Features and fixes for 4.1 (kvm/next)

1. Assorted changes
 1.1 allow more feature bits for the guest
 1.2 Store breaking event address on program interrupts
 
 2. Interrupt handling rework
 2.1 Fix copy_to_user while holding a spinlock (cc stable)
 2.2 Rework floating interrupts to follow the priorities
 2.3 Allow to inject all local interrupts via new ioctl
 2.4 allow to get/set the full local irq state, e.g. for migration
     and introspection
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJVGvEUAAoJEBF7vIC1phx82tEP/3KrwsDRs+buiBqyv9k+qCFV
 v+R94gReBB5ggfbGfUYgBJMR2/4XQ+0jcZ55jfBCC4osOq6Juw/8HIj2nSgbQHmz
 F9Go0n8IqJ3DnqPTc0KYdFZ7kqDvMV5ME3XJrFiAHv1TUL9H/KpZArkcVIwD2NOo
 w01AVrCDY4bTajYqKShzGFymQl1K5vTGGvgxhh4kAHct4Nt5N5HFmyROm0RrsFZx
 Sycx4t177O7zhCN2tv5Zy8iWaEvzHAESoXkhZ2cJ6t+FXii2Eov5IgyyfYRXBfbm
 YACyvlFD087UdFGTt85ggPVS/S/5hn9xXmVHuIimHeyZU7CXCN5vYPcn+ZyksYr5
 uA8+/2OPAgcaeDa2f7nCjl8jmcLR3hkQ0n/urA+pPYAZANJoFDfiGOr/kVk6aKff
 JTGSFUjNK891/IGEsdrSk2p64U5xMd8LFa3Il++kZT91gc2nrZOHNz5FGlXlkLdJ
 sADeNFWhoprEt/2P4aX6W2j26L8G874XkldDSjrS41U8L55+IiEm09r8oAWgfc5A
 pryeDaN4nSjFC+HOtlPkcVkAcsswiI6nHIm3+/XFetCq+v4pnVKFMHWsTeEjiQgQ
 H5aV9mfEKTJaCPrAJMsj8ZsKq0usG+BeRNqpIvxPAQB8fyl3jw9iu+RHeY1xWsTg
 BRHB/+CGYIxDu4XdRexv
 =Rrx5
 -----END PGP SIGNATURE-----

Merge tag 'kvm-s390-next-20150331' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

Features and fixes for 4.1 (kvm/next)

1. Assorted changes
1.1 allow more feature bits for the guest
1.2 Store breaking event address on program interrupts

2. Interrupt handling rework
2.1 Fix copy_to_user while holding a spinlock (cc stable)
2.2 Rework floating interrupts to follow the priorities
2.3 Allow to inject all local interrupts via new ioctl
2.4 allow to get/set the full local irq state, e.g. for migration
    and introspection

Documentation/virtual/kvm/api.txt

@@ -2861,6 +2861,123 @@ single frame starting at start_gfn for count frames.
 Note: If any architecturally invalid key value is found in the given data then
 the ioctl will return -EINVAL.
 
