From cc4f602bc4365d9a8665803a49dddc70eb56f7f1 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 4 Nov 2021 16:41:07 +0000 Subject: KVM: RISC-V: Use common KVM implementation of MMU memory caches Use common KVM's implementation of the MMU memory caches, which for all intents and purposes is semantically identical to RISC-V's version, the only difference being that the common implementation will fall back to an atomic allocation if there's a KVM bug that triggers a cache underflow. RISC-V appears to have based its MMU code on arm64 before the conversion to the common caches in commit c1a33aebe91d ("KVM: arm64: Use common KVM implementation of MMU memory caches"), despite having also copy-pasted the definition of KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE in kvm_types.h. Opportunistically drop the superfluous wrapper kvm_riscv_stage2_flush_cache(), whose name is very, very confusing as "cache flush" in the context of MMU code almost always refers to flushing hardware caches, not freeing unused software objects. No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_host.h | 10 +----- arch/riscv/include/asm/kvm_types.h | 2 +- arch/riscv/kvm/mmu.c | 66 ++++++++------------------------------ arch/riscv/kvm/vcpu.c | 5 +-- 4 files changed, 18 insertions(+), 65 deletions(-) diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 907fafea787e..52e19888ce43 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -77,13 +77,6 @@ struct kvm_sbi_context { int return_handled; }; -#define KVM_MMU_PAGE_CACHE_NR_OBJS 32 - -struct kvm_mmu_page_cache { - int nobjs; - void *objects[KVM_MMU_PAGE_CACHE_NR_OBJS]; -}; - struct kvm_cpu_trap { unsigned long sepc; unsigned long scause; @@ -193,7 +186,7 @@ struct kvm_vcpu_arch { struct kvm_sbi_context sbi_context; /* Cache pages needed to program page tables with spinlock held */ - struct kvm_mmu_page_cache mmu_page_cache; + struct kvm_mmu_memory_cache mmu_page_cache; /* VCPU power-off state */ bool power_off; @@ -220,7 +213,6 @@ void __kvm_riscv_hfence_gvma_all(void); int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, gpa_t gpa, unsigned long hva, bool is_write); -void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu); int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm); void kvm_riscv_stage2_free_pgd(struct kvm *kvm); void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu); diff --git a/arch/riscv/include/asm/kvm_types.h b/arch/riscv/include/asm/kvm_types.h index e476b404eb67..e15765f98d7a 100644 --- a/arch/riscv/include/asm/kvm_types.h +++ b/arch/riscv/include/asm/kvm_types.h @@ -2,6 +2,6 @@ #ifndef _ASM_RISCV_KVM_TYPES_H #define _ASM_RISCV_KVM_TYPES_H -#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40 +#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 32 #endif /* _ASM_RISCV_KVM_TYPES_H */ diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 7d884b15cf5e..5f2736c2e773 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -83,43 +83,6 @@ static int stage2_level_to_page_size(u32 level, unsigned long *out_pgsize) return 0; } -static int stage2_cache_topup(struct kvm_mmu_page_cache *pcache, - int min, int max) -{ - void *page; - - BUG_ON(max > KVM_MMU_PAGE_CACHE_NR_OBJS); - if (pcache->nobjs >= min) - return 0; - while (pcache->nobjs < max) { - page = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - if (!page) - return -ENOMEM; - pcache->objects[pcache->nobjs++] = page; - } - - return 0; -} - -static void stage2_cache_flush(struct kvm_mmu_page_cache *pcache) -{ - while (pcache && pcache->nobjs) - free_page((unsigned long)pcache->objects[--pcache->nobjs]); -} - -static void *stage2_cache_alloc(struct kvm_mmu_page_cache *pcache) -{ - void *p; - - if (!pcache) - return NULL; - - BUG_ON(!pcache->nobjs); - p = pcache->objects[--pcache->nobjs]; - - return p; -} - static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr, pte_t **ptepp, u32 *ptep_level) { @@ -171,7 +134,7 @@ static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr) } static int stage2_set_pte(struct kvm *kvm, u32 level, - struct kvm_mmu_page_cache *pcache, + struct kvm_mmu_memory_cache *pcache, gpa_t addr, const pte_t *new_pte) { u32 current_level = stage2_pgd_levels - 1; @@ -186,7 +149,9 @@ static int stage2_set_pte(struct kvm *kvm, u32 level, return -EEXIST; if (!pte_val(*ptep)) { - next_ptep = stage2_cache_alloc(pcache); + if (!pcache) + return -ENOMEM; + next_ptep = kvm_mmu_memory_cache_alloc(pcache); if (!next_ptep) return -ENOMEM; *ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)), @@ -209,7 +174,7 @@ static int stage2_set_pte(struct kvm *kvm, u32 level, } static int stage2_map_page(struct kvm *kvm, - struct kvm_mmu_page_cache *pcache, + struct kvm_mmu_memory_cache *pcache, gpa_t gpa, phys_addr_t hpa, unsigned long page_size, bool page_rdonly, bool page_exec) @@ -384,7 +349,10 @@ static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, int ret = 0; unsigned long pfn; phys_addr_t addr, end; - struct kvm_mmu_page_cache pcache = { 0, }; + struct kvm_mmu_memory_cache pcache; + + memset(&pcache, 0, sizeof(pcache)); + pcache.gfp_zero = __GFP_ZERO; end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK; pfn = __phys_to_pfn(hpa); @@ -395,9 +363,7 @@ static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, if (!writable) pte = pte_wrprotect(pte); - ret = stage2_cache_topup(&pcache, - stage2_pgd_levels, - KVM_MMU_PAGE_CACHE_NR_OBJS); + ret = kvm_mmu_topup_memory_cache(&pcache, stage2_pgd_levels); if (ret) goto out; @@ -411,7 +377,7 @@ static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, } out: - stage2_cache_flush(&pcache); + kvm_mmu_free_memory_cache(&pcache); return ret; } @@ -649,7 +615,7 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gfn_t gfn = gpa >> PAGE_SHIFT; struct vm_area_struct *vma; struct kvm *kvm = vcpu->kvm; - struct kvm_mmu_page_cache *pcache = &vcpu->arch.mmu_page_cache; + struct kvm_mmu_memory_cache *pcache = &vcpu->arch.mmu_page_cache; bool logging = (memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY)) ? true : false; unsigned long vma_pagesize, mmu_seq; @@ -684,8 +650,7 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, } /* We need minimum second+third level pages */ - ret = stage2_cache_topup(pcache, stage2_pgd_levels, - KVM_MMU_PAGE_CACHE_NR_OBJS); + ret = kvm_mmu_topup_memory_cache(pcache, stage2_pgd_levels); if (ret) { kvm_err("Failed to topup stage2 cache\n"); return ret; @@ -734,11 +699,6 @@ out_unlock: return ret; } -void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu) -{ - stage2_cache_flush(&vcpu->arch.mmu_page_cache); -} - int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm) { struct page *pgd_page; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index fb84619df012..2ae11b4e93d1 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -77,6 +77,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Mark this VCPU never ran */ vcpu->arch.ran_atleast_once = false; + vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; /* Setup ISA features available to VCPU */ vcpu->arch.isa = riscv_isa_extension_base(NULL) & KVM_RISCV_ISA_ALLOWED; @@ -107,8 +108,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) /* Cleanup VCPU timer */ kvm_riscv_vcpu_timer_deinit(vcpu); - /* Flush the pages pre-allocated for Stage2 page table mappings */ - kvm_riscv_stage2_flush_cache(vcpu); + /* Free unused pages pre-allocated for Stage2 page table mappings */ + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) -- cgit v1.2.3 From cf70be9d214c3ba8dd228cb373f7dc0edfa8da6b Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 18 Nov 2021 00:39:08 -0800 Subject: RISC-V: KVM: Mark the existing SBI implementation as v0.1 The existing SBI specification impelementation follows v0.1 specification. The latest specification allows more scalability and performance improvements. Rename the existing implementation as v0.1 and provide a way to allow future extensions. