[Backport] KVM support THP and huge pages spliting for dirty logging

arch/riscv/Kconfig

@@ -60,6 +60,7 @@ config RISCV
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
+	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
 	select ARCH_SUPPORTS_PER_VMA_LOCK if MMU

arch/riscv/include/asm/kvm_aia.h

@@ -150,7 +150,7 @@ int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num,
 
 int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu);
-int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu);
 
 int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm, u32 hart_index,

arch/riscv/include/asm/kvm_gstage.h

@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2025 Ventana Micro Systems Inc.
+ */
+
+#ifndef __RISCV_KVM_GSTAGE_H_
+#define __RISCV_KVM_GSTAGE_H_
+
+#include <linux/kvm_types.h>
+
+struct kvm_gstage {
+	struct kvm *kvm;
+	unsigned long flags;
+#define KVM_GSTAGE_FLAGS_LOCAL		BIT(0)
+	unsigned long vmid;
+	pgd_t *pgd;
+};
+
+struct kvm_gstage_mapping {
+	gpa_t addr;
+	pte_t pte;
+	u32 level;
+};
+
+#ifdef CONFIG_64BIT
+#define kvm_riscv_gstage_index_bits	9
+#else
+#define kvm_riscv_gstage_index_bits	10
+#endif
+
+extern unsigned long kvm_riscv_gstage_mode;
+extern unsigned long kvm_riscv_gstage_pgd_levels;
+
+#define kvm_riscv_gstage_pgd_xbits	2
+#define kvm_riscv_gstage_pgd_size	(1UL << (HGATP_PAGE_SHIFT + kvm_riscv_gstage_pgd_xbits))
+#define kvm_riscv_gstage_gpa_bits	(HGATP_PAGE_SHIFT + \
+					 (kvm_riscv_gstage_pgd_levels * \
+					  kvm_riscv_gstage_index_bits) + \
+					 kvm_riscv_gstage_pgd_xbits)
+#define kvm_riscv_gstage_gpa_size	((gpa_t)(1ULL << kvm_riscv_gstage_gpa_bits))
+
+bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr,
+			       pte_t **ptepp, u32 *ptep_level);
+
+int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
+			     struct kvm_mmu_memory_cache *pcache,
+			     const struct kvm_gstage_mapping *map);
+
+int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage,
+			      struct kvm_mmu_memory_cache *pcache,
+			      gpa_t gpa, phys_addr_t hpa, unsigned long page_size,
+			      bool page_rdonly, bool page_exec,
+			      struct kvm_gstage_mapping *out_map);
+
+int kvm_riscv_gstage_split_huge(struct kvm_gstage *gstage,
+				struct kvm_mmu_memory_cache *pcache,
+				gpa_t addr, u32 target_level, bool flush);
+
+enum kvm_riscv_gstage_op {
+	GSTAGE_OP_NOP = 0,	/* Nothing */
+	GSTAGE_OP_CLEAR,	/* Clear/Unmap */
+	GSTAGE_OP_WP,		/* Write-protect */
+};
+
+void kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr,
+			     pte_t *ptep, u32 ptep_level, enum kvm_riscv_gstage_op op);
+
+void kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage,
+				  gpa_t start, gpa_t size, bool may_block);
+
+void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end);
+
+void kvm_riscv_gstage_mode_detect(void);
+
+#endif

arch/riscv/include/asm/kvm_host.h

@@ -16,6 +16,8 @@
 #include <asm/hwcap.h>
 #include <asm/kvm_aia.h>
 #include <asm/ptrace.h>
+#include <asm/kvm_tlb.h>
+#include <asm/kvm_vmid.h>
 #include <asm/kvm_vcpu_fp.h>
 #include <asm/kvm_vcpu_insn.h>
 #include <asm/kvm_vcpu_sbi.h>
@@ -37,13 +39,14 @@
 #define KVM_REQ_UPDATE_HGATP		KVM_ARCH_REQ(2)
 #define KVM_REQ_FENCE_I			\
 	KVM_ARCH_REQ_FLAGS(3, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_HFENCE_GVMA_VMID_ALL	KVM_REQ_TLB_FLUSH
 #define KVM_REQ_HFENCE_VVMA_ALL		\
 	KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_HFENCE			\
 	KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(6)
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
 #define KVM_HEDELEG_DEFAULT		(BIT(EXC_INST_MISALIGNED) | \
 					 BIT(EXC_BREAKPOINT)      | \
 					 BIT(EXC_SYSCALL)         | \
@@ -55,24 +58,6 @@
 					 BIT(IRQ_VS_TIMER) | \
 					 BIT(IRQ_VS_EXT))
 
