Linux-RISC-V Archive on lore.kernel.org
 help / color / Atom feed
From: Anup Patel <Anup.Patel@wdc.com>
To: Palmer Dabbelt <palmer@sifive.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Paolo Bonzini <pbonzini@redhat.com>, Radim K <rkrcmar@redhat.com>
Cc: Damien Le Moal <Damien.LeMoal@wdc.com>,
	Anup Patel <Anup.Patel@wdc.com>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	Anup Patel <anup@brainfault.org>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Christoph Hellwig <hch@infradead.org>,
	Atish Patra <Atish.Patra@wdc.com>,
	Alexander Graf <graf@amazon.com>,
	Alistair Francis <Alistair.Francis@wdc.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	"linux-riscv@lists.infradead.org"
	<linux-riscv@lists.infradead.org>
Subject: [PATCH v8 11/19] RISC-V: KVM: Implement stage2 page table programming
Date: Thu, 3 Oct 2019 05:07:54 +0000
Message-ID: <20191003050558.9031-12-anup.patel@wdc.com> (raw)
In-Reply-To: <20191003050558.9031-1-anup.patel@wdc.com>

This patch implements all required functions for programming
the stage2 page table for each Guest/VM.

At high-level, the flow of stage2 related functions is similar
from KVM ARM/ARM64 implementation but the stage2 page table
format is quite different for KVM RISC-V.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/riscv/include/asm/kvm_host.h     |  10 +
 arch/riscv/include/asm/pgtable-bits.h |   1 +
 arch/riscv/kvm/mmu.c                  | 643 +++++++++++++++++++++++++-
 3 files changed, 644 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 8aaf22a900be..bc27f664b443 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -73,6 +73,13 @@ struct kvm_mmio_decode {
 	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_context {
 	unsigned long zero;
 	unsigned long ra;
@@ -164,6 +171,9 @@ struct kvm_vcpu_arch {
 	/* MMIO instruction details */
 	struct kvm_mmio_decode mmio_decode;
 
+	/* Cache pages needed to program page tables with spinlock held */
+	struct kvm_mmu_page_cache mmu_page_cache;
+
 	/* VCPU power-off state */
 	bool power_off;
 
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index bbaeb5d35842..be49d62fcc2b 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -26,6 +26,7 @@
 
