @@ -10065,21 +10030,26 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - vmcs12->vm_entry_intr_info_field); - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs12->vm_entry_exception_error_code); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs12->vm_entry_instruction_len); - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, - vmcs12->guest_interruptibility_info); + if (from_vmentry) { + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + vmcs12->vm_entry_intr_info_field); + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, + vmcs12->vm_entry_exception_error_code); + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, + vmcs12->vm_entry_instruction_len); + vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, + vmcs12->guest_interruptibility_info); + } else { + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); + } vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, @@ -10108,12 +10078,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, - page_to_phys(vmx->nested.pi_desc_page) + - (unsigned long)(vmcs12->posted_intr_desc_addr & - (PAGE_SIZE - 1))); - } else + } else { exec_control &= ~PIN_BASED_POSTED_INTR; + } vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); @@ -10158,26 +10125,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; - if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) { - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ - if (!vmx->nested.apic_access_page) - exec_control &= - ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - else - vmcs_write64(APIC_ACCESS_ADDR, - page_to_phys(vmx->nested.apic_access_page)); - } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - exec_control |= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - kvm_vcpu_reload_apic_access_page(vcpu); - } - if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0); @@ -10192,6 +10139,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0; + + /* + * Write an illegal value to APIC_ACCESS_ADDR. Later, + * nested_get_vmcs12_pages will either fix it up or + * remove the VM execution control. + */ + if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) + vmcs_write64(APIC_ACCESS_ADDR, -1ull); + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } @@ -10228,19 +10184,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + /* + * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if + * nested_get_vmcs12_pages can't fix it up, the illegal value + * will result in a VM entry failure. + */ if (exec_control & CPU_BASED_TPR_SHADOW) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - page_to_phys(vmx->nested.virtual_apic_page)); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); } - if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS && - nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) - ; /* MSR_BITMAP will be set by following vmx_set_efer. */ - else - exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; - /* * Merging of IO bitmap not currently supported. * Rather, exit every time. @@ -10272,16 +10225,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) { + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) { vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; - } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - + } set_cr4_guest_host_mask(vmx); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) + if (from_vmentry && + vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) @@ -10320,8 +10275,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } /* - * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified - * TS bit (for lazy fpu) and bits which we consider mandatory enabled. + * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those + * bits which we consider mandatory enabled. * The CR0_READ_SHADOW is what L2 should have expected to read given * the specifications by L1; It's not enough to take * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we @@ -10333,7 +10288,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_set_cr4(vcpu, vmcs12->guest_cr4); vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) vcpu->arch.efer = vmcs12->guest_ia32_efer; else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); @@ -10367,73 +10323,22 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, return 0; } -/* - * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 - * for running an L2 nested guest. - */ -static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) +static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - int cpu; - struct loaded_vmcs *vmcs02; - bool ia32e; - u32 msr_entry_idx; - unsigned long exit_qualification; - - if (!nested_vmx_check_permission(vcpu)) - return 1; - - if (!nested_vmx_check_vmcs12(vcpu)) - goto out; - - vmcs12 = get_vmcs12(vcpu); - - if (enable_shadow_vmcs) - copy_shadow_to_vmcs12(vmx); - - /* - * The nested entry process starts with enforcing various prerequisites - * on vmcs12 as required by the Intel SDM, and act appropriately when - * they fail: As the SDM explains, some conditions should cause the - * instruction to fail, while others will cause the instruction to seem - * to succeed, but return an EXIT_REASON_INVALID_STATE. - * To speed up the normal (success) code path, we should avoid checking - * for misconfigurations which will anyway be caught by the processor - * when using the merged vmcs02. - */ - if (vmcs12->launch_state == launch) { - nested_vmx_failValid(vcpu, - launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS - : VMXERR_VMRESUME_NONLAUNCHED_VMCS); - goto out; - } if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && - vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } - - if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, vmx->nested.nested_vmx_procbased_ctls_low, @@ -10450,28 +10355,30 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !vmx_control_verify(vmcs12->vm_entry_controls, vmx->nested.nested_vmx_entry_ctls_low, vmx->nested.nested_vmx_entry_ctls_high)) - { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) || !