From: Atish Patra atish.patra@wdc.com
euleros inclusion category: feature feature: initial KVM RISC-V support bugzilla: 46845 CVE: NA
The KVM host kernel is running in HS-mode needs so we need to handle the SBI calls coming from guest kernel running in VS-mode.
This patch adds SBI v0.1 support in KVM RISC-V. Almost all SBI v0.1 calls are implemented in KVM kernel module except GETCHAR and PUTCHART calls which are forwarded to user space because these calls cannot be implemented in kernel space. In future, when we implement SBI v0.2 for Guest, we will forward SBI v0.2 experimental and vendor extension calls to user space.
Reference: https://gitee.com/openeuler/kernel/issues/I26X9V Signed-off-by: Atish Patra atish.patra@wdc.com Signed-off-by: Anup Patel anup.patel@wdc.com Acked-by: Paolo Bonzini pbonzini@redhat.com Reviewed-by: Paolo Bonzini pbonzini@redhat.com --- arch/riscv/include/asm/kvm_host.h | 10 ++ arch/riscv/kvm/Makefile | 2 +- arch/riscv/kvm/vcpu.c | 9 ++ arch/riscv/kvm/vcpu_exit.c | 4 + arch/riscv/kvm/vcpu_sbi.c | 173 ++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 8 ++ 6 files changed, 205 insertions(+), 1 deletion(-) create mode 100644 arch/riscv/kvm/vcpu_sbi.c
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 6c2298157..241030956 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -80,6 +80,10 @@ struct kvm_mmio_decode { int return_handled; };
+struct kvm_sbi_context { + int return_handled; +}; + #define KVM_MMU_PAGE_CACHE_NR_OBJS 32
struct kvm_mmu_page_cache { @@ -192,6 +196,9 @@ struct kvm_vcpu_arch { /* MMIO instruction details */ struct kvm_mmio_decode mmio_decode;
+ /* SBI context */ + struct kvm_sbi_context sbi_context; + /* Cache pages needed to program page tables with spinlock held */ struct kvm_mmu_page_cache mmu_page_cache;
@@ -266,4 +273,7 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask); void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run); + #endif /* __RISCV_KVM_HOST_H__ */ diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index a034826f9..7cf0015d9 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -10,6 +10,6 @@ ccflags-y := -Ivirt/kvm -Iarch/riscv/kvm kvm-objs := $(common-objs-y)
kvm-objs += main.o vm.o vmid.o tlb.o mmu.o -kvm-objs += vcpu.o vcpu_exit.o vcpu_switch.o vcpu_timer.o +kvm-objs += vcpu.o vcpu_exit.o vcpu_switch.o vcpu_timer.o vcpu_sbi.o
obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 2d8bab65d..bcc4af9d2 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -882,6 +882,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } }
+ /* Process SBI value returned from user-space */ + if (run->exit_reason == KVM_EXIT_RISCV_SBI) { + ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); + if (ret) { + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + return ret; + } + } + if (run->immediate_exit) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); return -EINTR; diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 5b41a12ee..f05440679 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -678,6 +678,10 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = stage2_page_fault(vcpu, run, trap); break; + case EXC_SUPERVISOR_SYSCALL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) + ret = kvm_riscv_vcpu_sbi_ecall(vcpu, run); + break; default: break; }; diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c new file mode 100644 index 000000000..9d1d25cf2 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0 +/** + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra atish.patra@wdc.com + */ + +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <asm/csr.h> +#include <asm/sbi.h> +#include <asm/kvm_vcpu_timer.h> + +#define SBI_VERSION_MAJOR 0 +#define SBI_VERSION_MINOR 1 + +static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, + struct kvm_run *run, u32 type) +{ + int i; + struct kvm_vcpu *tmp; + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) + tmp->arch.power_off = true; + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); + + memset(&run->system_event, 0, sizeof(run->system_event)); + run->system_event.type = type; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + +static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, + struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + vcpu->arch.sbi_context.return_handled = 0; + vcpu->stat.ecall_exit_stat++; + run->exit_reason = KVM_EXIT_RISCV_SBI; + run->riscv_sbi.extension_id = cp->a7; + run->riscv_sbi.function_id = cp->a6; + run->riscv_sbi.args[0] = cp->a0; + run->riscv_sbi.args[1] = cp->a1; + run->riscv_sbi.args[2] = cp->a2; + run->riscv_sbi.args[3] = cp->a3; + run->riscv_sbi.args[4] = cp->a4; + run->riscv_sbi.args[5] = cp->a5; + run->riscv_sbi.ret[0] = cp->a0; + run->riscv_sbi.ret[1] = cp->a1; +} + +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + /* Handle SBI return only once */ + if (vcpu->arch.sbi_context.return_handled) + return 0; + vcpu->arch.sbi_context.return_handled = 1; + + /* Update return values */ + cp->a0 = run->riscv_sbi.ret[0]; + cp->a1 = run->riscv_sbi.ret[1]; + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += 4; + + return 0; +} + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + ulong hmask; + int i, ret = 1; + u64 next_cycle; + struct kvm_vcpu *rvcpu; + bool next_sepc = true; + struct cpumask cm, hm; + struct kvm *kvm = vcpu->kvm; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + if (!cp) + return -EINVAL; + + switch (cp->a7) { + case SBI_EXT_0_1_CONSOLE_GETCHAR: + case SBI_EXT_0_1_CONSOLE_PUTCHAR: + /* + * The CONSOLE_GETCHAR/CONSOLE_PUTCHAR SBI calls cannot be + * handled in kernel so we forward these to user-space + */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + next_sepc = false; + ret = 0; + break; + case SBI_EXT_0_1_SET_TIMER: +#if __riscv_xlen == 32 + next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; +#else + next_cycle = (u64)cp->a0; +#endif + kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + break; + case SBI_EXT_0_1_CLEAR_IPI: + kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_SOFT); + break; + case SBI_EXT_0_1_SEND_IPI: + if (cp->a0) + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, + &utrap); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap.scause) { + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + break; + } + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + } + break; + case SBI_EXT_0_1_SHUTDOWN: + kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN); + next_sepc = false; + ret = 0; + break; + case SBI_EXT_0_1_REMOTE_FENCE_I: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: + if (cp->a0) + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, + &utrap); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap.scause) { + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + break; + } + cpumask_clear(&cm); + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + if (rvcpu->cpu < 0) + continue; + cpumask_set_cpu(rvcpu->cpu, &cm); + } + riscv_cpuid_to_hartid_mask(&cm, &hm); + if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) + sbi_remote_fence_i(cpumask_bits(&hm)); + else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) + sbi_remote_hfence_vvma(cpumask_bits(&hm), + cp->a1, cp->a2); + else + sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), + cp->a1, cp->a2, cp->a3); + break; + default: + /* Return error for unsupported SBI calls */ + cp->a0 = SBI_ERR_NOT_SUPPORTED; + break; + }; + + if (next_sepc) + cp->sepc += 4; + + return ret; +} diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ca41220b4..a5221526c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -250,6 +250,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_ARM_NISV 28 #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 +#define KVM_EXIT_RISCV_SBI 31
/* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -426,6 +427,13 @@ struct kvm_run { __u32 index; /* kernel -> user */ __u64 data; /* kernel <-> user */ } msr; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; /* Fix the size of the union. */ char padding[256]; };