 #define _PAGE_SPECIAL   _PAGE_SOFT
 #define _PAGE_TABLE     _PAGE_PRESENT
+#define _PAGE_LEAF      (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 
 /*
  * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 2b965f9aac07..590669290139 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -18,6 +18,438 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
+#ifdef CONFIG_64BIT
+#define stage2_have_pmd		true
+#define stage2_gpa_size		((phys_addr_t)(1ULL << 39))
+#define stage2_cache_min_pages	2
+#else
+#define pmd_index(x)		0
+#define pfn_pmd(x, y)		({ pmd_t __x = { 0 }; __x; })
+#define stage2_have_pmd		false
+#define stage2_gpa_size		((phys_addr_t)(1ULL << 32))
+#define stage2_cache_min_pages	1
+#endif
+
+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;
+}
+
+struct local_guest_tlb_info {
+	struct kvm_vmid *vmid;
+	gpa_t addr;
+};
+
+static void local_guest_tlb_flush_vmid_gpa(void *info)
+{
+	struct local_guest_tlb_info *infop = info;
+
+	__kvm_riscv_hfence_gvma_vmid_gpa(READ_ONCE(infop->vmid->vmid_version),
+					 infop->addr);
+}
+
+static void stage2_remote_tlb_flush(struct kvm *kvm, gpa_t addr)
+{
+	struct local_guest_tlb_info info;
+	struct kvm_vmid *vmid = &kvm->arch.vmid;
+
+	/*
+	 * Ideally, we should have a SBI call OR some remote TLB instruction
+	 * but we don't have it so we explicitly flush TLBs using IPIs.
+	 *
+	 * TODO: Instead of cpu_online_mask, we should only target CPUs
+	 * where the Guest/VM is running.
+	 */
+	info.vmid = vmid;
+	info.addr = addr;
+	preempt_disable();
+	smp_call_function_many(cpu_online_mask,
+			       local_guest_tlb_flush_vmid_gpa, &info, true);
+	preempt_enable();
+}
+
+static int stage2_set_pgd(struct kvm *kvm, gpa_t addr, const pgd_t *new_pgd)
+{
+	pgd_t *pgdp = &kvm->arch.pgd[pgd_index(addr)];
+
+	*pgdp = *new_pgd;
+	if (pgd_val(*pgdp) & _PAGE_LEAF)
+		stage2_remote_tlb_flush(kvm, addr);
+
+	return 0;
+}
+
+static int stage2_set_pmd(struct kvm *kvm, struct kvm_mmu_page_cache *pcache,
+			  gpa_t addr, const pmd_t *new_pmd)
+{
+	int rc;
+	pmd_t *pmdp;
+	pgd_t new_pgd;
+	pgd_t *pgdp = &kvm->arch.pgd[pgd_index(addr)];
+
+	if (!pgd_val(*pgdp)) {
+		pmdp = stage2_cache_alloc(pcache);
+		if (!pmdp)
+			return -ENOMEM;
+		new_pgd = pfn_pgd(PFN_DOWN(__pa(pmdp)), __pgprot(_PAGE_TABLE));
+		rc = stage2_set_pgd(kvm, addr, &new_pgd);
+		if (rc)
+			return rc;
+	}
+
+	if (pgd_val(*pgdp) & _PAGE_LEAF)
+		return -EEXIST;
+
+	pmdp = (void *)pgd_page_vaddr(*pgdp);
+	pmdp = &pmdp[pmd_index(addr)];
+
+	*pmdp = *new_pmd;
+	if (pmd_val(*pmdp) & _PAGE_LEAF)
+		stage2_remote_tlb_flush(kvm, addr);
+
+	return 0;
+}
+
+static int stage2_set_pte(struct kvm *kvm,
+			  struct kvm_mmu_page_cache *pcache,
+			  gpa_t addr, const pte_t *new_pte)
+{
+	int rc;
+	pte_t *ptep;
+	pmd_t new_pmd;
+	pmd_t *pmdp;
+	pgd_t new_pgd;
+	pgd_t *pgdp = &kvm->arch.pgd[pgd_index(addr)];
+
+	if (!pgd_val(*pgdp)) {
+		pmdp = stage2_cache_alloc(pcache);
+		if (!pmdp)
+			return -ENOMEM;
+		new_pgd = pfn_pgd(PFN_DOWN(__pa(pmdp)), __pgprot(_PAGE_TABLE));
+		rc = stage2_set_pgd(kvm, addr, &new_pgd);
+		if (rc)
+			return rc;
+	}
+
+	if (pgd_val(*pgdp) & _PAGE_LEAF)
+		return -EEXIST;
+
+	if (stage2_have_pmd) {
+		pmdp = (void *)pgd_page_vaddr(*pgdp);
+		pmdp = &pmdp[pmd_index(addr)];
+		if (!pmd_present(*pmdp)) {
+			ptep = stage2_cache_alloc(pcache);
+			if (!ptep)
+				return -ENOMEM;
+			new_pmd = pfn_pmd(PFN_DOWN(__pa(ptep)),
+					  __pgprot(_PAGE_TABLE));
+			rc = stage2_set_pmd(kvm, pcache, addr, &new_pmd);
+			if (rc)
+				return rc;
+		}
+
+		if (pmd_val(*pmdp) & _PAGE_LEAF)
+			return -EEXIST;
+
+		ptep = (void *)pmd_page_vaddr(*pmdp);
+	} else {
+		ptep = (void *)pgd_page_vaddr(*pgdp);
+	}
+
+	ptep = &ptep[pte_index(addr)];
+
+	*ptep = *new_pte;
+	if (pte_val(*ptep) & _PAGE_LEAF)
+		stage2_remote_tlb_flush(kvm, addr);
+
+	return 0;
+}
+
+static int stage2_map_page(struct kvm *kvm,
+			   struct kvm_mmu_page_cache *pcache,
+			   gpa_t gpa, phys_addr_t hpa,
+			   unsigned long page_size, pgprot_t prot)
+{
+	pte_t new_pte;
+	pmd_t new_pmd;