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_vcpu_sbi.h | 29 +++++++ arch/riscv/kvm/vcpu_sbi.c | 147 ++++++++++++++++++++++++++-------- 2 files changed, 144 insertions(+), 32 deletions(-) create mode 100644 arch/riscv/include/asm/kvm_vcpu_sbi.h diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h new file mode 100644 index 000000000000..1a4cb0db2d0b --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/** + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#ifndef __RISCV_KVM_VCPU_SBI_H__ +#define __RISCV_KVM_VCPU_SBI_H__ + +#define KVM_SBI_VERSION_MAJOR 0 +#define KVM_SBI_VERSION_MINOR 2 + +struct kvm_vcpu_sbi_extension { + unsigned long extid_start; + unsigned long extid_end; + /** + * SBI extension handler. It can be defined for a given extension or group of + * extension. But it should always return linux error codes rather than SBI + * specific error codes. + */ + int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, struct kvm_cpu_trap *utrap, + bool *exit); +}; + +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid); +#endif /* __RISCV_KVM_VCPU_SBI_H__ */ diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index d0d2bcab2f7b..8c5b50d2b27e 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -12,9 +12,25 @@ #include #include #include +#include -#define SBI_VERSION_MAJOR 0 -#define SBI_VERSION_MINOR 1 +static int kvm_linux_err_map_sbi(int err) +{ + switch (err) { + case 0: + return SBI_SUCCESS; + case -EPERM: + return SBI_ERR_DENIED; + case -EINVAL: + return SBI_ERR_INVALID_PARAM; + case -EFAULT: + return SBI_ERR_INVALID_ADDRESS; + case -EOPNOTSUPP: + return SBI_ERR_NOT_SUPPORTED; + default: + return SBI_ERR_FAILURE; + }; +} static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) @@ -72,21 +88,19 @@ static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } -int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, + bool *exit) { ulong hmask; - int i, ret = 1; + int i, ret = 0; 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: @@ -95,8 +109,7 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) * handled in kernel so we forward these to user-space */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - next_sepc = false; - ret = 0; + *exit = true; break; case SBI_EXT_0_1_SET_TIMER: #if __riscv_xlen == 32 @@ -104,47 +117,42 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) #else next_cycle = (u64)cp->a0; #endif - kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + ret = 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); + ret = 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); + 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; + if (utrap->scause) 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); + ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + if (ret < 0) + break; } break; case SBI_EXT_0_1_SHUTDOWN: kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN); - next_sepc = false; - ret = 0; + *exit = true; 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); + 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; + if (utrap->scause) break; - } + cpumask_clear(&cm); for_each_set_bit(i, &hmask, BITS_PER_LONG) { rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); @@ -154,22 +162,97 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) } riscv_cpuid_to_hartid_mask(&cm, &hm); if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) - sbi_remote_fence_i(cpumask_bits(&hm)); + ret = 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), + ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), cp->a1, cp->a2); else - sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), + ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), cp->a1, cp->a2, cp->a3); break; default: + ret = -EINVAL; + break; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { + .extid_start = SBI_EXT_0_1_SET_TIMER, + .extid_end = SBI_EXT_0_1_SHUTDOWN, + .handler = kvm_sbi_ext_v01_handler, +}; + +static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { + &vcpu_sbi_ext_v01, +}; + +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid) +{ + int i = 0; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + if (sbi_ext[i]->extid_start <= extid && + sbi_ext[i]->extid_end >= extid) + return sbi_ext[i]; + } + + return NULL; +} + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + int ret = 1; + bool next_sepc = true; + bool userspace_exit = false; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + const struct kvm_vcpu_sbi_extension *sbi_ext; + struct kvm_cpu_trap utrap = { 0 }; + unsigned long out_val = 0; + bool ext_is_v01 = false; + + sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7); + if (sbi_ext && sbi_ext->handler) { + if (cp->a7 >= SBI_EXT_0_1_SET_TIMER && + cp->a7 <= SBI_EXT_0_1_SHUTDOWN) + ext_is_v01 = true; + ret = sbi_ext->handler(vcpu, run, &out_val, &utrap, &userspace_exit); + } else { /* Return error for unsupported SBI calls */ cp->a0 = SBI_ERR_NOT_SUPPORTED; - break; + goto ecall_done; + } + + /* Handle special error cases i.e trap, exit or userspace forward */ + if (utrap.scause) { + /* No need to increment sepc or exit ioctl loop */ + ret = 1; + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + goto ecall_done; } + /* Exit ioctl loop or Propagate the error code the guest */ + if (userspace_exit) { + next_sepc = false; + ret = 0; + } else { + /** + * SBI extension handler always returns an Linux error code. Convert + * it to the SBI specific error code that can be propagated the SBI + * caller. + */ + ret = kvm_linux_err_map_sbi(ret); + cp->a0 = ret; + ret = 1; + } +ecall_done: if (next_sepc) cp->sepc += 4; + if (!ext_is_v01) + cp->a1 = out_val; return ret; } -- cgit v1.2.3 From a046c2d8578c93b85ab9272a818c821c254931d0 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 18 Nov 2021 00:39:09 -0800 Subject: RISC-V: KVM: Reorganize SBI code by moving SBI v0.1 to its own file With SBI v0.2, there may be more SBI extensions in future. It makes more sense to group related extensions in separate files. Guest kernel will choose appropriate SBI version dynamically. Move the existing implementation to a separate file so that it can be removed in future without much conflict. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_vcpu_sbi.h | 2 + arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu_sbi.c | 148 ++++------------------------------ arch/riscv/kvm/vcpu_sbi_v01.c | 126 +++++++++++++++++++++++++++++ 4 files changed, 146 insertions(+), 131 deletions(-) create mode 100644 arch/riscv/kvm/vcpu_sbi_v01.c diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index 1a4cb0db2d0b..704151969ceb 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -25,5 +25,7 @@ struct kvm_vcpu_sbi_extension { bool *exit); }; +void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid); + #endif /* __RISCV_KVM_VCPU_SBI_H__ */ diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 300590225348..892c60b07823 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -19,4 +19,5 @@ kvm-y += vcpu_exit.o kvm-y += vcpu_fp.o kvm-y += vcpu_switch.o kvm-y += vcpu_sbi.o +kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 8c5b50d2b27e..a8e0191cd9fc 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -9,9 +9,7 @@ #include #include #include -#include #include -#include #include static int kvm_linux_err_map_sbi(int err) @@ -32,8 +30,21 @@ static int kvm_linux_err_map_sbi(int err) }; } -static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, - struct kvm_run *run) +#ifdef CONFIG_RISCV_SBI_V01 +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01; +#else +static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { + .extid_start = -1UL, + .extid_end = -1UL, + .handler = NULL, +}; +#endif + +static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { + &vcpu_sbi_ext_v01, +}; + +void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -71,123 +82,6 @@ int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) return 0; } -#ifdef CONFIG_RISCV_SBI_V01 - -static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, - struct kvm_run *run, u32 type) -{ - unsigned long 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 int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) -{ - ulong hmask; - int i, ret = 0; - u64 next_cycle; - struct kvm_vcpu *rvcpu; - struct cpumask cm, hm; - struct kvm *kvm = vcpu->kvm; - struct kvm_cpu_context *cp = &vcpu->arch.guest_context; - - 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); - *exit = true; - 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 - ret = kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); - break; - case SBI_EXT_0_1_CLEAR_IPI: - ret = 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) - break; - - for_each_set_bit(i, &hmask, BITS_PER_LONG) { - rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); - ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); - if (ret < 0) - break; - } - break; - case SBI_EXT_0_1_SHUTDOWN: - kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN); - *exit = true; - 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) - 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) - ret = sbi_remote_fence_i(cpumask_bits(&hm)); - else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) - ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), - cp->a1, cp->a2); - else - ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), - cp->a1, cp->a2, cp->a3); - break; - default: - ret = -EINVAL; - break; - } - - return ret; -} - -const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { - .extid_start = SBI_EXT_0_1_SET_TIMER, - .extid_end = SBI_EXT_0_1_SHUTDOWN, - .handler = kvm_sbi_ext_v01_handler, -}; - -static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { - &vcpu_sbi_ext_v01, -}; - const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid) { int i = 0; @@ -214,9 +108,11 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7); if (sbi_ext && sbi_ext->handler) { +#ifdef CONFIG_RISCV_SBI_V01 if (cp->a7 >= SBI_EXT_0_1_SET_TIMER && cp->a7 <= SBI_EXT_0_1_SHUTDOWN) ext_is_v01 = true; +#endif ret = sbi_ext->handler(vcpu, run, &out_val, &utrap, &userspace_exit); } else { /* Return error for unsupported SBI calls */ @@ -256,13 +152,3 @@ ecall_done: return ret; } - -#else - -int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - kvm_riscv_vcpu_sbi_forward(vcpu, run); - return 0; -} - -#endif diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c new file mode 100644 index 000000000000..4c7e13ec9ccc --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include +#include + +static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, + struct kvm_run *run, u32 type) +{ + unsigned long 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 int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, + bool *exit) +{ + ulong hmask; + int i, ret = 0; + u64 next_cycle; + struct kvm_vcpu *rvcpu; + struct cpumask cm, hm; + struct kvm *kvm = vcpu->kvm; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + 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); + *exit = true; + 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 + ret = kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + break; + case SBI_EXT_0_1_CLEAR_IPI: + ret = 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) + break; + + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + if (ret < 0) + break; + } + break; + case SBI_EXT_0_1_SHUTDOWN: + kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN); + *exit = true; + 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) + 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) + ret = sbi_remote_fence_i(cpumask_bits(&hm)); + else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) + ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), + cp->a1, cp->a2); + else + ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), + cp->a1, cp->a2, cp->a3); + break; + default: + ret = -EINVAL; + break; + }; + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { + .extid_start = SBI_EXT_0_1_SET_TIMER, + .extid_end = SBI_EXT_0_1_SHUTDOWN, + .handler = kvm_sbi_ext_v01_handler, +}; -- cgit v1.2.3 From c62a76859723fb732bfeda847f22192e24e121a7 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 18 Nov 2021 00:39:10 -0800 Subject: RISC-V: KVM: Add SBI v0.2 base extension SBI v0.2 base extension defined to allow backward compatibility and probing of future extensions. This is also the only mandatory SBI extension that must be implemented by SBI implementors. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_vcpu_sbi.h | 2 + arch/riscv/include/asm/sbi.h | 8 ++++ arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu_sbi.c | 3 +- arch/riscv/kvm/vcpu_sbi_base.c | 72 +++++++++++++++++++++++++++++++++++ 5 files changed, 85 insertions(+), 1 deletion(-) create mode 100644 arch/riscv/kvm/vcpu_sbi_base.c diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index 704151969ceb..76e4e17a3e00 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -9,6 +9,8 @@ #ifndef __RISCV_KVM_VCPU_SBI_H__ #define __RISCV_KVM_VCPU_SBI_H__ +#define KVM_SBI_IMPID 3 + #define KVM_SBI_VERSION_MAJOR 0 #define KVM_SBI_VERSION_MINOR 2 diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 0d42693cb65e..9e4c79fd49d7 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -27,6 +27,14 @@ enum sbi_ext_id { SBI_EXT_IPI = 0x735049, SBI_EXT_RFENCE = 0x52464E43, SBI_EXT_HSM = 0x48534D, + + /* Experimentals extensions must lie within this range */ + SBI_EXT_EXPERIMENTAL_START = 0x08000000, + SBI_EXT_EXPERIMENTAL_END = 0x08FFFFFF, + + /* Vendor extensions must lie within this range */ + SBI_EXT_VENDOR_START = 0x09000000, + SBI_EXT_VENDOR_END = 0x09FFFFFF, }; enum sbi_ext_base_fid { diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 892c60b07823..c90b3802ee6d 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -20,4 +20,5 @@ kvm-y += vcpu_fp.o kvm-y += vcpu_switch.o kvm-y += vcpu_sbi.o kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o +kvm-y += vcpu_sbi_base.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index a8e0191cd9fc..915a044a0b4f 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -39,9 +39,10 @@ static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { .handler = NULL, }; #endif - +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base; static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, + &vcpu_sbi_ext_base, }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c new file mode 100644 index 000000000000..d1ec08fe7289 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *trap, bool *exit) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct sbiret ecall_ret; + + switch (cp->a6) { + case SBI_EXT_BASE_GET_SPEC_VERSION: + *out_val = (KVM_SBI_VERSION_MAJOR << + SBI_SPEC_VERSION_MAJOR_SHIFT) | + KVM_SBI_VERSION_MINOR; + break; + case SBI_EXT_BASE_GET_IMP_ID: + *out_val = KVM_SBI_IMPID; + break; + case SBI_EXT_BASE_GET_IMP_VERSION: + *out_val = 0; + break; + case SBI_EXT_BASE_PROBE_EXT: + if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START && + cp->a0 <= SBI_EXT_EXPERIMENTAL_END) || + (cp->a0 >= SBI_EXT_VENDOR_START && + cp->a0 <= SBI_EXT_VENDOR_END)) { + /* + * For experimental/vendor extensions + * forward it to the userspace + */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + *exit = true; + } else + *out_val = kvm_vcpu_sbi_find_ext(cp->a0) ? 