diff mbox

[RFC,2/9] KVM: PPC: Book3S: Add infrastructure to implement kernel-side RTAS calls

Message ID 20121105032023.GC22409@drongo
State New, archived
Headers show

Commit Message

Paul Mackerras Nov. 5, 2012, 3:20 a.m. UTC
From: Michael Ellerman <michael@ellerman.id.au>

For pseries machine emulation, in order to move the interrupt
controller code to the kernel, we need to intercept some RTAS
calls in the kernel itself.  This adds an infrastructure to allow
in-kernel handlers to be registered for RTAS services by name.
A new ioctl, KVM_PPC_RTAS_DEFINE_TOKEN, then allows userspace to
associate token values with those service names.  Then, when the
guest requests an RTAS service with one of those token values, it
will be handled by the relevant in-kernel handler rather than being
passed up to userspace as at present.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 Documentation/virtual/kvm/api.txt   |   19 ++++
 arch/powerpc/include/asm/hvcall.h   |    3 +
 arch/powerpc/include/asm/kvm_host.h |    1 +
 arch/powerpc/include/asm/kvm_ppc.h  |    4 +
 arch/powerpc/include/uapi/asm/kvm.h |    6 ++
 arch/powerpc/kvm/Makefile           |    1 +
 arch/powerpc/kvm/book3s_hv.c        |   18 +++-
 arch/powerpc/kvm/book3s_pr_papr.c   |    7 ++
 arch/powerpc/kvm/book3s_rtas.c      |  182 +++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/powerpc.c          |    9 +-
 include/uapi/linux/kvm.h            |    4 +
 11 files changed, 252 insertions(+), 2 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_rtas.c
diff mbox

Patch

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6671fdc..8ca0a7c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2071,6 +2071,25 @@  KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
+4.78 KVM_PPC_RTAS_DEFINE_TOKEN
+
+Capability: KVM_CAP_PPC_RTAS
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_rtas_token_args
+Returns: 0 on success, -1 on error
+
+Defines a token value for a RTAS (Run Time Abstraction Services)
+service in order to allow it to be handled in the kernel.  The
+argument struct gives the name of the service, which must be the name
+of a service that has a kernel-side implementation.  If the token
+value is non-zero, it will be associated with that service, and
+subsequent RTAS calls by the guest specifying that token will be
+handled by the kernel.  If the token value is 0, then any token
+associated with the service will be forgotten, and subsequent RTAS
+calls by the guest for that service will be passed to userspace to be
+handled.
+
 
 5. The kvm_run structure
 ------------------------
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 7a86706..9ea22b2 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -269,6 +269,9 @@ 
 #define H_GET_MPP_X		0x314
 #define MAX_HCALL_OPCODE	H_GET_MPP_X
 
+/* Platform specific hcalls, used by KVM */
+#define H_RTAS			0xf000
+
 #ifndef __ASSEMBLY__
 
 /**
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3093896..8e745a8 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -255,6 +255,7 @@  struct kvm_arch {
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
+	struct list_head rtas_tokens;
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 9fd2654..996aeca 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -163,6 +163,10 @@  extern void kvmppc_bookehv_exit(void);
 
 extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu);
 
+extern int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp);
+extern int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu);
+extern void kvmppc_rtas_tokens_free(struct kvm *kvm);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index b89ae4d..fd0a6f7 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -296,6 +296,12 @@  struct kvm_allocate_rma {
 	__u64 rma_size;
 };
 
+/* for KVM_CAP_PPC_RTAS */
+struct kvm_rtas_token_args {
+	char name[120];
+	__u64 token;	/* Use a token of 0 to undefine a mapping */
+};
+
 struct kvm_book3e_206_tlb_entry {
 	__u32 mas8;
 	__u32 mas1;
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index c2a0863..536f65f 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -80,6 +80,7 @@  kvm-book3s_64-module-objs := \
 	emulate.o \
 	book3s.o \
 	book3s_64_vio.o \
+	book3s_rtas.o \
 	$(kvm-book3s_64-objs-y)
 
 kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 843eb75..8284d55 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -479,7 +479,7 @@  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	unsigned long req = kvmppc_get_gpr(vcpu, 3);
 	unsigned long target, ret = H_SUCCESS;
 	struct kvm_vcpu *tvcpu;
-	int idx;
+	int idx, rc;
 
 	switch (req) {
 	case H_ENTER:
@@ -515,6 +515,19 @@  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 					kvmppc_get_gpr(vcpu, 5),
 					kvmppc_get_gpr(vcpu, 6));
 		break;
+	case H_RTAS:
+		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
+			return RESUME_HOST;
+
+		rc = kvmppc_rtas_hcall(vcpu);
+
+		if (rc == -ENOENT)
+			return RESUME_HOST;
+		else if (rc == 0)
+			break;
+
+		/* Send the error out to userspace via KVM_RUN */
+		return rc;
 	default:
 		return RESUME_HOST;
 	}
@@ -1815,6 +1828,7 @@  int kvmppc_core_init_vm(struct kvm *kvm)
 	kvm->arch.lpid = lpid;
 
 	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
 
 	kvm->arch.rma = NULL;
 
@@ -1860,6 +1874,8 @@  void kvmppc_core_destroy_vm(struct kvm *kvm)
 		kvm->arch.rma = NULL;
 	}
 
+	kvmppc_rtas_tokens_free(kvm);
+
 	kvmppc_free_hpt(kvm);
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 }
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index ee02b30..4efa4a4 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -246,6 +246,13 @@  int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		vcpu->stat.halt_wakeup++;
 		return EMULATE_DONE;
+	case H_RTAS:
+		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
+			return RESUME_HOST;
+		if (kvmppc_rtas_hcall(vcpu))
+			break;
+		kvmppc_set_gpr(vcpu, 3, 0);
+		return EMULATE_DONE;
 	}
 
 	return EMULATE_FAIL;
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
new file mode 100644
index 0000000..8a324e8
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -0,0 +1,182 @@ 
+/*
+ * Copyright 2012 Michael Ellerman, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/err.h>
+
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/rtas.h>
+
+
+struct rtas_handler {
+	void (*handler)(struct kvm_vcpu *vcpu, struct rtas_args *args);
+	char *name;
+};
+
+static struct rtas_handler rtas_handlers[] = { };
+
+struct rtas_token_definition {
+	struct list_head list;
+	struct rtas_handler *handler;
+	u64 token;
+};
+
+static int rtas_name_matches(char *s1, char *s2)
+{
+	struct kvm_rtas_token_args args;
+	return !strncmp(s1, s2, sizeof(args.name));
+}
+
+static int rtas_token_undefine(struct kvm *kvm, char *name)
+{
+	struct rtas_token_definition *d, *tmp;
+
+	lockdep_assert_held(&kvm->lock);
+
+	list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) {
+		if (rtas_name_matches(d->handler->name, name)) {
+			list_del(&d->list);
+			kfree(d);
+			return 0;
+		}
+	}
+
+	/* It's not an error to undefine an undefined token */
+	return 0;
+}
+
+static int rtas_token_define(struct kvm *kvm, char *name, u64 token)
+{
+	struct rtas_token_definition *d;
+	struct rtas_handler *h;
+	bool found;
+	int i;
+
+	lockdep_assert_held(&kvm->lock);
+
+	list_for_each_entry(d, &kvm->arch.rtas_tokens, list) {
+		if (d->token == token)
+			return -EEXIST;
+	}
+
+	found = false;
+	for (i = 0; i < ARRAY_SIZE(rtas_handlers); i++) {
+		h = &rtas_handlers[i];
+		if (rtas_name_matches(h->name, name)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		return -ENOENT;
+
+	d = kzalloc(sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	d->handler = h;
+	d->token = token;
+
+	list_add_tail(&d->list, &kvm->arch.rtas_tokens);
+
+	return 0;
+}
+
+int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_rtas_token_args args;
+	int rc;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	mutex_lock(&kvm->lock);
+
+	if (args.token)
+		rc = rtas_token_define(kvm, args.name, args.token);
+	else
+		rc = rtas_token_undefine(kvm, args.name);
+
+	mutex_unlock(&kvm->lock);
+
+	return rc;
+}
+
+int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
+{
+	struct rtas_token_definition *d;
+	struct rtas_args args;
+	rtas_arg_t *orig_rets;
+	gpa_t args_phys;
+	int rc;
+
+	/* r4 contains the guest physical address of the RTAS args */
+	args_phys = kvmppc_get_gpr(vcpu, 4);
+
+	rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args));
+	if (rc)
+		goto fail;
+
+	/*
+	 * 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,
+	 * not the guest args. We also need to save the original
+	 * value so we can restore it on the way out.
+	 */
+	orig_rets = args.rets;
+	args.rets = &args.args[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) {
+			d->handler->handler(vcpu, &args);
+			rc = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&vcpu->kvm->lock);
+
+	if (rc == 0) {
+		args.rets = orig_rets;
+		rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args));
+		if (rc)
+			goto fail;
+	}
+
+	return rc;
+
+fail:
+	/*
+	 * We only get here if the guest has called RTAS with a bogus
+	 * args pointer. That means we can't get to the args, and so we
+	 * can't fail the RTAS call. So fail right out to userspace,
+	 * which should kill the guest.
+	 */
+	return rc;
+}
+
+void kvmppc_rtas_tokens_free(struct kvm *kvm)
+{
+	struct rtas_token_definition *d, *tmp;
+
+	lockdep_assert_held(&kvm->lock);
+
+	list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) {
+		list_del(&d->list);
+		kfree(d);
+	}
+}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a42e1e3..ba552f8 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -332,6 +332,7 @@  int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_PPC_ALLOC_HTAB:
+	case KVM_CAP_PPC_RTAS:
 		r = 1;
 		break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -909,8 +910,8 @@  long kvm_arch_vm_ioctl(struct file *filp,
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_ALLOCATE_RMA: {
-		struct kvm *kvm = filp->private_data;
 		struct kvm_allocate_rma rma;
+		struct kvm *kvm = filp->private_data;
 
 		r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
 		if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
@@ -947,6 +948,12 @@  long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_PPC_RTAS_DEFINE_TOKEN: {
+		struct kvm *kvm = filp->private_data;
+
+		r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
+		break;
+	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 494a84c..3a92001 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -634,6 +634,7 @@  struct kvm_ppc_smmu_info {
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_RTAS 84
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -859,6 +860,9 @@  struct kvm_s390_ucas_mapping {
 #define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
 /* Available with KVM_CAP_RMA */
 #define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_RTAS */
+#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO,  0xaa, struct kvm_rtas_token_args)
+
 
 /*
  * ioctls for vcpu fds