[v3,15/33] KVM: PPC: Book3S HV: Refactor radix page fault handler

Commit Message

Paul Mackerras Oct. 2, 2018, 11:31 a.m. UTC

From: Suraj Jitindar Singh <[e-mail]>

The radix page fault handler accounts for all cases, including just
needing to insert a pte.  This breaks it up into separate functions for
the two main cases; setting rc and inserting a pte.

This allows us to make the setting of rc and inserting of a pte
generic for any pgtable, not specific to the one for this guest.

[[e-mail] - reduced diffs from previous code]

Reviewed-by: David Gibson <[e-mail]>
Signed-off-by: Suraj Jitindar Singh <[e-mail]>
Signed-off-by: Paul Mackerras <[e-mail]>
---
 arch/powerpc/kvm/book3s_64_mmu_radix.c | 210 +++++++++++++++++++--------------
 1 file changed, 123 insertions(+), 87 deletions(-)

Patch

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index f2976f4..47f2b18 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -400,8 +400,9 @@  static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
  */
 #define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
 
-static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
-			     unsigned int level, unsigned long mmu_seq)
+static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
+			     unsigned long gpa, unsigned int level,
+			     unsigned long mmu_seq)
 {
 	pgd_t *pgd;
 	pud_t *pud, *new_pud = NULL;
@@ -410,7 +411,7 @@  static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	int ret;
 
 	/* Traverse the guest's 2nd-level tree, allocate new levels needed */
-	pgd = kvm->arch.pgtable + pgd_index(gpa);
+	pgd = pgtable + pgd_index(gpa);
 	pud = NULL;
 	if (pgd_present(*pgd))
 		pud = pud_offset(pgd, gpa);
@@ -565,95 +566,49 @@  static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	return ret;
 }
 
-int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
-				   unsigned long ea, unsigned long dsisr)
+static bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
+				    bool writing, unsigned long gpa)
+{
+	unsigned long pgflags;
+	unsigned int shift;
+	pte_t *ptep;
+
+	/*
+	 * Need to set an R or C bit in the 2nd-level tables;
+	 * since we are just helping out the hardware here,
+	 * it is sufficient to do what the hardware does.
+	 */
+	pgflags = _PAGE_ACCESSED;
+	if (writing)
+		pgflags |= _PAGE_DIRTY;
+	/*
+	 * We are walking the secondary (partition-scoped) page table here.
+	 * We can do this without disabling irq because the Linux MM
+	 * subsystem doesn't do THP splits and collapses on this tree.
+	 */
+	ptep = __find_linux_pte(pgtable, gpa, NULL, &shift);
+	if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
+		kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
+		return true;
+	}
+	return false;
+}
+
+static int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+				unsigned long gpa,
+				struct kvm_memory_slot *memslot,
+				bool writing, bool kvm_ro,
+				pte_t *inserted_pte, unsigned int *levelp)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long mmu_seq;
-	unsigned long gpa, gfn, hva;
-	struct kvm_memory_slot *memslot;
 	struct page *page = NULL;
-	long ret;
-	bool writing;
+	unsigned long mmu_seq;
+	unsigned long hva, gfn = gpa >> PAGE_SHIFT;
 	bool upgrade_write = false;
 	bool *upgrade_p = &upgrade_write;
 	pte_t pte, *ptep;
-	unsigned long pgflags;
 	unsigned int shift, level;
-
-	/* Check for unusual errors */
-	if (dsisr & DSISR_UNSUPP_MMU) {
-		pr_err("KVM: Got unsupported MMU fault\n");
-		return -EFAULT;
-	}
-	if (dsisr & DSISR_BADACCESS) {
-		/* Reflect to the guest as DSI */
-		pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
-		kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
-		return RESUME_GUEST;
-	}
-
-	/* Translate the logical address and get the page */
-	gpa = vcpu->arch.fault_gpa & ~0xfffUL;
-	gpa &= ~0xF000000000000000ul;
-	gfn = gpa >> PAGE_SHIFT;
-	if (!(dsisr & DSISR_PRTABLE_FAULT))
-		gpa |= ea & 0xfff;
-	memslot = gfn_to_memslot(kvm, gfn);
-
-	/* No memslot means it's an emulated MMIO region */
-	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
-		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
-			     DSISR_SET_RC)) {
-			/*
-			 * Bad address in guest page table tree, or other
-			 * unusual error - reflect it to the guest as DSI.
-			 */
-			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
-			return RESUME_GUEST;
-		}
-		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
-					      dsisr & DSISR_ISSTORE);
-	}
-
-	writing = (dsisr & DSISR_ISSTORE) != 0;
-	if (memslot->flags & KVM_MEM_READONLY) {
-		if (writing) {
-			/* give the guest a DSI */
-			dsisr = DSISR_ISSTORE | DSISR_PROTFAULT;
-			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
-			return RESUME_GUEST;
-		}
-		upgrade_p = NULL;
-	}
-
-	if (dsisr & DSISR_SET_RC) {
-		/*
-		 * Need to set an R or C bit in the 2nd-level tables;
-		 * since we are just helping out the hardware here,
-		 * it is sufficient to do what the hardware does.
-		 */
-		pgflags = _PAGE_ACCESSED;
-		if (writing)
-			pgflags |= _PAGE_DIRTY;
-		/*
-		 * We are walking the secondary page table here. We can do this
-		 * without disabling irq.
-		 */
-		spin_lock(&kvm->mmu_lock);
-		ptep = __find_linux_pte(kvm->arch.pgtable,
-					gpa, NULL, &shift);
-		if (ptep && pte_present(*ptep) &&
-		    (!writing || pte_write(*ptep))) {
-			kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
-						gpa, shift);
-			dsisr &= ~DSISR_SET_RC;
-		}
-		spin_unlock(&kvm->mmu_lock);
-		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
-			       DSISR_PROTFAULT | DSISR_SET_RC)))
-			return RESUME_GUEST;
-	}
+	int ret;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -666,7 +621,7 @@  int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * is that the page is writable.
 	 */
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
+	if (!kvm_ro && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
 		upgrade_write = true;
 	} else {
 		unsigned long pfn;
@@ -724,7 +679,12 @@  int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 	/* Allocate space in the tree and write the PTE */
-	ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+	ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
+				mmu_seq);
+	if (inserted_pte)
+		*inserted_pte = pte;
+	if (levelp)
+		*levelp = level;
 
