KVM: PPC: Book3S: Controls for in-kernel sPAPR hypercall handling

This provides a way for userspace controls which sPAPR hcalls get
handled in the kernel.  Each hcall can be individually enabled or
disabled for in-kernel handling, except for H_RTAS.  The exception
for H_RTAS is because userspace can already control whether
individual RTAS functions are handled in-kernel or not via the
KVM_PPC_RTAS_DEFINE_TOKEN ioctl, and because the numeric value for
H_RTAS is out of the normal sequence of hcall numbers.

Hcalls are enabled or disabled using the KVM_ENABLE_CAP ioctl for the
KVM_CAP_PPC_ENABLE_HCALL capability on the file descriptor for the VM.
The args field of the struct kvm_enable_cap specifies the hcall number
in args[0] and the enable/disable flag in args[1]; 0 means disable
in-kernel handling (so that the hcall will always cause an exit to
userspace) and 1 means enable.  Enabling or disabling in-kernel
handling of an hcall is effective across the whole VM.

The ability for KVM_ENABLE_CAP to be used on a VM file descriptor
on PowerPC is new, added by this commit.  The KVM_CAP_ENABLE_CAP_VM
capability advertises that this ability exists.

When a VM is created, an initial set of hcalls are enabled for
in-kernel handling.  The set that is enabled is the set that have
an in-kernel implementation at this point.  Any new hcall
implementations from this point onwards should not be added to the
default set without a good reason.

No distinction is made between real-mode and virtual-mode hcall
implementations; the one setting controls them both.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

Documentation/virtual/kvm/api.txt

@@ -2863,8 +2863,8 @@ The fields in each entry are defined as follows:
          this function/index combination
 
 
-6. Capabilities that can be enabled
------------------------------------
+6. Capabilities that can be enabled on vCPUs
+--------------------------------------------
 
 There are certain capabilities that change the behavior of the virtual CPU when
 enabled. To enable them, please see section 4.37. Below you can find a list of
@@ -3002,3 +3002,40 @@ Parameters: args[0] is the XICS device fd
             args[1] is the XICS CPU number (server ID) for this vcpu
 
 This capability connects the vcpu to an in-kernel XICS device.
+
+
+7. Capabilities that can be enabled on VMs
+------------------------------------------
+
+There are certain capabilities that change the behavior of the virtual
+machine when enabled. To enable them, please see section 4.37. Below
+you can find a list of capabilities and what their effect on the VM
+is when enabling them.
+
+The following information is provided along with the description:
+
+  Architectures: which instruction set architectures provide this ioctl.
+      x86 includes both i386 and x86_64.
+
+  Parameters: what parameters are accepted by the capability.
+
+  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
+      are not detailed, but errors with specific meanings are.
+
+
+7.1 KVM_CAP_PPC_ENABLE_HCALL
+
+Architectures: ppc
+Parameters: args[0] is the sPAPR hcall number
+	    args[1] is 0 to disable, 1 to enable in-kernel handling
+
+This capability controls whether individual sPAPR hypercalls (hcalls)
+get handled by the kernel or not.  Enabling or disabling in-kernel
+handling of an hcall is effective across the VM.  On creation, an
+initial set of hcalls are enabled for in-kernel handling, which
+consists of those hcalls for which in-kernel handlers were implemented
+before this capability was implemented.  If disabled, the kernel will
+not to attempt to handle the hcall, but will always exit to userspace
+to handle it.  Note that it may not make sense to enable some and
+disable others of a group of related hcalls, but KVM does not prevent
+userspace from doing that.

arch/powerpc/include/asm/kvm_book3s.h

@@ -187,6 +187,7 @@ extern void kvmppc_hv_entry_trampoline(void);
 extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
 extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
 extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
+extern void kvmppc_pr_init_default_hcalls(struct kvm *kvm);
 extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
 				 struct kvm_vcpu *vcpu);
 extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,

arch/powerpc/include/asm/kvm_host.h

@@ -34,6 +34,7 @@
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
+#include <asm/hvcall.h>
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
@@ -263,6 +264,7 @@ struct kvm_arch {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
 	struct list_head rtas_tokens;
+	DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 #endif
 #ifdef CONFIG_KVM_MPIC
 	struct openpic *mpic;

arch/powerpc/kernel/asm-offsets.c

@@ -493,6 +493,7 @@ int main(void)
 	DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
 	DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
 	DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
+	DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
 	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
 	DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
 	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));

arch/powerpc/kvm/book3s_hv.c

@@ -67,6 +67,8 @@
 /* Used as a "null" value for timebase values */
 #define TB_NIL	(~(u64)0)
 
+static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
+
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
@@ -562,6 +564,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu *tvcpu;
 	int idx, rc;
 
+	if (req <= MAX_HCALL_OPCODE &&
+	    !test_bit(req/4, vcpu->kvm->arch.enabled_hcalls))
+		return RESUME_HOST;
+
 	switch (req) {
 	case H_ENTER:
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -2269,6 +2275,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	 */
 	cpumask_setall(&kvm->arch.need_tlb_flush);
 
+	/* Start out with the default set of hcalls enabled */
+	memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
+	       sizeof(kvm->arch.enabled_hcalls));
+
 	kvm->arch.rma = NULL;
 
 	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
@@ -2407,6 +2417,45 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 	return r;
 }
 
