[PW_SID:1076438] Support runtime configuration for per-VM's HGATP mode

Documentation/virt/kvm/api.rst

@@ -8902,6 +8902,33 @@ helpful if user space wants to emulate instructions which are not
 This capability can be enabled dynamically even if VCPUs were already
 created and are running.
 
+7.47 KVM_CAP_RISCV_SET_HGATP_MODE
+---------------------------------
+
+:Architectures: riscv
+:Type: VM
+:Parameters: args[0] contains the requested HGATP mode
+:Returns:
+  - 0 on success.
+  - -EINVAL if args[0] is outside the range of HGATP modes supported by the
+    hardware.
+  - -EBUSY if vCPUs have already been created for the VM, if the VM has any
+    non-empty memslots.
+
+This capability allows userspace to explicitly select the HGATP mode for
+the VM. The selected mode must be supported by both KVM and hardware. This
+capability must be enabled before creating any vCPUs or memslots.
+
+If this capability is not enabled, KVM will select the default HGATP mode
+automatically. The default is the highest HGATP.MODE value supported by
+hardware.
+
+``KVM_CHECK_EXTENSION(KVM_CAP_RISCV_SET_HGATP_MODE)`` returns a bitmask of
+HGATP.MODE values supported by the host. A return value of 0 indicates that
+the capability is not supported. Supported-mode bitmask use HGATP.MODE
+encodings as defined by the RISC-V privileged specification, such as Sv39x4
+corresponds to HGATP.MODE=8, so userspace should test bitmask & BIT(8).
+
 8. Other capabilities.
 ======================
 

arch/riscv/include/asm/kvm_gstage.h

@@ -15,6 +15,7 @@ struct kvm_gstage {
 #define KVM_GSTAGE_FLAGS_LOCAL		BIT(0)
 	unsigned long vmid;
 	pgd_t *pgd;
+	unsigned long pgd_levels;
 };
 
 struct kvm_gstage_mapping {
@@ -29,16 +30,23 @@ struct kvm_gstage_mapping {
 #define kvm_riscv_gstage_index_bits	10
 #endif
 
-extern unsigned long kvm_riscv_gstage_mode;
-extern unsigned long kvm_riscv_gstage_pgd_levels;
+extern unsigned long kvm_riscv_gstage_max_pgd_levels;
+extern u32 kvm_riscv_gstage_supported_mode_mask;
 
 #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))
+
+static inline unsigned long kvm_riscv_gstage_gpa_bits(unsigned long pgd_levels)
+{
+	return (HGATP_PAGE_SHIFT +
+		pgd_levels * kvm_riscv_gstage_index_bits +
+		kvm_riscv_gstage_pgd_xbits);
+}
+
+static inline gpa_t kvm_riscv_gstage_gpa_size(unsigned long pgd_levels)
+{
+	return BIT_ULL(kvm_riscv_gstage_gpa_bits(pgd_levels));
+}
 
 bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr,
 			       pte_t **ptepp, u32 *ptep_level);
@@ -69,4 +77,40 @@ void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end
 
 void kvm_riscv_gstage_mode_detect(void);
 
+static inline unsigned long kvm_riscv_gstage_mode(unsigned long pgd_levels)
+{
+	switch (pgd_levels) {
+	case 2:
+		return HGATP_MODE_SV32X4;
+	case 3:
+		return HGATP_MODE_SV39X4;
+	case 4:
+		return HGATP_MODE_SV48X4;
+	case 5:
+		return HGATP_MODE_SV57X4;
+	default:
+		WARN_ON_ONCE(1);
+		return HGATP_MODE_OFF;
+	}
+}
+
+static inline void kvm_riscv_gstage_init(struct kvm_gstage *gstage, struct kvm *kvm)
+{
+	gstage->kvm = kvm;
+	gstage->flags = 0;
+	gstage->vmid = READ_ONCE(kvm->arch.vmid.vmid);
+	gstage->pgd = kvm->arch.pgd;
+	gstage->pgd_levels = kvm->arch.pgd_levels;
+}
+
+static inline u32 kvm_riscv_get_hgatp_mode_mask(void)
+{
+	return kvm_riscv_gstage_supported_mode_mask;
+}
+
+static inline bool kvm_riscv_hgatp_mode_is_valid(unsigned long mode)
+{
+	return kvm_riscv_gstage_supported_mode_mask & BIT(mode);
+}
+
 #endif