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || - !nested_cr3_valid(vcpu, vmcs12->host_cr3)) { - nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); - goto out; - } + !nested_cr3_valid(vcpu, vmcs12->host_cr3)) + return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + + return 0; +} + +static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 *exit_qual) +{ + bool ia32e; + + *exit_qual = ENTRY_FAIL_DEFAULT; if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) || - !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) return 1; - } - if (vmcs12->vmcs_link_pointer != -1ull) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_VMCS_LINK_PTR); + + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS) && + vmcs12->vmcs_link_pointer != -1ull) { + *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR; return 1; } @@ -10484,16 +10391,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * to bit 8 (LME) if bit 31 in the CR0 field (corresponding to * CR0.PG) is 1. */ - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) { + if (to_vmx(vcpu)->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || ((vmcs12->guest_cr0 & X86_CR0_PG) && - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) return 1; - } } /* @@ -10507,28 +10412,26 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) return 1; - } } - /* - * We're finally done with prerequisite checking, and can start with - * the nested entry. - */ + return 0; +} + +static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct loaded_vmcs *vmcs02; + int cpu; + u32 msr_entry_idx; + u32 exit_qual; vmcs02 = nested_get_current_vmcs02(vmx); if (!vmcs02) return -ENOMEM; - /* - * After this point, the trap flag no longer triggers a singlestep trap - * on the vm entry instructions. Don't call - * kvm_skip_emulated_instruction. - */ - skip_emulated_instruction(vcpu); enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -10543,14 +10446,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmx_segment_cache_clear(vmx); - if (prepare_vmcs02(vcpu, vmcs12, &exit_qualification)) { + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { leave_guest_mode(vcpu); vmx_load_vmcs01(vcpu); nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, exit_qualification); + EXIT_REASON_INVALID_STATE, exit_qual); return 1; } + nested_get_vmcs12_pages(vcpu, vmcs12); + msr_entry_idx = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); @@ -10564,17 +10469,90 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_vcpu_halt(vcpu); - - vmx->nested.nested_run_pending = 1; - /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ + return 0; +} + +/* + * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 + * for running an L2 nested guest. + */ +static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) +{ + struct vmcs12 *vmcs12; + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 exit_qual; + int ret; + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (!nested_vmx_check_vmcs12(vcpu)) + goto out; + + vmcs12 = get_vmcs12(vcpu); + + if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + + /* + * The nested entry process starts with enforcing various prerequisites + * on vmcs12 as required by the Intel SDM, and act appropriately when + * they fail: As the SDM explains, some conditions should cause the + * instruction to fail, while others will cause the instruction to seem + * to succeed, but return an EXIT_REASON_INVALID_STATE. + * To speed up the normal (success) code path, we should avoid checking + * for misconfigurations which will anyway be caught by the processor + * when using the merged vmcs02. + */ + if (vmcs12->launch_state == launch) { + nested_vmx_failValid(vcpu, + launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS + : VMXERR_VMRESUME_NONLAUNCHED_VMCS); + goto out; + } + + ret = check_vmentry_prereqs(vcpu, vmcs12); + if (ret) { + nested_vmx_failValid(vcpu, ret); + goto out; + } + + /* + * After this point, the trap flag no longer triggers a singlestep trap + * on the vm entry instructions; don't call kvm_skip_emulated_instruction. + * This is not 100% correct; for performance reasons, we delegate most + * of the checks on host state to the processor. If those fail, + * the singlestep trap is missed. + */ + skip_emulated_instruction(vcpu); + + ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual); + if (ret) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, exit_qual); + return 1; + } + + /* + * We're finally done with prerequisite checking, and can start with + * the nested entry. + */ + + ret = enter_vmx_non_root_mode(vcpu, true); + if (ret) + return ret; + + if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + return kvm_vcpu_halt(vcpu); + + vmx->nested.nested_run_pending = 1; + return 1; out: @@ -10696,7 +10674,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - return vmx_complete_nested_posted_interrupt(vcpu); + vmx_complete_nested_posted_interrupt(vcpu); + return 0; } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -10714,21 +10693,13 @@ static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) } /* - * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits - * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), - * and this function updates it to reflect the changes to the guest state while - * L2 was running (and perhaps made some exits which were handled directly by L0 - * without going back to L1), and to reflect the exit reason. - * Note that we do not have to copy here all VMCS fields, just those that - * could have changed by the L2 guest or the exit - i.e., the guest-state and - * exit-information fields only. Other fields are modified by L1 with VMWRITE, - * which already writes to vmcs12 directly. + * Update the guest state fields of vmcs12 to reflect changes that + * occurred while L2 was running. (The "IA-32e mode guest" bit of the + * VM-entry controls is also updated, since this is really a guest + * state bit.) */ -static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - u32 exit_reason, u32 exit_intr_info, - unsigned long exit_qualification) +static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - /* update guest state fields: */ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -10834,6 +10805,25 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); if (nested_cpu_has_xsaves(vmcs12)) vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); +} + +/* + * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits + * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), + * and this function updates it to reflect the changes to the guest state while + * L2 was running (and perhaps made some exits which were handled directly by L0 + * without going back to L1), and to reflect the exit reason. + * Note that we do not have to copy here all VMCS fields, just those that + * could have changed by the L2 guest or the exit - i.e., the guest-state and + * exit-information fields only. Other fields are modified by L1 with VMWRITE, + * which already writes to vmcs12 directly. + */ +static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 exit_reason, u32 exit_intr_info, + unsigned long exit_qualification) +{ + /* update guest state fields: */ + sync_vmcs12(vcpu, vmcs12); /* update exit information fields: */ @@ -10884,7 +10874,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct kvm_segment seg; - unsigned long entry_failure_code; + u32 entry_failure_code; if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; @@ -10899,24 +10889,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmx_set_rflags(vcpu, X86_EFLAGS_FIXED); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't - * actually changed, because it depends on the current state of - * fpu_active (which may have changed). - * Note that vmx_set_cr0 refers to efer set above. + * actually changed, because vmx_set_cr0 refers to efer set above. + * + * CR0_GUEST_HOST_MASK is already set in the original vmcs01 + * (KVM doesn't change it); */ + vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; vmx_set_cr0(vcpu, vmcs12->host_cr0); - /* - * If we did fpu_activate()/fpu_deactivate() during L2's run, we need - * to apply the same changes to L1's vmcs. We just set cr0 correctly, - * but we also need to update cr0_guest_host_mask and exception_bitmap. - */ - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0); - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - /* - * Note that CR4_GUEST_HOST_MASK is already set in the original vmcs01 - * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask(); - */ + /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); kvm_set_cr4(vcpu, vmcs12->host_cr4); @@ -11545,9 +11526,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_pkru = vmx_get_pkru, - .fpu_activate = vmx_fpu_activate, - .fpu_deactivate = vmx_fpu_deactivate, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, @@ -11572,6 +11550,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .sync_pir_to_irr = vmx_sync_pir_to_irr, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e52c908..b2a4b11 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -180,6 +180,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, { "irq_injections", VCPU_STAT(irq_injections) }, { "nmi_injections", VCPU_STAT(nmi_injections) }, + { "req_event", VCPU_STAT(req_event) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, @@ -190,6 +191,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages) }, + { "max_mmu_page_hash_collisions", + VM_STAT(max_mmu_page_hash_collisions) }, { NULL } }; @@ -1139,6 +1142,7 @@ struct pvclock_gtod_data { u64 boot_ns; u64 nsec_base; + u64 wall_time_sec; }; static struct pvclock_gtod_data pvclock_gtod_data; @@ -1162,6 +1166,8 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->boot_ns = boot_ns; vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->wall_time_sec = tk->xtime_sec; + write_seqcount_end(&vdata->seq); } #endif @@ -1623,6 +1629,28 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now) return mode; } +static int do_realtime(struct timespec *ts, u64 *cycle_now) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->wall_time_sec; + ns = gtod->nsec_base; + ns += vgettsc(cycle_now); + ns >>= gtod->clock.shift; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + + ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); + ts->tv_nsec = ns; + + return mode; +} + /* returns true if host is using tsc clocksource */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) { @@ -1632,6 +1660,17 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; } + +/* returns true if host is using tsc clocksource */ +static bool kvm_get_walltime_and_clockread(struct timespec *ts, + u64 *cycle_now) +{ + /* checked again under seqlock below */ + if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + return false; + + return do_realtime(ts, cycle_now) == VCLOCK_TSC; +} #endif /* @@ -1772,7 +1811,7 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info guest_hv_clock; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + if (unlikely(kvm_vcpu_read_guest_cached(v, &vcpu->pv_time, &guest_hv_clock, sizeof(guest_hv_clock)))) return; @@ -1793,9 +1832,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); smp_wmb(); @@ -1809,16 +1848,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); smp_wmb(); vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); } static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -2051,7 +2090,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apf.data, gpa, sizeof(u32))) return 1; @@ -2070,7 +2109,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + if (unlikely(kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) return; @@ -2081,7 +2120,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) vcpu->arch.st.steal.version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); smp_wmb(); @@ -2090,14 +2129,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); smp_wmb(); vcpu->arch.st.steal.version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); } @@ -2202,7 +2241,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) vcpu->arch.pv_time_enabled = false; @@ -2223,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.st.stime, data & KVM_STEAL_VALID_BITS, sizeof(struct kvm_steal_time))) return 1; @@ -2633,6 +2672,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_DISABLE_QUIRKS: case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: + case KVM_CAP_IMMEDIATE_EXIT: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -2836,7 +2876,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) vcpu->arch.st.steal.preempted = 1; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_offset_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal.preempted, offsetof(struct kvm_steal_time, preempted), sizeof(vcpu->arch.st.steal.preempted)); @@ -2870,7 +2910,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); @@ -3897,7 +3937,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, goto split_irqchip_unlock; /* Pairs with irqchip_in_kernel. */ smp_wmb(); - kvm->arch.irqchip_split = true; + kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; r = 0; split_irqchip_unlock: @@ -3960,40 +4000,41 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); break; case KVM_CREATE_IRQCHIP: { - struct kvm_pic *vpic; - mutex_lock(&kvm->lock); + r = -EEXIST; - if (kvm->arch.vpic) + if (irqchip_in_kernel(kvm)) goto create_irqchip_unlock; + r = -EINVAL; if (kvm->created_vcpus) goto create_irqchip_unlock; - r = -ENOMEM; - vpic = kvm_create_pic(kvm); - if (vpic) { - r = kvm_ioapic_init(kvm); - if (r) { - mutex_lock(&kvm->slots_lock); - kvm_destroy_pic(vpic); - mutex_unlock(&kvm->slots_lock); - goto create_irqchip_unlock; - } - } else + + r = kvm_pic_init(kvm); + if (r) + goto create_irqchip_unlock; + + r = kvm_ioapic_init(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + kvm_pic_destroy(kvm); + mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; + } + r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->irq_lock); kvm_ioapic_destroy(kvm); - kvm_destroy_pic(vpic); + kvm_pic_destroy(kvm); mutex_unlock(&kvm->irq_lock); mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; } - /* Write kvm->irq_routing before kvm->arch.vpic. */ + /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); - kvm->arch.vpic = vpic; + kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -4029,7 +4070,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) + if (!irqchip_kernel(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -4053,7 +4094,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) + if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); if (r) @@ -4462,6 +4503,21 @@ out: } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva, + gpa_t gpa, bool write) +{ + /* For APIC access vmexit */ + if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + return 1; + + if (vcpu_match_mmio_gpa(vcpu, gpa)) { + trace_vcpu_match_mmio(gva, gpa, write, true); + return 1; + } + + return 0; +} + static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) @@ -4488,16 +4544,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, if (*gpa == UNMAPPED_GVA) return -1; - /* For APIC access vmexit */ - if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - return 1; - - if (vcpu_match_mmio_gpa(vcpu, *gpa)) { - trace_vcpu_match_mmio(gva, *gpa, write, true); - return 1; - } - - return 0; + return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write); } int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -4594,6 +4641,22 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + /* + * If the exit was due to a NPF we may already have a GPA. + * If the GPA is present, use it to avoid the GVA to GPA