+	pgd_t new_pgd;
+
+	if (page_size == PAGE_SIZE) {
+		new_pte = pfn_pte(PFN_DOWN(hpa), prot);
+		return stage2_set_pte(kvm, pcache, gpa, &new_pte);
+	}
+
+	if (stage2_have_pmd && page_size == PMD_SIZE) {
+		new_pmd = pfn_pmd(PFN_DOWN(hpa), prot);
+		return stage2_set_pmd(kvm, pcache, gpa, &new_pmd);
+	}
+
+	if (page_size == PGDIR_SIZE) {
+		new_pgd = pfn_pgd(PFN_DOWN(hpa), prot);
+		return stage2_set_pgd(kvm, gpa, &new_pgd);
+	}
+
+	return -EINVAL;
+}
+
+enum stage2_op {
+	STAGE2_OP_NOP = 0,	/* Nothing */
+	STAGE2_OP_CLEAR,	/* Clear/Unmap */
+	STAGE2_OP_WP,		/* Write-protect */
+};
+
+static void stage2_op_pte(struct kvm *kvm, gpa_t addr, pte_t *ptep,
+			  enum stage2_op op)
+{
+	BUG_ON(addr & (PAGE_SIZE - 1));
+
+	if (!pte_present(*ptep))
+		return;
+
+	if (op == STAGE2_OP_CLEAR)
+		set_pte(ptep, __pte(0));
+	else if (op == STAGE2_OP_WP)
+		set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+	stage2_remote_tlb_flush(kvm, addr);
+}
+
+static void stage2_op_pmd(struct kvm *kvm, gpa_t addr, pmd_t *pmdp,
+			  enum stage2_op op)
+{
+	int i;
+	pte_t *ptep;
+
+	BUG_ON(addr & (PMD_SIZE - 1));
+
+	if (!pmd_present(*pmdp))
+		return;
+
+	if (pmd_val(*pmdp) & _PAGE_LEAF)
+		ptep = NULL;
+	else
+		ptep = (pte_t *)pmd_page_vaddr(*pmdp);
+
+	if (op == STAGE2_OP_CLEAR)
+		set_pmd(pmdp, __pmd(0));
+
+	if (ptep) {
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			stage2_op_pte(kvm, addr + i * PAGE_SIZE, &ptep[i], op);
+		if (op == STAGE2_OP_CLEAR)
+			put_page(virt_to_page(ptep));
+	} else {
+		if (op == STAGE2_OP_WP)
+			set_pmd(pmdp, __pmd(pmd_val(*pmdp) & ~_PAGE_WRITE));
+		stage2_remote_tlb_flush(kvm, addr);
+	}
+}
+
+static void stage2_op_pgd(struct kvm *kvm, gpa_t addr, pgd_t *pgdp,
+			  enum stage2_op op)
+{
+	int i;
+	pte_t *ptep;
+	pmd_t *pmdp;
+
+	BUG_ON(addr & (PGDIR_SIZE - 1));
+
+	if (!pgd_val(*pgdp))
+		return;
+
+	ptep = NULL;
+	pmdp = NULL;
+	if (!(pgd_val(*pgdp) & _PAGE_LEAF)) {
+		if (stage2_have_pmd)
+			pmdp = (pmd_t *)pgd_page_vaddr(*pgdp);
+		else
+			ptep = (pte_t *)pgd_page_vaddr(*pgdp);
+	}
+
+	if (op == STAGE2_OP_CLEAR)
+		set_pgd(pgdp, __pgd(0));
+
+	if (pmdp) {
+		for (i = 0; i < PTRS_PER_PMD; i++)
+			stage2_op_pmd(kvm, addr + i * PMD_SIZE, &pmdp[i], op);
+		if (op == STAGE2_OP_CLEAR)
+			put_page(virt_to_page(pmdp));
+	} else if (ptep) {
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			stage2_op_pte(kvm, addr + i * PAGE_SIZE, &ptep[i], op);
+		if (op == STAGE2_OP_CLEAR)
+			put_page(virt_to_page(ptep));
+	} else {
+		if (op == STAGE2_OP_WP)
+			set_pgd(pgdp, __pgd(pgd_val(*pgdp) & ~_PAGE_WRITE));
+		stage2_remote_tlb_flush(kvm, addr);
+	}
+}
+
+static void stage2_unmap_range(struct kvm *kvm, gpa_t start, gpa_t size)
+{
+	pmd_t *pmdp;
+	pte_t *ptep;
+	pgd_t *pgdp;
+	gpa_t addr = start, end = start + size;
+
+	while (addr < end) {
+		pgdp = &kvm->arch.pgd[pgd_index(addr)];
+		if (!pgd_val(*pgdp)) {
+			addr += PGDIR_SIZE;
+			continue;
+		} else if (!(addr & (PGDIR_SIZE - 1)) &&
+			  ((end - addr) >= PGDIR_SIZE)) {
+			stage2_op_pgd(kvm, addr, pgdp, STAGE2_OP_CLEAR);
+			addr += PGDIR_SIZE;
+			continue;
+		}
+
+		if (stage2_have_pmd) {
+			pmdp = (pmd_t *)pgd_page_vaddr(*pgdp);
+			if (!pmd_present(*pmdp)) {
+				addr += PMD_SIZE;
+				continue;
+			} else if (!(addr & (PMD_SIZE - 1)) &&
+				   ((end - addr) >= PMD_SIZE)) {
+				stage2_op_pmd(kvm, addr, pmdp,
+					      STAGE2_OP_CLEAR);
+				addr += PMD_SIZE;
+				continue;
+			}
+			ptep = (pte_t *)pmd_page_vaddr(*pmdp);
+		} else {
+			ptep = (pte_t *)pgd_page_vaddr(*pgdp);
+		}
+
+		stage2_op_pte(kvm, addr, ptep, STAGE2_OP_CLEAR);
+		addr += PAGE_SIZE;
+	}
+}
+
+static void stage2_wp_range(struct kvm *kvm, gpa_t start, gpa_t end)
+{
+	pmd_t *pmdp;
+	pte_t *ptep;
+	pgd_t *pgdp;
+	gpa_t addr = start;
+
+	while (addr < end) {
+		pgdp = &kvm->arch.pgd[pgd_index(addr)];
+		if (!pgd_val(*pgdp)) {
+			addr += PGDIR_SIZE;
+			continue;
+		} else if (!(addr & (PGDIR_SIZE - 1)) &&
+			   ((end - addr) >= PGDIR_SIZE)) {
+			stage2_op_pgd(kvm, addr, pgdp, STAGE2_OP_WP);
