1 files changed, 65 insertions, 67 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index b5905ae4377c..b3e6e73d6a08 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -15,6 +15,7 @@
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
+#include "book3s_hv.h"
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm/pgalloc.h>
@@ -22,6 +23,7 @@
 #include <asm/ultravisor.h>
 #include <asm/kvm_book3s_uvmem.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/firmware.h>
 
 /*
  * Supported radix tree geometry.
@@ -38,12 +40,18 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	unsigned long quadrant, ret = n;
 	bool is_load = !!to;
 
+	if (kvmhv_is_nestedv2())
+		return H_UNSUPPORTED;
+
 	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
 	if (kvmhv_on_pseries())
 		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
 					  (to != NULL) ? __pa(to): 0,
 					  (from != NULL) ? __pa(from): 0, n);
 
+	if (eaddr & (0xFFFUL << 52))
+		return ret;
+
 	quadrant = 1;
 	if (!pid)
 		quadrant = 2;
@@ -54,6 +62,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 
 	preempt_disable();
 
+	asm volatile("hwsync" ::: "memory");
+	isync();
 	/* switch the lpid first to avoid running host with unallocated pid */
 	old_lpid = mfspr(SPRN_LPID);
 	if (old_lpid != lpid)
@@ -65,11 +75,15 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	}
 	isync();
 
+	pagefault_disable();
 	if (is_load)
-		ret = copy_from_user_nofault(to, (const void __user *)from, n);
+		ret = __copy_from_user_inatomic(to, (const void __user *)from, n);
 	else
-		ret = copy_to_user_nofault((void __user *)to, from, n);
+		ret = __copy_to_user_inatomic((void __user *)to, from, n);
+	pagefault_enable();
 
+	asm volatile("hwsync" ::: "memory");
+	isync();
 	/* switch the pid first to avoid running host with unallocated pid */
 	if (quadrant == 1 && pid != old_pid)
 		mtspr(SPRN_PID, old_pid);
@@ -81,13 +95,12 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__kvmhv_copy_tofrom_guest_radix);
 
 static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  void *to, void *from, unsigned long n)
 {
 	int lpid = vcpu->kvm->arch.lpid;
-	int pid = vcpu->arch.pid;
+	int pid;
 
 	/* This would cause a data segment intr so don't allow the access */
 	if (eaddr & (0x3FFUL << 52))
@@ -100,6 +113,8 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* If accessing quadrant 3 then pid is expected to be 0 */
 	if (((eaddr >> 62) & 0x3) == 0x3)
 		pid = 0;
+	else
+		pid = kvmppc_get_pid(vcpu);
 
 	eaddr &= ~(0xFFFUL << 52);
 
@@ -117,14 +132,12 @@ long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *to,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(kvmhv_copy_from_guest_radix);
 
 long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *from,
 			       unsigned long n)
 {
 	return kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, NULL, from, n);
 }
-EXPORT_SYMBOL_GPL(kvmhv_copy_to_guest_radix);
 
 int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 			       struct kvmppc_pte *gpte, u64 root,
@@ -162,9 +175,10 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 			return -EINVAL;
 		/* Read the entry from guest memory */
 		addr = base + (index * sizeof(rpte));
-		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+
+		kvm_vcpu_srcu_read_lock(vcpu);
 		ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte));
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		if (ret) {
 			if (pte_ret_p)
 				*pte_ret_p = addr;
@@ -240,9 +254,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	/* Read the table to find the root of the radix tree */
 	ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
-	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
-	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	if (ret)
 		return ret;
 
@@ -262,7 +276,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Work out effective PID */
 	switch (eaddr >> 62) {
 	case 0:
-		pid = vcpu->arch.pid;
+		pid = kvmppc_get_pid(vcpu);
 		break;
 	case 3:
 		pid = 0;
@@ -286,9 +300,9 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	} else {
 		if (!(pte & _PAGE_PRIVILEGED)) {
 			/* Check AMR/IAMR to see if strict mode is in force */
-			if (vcpu->arch.amr & (1ul << 62))
+			if (kvmppc_get_amr_hv(vcpu) & (1ul << 62))
 				gpte->may_read = 0;
-			if (vcpu->arch.amr & (1ul << 63))
+			if (kvmppc_get_amr_hv(vcpu) & (1ul << 63))
 				gpte->may_write = 0;
 			if (vcpu->arch.iamr & (1ul << 62))
 				gpte->may_execute = 0;
@@ -299,7 +313,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 }
 
 void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
-			     unsigned int pshift, unsigned int lpid)
+			     unsigned int pshift, u64 lpid)
 {
 	unsigned long psize = PAGE_SIZE;
 	int psi;
@@ -336,7 +350,7 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
 }
 