 	if (page) {
 		if (!ret && (pte_val(pte) & _PAGE_WRITE))
@@ -732,6 +692,82 @@  int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		put_page(page);
 	}
 
+	return ret;
+}
+
+int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				   unsigned long ea, unsigned long dsisr)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long gpa, gfn;
+	struct kvm_memory_slot *memslot;
+	long ret;
+	bool writing = !!(dsisr & DSISR_ISSTORE);
+	bool kvm_ro = false;
+
+	/* Check for unusual errors */
+	if (dsisr & DSISR_UNSUPP_MMU) {
+		pr_err("KVM: Got unsupported MMU fault\n");
+		return -EFAULT;
+	}
+	if (dsisr & DSISR_BADACCESS) {
+		/* Reflect to the guest as DSI */
+		pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
+		kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+		return RESUME_GUEST;
+	}
+
+	/* Translate the logical address */
+	gpa = vcpu->arch.fault_gpa & ~0xfffUL;
+	gpa &= ~0xF000000000000000ul;
+	gfn = gpa >> PAGE_SHIFT;
+	if (!(dsisr & DSISR_PRTABLE_FAULT))
+		gpa |= ea & 0xfff;
+
+	/* Get the corresponding memslot */
+	memslot = gfn_to_memslot(kvm, gfn);
+
+	/* No memslot means it's an emulated MMIO region */
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
+			     DSISR_SET_RC)) {
+			/*
+			 * Bad address in guest page table tree, or other
+			 * unusual error - reflect it to the guest as DSI.
+			 */
+			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+			return RESUME_GUEST;
+		}
+		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
+	}
+
+	if (memslot->flags & KVM_MEM_READONLY) {
+		if (writing) {
+			/* give the guest a DSI */
+			kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE |
+						       DSISR_PROTFAULT);
+			return RESUME_GUEST;
+		}
+		kvm_ro = true;
+	}
+
+	/* Failed to set the reference/change bits */
+	if (dsisr & DSISR_SET_RC) {
+		spin_lock(&kvm->mmu_lock);
+		if (kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable,
+					    writing, gpa))
+			dsisr &= ~DSISR_SET_RC;
+		spin_unlock(&kvm->mmu_lock);
+
+		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+			       DSISR_PROTFAULT | DSISR_SET_RC)))
+			return RESUME_GUEST;
+	}
+
+	/* Try to insert a pte */
+	ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
+					     kvm_ro, NULL, NULL);
+
 	if (ret == 0 || ret == -EAGAIN)
 		ret = RESUME_GUEST;
 	return ret;