-enum kvm_riscv_hfence_type {
-	KVM_RISCV_HFENCE_UNKNOWN = 0,
-	KVM_RISCV_HFENCE_GVMA_VMID_GPA,
-	KVM_RISCV_HFENCE_VVMA_ASID_GVA,
-	KVM_RISCV_HFENCE_VVMA_ASID_ALL,
-	KVM_RISCV_HFENCE_VVMA_GVA,
-};
-
-struct kvm_riscv_hfence {
-	enum kvm_riscv_hfence_type type;
-	unsigned long asid;
-	unsigned long order;
-	gpa_t addr;
-	gpa_t size;
-};
-
-#define KVM_RISCV_VCPU_MAX_HFENCE	64
-
 struct kvm_vm_stat {
 	struct kvm_vm_stat_generic generic;
 };
@@ -98,15 +83,6 @@ struct kvm_vcpu_stat {
 struct kvm_arch_memory_slot {
 };
 
-struct kvm_vmid {
-	/*
-	 * Writes to vmid_version and vmid happen with vmid_lock held
-	 * whereas reads happen without any lock held.
-	 */
-	unsigned long vmid_version;
-	unsigned long vmid;
-};
-
 struct kvm_arch {
 	/* G-stage vmid */
 	struct kvm_vmid vmid;
@@ -309,77 +285,6 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 
-#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
-
-void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
-					  gpa_t gpa, gpa_t gpsz,
-					  unsigned long order);
-void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid);
-void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
-				     unsigned long order);
-void kvm_riscv_local_hfence_gvma_all(void);
-void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
-					  unsigned long asid,
-					  unsigned long gva,
-					  unsigned long gvsz,
-					  unsigned long order);
-void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
-					  unsigned long asid);
-void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
-				     unsigned long gva, unsigned long gvsz,
-				     unsigned long order);
-void kvm_riscv_local_hfence_vvma_all(unsigned long vmid);
-
-void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu);
-
-void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu);
-void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu);
-void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu);
-void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu);
-
-void kvm_riscv_fence_i(struct kvm *kvm,
-		       unsigned long hbase, unsigned long hmask);
-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);
-void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm,
-				    unsigned long hbase, unsigned long hmask);
-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);
-void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm,
-				    unsigned long hbase, unsigned long hmask,
-				    unsigned long asid);
-void kvm_riscv_hfence_vvma_gva(struct kvm *kvm,
-			       unsigned long hbase, unsigned long hmask,
-			       unsigned long gva, unsigned long gvsz,
-			       unsigned long order);
-void kvm_riscv_hfence_vvma_all(struct kvm *kvm,
-			       unsigned long hbase, unsigned long hmask);
-
-int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa,
-			     phys_addr_t hpa, unsigned long size,
-			     bool writable, bool in_atomic);
-void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa,
-			      unsigned long size);
-int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
-			 struct kvm_memory_slot *memslot,
-			 gpa_t gpa, unsigned long hva, bool is_write);
-int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm);
-void kvm_riscv_gstage_free_pgd(struct kvm *kvm);
-void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu);
-void __init kvm_riscv_gstage_mode_detect(void);
-unsigned long __init kvm_riscv_gstage_mode(void);
-int kvm_riscv_gstage_gpa_bits(void);
-
-void __init kvm_riscv_gstage_vmid_detect(void);
-unsigned long kvm_riscv_gstage_vmid_bits(void);
-int kvm_riscv_gstage_vmid_init(struct kvm *kvm);
-bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid);
-void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu);
-
 int kvm_riscv_setup_default_irq_routing(struct kvm *kvm, u32 lines);
 
 void __kvm_riscv_unpriv_trap(void);