+			addr += PGDIR_SIZE;
+			continue;
+		}
+
+		if (stage2_have_pmd) {
+			pmdp = (pmd_t *)pgd_page_vaddr(*pgdp);
+			if (!pmd_present(*pmdp)) {
+				addr += PMD_SIZE;
+				continue;
+			} else if (!(addr & (PMD_SIZE - 1)) &&
+				   ((end - addr) >= PMD_SIZE)) {
+				stage2_op_pmd(kvm, addr, pmdp, STAGE2_OP_WP);
+				addr += PMD_SIZE;
+				continue;
+			}
+			ptep = (pte_t *)pmd_page_vaddr(*pmdp);
+		} else {
+			ptep = (pte_t *)pgd_page_vaddr(*pgdp);
+		}
+
+		stage2_op_pte(kvm, addr, ptep, STAGE2_OP_WP);
+		addr += PAGE_SIZE;
+	}
+}
+
+void stage2_wp_memory_region(struct kvm *kvm, int slot)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
+	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_wp_range(kvm, start, end);
+	spin_unlock(&kvm->mmu_lock);
+	kvm_flush_remote_tlbs(kvm);
+}
+
+int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
+		   unsigned long size, bool writable)
+{
+	pte_t pte;
+	int ret = 0;
+	unsigned long pfn;
+	phys_addr_t addr, end;
+	struct kvm_mmu_page_cache pcache = { 0, };
+
+	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);
+
+		if (!writable)
+			pte = pte_wrprotect(pte);
+
+		ret = stage2_cache_topup(&pcache,
+					 stage2_cache_min_pages,
+					 KVM_MMU_PAGE_CACHE_NR_OBJS);
+		if (ret)
+			goto out;
+
+		spin_lock(&kvm->mmu_lock);
+		ret = stage2_set_pte(kvm, &pcache, addr, &pte);
+		spin_unlock(&kvm->mmu_lock);
+		if (ret)
+			goto out;
+
+		pfn++;
+	}
+
+out:
+	stage2_cache_flush(&pcache);
+	return ret;
+
+}
+
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
@@ -35,7 +467,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	/* TODO: */
+	kvm_riscv_stage2_free_pgd(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -49,7 +481,13 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	/* TODO: */
+	/*
+	 * At this point memslot has been committed and there is an
+	 * allocated dirty_bitmap[], dirty pages will be be tracked while the
+	 * memory slot is write protected.
+	 */
+	if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES)
+		stage2_wp_memory_region(kvm, mem->slot);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -57,34 +495,219 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
-	/* TODO: */
-	return 0;
+	hva_t hva = mem->userspace_addr;
+	hva_t reg_end = hva + mem->memory_size;
+	bool writable = !(mem->flags & KVM_MEM_READONLY);
+	int ret = 0;
+
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
+			change != KVM_MR_FLAGS_ONLY)
+		return 0;
+
+	/*
+	 * Prevent userspace from creating a memory region outside of the GPA
+	 * space addressable by the KVM guest GPA space.
+	 */
+	if ((memslot->base_gfn + memslot->npages) >=
+	    (stage2_gpa_size >> PAGE_SHIFT))
+		return -EFAULT;
+
+	down_read(&current->mm->mmap_sem);
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and
+	 * any holes between them, so iterate over all of them to find
+	 * out if we can map any of them right now.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Mapping a read-only VMA is only allowed if the
+		 * memory region is configured as read-only.
+		 */
+		if (writable && !(vma->vm_flags & VM_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/* Take the intersection of this VMA with the memory region */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (vma->vm_flags & VM_PFNMAP) {
+			gpa_t gpa = mem->guest_phys_addr +
+				    (vm_start - mem->userspace_addr);
+			phys_addr_t pa;
+
+			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+			pa += vm_start - vma->vm_start;
+
+			/* IO region dirty page logging not allowed */
+			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ret = stage2_ioremap(kvm, gpa, pa,
+					     vm_end - vm_start, writable);
+			if (ret)
+				break;
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+
+	if (change == KVM_MR_FLAGS_ONLY)
+		goto out;
+
+	spin_lock(&kvm->mmu_lock);
+	if (ret)
+		stage2_unmap_range(kvm, mem->guest_phys_addr,
+				   mem->memory_size);
+	spin_unlock(&kvm->mmu_lock);
+
+out:
+	up_read(&current->mm->mmap_sem);
+	return ret;
 }
 