arch/riscv/include/asm/kvm_host.h

@@ -94,6 +94,7 @@ struct kvm_arch {
 	/* G-stage page table */
 	pgd_t *pgd;
 	phys_addr_t pgd_phys;
+	unsigned long pgd_levels;
 
 	/* Guest Timer */
 	struct kvm_guest_timer timer;

arch/riscv/kvm/gstage.c

@@ -12,22 +12,23 @@
 #include <asm/kvm_gstage.h>
 
 #ifdef CONFIG_64BIT
-unsigned long kvm_riscv_gstage_mode __ro_after_init = HGATP_MODE_SV39X4;
-unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init = 3;
+unsigned long kvm_riscv_gstage_max_pgd_levels __ro_after_init = 3;
 #else
-unsigned long kvm_riscv_gstage_mode __ro_after_init = HGATP_MODE_SV32X4;
-unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init = 2;
+unsigned long kvm_riscv_gstage_max_pgd_levels __ro_after_init = 2;
 #endif
+/* Bitmask of supported HGATP.MODE encodings (BIT(HGATP_MODE_*)). */
+u32 kvm_riscv_gstage_supported_mode_mask __ro_after_init;
 
 #define gstage_pte_leaf(__ptep)	\
 	(pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC))
 
-static inline unsigned long gstage_pte_index(gpa_t addr, u32 level)
+static inline unsigned long gstage_pte_index(struct kvm_gstage *gstage,
+					     gpa_t addr, u32 level)
 {
 	unsigned long mask;
 	unsigned long shift = HGATP_PAGE_SHIFT + (kvm_riscv_gstage_index_bits * level);
 
-	if (level == (kvm_riscv_gstage_pgd_levels - 1))
+	if (level == gstage->pgd_levels - 1)
 		mask = (PTRS_PER_PTE * (1UL << kvm_riscv_gstage_pgd_xbits)) - 1;
 	else
 		mask = PTRS_PER_PTE - 1;
@@ -40,12 +41,13 @@ static inline unsigned long gstage_pte_page_vaddr(pte_t pte)
 	return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte)));
 }
 
-static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level)
+static int gstage_page_size_to_level(struct kvm_gstage *gstage, unsigned long page_size,
+				     u32 *out_level)
 {
 	u32 i;
 	unsigned long psz = 1UL << 12;
 
-	for (i = 0; i < kvm_riscv_gstage_pgd_levels; i++) {
+	for (i = 0; i < gstage->pgd_levels; i++) {
 		if (page_size == (psz << (i * kvm_riscv_gstage_index_bits))) {
 			*out_level = i;
 			return 0;
@@ -55,21 +57,23 @@ static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level)
 	return -EINVAL;
 }
 
-static int gstage_level_to_page_order(u32 level, unsigned long *out_pgorder)
+static int gstage_level_to_page_order(struct kvm_gstage *gstage, u32 level,
+				      unsigned long *out_pgorder)
 {
-	if (kvm_riscv_gstage_pgd_levels < level)
+	if (gstage->pgd_levels < level)
 		return -EINVAL;
 
 	*out_pgorder = 12 + (level * kvm_riscv_gstage_index_bits);
 	return 0;
 }
 
-static int gstage_level_to_page_size(u32 level, unsigned long *out_pgsize)
+static int gstage_level_to_page_size(struct kvm_gstage *gstage, u32 level,
+				     unsigned long *out_pgsize)
 {
 	int rc;
 	unsigned long page_order = PAGE_SHIFT;
 