1 : 0; + break; + case SBI_EXT_BASE_GET_MVENDORID: + case SBI_EXT_BASE_GET_MARCHID: + case SBI_EXT_BASE_GET_MIMPID: + ecall_ret = sbi_ecall(SBI_EXT_BASE, cp->a6, 0, 0, 0, 0, 0, 0); + if (!ecall_ret.error) + *out_val = ecall_ret.value; + /*TODO: We are unnecessarily converting the error twice */ + ret = sbi_err_map_linux_errno(ecall_ret.error); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { + .extid_start = SBI_EXT_BASE, + .extid_end = SBI_EXT_BASE, + .handler = kvm_sbi_ext_base_handler, +}; -- cgit v1.2.3 From 5f862df5585cf9d74b97ecaf3078243591f1009f Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 18 Nov 2021 00:39:11 -0800 Subject: RISC-V: KVM: Add v0.1 replacement SBI extensions defined in v0.2 The SBI v0.2 contains some of the improved versions of required v0.1 extensions such as remote fence, timer and IPI. This patch implements those extensions. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu_sbi.c | 7 ++ arch/riscv/kvm/vcpu_sbi_replace.c | 135 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 143 insertions(+) create mode 100644 arch/riscv/kvm/vcpu_sbi_replace.c diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index c90b3802ee6d..7fd9fc184ae9 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -21,4 +21,5 @@ kvm-y += vcpu_switch.o kvm-y += vcpu_sbi.o kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o kvm-y += vcpu_sbi_base.o +kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 915a044a0b4f..cf284e080f3e 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -40,9 +40,16 @@ static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { }; #endif extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; + static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, &vcpu_sbi_ext_base, + &vcpu_sbi_ext_time, + &vcpu_sbi_ext_ipi, + &vcpu_sbi_ext_rfence, }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c new file mode 100644 index 000000000000..00036b7f83b9 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, bool *exit) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + u64 next_cycle; + + if (cp->a6 != SBI_EXT_TIME_SET_TIMER) + return -EINVAL; + +#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); + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { + .extid_start = SBI_EXT_TIME, + .extid_end = SBI_EXT_TIME, + .handler = kvm_sbi_ext_time_handler, +}; + +static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, bool *exit) +{ + int ret = 0; + unsigned long i; + struct kvm_vcpu *tmp; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long hmask = cp->a0; + unsigned long hbase = cp->a1; + + if (cp->a6 != SBI_EXT_IPI_SEND_IPI) + return -EINVAL; + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (hbase != -1UL) { + if (tmp->vcpu_id < hbase) + continue; + if (!(hmask & (1UL << (tmp->vcpu_id - hbase)))) + continue; + } + ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT); + if (ret < 0) + break; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi = { + .extid_start = SBI_EXT_IPI, + .extid_end = SBI_EXT_IPI, + .handler = kvm_sbi_ext_ipi_handler, +}; + +static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, bool *exit) +{ + int ret = 0; + unsigned long i; + struct cpumask cm, hm; + struct kvm_vcpu *tmp; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long hmask = cp->a0; + unsigned long hbase = cp->a1; + unsigned long funcid = cp->a6; + + cpumask_clear(&cm); + cpumask_clear(&hm); + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (hbase != -1UL) { + if (tmp->vcpu_id < hbase) + continue; + if (!(hmask & (1UL << (tmp->vcpu_id - hbase)))) + continue; + } + if (tmp->cpu < 0) + continue; + cpumask_set_cpu(tmp->cpu, &cm); + } + + riscv_cpuid_to_hartid_mask(&cm, &hm); + + switch (funcid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + ret = sbi_remote_fence_i(cpumask_bits(&hm)); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), cp->a2, cp->a3); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), cp->a2, + cp->a3, cp->a4); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA: + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: + /* TODO: implement for nested hypervisor case */ + default: + ret = -EOPNOTSUPP; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { + .extid_start = SBI_EXT_RFENCE, + .extid_end = SBI_EXT_RFENCE, + .handler = kvm_sbi_ext_rfence_handler, +}; -- cgit v1.2.3 From 3e1d86569c210ec64398091bd035e539f0e26e81 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 18 Nov 2021 00:39:12 -0800 Subject: RISC-V: KVM: Add SBI HSM extension in KVM SBI HSM extension allows OS to start/stop harts any time. It also allows ordered booting of harts instead of random booting. Implement SBI HSM exntesion and designate the vcpu 0 as the boot vcpu id. All other non-zero non-booting vcpus should be brought up by the OS implementing HSM extension. If the guest OS doesn't implement HSM extension, only single vcpu will be available to OS. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/asm/sbi.h | 1 + arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu.c | 23 +++++++++ arch/riscv/kvm/vcpu_sbi.c | 4 ++ arch/riscv/kvm/vcpu_sbi_hsm.c | 105 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 134 insertions(+) create mode 100644 arch/riscv/kvm/vcpu_sbi_hsm.c diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 9e4c79fd49d7..9c46dd3ff4a2 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -90,6 +90,7 @@ enum sbi_hsm_hart_status { #define SBI_ERR_INVALID_PARAM -3 #define SBI_ERR_DENIED -4 #define SBI_ERR_INVALID_ADDRESS -5 +#define SBI_ERR_ALREADY_AVAILABLE -6 extern unsigned long sbi_spec_version; struct sbiret { diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 7fd9fc184ae9..e5c56182f48f 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -22,4 +22,5 @@ kvm-y += vcpu_sbi.o kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o kvm-y += vcpu_sbi_base.o kvm-y += vcpu_sbi_replace.o +kvm-y += vcpu_sbi_hsm.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 2ae11b4e93d1..0c5239e05721 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -53,6 +53,17 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context; + bool loaded; + + /** + * The preemption should be disabled here because it races with + * kvm_sched_out/kvm_sched_in(called from preempt notifiers) which + * also calls vcpu_load/put. + */ + get_cpu(); + loaded = (vcpu->cpu != -1); + if (loaded) + kvm_arch_vcpu_put(vcpu); memcpy(csr, reset_csr, sizeof(*csr)); @@ -64,6 +75,11 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) WRITE_ONCE(vcpu->arch.irqs_pending, 0); WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + + /* Reset the guest CSRs for hotplug usecase */ + if (loaded) + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + put_cpu(); } int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) @@ -101,6 +117,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { + /** + * vcpu with id 0 is the designated boot cpu. + * Keep all vcpus with non-zero id in power-off state so that + * they can be brought up using SBI HSM extension. + */ + if (vcpu->vcpu_idx != 0) + kvm_riscv_vcpu_power_off(vcpu); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index cf284e080f3e..f62d25bc9733 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -25,6 +25,8 @@ static int kvm_linux_err_map_sbi(int err) return SBI_ERR_INVALID_ADDRESS; case -EOPNOTSUPP: return SBI_ERR_NOT_SUPPORTED; + case -EALREADY: + return SBI_ERR_ALREADY_AVAILABLE; default: return SBI_ERR_FAILURE; }; @@ -43,6 +45,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm; static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, @@ -50,6 +53,7 @@ static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_time, &vcpu_sbi_ext_ipi, &vcpu_sbi_ext_rfence, + &vcpu_sbi_ext_hsm, }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c new file mode 100644 index 000000000000..2e383687fa48 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *reset_cntx; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_vcpu *target_vcpu; + unsigned long target_vcpuid = cp->a0; + + target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); + if (!target_vcpu) + return -EINVAL; + if (!target_vcpu->arch.power_off) + return -EALREADY; + + reset_cntx = &target_vcpu->arch.guest_reset_context; + /* start address */ + reset_cntx->sepc = cp->a1; + /* target vcpu id to start */ + reset_cntx->a0 = target_vcpuid; + /* private data passed from kernel */ + reset_cntx->a1 = cp->a2; + kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu); + + kvm_riscv_vcpu_power_on(target_vcpu); + + return 0; +} + +static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.power_off) + return -EINVAL; + + kvm_riscv_vcpu_power_off(vcpu); + + return 0; +} + +static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long target_vcpuid = cp->a0; + struct kvm_vcpu *target_vcpu; + + target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); + if (!target_vcpu) + return -EINVAL; + if (!target_vcpu->arch.power_off) + return SBI_HSM_HART_STATUS_STARTED; + else + return SBI_HSM_HART_STATUS_STOPPED; +} + +static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, + bool *exit) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm *kvm = vcpu->kvm; + unsigned long funcid = cp->a6; + + switch (funcid) { + case SBI_EXT_HSM_HART_START: + mutex_lock(&kvm->lock); + ret = kvm_sbi_hsm_vcpu_start(vcpu); + mutex_unlock(&kvm->lock); + break; + case SBI_EXT_HSM_HART_STOP: + ret = kvm_sbi_hsm_vcpu_stop(vcpu); + break; + case SBI_EXT_HSM_HART_STATUS: + ret = kvm_sbi_hsm_vcpu_get_status(vcpu); + if (ret >= 0) { + *out_val = ret; + ret = 0; + } + break; + default: + ret = -EOPNOTSUPP; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = { + .extid_start = SBI_EXT_HSM, + .extid_end = SBI_EXT_HSM, + .handler = kvm_sbi_ext_hsm_handler, +}; -- cgit v1.2.3 From 4abed558b2cedebde400856e52800115d92e994a Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 2 Dec 2021 15:58:23 -0800 Subject: MAINTAINERS: Update Atish's email address I am no longer employed by western digital. Update my email address to personal one and add entries to .mailmap as well. Signed-off-by: Atish Patra Signed-off-by: Anup Patel --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 6277bb27b4bf..29eedc1fab89 100644 --- a/.mailmap +++ b/.mailmap @@ -50,6 +50,7 @@ Archit Taneja Ard Biesheuvel Arnaud Patard Arnd Bergmann +Atish Patra Axel Dyks Axel Lin Bart Van Assche diff --git a/MAINTAINERS b/MAINTAINERS index 43007f2d29e0..d8972ed1f8d9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10445,7 +10445,7 @@ F: arch/powerpc/kvm/ KERNEL VIRTUAL MACHINE FOR RISC-V (KVM/riscv) M: Anup Patel -R: Atish Patra +R: Atish Patra L: kvm@vger.kernel.org L: kvm-riscv@lists.infradead.org L: linux-riscv@lists.infradead.org -- cgit v1.2.3 From 637ad6551b2801cdf9c76046cffc1abe1f5c2243 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Mon, 29 Nov 2021 00:07:39 +0800 Subject: RISC-V: KVM: make kvm_riscv_vcpu_fp_clean() static There are no users outside vcpu_fp.c so make kvm_riscv_vcpu_fp_clean() static. Signed-off-by: Jisheng Zhang Signed-off-by: Anup Patel --- arch/riscv/kvm/vcpu_fp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 1b070152578f..4449a976e5a6 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -26,7 +26,7 @@ void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) cntx->sstatus |= SR_FS_OFF; } -void kvm_riscv_vcpu_fp_clean(struct kvm_cpu_context *cntx) +static void kvm_riscv_vcpu_fp_clean(struct kvm_cpu_context *cntx) { cntx->sstatus &= ~SR_FS; cntx->sstatus |= SR_FS_CLEAN; -- cgit v1.2.3 From ef8949a986f0e325b1d535389101541849d611d3 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 26 Nov 2021 10:48:41 +0530 Subject: RISC-V: KVM: Forward SBI experimental and vendor extensions The SBI experimental extension space is for temporary (or experimental) stuff whereas SBI vendor extension space is for hardware vendor specific stuff. Both these SBI extension spaces won't be standardized by the SBI specification so let's blindly forward such SBI calls to the userspace. Signed-off-by: Anup Patel Reviewed-and-tested-by: Atish Patra --- arch/riscv/kvm/vcpu_sbi.c | 4 ++++ arch/riscv/kvm/vcpu_sbi_base.c | 27 +++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index f62d25bc9733..78aa3db76225 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -46,6 +46,8 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor; static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, @@ -54,6 +56,8 @@ static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_ipi, &vcpu_sbi_ext_rfence, &vcpu_sbi_ext_hsm, + &vcpu_sbi_ext_experimental, + &vcpu_sbi_ext_vendor, }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index d1ec08fe7289..4ecf377f483b 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -70,3 +70,30 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { .extid_end = SBI_EXT_BASE, .handler = kvm_sbi_ext_base_handler, }; + +static int kvm_sbi_ext_forward_handler(struct kvm_vcpu *vcpu, + struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, + bool *exit) +{ + /* + * Both SBI experimental and vendor extensions are + * unconditionally forwarded to userspace. + */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + *exit = true; + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental = { + .extid_start = SBI_EXT_EXPERIMENTAL_START, + .extid_end = SBI_EXT_EXPERIMENTAL_END, + .handler = kvm_sbi_ext_forward_handler, +}; + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor = { + .extid_start = SBI_EXT_VENDOR_START, + .extid_end = SBI_EXT_VENDOR_END, + .handler = kvm_sbi_ext_forward_handler, +}; -- cgit v1.2.3 From a457fd5660efa9cf960d2461156a1025bfdb13fa Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 26 Nov 2021 17:05:51 +0530 Subject: RISC-V: KVM: Add VM capability to allow userspace get GPA bits The number of GPA bits supported for a RISC-V Guest/VM is based on the MMU mode used by the G-stage translation. The KVM RISC-V will detect and use the best possible MMU mode for the G-stage in kvm_arch_init(). We add a generic VM capability KVM_CAP_VM_GPA_BITS which can be used by the KVM userspace to get the number of GPA (guest physical address) bits supported for a Guest/VM. Signed-off-by: Anup Patel Reviewed-and-tested-by: Atish Patra --- arch/riscv/include/asm/kvm_host.h | 1 + arch/riscv/kvm/mmu.c | 5 +++++ arch/riscv/kvm/vm.c | 3 +++ include/uapi/linux/kvm.h | 1 + 4 files changed, 10 insertions(+) diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 52e19888ce43..99ef6a120617 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -218,6 +218,7 @@ void kvm_riscv_stage2_free_pgd(struct kvm *kvm); void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu); void kvm_riscv_stage2_mode_detect(void); unsigned long kvm_riscv_stage2_mode(void); +int kvm_riscv_stage2_gpa_bits(void); void kvm_riscv_stage2_vmid_detect(void); unsigned long kvm_riscv_stage2_vmid_bits(void); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 5f2736c2e773..9af67dbdc66a 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -769,3 +769,8 @@ unsigned long kvm_riscv_stage2_mode(void) { return stage2_mode >> HGATP_MODE_SHIFT; } + +int kvm_riscv_stage2_gpa_bits(void) +{ + return stage2_gpa_bits; +} diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7619691d8953..c768f75279ef 