 int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
 			 bool is_write)
 {
-	/* TODO: */
-	return 0;
+	int ret;
+	short lsb;
+	kvm_pfn_t hfn;
+	bool writeable;
+	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;
+	unsigned long vma_pagesize;
+
+	down_read(&current->mm->mmap_sem);
+
+	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (unlikely(!vma)) {
+		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+		up_read(&current->mm->mmap_sem);
+		return -EFAULT;
+	}
+
+	vma_pagesize = vma_kernel_pagesize(vma);
+
+	up_read(&current->mm->mmap_sem);
+
+	if (vma_pagesize != PGDIR_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 = stage2_cache_topup(pcache, stage2_cache_min_pages,
+				 KVM_MMU_PAGE_CACHE_NR_OBJS);
+	if (ret) {
+		kvm_err("Failed to topup stage2 cache\n");
+		return ret;
+	}
+
+	hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writeable);
+	if (hfn == KVM_PFN_ERR_HWPOISON) {
+		if (is_vm_hugetlb_page(vma))
+			lsb = huge_page_shift(hstate_vma(vma));
+		else
+			lsb = PAGE_SHIFT;
+
+		send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva,
+				lsb, current);
+		return 0;
+	}
+	if (is_error_noslot_pfn(hfn))
+		return -EFAULT;
+	if (!writeable && is_write)
+		return -EPERM;
+
+	spin_lock(&kvm->mmu_lock);
+
+	if (writeable) {
+		kvm_set_pfn_dirty(hfn);
+		ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
+				      vma_pagesize, PAGE_WRITE_EXEC);
+	} else {
+		ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
+				      vma_pagesize, PAGE_READ_EXEC);
+	}
+
+	if (ret)
+		kvm_err("Failed to map in stage2\n");
+
+	spin_unlock(&kvm->mmu_lock);
+	kvm_set_pfn_accessed(hfn);
+	kvm_release_pfn_clean(hfn);
+	return ret;
 }
 