-static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, u64 lpid)
 {
 	long rc;
 
@@ -409,7 +423,7 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
 void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
 		      unsigned int shift,
 		      const struct kvm_memory_slot *memslot,
-		      unsigned int lpid)
+		      u64 lpid)
 
 {
 	unsigned long old;
@@ -460,7 +474,7 @@ void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
  * (or 4kB) mappings (of sub-pages of the same 2MB page).
  */
 static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	if (full) {
 		memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE);
@@ -481,7 +495,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
 }
 
 static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	unsigned long im;
 	pmd_t *p = pmd;
@@ -489,7 +503,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 	for (im = 0; im < PTRS_PER_PMD; ++im, ++p) {
 		if (!pmd_present(*p))
 			continue;
-		if (pmd_is_leaf(*p)) {
+		if (pmd_leaf(*p)) {
 			if (full) {
 				pmd_clear(p);
 			} else {
@@ -501,7 +515,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 		} else {
 			pte_t *pte;
 
-			pte = pte_offset_map(p, 0);
+			pte = pte_offset_kernel(p, 0);
 			kvmppc_unmap_free_pte(kvm, pte, full, lpid);
 			pmd_clear(p);
 		}
@@ -510,7 +524,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 }
 
 static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	unsigned long iu;
 	pud_t *p = pud;
@@ -518,7 +532,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
 	for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
 		if (!pud_present(*p))
 			continue;
-		if (pud_is_leaf(*p)) {
+		if (pud_leaf(*p)) {
 			pud_clear(p);
 		} else {
 			pmd_t *pmd;
@@ -531,7 +545,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
 	pud_free(kvm->mm, pud);
 }
 
-void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid)
+void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, u64 lpid)
 {
 	unsigned long ig;
 
@@ -558,7 +572,7 @@ void kvmppc_free_radix(struct kvm *kvm)
 }
 
 static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
-					unsigned long gpa, unsigned int lpid)
+					unsigned long gpa, u64 lpid)
 {
 	pte_t *pte = pte_offset_kernel(pmd, 0);
 
@@ -574,7 +588,7 @@ static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
 }
 
 static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
-					unsigned long gpa, unsigned int lpid)
+					unsigned long gpa, u64 lpid)
 {
 	pmd_t *pmd = pmd_offset(pud, 0);
 
@@ -600,7 +614,7 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
 
 int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		      unsigned long gpa, unsigned int level,
-		      unsigned long mmu_seq, unsigned int lpid,
+		      unsigned long mmu_seq, u64 lpid,
 		      unsigned long *rmapp, struct rmap_nested **n_rmap)
 {
 	pgd_t *pgd;
@@ -621,18 +635,18 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pud = pud_alloc_one(kvm->mm, gpa);
 
 	pmd = NULL;
-	if (pud && pud_present(*pud) && !pud_is_leaf(*pud))
+	if (pud && pud_present(*pud) && !pud_leaf(*pud))
 		pmd = pmd_offset(pud, gpa);
 	else if (level <= 1)
 		new_pmd = kvmppc_pmd_alloc();
 
-	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
+	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_leaf(*pmd)))
 		new_ptep = kvmppc_pte_alloc();
 
 	/* Check if we might have been invalidated; let the guest retry if so */
 	spin_lock(&kvm->mmu_lock);
 	ret = -EAGAIN;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/* Now traverse again under the lock and change the tree */
@@ -644,7 +658,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pud = NULL;
 	}
 	pud = pud_offset(p4d, gpa);
-	if (pud_is_leaf(*pud)) {
+	if (pud_leaf(*pud)) {
 		unsigned long hgpa = gpa & PUD_MASK;
 