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -74,6 +74,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_NR_MEMSLOTS: r = KVM_USER_MEM_SLOTS; break; + case KVM_CAP_VM_GPA_BITS: + r = kvm_riscv_stage2_gpa_bits(); + break; default: r = 0; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 1daa45268de2..469f05d69c8d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1131,6 +1131,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 +#define KVM_CAP_VM_GPA_BITS 207 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 788490e798a707cea75d80448f5c6c5f322ada6e Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 26 Nov 2021 18:33:45 +0530 Subject: KVM: selftests: Add EXTRA_CFLAGS in top-level Makefile We add EXTRA_CFLAGS to the common CFLAGS of top-level Makefile which will allow users to pass additional compile-time flags such as "-static". Signed-off-by: Anup Patel Reviewed-and-tested-by: Atish Patra Reviewed-and-tested-by: Sean Christopherson --- tools/testing/selftests/kvm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 17342b575e85..869edc2a5a34 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -133,7 +133,7 @@ endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$( Date: Tue, 5 Oct 2021 18:09:56 +0530 Subject: KVM: selftests: Add initial support for RISC-V 64-bit We add initial support for RISC-V 64-bit in KVM selftests using which we can cross-compile and run arch independent tests such as: demand_paging_test dirty_log_test kvm_create_max_vcpus, kvm_page_table_test set_memory_region_test kvm_binary_stats_test All VM guest modes defined in kvm_util.h require at least 48-bit guest virtual address so to use KVM RISC-V selftests hardware need to support at least Sv48 MMU for guest (i.e. VS-mode). Signed-off-by: Anup Patel Reviewed-and-tested-by: Atish Patra --- tools/testing/selftests/kvm/Makefile | 12 + tools/testing/selftests/kvm/include/kvm_util.h | 10 + .../selftests/kvm/include/riscv/processor.h | 135 ++++++++ tools/testing/selftests/kvm/lib/guest_modes.c | 10 + tools/testing/selftests/kvm/lib/riscv/processor.c | 362 +++++++++++++++++++++ tools/testing/selftests/kvm/lib/riscv/ucall.c | 87 +++++ 6 files changed, 616 insertions(+) create mode 100644 tools/testing/selftests/kvm/include/riscv/processor.h create mode 100644 tools/testing/selftests/kvm/lib/riscv/processor.c create mode 100644 tools/testing/selftests/kvm/lib/riscv/ucall.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 869edc2a5a34..a2d65f218795 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -32,11 +32,16 @@ endif ifeq ($(ARCH),s390) UNAME_M := s390x endif +# Set UNAME_M riscv compile/install to work +ifeq ($(ARCH),riscv) + UNAME_M := riscv +endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c +LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features @@ -119,6 +124,13 @@ TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += demand_paging_test +TEST_GEN_PROGS_riscv += dirty_log_test +TEST_GEN_PROGS_riscv += kvm_create_max_vcpus +TEST_GEN_PROGS_riscv += kvm_page_table_test +TEST_GEN_PROGS_riscv += set_memory_region_test +TEST_GEN_PROGS_riscv += kvm_binary_stats_test + TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 2d62edc49d67..da854f997aeb 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -69,6 +69,16 @@ enum vm_guest_mode { #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) +#elif defined(__riscv) + +#if __riscv_xlen == 32 +#error "RISC-V 32-bit kvm selftests not supported" +#endif + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + #endif #define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h new file mode 100644 index 000000000000..dc284c6bdbc3 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * RISC-V processor specific defines + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H + +#include "kvm_util.h" +#include + +static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, + uint64_t size) +{ + return KVM_REG_RISCV | type | idx | size; +} + +#if __riscv_xlen == 64 +#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U64 +#else +#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32 +#endif + +#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \ + KVM_REG_RISCV_CONFIG_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \ + KVM_REG_RISCV_CORE_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \ + KVM_REG_RISCV_CSR_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \ + KVM_REG_RISCV_TIMER_REG(name), \ + KVM_REG_SIZE_U64) + +static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, + unsigned long *addr) +{ + struct kvm_one_reg reg; + + reg.id = id; + reg.addr = (unsigned long)addr; + vcpu_get_reg(vm, vcpuid, ®); +} + +static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, + unsigned long val) +{ + struct kvm_one_reg reg; + + reg.id = id; + reg.addr = (unsigned long)&val; + vcpu_set_reg(vm, vcpuid, ®); +} + +/* L3 index Bit[47:39] */ +#define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL +#define PGTBL_L3_INDEX_SHIFT 39 +#define PGTBL_L3_BLOCK_SHIFT 39 +#define PGTBL_L3_BLOCK_SIZE 0x0000008000000000ULL +#define PGTBL_L3_MAP_MASK (~(PGTBL_L3_BLOCK_SIZE - 1)) +/* L2 index Bit[38:30] */ +#define PGTBL_L2_INDEX_MASK 0x0000007FC0000000ULL +#define PGTBL_L2_INDEX_SHIFT 30 +#define PGTBL_L2_BLOCK_SHIFT 30 +#define PGTBL_L2_BLOCK_SIZE 0x0000000040000000ULL +#define PGTBL_L2_MAP_MASK (~(PGTBL_L2_BLOCK_SIZE - 1)) +/* L1 index Bit[29:21] */ +#define PGTBL_L1_INDEX_MASK 0x000000003FE00000ULL +#define PGTBL_L1_INDEX_SHIFT 21 +#define PGTBL_L1_BLOCK_SHIFT 21 +#define PGTBL_L1_BLOCK_SIZE 0x0000000000200000ULL +#define PGTBL_L1_MAP_MASK (~(PGTBL_L1_BLOCK_SIZE - 1)) +/* L0 index Bit[20:12] */ +#define PGTBL_L0_INDEX_MASK 0x00000000001FF000ULL +#define PGTBL_L0_INDEX_SHIFT 12 +#define PGTBL_L0_BLOCK_SHIFT 12 +#define PGTBL_L0_BLOCK_SIZE 0x0000000000001000ULL +#define PGTBL_L0_MAP_MASK (~(PGTBL_L0_BLOCK_SIZE - 1)) + +#define PGTBL_PTE_ADDR_MASK 0x003FFFFFFFFFFC00ULL +#define PGTBL_PTE_ADDR_SHIFT 10 +#define PGTBL_PTE_RSW_MASK 0x0000000000000300ULL +#define PGTBL_PTE_RSW_SHIFT 8 +#define PGTBL_PTE_DIRTY_MASK 0x0000000000000080ULL +#define PGTBL_PTE_DIRTY_SHIFT 7 +#define PGTBL_PTE_ACCESSED_MASK 0x0000000000000040ULL +#define PGTBL_PTE_ACCESSED_SHIFT 6 +#define PGTBL_PTE_GLOBAL_MASK 0x0000000000000020ULL +#define PGTBL_PTE_GLOBAL_SHIFT 5 +#define PGTBL_PTE_USER_MASK 0x0000000000000010ULL +#define PGTBL_PTE_USER_SHIFT 4 +#define PGTBL_PTE_EXECUTE_MASK 0x0000000000000008ULL +#define PGTBL_PTE_EXECUTE_SHIFT 3 +#define PGTBL_PTE_WRITE_MASK 0x0000000000000004ULL +#define PGTBL_PTE_WRITE_SHIFT 2 +#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL +#define PGTBL_PTE_READ_SHIFT 1 +#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \ + PGTBL_PTE_WRITE_MASK | \ + PGTBL_PTE_READ_MASK) +#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL +#define PGTBL_PTE_VALID_SHIFT 0 + +#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE +#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT + +#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) +#define SATP_MODE_39 _AC(0x8000000000000000, UL) +#define SATP_MODE_48 _AC(0x9000000000000000, UL) +#define SATP_ASID_BITS 16 +#define SATP_ASID_SHIFT 44 +#define SATP_ASID_MASK _AC(0xFFFF, UL) + +#define SBI_EXT_EXPERIMENTAL_START 0x08000000 +#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF + +#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END + +struct sbiret { + long error; + long value; +}; + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5); + +#endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index c330f414ef96..57839a12e472 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -38,6 +38,16 @@ void