RISC-V: KVM: Support runtime configuration for per-VM's HGATP mode

Introduces one per-VM architecture-specific fields to support runtime
configuration of the G-stage page table format:

- kvm->arch.pgd_levels: the corresponding number of page table levels
  for the selected mode.

These fields replace the previous global variables
kvm_riscv_gstage_mode and kvm_riscv_gstage_pgd_levels, enabling different
virtual machines to independently select their G-stage page table format
instead of being forced to share the maximum mode detected by the kernel
at boot time.

Signed-off-by: Fangyu Yu <fangyu.yu@linux.alibaba.com>
Reviewed-by: Andrew Jones <andrew.jones@oss.qualcomm.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Link: https://lore.kernel.org/r/20260403153019.9916-2-fangyu.yu@linux.alibaba.com
Signed-off-by: Anup Patel <anup@brainfault.org>

arch/riscv/include/asm/kvm_gstage.h

@@ -29,16 +29,22 @@ 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;
 
 #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);
@@ -73,4 +79,21 @@ 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;
+	}
+}
+
 #endif

arch/riscv/include/asm/kvm_host.h

@@ -83,6 +83,7 @@ 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 +12,21 @@
 #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
 
 #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->kvm->arch.pgd_levels - 1)
 		mask = (PTRS_PER_PTE * (1UL << kvm_riscv_gstage_pgd_xbits)) - 1;
 	else
 		mask = PTRS_PER_PTE - 1;
@@ -40,12 +39,13 @@ 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->kvm->arch.pgd_levels; i++) {
 		if (page_size == (psz << (i * kvm_riscv_gstage_index_bits))) {
 			*out_level = i;
 			return 0;
@@ -55,21 +55,23 @@ 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->kvm->arch.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 +83,11 @@ 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->kvm->arch.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 +99,7 @@ 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 +112,7 @@ 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 +127,9 @@ 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->kvm->arch.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 +153,7 @@ 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)) {
@@ -194,7 +196,7 @@ 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;
 
@@ -286,7 +288,7 @@ int kvm_riscv_gstage_split_huge(struct kvm_gstage *gstage,
 				struct kvm_mmu_memory_cache *pcache,
 				gpa_t addr, u32 target_level, bool flush)
 {
-	u32 current_level = kvm_riscv_gstage_pgd_levels - 1;
+	u32 current_level = gstage->kvm->arch.pgd_levels - 1;
 	pte_t *next_ptep = (pte_t *)gstage->pgd;
 	unsigned long huge_pte, child_pte;
 	unsigned long child_page_size;
@@ -297,7 +299,7 @@ int kvm_riscv_gstage_split_huge(struct kvm_gstage *gstage,
 		return -ENOMEM;
 
 	while(current_level > target_level) {
-		ptep = (pte_t *)&next_ptep[gstage_pte_index(addr, current_level)];
+		ptep = (pte_t *)&next_ptep[gstage_pte_index(gstage, addr, current_level)];
 
 		if (!pte_val(ptep_get(ptep)))
 			break;
@@ -310,7 +312,7 @@ int kvm_riscv_gstage_split_huge(struct kvm_gstage *gstage,
 
 		huge_pte = pte_val(ptep_get(ptep));
 
-		ret = gstage_level_to_page_size(current_level - 1, &child_page_size);
+		ret = gstage_level_to_page_size(gstage, current_level - 1, &child_page_size);
 		if (ret)
 			return ret;
 
@@ -343,7 +345,7 @@ 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;
 
@@ -355,7 +357,7 @@ 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;
 
@@ -389,7 +391,7 @@ 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;
 
@@ -423,7 +425,7 @@ 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;
 
@@ -444,39 +446,34 @@ void __init kvm_riscv_gstage_mode_detect(void)
 	/* 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;
 		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;
 		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;
 		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;
 		goto done;
 	}
 #endif
 
 	/* KVM depends on !HGATP_MODE_OFF */
-	kvm_riscv_gstage_mode = HGATP_MODE_OFF;
-	kvm_riscv_gstage_pgd_levels = 0;
+	kvm_riscv_gstage_max_pgd_levels = 0;
 
 done:
 	csr_write(CSR_HGATP, 0);

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());
 

arch/riscv/kvm/mmu.c

@@ -67,7 +67,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 		if (!writable)
 			map.pte = pte_wrprotect(map.pte);
 