-	rc = gstage_level_to_page_order(level, &page_order);
+	rc = gstage_level_to_page_order(gstage, level, &page_order);
 	if (rc)
 		return rc;
 
@@ -81,11 +85,11 @@ bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr,
 			       pte_t **ptepp, u32 *ptep_level)
 {
 	pte_t *ptep;
-	u32 current_level = kvm_riscv_gstage_pgd_levels - 1;
+	u32 current_level = gstage->pgd_levels - 1;
 
 	*ptep_level = current_level;
 	ptep = (pte_t *)gstage->pgd;
-	ptep = &ptep[gstage_pte_index(addr, current_level)];
+	ptep = &ptep[gstage_pte_index(gstage, addr, current_level)];
 	while (ptep && pte_val(ptep_get(ptep))) {
 		if (gstage_pte_leaf(ptep)) {
 			*ptep_level = current_level;
@@ -97,7 +101,7 @@ bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr,
 			current_level--;
 			*ptep_level = current_level;
 			ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
-			ptep = &ptep[gstage_pte_index(addr, current_level)];
+			ptep = &ptep[gstage_pte_index(gstage, addr, current_level)];
 		} else {
 			ptep = NULL;
 		}
@@ -110,7 +114,7 @@ static void gstage_tlb_flush(struct kvm_gstage *gstage, u32 level, gpa_t addr)
 {
 	unsigned long order = PAGE_SHIFT;
 
-	if (gstage_level_to_page_order(level, &order))
+	if (gstage_level_to_page_order(gstage, level, &order))
 		return;
 	addr &= ~(BIT(order) - 1);
 
@@ -125,9 +129,9 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
 			     struct kvm_mmu_memory_cache *pcache,
 			     const struct kvm_gstage_mapping *map)
 {
-	u32 current_level = kvm_riscv_gstage_pgd_levels - 1;
+	u32 current_level = gstage->pgd_levels - 1;
 	pte_t *next_ptep = (pte_t *)gstage->pgd;
-	pte_t *ptep = &next_ptep[gstage_pte_index(map->addr, current_level)];
+	pte_t *ptep = &next_ptep[gstage_pte_index(gstage, map->addr, current_level)];
 
 	if (current_level < map->level)
 		return -EINVAL;
@@ -151,7 +155,7 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
 		}
 
 		current_level--;
-		ptep = &next_ptep[gstage_pte_index(map->addr, current_level)];
+		ptep = &next_ptep[gstage_pte_index(gstage, map->addr, current_level)];
 	}
 
 	if (pte_val(*ptep) != pte_val(map->pte)) {
@@ -175,7 +179,7 @@ int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage,
 	out_map->addr = gpa;
 	out_map->level = 0;
 
-	ret = gstage_page_size_to_level(page_size, &out_map->level);
+	ret = gstage_page_size_to_level(gstage, page_size, &out_map->level);
 	if (ret)
 		return ret;
 
@@ -217,7 +221,7 @@ void kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr,
 	u32 next_ptep_level;
 	unsigned long next_page_size, page_size;
 
-	ret = gstage_level_to_page_size(ptep_level, &page_size);
+	ret = gstage_level_to_page_size(gstage, ptep_level, &page_size);
 	if (ret)
 		return;
 
@@ -229,7 +233,7 @@ void kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr,
 	if (ptep_level && !gstage_pte_leaf(ptep)) {
 		next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		next_ptep_level = ptep_level - 1;
-		ret = gstage_level_to_page_size(next_ptep_level, &next_page_size);
+		ret = gstage_level_to_page_size(gstage, next_ptep_level, &next_page_size);
 		if (ret)
 			return;
 
@@ -263,7 +267,7 @@ void kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage,
 
 	while (addr < end) {
 		found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level);
-		ret = gstage_level_to_page_size(ptep_level, &page_size);
+		ret = gstage_level_to_page_size(gstage, ptep_level, &page_size);
 		if (ret)
 			break;
 
