1 files changed, 64 insertions, 57 deletions

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 9826073fbc67..a9e2fd7245e1 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -20,12 +20,12 @@
 #include <asm/pgtable.h>
 
 #ifdef CONFIG_64BIT
-static unsigned long gstage_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT);
-static unsigned long gstage_pgd_levels = 3;
+static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT);
+static unsigned long gstage_pgd_levels __ro_after_init = 3;
 #define gstage_index_bits	9
 #else
-static unsigned long gstage_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT);
-static unsigned long gstage_pgd_levels = 2;
+static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT);
+static unsigned long gstage_pgd_levels __ro_after_init = 2;
 #define gstage_index_bits	10
 #endif
 
@@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 	*ptep_level = current_level;
 	ptep = (pte_t *)kvm->arch.pgd;
 	ptep = &ptep[gstage_pte_index(addr, current_level)];
-	while (ptep && pte_val(*ptep)) {
+	while (ptep && pte_val(ptep_get(ptep))) {
 		if (gstage_pte_leaf(ptep)) {
 			*ptep_level = current_level;
 			*ptepp = ptep;
@@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 		if (current_level) {
 			current_level--;
 			*ptep_level = current_level;
-			ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 			ptep = &ptep[gstage_pte_index(addr, current_level)];
 		} else {
 			ptep = NULL;
@@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kvm, u32 level,
 		if (gstage_pte_leaf(ptep))
 			return -EEXIST;
 
-		if (!pte_val(*ptep)) {
+		if (!pte_val(ptep_get(ptep))) {
 			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));
+			set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)),
+					      __pgprot(_PAGE_TABLE)));
 		} else {
 			if (gstage_pte_leaf(ptep))
 				return -EEXIST;
-			next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		}
 
 		current_level--;
 		ptep = &next_ptep[gstage_pte_index(addr, current_level)];
 	}
 
-	*ptep = *new_pte;
+	set_pte(ptep, *new_pte);
 	if (gstage_pte_leaf(ptep))
 		gstage_remote_tlb_flush(kvm, current_level, addr);
 
@@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 
 	BUG_ON(addr & (page_size - 1));
 
-	if (!pte_val(*ptep))
+	if (!pte_val(ptep_get(ptep)))
 		return;
 
 	if (ptep_level && !gstage_pte_leaf(ptep)) {
-		next_ptep = (pte_t *)gstage_pte_page_vaddr(*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);
@@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr,
 		if (op == GSTAGE_OP_CLEAR)
 			set_pte(ptep, __pte(0));
 		else if (op == GSTAGE_OP_WP)
-			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+			set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE));
 		gstage_remote_tlb_flush(kvm, ptep_level, addr);
 	}
 }
@@ -343,23 +343,24 @@ static void gstage_wp_memory_region(struct kvm *kvm, int slot)
 	kvm_flush_remote_tlbs(kvm);
 }
 
-static int gstage_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_memory_cache pcache;
-
-	memset(&pcache, 0, sizeof(pcache));
-	pcache.gfp_zero = __GFP_ZERO;
+	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);
@@ -382,6 +383,13 @@ out:
 	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,
@@ -398,12 +406,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free)
 {
 }
@@ -517,8 +519,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				goto out;
 			}
 
-			ret = gstage_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;
 		}
@@ -528,10 +531,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (change == KVM_MR_FLAGS_ONLY)
 		goto out;
 
-	spin_lock(&kvm->mmu_lock);
 	if (ret)
-		gstage_unmap_range(kvm, base_gpa, size, false);
-	spin_unlock(&kvm->mmu_lock);
+		kvm_riscv_gstage_iounmap(kvm, base_gpa, size);
 
 out:
 	mmap_read_unlock(current->mm);
@@ -552,7 +553,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	int ret;
-	kvm_pfn_t pfn = pte_pfn(range->pte);
+	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
 
 	if (!kvm->arch.pgd)
 		return false;
@@ -578,7 +579,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.pgd)
 		return false;
 
-	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
 
 	if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT,
 				   &ptep, &ptep_level))
@@ -596,13 +597,13 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.pgd)
 		return false;
 
-	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
 
 	if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT,
 				   &ptep, &ptep_level))
 		return false;
 
-	return pte_young(*ptep);
+	return pte_young(ptep_get(ptep));
 }
 
 int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
@@ -611,7 +612,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 {
 	int ret;
 	kvm_pfn_t hfn;
-	bool writeable;
+	bool writable;
 	short vma_pageshift;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct vm_area_struct *vma;
@@ -621,9 +622,16 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 			!(memslot->flags & KVM_MEM_READONLY)) ? true : false;
 	unsigned long vma_pagesize, mmu_seq;
 
+	/* We need minimum second+third level pages */
+	ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels);
+	if (ret) {
+		kvm_err("Failed to topup G-stage cache\n");
+		return ret;
+	}
+
 	mmap_read_lock(current->mm);
 
-	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	vma = vma_lookup(current->mm, hva);
 	if (unlikely(!vma)) {
 		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
 		mmap_read_unlock(current->mm);
@@ -638,28 +646,28 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 	if (logging || (vma->vm_flags & VM_PFNMAP))
 		vma_pagesize = PAGE_SIZE;
 
-	if (vma_pagesize == PMD_SIZE || vma_pagesize == PGDIR_SIZE)
+	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
 		gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
 
+	/*
+	 * Read mmu_invalidate_seq so that KVM can detect if the results of
+	 * vma_lookup() or gfn_to_pfn_prot() become stale priort to acquiring
+	 * kvm->mmu_lock.
+	 *
+	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
+	 * with the smp_wmb() in kvm_mmu_invalidate_end().
+	 */
+	mmu_seq = kvm->mmu_invalidate_seq;
 	mmap_read_unlock(current->mm);
 
-	if (vma_pagesize != PGDIR_SIZE &&
+	if (vma_pagesize != PUD_SIZE &&
 	    vma_pagesize != PMD_SIZE &&
 	    vma_pagesize != PAGE_SIZE) {
 		kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize);
 		return -EFAULT;
 	}
 
-	/* We need minimum second+third level pages */
-	ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels);
-	if (ret) {
-		kvm_err("Failed to topup G-stage cache\n");
-		return ret;
-	}
-
-	mmu_seq = kvm->mmu_notifier_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);
@@ -673,14 +681,14 @@ int kvm_riscv_gstage_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 = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
@@ -741,8 +749,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu)
 	unsigned long hgatp = gstage_mode;
 	struct kvm_arch *k = &vcpu->kvm->arch;
 
-	hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) &
-		 HGATP_VMID_MASK;
+	hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID;
 	hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;
 
 	csr_write(CSR_HGATP, hgatp);
@@ -751,7 +758,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu)
 		kvm_riscv_local_hfence_gvma_all();
 }
 
-void kvm_riscv_gstage_mode_detect(void)
+void __init kvm_riscv_gstage_mode_detect(void)
 {
 #ifdef CONFIG_64BIT
 	/* Try Sv57x4 G-stage mode */
@@ -775,7 +782,7 @@ skip_sv48x4_test:
 #endif
 }
 
-unsigned long kvm_riscv_gstage_mode(void)
+unsigned long __init kvm_riscv_gstage_mode(void)
 {
 	return gstage_mode >> HGATP_MODE_SHIFT;
 }