+4.92 KVM_S390_IRQ
+
+Capability: KVM_CAP_S390_INJECT_IRQ
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_irq (in)
+Returns: 0 on success, -1 on error
+Errors:
+  EINVAL: interrupt type is invalid
+          type is KVM_S390_SIGP_STOP and flag parameter is invalid value
+          type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
+            than the maximum of VCPUs
+  EBUSY:  type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped
+          type is KVM_S390_SIGP_STOP and a stop irq is already pending
+          type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
+            is already pending
+
+Allows to inject an interrupt to the guest.
+
+Using struct kvm_s390_irq as a parameter allows
+to inject additional payload which is not
+possible via KVM_S390_INTERRUPT.
+
+Interrupt parameters are passed via kvm_s390_irq:
+
+struct kvm_s390_irq {
+	__u64 type;
+	union {
+		struct kvm_s390_io_info io;
+		struct kvm_s390_ext_info ext;
+		struct kvm_s390_pgm_info pgm;
+		struct kvm_s390_emerg_info emerg;
+		struct kvm_s390_extcall_info extcall;
+		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_stop_info stop;
+		struct kvm_s390_mchk_info mchk;
+		char reserved[64];
+	} u;
+};
+
+type can be one of the following:
+
+KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
+KVM_S390_PROGRAM_INT - program check; parameters in .pgm
+KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
+KVM_S390_RESTART - restart; no parameters
+KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
+KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
+KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
+KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
+KVM_S390_MCHK - machine check interrupt; parameters in .mchk
+
+
+Note that the vcpu ioctl is asynchronous to vcpu execution.
+
+4.94 KVM_S390_GET_IRQ_STATE
+
+Capability: KVM_CAP_S390_IRQ_STATE
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_irq_state (out)
+Returns: >= number of bytes copied into buffer,
+         -EINVAL if buffer size is 0,
+         -ENOBUFS if buffer size is too small to fit all pending interrupts,
+         -EFAULT if the buffer address was invalid
+
+This ioctl allows userspace to retrieve the complete state of all currently
+pending interrupts in a single buffer. Use cases include migration
+and introspection. The parameter structure contains the address of a
+userspace buffer and its length:
+
+struct kvm_s390_irq_state {
+	__u64 buf;
+	__u32 flags;
+	__u32 len;
+	__u32 reserved[4];
+};
+
+Userspace passes in the above struct and for each pending interrupt a
+struct kvm_s390_irq is copied to the provided buffer.
+
+If -ENOBUFS is returned the buffer provided was too small and userspace
+may retry with a bigger buffer.
+
+4.95 KVM_S390_SET_IRQ_STATE
+
+Capability: KVM_CAP_S390_IRQ_STATE
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_irq_state (in)
+Returns: 0 on success,
+         -EFAULT if the buffer address was invalid,
+         -EINVAL for an invalid buffer length (see below),
+         -EBUSY if there were already interrupts pending,
+         errors occurring when actually injecting the
+          interrupt. See KVM_S390_IRQ.
+
+This ioctl allows userspace to set the complete state of all cpu-local
+interrupts currently pending for the vcpu. It is intended for restoring
+interrupt state after a migration. The input parameter is a userspace buffer
+containing a struct kvm_s390_irq_state:
+
+struct kvm_s390_irq_state {
+	__u64 buf;
+	__u32 len;
+	__u32 pad;
+};
+
+The userspace memory referenced by buf contains a struct kvm_s390_irq
+for each interrupt to be injected into the guest.
+If one of the interrupts could not be injected for some reason the
+ioctl aborts.
+
+len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
+and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
+which is the maximum number of possibly pending cpu-local interrupts.
+
 5. The kvm_run structure
 ------------------------
 

Documentation/virtual/kvm/devices/s390_flic.txt

@@ -27,6 +27,9 @@ Groups:
     Copies all floating interrupts into a buffer provided by userspace.
     When the buffer is too small it returns -ENOMEM, which is the indication
     for userspace to try again with a bigger buffer.
+    -ENOBUFS is returned when the allocation of a kernelspace buffer has
+    failed.
+    -EFAULT is returned when copying data to userspace failed.
     All interrupts remain pending, i.e. are not deleted from the list of
     currently pending interrupts.
     attr->addr contains the userspace address of the buffer into which all

arch/s390/include/asm/kvm_host.h

@@ -344,6 +344,11 @@ enum irq_types {
 	IRQ_PEND_COUNT
 };
 
+/* We have 2M for virtio device descriptor pages. Smallest amount of
+ * memory per page is 24 bytes (1 queue), so (2048*1024) / 24 = 87381
+ */
+#define KVM_S390_MAX_VIRTIO_IRQS 87381
+
 /*
  * Repressible (non-floating) machine check interrupts
  * subclass bits in MCIC
@@ -421,13 +426,32 @@ struct kvm_s390_local_interrupt {
 	unsigned long pending_irqs;
 };
 