+/*
+ * List of hcall numbers to enable by default.
+ * For compatibility with old userspace, we enable by default
+ * all hcalls that were implemented before the hcall-enabling
+ * facility was added.  Note this list should not include H_RTAS.
+ */
+static unsigned int default_hcall_list[] = {
+	H_REMOVE,
+	H_ENTER,
+	H_READ,
+	H_PROTECT,
+	H_BULK_REMOVE,
+	H_GET_TCE,
+	H_PUT_TCE,
+	H_SET_DABR,
+	H_SET_XDABR,
+	H_CEDE,
+	H_PROD,
+	H_CONFER,
+	H_REGISTER_VPA,
+#ifdef CONFIG_KVM_XICS
+	H_EOI,
+	H_CPPR,
+	H_IPI,
+	H_IPOLL,
+	H_XIRR,
+	H_XIRR_X,
+#endif
+	0
+};
+
+static void init_default_hcalls(void)
+{
+	int i;
+
+	for (i = 0; default_hcall_list[i]; ++i)
+		__set_bit(default_hcall_list[i] / 4, default_enabled_hcalls);
+}
+
 static struct kvmppc_ops kvm_ops_hv = {
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -2454,6 +2503,8 @@ static int kvmppc_book3s_init_hv(void)
 	kvm_ops_hv.owner = THIS_MODULE;
 	kvmppc_hv_ops = &kvm_ops_hv;
 
+	init_default_hcalls();
+
 	r = kvmppc_mmu_hv_init();
 	return r;
 }

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1909,6 +1909,17 @@ hcall_try_real_mode:
 	clrrdi	r3,r3,2
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
+	/* See if this hcall is enabled for in-kernel handling */
+	ld	r4, VCPU_KVM(r9)
+	srdi	r0, r3, 8	/* r0 = (r3 / 4) >> 6 */
+	sldi	r0, r0, 3	/* index into kvm->arch.enabled_hcalls[] */
+	add	r4, r4, r0
+	ld	r0, KVM_ENABLED_HCALLS(r4)
+	rlwinm	r4, r3, 32-2, 0x3f	/* r4 = (r3 / 4) & 0x3f */
+	srd	r0, r0, r4
+	andi.	r0, r0, 1
+	beq	guest_exit_cont
+	/* Get pointer to handler, if any, and call it */
 	LOAD_REG_ADDR(r4, hcall_real_table)
 	lwax	r3,r3,r4
 	cmpwi	r3,0

arch/powerpc/kvm/book3s_pr.c

@@ -1597,6 +1597,11 @@ static int kvmppc_core_init_vm_pr(struct kvm *kvm)
 {
 	mutex_init(&kvm->arch.hpt_mutex);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Start out with the default set of hcalls enabled */
+	kvmppc_pr_init_default_hcalls(kvm);
+#endif
+
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		spin_lock(&kvm_global_user_count_lock);
 		if (++kvm_global_user_count == 1)

arch/powerpc/kvm/book3s_pr_papr.c

@@ -267,6 +267,10 @@ static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
 
 int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 {
+	if (cmd <= MAX_HCALL_OPCODE &&
+	    !test_bit(cmd/4, vcpu->kvm->arch.enabled_hcalls))
+		return EMULATE_FAIL;
+
 	switch (cmd) {
 	case H_ENTER:
 		return kvmppc_h_pr_enter(vcpu);
@@ -304,3 +308,36 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 
 	return EMULATE_FAIL;
 }
+
+
+/*
+ * List of hcall numbers to enable by default.
+ * For compatibility with old userspace, we enable by default
+ * all hcalls that were implemented before the hcall-enabling
+ * facility was added.  Note this list should not include H_RTAS.
+ */
+static unsigned int default_hcall_list[] = {
+	H_ENTER,
+	H_REMOVE,
+	H_PROTECT,
+	H_BULK_REMOVE,
+	H_PUT_TCE,
+	H_CEDE,
+#ifdef CONFIG_KVM_XICS
+	H_XIRR,
+	H_CPPR,
+	H_EOI,
+	H_IPI,
+	H_IPOLL,
+	H_XIRR_X,
+#endif
+	0
+};
+
+void kvmppc_pr_init_default_hcalls(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; default_hcall_list[i]; ++i)
+		__set_bit(default_hcall_list[i] / 4, kvm->arch.enabled_hcalls);
+}

arch/powerpc/kvm/powerpc.c

@@ -387,6 +387,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_UNSET_IRQ:
 	case KVM_CAP_PPC_IRQ_LEVEL:
 	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
@@ -417,6 +418,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_ALLOC_HTAB:
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
+	case KVM_CAP_PPC_ENABLE_HCALL:
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS:
 #endif
@@ -1099,6 +1101,40 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
 	return 0;
 }
 
+
+static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+				   struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	case KVM_CAP_PPC_ENABLE_HCALL: {
+		unsigned long hcall = cap->args[0];
+
+		r = -EINVAL;
+		if (hcall > MAX_HCALL_OPCODE || (hcall & 3) ||
+		    cap->args[1] > 1)
+			break;
+		if (cap->args[1])
+			set_bit(hcall / 4, kvm->arch.enabled_hcalls);
+		else
+			clear_bit(hcall / 4, kvm->arch.enabled_hcalls);
+		r = 0;
+		break;
+	}
+#endif
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {
@@ -1118,6 +1154,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 		break;
 	}
+	case KVM_ENABLE_CAP:
+	{
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			goto out;
+		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
+		break;
+	}
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CREATE_SPAPR_TCE: {
 		struct kvm_create_spapr_tce create_tce;

include/uapi/linux/kvm.h

@@ -758,6 +758,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_VM_ATTRIBUTES 101
 #define KVM_CAP_ARM_PSCI_0_2 102
 #define KVM_CAP_PPC_FIXUP_HCALL 103
+#define KVM_CAP_PPC_ENABLE_HCALL 104
 
 #ifdef KVM_CAP_IRQ_ROUTING