diff options
Diffstat (limited to 'arch/riscv/kvm')
| -rw-r--r-- | arch/riscv/kvm/Kconfig | 1 | ||||
| -rw-r--r-- | arch/riscv/kvm/Makefile | 11 | ||||
| -rw-r--r-- | arch/riscv/kvm/main.c | 21 | ||||
| -rw-r--r-- | arch/riscv/kvm/mmu.c | 375 | ||||
| -rw-r--r-- | arch/riscv/kvm/tlb.S | 74 | ||||
| -rw-r--r-- | arch/riscv/kvm/tlb.c | 402 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu.c | 413 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_exit.c | 531 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_fp.c | 30 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_insn.c | 751 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_sbi.c | 223 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_sbi_base.c | 100 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_sbi_hsm.c | 119 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_sbi_replace.c | 174 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_sbi_v01.c | 118 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_switch.S | 60 | ||||
| -rw-r--r-- | arch/riscv/kvm/vcpu_timer.c | 157 | ||||
| -rw-r--r-- | arch/riscv/kvm/vm.c | 23 | ||||
| -rw-r--r-- | arch/riscv/kvm/vmid.c | 36 |
19 files changed, 2562 insertions, 1057 deletions
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index f5a342fa1b1d..f36a737d5f96 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -24,6 +24,7 @@ config KVM select PREEMPT_NOTIFIERS select KVM_MMIO select KVM_GENERIC_DIRTYLOG_READ_PROTECT + select KVM_XFER_TO_GUEST_WORK select HAVE_KVM_VCPU_ASYNC_IOCTL select HAVE_KVM_EVENTFD select SRCU diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 30cdd1df0098..019df9208bdd 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -5,14 +5,10 @@ ccflags-y += -I $(srctree)/$(src) -KVM := ../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o -kvm-y += $(KVM)/kvm_main.o -kvm-y += $(KVM)/coalesced_mmio.o -kvm-y += $(KVM)/binary_stats.o -kvm-y += $(KVM)/eventfd.o kvm-y += main.o kvm-y += vm.o kvm-y += vmid.o @@ -21,6 +17,11 @@ kvm-y += mmu.o kvm-y += vcpu.o kvm-y += vcpu_exit.o kvm-y += vcpu_fp.o +kvm-y += vcpu_insn.o kvm-y += vcpu_switch.o kvm-y += vcpu_sbi.o +kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o +kvm-y += vcpu_sbi_base.o +kvm-y += vcpu_sbi_replace.o +kvm-y += vcpu_sbi_hsm.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 421ecf4e6360..df2d8716851f 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); } @@ -81,13 +89,13 @@ int kvm_arch_init(void *opaque) return -ENODEV; } - kvm_riscv_stage2_mode_detect(); + kvm_riscv_gstage_mode_detect(); - kvm_riscv_stage2_vmid_detect(); + kvm_riscv_gstage_vmid_detect(); kvm_info("hypervisor extension available\n"); - switch (kvm_riscv_stage2_mode()) { + switch (kvm_riscv_gstage_mode()) { case HGATP_MODE_SV32X4: str = "Sv32x4"; break; @@ -97,12 +105,15 @@ int kvm_arch_init(void *opaque) case HGATP_MODE_SV48X4: str = "Sv48x4"; break; + case HGATP_MODE_SV57X4: + str = "Sv57x4"; + break; default: return -ENODEV; } kvm_info("using %s G-stage page table format\n", str); - kvm_info("VMID %ld bits available\n", kvm_riscv_stage2_vmid_bits()); + kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits()); return 0; } @@ -111,7 +122,7 @@ void kvm_arch_exit(void) { } -static int riscv_kvm_init(void) +static int __init riscv_kvm_init(void) { return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); } diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index fc058ff5f4b6..3620ecac2fa1 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -18,53 +18,52 @@ #include <asm/csr.h> #include <asm/page.h> #include <asm/pgtable.h> -#include <asm/sbi.h> #ifdef CONFIG_64BIT -static unsigned long stage2_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); -static unsigned long stage2_pgd_levels = 3; -#define stage2_index_bits 9 +static unsigned long gstage_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); +static unsigned long gstage_pgd_levels = 3; +#define gstage_index_bits 9 #else -static unsigned long stage2_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); -static unsigned long stage2_pgd_levels = 2; -#define stage2_index_bits 10 +static unsigned long gstage_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); +static unsigned long gstage_pgd_levels = 2; +#define gstage_index_bits 10 #endif -#define stage2_pgd_xbits 2 -#define stage2_pgd_size (1UL << (HGATP_PAGE_SHIFT + stage2_pgd_xbits)) -#define stage2_gpa_bits (HGATP_PAGE_SHIFT + \ - (stage2_pgd_levels * stage2_index_bits) + \ - stage2_pgd_xbits) -#define stage2_gpa_size ((gpa_t)(1ULL << stage2_gpa_bits)) +#define gstage_pgd_xbits 2 +#define gstage_pgd_size (1UL << (HGATP_PAGE_SHIFT + gstage_pgd_xbits)) +#define gstage_gpa_bits (HGATP_PAGE_SHIFT + \ + (gstage_pgd_levels * gstage_index_bits) + \ + gstage_pgd_xbits) +#define gstage_gpa_size ((gpa_t)(1ULL << gstage_gpa_bits)) -#define stage2_pte_leaf(__ptep) \ +#define gstage_pte_leaf(__ptep) \ (pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)) -static inline unsigned long stage2_pte_index(gpa_t addr, u32 level) +static inline unsigned long gstage_pte_index(gpa_t addr, u32 level) { unsigned long mask; - unsigned long shift = HGATP_PAGE_SHIFT + (stage2_index_bits * level); + unsigned long shift = HGATP_PAGE_SHIFT + (gstage_index_bits * level); - if (level == (stage2_pgd_levels - 1)) - mask = (PTRS_PER_PTE * (1UL << stage2_pgd_xbits)) - 1; + if (level == (gstage_pgd_levels - 1)) + mask = (PTRS_PER_PTE * (1UL << gstage_pgd_xbits)) - 1; else mask = PTRS_PER_PTE - 1; return (addr >> shift) & mask; } -static inline unsigned long stage2_pte_page_vaddr(pte_t pte) +static inline unsigned long gstage_pte_page_vaddr(pte_t pte) { - return (unsigned long)pfn_to_virt(pte_val(pte) >> _PAGE_PFN_SHIFT); + return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte))); } -static int stage2_page_size_to_level(unsigned long page_size, u32 *out_level) +static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level) { u32 i; unsigned long psz = 1UL << 12; - for (i = 0; i < stage2_pgd_levels; i++) { - if (page_size == (psz << (i * stage2_index_bits))) { + for (i = 0; i < gstage_pgd_levels; i++) { + if (page_size == (psz << (i * gstage_index_bits))) { *out_level = i; return 0; } @@ -73,64 +72,39 @@ static int stage2_page_size_to_level(unsigned long page_size, u32 *out_level) return -EINVAL; } -static int stage2_level_to_page_size(u32 level, unsigned long *out_pgsize) +static int gstage_level_to_page_order(u32 level, unsigned long *out_pgorder) { - if (stage2_pgd_levels < level) + if (gstage_pgd_levels < level) return -EINVAL; - *out_pgsize = 1UL << (12 + (level * stage2_index_bits)); - + *out_pgorder = 12 + (level * gstage_index_bits); return 0; } -static int stage2_cache_topup(struct kvm_mmu_page_cache *pcache, - int min, int max) +static int gstage_level_to_page_size(u32 level, unsigned long *out_pgsize) { - void *page; + int rc; + unsigned long page_order = PAGE_SHIFT; - 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; - } + rc = gstage_level_to_page_order(level, &page_order); + if (rc) + return rc; + *out_pgsize = BIT(page_order); 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, +static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr, pte_t **ptepp, u32 *ptep_level) { pte_t *ptep; - u32 current_level = stage2_pgd_levels - 1; + u32 current_level = gstage_pgd_levels - 1; *ptep_level = current_level; ptep = (pte_t *)kvm->arch.pgd; - ptep = &ptep[stage2_pte_index(addr, current_level)]; + ptep = &ptep[gstage_pte_index(addr, current_level)]; while (ptep && pte_val(*ptep)) { - if (stage2_pte_leaf(ptep)) { + if (gstage_pte_leaf(ptep)) { *ptep_level = current_level; *ptepp = ptep; return true; @@ -139,8 +113,8 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr, if (current_level) { current_level--; *ptep_level = current_level; - ptep = (pte_t *)stage2_pte_page_vaddr(*ptep); - ptep = &ptep[stage2_pte_index(addr, current_level)]; + ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + ptep = &ptep[gstage_pte_index(addr, current_level)]; } else { ptep = NULL; } @@ -149,67 +123,59 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr, return false; } -static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr) +static void gstage_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr) { - struct cpumask hmask; - unsigned long size = PAGE_SIZE; - struct kvm_vmid *vmid = &kvm->arch.vmid; + unsigned long order = PAGE_SHIFT; - if (stage2_level_to_page_size(level, &size)) + if (gstage_level_to_page_order(level, &order)) return; - addr &= ~(size - 1); + addr &= ~(BIT(order) - 1); - /* - * TODO: Instead of cpu_online_mask, we should only target CPUs - * where the Guest/VM is running. - */ - preempt_disable(); - riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask); - sbi_remote_hfence_gvma_vmid(cpumask_bits(&hmask), addr, size, - READ_ONCE(vmid->vmid)); - preempt_enable(); + kvm_riscv_hfence_gvma_vmid_gpa(kvm, -1UL, 0, addr, BIT(order), order); } -static int stage2_set_pte(struct kvm *kvm, u32 level, - struct kvm_mmu_page_cache *pcache, +static int gstage_set_pte(struct kvm *kvm, u32 level, + struct kvm_mmu_memory_cache *pcache, gpa_t addr, const pte_t *new_pte) { - u32 current_level = stage2_pgd_levels - 1; + u32 current_level = gstage_pgd_levels - 1; pte_t *next_ptep = (pte_t *)kvm->arch.pgd; - pte_t *ptep = &next_ptep[stage2_pte_index(addr, current_level)]; + pte_t *ptep = &next_ptep[gstage_pte_index(addr, current_level)]; if (current_level < level) return -EINVAL; while (current_level != level) { - if (stage2_pte_leaf(ptep)) + if (gstage_pte_leaf(ptep)) 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)), __pgprot(_PAGE_TABLE)); } else { - if (stage2_pte_leaf(ptep)) + if (gstage_pte_leaf(ptep)) return -EEXIST; - next_ptep = (pte_t *)stage2_pte_page_vaddr(*ptep); + next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); } current_level--; - ptep = &next_ptep[stage2_pte_index(addr, current_level)]; + ptep = &next_ptep[gstage_pte_index(addr, current_level)]; } *ptep = *new_pte; - if (stage2_pte_leaf(ptep)) - stage2_remote_tlb_flush(kvm, current_level, addr); + if (gstage_pte_leaf(ptep)) + gstage_remote_tlb_flush(kvm, current_level, addr); return 0; } -static int stage2_map_page(struct kvm *kvm, - struct kvm_mmu_page_cache *pcache, +static int gstage_map_page(struct kvm *kvm, + struct kvm_mmu_memory_cache *pcache, gpa_t gpa, phys_addr_t hpa, unsigned long page_size, bool page_rdonly, bool page_exec) @@ -219,7 +185,7 @@ static int stage2_map_page(struct kvm *kvm, pte_t new_pte; pgprot_t prot; - ret = stage2_page_size_to_level(page_size, &level); + ret = gstage_page_size_to_level(page_size, &level); if (ret) return ret; @@ -230,9 +196,9 @@ static int stage2_map_page(struct kvm *kvm, * PTE so that software can update these bits. * * We support both options mentioned above. To achieve this, we - * always set 'A' and 'D' PTE bits at time of creating stage2 + * always set 'A' and 'D' PTE bits at time of creating G-stage * mapping. To support KVM dirty page logging with both options - * mentioned above, we will write-protect stage2 PTEs to track + * mentioned above, we will write-protect G-stage PTEs to track * dirty pages. */ @@ -250,24 +216,24 @@ static int stage2_map_page(struct kvm *kvm, new_pte = pfn_pte(PFN_DOWN(hpa), prot); new_pte = pte_mkdirty(new_pte); - return stage2_set_pte(kvm, level, pcache, gpa, &new_pte); + return gstage_set_pte(kvm, level, pcache, gpa, &new_pte); } -enum stage2_op { - STAGE2_OP_NOP = 0, /* Nothing */ - STAGE2_OP_CLEAR, /* Clear/Unmap */ - STAGE2_OP_WP, /* Write-protect */ +enum gstage_op { + GSTAGE_OP_NOP = 0, /* Nothing */ + GSTAGE_OP_CLEAR, /* Clear/Unmap */ + GSTAGE_OP_WP, /* Write-protect */ }; -static void stage2_op_pte(struct kvm *kvm, gpa_t addr, - pte_t *ptep, u32 ptep_level, enum stage2_op op) +static void gstage_op_pte(struct kvm *kvm, gpa_t addr, + pte_t *ptep, u32 ptep_level, enum gstage_op op) { int i, ret; pte_t *next_ptep; u32 next_ptep_level; unsigned long next_page_size, page_size; - ret = stage2_level_to_page_size(ptep_level, &page_size); + ret = gstage_level_to_page_size(ptep_level, &page_size); if (ret) return; @@ -276,31 +242,31 @@ static void stage2_op_pte(struct kvm *kvm, gpa_t addr, if (!pte_val(*ptep)) return; - if (ptep_level && !stage2_pte_leaf(ptep)) { - next_ptep = (pte_t *)stage2_pte_page_vaddr(*ptep); + if (ptep_level && !gstage_pte_leaf(ptep)) { + next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); next_ptep_level = ptep_level - 1; - ret = stage2_level_to_page_size(next_ptep_level, + ret = gstage_level_to_page_size(next_ptep_level, &next_page_size); if (ret) return; - if (op == STAGE2_OP_CLEAR) + if (op == GSTAGE_OP_CLEAR) set_pte(ptep, __pte(0)); for (i = 0; i < PTRS_PER_PTE; i++) - stage2_op_pte(kvm, addr + i * next_page_size, + gstage_op_pte(kvm, addr + i * next_page_size, &next_ptep[i], next_ptep_level, op); - if (op == STAGE2_OP_CLEAR) + if (op == GSTAGE_OP_CLEAR) put_page(virt_to_page(next_ptep)); } else { - if (op == STAGE2_OP_CLEAR) + if (op == GSTAGE_OP_CLEAR) set_pte(ptep, __pte(0)); - else if (op == STAGE2_OP_WP) + else if (op == GSTAGE_OP_WP) set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE)); - stage2_remote_tlb_flush(kvm, ptep_level, addr); + gstage_remote_tlb_flush(kvm, ptep_level, addr); } } -static void stage2_unmap_range(struct kvm *kvm, gpa_t start, +static void gstage_unmap_range(struct kvm *kvm, gpa_t start, gpa_t size, bool may_block) { int ret; @@ -311,9 +277,9 @@ static void stage2_unmap_range(struct kvm *kvm, gpa_t start, gpa_t addr = start, end = start + size; while (addr < end) { - found_leaf = stage2_get_leaf_entry(kvm, addr, + found_leaf = gstage_get_leaf_entry(kvm, addr, &ptep, &ptep_level); - ret = stage2_level_to_page_size(ptep_level, &page_size); + ret = gstage_level_to_page_size(ptep_level, &page_size); if (ret) break; @@ -321,8 +287,8 @@ static void stage2_unmap_range(struct kvm *kvm, gpa_t start, goto next; if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) - stage2_op_pte(kvm, addr, ptep, - ptep_level, STAGE2_OP_CLEAR); + gstage_op_pte(kvm, addr, ptep, + ptep_level, GSTAGE_OP_CLEAR); next: addr += page_size; @@ -336,7 +302,7 @@ next: } } -static void stage2_wp_range(struct kvm *kvm, gpa_t start, gpa_t end) +static void gstage_wp_range(struct kvm *kvm, gpa_t start, gpa_t end) { int ret; pte_t *ptep; @@ -346,9 +312,9 @@ static void stage2_wp_range(struct kvm *kvm, gpa_t start, gpa_t end) unsigned long page_size; while (addr < end) { - found_leaf = stage2_get_leaf_entry(kvm, addr, + found_leaf = gstage_get_leaf_entry(kvm, addr, &ptep, &ptep_level); - ret = stage2_level_to_page_size(ptep_level, &page_size); + ret = gstage_level_to_page_size(ptep_level, &page_size); if (ret) break; @@ -356,15 +322,15 @@ static void stage2_wp_range(struct kvm *kvm, gpa_t start, gpa_t end) goto next; if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) - stage2_op_pte(kvm, addr, ptep, - ptep_level, STAGE2_OP_WP); + gstage_op_pte(kvm, addr, ptep, + ptep_level, GSTAGE_OP_WP); next: addr += page_size; } } -static void stage2_wp_memory_region(struct kvm *kvm, int slot) +static void gstage_wp_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); @@ -372,37 +338,39 @@ static void stage2_wp_memory_region(struct kvm *kvm, int slot) phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); - stage2_wp_range(kvm, start, end); + gstage_wp_range(kvm, start, end); spin_unlock(&kvm->mmu_lock); kvm_flush_remote_tlbs(kvm); } -static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, - unsigned long size, bool writable) +int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa, + phys_addr_t hpa, unsigned long size, + bool writable, bool in_atomic) { pte_t pte; int ret = 0; unsigned long pfn; phys_addr_t addr, end; - struct kvm_mmu_page_cache pcache = { 0, }; + struct kvm_mmu_memory_cache pcache = { + .gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0, + .gfp_zero = __GFP_ZERO, + }; end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK; pfn = __phys_to_pfn(hpa); for (addr = gpa; addr < end; addr += PAGE_SIZE) { - pte = pfn_pte(pfn, PAGE_KERNEL); + pte = pfn_pte(pfn, PAGE_KERNEL_IO); 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, gstage_pgd_levels); if (ret) goto out; spin_lock(&kvm->mmu_lock); - ret = stage2_set_pte(kvm, 0, &pcache, addr, &pte); + ret = gstage_set_pte(kvm, 0, &pcache, addr, &pte); spin_unlock(&kvm->mmu_lock); if (ret) goto out; @@ -411,10 +379,17 @@ 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; } +void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size) +{ + spin_lock(&kvm->mmu_lock); + gstage_unmap_range(kvm, gpa, size, false); + spin_unlock(&kvm->mmu_lock); +} + void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, @@ -424,7 +399,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; - stage2_wp_range(kvm, start, end); + gstage_wp_range(kvm, start, end); } void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) @@ -447,7 +422,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) void kvm_arch_flush_shadow_all(struct kvm *kvm) { - kvm_riscv_stage2_free_pgd(kvm); + kvm_riscv_gstage_free_pgd(kvm); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, @@ -457,12 +432,11 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, phys_addr_t size = slot->npages << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); - stage2_unmap_range(kvm, gpa, size, false); + gstage_unmap_range(kvm, gpa, size, false); spin_unlock(&kvm->mmu_lock); } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -472,18 +446,18 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while * the memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) - stage2_wp_memory_region(kvm, mem->slot); + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) + gstage_wp_memory_region(kvm, new->id); } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; - bool writable = !(mem->flags & KVM_MEM_READONLY); + hva_t hva, reg_end, size; + gpa_t base_gpa; + bool writable; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -494,10 +468,16 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the GPA * space addressable by the KVM guest GPA space. */ - if ((memslot->base_gfn + memslot->npages) >= - (stage2_gpa_size >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) >= + (gstage_gpa_size >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + size = new->npages << PAGE_SHIFT; + reg_end = hva + size; + base_gpa = new->base_gfn << PAGE_SHIFT; + writable = !(new->flags & KVM_MEM_READONLY); + mmap_read_lock(current->mm); /* @@ -533,21 +513,21 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, vm_end = min(reg_end, vma->vm_end); if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = mem->guest_phys_addr + - (vm_start - mem->userspace_addr); + gpa_t gpa = base_gpa + (vm_start - hva); phys_addr_t pa; pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } - ret = stage2_ioremap(kvm, gpa, pa, - vm_end - vm_start, writable); + ret = kvm_riscv_gstage_ioremap(kvm, gpa, pa, + vm_end - vm_start, + writable, false); if (ret) break; } @@ -559,8 +539,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, spin_lock(&kvm->mmu_lock); if (ret) - stage2_unmap_range(kvm, mem->guest_phys_addr, - mem->memory_size, false); + gstage_unmap_range(kvm, base_gpa, size, false); spin_unlock(&kvm->mmu_lock); out: @@ -573,7 +552,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - stage2_unmap_range(kvm, range->start << PAGE_SHIFT, + gstage_unmap_range(kvm, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); return false; @@ -589,10 +568,10 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) WARN_ON(range->end - range->start != 1); - ret = stage2_map_page(kvm, NULL, range->start << PAGE_SHIFT, + ret = gstage_map_page(kvm, NULL, range->start << PAGE_SHIFT, __pfn_to_phys(pfn), PAGE_SIZE, true, true); if (ret) { - kvm_debug("Failed to map stage2 page (error %d)\n", ret); + kvm_debug("Failed to map G-stage page (error %d)\n", ret); return true; } @@ -610,7 +589,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); - if (!stage2_get_leaf_entry(kvm, range->start << PAGE_SHIFT, + if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) return false; @@ -628,25 +607,25 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); - if (!stage2_get_leaf_entry(kvm, range->start << PAGE_SHIFT, + if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) return false; return pte_young(*ptep); } -int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, +int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, gpa_t gpa, unsigned long hva, bool is_write) { int ret; kvm_pfn_t hfn; - bool writeable; + bool writable; short vma_pageshift; 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; @@ -681,16 +660,15 @@ 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, gstage_pgd_levels); if (ret) { - kvm_err("Failed to topup stage2 cache\n"); + kvm_err("Failed to topup G-stage cache\n"); return ret; } - mmu_seq = kvm->mmu_notifier_seq; + mmu_seq = kvm->mmu_invalidate_seq; - hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writeable); + hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable); if (hfn == KVM_PFN_ERR_HWPOISON) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, vma_pageshift, current); @@ -704,25 +682,25 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, * for write faults. */ if (logging && !is_write) - writeable = false; + writable = false; spin_lock(&kvm->mmu_lock); - if (mmu_notifier_retry(kvm, mmu_seq)) + if (mmu_invalidate_retry(kvm, mmu_seq)) goto out_unlock; - if (writeable) { + if (writable) { kvm_set_pfn_dirty(hfn); mark_page_dirty(kvm, gfn); - ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, + ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, vma_pagesize, false, true); } else { - ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, + ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, vma_pagesize, true, true); } if (ret) - kvm_err("Failed to map in stage2\n"); + kvm_err("Failed to map in G-stage\n"); out_unlock: spin_unlock(&kvm->mmu_lock); @@ -731,12 +709,7 @@ 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) +int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm) { struct page *pgd_page; @@ -746,7 +719,7 @@ int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm) } pgd_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, - get_order(stage2_pgd_size)); + get_order(gstage_pgd_size)); if (!pgd_page) return -ENOMEM; kvm->arch.pgd = page_to_virt(pgd_page); @@ -755,13 +728,13 @@ int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm) return 0; } -void kvm_riscv_stage2_free_pgd(struct kvm *kvm) +void kvm_riscv_gstage_free_pgd(struct kvm *kvm) { void *pgd = NULL; spin_lock(&kvm->mmu_lock); if (kvm->arch.pgd) { - stage2_unmap_range(kvm, 0UL, stage2_gpa_size, false); + gstage_unmap_range(kvm, 0UL, gstage_gpa_size, false); pgd = READ_ONCE(kvm->arch.pgd); kvm->arch.pgd = NULL; kvm->arch.pgd_phys = 0; @@ -769,12 +742,12 @@ void kvm_riscv_stage2_free_pgd(struct kvm *kvm) spin_unlock(&kvm->mmu_lock); if (pgd) - free_pages((unsigned long)pgd, get_order(stage2_pgd_size)); + free_pages((unsigned long)pgd, get_order(gstage_pgd_size)); } -void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu) +void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) { - unsigned long hgatp = stage2_mode; + unsigned long hgatp = gstage_mode; struct kvm_arch *k = &vcpu->kvm->arch; hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & @@ -783,26 +756,40 @@ void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu) csr_write(CSR_HGATP, hgatp); - if (!kvm_riscv_stage2_vmid_bits()) - __kvm_riscv_hfence_gvma_all(); + if (!kvm_riscv_gstage_vmid_bits()) + kvm_riscv_local_hfence_gvma_all(); } -void kvm_riscv_stage2_mode_detect(void) +void kvm_riscv_gstage_mode_detect(void) { #ifdef CONFIG_64BIT - /* Try Sv48x4 stage2 mode */ + /* Try Sv57x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV57X4) { + gstage_mode = (HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT); + gstage_pgd_levels = 5; + goto skip_sv48x4_test; + } + + /* Try Sv48x4 G-stage mode */ csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) { - stage2_mode = (HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); - stage2_pgd_levels = 4; + gstage_mode = (HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); + gstage_pgd_levels = 4; } - csr_write(CSR_HGATP, 0); +skip_sv48x4_test: - __kvm_riscv_hfence_gvma_all(); + csr_write(CSR_HGATP, 0); + kvm_riscv_local_hfence_gvma_all(); #endif } -unsigned long kvm_riscv_stage2_mode(void) +unsigned long kvm_riscv_gstage_mode(void) +{ + return gstage_mode >> HGATP_MODE_SHIFT; +} + +int kvm_riscv_gstage_gpa_bits(void) { - return stage2_mode >> HGATP_MODE_SHIFT; + return gstage_gpa_bits; } diff --git a/arch/riscv/kvm/tlb.S b/arch/riscv/kvm/tlb.S deleted file mode 100644 index 899f75d60bad..000000000000 --- a/arch/riscv/kvm/tlb.S +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2019 Western Digital Corporation or its affiliates. - * - * Authors: - * Anup Patel <anup.patel@wdc.com> - */ - -#include <linux/linkage.h> -#include <asm/asm.h> - - .text - .altmacro - .option norelax - - /* - * Instruction encoding of hfence.gvma is: - * HFENCE.GVMA rs1, rs2 - * HFENCE.GVMA zero, rs2 - * HFENCE.GVMA rs1 - * HFENCE.GVMA - * - * rs1!=zero and rs2!=zero ==> HFENCE.GVMA rs1, rs2 - * rs1==zero and rs2!=zero ==> HFENCE.GVMA zero, rs2 - * rs1!=zero and rs2==zero ==> HFENCE.GVMA rs1 - * rs1==zero and rs2==zero ==> HFENCE.GVMA - * - * Instruction encoding of HFENCE.GVMA is: - * 0110001 rs2(5) rs1(5) 000 00000 1110011 - */ - -ENTRY(__kvm_riscv_hfence_gvma_vmid_gpa) - /* - * rs1 = a0 (GPA >> 2) - * rs2 = a1 (VMID) - * HFENCE.GVMA a0, a1 - * 0110001 01011 01010 000 00000 1110011 - */ - .word 0x62b50073 - ret -ENDPROC(__kvm_riscv_hfence_gvma_vmid_gpa) - -ENTRY(__kvm_riscv_hfence_gvma_vmid) - /* - * rs1 = zero - * rs2 = a0 (VMID) - * HFENCE.GVMA zero, a0 - * 0110001 01010 00000 000 00000 1110011 - */ - .word 0x62a00073 - ret -ENDPROC(__kvm_riscv_hfence_gvma_vmid) - -ENTRY(__kvm_riscv_hfence_gvma_gpa) - /* - * rs1 = a0 (GPA >> 2) - * rs2 = zero - * HFENCE.GVMA a0 - * 0110001 00000 01010 000 00000 1110011 - */ - .word 0x62050073 - ret -ENDPROC(__kvm_riscv_hfence_gvma_gpa) - -ENTRY(__kvm_riscv_hfence_gvma_all) - /* - * rs1 = zero - * rs2 = zero - * HFENCE.GVMA - * 0110001 00000 00000 000 00000 1110011 - */ - .word 0x62000073 - ret -ENDPROC(__kvm_riscv_hfence_gvma_all) diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c new file mode 100644 index 000000000000..309d79b3e5cd --- /dev/null +++ b/arch/riscv/kvm/tlb.c @@ -0,0 +1,402 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include <linux/bitmap.h> +#include <linux/cpumask.h> +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/smp.h> +#include <linux/kvm_host.h> +#include <asm/cacheflush.h> +#include <asm/csr.h> +#include <asm/hwcap.h> +#include <asm/insn-def.h> + +#define has_svinval() \ + static_branch_unlikely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_SVINVAL]) + +void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, + gpa_t gpa, gpa_t gpsz, + unsigned long order) +{ + gpa_t pos; + + if (PTRS_PER_PTE < (gpsz >> order)) { + kvm_riscv_local_hfence_gvma_vmid_all(vmid); + return; + } + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) + asm volatile (HINVAL_GVMA(%0, %1) + : : "r" (pos >> 2), "r" (vmid) : "memory"); + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) + asm volatile (HFENCE_GVMA(%0, %1) + : : "r" (pos >> 2), "r" (vmid) : "memory"); + } +} + +void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid) +{ + asm volatile(HFENCE_GVMA(zero, %0) : : "r" (vmid) : "memory"); +} + +void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz, + unsigned long order) +{ + gpa_t pos; + + if (PTRS_PER_PTE < (gpsz >> order)) { + kvm_riscv_local_hfence_gvma_all(); + return; + } + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) + asm volatile(HINVAL_GVMA(%0, zero) + : : "r" (pos >> 2) : "memory"); + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) + asm volatile(HFENCE_GVMA(%0, zero) + : : "r" (pos >> 2) : "memory"); + } +} + +void kvm_riscv_local_hfence_gvma_all(void) +{ + asm volatile(HFENCE_GVMA(zero, zero) : : : "memory"); +} + +void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid, + unsigned long asid, + unsigned long gva, + unsigned long gvsz, + unsigned long order) +{ + unsigned long pos, hgatp; + + if (PTRS_PER_PTE < (gvsz >> order)) { + kvm_riscv_local_hfence_vvma_asid_all(vmid, asid); + return; + } + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) + asm volatile(HINVAL_VVMA(%0, %1) + : : "r" (pos), "r" (asid) : "memory"); + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) + asm volatile(HFENCE_VVMA(%0, %1) + : : "r" (pos), "r" (asid) : "memory"); + } + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid, + unsigned long asid) +{ + unsigned long hgatp; + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + asm volatile(HFENCE_VVMA(zero, %0) : : "r" (asid) : "memory"); + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid, + unsigned long gva, unsigned long gvsz, + unsigned long order) +{ + unsigned long pos, hgatp; + + if (PTRS_PER_PTE < (gvsz >> order)) { + kvm_riscv_local_hfence_vvma_all(vmid); + return; + } + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) + asm volatile(HINVAL_VVMA(%0, zero) + : : "r" (pos) : "memory"); + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) + asm volatile(HFENCE_VVMA(%0, zero) + : : "r" (pos) : "memory"); + } + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_hfence_vvma_all(unsigned long vmid) +{ + unsigned long hgatp; + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + asm volatile(HFENCE_VVMA(zero, zero) : : : "memory"); + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) +{ + unsigned long vmid; + + if (!kvm_riscv_gstage_vmid_bits() || + vcpu->arch.last_exit_cpu == vcpu->cpu) + return; + + /* + * On RISC-V platforms with hardware VMID support, we share same + * VMID for all VCPUs of a particular Guest/VM. This means we might + * have stale G-stage TLB entries on the current Host CPU due to + * some other VCPU of the same Guest which ran previously on the + * current Host CPU. + * + * To cleanup stale TLB entries, we simply flush all G-stage TLB + * entries by VMID whenever underlying Host CPU changes for a VCPU. + */ + + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + kvm_riscv_local_hfence_gvma_vmid_all(vmid); +} + +void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) +{ + local_flush_icache_all(); +} + +void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu) +{ + struct kvm_vmid *vmid; + + vmid = &vcpu->kvm->arch.vmid; + kvm_riscv_local_hfence_gvma_vmid_all(READ_ONCE(vmid->vmid)); +} + +void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu) +{ + struct kvm_vmid *vmid; + + vmid = &vcpu->kvm->arch.vmid; + kvm_riscv_local_hfence_vvma_all(READ_ONCE(vmid->vmid)); +} + +static bool vcpu_hfence_dequeue(struct kvm_vcpu *vcpu, + struct kvm_riscv_hfence *out_data) +{ + bool ret = false; + struct kvm_vcpu_arch *varch = &vcpu->arch; + + spin_lock(&varch->hfence_lock); + + if (varch->hfence_queue[varch->hfence_head].type) { + memcpy(out_data, &varch->hfence_queue[varch->hfence_head], + sizeof(*out_data)); + varch->hfence_queue[varch->hfence_head].type = 0; + + varch->hfence_head++; + if (varch->hfence_head == KVM_RISCV_VCPU_MAX_HFENCE) + varch->hfence_head = 0; + + ret = true; + } + + spin_unlock(&varch->hfence_lock); + + return ret; +} + +static bool vcpu_hfence_enqueue(struct kvm_vcpu *vcpu, + const struct kvm_riscv_hfence *data) +{ + bool ret = false; + struct kvm_vcpu_arch *varch = &vcpu->arch; + + spin_lock(&varch->hfence_lock); + + if (!varch->hfence_queue[varch->hfence_tail].type) { + memcpy(&varch->hfence_queue[varch->hfence_tail], + data, sizeof(*data)); + + varch->hfence_tail++; + if (varch->hfence_tail == KVM_RISCV_VCPU_MAX_HFENCE) + varch->hfence_tail = 0; + + ret = true; + } + + spin_unlock(&varch->hfence_lock); + + return ret; +} + +void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) +{ + struct kvm_riscv_hfence d = { 0 }; + struct kvm_vmid *v = &vcpu->kvm->arch.vmid; + + while (vcpu_hfence_dequeue(vcpu, &d)) { + switch (d.type) { + case KVM_RISCV_HFENCE_UNKNOWN: + break; + case KVM_RISCV_HFENCE_GVMA_VMID_GPA: + kvm_riscv_local_hfence_gvma_vmid_gpa( + READ_ONCE(v->vmid), + d.addr, d.size, d.order); + break; + case KVM_RISCV_HFENCE_VVMA_ASID_GVA: + kvm_riscv_local_hfence_vvma_asid_gva( + READ_ONCE(v->vmid), d.asid, + d.addr, d.size, d.order); + break; + case KVM_RISCV_HFENCE_VVMA_ASID_ALL: + kvm_riscv_local_hfence_vvma_asid_all( + READ_ONCE(v->vmid), d.asid); + break; + case KVM_RISCV_HFENCE_VVMA_GVA: + kvm_riscv_local_hfence_vvma_gva( + READ_ONCE(v->vmid), + d.addr, d.size, d.order); + break; + default: + break; + } + } +} + +static void make_xfence_request(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned int req, unsigned int fallback_req, + const struct kvm_riscv_hfence *data) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + unsigned int actual_req = req; + DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); + + bitmap_clear(vcpu_mask, 0, KVM_MAX_VCPUS); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (hbase != -1UL) { + if (vcpu->vcpu_id < hbase) + continue; + if (!(hmask & (1UL << (vcpu->vcpu_id - hbase)))) + continue; + } + + bitmap_set(vcpu_mask, i, 1); + + if (!data || !data->type) + continue; + + /* + * Enqueue hfence data to VCPU hfence queue. If we don't + * have space in the VCPU hfence queue then fallback to + * a more conservative hfence request. + */ + if (!vcpu_hfence_enqueue(vcpu, data)) + actual_req = fallback_req; + } + + kvm_make_vcpus_request_mask(kvm, actual_req, vcpu_mask); +} + +void kvm_riscv_fence_i(struct kvm *kvm, + unsigned long hbase, unsigned long hmask) +{ + make_xfence_request(kvm, hbase, hmask, KVM_REQ_FENCE_I, + KVM_REQ_FENCE_I, NULL); +} + +void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + gpa_t gpa, gpa_t gpsz, + unsigned long order) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_GVMA_VMID_GPA; + data.asid = 0; + data.addr = gpa; + data.size = gpsz; + data.order = order; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_GVMA_VMID_ALL, &data); +} + +void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask) +{ + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE_GVMA_VMID_ALL, + KVM_REQ_HFENCE_GVMA_VMID_ALL, NULL); +} + +void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long asid) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_VVMA_ASID_GVA; + data.asid = asid; + data.addr = gva; + data.size = gvsz; + data.order = order; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long asid) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_VVMA_ASID_ALL; + data.asid = asid; + data.addr = data.size = data.order = 0; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_VVMA_GVA; + data.asid = 0; + data.addr = gva; + data.size = gvsz; + data.order = order; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +void kvm_riscv_hfence_vvma_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask) +{ + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE_VVMA_ALL, + KVM_REQ_HFENCE_VVMA_ALL, NULL); +} diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index fb84619df012..71ebbc4821f0 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -7,6 +7,7 @@ */ #include <linux/bitops.h> +#include <linux/entry-kvm.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/kdebug.h> @@ -18,6 +19,7 @@ #include <linux/fs.h> #include <linux/kvm_host.h> #include <asm/csr.h> +#include <asm/cacheflush.h> #include <asm/hwcap.h> const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { @@ -26,6 +28,9 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, wfi_exit_stat), STATS_DESC_COUNTER(VCPU, mmio_exit_user), STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), + STATS_DESC_COUNTER(VCPU, csr_exit_user), + STATS_DESC_COUNTER(VCPU, csr_exit_kernel), + STATS_DESC_COUNTER(VCPU, signal_exits), STATS_DESC_COUNTER(VCPU, exits) }; @@ -38,14 +43,68 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -#define KVM_RISCV_ISA_ALLOWED (riscv_isa_extension_mask(a) | \ - riscv_isa_extension_mask(c) | \ - riscv_isa_extension_mask(d) | \ - riscv_isa_extension_mask(f) | \ - riscv_isa_extension_mask(i) | \ - riscv_isa_extension_mask(m) | \ - riscv_isa_extension_mask(s) | \ - riscv_isa_extension_mask(u)) +#define KVM_RISCV_BASE_ISA_MASK GENMASK(25, 0) + +#define KVM_ISA_EXT_ARR(ext) [KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext + +/* Mapping between KVM ISA Extension ID & Host ISA extension ID */ +static const unsigned long kvm_isa_ext_arr[] = { + [KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a, + [KVM_RISCV_ISA_EXT_C] = RISCV_ISA_EXT_c, + [KVM_RISCV_ISA_EXT_D] = RISCV_ISA_EXT_d, + [KVM_RISCV_ISA_EXT_F] = RISCV_ISA_EXT_f, + [KVM_RISCV_ISA_EXT_H] = RISCV_ISA_EXT_h, + [KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i, + [KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m, + + KVM_ISA_EXT_ARR(SSTC), + KVM_ISA_EXT_ARR(SVINVAL), + KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(ZIHINTPAUSE), + KVM_ISA_EXT_ARR(ZICBOM), +}; + +static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext) +{ + unsigned long i; + + for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { + if (kvm_isa_ext_arr[i] == base_ext) + return i; + } + + return KVM_RISCV_ISA_EXT_MAX; +} + +static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext) +{ + switch (ext) { + case KVM_RISCV_ISA_EXT_H: + return false; + default: + break; + } + + return true; +} + +static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) +{ + switch (ext) { + case KVM_RISCV_ISA_EXT_A: + case KVM_RISCV_ISA_EXT_C: + case KVM_RISCV_ISA_EXT_I: + case KVM_RISCV_ISA_EXT_M: + case KVM_RISCV_ISA_EXT_SSTC: + case KVM_RISCV_ISA_EXT_SVINVAL: + case KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + return false; + default: + break; + } + + return true; +} static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) { @@ -53,6 +112,19 @@ 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); + + vcpu->arch.last_exit_cpu = -1; memcpy(csr, reset_csr, sizeof(*csr)); @@ -64,6 +136,15 @@ 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); + + vcpu->arch.hfence_head = 0; + vcpu->arch.hfence_tail = 0; + memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue)); + + /* 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) @@ -74,12 +155,24 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *cntx; + struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; + unsigned long host_isa, i; /* Mark this VCPU never ran */ vcpu->arch.ran_atleast_once = false; + vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; + bitmap_zero(vcpu->arch.isa, RISCV_ISA_EXT_MAX); /* Setup ISA features available to VCPU */ - vcpu->arch.isa = riscv_isa_extension_base(NULL) & KVM_RISCV_ISA_ALLOWED; + for (i = 0; i < ARRAY_SIZE(kvm_isa_ext_arr); i++) { + host_isa = kvm_isa_ext_arr[i]; + if (__riscv_isa_extension_available(NULL, host_isa) && + kvm_riscv_vcpu_isa_enable_allowed(i)) + set_bit(host_isa, vcpu->arch.isa); + } + + /* Setup VCPU hfence queue */ + spin_lock_init(&vcpu->arch.hfence_lock); /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ cntx = &vcpu->arch.guest_reset_context; @@ -89,6 +182,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) cntx->hstatus |= HSTATUS_SPVP; cntx->hstatus |= HSTATUS_SPV; + /* By default, make CY, TM, and IR counters accessible in VU mode */ + reset_csr->scounteren = 0x7; + /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); @@ -100,6 +196,13 @@ 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) @@ -107,13 +210,13 @@ 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 G-stage page table mappings */ + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return kvm_riscv_vcpu_has_interrupts(vcpu, 1UL << IRQ_VS_TIMER); + return kvm_riscv_vcpu_timer_pending(vcpu); } void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) @@ -160,7 +263,12 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu, switch (reg_num) { case KVM_REG_RISCV_CONFIG_REG(isa): - reg_val = vcpu->arch.isa; + reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK; + break; + case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): + if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM)) + return -EINVAL; + reg_val = riscv_cbom_block_size; break; default: return -EINVAL; @@ -180,7 +288,7 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CONFIG); - unsigned long reg_val; + unsigned long i, isa_ext, reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; @@ -188,17 +296,39 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; + /* This ONE REG interface is only defined for single letter extensions */ + if (fls(reg_val) >= RISCV_ISA_EXT_BASE) + return -EINVAL; + switch (reg_num) { case KVM_REG_RISCV_CONFIG_REG(isa): if (!vcpu->arch.ran_atleast_once) { - vcpu->arch.isa = reg_val; - vcpu->arch.isa &= riscv_isa_extension_base(NULL); - vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED; + /* Ignore the enable/disable request for certain extensions */ + for (i = 0; i < RISCV_ISA_EXT_BASE; i++) { + isa_ext = kvm_riscv_vcpu_base2isa_ext(i); + if (isa_ext >= KVM_RISCV_ISA_EXT_MAX) { + reg_val &= ~BIT(i); + continue; + } + if (!kvm_riscv_vcpu_isa_enable_allowed(isa_ext)) + if (reg_val & BIT(i)) + reg_val &= ~BIT(i); + if (!kvm_riscv_vcpu_isa_disable_allowed(isa_ext)) + if (!(reg_val & BIT(i))) + reg_val |= BIT(i); + } + reg_val &= riscv_isa_extension_base(NULL); + /* Do not modify anything beyond single letter extensions */ + reg_val = (vcpu->arch.isa[0] & ~KVM_RISCV_BASE_ISA_MASK) | + (reg_val & KVM_RISCV_BASE_ISA_MASK); + vcpu->arch.isa[0] = reg_val; kvm_riscv_vcpu_fp_reset(vcpu); } else { return -EOPNOTSUPP; } break; + case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): + return -EOPNOTSUPP; default: return -EINVAL; } @@ -334,6 +464,80 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, return 0; } +static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_ISA_EXT); + unsigned long reg_val = 0; + unsigned long host_isa_ext; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + if (reg_num >= KVM_RISCV_ISA_EXT_MAX || + reg_num >= ARRAY_SIZE(kvm_isa_ext_arr)) + return -EINVAL; + + host_isa_ext = kvm_isa_ext_arr[reg_num]; + if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext)) + reg_val = 1; /* Mark the given extension as available */ + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_ISA_EXT); + unsigned long reg_val; + unsigned long host_isa_ext; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + if (reg_num >= KVM_RISCV_ISA_EXT_MAX || + reg_num >= ARRAY_SIZE(kvm_isa_ext_arr)) + return -EINVAL; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + host_isa_ext = kvm_isa_ext_arr[reg_num]; + if (!__riscv_isa_extension_available(NULL, host_isa_ext)) + return -EOPNOTSUPP; + + if (!vcpu->arch.ran_atleast_once) { + /* + * All multi-letter extension and a few single letter + * extension can be disabled + */ + if (reg_val == 1 && + kvm_riscv_vcpu_isa_enable_allowed(reg_num)) + set_bit(host_isa_ext, vcpu->arch.isa); + else if (!reg_val && + kvm_riscv_vcpu_isa_disable_allowed(reg_num)) + clear_bit(host_isa_ext, vcpu->arch.isa); + else + return -EINVAL; + kvm_riscv_vcpu_fp_reset(vcpu); + } else { + return -EOPNOTSUPP; + } + + return 0; +} + static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { @@ -351,6 +555,8 @@ static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu, else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D) return kvm_riscv_vcpu_set_reg_fp(vcpu, reg, KVM_REG_RISCV_FP_D); + else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT) + return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg); return -EINVAL; } @@ -372,6 +578,8 @@ static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu, else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D) return kvm_riscv_vcpu_get_reg_fp(vcpu, reg, KVM_REG_RISCV_FP_D); + else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT) + return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg); return -EINVAL; } @@ -500,6 +708,9 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) clear_bit(IRQ_VS_SOFT, &v->irqs_pending); } } + + /* Sync-up timer CSRs */ + kvm_riscv_vcpu_timer_sync(vcpu); } int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) @@ -590,6 +801,25 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, return -EINVAL; } +static void kvm_riscv_vcpu_update_config(const unsigned long *isa) +{ + u64 henvcfg = 0; + + if (riscv_isa_extension_available(isa, SVPBMT)) + henvcfg |= ENVCFG_PBMTE; + + if (riscv_isa_extension_available(isa, SSTC)) + henvcfg |= ENVCFG_STCE; + + if (riscv_isa_extension_available(isa, ZICBOM)) + henvcfg |= (ENVCFG_CBIE | ENVCFG_CBCFE); + + csr_write(CSR_HENVCFG, henvcfg); +#ifdef CONFIG_32BIT + csr_write(CSR_HENVCFGH, henvcfg >> 32); +#endif +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; @@ -604,7 +834,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) csr_write(CSR_HVIP, csr->hvip); csr_write(CSR_VSATP, csr->vsatp); - kvm_riscv_stage2_update_hgatp(vcpu); + kvm_riscv_vcpu_update_config(vcpu->arch.isa); + + kvm_riscv_gstage_update_hgatp(vcpu); kvm_riscv_vcpu_timer_restore(vcpu); @@ -625,7 +857,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.isa); kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); - csr_write(CSR_HGATP, 0); + kvm_riscv_vcpu_timer_save(vcpu); csr->vsstatus = csr_read(CSR_VSSTATUS); csr->vsie = csr_read(CSR_VSIE); @@ -644,9 +876,11 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) { + kvm_vcpu_srcu_read_unlock(vcpu); rcuwait_wait_event(wait, (!vcpu->arch.power_off) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); + kvm_vcpu_srcu_read_lock(vcpu); if (vcpu->arch.power_off || vcpu->arch.pause) { /* @@ -661,10 +895,23 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) kvm_riscv_reset_vcpu(vcpu); if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu)) - kvm_riscv_stage2_update_hgatp(vcpu); + kvm_riscv_gstage_update_hgatp(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) - __kvm_riscv_hfence_gvma_all(); + if (kvm_check_request(KVM_REQ_FENCE_I, vcpu)) + kvm_riscv_fence_i_process(vcpu); + + /* + * The generic KVM_REQ_TLB_FLUSH is same as + * KVM_REQ_HFENCE_GVMA_VMID_ALL + */ + if (kvm_check_request(KVM_REQ_HFENCE_GVMA_VMID_ALL, vcpu)) + kvm_riscv_hfence_gvma_vmid_all_process(vcpu); + + if (kvm_check_request(KVM_REQ_HFENCE_VVMA_ALL, vcpu)) + kvm_riscv_hfence_vvma_all_process(vcpu); + + if (kvm_check_request(KVM_REQ_HFENCE, vcpu)) + kvm_riscv_hfence_process(vcpu); } } @@ -675,6 +922,21 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) csr_write(CSR_HVIP, csr->hvip); } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + guest_state_enter_irqoff(); + __kvm_riscv_switch_to(&vcpu->arch); + vcpu->arch.last_exit_cpu = vcpu->cpu; + guest_state_exit_irqoff(); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { int ret; @@ -684,28 +946,32 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Mark this VCPU ran at least once */ vcpu->arch.ran_atleast_once = true; - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); - /* Process MMIO value returned from user-space */ - if (run->exit_reason == KVM_EXIT_MMIO) { + switch (run->exit_reason) { + case KVM_EXIT_MMIO: + /* Process MMIO value returned from user-space */ ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); - if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - return ret; - } - } - - /* Process SBI value returned from user-space */ - if (run->exit_reason == KVM_EXIT_RISCV_SBI) { + break; + case KVM_EXIT_RISCV_SBI: + /* Process SBI value returned from user-space */ ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); - if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - return ret; - } + break; + case KVM_EXIT_RISCV_CSR: + /* Process CSR value returned from user-space */ + ret = kvm_riscv_vcpu_csr_return(vcpu, vcpu->run); + break; + default: + ret = 0; + break; + } + if (ret) { + kvm_vcpu_srcu_read_unlock(vcpu); + return ret; } if (run->immediate_exit) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return -EINTR; } @@ -717,26 +983,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) run->exit_reason = KVM_EXIT_UNKNOWN; while (ret > 0) { /* Check conditions before entering the guest */ - cond_resched(); + ret = xfer_to_guest_mode_handle_work(vcpu); + if (!ret) + ret = 1; - kvm_riscv_stage2_vmid_update(vcpu); + kvm_riscv_gstage_vmid_update(vcpu); kvm_riscv_check_vcpu_requests(vcpu); - preempt_disable(); - local_irq_disable(); /* - * Exit if we have a signal pending so that we can deliver - * the signal to user space. - */ - if (signal_pending(current)) { - ret = -EINTR; - run->exit_reason = KVM_EXIT_INTR; - } - - /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and @@ -744,7 +1001,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ vcpu->mode = IN_GUEST_MODE; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); smp_mb__after_srcu_read_unlock(); /* @@ -757,18 +1014,26 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_riscv_update_hvip(vcpu); if (ret <= 0 || - kvm_riscv_stage2_vmid_ver_changed(&vcpu->kvm->arch.vmid) || - kvm_request_pending(vcpu)) { + kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) || + kvm_request_pending(vcpu) || + xfer_to_guest_mode_work_pending()) { vcpu->mode = OUTSIDE_GUEST_MODE; local_irq_enable(); - preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); continue; } - guest_enter_irqoff(); + /* + * Cleanup stale TLB enteries + * + * Note: This should be done after G-stage VMID has been + * updated using kvm_riscv_gstage_vmid_ver_changed() + */ + kvm_riscv_local_tlb_sanitize(vcpu); + + guest_timing_enter_irqoff(); - __kvm_riscv_switch_to(&vcpu->arch); + kvm_riscv_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; @@ -787,30 +1052,28 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Syncup interrupts state with HW */ kvm_riscv_vcpu_sync_interrupts(vcpu); + preempt_disable(); + /* - * We may have taken a host interrupt in VS/VU-mode (i.e. - * while executing the guest). This interrupt is still - * pending, as we haven't serviced it yet! + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. * - * We're now back in HS-mode with interrupts disabled - * so enabling the interrupts now will have the effect - * of taking the interrupt again, in HS-mode this time. + * There's no barrier which ensures that pending interrupts are + * recognised, so we just hope that the CPU takes any pending + * interrupts between the enable and disable. */ local_irq_enable(); + local_irq_disable(); - /* - * We do local_irq_enable() before calling guest_exit() so - * that if a timer interrupt hits while running the guest - * we account that tick as being spent in the guest. We - * enable preemption after calling guest_exit() so that if - * we get preempted we make sure ticks after that is not - * counted as guest time. - */ - guest_exit(); + guest_timing_exit_irqoff(); + + local_irq_enable(); preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_riscv_vcpu_exit(vcpu, run, &trap); } @@ -819,7 +1082,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_put(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 7f2d742ae4c6..c9f741ab26f5 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -6,446 +6,41 @@ * Anup Patel <anup.patel@wdc.com> */ -#include <linux/bitops.h> -#include <linux/errno.h> -#include <linux/err.h> #include <linux/kvm_host.h> #include <asm/csr.h> +#include <asm/insn-def.h> -#define INSN_OPCODE_MASK 0x007c -#define INSN_OPCODE_SHIFT 2 -#define INSN_OPCODE_SYSTEM 28 - -#define INSN_MASK_WFI 0xffffffff -#define INSN_MATCH_WFI 0x10500073 - -#define INSN_MATCH_LB 0x3 -#define INSN_MASK_LB 0x707f -#define INSN_MATCH_LH 0x1003 -#define INSN_MASK_LH 0x707f -#define INSN_MATCH_LW 0x2003 -#define INSN_MASK_LW 0x707f -#define INSN_MATCH_LD 0x3003 -#define INSN_MASK_LD 0x707f -#define INSN_MATCH_LBU 0x4003 -#define INSN_MASK_LBU 0x707f -#define INSN_MATCH_LHU 0x5003 -#define INSN_MASK_LHU 0x707f -#define INSN_MATCH_LWU 0x6003 -#define INSN_MASK_LWU 0x707f -#define INSN_MATCH_SB 0x23 -#define INSN_MASK_SB 0x707f -#define INSN_MATCH_SH 0x1023 -#define INSN_MASK_SH 0x707f -#define INSN_MATCH_SW 0x2023 -#define INSN_MASK_SW 0x707f -#define INSN_MATCH_SD 0x3023 -#define INSN_MASK_SD 0x707f - -#define INSN_MATCH_C_LD 0x6000 -#define INSN_MASK_C_LD 0xe003 -#define INSN_MATCH_C_SD 0xe000 -#define INSN_MASK_C_SD 0xe003 -#define INSN_MATCH_C_LW 0x4000 -#define INSN_MASK_C_LW 0xe003 -#define INSN_MATCH_C_SW 0xc000 -#define INSN_MASK_C_SW 0xe003 -#define INSN_MATCH_C_LDSP 0x6002 -#define INSN_MASK_C_LDSP 0xe003 -#define INSN_MATCH_C_SDSP 0xe002 -#define INSN_MASK_C_SDSP 0xe003 -#define INSN_MATCH_C_LWSP 0x4002 -#define INSN_MASK_C_LWSP 0xe003 -#define INSN_MATCH_C_SWSP 0xc002 -#define INSN_MASK_C_SWSP 0xe003 - -#define INSN_16BIT_MASK 0x3 - -#define INSN_IS_16BIT(insn) (((insn) & INSN_16BIT_MASK) != INSN_16BIT_MASK) - -#define INSN_LEN(insn) (INSN_IS_16BIT(insn) ? 2 : 4) - -#ifdef CONFIG_64BIT -#define LOG_REGBYTES 3 -#else -#define LOG_REGBYTES 2 -#endif -#define REGBYTES (1 << LOG_REGBYTES) - -#define SH_RD 7 -#define SH_RS1 15 -#define SH_RS2 20 -#define SH_RS2C 2 - -#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) -#define RVC_LW_IMM(x) ((RV_X(x, 6, 1) << 2) | \ - (RV_X(x, 10, 3) << 3) | \ - (RV_X(x, 5, 1) << 6)) -#define RVC_LD_IMM(x) ((RV_X(x, 10, 3) << 3) | \ - (RV_X(x, 5, 2) << 6)) -#define RVC_LWSP_IMM(x) ((RV_X(x, 4, 3) << 2) | \ - (RV_X(x, 12, 1) << 5) | \ - (RV_X(x, 2, 2) << 6)) -#define RVC_LDSP_IMM(x) ((RV_X(x, 5, 2) << 3) | \ - (RV_X(x, 12, 1) << 5) | \ - (RV_X(x, 2, 3) << 6)) -#define RVC_SWSP_IMM(x) ((RV_X(x, 9, 4) << 2) | \ - (RV_X(x, 7, 2) << 6)) -#define RVC_SDSP_IMM(x) ((RV_X(x, 10, 3) << 3) | \ - (RV_X(x, 7, 3) << 6)) -#define RVC_RS1S(insn) (8 + RV_X(insn, SH_RD, 3)) -#define RVC_RS2S(insn) (8 + RV_X(insn, SH_RS2C, 3)) -#define RVC_RS2(insn) RV_X(insn, SH_RS2C, 5) - -#define SHIFT_RIGHT(x, y) \ - ((y) < 0 ? ((x) << -(y)) : ((x) >> (y))) - -#define REG_MASK \ - ((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES)) - -#define REG_OFFSET(insn, pos) \ - (SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK) - -#define REG_PTR(insn, pos, regs) \ - ((ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))) - -#define GET_RM(insn) (((insn) >> 12) & 7) - -#define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs)) -#define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs)) -#define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs)) -#define GET_RS2S(insn, regs) (*REG_PTR(RVC_RS2S(insn), 0, regs)) -#define GET_RS2C(insn, regs) (*REG_PTR(insn, SH_RS2C, regs)) -#define GET_SP(regs) (*REG_PTR(2, 0, regs)) -#define SET_RD(insn, regs, val) (*REG_PTR(insn, SH_RD, regs) = (val)) -#define IMM_I(insn) ((s32)(insn) >> 20) -#define IMM_S(insn) (((s32)(insn) >> 25 << 5) | \ - (s32)(((insn) >> 7) & 0x1f)) -#define MASK_FUNCT3 0x7000 - -static int truly_illegal_insn(struct kvm_vcpu *vcpu, - struct kvm_run *run, - ulong insn) -{ - struct kvm_cpu_trap utrap = { 0 }; - - /* Redirect trap to Guest VCPU */ - utrap.sepc = vcpu->arch.guest_context.sepc; - utrap.scause = EXC_INST_ILLEGAL; - utrap.stval = insn; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); - - return 1; -} - -static int system_opcode_insn(struct kvm_vcpu *vcpu, - struct kvm_run *run, - ulong insn) -{ - if ((insn & INSN_MASK_WFI) == INSN_MATCH_WFI) { - vcpu->stat.wfi_exit_stat++; - if (!kvm_arch_vcpu_runnable(vcpu)) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - kvm_vcpu_block(vcpu); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); - } - vcpu->arch.guest_context.sepc += INSN_LEN(insn); - return 1; - } - - return truly_illegal_insn(vcpu, run, insn); -} - -static int virtual_inst_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_cpu_trap *trap) -{ - unsigned long insn = trap->stval; - struct kvm_cpu_trap utrap = { 0 }; - struct kvm_cpu_context *ct; - - if (unlikely(INSN_IS_16BIT(insn))) { - if (insn == 0) { - ct = &vcpu->arch.guest_context; - insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, - ct->sepc, - &utrap); - if (utrap.scause) { - utrap.sepc = ct->sepc; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); - return 1; - } - } - if (INSN_IS_16BIT(insn)) - return truly_illegal_insn(vcpu, run, insn); - } - - switch ((insn & INSN_OPCODE_MASK) >> INSN_OPCODE_SHIFT) { - case INSN_OPCODE_SYSTEM: - return system_opcode_insn(vcpu, run, insn); - default: - return truly_illegal_insn(vcpu, run, insn); - } -} - -static int emulate_load(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long fault_addr, unsigned long htinst) -{ - u8 data_buf[8]; - unsigned long insn; - int shift = 0, len = 0, insn_len = 0; - struct kvm_cpu_trap utrap = { 0 }; - struct kvm_cpu_context *ct = &vcpu->arch.guest_context; - - /* Determine trapped instruction */ - if (htinst & 0x1) { - /* - * Bit[0] == 1 implies trapped instruction value is - * transformed instruction or custom instruction. - */ - insn = htinst | INSN_16BIT_MASK; - insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2; - } else { - /* - * Bit[0] == 0 implies trapped instruction value is - * zero or special value. - */ - insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, - &utrap); - if (utrap.scause) { - /* Redirect trap if we failed to read instruction */ - utrap.sepc = ct->sepc; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); - return 1; - } - insn_len = INSN_LEN(insn); - } - - /* Decode length of MMIO and shift */ - if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) { - len = 4; - shift = 8 * (sizeof(ulong) - len); - } else if ((insn & INSN_MASK_LB) == INSN_MATCH_LB) { - len = 1; - shift = 8 * (sizeof(ulong) - len); - } else if ((insn & INSN_MASK_LBU) == INSN_MATCH_LBU) { - len = 1; - shift = 8 * (sizeof(ulong) - len); -#ifdef CONFIG_64BIT - } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) { - len = 8; - shift = 8 * (sizeof(ulong) - len); - } else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) { - len = 4; -#endif - } else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) { - len = 2; - shift = 8 * (sizeof(ulong) - len); - } else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) { - len = 2; -#ifdef CONFIG_64BIT - } else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) { - len = 8; - shift = 8 * (sizeof(ulong) - len); - insn = RVC_RS2S(insn) << SH_RD; - } else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP && - ((insn >> SH_RD) & 0x1f)) { - len = 8; - shift = 8 * (sizeof(ulong) - len); -#endif - } else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) { - len = 4; - shift = 8 * (sizeof(ulong) - len); - insn = RVC_RS2S(insn) << SH_RD; - } else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP && - ((insn >> SH_RD) & 0x1f)) { - len = 4; - shift = 8 * (sizeof(ulong) - len); - } else { - return -EOPNOTSUPP; - } - - /* Fault address should be aligned to length of MMIO */ - if (fault_addr & (len - 1)) - return -EIO; - - /* Save instruction decode info */ - vcpu->arch.mmio_decode.insn = insn; - vcpu->arch.mmio_decode.insn_len = insn_len; - vcpu->arch.mmio_decode.shift = shift; - vcpu->arch.mmio_decode.len = len; - vcpu->arch.mmio_decode.return_handled = 0; - - /* Update MMIO details in kvm_run struct */ - run->mmio.is_write = false; - run->mmio.phys_addr = fault_addr; - run->mmio.len = len; - - /* Try to handle MMIO access in the kernel */ - if (!kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_addr, len, data_buf)) { - /* Successfully handled MMIO access in the kernel so resume */ - memcpy(run->mmio.data, data_buf, len); - vcpu->stat.mmio_exit_kernel++; - kvm_riscv_vcpu_mmio_return(vcpu, run); - return 1; - } - - /* Exit to userspace for MMIO emulation */ - vcpu->stat.mmio_exit_user++; - run->exit_reason = KVM_EXIT_MMIO; - - return 0; -} - -static int emulate_store(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long fault_addr, unsigned long htinst) -{ - u8 data8; - u16 data16; - u32 data32; - u64 data64; - ulong data; - unsigned long insn; - int len = 0, insn_len = 0; - struct kvm_cpu_trap utrap = { 0 }; - struct kvm_cpu_context *ct = &vcpu->arch.guest_context; - - /* Determine trapped instruction */ - if (htinst & 0x1) { - /* - * Bit[0] == 1 implies trapped instruction value is - * transformed instruction or custom instruction. - */ - insn = htinst | INSN_16BIT_MASK; - insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2; - } else { - /* - * Bit[0] == 0 implies trapped instruction value is - * zero or special value. - */ - insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, - &utrap); - if (utrap.scause) { - /* Redirect trap if we failed to read instruction */ - utrap.sepc = ct->sepc; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); - return 1; - } - insn_len = INSN_LEN(insn); - } - - data = GET_RS2(insn, &vcpu->arch.guest_context); - data8 = data16 = data32 = data64 = data; - - if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) { - len = 4; - } else if ((insn & INSN_MASK_SB) == INSN_MATCH_SB) { - len = 1; -#ifdef CONFIG_64BIT - } else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) { - len = 8; -#endif - } else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) { - len = 2; -#ifdef CONFIG_64BIT - } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { - len = 8; - data64 = GET_RS2S(insn, &vcpu->arch.guest_context); - } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP && - ((insn >> SH_RD) & 0x1f)) { - len = 8; - data64 = GET_RS2C(insn, &vcpu->arch.guest_context); -#endif - } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { - len = 4; - data32 = GET_RS2S(insn, &vcpu->arch.guest_context); - } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP && - ((insn >> SH_RD) & 0x1f)) { - len = 4; - data32 = GET_RS2C(insn, &vcpu->arch.guest_context); - } else { - return -EOPNOTSUPP; - } - - /* Fault address should be aligned to length of MMIO */ - if (fault_addr & (len - 1)) - return -EIO; - - /* Save instruction decode info */ - vcpu->arch.mmio_decode.insn = insn; - vcpu->arch.mmio_decode.insn_len = insn_len; - vcpu->arch.mmio_decode.shift = 0; - vcpu->arch.mmio_decode.len = len; - vcpu->arch.mmio_decode.return_handled = 0; - - /* Copy data to kvm_run instance */ - switch (len) { - case 1: - *((u8 *)run->mmio.data) = data8; - break; - case 2: - *((u16 *)run->mmio.data) = data16; - break; - case 4: - *((u32 *)run->mmio.data) = data32; - break; - case 8: - *((u64 *)run->mmio.data) = data64; - break; - default: - return -EOPNOTSUPP; - } - - /* Update MMIO details in kvm_run struct */ - run->mmio.is_write = true; - run->mmio.phys_addr = fault_addr; - run->mmio.len = len; - - /* Try to handle MMIO access in the kernel */ - if (!kvm_io_bus_write(vcpu, KVM_MMIO_BUS, - fault_addr, len, run->mmio.data)) { - /* Successfully handled MMIO access in the kernel so resume */ - vcpu->stat.mmio_exit_kernel++; - kvm_riscv_vcpu_mmio_return(vcpu, run); - return 1; - } - - /* Exit to userspace for MMIO emulation */ - vcpu->stat.mmio_exit_user++; - run->exit_reason = KVM_EXIT_MMIO; - - return 0; -} - -static int stage2_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, +static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_cpu_trap *trap) { struct kvm_memory_slot *memslot; unsigned long hva, fault_addr; - bool writeable; + bool writable; gfn_t gfn; int ret; fault_addr = (trap->htval << 2) | (trap->stval & 0x3); gfn = fault_addr >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); - hva = gfn_to_hva_memslot_prot(memslot, gfn, &writeable); + hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); if (kvm_is_error_hva(hva) || - (trap->scause == EXC_STORE_GUEST_PAGE_FAULT && !writeable)) { + (trap->scause == EXC_STORE_GUEST_PAGE_FAULT && !writable)) { switch (trap->scause) { case EXC_LOAD_GUEST_PAGE_FAULT: - return emulate_load(vcpu, run, fault_addr, - trap->htinst); + return kvm_riscv_vcpu_mmio_load(vcpu, run, + fault_addr, + trap->htinst); case EXC_STORE_GUEST_PAGE_FAULT: - return emulate_store(vcpu, run, fault_addr, - trap->htinst); + return kvm_riscv_vcpu_mmio_store(vcpu, run, + fault_addr, + trap->htinst); default: return -EOPNOTSUPP; }; } - ret = kvm_riscv_stage2_map(vcpu, memslot, fault_addr, hva, + ret = kvm_riscv_gstage_map(vcpu, memslot, fault_addr, hva, (trap->scause == EXC_STORE_GUEST_PAGE_FAULT) ? true : false); if (ret < 0) return ret; @@ -468,11 +63,7 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu, { register unsigned long taddr asm("a0") = (unsigned long)trap; register unsigned long ttmp asm("a1"); - register unsigned long val asm("t0"); - register unsigned long tmp asm("t1"); - register unsigned long addr asm("t2") = guest_addr; - unsigned long flags; - unsigned long old_stvec, old_hstatus; + unsigned long flags, val, tmp, old_stvec, old_hstatus; local_irq_save(flags); @@ -488,29 +79,19 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu, ".option push\n" ".option norvc\n" "add %[ttmp], %[taddr], 0\n" - /* - * HLVX.HU %[val], (%[addr]) - * HLVX.HU t0, (t2) - * 0110010 00011 00111 100 00101 1110011 - */ - ".word 0x6433c2f3\n" + HLVX_HU(%[val], %[addr]) "andi %[tmp], %[val], 3\n" "addi %[tmp], %[tmp], -3\n" "bne %[tmp], zero, 2f\n" "addi %[addr], %[addr], 2\n" - /* - * HLVX.HU %[tmp], (%[addr]) - * HLVX.HU t1, (t2) - * 0110010 00011 00111 100 00110 1110011 - */ - ".word 0x6433c373\n" + HLVX_HU(%[tmp], %[addr]) "sll %[tmp], %[tmp], 16\n" "add %[val], %[val], %[tmp]\n" "2:\n" ".option pop" : [val] "=&r" (val), [tmp] "=&r" (tmp), [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp), - [addr] "+&r" (addr) : : "memory"); + [addr] "+&r" (guest_addr) : : "memory"); if (trap->scause == EXC_LOAD_PAGE_FAULT) trap->scause = EXC_INST_PAGE_FAULT; @@ -527,24 +108,14 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu, ".option norvc\n" "add %[ttmp], %[taddr], 0\n" #ifdef CONFIG_64BIT - /* - * HLV.D %[val], (%[addr]) - * HLV.D t0, (t2) - * 0110110 00000 00111 100 00101 1110011 - */ - ".word 0x6c03c2f3\n" + HLV_D(%[val], %[addr]) #else - /* - * HLV.W %[val], (%[addr]) - * HLV.W t0, (t2) - * 0110100 00000 00111 100 00101 1110011 - */ - ".word 0x6803c2f3\n" + HLV_W(%[val], %[addr]) #endif ".option pop" : [val] "=&r" (val), [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp) - : [addr] "r" (addr) : "memory"); + : [addr] "r" (guest_addr) : "memory"); } csr_write(CSR_STVEC, old_stvec); @@ -591,66 +162,6 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, vcpu->arch.guest_context.sepc = csr_read(CSR_VSTVEC); } -/** - * kvm_riscv_vcpu_mmio_return -- Handle MMIO loads after user space emulation - * or in-kernel IO emulation - * - * @vcpu: The VCPU pointer - * @run: The VCPU run struct containing the mmio data - */ -int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - u8 data8; - u16 data16; - u32 data32; - u64 data64; - ulong insn; - int len, shift; - - if (vcpu->arch.mmio_decode.return_handled) - return 0; - - vcpu->arch.mmio_decode.return_handled = 1; - insn = vcpu->arch.mmio_decode.insn; - - if (run->mmio.is_write) - goto done; - - len = vcpu->arch.mmio_decode.len; - shift = vcpu->arch.mmio_decode.shift; - - switch (len) { - case 1: - data8 = *((u8 *)run->mmio.data); - SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data8 << shift >> shift); - break; - case 2: - data16 = *((u16 *)run->mmio.data); - SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data16 << shift >> shift); - break; - case 4: - data32 = *((u32 *)run->mmio.data); - SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data32 << shift >> shift); - break; - case 8: - data64 = *((u64 *)run->mmio.data); - SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data64 << shift >> shift); - break; - default: - return -EOPNOTSUPP; - } - -done: - /* Move to next instruction */ - vcpu->arch.guest_context.sepc += vcpu->arch.mmio_decode.insn_len; - - return 0; -} - /* * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on * proper exit to userspace. @@ -670,13 +181,13 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, switch (trap->scause) { case EXC_VIRTUAL_INST_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) - ret = virtual_inst_fault(vcpu, run, trap); + ret = kvm_riscv_vcpu_virtual_insn(vcpu, run, trap); break; case EXC_INST_GUEST_PAGE_FAULT: case EXC_LOAD_GUEST_PAGE_FAULT: case EXC_STORE_GUEST_PAGE_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) - ret = stage2_page_fault(vcpu, run, trap); + ret = gstage_page_fault(vcpu, run, trap); break; case EXC_SUPERVISOR_SYSCALL: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 1b070152578f..9d8cbc42057a 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -11,46 +11,46 @@ #include <linux/err.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> +#include <asm/hwcap.h> #ifdef CONFIG_FPU void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) { - unsigned long isa = vcpu->arch.isa; struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; cntx->sstatus &= ~SR_FS; - if (riscv_isa_extension_available(&isa, f) || - riscv_isa_extension_available(&isa, d)) + if (riscv_isa_extension_available(vcpu->arch.isa, f) || + riscv_isa_extension_available(vcpu->arch.isa, d)) cntx->sstatus |= SR_FS_INITIAL; else 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; } void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx, - unsigned long isa) + const unsigned long *isa) { if ((cntx->sstatus & SR_FS) == SR_FS_DIRTY) { - if (riscv_isa_extension_available(&isa, d)) + if (riscv_isa_extension_available(isa, d)) __kvm_riscv_fp_d_save(cntx); - else if (riscv_isa_extension_available(&isa, f)) + else if (riscv_isa_extension_available(isa, f)) __kvm_riscv_fp_f_save(cntx); kvm_riscv_vcpu_fp_clean(cntx); } } void kvm_riscv_vcpu_guest_fp_restore(struct kvm_cpu_context *cntx, - unsigned long isa) + const unsigned long *isa) { if ((cntx->sstatus & SR_FS) != SR_FS_OFF) { - if (riscv_isa_extension_available(&isa, d)) + if (riscv_isa_extension_available(isa, d)) __kvm_riscv_fp_d_restore(cntx); - else if (riscv_isa_extension_available(&isa, f)) + else if (riscv_isa_extension_available(isa, f)) __kvm_riscv_fp_f_restore(cntx); kvm_riscv_vcpu_fp_clean(cntx); } @@ -79,7 +79,6 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, unsigned long rtype) { struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; - unsigned long isa = vcpu->arch.isa; unsigned long __user *uaddr = (unsigned long __user *)(unsigned long)reg->addr; unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | @@ -88,7 +87,7 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, void *reg_val; if ((rtype == KVM_REG_RISCV_FP_F) && - riscv_isa_extension_available(&isa, f)) { + riscv_isa_extension_available(vcpu->arch.isa, f)) { if (KVM_REG_SIZE(reg->id) != sizeof(u32)) return -EINVAL; if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) @@ -99,7 +98,7 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, else return -EINVAL; } else if ((rtype == KVM_REG_RISCV_FP_D) && - riscv_isa_extension_available(&isa, d)) { + riscv_isa_extension_available(vcpu->arch.isa, d)) { if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) { if (KVM_REG_SIZE(reg->id) != sizeof(u32)) return -EINVAL; @@ -125,7 +124,6 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, unsigned long rtype) { struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; - unsigned long isa = vcpu->arch.isa; unsigned long __user *uaddr = (unsigned long __user *)(unsigned long)reg->addr; unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | @@ -134,7 +132,7 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, void *reg_val; if ((rtype == KVM_REG_RISCV_FP_F) && - riscv_isa_extension_available(&isa, f)) { + riscv_isa_extension_available(vcpu->arch.isa, f)) { if (KVM_REG_SIZE(reg->id) != sizeof(u32)) return -EINVAL; if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) @@ -145,7 +143,7 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, else return -EINVAL; } else if ((rtype == KVM_REG_RISCV_FP_D) && - riscv_isa_extension_available(&isa, d)) { + riscv_isa_extension_available(vcpu->arch.isa, d)) { if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) { if (KVM_REG_SIZE(reg->id) != sizeof(u32)) return -EINVAL; diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c new file mode 100644 index 000000000000..0bb52761a3f7 --- /dev/null +++ b/arch/riscv/kvm/vcpu_insn.c @@ -0,0 +1,751 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include <linux/bitops.h> +#include <linux/kvm_host.h> + +#define INSN_OPCODE_MASK 0x007c +#define INSN_OPCODE_SHIFT 2 +#define INSN_OPCODE_SYSTEM 28 + +#define INSN_MASK_WFI 0xffffffff +#define INSN_MATCH_WFI 0x10500073 + +#define INSN_MATCH_CSRRW 0x1073 +#define INSN_MASK_CSRRW 0x707f +#define INSN_MATCH_CSRRS 0x2073 +#define INSN_MASK_CSRRS 0x707f +#define INSN_MATCH_CSRRC 0x3073 +#define INSN_MASK_CSRRC 0x707f +#define INSN_MATCH_CSRRWI 0x5073 +#define INSN_MASK_CSRRWI 0x707f +#define INSN_MATCH_CSRRSI 0x6073 +#define INSN_MASK_CSRRSI 0x707f +#define INSN_MATCH_CSRRCI 0x7073 +#define INSN_MASK_CSRRCI 0x707f + +#define INSN_MATCH_LB 0x3 +#define INSN_MASK_LB 0x707f +#define INSN_MATCH_LH 0x1003 +#define INSN_MASK_LH 0x707f +#define INSN_MATCH_LW 0x2003 +#define INSN_MASK_LW 0x707f +#define INSN_MATCH_LD 0x3003 +#define INSN_MASK_LD 0x707f +#define INSN_MATCH_LBU 0x4003 +#define INSN_MASK_LBU 0x707f +#define INSN_MATCH_LHU 0x5003 +#define INSN_MASK_LHU 0x707f +#define INSN_MATCH_LWU 0x6003 +#define INSN_MASK_LWU 0x707f +#define INSN_MATCH_SB 0x23 +#define INSN_MASK_SB 0x707f +#define INSN_MATCH_SH 0x1023 +#define INSN_MASK_SH 0x707f +#define INSN_MATCH_SW 0x2023 +#define INSN_MASK_SW 0x707f +#define INSN_MATCH_SD 0x3023 +#define INSN_MASK_SD 0x707f + +#define INSN_MATCH_C_LD 0x6000 +#define INSN_MASK_C_LD 0xe003 +#define INSN_MATCH_C_SD 0xe000 +#define INSN_MASK_C_SD 0xe003 +#define INSN_MATCH_C_LW 0x4000 +#define INSN_MASK_C_LW 0xe003 +#define INSN_MATCH_C_SW 0xc000 +#define INSN_MASK_C_SW 0xe003 +#define INSN_MATCH_C_LDSP 0x6002 +#define INSN_MASK_C_LDSP 0xe003 +#define INSN_MATCH_C_SDSP 0xe002 +#define INSN_MASK_C_SDSP 0xe003 +#define INSN_MATCH_C_LWSP 0x4002 +#define INSN_MASK_C_LWSP 0xe003 +#define INSN_MATCH_C_SWSP 0xc002 +#define INSN_MASK_C_SWSP 0xe003 + +#define INSN_16BIT_MASK 0x3 + +#define INSN_IS_16BIT(insn) (((insn) & INSN_16BIT_MASK) != INSN_16BIT_MASK) + +#define INSN_LEN(insn) (INSN_IS_16BIT(insn) ? 2 : 4) + +#ifdef CONFIG_64BIT +#define LOG_REGBYTES 3 +#else +#define LOG_REGBYTES 2 +#endif +#define REGBYTES (1 << LOG_REGBYTES) + +#define SH_RD 7 +#define SH_RS1 15 +#define SH_RS2 20 +#define SH_RS2C 2 +#define MASK_RX 0x1f + +#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) +#define RVC_LW_IMM(x) ((RV_X(x, 6, 1) << 2) | \ + (RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 5, 1) << 6)) +#define RVC_LD_IMM(x) ((RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 5, 2) << 6)) +#define RVC_LWSP_IMM(x) ((RV_X(x, 4, 3) << 2) | \ + (RV_X(x, 12, 1) << 5) | \ + (RV_X(x, 2, 2) << 6)) +#define RVC_LDSP_IMM(x) ((RV_X(x, 5, 2) << 3) | \ + (RV_X(x, 12, 1) << 5) | \ + (RV_X(x, 2, 3) << 6)) +#define RVC_SWSP_IMM(x) ((RV_X(x, 9, 4) << 2) | \ + (RV_X(x, 7, 2) << 6)) +#define RVC_SDSP_IMM(x) ((RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 7, 3) << 6)) +#define RVC_RS1S(insn) (8 + RV_X(insn, SH_RD, 3)) +#define RVC_RS2S(insn) (8 + RV_X(insn, SH_RS2C, 3)) +#define RVC_RS2(insn) RV_X(insn, SH_RS2C, 5) + +#define SHIFT_RIGHT(x, y) \ + ((y) < 0 ? ((x) << -(y)) : ((x) >> (y))) + +#define REG_MASK \ + ((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES)) + +#define REG_OFFSET(insn, pos) \ + (SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK) + +#define REG_PTR(insn, pos, regs) \ + ((ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))) + +#define GET_FUNCT3(insn) (((insn) >> 12) & 7) + +#define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs)) +#define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs)) +#define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs)) +#define GET_RS2S(insn, regs) (*REG_PTR(RVC_RS2S(insn), 0, regs)) +#define GET_RS2C(insn, regs) (*REG_PTR(insn, SH_RS2C, regs)) +#define GET_SP(regs) (*REG_PTR(2, 0, regs)) +#define SET_RD(insn, regs, val) (*REG_PTR(insn, SH_RD, regs) = (val)) +#define IMM_I(insn) ((s32)(insn) >> 20) +#define IMM_S(insn) (((s32)(insn) >> 25 << 5) | \ + (s32)(((insn) >> 7) & 0x1f)) + +struct insn_func { + unsigned long mask; + unsigned long match; + /* + * Possible return values are as follows: + * 1) Returns < 0 for error case + * 2) Returns 0 for exit to user-space + * 3) Returns 1 to continue with next sepc + * 4) Returns 2 to continue with same sepc + * 5) Returns 3 to inject illegal instruction trap and continue + * 6) Returns 4 to inject virtual instruction trap and continue + * + * Use enum kvm_insn_return for return values + */ + int (*func)(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn); +}; + +static int truly_illegal_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + ulong insn) +{ + struct kvm_cpu_trap utrap = { 0 }; + + /* Redirect trap to Guest VCPU */ + utrap.sepc = vcpu->arch.guest_context.sepc; + utrap.scause = EXC_INST_ILLEGAL; + utrap.stval = insn; + utrap.htval = 0; + utrap.htinst = 0; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + + return 1; +} + +static int truly_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + ulong insn) +{ + struct kvm_cpu_trap utrap = { 0 }; + + /* Redirect trap to Guest VCPU */ + utrap.sepc = vcpu->arch.guest_context.sepc; + utrap.scause = EXC_VIRTUAL_INST_FAULT; + utrap.stval = insn; + utrap.htval = 0; + utrap.htinst = 0; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + + return 1; +} + +/** + * kvm_riscv_vcpu_wfi -- Emulate wait for interrupt (WFI) behaviour + * + * @vcpu: The VCPU pointer + */ +void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) +{ + if (!kvm_arch_vcpu_runnable(vcpu)) { + kvm_vcpu_srcu_read_unlock(vcpu); + kvm_vcpu_halt(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + } +} + +static int wfi_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) +{ + vcpu->stat.wfi_exit_stat++; + kvm_riscv_vcpu_wfi(vcpu); + return KVM_INSN_CONTINUE_NEXT_SEPC; +} + +struct csr_func { + unsigned int base; + unsigned int count; + /* + * Possible return values are as same as "func" callback in + * "struct insn_func". + */ + int (*func)(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); +}; + +static const struct csr_func csr_funcs[] = { }; + +/** + * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space + * emulation or in-kernel emulation + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the CSR data + * + * Returns > 0 upon failure and 0 upon success + */ +int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + ulong insn; + + if (vcpu->arch.csr_decode.return_handled) + return 0; + vcpu->arch.csr_decode.return_handled = 1; + + /* Update destination register for CSR reads */ + insn = vcpu->arch.csr_decode.insn; + if ((insn >> SH_RD) & MASK_RX) + SET_RD(insn, &vcpu->arch.guest_context, + run->riscv_csr.ret_value); + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += INSN_LEN(insn); + + return 0; +} + +static int csr_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) +{ + int i, rc = KVM_INSN_ILLEGAL_TRAP; + unsigned int csr_num = insn >> SH_RS2; + unsigned int rs1_num = (insn >> SH_RS1) & MASK_RX; + ulong rs1_val = GET_RS1(insn, &vcpu->arch.guest_context); + const struct csr_func *tcfn, *cfn = NULL; + ulong val = 0, wr_mask = 0, new_val = 0; + + /* Decode the CSR instruction */ + switch (GET_FUNCT3(insn)) { + case GET_FUNCT3(INSN_MATCH_CSRRW): + wr_mask = -1UL; + new_val = rs1_val; + break; + case GET_FUNCT3(INSN_MATCH_CSRRS): + wr_mask = rs1_val; + new_val = -1UL; + break; + case GET_FUNCT3(INSN_MATCH_CSRRC): + wr_mask = rs1_val; + new_val = 0; + break; + case GET_FUNCT3(INSN_MATCH_CSRRWI): + wr_mask = -1UL; + new_val = rs1_num; + break; + case GET_FUNCT3(INSN_MATCH_CSRRSI): + wr_mask = rs1_num; + new_val = -1UL; + break; + case GET_FUNCT3(INSN_MATCH_CSRRCI): + wr_mask = rs1_num; + new_val = 0; + break; + default: + return rc; + } + + /* Save instruction decode info */ + vcpu->arch.csr_decode.insn = insn; + vcpu->arch.csr_decode.return_handled = 0; + + /* Update CSR details in kvm_run struct */ + run->riscv_csr.csr_num = csr_num; + run->riscv_csr.new_value = new_val; + run->riscv_csr.write_mask = wr_mask; + run->riscv_csr.ret_value = 0; + + /* Find in-kernel CSR function */ + for (i = 0; i < ARRAY_SIZE(csr_funcs); i++) { + tcfn = &csr_funcs[i]; + if ((tcfn->base <= csr_num) && + (csr_num < (tcfn->base + tcfn->count))) { + cfn = tcfn; + break; + } + } + + /* First try in-kernel CSR emulation */ + if (cfn && cfn->func) { + rc = cfn->func(vcpu, csr_num, &val, new_val, wr_mask); + if (rc > KVM_INSN_EXIT_TO_USER_SPACE) { + if (rc == KVM_INSN_CONTINUE_NEXT_SEPC) { + run->riscv_csr.ret_value = val; + vcpu->stat.csr_exit_kernel++; + kvm_riscv_vcpu_csr_return(vcpu, run); + rc = KVM_INSN_CONTINUE_SAME_SEPC; + } + return rc; + } + } + + /* Exit to user-space for CSR emulation */ + if (rc <= KVM_INSN_EXIT_TO_USER_SPACE) { + vcpu->stat.csr_exit_user++; + run->exit_reason = KVM_EXIT_RISCV_CSR; + } + + return rc; +} + +static const struct insn_func system_opcode_funcs[] = { + { + .mask = INSN_MASK_CSRRW, + .match = INSN_MATCH_CSRRW, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRS, + .match = INSN_MATCH_CSRRS, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRC, + .match = INSN_MATCH_CSRRC, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRWI, + .match = INSN_MATCH_CSRRWI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRSI, + .match = INSN_MATCH_CSRRSI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRCI, + .match = INSN_MATCH_CSRRCI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_WFI, + .match = INSN_MATCH_WFI, + .func = wfi_insn, + }, +}; + +static int system_opcode_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + ulong insn) +{ + int i, rc = KVM_INSN_ILLEGAL_TRAP; + const struct insn_func *ifn; + + for (i = 0; i < ARRAY_SIZE(system_opcode_funcs); i++) { + ifn = &system_opcode_funcs[i]; + if ((insn & ifn->mask) == ifn->match) { + rc = ifn->func(vcpu, run, insn); + break; + } + } + + switch (rc) { + case KVM_INSN_ILLEGAL_TRAP: + return truly_illegal_insn(vcpu, run, insn); + case KVM_INSN_VIRTUAL_TRAP: + return truly_virtual_insn(vcpu, run, insn); + case KVM_INSN_CONTINUE_NEXT_SEPC: + vcpu->arch.guest_context.sepc += INSN_LEN(insn); + break; + default: + break; + } + + return (rc <= 0) ? rc : 1; +} + +/** + * kvm_riscv_vcpu_virtual_insn -- Handle virtual instruction trap + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * @trap: Trap details + * + * Returns > 0 to continue run-loop + * Returns 0 to exit run-loop and handle in user-space. + * Returns < 0 to report failure and exit run-loop + */ +int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_cpu_trap *trap) +{ + unsigned long insn = trap->stval; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *ct; + + if (unlikely(INSN_IS_16BIT(insn))) { + if (insn == 0) { + ct = &vcpu->arch.guest_context; + insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, + ct->sepc, + &utrap); + if (utrap.scause) { + utrap.sepc = ct->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + return 1; + } + } + if (INSN_IS_16BIT(insn)) + return truly_illegal_insn(vcpu, run, insn); + } + + switch ((insn & INSN_OPCODE_MASK) >> INSN_OPCODE_SHIFT) { + case INSN_OPCODE_SYSTEM: + return system_opcode_insn(vcpu, run, insn); + default: + return truly_illegal_insn(vcpu, run, insn); + } +} + +/** + * kvm_riscv_vcpu_mmio_load -- Emulate MMIO load instruction + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * @fault_addr: Guest physical address to load + * @htinst: Transformed encoding of the load instruction + * + * Returns > 0 to continue run-loop + * Returns 0 to exit run-loop and handle in user-space. + * Returns < 0 to report failure and exit run-loop + */ +int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long fault_addr, + unsigned long htinst) +{ + u8 data_buf[8]; + unsigned long insn; + int shift = 0, len = 0, insn_len = 0; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *ct = &vcpu->arch.guest_context; + + /* Determine trapped instruction */ + if (htinst & 0x1) { + /* + * Bit[0] == 1 implies trapped instruction value is + * transformed instruction or custom instruction. + */ + insn = htinst | INSN_16BIT_MASK; + insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2; + } else { + /* + * Bit[0] == 0 implies trapped instruction value is + * zero or special value. + */ + insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, + &utrap); + if (utrap.scause) { + /* Redirect trap if we failed to read instruction */ + utrap.sepc = ct->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + return 1; + } + insn_len = INSN_LEN(insn); + } + + /* Decode length of MMIO and shift */ + if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) { + len = 4; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LB) == INSN_MATCH_LB) { + len = 1; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LBU) == INSN_MATCH_LBU) { + len = 1; + shift = 8 * (sizeof(ulong) - len); +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) { + len = 8; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) { + len = 4; +#endif + } else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) { + len = 2; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) { + len = 2; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) { + len = 8; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP && + ((insn >> SH_RD) & 0x1f)) { + len = 8; + shift = 8 * (sizeof(ulong) - len); +#endif + } else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) { + len = 4; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP && + ((insn >> SH_RD) & 0x1f)) { + len = 4; + shift = 8 * (sizeof(ulong) - len); + } else { + return -EOPNOTSUPP; + } + + /* Fault address should be aligned to length of MMIO */ + if (fault_addr & (len - 1)) + return -EIO; + + /* Save instruction decode info */ + vcpu->arch.mmio_decode.insn = insn; + vcpu->arch.mmio_decode.insn_len = insn_len; + vcpu->arch.mmio_decode.shift = shift; + vcpu->arch.mmio_decode.len = len; + vcpu->arch.mmio_decode.return_handled = 0; + + /* Update MMIO details in kvm_run struct */ + run->mmio.is_write = false; + run->mmio.phys_addr = fault_addr; + run->mmio.len = len; + + /* Try to handle MMIO access in the kernel */ + if (!kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_addr, len, data_buf)) { + /* Successfully handled MMIO access in the kernel so resume */ + memcpy(run->mmio.data, data_buf, len); + vcpu->stat.mmio_exit_kernel++; + kvm_riscv_vcpu_mmio_return(vcpu, run); + return 1; + } + + /* Exit to userspace for MMIO emulation */ + vcpu->stat.mmio_exit_user++; + run->exit_reason = KVM_EXIT_MMIO; + + return 0; +} + +/** + * kvm_riscv_vcpu_mmio_store -- Emulate MMIO store instruction + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * @fault_addr: Guest physical address to store + * @htinst: Transformed encoding of the store instruction + * + * Returns > 0 to continue run-loop + * Returns 0 to exit run-loop and handle in user-space. + * Returns < 0 to report failure and exit run-loop + */ +int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long fault_addr, + unsigned long htinst) +{ + u8 data8; + u16 data16; + u32 data32; + u64 data64; + ulong data; + unsigned long insn; + int len = 0, insn_len = 0; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *ct = &vcpu->arch.guest_context; + + /* Determine trapped instruction */ + if (htinst & 0x1) { + /* + * Bit[0] == 1 implies trapped instruction value is + * transformed instruction or custom instruction. + */ + insn = htinst | INSN_16BIT_MASK; + insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2; + } else { + /* + * Bit[0] == 0 implies trapped instruction value is + * zero or special value. + */ + insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, + &utrap); + if (utrap.scause) { + /* Redirect trap if we failed to read instruction */ + utrap.sepc = ct->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + return 1; + } + insn_len = INSN_LEN(insn); + } + + data = GET_RS2(insn, &vcpu->arch.guest_context); + data8 = data16 = data32 = data64 = data; + + if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) { + len = 4; + } else if ((insn & INSN_MASK_SB) == INSN_MATCH_SB) { + len = 1; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) { + len = 8; +#endif + } else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) { + len = 2; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { + len = 8; + data64 = GET_RS2S(insn, &vcpu->arch.guest_context); + } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP && + ((insn >> SH_RD) & 0x1f)) { + len = 8; + data64 = GET_RS2C(insn, &vcpu->arch.guest_context); +#endif + } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { + len = 4; + data32 = GET_RS2S(insn, &vcpu->arch.guest_context); + } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP && + ((insn >> SH_RD) & 0x1f)) { + len = 4; + data32 = GET_RS2C(insn, &vcpu->arch.guest_context); + } else { + return -EOPNOTSUPP; + } + + /* Fault address should be aligned to length of MMIO */ + if (fault_addr & (len - 1)) + return -EIO; + + /* Save instruction decode info */ + vcpu->arch.mmio_decode.insn = insn; + vcpu->arch.mmio_decode.insn_len = insn_len; + vcpu->arch.mmio_decode.shift = 0; + vcpu->arch.mmio_decode.len = len; + vcpu->arch.mmio_decode.return_handled = 0; + + /* Copy data to kvm_run instance */ + switch (len) { + case 1: + *((u8 *)run->mmio.data) = data8; + break; + case 2: + *((u16 *)run->mmio.data) = data16; + break; + case 4: + *((u32 *)run->mmio.data) = data32; + break; + case 8: + *((u64 *)run->mmio.data) = data64; + break; + default: + return -EOPNOTSUPP; + } + + /* Update MMIO details in kvm_run struct */ + run->mmio.is_write = true; + run->mmio.phys_addr = fault_addr; + run->mmio.len = len; + + /* Try to handle MMIO access in the kernel */ + if (!kvm_io_bus_write(vcpu, KVM_MMIO_BUS, + fault_addr, len, run->mmio.data)) { + /* Successfully handled MMIO access in the kernel so resume */ + vcpu->stat.mmio_exit_kernel++; + kvm_riscv_vcpu_mmio_return(vcpu, run); + return 1; + } + + /* Exit to userspace for MMIO emulation */ + vcpu->stat.mmio_exit_user++; + run->exit_reason = KVM_EXIT_MMIO; + + return 0; +} + +/** + * kvm_riscv_vcpu_mmio_return -- Handle MMIO loads after user space emulation + * or in-kernel IO emulation + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + */ +int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + u8 data8; + u16 data16; + u32 data32; + u64 data64; + ulong insn; + int len, shift; + + if (vcpu->arch.mmio_decode.return_handled) + return 0; + + vcpu->arch.mmio_decode.return_handled = 1; + insn = vcpu->arch.mmio_decode.insn; + + if (run->mmio.is_write) + goto done; + + len = vcpu->arch.mmio_decode.len; + shift = vcpu->arch.mmio_decode.shift; + + switch (len) { + case 1: + data8 = *((u8 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (ulong)data8 << shift >> shift); + break; + case 2: + data16 = *((u16 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (ulong)data16 << shift >> shift); + break; + case 4: + data32 = *((u32 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (ulong)data32 << shift >> shift); + break; + case 8: + data64 = *((u64 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (ulong)data64 << shift >> shift); + break; + default: + return -EOPNOTSUPP; + } + +done: + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += vcpu->arch.mmio_decode.insn_len; + + return 0; +} diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 3b0e703d22cf..f96991d230bf 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -9,15 +9,50 @@ #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> +#include <asm/kvm_vcpu_sbi.h> -#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; + case -EALREADY: + return SBI_ERR_ALREADY_AVAILABLE; + default: + return SBI_ERR_FAILURE; + }; +} -static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, - struct kvm_run *run) +#ifndef CONFIG_RISCV_SBI_V01 +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, + &vcpu_sbi_ext_base, + &vcpu_sbi_ext_time, + &vcpu_sbi_ext_ipi, + &vcpu_sbi_ext_rfence, + &vcpu_sbi_ext_srst, + &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) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -36,6 +71,24 @@ static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, run->riscv_sbi.ret[1] = cp->a1; } +void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, + struct kvm_run *run, + u32 type, u64 reason) +{ + 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->system_event.ndata = 1; + run->system_event.data[0] = reason; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -55,131 +108,73 @@ 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) +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid) { - int i; - struct kvm_vcpu *tmp; + int i = 0; - kvm_for_each_vcpu(i, tmp, vcpu->kvm) - tmp->arch.power_off = true; - kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); + 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]; + } - memset(&run->system_event, 0, sizeof(run->system_event)); - run->system_event.type = type; - run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + return NULL; } 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; + int ret = 1; bool next_sepc = true; - struct cpumask cm, hm; - struct kvm *kvm = vcpu->kvm; - struct kvm_cpu_trap utrap = { 0 }; + 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; - 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; + 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 - 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: + 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; } - -#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_base.c b/arch/riscv/kvm/vcpu_sbi_base.c new file mode 100644 index 000000000000..48f431091cdb --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 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 <linux/version.h> +#include <asm/csr.h> +#include <asm/sbi.h> +#include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_sbi.h> + +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 = LINUX_VERSION_CODE; + 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, +}; + +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, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c new file mode 100644 index 000000000000..239dec0a628a --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 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_sbi.h> + +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_STATE_STARTED; + else if (vcpu->stat.generic.blocking) + return SBI_HSM_STATE_SUSPENDED; + else + return SBI_HSM_STATE_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; + case SBI_EXT_HSM_HART_SUSPEND: + switch (cp->a0) { + case SBI_HSM_SUSPEND_RET_DEFAULT: + kvm_riscv_vcpu_wfi(vcpu); + break; + case SBI_HSM_SUSPEND_NON_RET_DEFAULT: + ret = -EOPNOTSUPP; + break; + default: + ret = -EINVAL; + } + 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, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c new file mode 100644 index 000000000000..4c034d8a606a --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 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> +#include <asm/kvm_vcpu_sbi.h> + +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; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long hmask = cp->a0; + unsigned long hbase = cp->a1; + unsigned long funcid = cp->a6; + + switch (funcid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + kvm_riscv_fence_i(vcpu->kvm, hbase, hmask); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + if (cp->a2 == 0 && cp->a3 == 0) + kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask); + else + kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, + cp->a2, cp->a3, PAGE_SHIFT); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + if (cp->a2 == 0 && cp->a3 == 0) + kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, + hbase, hmask, cp->a4); + else + kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, + hbase, hmask, + cp->a2, cp->a3, + PAGE_SHIFT, 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: + /* + * Until nested virtualization is implemented, the + * SBI HFENCE calls should be treated as NOPs + */ + break; + 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, +}; + +static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, + struct kvm_run *run, + unsigned long *out_val, + struct kvm_cpu_trap *utrap, bool *exit) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + u32 reason = cp->a1; + u32 type = cp->a0; + int ret = 0; + + switch (funcid) { + case SBI_EXT_SRST_RESET: + switch (type) { + case SBI_SRST_RESET_TYPE_SHUTDOWN: + kvm_riscv_vcpu_sbi_system_reset(vcpu, run, + KVM_SYSTEM_EVENT_SHUTDOWN, + reason); + *exit = true; + break; + case SBI_SRST_RESET_TYPE_COLD_REBOOT: + case SBI_SRST_RESET_TYPE_WARM_REBOOT: + kvm_riscv_vcpu_sbi_system_reset(vcpu, run, + KVM_SYSTEM_EVENT_RESET, + reason); + *exit = true; + break; + default: + ret = -EOPNOTSUPP; + } + break; + default: + ret = -EOPNOTSUPP; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst = { + .extid_start = SBI_EXT_SRST, + .extid_end = SBI_EXT_SRST, + .handler = kvm_sbi_ext_srst_handler, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c new file mode 100644 index 000000000000..8a91a14e7139 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 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> +#include <asm/kvm_vcpu_sbi.h> + +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 