guest_modes_append_default(void) guest_mode_append(VM_MODE_P47V64_4K, true, true); } #endif +#ifdef __riscv + { + unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS); + + if (sz >= 52) + guest_mode_append(VM_MODE_P52V48_4K, true, true); + if (sz >= 48) + guest_mode_append(VM_MODE_P48V48_4K, true, true); + } +#endif } void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg) diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c new file mode 100644 index 000000000000..d377f2603d98 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V code + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include +#include + +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" + +#define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 + +static uint64_t page_align(struct kvm_vm *vm, uint64_t v) +{ + return (v + vm->page_size) & ~(vm->page_size - 1); +} + +static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +{ + return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) << + PGTBL_PAGE_SIZE_SHIFT; +} + +static uint64_t ptrs_per_pte(struct kvm_vm *vm) +{ + return PGTBL_PAGE_SIZE / sizeof(uint64_t); +} + +static uint64_t pte_index_mask[] = { + PGTBL_L0_INDEX_MASK, + PGTBL_L1_INDEX_MASK, + PGTBL_L2_INDEX_MASK, + PGTBL_L3_INDEX_MASK, +}; + +static uint32_t pte_index_shift[] = { + PGTBL_L0_INDEX_SHIFT, + PGTBL_L1_INDEX_SHIFT, + PGTBL_L2_INDEX_SHIFT, + PGTBL_L3_INDEX_SHIFT, +}; + +static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level) +{ + TEST_ASSERT(level > -1, + "Negative page table level (%d) not possible", level); + TEST_ASSERT(level < vm->pgtable_levels, + "Invalid page table level (%d)", level); + + return (gva & pte_index_mask[level]) >> pte_index_shift[level]; +} + +void virt_pgd_alloc(struct kvm_vm *vm) +{ + if (!vm->pgd_created) { + vm_paddr_t paddr = vm_phy_pages_alloc(vm, + page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size, + KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); + vm->pgd = paddr; + vm->pgd_created = true; + } +} + +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + uint64_t *ptep, next_ppn; + int level = vm->pgtable_levels - 1; + + TEST_ASSERT((vaddr % vm->page_size) == 0, + "Virtual address not on page boundary,\n" + " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, + (vaddr >> vm->page_shift)), + "Invalid virtual address, vaddr: 0x%lx", vaddr); + TEST_ASSERT((paddr % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, vaddr, level) * 8; + if (!*ptep) { + next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_VALID_MASK; + } + level--; + + while (level > -1) { + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + + pte_index(vm, vaddr, level) * 8; + if (!*ptep && level > 0) { + next_ppn = vm_alloc_page_table(vm) >> + PGTBL_PAGE_SIZE_SHIFT; + *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_VALID_MASK; + } + level--; + } + + paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK; +} + +vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + uint64_t *ptep; + int level = vm->pgtable_levels - 1; + + if (!vm->pgd_created) + goto unmapped_gva; + + ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, gva, level) * 8; + if (!ptep) + goto unmapped_gva; + level--; + + while (level > -1) { + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + + pte_index(vm, gva, level) * 8; + if (!ptep) + goto unmapped_gva; + level--; + } + + return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); + +unmapped_gva: + TEST_FAIL("No mapping for vm virtual address gva: 0x%lx level: %d", + gva, level); + exit(1); +} + +static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, + uint64_t page, int level) +{ +#ifdef DEBUG + static const char *const type[] = { "pte", "pmd", "pud", "p4d"}; + uint64_t pte, *ptep; + + if (level < 0) + return; + + for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) { + ptep = addr_gpa2hva(vm, pte); + if (!*ptep) + continue; + fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", + type[level], pte, *ptep, ptep); + pte_dump(stream, vm, indent + 1, + pte_addr(vm, *ptep), level - 1); + } +#endif +} + +void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + int level = vm->pgtable_levels - 1; + uint64_t pgd, *ptep; + + if (!vm->pgd_created) + return; + + for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pte(vm) * 8; pgd += 8) { + ptep = addr_gpa2hva(vm, pgd); + if (!*ptep) + continue; + fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", + pgd, *ptep, ptep); + pte_dump(stream, vm, indent + 1, + pte_addr(vm, *ptep), level - 1); + } +} + +void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid) +{ + unsigned long satp; + + /* + * The RISC-V Sv48 MMU mode supports 56-bit physical address + * for 48-bit virtual address with 4KB last level page size. + */ + switch (vm->mode) { + case VM_MODE_P52V48_4K: + case VM_MODE_P48V48_4K: + case VM_MODE_P40V48_4K: + break; + default: + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); + } + + satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN; + satp |= SATP_MODE_48; + + set_reg(vm, vcpuid, RISCV_CSR_REG(satp), satp); +} + +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +{ + struct kvm_riscv_core core; + + get_reg(vm, vcpuid, RISCV_CORE_REG(mode), &core.mode); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), &core.regs.pc); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.ra), &core.regs.ra); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), &core.regs.sp); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), &core.regs.gp); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.tp), &core.regs.tp); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t0), &core.regs.t0); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t1), &core.regs.t1); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t2), &core.regs.t2); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s0), &core.regs.s0); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s1), &core.regs.s1); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a0), &core.regs.a0); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a1), &core.regs.a1); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a2), &core.regs.a2); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a3), &core.regs.a3); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a4), &core.regs.a4); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a5), &core.regs.a5); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a6), &core.regs.a6); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a7), &core.regs.a7); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s2), &core.regs.s2); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s3), &core.regs.s3); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s4), &core.regs.s4); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s5), &core.regs.s5); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s6), &core.regs.s6); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s7), &core.regs.s7); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s8), &core.regs.s8); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s9), &core.regs.s9); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s10), &core.regs.s10); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s11), &core.regs.s11); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t3), &core.regs.t3); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t4), &core.regs.t4); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t5), &core.regs.t5); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t6), &core.regs.t6); + + fprintf(stream, + " MODE: 0x%lx\n", core.mode); + fprintf(stream, + " PC: 0x%016lx RA: 0x%016lx SP: 0x%016lx GP: 