Merge tag 'kvm-riscv-5.17-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv changes for 5.17, take #1

- Use common KVM implementation of MMU memory caches
- SBI v0.2 support for Guest
- Initial KVM selftests support
- Fix to avoid spurious virtual interrupts after clearing hideleg CSR
- Update email address for Anup and Atish

.mailmap

@@ -46,10 +46,12 @@ Andy Adamson <andros@citi.umich.edu>
 Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
 Antoine Tenart <atenart@kernel.org> <antoine.tenart@free-electrons.com>
 Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
+Anup Patel <anup@brainfault.org> <anup.patel@wdc.com>
 Archit Taneja <archit@ti.com>
 Ard Biesheuvel <ardb@kernel.org> <ard.biesheuvel@linaro.org>
 Arnaud Patard <arnaud.patard@rtp-net.org>
 Arnd Bergmann <arnd@arndb.de>
+Atish Patra <atishp@atishpatra.org> <atish.patra@wdc.com>
 Axel Dyks <xl@xlsigned.net>
 Axel Lin <axel.lin@gmail.com>
 Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com>

MAINTAINERS

@@ -10444,8 +10444,8 @@ F:	arch/powerpc/kernel/kvm*
 F:	arch/powerpc/kvm/
 
 KERNEL VIRTUAL MACHINE FOR RISC-V (KVM/riscv)
-M:	Anup Patel <anup.patel@wdc.com>
-R:	Atish Patra <atish.patra@wdc.com>
+M:	Anup Patel <anup@brainfault.org>
+R:	Atish Patra <atishp@atishpatra.org>
 L:	kvm@vger.kernel.org
 L:	kvm-riscv@lists.infradead.org
 L:	linux-riscv@lists.infradead.org

arch/riscv/include/asm/kvm_host.h

@@ -77,13 +77,6 @@ struct kvm_sbi_context {
 	int return_handled;
 };
 
-#define KVM_MMU_PAGE_CACHE_NR_OBJS	32
-
-struct kvm_mmu_page_cache {
-	int nobjs;
-	void *objects[KVM_MMU_PAGE_CACHE_NR_OBJS];
-};
-
 struct kvm_cpu_trap {
 	unsigned long sepc;
 	unsigned long scause;
@@ -193,7 +186,7 @@ struct kvm_vcpu_arch {
 	struct kvm_sbi_context sbi_context;
 
 	/* Cache pages needed to program page tables with spinlock held */
-	struct kvm_mmu_page_cache mmu_page_cache;
+	struct kvm_mmu_memory_cache mmu_page_cache;
 
 	/* VCPU power-off state */
 	bool power_off;
@@ -220,12 +213,12 @@ void __kvm_riscv_hfence_gvma_all(void);
 int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu,
 			 struct kvm_memory_slot *memslot,
 			 gpa_t gpa, unsigned long hva, bool is_write);
-void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu);
 int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm);
 void kvm_riscv_stage2_free_pgd(struct kvm *kvm);
 void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu);
 void kvm_riscv_stage2_mode_detect(void);
 unsigned long kvm_riscv_stage2_mode(void);
+int kvm_riscv_stage2_gpa_bits(void);
 
 void kvm_riscv_stage2_vmid_detect(void);
 unsigned long kvm_riscv_stage2_vmid_bits(void);

arch/riscv/include/asm/kvm_types.h

@@ -2,6 +2,6 @@
 #ifndef _ASM_RISCV_KVM_TYPES_H
 #define _ASM_RISCV_KVM_TYPES_H
 
-#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 32
 
 #endif /* _ASM_RISCV_KVM_TYPES_H */

arch/riscv/include/asm/kvm_vcpu_sbi.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/**
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#ifndef __RISCV_KVM_VCPU_SBI_H__
+#define __RISCV_KVM_VCPU_SBI_H__
+
+#define KVM_SBI_IMPID 3
+
+#define KVM_SBI_VERSION_MAJOR 0
+#define KVM_SBI_VERSION_MINOR 2
+
+struct kvm_vcpu_sbi_extension {
+	unsigned long extid_start;
+	unsigned long extid_end;
+	/**
+	 * SBI extension handler. It can be defined for a given extension or group of
+	 * extension. But it should always return linux error codes rather than SBI
+	 * specific error codes.
+	 */
+	int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       unsigned long *out_val, struct kvm_cpu_trap *utrap,
+		       bool *exit);
+};
+
+void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run);
+const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid);
+
+#endif /* __RISCV_KVM_VCPU_SBI_H__ */