@@ -297,7 +301,7 @@ void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end
 
 	while (addr < end) {
 		found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level);
-		ret = gstage_level_to_page_size(ptep_level, &page_size);
+		ret = gstage_level_to_page_size(gstage, ptep_level, &page_size);
 		if (ret)
 			break;
 
@@ -315,44 +319,46 @@ void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end
 
 void __init kvm_riscv_gstage_mode_detect(void)
 {
+	kvm_riscv_gstage_supported_mode_mask = 0;
+	kvm_riscv_gstage_max_pgd_levels = 0;
+
 #ifdef CONFIG_64BIT
 	/* 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) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV57X4;
-		kvm_riscv_gstage_pgd_levels = 5;
+		kvm_riscv_gstage_max_pgd_levels = 5;
+		kvm_riscv_gstage_supported_mode_mask |= BIT(HGATP_MODE_SV57X4) |
+							BIT(HGATP_MODE_SV48X4) |
+							BIT(HGATP_MODE_SV39X4);
 		goto done;
 	}
 
 	/* 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) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV48X4;
-		kvm_riscv_gstage_pgd_levels = 4;
+		kvm_riscv_gstage_max_pgd_levels = 4;
+		kvm_riscv_gstage_supported_mode_mask |= BIT(HGATP_MODE_SV48X4) |
+							BIT(HGATP_MODE_SV39X4);
 		goto done;
 	}
 
 	/* Try Sv39x4 G-stage mode */
 	csr_write(CSR_HGATP, HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT);
 	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV39X4) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV39X4;
-		kvm_riscv_gstage_pgd_levels = 3;
+		kvm_riscv_gstage_max_pgd_levels = 3;
+		kvm_riscv_gstage_supported_mode_mask |= BIT(HGATP_MODE_SV39X4);
 		goto done;
 	}
 #else /* CONFIG_32BIT */
 	/* Try Sv32x4 G-stage mode */
 	csr_write(CSR_HGATP, HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT);
 	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV32X4) {
-		kvm_riscv_gstage_mode = HGATP_MODE_SV32X4;
-		kvm_riscv_gstage_pgd_levels = 2;
+		kvm_riscv_gstage_max_pgd_levels = 2;
+		kvm_riscv_gstage_supported_mode_mask |= BIT(HGATP_MODE_SV32X4);
 		goto done;
 	}
 #endif
 
-	/* KVM depends on !HGATP_MODE_OFF */
-	kvm_riscv_gstage_mode = HGATP_MODE_OFF;
-	kvm_riscv_gstage_pgd_levels = 0;
-
 done:
 	csr_write(CSR_HGATP, 0);
 	kvm_riscv_local_hfence_gvma_all();

arch/riscv/kvm/main.c

@@ -105,17 +105,17 @@ static int __init riscv_kvm_init(void)
 		return rc;
 
 	kvm_riscv_gstage_mode_detect();
-	switch (kvm_riscv_gstage_mode) {
-	case HGATP_MODE_SV32X4:
+	switch (kvm_riscv_gstage_max_pgd_levels) {
+	case 2:
 		str = "Sv32x4";
 		break;
-	case HGATP_MODE_SV39X4:
+	case 3:
 		str = "Sv39x4";
 		break;
-	case HGATP_MODE_SV48X4:
+	case 4:
 		str = "Sv48x4";
 		break;
-	case HGATP_MODE_SV57X4:
+	case 5:
 		str = "Sv57x4";
 		break;
 	default:
@@ -164,7 +164,7 @@ static int __init riscv_kvm_init(void)
 			 (rc) ? slist : "no features");
 	}
 
-	kvm_info("using %s G-stage page table format\n", str);
+	kvm_info("highest G-stage page table mode is %s\n", str);
 
 	kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits());