Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "These are mostly PPC changes for 3.16-new things.  However, there is
  an x86 change too and it is a regression from 3.14.  As it only
  affects nested virtualization and there were other changes in this
  area in 3.16, I am not nominating it for 3.15-stable"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Check for nested events if there is an injectable interrupt
  KVM: PPC: RTAS: Do byte swaps explicitly
  KVM: PPC: Book3S PR: Fix ABIv2 on LE
  KVM: PPC: Assembly functions exported to modules need _GLOBAL_TOC()
  PPC: Add _GLOBAL_TOC for 32bit
  KVM: PPC: BOOK3S: HV: Use base page size when comparing against slb value
  KVM: PPC: Book3E: Unlock mmu_lock when setting caching atttribute

10 files changed, 64 insertions, 58 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index fddb72b..d645428 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -198,8 +198,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
-static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
+					     bool is_base_size)
 {
+
 	int size, a_psize;
 	/* Look at the 8 bit LP value */
 	unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
@@ -214,14 +216,27 @@ static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
 				continue;
 
 			a_psize = __hpte_actual_psize(lp, size);
-			if (a_psize != -1)
+			if (a_psize != -1) {
+				if (is_base_size)
+					return 1ul << mmu_psize_defs[size].shift;
 				return 1ul << mmu_psize_defs[a_psize].shift;
+			}
 		}
 
 	}
 	return 0;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 0);
+}
+
+static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 1);
+}
+
 static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
 {
 	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 9ea266e..7e46125 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -277,6 +277,8 @@ n:
 	.globl n;	\
 n:
 
+#define _GLOBAL_TOC(name) _GLOBAL(name)
+
 #define _KPROBE(n)	\
 	.section ".kprobes.text","a";	\
 	.globl	n;	\
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 8056107..68468d6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1562,7 +1562,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				goto out;
 			}
 			if (!rma_setup && is_vrma_hpte(v)) {
-				unsigned long psize = hpte_page_size(v, r);
+				unsigned long psize = hpte_base_page_size(v, r);
 				unsigned long senc = slb_pgsize_encoding(psize);
 				unsigned long lpcr;
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6e62243..5a24d3c 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -814,13 +814,10 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			r = hpte[i+1];
 
 			/*
-			 * Check the HPTE again, including large page size
-			 * Since we don't currently allow any MPSS (mixed
-			 * page-size segment) page sizes, it is sufficient
-			 * to check against the actual page size.
+			 * Check the HPTE again, including base page size
 			 */
 			if ((v & valid) && (v & mask) == val &&
-			    hpte_page_size(v, r) == (1ul << pshift))
+			    hpte_base_page_size(v, r) == (1ul << pshift))
 				/* Return with the HPTE still locked */
 				return (hash << 3) + (i >> 1);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 868347e..558a67d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -48,7 +48,7 @@
  *
  * LR = return address to continue at after eventually re-enabling MMU
  */
-_GLOBAL(kvmppc_hv_entry_trampoline)
+_GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 	stdu	r1, -112(r1)
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index e2c29e3..d044b8b 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -25,7 +25,11 @@
 #include <asm/exception-64s.h>
 
 #if defined(CONFIG_PPC_BOOK3S_64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 #define GET_SHADOW_VCPU(reg)    addi	reg, r13, PACA_SVCPU
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 9eec675..16c4d88 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -36,7 +36,11 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -146,7 +150,7 @@ kvmppc_handler_skip_ins:
  * On entry, r4 contains the guest shadow MSR
  * MSR.EE has to be 0 when calling this function
  */
-_GLOBAL(kvmppc_entry_trampoline)
+_GLOBAL_TOC(kvmppc_entry_trampoline)
 	mfmsr	r5
 	LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter)
 	toreal(r7)
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index edb14ba..ef27fbd 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -23,20 +23,20 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 3 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 3 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
-	server = args->args[1];
-	priority = args->args[2];
+	irq = be32_to_cpu(args->args[0]);
+	server = be32_to_cpu(args->args[1]);
+	priority = be32_to_cpu(args->args[2]);
 
 	rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -44,12 +44,12 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 3) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 3) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	server = priority = 0;
 	rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
@@ -58,10 +58,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 		goto out;
 	}
 
-	args->rets[1] = server;
-	args->rets[2] = priority;
+	args->rets[1] = cpu_to_be32(server);
+	args->rets[2] = cpu_to_be32(priority);
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -69,18 +69,18 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_off(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -88,18 +88,18 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_on(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 #endif /* CONFIG_KVM_XICS */
 
@@ -205,32 +205,6 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp)
 	return rc;
 }
 
-static void kvmppc_rtas_swap_endian_in(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	args->token = be32_to_cpu(args->token);
-	args->nargs = be32_to_cpu(args->nargs);
-	args->nret = be32_to_cpu(args->nret);
-	for (i = 0; i < args->nargs; i++)
-		args->args[i] = be32_to_cpu(args->args[i]);
-#endif
-}
-
-static void kvmppc_rtas_swap_endian_out(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	for (i = 0; i < args->nret; i++)
-		args->args[i] = cpu_to_be32(args->args[i]);
-	args->token = cpu_to_be32(args->token);
-	args->nargs = cpu_to_be32(args->nargs);
-	args->nret = cpu_to_be32(args->nret);
-#endif
-}
-
 int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 {
 	struct rtas_token_definition *d;
@@ -249,8 +223,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	if (rc)
 		goto fail;
 
-	kvmppc_rtas_swap_endian_in(&args);
-
 	/*
 	 * args->rets is a pointer into args->args. Now that we've
 	 * copied args we need to fix it up to point into our copy,
@@ -258,13 +230,13 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	 * value so we can restore it on the way out.
 	 */
 	orig_rets = args.rets;
-	args.rets = &args.args[args.nargs];
+	args.rets = &args.args[be32_to_cpu(args.nargs)];
 
 	mutex_lock(&vcpu->kvm->lock);
 
 	rc = -ENOENT;
 	list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) {
-		if (d->token == args.token) {
+		if (d->token == be32_to_cpu(args.token)) {
 			d->handler->handler(vcpu, &args);
 			rc = 0;
 			break;
@@ -275,7 +247,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 
 	if (rc == 0) {
 		args.rets = orig_rets;
-		kvmppc_rtas_swap_endian_out(&args);
 		rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 		if (rc)
 			goto fail;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index dd2cc03..86903d3 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -473,7 +473,8 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		if (printk_ratelimit())
 			pr_err("%s: pte not present: gfn %lx, pfn %lx\n",
 				__func__, (long)gfn, pfn);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f644933..ef432f8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5887,6 +5887,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 			kvm_x86_ops->set_nmi(vcpu);
 		}
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
+		/*
+		 * Because interrupts can be injected asynchronously, we are
+		 * calling check_nested_events again here to avoid a race condition.
+		 * See https://lkml.org/lkml/2014/7/2/60 for discussion about this
+		 * proposal and current concerns.  Perhaps we should be setting
+		 * KVM_REQ_EVENT only on certain events and not unconditionally?
+		 */
+		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			if (r != 0)
+				return r;
+		}
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);