arch/riscv/include/asm/sbi.h

@@ -27,6 +27,14 @@ enum sbi_ext_id {
 	SBI_EXT_IPI = 0x735049,
 	SBI_EXT_RFENCE = 0x52464E43,
 	SBI_EXT_HSM = 0x48534D,
+
+	/* Experimentals extensions must lie within this range */
+	SBI_EXT_EXPERIMENTAL_START = 0x08000000,
+	SBI_EXT_EXPERIMENTAL_END = 0x08FFFFFF,
+
+	/* Vendor extensions must lie within this range */
+	SBI_EXT_VENDOR_START = 0x09000000,
+	SBI_EXT_VENDOR_END = 0x09FFFFFF,
 };
 
 enum sbi_ext_base_fid {
@@ -82,6 +90,7 @@ enum sbi_hsm_hart_status {
 #define SBI_ERR_INVALID_PARAM	-3
 #define SBI_ERR_DENIED		-4
 #define SBI_ERR_INVALID_ADDRESS	-5
+#define SBI_ERR_ALREADY_AVAILABLE -6
 
 extern unsigned long sbi_spec_version;
 struct sbiret {

arch/riscv/kvm/Makefile

@@ -19,4 +19,8 @@ kvm-y += vcpu_exit.o
 kvm-y += vcpu_fp.o
 kvm-y += vcpu_switch.o
 kvm-y += vcpu_sbi.o
+kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
+kvm-y += vcpu_sbi_base.o
+kvm-y += vcpu_sbi_replace.o
+kvm-y += vcpu_sbi_hsm.o
 kvm-y += vcpu_timer.o

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);
 }

arch/riscv/kvm/mmu.c

@@ -83,43 +83,6 @@ static int stage2_level_to_page_size(u32 level, unsigned long *out_pgsize)
 	return 0;
 }
 
-static int stage2_cache_topup(struct kvm_mmu_page_cache *pcache,
-			      int min, int max)
-{
-	void *page;
-
-	BUG_ON(max > KVM_MMU_PAGE_CACHE_NR_OBJS);
-	if (pcache->nobjs >= min)
-		return 0;
-	while (pcache->nobjs < max) {
-		page = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-		if (!page)
-			return -ENOMEM;
-		pcache->objects[pcache->nobjs++] = page;
-	}
-
-	return 0;
-}
-
-static void stage2_cache_flush(struct kvm_mmu_page_cache *pcache)
-{
-	while (pcache && pcache->nobjs)
-		free_page((unsigned long)pcache->objects[--pcache->nobjs]);
-}
-
-static void *stage2_cache_alloc(struct kvm_mmu_page_cache *pcache)
-{
-	void *p;
-
-	if (!pcache)
-		return NULL;
-
-	BUG_ON(!pcache->nobjs);
-	p = pcache->objects[--pcache->nobjs];
-
-	return p;
-}
-
 static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 				  pte_t **ptepp, u32 *ptep_level)
 {
@@ -171,7 +134,7 @@ static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
 }
 
 static int stage2_set_pte(struct kvm *kvm, u32 level,
-			   struct kvm_mmu_page_cache *pcache,
+			   struct kvm_mmu_memory_cache *pcache,
 			   gpa_t addr, const pte_t *new_pte)
 {
 	u32 current_level = stage2_pgd_levels - 1;
@@ -186,7 +149,9 @@ static int stage2_set_pte(struct kvm *kvm, u32 level,
 			return -EEXIST;
 
 		if (!pte_val(*ptep)) {
-			next_ptep = stage2_cache_alloc(pcache);
+			if (!pcache)
+				return -ENOMEM;
+			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
 			if (!next_ptep)
 				return -ENOMEM;
 			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
@@ -209,7 +174,7 @@ static int stage2_set_pte(struct kvm *kvm, u32 level,
 }
 