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_riscv_vcpu_sbi_system_reset(vcpu, run, + KVM_SYSTEM_EVENT_SHUTDOWN, 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); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap->scause) + break; + + if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) + kvm_riscv_fence_i(vcpu->kvm, 0, hmask); + else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) { + if (cp->a1 == 0 && cp->a2 == 0) + kvm_riscv_hfence_vvma_all(vcpu->kvm, + 0, hmask); + else + kvm_riscv_hfence_vvma_gva(vcpu->kvm, + 0, hmask, + cp->a1, cp->a2, + PAGE_SHIFT); + } else { + if (cp->a1 == 0 && cp->a2 == 0) + kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, + 0, hmask, + cp->a3); + else + kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, + 0, hmask, + cp->a1, cp->a2, + PAGE_SHIFT, + 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, +}; diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S index 029a28a195c6..d74df8eb4d71 100644 --- a/arch/riscv/kvm/vcpu_switch.S +++ b/arch/riscv/kvm/vcpu_switch.S @@ -41,33 +41,37 @@ ENTRY(__kvm_riscv_switch_to) REG_S s10, (KVM_ARCH_HOST_S10)(a0) REG_S s11, (KVM_ARCH_HOST_S11)(a0) - /* Save Host and Restore Guest SSTATUS */ + /* Load Guest CSR values */ REG_L t0, (KVM_ARCH_GUEST_SSTATUS)(a0) + REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0) + REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0) + la t4, __kvm_switch_return + REG_L t5, (KVM_ARCH_GUEST_SEPC)(a0) + + /* Save Host and Restore Guest SSTATUS */ csrrw t0, CSR_SSTATUS, t0 - REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0) /* Save Host and Restore Guest HSTATUS */ - REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0) csrrw t1, CSR_HSTATUS, t1 - REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0) /* Save Host and Restore Guest SCOUNTEREN */ - REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0) csrrw t2, CSR_SCOUNTEREN, t2 - REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0) - - /* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */ - csrrw t3, CSR_SSCRATCH, a0 - REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0) /* Save Host STVEC and change it to return path */ - la t4, __kvm_switch_return csrrw t4, CSR_STVEC, t4 - REG_S t4, (KVM_ARCH_HOST_STVEC)(a0) + + /* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */ + csrrw t3, CSR_SSCRATCH, a0 /* Restore Guest SEPC */ - REG_L t0, (KVM_ARCH_GUEST_SEPC)(a0) - csrw CSR_SEPC, t0 + csrw CSR_SEPC, t5 + + /* Store Host CSR values */ + REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0) + REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0) + REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0) + REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0) + REG_S t4, (KVM_ARCH_HOST_STVEC)(a0) /* Restore Guest GPRs (except A0) */ REG_L ra, (KVM_ARCH_GUEST_RA)(a0) @@ -145,32 +149,36 @@ __kvm_switch_return: REG_S t5, (KVM_ARCH_GUEST_T5)(a0) REG_S t6, (KVM_ARCH_GUEST_T6)(a0) + /* Load Host CSR values */ + REG_L t1, (KVM_ARCH_HOST_STVEC)(a0) + REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0) + REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0) + REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0) + REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0) + /* Save Guest SEPC */ csrr t0, CSR_SEPC - REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0) - - /* Restore Host STVEC */ - REG_L t1, (KVM_ARCH_HOST_STVEC)(a0) - csrw CSR_STVEC, t1 /* Save Guest A0 and Restore Host SSCRATCH */ - REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0) csrrw t2, CSR_SSCRATCH, t2 - REG_S t2, (KVM_ARCH_GUEST_A0)(a0) + + /* Restore Host STVEC */ + csrw CSR_STVEC, t1 /* Save Guest and Restore Host SCOUNTEREN */ - REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0) csrrw t3, CSR_SCOUNTEREN, t3 - REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0) /* Save Guest and Restore Host HSTATUS */ - REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0) csrrw t4, CSR_HSTATUS, t4 - REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0) /* Save Guest and Restore Host SSTATUS */ - REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0) csrrw t5, CSR_SSTATUS, t5 + + /* Store Guest CSR values */ + REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0) + REG_S t2, (KVM_ARCH_GUEST_A0)(a0) + REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0) + REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0) REG_S t5, (KVM_ARCH_GUEST_SSTATUS)(a0) /* Restore Host GPRs (except A0 and T0-T6) */ diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index 5c4c37ff2d48..ad34519c8a13 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -69,7 +69,18 @@ static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t) return 0; } -int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles) +static int kvm_riscv_vcpu_update_vstimecmp(struct kvm_vcpu *vcpu, u64 ncycles) +{ +#if defined(CONFIG_32BIT) + csr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF); + csr_write(CSR_VSTIMECMPH, ncycles >> 32); +#else + csr_write(CSR_VSTIMECMP, ncycles); +#endif + return 0; +} + +static int kvm_riscv_vcpu_update_hrtimer(struct kvm_vcpu *vcpu, u64 ncycles) { struct kvm_vcpu_timer *t = &vcpu->arch.timer; struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; @@ -88,6 +99,65 @@ int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles) return 0; } +int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + return t->timer_next_event(vcpu, ncycles); +} + +static enum hrtimer_restart kvm_riscv_vcpu_vstimer_expired(struct hrtimer *h) +{ + u64 delta_ns; + struct kvm_vcpu_timer *t = container_of(h, struct kvm_vcpu_timer, hrt); + struct kvm_vcpu *vcpu = container_of(t, struct kvm_vcpu, arch.timer); + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + + if (kvm_riscv_current_cycles(gt) < t->next_cycles) { + delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t); + hrtimer_forward_now(&t->hrt, ktime_set(0, delta_ns)); + return HRTIMER_RESTART; + } + + t->next_set = false; + kvm_vcpu_kick(vcpu); + + return HRTIMER_NORESTART; +} + +bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + + if (!kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t) || + kvm_riscv_vcpu_has_interrupts(vcpu, 1UL << IRQ_VS_TIMER)) + return true; + else + return false; +} + +static void kvm_riscv_vcpu_timer_blocking(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + u64 delta_ns; + + if (!t->init_done) + return; + + delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t); + if (delta_ns) { + hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL); + t->next_set = true; + } +} + +static void kvm_riscv_vcpu_timer_unblocking(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer); +} + int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { @@ -180,10 +250,20 @@ int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu) return -EINVAL; hrtimer_init(&t->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - t->hrt.function = kvm_riscv_vcpu_hrtimer_expired; t->init_done = true; t->next_set = false; + /* Enable sstc for every vcpu if available in hardware */ + if (riscv_isa_extension_available(NULL, SSTC)) { + t->sstc_enabled = true; + t->hrt.function = kvm_riscv_vcpu_vstimer_expired; + t->timer_next_event = kvm_riscv_vcpu_update_vstimecmp; + } else { + t->sstc_enabled = false; + t->hrt.function = kvm_riscv_vcpu_hrtimer_expired; + t->timer_next_event = kvm_riscv_vcpu_update_hrtimer; + } + return 0; } @@ -199,27 +279,86 @@ int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu) int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu) { + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + t->next_cycles = -1ULL; return kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer); } -void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu) +static void kvm_riscv_vcpu_update_timedelta(struct kvm_vcpu *vcpu) { struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; -#ifdef CONFIG_64BIT - csr_write(CSR_HTIMEDELTA, gt->time_delta); -#else +#if defined(CONFIG_32BIT) csr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta)); csr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32)); +#else + csr_write(CSR_HTIMEDELTA, gt->time_delta); +#endif +} + +void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + kvm_riscv_vcpu_update_timedelta(vcpu); + + if (!t->sstc_enabled) + return; + +#if defined(CONFIG_32BIT) + csr_write(CSR_VSTIMECMP, (u32)t->next_cycles); + csr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32)); +#else + csr_write(CSR_VSTIMECMP, t->next_cycles); +#endif + + /* timer should be enabled for the remaining operations */ + if (unlikely(!t->init_done)) + return; + + kvm_riscv_vcpu_timer_unblocking(vcpu); +} + +void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + if (!t->sstc_enabled) + return; + +#if defined(CONFIG_32BIT) + t->next_cycles = csr_read(CSR_VSTIMECMP); + t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32; +#else + t->next_cycles = csr_read(CSR_VSTIMECMP); #endif } -int kvm_riscv_guest_timer_init(struct kvm *kvm) +void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + if (!t->sstc_enabled) + return; + + /* + * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync() + * upon every VM exit so no need to save here. + */ + + /* timer should be enabled for the remaining operations */ + if (unlikely(!t->init_done)) + return; + + if (kvm_vcpu_is_blocking(vcpu)) + kvm_riscv_vcpu_timer_blocking(vcpu); +} + +void kvm_riscv_guest_timer_init(struct kvm *kvm) { struct kvm_guest_timer *gt = &kvm->arch.timer; riscv_cs_get_mult_shift(>->nsec_mult, >->nsec_shift); gt->time_delta = -get_cycles64(); - - return 0; } diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index fb18af34a4b5..65a964d7e70d 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -31,30 +31,24 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int r; - r = kvm_riscv_stage2_alloc_pgd(kvm); + r = kvm_riscv_gstage_alloc_pgd(kvm); if (r) return r; - r = kvm_riscv_stage2_vmid_init(kvm); + r = kvm_riscv_gstage_vmid_init(kvm); if (r) { - kvm_riscv_stage2_free_pgd(kvm); + kvm_riscv_gstage_free_pgd(kvm); return r; } - return kvm_riscv_guest_timer_init(kvm); + kvm_riscv_guest_timer_init(kvm); + + return 0; } void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -82,6 +76,9 @@ 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_gstage_gpa_bits(); + break; default: r = 0; break; diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 2c6253b293bc..6cd93995fb65 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -11,16 +11,16 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/module.h> +#include <linux/smp.h> #include <linux/kvm_host.h> #include <asm/csr.h> -#include <asm/sbi.h> static unsigned long vmid_version = 1; static unsigned long vmid_next; static unsigned long vmid_bits; static DEFINE_SPINLOCK(vmid_lock); -void kvm_riscv_stage2_vmid_detect(void) +void kvm_riscv_gstage_vmid_detect(void) { unsigned long old; @@ -33,19 +33,19 @@ void kvm_riscv_stage2_vmid_detect(void) csr_write(CSR_HGATP, old); /* We polluted local TLB so flush all guest TLB */ - __kvm_riscv_hfence_gvma_all(); + kvm_riscv_local_hfence_gvma_all(); /* We don't use VMID bits if they are not sufficient */ if ((1UL << vmid_bits) < num_possible_cpus()) vmid_bits = 0; } -unsigned long kvm_riscv_stage2_vmid_bits(void) +unsigned long kvm_riscv_gstage_vmid_bits(void) { return vmid_bits; } -int kvm_riscv_stage2_vmid_init(struct kvm *kvm) +int kvm_riscv_gstage_vmid_init(struct kvm *kvm) { /* Mark the initial VMID and VMID version invalid */ kvm->arch.vmid.vmid_version = 0; @@ -54,7 +54,7 @@ int kvm_riscv_stage2_vmid_init(struct kvm *kvm) return 0; } -bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid) +bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid) { if (!vmid_bits) return false; @@ -63,14 +63,18 @@ bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid) READ_ONCE(vmid_version)); } -void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) +static void __local_hfence_gvma_all(void *info) { - int i; + kvm_riscv_local_hfence_gvma_all(); +} + +void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu) +{ + unsigned long i; struct kvm_vcpu *v; - struct cpumask hmask; struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid; - if (!kvm_riscv_stage2_vmid_ver_changed(vmid)) + if (!kvm_riscv_gstage_vmid_ver_changed(vmid)) return; spin_lock(&vmid_lock); @@ -79,7 +83,7 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) * We need to re-check the vmid_version here to ensure that if * another vcpu already allocated a valid vmid for this vm. */ - if (!kvm_riscv_stage2_vmid_ver_changed(vmid)) { + if (!kvm_riscv_gstage_vmid_ver_changed(vmid)) { spin_unlock(&vmid_lock); return; } @@ -93,17 +97,17 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) * We ran out of VMIDs so we increment vmid_version and * start assigning VMIDs from 1. * - * This also means existing VMIDs assignement to all Guest + * This also means existing VMIDs assignment to all Guest * instances is invalid and we have force VMID re-assignement * for all Guest instances. The Guest instances that were not * running will automatically pick-up new VMIDs because will - * call kvm_riscv_stage2_vmid_update() whenever they enter + * call kvm_riscv_gstage_vmid_update() whenever they enter * in-kernel run loop. For Guest instances that are already * running, we force VM exits on all host CPUs using IPI and * flush all Guest TLBs. */ - riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask); - sbi_remote_hfence_gvma(cpumask_bits(&hmask), 0, 0); + on_each_cpu_mask(cpu_online_mask, __local_hfence_gvma_all, + NULL, 1); } vmid->vmid = vmid_next; @@ -114,7 +118,7 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) spin_unlock(&vmid_lock); - /* Request stage2 page table update for all VCPUs */ + /* Request G-stage page table update for all VCPUs */ kvm_for_each_vcpu(i, v, vcpu->kvm) kvm_make_request(KVM_REQ_UPDATE_HGATP, v); } |