table walk. + * Note, this cannot be used on string operations since string + * operation using rep will only have the initial GPA from the NPF + * occurred. + */ + if (vcpu->arch.gpa_available && + emulator_can_use_gpa(ctxt) && + vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) && + (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) { + gpa = exception->address; + goto mmio; + } ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -5610,6 +5673,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, } restart: + /* Save the faulting GPA (cr2) in the address field */ + ctxt->exception.address = cr2; + r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) @@ -5924,9 +5990,6 @@ static void kvm_set_mmio_spte_mask(void) /* Mask the reserved physical address bits. */ mask = rsvd_bits(maxphyaddr, 51); - /* Bit 62 is always reserved for 32bit host. */ - mask |= 0x3ull << 62; - /* Set the present bit. */ mask |= 1ull; @@ -6025,7 +6088,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK); + PT_PRESENT_MASK, 0); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -6087,6 +6150,35 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +#ifdef CONFIG_X86_64 +static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, + unsigned long clock_type) +{ + struct kvm_clock_pairing clock_pairing; + struct timespec ts; + u64 cycle; + int ret; + + if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) + return -KVM_EOPNOTSUPP; + + if (kvm_get_walltime_and_clockread(&ts, &cycle) == false) + return -KVM_EOPNOTSUPP; + + clock_pairing.sec = ts.tv_sec; + clock_pairing.nsec = ts.tv_nsec; + clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); + clock_pairing.flags = 0; + + ret = 0; + if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, + sizeof(struct kvm_clock_pairing))) + ret = -KVM_EFAULT; + + return ret; +} +#endif + /* * kvm_pv_kick_cpu_op: Kick a vcpu. * @@ -6151,6 +6243,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); ret = 0; break; +#ifdef CONFIG_X86_64 + case KVM_HC_CLOCK_PAIRING: + ret = kvm_pv_clock_pairing(vcpu, a0, a1); + break; +#endif default: ret = -KVM_ENOSYS; break; @@ -6564,7 +6661,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (vcpu->arch.apicv_active) + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -6655,10 +6752,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } - if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) { - vcpu->fpu_active = 0; - kvm_x86_ops->fpu_deactivate(vcpu); - } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ vcpu->arch.apf.halted = true; @@ -6718,21 +6811,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_hv_process_stimers(vcpu); } - /* - * KVM_REQ_EVENT is not set when posted interrupts are set by - * VT-d hardware, so we have to update RVI unconditionally. - */ - if (kvm_lapic_enabled(vcpu)) { - /* - * Update architecture specific hints for APIC - * virtual interrupt delivery. - */ - if (vcpu->arch.apicv_active) - kvm_x86_ops->hwapic_irr_update(vcpu, - kvm_lapic_find_highest_irr(vcpu)); - } - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + ++vcpu->stat.req_event; kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; @@ -6773,22 +6853,40 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); - if (vcpu->fpu_active) - kvm_load_guest_fpu(vcpu); + kvm_load_guest_fpu(vcpu); + + /* + * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt + * IPI are then delayed after guest entry, which ensures that they + * result in virtual interrupt delivery. + */ + local_irq_disable(); vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); /* - * We should set ->mode before check ->requests, - * Please see the comment in kvm_make_all_cpus_request. - * This also orders the write to mode from any reads - * to the page tables done while the VCPU is running. - * Please see the comment in kvm_flush_remote_tlbs. + * 1) We should set ->mode before checking ->requests. Please see + * the comment in kvm_make_all_cpus_request. + * + * 2) For APICv, we should set ->mode before checking PIR.ON. This + * pairs with the memory barrier implicit in pi_test_and_set_on + * (see vmx_deliver_posted_interrupt). + * + * 3) This also orders the write to mode from any reads to the page + * tables done while the VCPU is running. Please see the comment + * in kvm_flush_remote_tlbs. */ smp_mb__after_srcu_read_unlock(); - local_irq_disable(); + /* + * This handles the case where a posted interrupt was + * notified with kvm_vcpu_kick. + */ + if (kvm_lapic_enabled(vcpu)) { + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + } if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests || need_resched() || signal_pending(current)) { @@ -6927,6 +7025,9 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) + kvm_x86_ops->check_nested_events(vcpu, false); + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } @@ -7098,7 +7199,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); - r = vcpu_run(vcpu); + if (kvm_run->immediate_exit) + r = -EINTR; + else + r = vcpu_run(vcpu); out: post_kvm_run_save(vcpu); @@ -8293,9 +8397,6 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } @@ -8432,9 +8533,8 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) { - - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, - sizeof(val)); + return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apf.data, &val, + sizeof(val)); } void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, |