0x%016lx\n", + core.regs.pc, core.regs.ra, core.regs.sp, core.regs.gp); + fprintf(stream, + " TP: 0x%016lx T0: 0x%016lx T1: 0x%016lx T2: 0x%016lx\n", + core.regs.tp, core.regs.t0, core.regs.t1, core.regs.t2); + fprintf(stream, + " S0: 0x%016lx S1: 0x%016lx A0: 0x%016lx A1: 0x%016lx\n", + core.regs.s0, core.regs.s1, core.regs.a0, core.regs.a1); + fprintf(stream, + " A2: 0x%016lx A3: 0x%016lx A4: 0x%016lx A5: 0x%016lx\n", + core.regs.a2, core.regs.a3, core.regs.a4, core.regs.a5); + fprintf(stream, + " A6: 0x%016lx A7: 0x%016lx S2: 0x%016lx S3: 0x%016lx\n", + core.regs.a6, core.regs.a7, core.regs.s2, core.regs.s3); + fprintf(stream, + " S4: 0x%016lx S5: 0x%016lx S6: 0x%016lx S7: 0x%016lx\n", + core.regs.s4, core.regs.s5, core.regs.s6, core.regs.s7); + fprintf(stream, + " S8: 0x%016lx S9: 0x%016lx S10: 0x%016lx S11: 0x%016lx\n", + core.regs.s8, core.regs.s9, core.regs.s10, core.regs.s11); + fprintf(stream, + " T3: 0x%016lx T4: 0x%016lx T5: 0x%016lx T6: 0x%016lx\n", + core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6); +} + +static void guest_hang(void) +{ + while (1) + ; +} + +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +{ + int r; + size_t stack_size = vm->page_size == 4096 ? + DEFAULT_STACK_PGS * vm->page_size : + vm->page_size; + unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size, + DEFAULT_RISCV_GUEST_STACK_VADDR_MIN); + unsigned long current_gp = 0; + struct kvm_mp_state mps; + + vm_vcpu_add(vm, vcpuid); + riscv_vcpu_mmu_setup(vm, vcpuid); + + /* + * With SBI HSM support in KVM RISC-V, all secondary VCPUs are + * powered-off by default so we ensure that all secondary VCPUs + * are powered-on using KVM_SET_MP_STATE ioctl(). + */ + mps.mp_state = KVM_MP_STATE_RUNNABLE; + r = _vcpu_ioctl(vm, vcpuid, KVM_SET_MP_STATE, &mps); + TEST_ASSERT(!r, "IOCTL KVM_SET_MP_STATE failed (error %d)", r); + + /* Setup global pointer of guest to be same as the host */ + asm volatile ( + "add %0, gp, zero" : "=r" (current_gp) : : "memory"); + set_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), current_gp); + + /* Setup stack pointer and program counter of guest */ + set_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), + stack_vaddr + stack_size); + set_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), + (unsigned long)guest_code); + + /* Setup default exception vector of guest */ + set_reg(vm, vcpuid, RISCV_CSR_REG(stvec), + (unsigned long)guest_hang); +} + +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +{ + va_list ap; + uint64_t id = RISCV_CORE_REG(regs.a0); + int i; + + TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n" + " num: %u\n", num); + + va_start(ap, num); + + for (i = 0; i < num; i++) { + switch (i) { + case 0: + id = RISCV_CORE_REG(regs.a0); + break; + case 1: + id = RISCV_CORE_REG(regs.a1); + break; + case 2: + id = RISCV_CORE_REG(regs.a2); + break; + case 3: + id = RISCV_CORE_REG(regs.a3); + break; + case 4: + id = RISCV_CORE_REG(regs.a4); + break; + case 5: + id = RISCV_CORE_REG(regs.a5); + break; + case 6: + id = RISCV_CORE_REG(regs.a6); + break; + case 7: + id = RISCV_CORE_REG(regs.a7); + break; + }; + set_reg(vm, vcpuid, id, va_arg(ap, uint64_t)); + } + + va_end(ap); +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c new file mode 100644 index 000000000000..9e42d8248fa6 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucall support. A ucall is a "hypercall to userspace". + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include + +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" + +void ucall_init(struct kvm_vm *vm, void *arg) +{ +} + +void ucall_uninit(struct kvm_vm *vm) +{ +} + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5) +{ + register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); + register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); + register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); + register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); + register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); + register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); + register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); + register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); + struct sbiret ret; + + asm volatile ( + "ecall" + : "+r" (a0), "+r" (a1) + : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) + : "memory"); + ret.error = a0; + ret.value = a1; + + return ret; +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall uc = { + .cmd = cmd, + }; + va_list va; + int i; + + nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + + va_start(va, nargs); + for (i = 0; i < nargs; ++i) + uc.args[i] = va_arg(va, uint64_t); + va_end(va); + + sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, 0, (vm_vaddr_t)&uc, + 0, 0, 0, 0, 0); +} + +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +{ + struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct ucall ucall = {}; + + if (uc) + memset(uc, 0, sizeof(*uc)); + + if (run->exit_reason == KVM_EXIT_RISCV_SBI && + run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT && + run->riscv_sbi.function_id == 0) { + memcpy(&ucall, addr_gva2hva(vm, run->riscv_sbi.args[0]), + sizeof(ucall)); + + vcpu_run_complete_io(vm, vcpu_id); + if (uc) + memcpy(uc, &ucall, sizeof(ucall)); + } + + return ucall.cmd; +} -- cgit v1.2.3 From 33e5b5746cc2336660c8710ba109d9a3923627b5 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Mon, 27 Dec 2021 11:05:14 +0800 Subject: KVM: RISC-V: Avoid spurious virtual interrupts after clearing hideleg CSR When the last VM is terminated, the host kernel will invoke function hardware_disable_nolock() on each CPU to disable the related virtualization functions. Here, RISC-V currently only clears hideleg CSR and hedeleg CSR. This behavior will cause the host kernel to receive spurious interrupts if hvip CSR has pending interrupts and the corresponding enable bits in vsie CSR are asserted. To avoid it, hvip CSR and vsie CSR must be cleared before clearing hideleg CSR. Fixes: 99cdc6c18c2d ("RISC-V: Add initial skeletal KVM support") Signed-off-by: Vincent Chen Reviewed-by: Anup Patel Signed-off-by: Anup Patel --- arch/riscv/kvm/main.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 421ecf4e6360..2e5ca43c8c49 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -58,6 +58,14 @@ int kvm_arch_hardware_enable(void) void kvm_arch_hardware_disable(void) { + /* + * After clearing the hideleg CSR, the host kernel will receive + * spurious interrupts if hvip CSR has pending interrupts and the + * corresponding enable bits in vsie CSR are asserted. To avoid it, + * hvip CSR and vsie CSR must be cleared before clearing hideleg CSR. + */ + csr_write(CSR_VSIE, 0); + csr_write(CSR_HVIP, 0); csr_write(CSR_HEDELEG, 0); csr_write(CSR_HIDELEG, 0); } -- cgit v1.2.3 From 497685f2c743f552ec5626d60fc12e7c00faaf06 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 3 Jan 2022 18:54:58 +0530 Subject: MAINTAINERS: Update Anup's email address I am no longer work at Western Digital so update my email address to personal one and add entries to .mailmap as well. Signed-off-by: Anup Patel Acked-by: Atish Patra --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 29eedc1fab89..c7a7cfc6d2fe 100644 --- a/.mailmap +++ b/.mailmap @@ -46,6 +46,7 @@ Andy Adamson Antoine Tenart Antoine Tenart Antonio Ospite +Anup Patel Archit Taneja Ard Biesheuvel Arnaud Patard diff --git a/MAINTAINERS b/MAINTAINERS index d8972ed1f8d9..14efdaa0616f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10444,7 +10444,7 @@ F: arch/powerpc/kernel/kvm* F: arch/powerpc/kvm/ KERNEL VIRTUAL MACHINE FOR RISC-V (KVM/riscv) -M: Anup Patel +M: Anup Patel R: Atish Patra L: kvm@vger.kernel.org L: kvm-riscv@lists.infradead.org -- cgit v1.2.3