 		/* Check if we raced and someone else has set the same thing */
@@ -695,7 +709,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pmd = NULL;
 	}
 	pmd = pmd_offset(pud, gpa);
-	if (pmd_is_leaf(*pmd)) {
+	if (pmd_leaf(*pmd)) {
 		unsigned long lgpa = gpa & PMD_MASK;
 
 		/* Check if we raced and someone else has set the same thing */
@@ -777,7 +791,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 }
 
 bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
-			     unsigned long gpa, unsigned int lpid)
+			     unsigned long gpa, u64 lpid)
 {
 	unsigned long pgflags;
 	unsigned int shift;
@@ -807,7 +821,7 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
 int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 				   unsigned long gpa,
 				   struct kvm_memory_slot *memslot,
-				   bool writing, bool kvm_ro,
+				   bool writing,
 				   pte_t *inserted_pte, unsigned int *levelp)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -815,40 +829,21 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	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 int shift, level;
 	int ret;
 	bool large_enable;
+	kvm_pfn_t pfn;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
-	/*
-	 * Do a fast check first, since __gfn_to_pfn_memslot doesn't
-	 * do it with !atomic && !async, which is how we call it.
-	 * We always ask for write permission since the common case
-	 * is that the page is writable.
-	 */
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	if (!kvm_ro && get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
-		upgrade_write = true;
-	} else {
-		unsigned long pfn;
-
-		/* Call KVM generic code to do the slow-path check */
-		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
-					   writing, upgrade_p, NULL);
-		if (is_error_noslot_pfn(pfn))
-			return -EFAULT;
-		page = NULL;
-		if (pfn_valid(pfn)) {
-			page = pfn_to_page(pfn);
-			if (PageReserved(page))
-				page = NULL;
-		}
-	}
+	pfn = __kvm_faultin_pfn(memslot, gfn, writing ? FOLL_WRITE : 0,
+				&upgrade_write, &page);
+	if (is_error_noslot_pfn(pfn))
+		return -EFAULT;
 
 	/*
 	 * Read the PTE from the process' radix tree and use that
@@ -936,7 +931,6 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 	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) {
@@ -946,7 +940,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 	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);
+		kvmppc_core_queue_data_storage(vcpu,
+				kvmppc_get_msr(vcpu) & SRR1_PREFIXED,
+				ea, dsisr);
 		return RESUME_GUEST;
 	}
 
@@ -971,7 +967,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 			 * 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);
+			kvmppc_core_queue_data_storage(vcpu,
+					kvmppc_get_msr(vcpu) & SRR1_PREFIXED,
+					ea, dsisr);
 			return RESUME_GUEST;
 		}
 		return kvmppc_hv_emulate_mmio(vcpu, gpa, ea, writing);
@@ -980,11 +978,11 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 	if (memslot->flags & KVM_MEM_READONLY) {
 		if (writing) {
 			/* give the guest a DSI */
-			kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE |
-						       DSISR_PROTFAULT);
+			kvmppc_core_queue_data_storage(vcpu,
+					kvmppc_get_msr(vcpu) & SRR1_PREFIXED,
+					ea, DSISR_ISSTORE | DSISR_PROTFAULT);
 			return RESUME_GUEST;
 		}
-		kvm_ro = true;
 	}
 
 	/* Failed to set the reference/change bits */
@@ -1002,7 +1000,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 
 	/* Try to insert a pte */
 	ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
-					     kvm_ro, NULL, NULL);
+					     NULL, NULL);
 
 	if (ret == 0 || ret == -EAGAIN)
 		ret = RESUME_GUEST;
@@ -1183,7 +1181,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	 * Increase the mmu notifier sequence number to prevent any page
 	 * fault that read the memslot earlier from writing a PTE.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	spin_unlock(&kvm->mmu_lock);
 }
 
@@ -1448,7 +1446,7 @@ static const struct file_operations debugfs_radix_fops = {
 
 void kvmhv_radix_debugfs_init(struct kvm *kvm)
 {
-	debugfs_create_file("radix", 0400, kvm->arch.debugfs_dir, kvm,
+	debugfs_create_file("radix", 0400, kvm->debugfs_dentry, kvm,
 			    &debugfs_radix_fops);
 }