-		ret = kvm_mmu_topup_memory_cache(&pcache, kvm_riscv_gstage_pgd_levels);
+		ret = kvm_mmu_topup_memory_cache(&pcache, kvm->arch.pgd_levels);
 		if (ret)
 			goto out;
 
@@ -186,7 +186,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * space addressable by the KVM guest GPA space.
 	 */
 	if ((new->base_gfn + new->npages) >=
-	    (kvm_riscv_gstage_gpa_size >> PAGE_SHIFT))
+	     kvm_riscv_gstage_gpa_size(kvm->arch.pgd_levels) >> PAGE_SHIFT)
 		return -EFAULT;
 
 	hva = new->userspace_addr;
@@ -472,7 +472,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	memset(out_map, 0, sizeof(*out_map));
 
 	/* We need minimum second+third level pages */
-	ret = kvm_mmu_topup_memory_cache(pcache, kvm_riscv_gstage_pgd_levels);
+	ret = kvm_mmu_topup_memory_cache(pcache, kvm->arch.pgd_levels);
 	if (ret) {
 		kvm_err("Failed to topup G-stage cache\n");
 		return ret;
@@ -575,6 +575,7 @@ int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm)
 		return -ENOMEM;
 	kvm->arch.pgd = page_to_virt(pgd_page);
 	kvm->arch.pgd_phys = page_to_phys(pgd_page);
+	kvm->arch.pgd_levels = kvm_riscv_gstage_max_pgd_levels;
 
 	return 0;
 }
@@ -590,10 +591,12 @@ void kvm_riscv_mmu_free_pgd(struct kvm *kvm)
 		gstage.flags = 0;
 		gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
 		gstage.pgd = kvm->arch.pgd;
-		kvm_riscv_gstage_unmap_range(&gstage, 0UL, kvm_riscv_gstage_gpa_size, false);
+		kvm_riscv_gstage_unmap_range(&gstage, 0UL,
+			kvm_riscv_gstage_gpa_size(kvm->arch.pgd_levels), false);
 		pgd = READ_ONCE(kvm->arch.pgd);
 		kvm->arch.pgd = NULL;
 		kvm->arch.pgd_phys = 0;
+		kvm->arch.pgd_levels = 0;
 	}
 	spin_unlock(&kvm->mmu_lock);
 
@@ -603,11 +606,12 @@ void kvm_riscv_mmu_free_pgd(struct kvm *kvm)
 
 void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu)
 {
-	unsigned long hgatp = kvm_riscv_gstage_mode << HGATP_MODE_SHIFT;
-	struct kvm_arch *k = &vcpu->kvm->arch;
+	struct kvm_arch *ka = &vcpu->kvm->arch;
+	unsigned long hgatp = kvm_riscv_gstage_mode(ka->pgd_levels)
+			      << HGATP_MODE_SHIFT;
 
-	hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID;
-	hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;
+	hgatp |= (READ_ONCE(ka->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID;
+	hgatp |= (ka->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;
 
 	ncsr_write(CSR_HGATP, hgatp);
 

arch/riscv/kvm/vm.c

@@ -199,7 +199,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_USER_MEM_SLOTS;
 		break;
 	case KVM_CAP_VM_GPA_BITS:
-		r = kvm_riscv_gstage_gpa_bits;
+		if (!kvm)
+			r = kvm_riscv_gstage_gpa_bits(kvm_riscv_gstage_max_pgd_levels);
+		else
+			r = kvm_riscv_gstage_gpa_bits(kvm->arch.pgd_levels);
 		break;
 	default:
 		r = 0;

arch/riscv/kvm/vmid.c

@@ -26,7 +26,8 @@ static DEFINE_SPINLOCK(vmid_lock);
 void __init kvm_riscv_gstage_vmid_detect(void)
 {
 	/* Figure-out number of VMID bits in HW */
-	csr_write(CSR_HGATP, (kvm_riscv_gstage_mode << HGATP_MODE_SHIFT) | HGATP_VMID);
+	csr_write(CSR_HGATP, (kvm_riscv_gstage_mode(kvm_riscv_gstage_max_pgd_levels) <<
+			      HGATP_MODE_SHIFT) | HGATP_VMID);
 	vmid_bits = csr_read(CSR_HGATP);
 	vmid_bits = (vmid_bits & HGATP_VMID) >> HGATP_VMID_SHIFT;
 	vmid_bits = fls_long(vmid_bits);