 static int stage2_map_page(struct kvm *kvm,
-			   struct kvm_mmu_page_cache *pcache,
+			   struct kvm_mmu_memory_cache *pcache,
 			   gpa_t gpa, phys_addr_t hpa,
 			   unsigned long page_size,
 			   bool page_rdonly, bool page_exec)
@@ -384,7 +349,10 @@ static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 	int ret = 0;
 	unsigned long pfn;
 	phys_addr_t addr, end;
-	struct kvm_mmu_page_cache pcache = { 0, };
+	struct kvm_mmu_memory_cache pcache;
+
+	memset(&pcache, 0, sizeof(pcache));
+	pcache.gfp_zero = __GFP_ZERO;
 
 	end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
 	pfn = __phys_to_pfn(hpa);
@@ -395,9 +363,7 @@ static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 		if (!writable)
 			pte = pte_wrprotect(pte);
 
-		ret = stage2_cache_topup(&pcache,
-					 stage2_pgd_levels,
-					 KVM_MMU_PAGE_CACHE_NR_OBJS);
+		ret = kvm_mmu_topup_memory_cache(&pcache, stage2_pgd_levels);
 		if (ret)
 			goto out;
 
@@ -411,7 +377,7 @@ static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 	}
 
 out:
-	stage2_cache_flush(&pcache);
+	kvm_mmu_free_memory_cache(&pcache);
 	return ret;
 }
 
@@ -649,7 +615,7 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct vm_area_struct *vma;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvm_mmu_page_cache *pcache = &vcpu->arch.mmu_page_cache;
+	struct kvm_mmu_memory_cache *pcache = &vcpu->arch.mmu_page_cache;
 	bool logging = (memslot->dirty_bitmap &&
 			!(memslot->flags & KVM_MEM_READONLY)) ? true : false;
 	unsigned long vma_pagesize, mmu_seq;
@@ -684,8 +650,7 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu,
 	}
 
 	/* We need minimum second+third level pages */
-	ret = stage2_cache_topup(pcache, stage2_pgd_levels,
-				 KVM_MMU_PAGE_CACHE_NR_OBJS);
+	ret = kvm_mmu_topup_memory_cache(pcache, stage2_pgd_levels);
 	if (ret) {
 		kvm_err("Failed to topup stage2 cache\n");
 		return ret;
@@ -734,11 +699,6 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu,
 	return ret;
 }
 
-void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu)
-{
-	stage2_cache_flush(&vcpu->arch.mmu_page_cache);
-}
-
 int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm)
 {
 	struct page *pgd_page;
@@ -809,3 +769,8 @@ unsigned long kvm_riscv_stage2_mode(void)
 {
 	return stage2_mode >> HGATP_MODE_SHIFT;
 }
+
+int kvm_riscv_stage2_gpa_bits(void)
+{
+	return stage2_gpa_bits;
+}

arch/riscv/kvm/vcpu.c

@@ -53,6 +53,17 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 	struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context;
+	bool loaded;
+
+	/**
+	 * The preemption should be disabled here because it races with
+	 * kvm_sched_out/kvm_sched_in(called from preempt notifiers) which
+	 * also calls vcpu_load/put.
+	 */
+	get_cpu();
+	loaded = (vcpu->cpu != -1);
+	if (loaded)
+		kvm_arch_vcpu_put(vcpu);
 
 	memcpy(csr, reset_csr, sizeof(*csr));
 
@@ -64,6 +75,11 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
 	WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
+
+	/* Reset the guest CSRs for hotplug usecase */
+	if (loaded)
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	put_cpu();
 }
 
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
@@ -77,6 +93,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	/* Mark this VCPU never ran */
 	vcpu->arch.ran_atleast_once = false;
+	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
 
 	/* Setup ISA features available to VCPU */
 	vcpu->arch.isa = riscv_isa_extension_base(NULL) & KVM_RISCV_ISA_ALLOWED;
@@ -100,6 +117,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
+	/**
+	 * vcpu with id 0 is the designated boot cpu.
+	 * Keep all vcpus with non-zero id in power-off state so that
+	 * they can be brought up using SBI HSM extension.
+	 */
+	if (vcpu->vcpu_idx != 0)
+		kvm_riscv_vcpu_power_off(vcpu);
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -107,8 +131,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	/* Cleanup VCPU timer */
 	kvm_riscv_vcpu_timer_deinit(vcpu);
 
-	/* Flush the pages pre-allocated for Stage2 page table mappings */
-	kvm_riscv_stage2_flush_cache(vcpu);
+	/* Free unused pages pre-allocated for Stage2 page table mappings */
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)

arch/riscv/kvm/vcpu_fp.c

@@ -26,7 +26,7 @@ void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)
 		cntx->sstatus |= SR_FS_OFF;
 }
 
-void kvm_riscv_vcpu_fp_clean(struct kvm_cpu_context *cntx)
+static void kvm_riscv_vcpu_fp_clean(struct kvm_cpu_context *cntx)
 {
 	cntx->sstatus &= ~SR_FS;
 	cntx->sstatus |= SR_FS_CLEAN;

arch/riscv/kvm/vcpu_sbi.c

@@ -9,15 +9,58 @@
 #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)
+#ifdef CONFIG_RISCV_SBI_V01
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
+#else
+static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = {
+	.extid_start = -1UL,
+	.extid_end = -1UL,
+	.handler = NULL,
+};
+#endif
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
+
+static const struct kvm_vcpu_sbi_extension *sbi_ext[] = {
+	&vcpu_sbi_ext_v01,
+	&vcpu_sbi_ext_base,
+	&vcpu_sbi_ext_time,
+	&vcpu_sbi_ext_ipi,
+	&vcpu_sbi_ext_rfence,
+	&vcpu_sbi_ext_hsm,
+	&vcpu_sbi_ext_experimental,
+	&vcpu_sbi_ext_vendor,
+};
+
+void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 
@@ -55,131 +98,73 @@ 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)
 {
-	unsigned long 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

arch/riscv/kvm/vcpu_sbi_base.c

+// 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_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				    unsigned long *out_val,
+				    struct kvm_cpu_trap *trap, bool *exit)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	struct sbiret ecall_ret;
+
+	switch (cp->a6) {
+	case SBI_EXT_BASE_GET_SPEC_VERSION:
+		*out_val = (KVM_SBI_VERSION_MAJOR <<
+			    SBI_SPEC_VERSION_MAJOR_SHIFT) |
+			    KVM_SBI_VERSION_MINOR;
+		break;
+	case SBI_EXT_BASE_GET_IMP_ID:
+		*out_val = KVM_SBI_IMPID;
+		break;
+	case SBI_EXT_BASE_GET_IMP_VERSION:
+		*out_val = 0;
+		break;
+	case SBI_EXT_BASE_PROBE_EXT:
+		if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START &&
+		     cp->a0 <= SBI_EXT_EXPERIMENTAL_END) ||
+		    (cp->a0 >= SBI_EXT_VENDOR_START &&
+		     cp->a0 <= SBI_EXT_VENDOR_END)) {
+			/*
+			 * For experimental/vendor extensions
+			 * forward it to the userspace
+			 */
+			kvm_riscv_vcpu_sbi_forward(vcpu, run);
+			*exit = true;
+		} else
+			*out_val = kvm_vcpu_sbi_find_ext(cp->a0) ? 1 : 0;
+		break;
+	case SBI_EXT_BASE_GET_MVENDORID:
+	case SBI_EXT_BASE_GET_MARCHID:
+	case SBI_EXT_BASE_GET_MIMPID:
+		ecall_ret = sbi_ecall(SBI_EXT_BASE, cp->a6, 0, 0, 0, 0, 0, 0);
+		if (!ecall_ret.error)
+			*out_val = ecall_ret.value;
+		/*TODO: We are unnecessarily converting the error twice */
+		ret = sbi_err_map_linux_errno(ecall_ret.error);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = {
+	.extid_start = SBI_EXT_BASE,
+	.extid_end = SBI_EXT_BASE,
+	.handler = kvm_sbi_ext_base_handler,
+};
+
+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,
+};

arch/riscv/kvm/vcpu_sbi_hsm.c

+// 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_HART_STATUS_STARTED;
+	else
+		return SBI_HSM_HART_STATUS_STOPPED;
+}
+
+static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				   unsigned long *out_val,
+				   struct kvm_cpu_trap *utrap,
+				   bool *exit)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long funcid = cp->a6;
+
+	switch (funcid) {
+	case SBI_EXT_HSM_HART_START:
+		mutex_lock(&kvm->lock);
+		ret = kvm_sbi_hsm_vcpu_start(vcpu);
+		mutex_unlock(&kvm->lock);
+		break;
+	case SBI_EXT_HSM_HART_STOP:
+		ret = kvm_sbi_hsm_vcpu_stop(vcpu);
+		break;
+	case SBI_EXT_HSM_HART_STATUS:
+		ret = kvm_sbi_hsm_vcpu_get_status(vcpu);
+		if (ret >= 0) {
+			*out_val = ret;
+			ret = 0;
+		}
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = {
+	.extid_start = SBI_EXT_HSM,
+	.extid_end = SBI_EXT_HSM,
+	.handler = kvm_sbi_ext_hsm_handler,
+};

arch/riscv/kvm/vcpu_sbi_replace.c

+// 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;
+	unsigned long i;
+	struct cpumask cm, hm;
+	struct kvm_vcpu *tmp;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long hmask = cp->a0;
+	unsigned long hbase = cp->a1;
+	unsigned long funcid = cp->a6;
+
+	cpumask_clear(&cm);
+	cpumask_clear(&hm);
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+		if (hbase != -1UL) {
+			if (tmp->vcpu_id < hbase)
+				continue;
+			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+				continue;
+		}
+		if (tmp->cpu < 0)
+			continue;
+		cpumask_set_cpu(tmp->cpu, &cm);
+	}
+
+	riscv_cpuid_to_hartid_mask(&cm, &hm);
+
+	switch (funcid) {
+	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+		ret = sbi_remote_fence_i(cpumask_bits(&hm));
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+		ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), cp->a2, cp->a3);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+		ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), cp->a2,
+						  cp->a3, cp->a4);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
+	/* TODO: implement for nested hypervisor case */
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = {
+	.extid_start = SBI_EXT_RFENCE,
+	.extid_end = SBI_EXT_RFENCE,
+	.handler = kvm_sbi_ext_rfence_handler,
+};

arch/riscv/kvm/vcpu_sbi_v01.c

+// 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 void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu,
+				    struct kvm_run *run, u32 type)
+{
+	unsigned long i;
+	struct kvm_vcpu *tmp;
+
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm)
+		tmp->arch.power_off = true;
+	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
+
+	memset(&run->system_event, 0, sizeof(run->system_event));
+	run->system_event.type = type;
+	run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				      unsigned long *out_val,
+				      struct kvm_cpu_trap *utrap,
+				      bool *exit)
+{
+	ulong hmask;
+	int i, ret = 0;
+	u64 next_cycle;
+	struct kvm_vcpu *rvcpu;
+	struct cpumask cm, hm;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+
+	switch (cp->a7) {
+	case SBI_EXT_0_1_CONSOLE_GETCHAR:
+	case SBI_EXT_0_1_CONSOLE_PUTCHAR:
+		/*
+		 * The CONSOLE_GETCHAR/CONSOLE_PUTCHAR SBI calls cannot be
+		 * handled in kernel so we forward these to user-space
+		 */
+		kvm_riscv_vcpu_sbi_forward(vcpu, run);
+		*exit = true;
+		break;
+	case SBI_EXT_0_1_SET_TIMER:
+#if __riscv_xlen == 32
+		next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0;
+#else
+		next_cycle = (u64)cp->a0;
+#endif
+		ret = kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle);
+		break;
+	case SBI_EXT_0_1_CLEAR_IPI:
+		ret = kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_SOFT);
+		break;
+	case SBI_EXT_0_1_SEND_IPI:
+		if (cp->a0)
+			hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0,
+							   utrap);
+		else
+			hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1;
+		if (utrap->scause)
+			break;
+
+		for_each_set_bit(i, &hmask, BITS_PER_LONG) {
+			rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i);
+			ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT);
+			if (ret < 0)
+				break;
+		}
+		break;
+	case SBI_EXT_0_1_SHUTDOWN:
+		kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN);
+		*exit = true;
+		break;
+	case SBI_EXT_0_1_REMOTE_FENCE_I:
+	case SBI_EXT_0_1_REMOTE_SFENCE_VMA:
+	case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID:
+		if (cp->a0)
+			hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0,
+							   utrap);
+		else
+			hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1;
+		if (utrap->scause)
+			break;
+
+		cpumask_clear(&cm);
+		for_each_set_bit(i, &hmask, BITS_PER_LONG) {
+			rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i);
+			if (rvcpu->cpu < 0)
+				continue;
+			cpumask_set_cpu(rvcpu->cpu, &cm);
+		}
+		riscv_cpuid_to_hartid_mask(&cm, &hm);
+		if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I)
+			ret = sbi_remote_fence_i(cpumask_bits(&hm));
+		else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA)
+			ret = sbi_remote_hfence_vvma(cpumask_bits(&hm),
+						cp->a1, cp->a2);
+		else
+			ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm),
+						cp->a1, cp->a2, cp->a3);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	};
+
+	return ret;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = {
+	.extid_start = SBI_EXT_0_1_SET_TIMER,
+	.extid_end = SBI_EXT_0_1_SHUTDOWN,
+	.handler = kvm_sbi_ext_v01_handler,
+};

arch/riscv/kvm/vm.c

@@ -74,6 +74,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_NR_MEMSLOTS:
 		r = KVM_USER_MEM_SLOTS;
 		break;
+	case KVM_CAP_VM_GPA_BITS:
+		r = kvm_riscv_stage2_gpa_bits();
+		break;
 	default:
 		r = 0;
 		break;

include/uapi/linux/kvm.h

@@ -1131,6 +1131,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
 #define KVM_CAP_ARM_MTE 205
 #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
+#define KVM_CAP_VM_GPA_BITS 207
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/testing/selftests/kvm/Makefile

@@ -32,11 +32,16 @@ endif
 ifeq ($(ARCH),s390)
 	UNAME_M := s390x
 endif
+# Set UNAME_M riscv compile/install to work
+ifeq ($(ARCH),riscv)
+	UNAME_M := riscv
+endif
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
 LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
+LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
@@ -120,6 +125,13 @@ TEST_GEN_PROGS_s390x += rseq_test
 TEST_GEN_PROGS_s390x += set_memory_region_test
 TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
+TEST_GEN_PROGS_riscv += demand_paging_test
+TEST_GEN_PROGS_riscv += dirty_log_test
+TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
+TEST_GEN_PROGS_riscv += kvm_page_table_test
+TEST_GEN_PROGS_riscv += set_memory_region_test
+TEST_GEN_PROGS_riscv += kvm_binary_stats_test
+
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
@@ -134,7 +146,7 @@ endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
-	-I$(<D) -Iinclude/$(UNAME_M) -I..
+	-I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS)
 
 no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
         $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)

tools/testing/selftests/kvm/include/kvm_util.h

@@ -77,6 +77,16 @@ extern enum vm_guest_mode vm_mode_default;
 #define MIN_PAGE_SHIFT			12U
 #define ptes_per_page(page_size)	((page_size) / 16)
 
+#elif defined(__riscv)
+
+#if __riscv_xlen == 32
+#error "RISC-V 32-bit kvm selftests not supported"
+#endif
+
+#define VM_MODE_DEFAULT			VM_MODE_P40V48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 8)
+
 #endif
 
 #define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)

tools/testing/selftests/kvm/include/riscv/processor.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RISC-V processor specific defines
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+#include <linux/stringify.h>
+
+static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
+				    uint64_t  size)
+{
+	return KVM_REG_RISCV | type | idx | size;
+}
+
+#if __riscv_xlen == 64
+#define KVM_REG_SIZE_ULONG	KVM_REG_SIZE_U64
+#else
+#define KVM_REG_SIZE_ULONG	KVM_REG_SIZE_U32
+#endif
+
+#define RISCV_CONFIG_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CONFIG, \
+					     KVM_REG_RISCV_CONFIG_REG(name), \
+					     KVM_REG_SIZE_ULONG)
+
+#define RISCV_CORE_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CORE, \
+					     KVM_REG_RISCV_CORE_REG(name), \
+					     KVM_REG_SIZE_ULONG)
+
+#define RISCV_CSR_REG(name)	__kvm_reg_id(KVM_REG_RISCV_CSR, \
+					     KVM_REG_RISCV_CSR_REG(name), \
+					     KVM_REG_SIZE_ULONG)
+
+#define RISCV_TIMER_REG(name)	__kvm_reg_id(KVM_REG_RISCV_TIMER, \
+					     KVM_REG_RISCV_TIMER_REG(name), \
+					     KVM_REG_SIZE_U64)
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
+			   unsigned long *addr)
+{
+	struct kvm_one_reg reg;
+
+	reg.id = id;
+	reg.addr = (unsigned long)addr;
+	vcpu_get_reg(vm, vcpuid, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
+			   unsigned long val)
+{
+	struct kvm_one_reg reg;
+
+	reg.id = id;
+	reg.addr = (unsigned long)&val;
+	vcpu_set_reg(vm, vcpuid, &reg);
+}
+
+/* L3 index Bit[47:39] */
+#define PGTBL_L3_INDEX_MASK			0x0000FF8000000000ULL
+#define PGTBL_L3_INDEX_SHIFT			39
+#define PGTBL_L3_BLOCK_SHIFT			39
+#define PGTBL_L3_BLOCK_SIZE			0x0000008000000000ULL
+#define PGTBL_L3_MAP_MASK			(~(PGTBL_L3_BLOCK_SIZE - 1))
+/* L2 index Bit[38:30] */
+#define PGTBL_L2_INDEX_MASK			0x0000007FC0000000ULL
+#define PGTBL_L2_INDEX_SHIFT			30
+#define PGTBL_L2_BLOCK_SHIFT			30
+#define PGTBL_L2_BLOCK_SIZE			0x0000000040000000ULL
+#define PGTBL_L2_MAP_MASK			(~(PGTBL_L2_BLOCK_SIZE - 1))
+/* L1 index Bit[29:21] */
+#define PGTBL_L1_INDEX_MASK			0x000000003FE00000ULL
+#define PGTBL_L1_INDEX_SHIFT			21
+#define PGTBL_L1_BLOCK_SHIFT			21
+#define PGTBL_L1_BLOCK_SIZE			0x0000000000200000ULL
+#define PGTBL_L1_MAP_MASK			(~(PGTBL_L1_BLOCK_SIZE - 1))
+/* L0 index Bit[20:12] */
+#define PGTBL_L0_INDEX_MASK			0x00000000001FF000ULL
+#define PGTBL_L0_INDEX_SHIFT			12
+#define PGTBL_L0_BLOCK_SHIFT			12
+#define PGTBL_L0_BLOCK_SIZE			0x0000000000001000ULL
+#define PGTBL_L0_MAP_MASK			(~(PGTBL_L0_BLOCK_SIZE - 1))
+
+#define PGTBL_PTE_ADDR_MASK			0x003FFFFFFFFFFC00ULL
+#define PGTBL_PTE_ADDR_SHIFT			10
+#define PGTBL_PTE_RSW_MASK			0x0000000000000300ULL
+#define PGTBL_PTE_RSW_SHIFT			8
+#define PGTBL_PTE_DIRTY_MASK			0x0000000000000080ULL
+#define PGTBL_PTE_DIRTY_SHIFT			7
+#define PGTBL_PTE_ACCESSED_MASK			0x0000000000000040ULL
+#define PGTBL_PTE_ACCESSED_SHIFT		6
+#define PGTBL_PTE_GLOBAL_MASK			0x0000000000000020ULL
+#define PGTBL_PTE_GLOBAL_SHIFT			5
+#define PGTBL_PTE_USER_MASK			0x0000000000000010ULL
+#define PGTBL_PTE_USER_SHIFT			4
+#define PGTBL_PTE_EXECUTE_MASK			0x0000000000000008ULL
+#define PGTBL_PTE_EXECUTE_SHIFT			3
+#define PGTBL_PTE_WRITE_MASK			0x0000000000000004ULL
+#define PGTBL_PTE_WRITE_SHIFT			2
+#define PGTBL_PTE_READ_MASK			0x0000000000000002ULL
+#define PGTBL_PTE_READ_SHIFT			1
+#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_EXECUTE_MASK | \
+						 PGTBL_PTE_WRITE_MASK | \
+						 PGTBL_PTE_READ_MASK)
+#define PGTBL_PTE_VALID_MASK			0x0000000000000001ULL
+#define PGTBL_PTE_VALID_SHIFT			0
+
+#define PGTBL_PAGE_SIZE				PGTBL_L0_BLOCK_SIZE
+#define PGTBL_PAGE_SIZE_SHIFT			PGTBL_L0_BLOCK_SHIFT
+
+#define SATP_PPN				_AC(0x00000FFFFFFFFFFF, UL)
+#define SATP_MODE_39				_AC(0x8000000000000000, UL)
+#define SATP_MODE_48				_AC(0x9000000000000000, UL)
+#define SATP_ASID_BITS				16
+#define SATP_ASID_SHIFT				44
+#define SATP_ASID_MASK				_AC(0xFFFF, UL)
+
+#define SBI_EXT_EXPERIMENTAL_START	0x08000000
+#define SBI_EXT_EXPERIMENTAL_END	0x08FFFFFF
+
+#define KVM_RISCV_SELFTESTS_SBI_EXT	SBI_EXT_EXPERIMENTAL_END
+
+struct sbiret {
+	long error;
+	long value;
+};
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5);
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */

tools/testing/selftests/kvm/lib/guest_modes.c

@@ -75,6 +75,16 @@ void guest_modes_append_default(void)
 			guest_mode_append(VM_MODE_P47V64_4K, true, true);
 	}
 #endif
+#ifdef __riscv
+	{
+		unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS);
+
+		if (sz >= 52)
+			guest_mode_append(VM_MODE_P52V48_4K, true, true);
+		if (sz >= 48)
+			guest_mode_append(VM_MODE_P48V48_4K, true, true);
+	}
+#endif
 }
 
 void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)

tools/testing/selftests/kvm/lib/riscv/ucall.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kvm.h>
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+void ucall_init(struct kvm_vm *vm, void *arg)
+{
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+}
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5)
+{
+	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+	struct sbiret ret;
+
+	asm volatile (
+		"ecall"
+		: "+r" (a0), "+r" (a1)
+		: "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+		: "memory");
+	ret.error = a0;
+	ret.value = a1;
+
+	return ret;
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+	struct ucall uc = {
+		.cmd = cmd,
+	};
+	va_list va;
+	int i;
+
+	nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+	va_start(va, nargs);
+	for (i = 0; i < nargs; ++i)
+		uc.args[i] = va_arg(va, uint64_t);
+	va_end(va);
+
+	sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, 0, (vm_vaddr_t)&uc,
+		  0, 0, 0, 0, 0);
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+	struct kvm_run *run = vcpu_state(vm, vcpu_id);
+	struct ucall ucall = {};
+
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
+	if (run->exit_reason == KVM_EXIT_RISCV_SBI &&
+	    run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT &&
+	    run->riscv_sbi.function_id == 0) {
+		memcpy(&ucall, addr_gva2hva(vm, run->riscv_sbi.args[0]),
+			sizeof(ucall));
+
+		vcpu_run_complete_io(vm, vcpu_id);
+		if (uc)
+			memcpy(uc, &ucall, sizeof(ucall));
+	}
+
+	return ucall.cmd;
+}