 void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
+	stage2_cache_flush(&vcpu->arch.mmu_page_cache);
 }
 
 int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm)
 {
-	/* TODO: */
+	if (kvm->arch.pgd != NULL) {
+		kvm_err("kvm_arch already initialized?\n");
+		return -EINVAL;
+	}
+
+	kvm->arch.pgd = alloc_pages_exact(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
+	if (!kvm->arch.pgd)
+		return -ENOMEM;
+	kvm->arch.pgd_phys = virt_to_phys(kvm->arch.pgd);
+
 	return 0;
 }
 
 void kvm_riscv_stage2_free_pgd(struct kvm *kvm)
 {
-	/* TODO: */
+	void *pgd = NULL;
+
+	spin_lock(&kvm->mmu_lock);
+	if (kvm->arch.pgd) {
+		stage2_unmap_range(kvm, 0UL, stage2_gpa_size);
+		pgd = READ_ONCE(kvm->arch.pgd);
+		kvm->arch.pgd = NULL;
+		kvm->arch.pgd_phys = 0;
+	}
+	spin_unlock(&kvm->mmu_lock);
+
+	/* Free the HW pgd, one page at a time */
+	if (pgd)
+		free_pages_exact(pgd, PAGE_SIZE);
 }
 
 void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
+	unsigned long hgatp = HGATP_MODE;
+	struct kvm_arch *k = &vcpu->kvm->arch;
+
+	hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) &
+		 HGATP_VMID_MASK;
+	hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;
+
+	csr_write(CSR_HGATP, hgatp);
+
+	if (!kvm_riscv_stage2_vmid_bits())
+		__kvm_riscv_hfence_gvma_all();
 }
-- 
2.17.1


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

  parent reply index

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-03  5:06 [PATCH v8 00/19] KVM RISC-V Support Anup Patel
2019-10-03  5:06 ` [PATCH v8 01/19] RISC-V: Add bitmap reprensenting ISA features common across CPUs Anup Patel
2019-10-03  5:06 ` [PATCH v8 02/19] RISC-V: Add hypervisor extension related CSR defines Anup Patel
2019-10-03  5:06 ` [PATCH v8 03/19] RISC-V: Add initial skeletal KVM support Anup Patel
2019-10-03  5:07 ` [PATCH v8 04/19] RISC-V: KVM: Implement VCPU create, init and destroy functions Anup Patel
2019-10-03  5:07 ` [PATCH v8 05/19] RISC-V: KVM: Implement VCPU interrupts and requests handling Anup Patel
2019-10-03  5:07 ` [PATCH v8 06/19] RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls Anup Patel
2019-10-03  5:07 ` [PATCH v8 07/19] RISC-V: KVM: Implement VCPU world-switch Anup Patel
2019-10-03  5:07 ` [PATCH v8 08/19] RISC-V: KVM: Handle MMIO exits for VCPU Anup Patel
2019-10-03 10:18   ` Paolo Bonzini
2019-10-03  5:07 ` [PATCH v8 09/19] RISC-V: KVM: Handle WFI " Anup Patel
2019-10-03  5:07 ` [PATCH v8 10/19] RISC-V: KVM: Implement VMID allocator Anup Patel
2019-10-03  5:07 ` Anup Patel [this message]
2019-10-03  5:08 ` [PATCH v8 12/19] RISC-V: KVM: Implement MMU notifiers Anup Patel
2019-10-03  5:08 ` [PATCH v8 13/19] RISC-V: KVM: Add timer functionality Anup Patel
2019-10-03  5:08 ` [PATCH v8 14/19] RISC-V: KVM: FP lazy save/restore Anup Patel
2019-10-03  5:08 ` [PATCH v8 15/19] RISC-V: KVM: Implement ONE REG interface for FP registers Anup Patel
2019-10-03  5:08 ` [PATCH v8 16/19] RISC-V: KVM: Add SBI v0.1 support Anup Patel
2019-10-03  5:08 ` [PATCH v8 17/19] RISC-V: KVM: Forward unhandled SBI calls to userspace Anup Patel
2019-10-03  5:08 ` [PATCH v8 18/19] RISC-V: KVM: Document RISC-V specific parts of KVM API Anup Patel
2019-10-03  5:08 ` [PATCH v8 19/19] RISC-V: KVM: Add MAINTAINERS entry Anup Patel

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191003050558.9031-12-anup.patel@wdc.com \
    --to=anup.patel@wdc.com \
    --cc=Alistair.Francis@wdc.com \
    --cc=Atish.Patra@wdc.com \
    --cc=Damien.LeMoal@wdc.com \
    --cc=anup@brainfault.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=graf@amazon.com \
    --cc=hch@infradead.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@sifive.com \
    --cc=paul.walmsley@sifive.com \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-RISC-V Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-riscv/0 linux-riscv/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-riscv linux-riscv/ https://lore.kernel.org/linux-riscv \
		linux-riscv@lists.infradead.org
	public-inbox-index linux-riscv

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-riscv


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git