arch/riscv/include/asm/kvm_mmu.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2025 Ventana Micro Systems Inc.
+ */
+
+#ifndef __RISCV_KVM_MMU_H_
+#define __RISCV_KVM_MMU_H_
+
+#include <asm/kvm_gstage.h>
+
+int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
+			  unsigned long size, bool writable, bool in_atomic);
+void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size);
+int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
+		      gpa_t gpa, unsigned long hva, bool is_write,
+		      struct kvm_gstage_mapping *out_map);
+int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm);
+void kvm_riscv_mmu_free_pgd(struct kvm *kvm);
+void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu);
+
+#endif

arch/riscv/include/asm/kvm_tlb.h

@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2025 Ventana Micro Systems Inc.
+ */
+
+#ifndef __RISCV_KVM_TLB_H_
+#define __RISCV_KVM_TLB_H_
+
+#include <linux/kvm_types.h>
+
+enum kvm_riscv_hfence_type {
+	KVM_RISCV_HFENCE_UNKNOWN = 0,
+	KVM_RISCV_HFENCE_GVMA_VMID_GPA,
+	KVM_RISCV_HFENCE_GVMA_VMID_ALL,
+	KVM_RISCV_HFENCE_VVMA_ASID_GVA,
+	KVM_RISCV_HFENCE_VVMA_ASID_ALL,
+	KVM_RISCV_HFENCE_VVMA_GVA,
+	KVM_RISCV_HFENCE_VVMA_ALL
+};
+
+struct kvm_riscv_hfence {
+	enum kvm_riscv_hfence_type type;
+	unsigned long asid;
+	unsigned long vmid;
+	unsigned long order;
+	gpa_t addr;
+	gpa_t size;
+};
+
+#define KVM_RISCV_VCPU_MAX_HFENCE	64
+
+#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
+
+void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
+					  gpa_t gpa, gpa_t gpsz,
+					  unsigned long order);
+void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid);
+void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
+				     unsigned long order);
+void kvm_riscv_local_hfence_gvma_all(void);
+void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
+					  unsigned long asid,
+					  unsigned long gva,
+					  unsigned long gvsz,
+					  unsigned long order);
+void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
+					  unsigned long asid);
+void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
+				     unsigned long gva, unsigned long gvsz,
+				     unsigned long order);
+void kvm_riscv_local_hfence_vvma_all(unsigned long vmid);
+
+void kvm_riscv_tlb_flush_process(struct kvm_vcpu *vcpu);
+
+void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu);
+void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu);
+void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu);
+
+void kvm_riscv_fence_i(struct kvm *kvm,
+		       unsigned long hbase, unsigned long hmask);
+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, unsigned long vmid);
+void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    unsigned long vmid);
+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,
+				    unsigned long vmid);
+void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm,
+				    unsigned long hbase, unsigned long hmask,
+				    unsigned long asid, unsigned long vmid);
+void kvm_riscv_hfence_vvma_gva(struct kvm *kvm,
+			       unsigned long hbase, unsigned long hmask,
+			       unsigned long gva, unsigned long gvsz,
+			       unsigned long order, unsigned long vmid);
+void kvm_riscv_hfence_vvma_all(struct kvm *kvm,
+			       unsigned long hbase, unsigned long hmask,
+			       unsigned long vmid);
+
+#endif

arch/riscv/include/asm/kvm_vmid.h

@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2025 Ventana Micro Systems Inc.
+ */
+
+#ifndef __RISCV_KVM_VMID_H_
+#define __RISCV_KVM_VMID_H_
+
+#include <linux/kvm_types.h>
+
+struct kvm_vmid {
+	/*
+	 * Writes to vmid_version and vmid happen with vmid_lock held
+	 * whereas reads happen without any lock held.
+	 */
+	unsigned long vmid_version;
+	unsigned long vmid;
+};
+
+void __init kvm_riscv_gstage_vmid_detect(void);
+unsigned long kvm_riscv_gstage_vmid_bits(void);
+int kvm_riscv_gstage_vmid_init(struct kvm *kvm);
+bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid);
+void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu);
+void kvm_riscv_gstage_vmid_sanitize(struct kvm_vcpu *vcpu);
+
+#endif