+#define FIRQ_LIST_IO_ISC_0 0
+#define FIRQ_LIST_IO_ISC_1 1
+#define FIRQ_LIST_IO_ISC_2 2
+#define FIRQ_LIST_IO_ISC_3 3
+#define FIRQ_LIST_IO_ISC_4 4
+#define FIRQ_LIST_IO_ISC_5 5
+#define FIRQ_LIST_IO_ISC_6 6
+#define FIRQ_LIST_IO_ISC_7 7
+#define FIRQ_LIST_PFAULT   8
+#define FIRQ_LIST_VIRTIO   9
+#define FIRQ_LIST_COUNT   10
+#define FIRQ_CNTR_IO       0
+#define FIRQ_CNTR_SERVICE  1
+#define FIRQ_CNTR_VIRTIO   2
+#define FIRQ_CNTR_PFAULT   3
+#define FIRQ_MAX_COUNT     4
+
 struct kvm_s390_float_interrupt {
+	unsigned long pending_irqs;
 	spinlock_t lock;
-	struct list_head list;
+	struct list_head lists[FIRQ_LIST_COUNT];
-	atomic_t active;
+	int counters[FIRQ_MAX_COUNT];
+	struct kvm_s390_mchk_info mchk;
+	struct kvm_s390_ext_info srv_signal;
 	int next_rr_cpu;
 	unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
-	unsigned int irq_count;
 };
 
 struct kvm_hw_wp_info_arch {

arch/s390/kvm/kvm-s390.c

@@ -31,6 +31,7 @@
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
+#include <asm/isc.h>
 #include <asm/sclp.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
@@ -40,6 +41,9 @@
 #include "trace-s390.h"
 
 #define MEM_OP_MAX_SIZE 65536	/* Maximum transfer size for KVM_S390_MEM_OP */
+#define LOCAL_IRQS 32
+#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
+			   (KVM_MAX_VCPUS + LOCAL_IRQS))
 
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
@@ -105,8 +109,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 /* upper facilities limit for kvm */
 unsigned long kvm_s390_fac_list_mask[] = {
-	0xff82fffbf4fc2000UL,
+	0xffe6fffbfcfdfc40UL,
-	0x005c000000000000UL,
+	0x205c800000000000UL,
 };
 
 unsigned long kvm_s390_fac_list_mask_size(void)
@@ -176,9 +180,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_IRQCHIP:
 	case KVM_CAP_VM_ATTRIBUTES:
 	case KVM_CAP_MP_STATE:
+	case KVM_CAP_S390_INJECT_IRQ:
 	case KVM_CAP_S390_USER_SIGP:
 	case KVM_CAP_S390_USER_STSI:
 	case KVM_CAP_S390_SKEYS:
+	case KVM_CAP_S390_IRQ_STATE:
 		r = 1;
 		break;
 	case KVM_CAP_S390_MEM_OP:
@@ -1069,7 +1075,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		goto out_err;
 
 	spin_lock_init(&kvm->arch.float_int.lock);
-	INIT_LIST_HEAD(&kvm->arch.float_int.list);
+	for (i = 0; i < FIRQ_LIST_COUNT; i++)
+		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
 	init_waitqueue_head(&kvm->arch.ipte_wq);
 	mutex_init(&kvm->arch.ipte_mutex);
 
@@ -2389,6 +2396,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	long r;
 
 	switch (ioctl) {
+	case KVM_S390_IRQ: {
+		struct kvm_s390_irq s390irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
+			break;
+		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
+		break;
+	}
 	case KVM_S390_INTERRUPT: {
 		struct kvm_s390_interrupt s390int;
 		struct kvm_s390_irq s390irq;
@@ -2488,6 +2504,38 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_S390_SET_IRQ_STATE: {
+		struct kvm_s390_irq_state irq_state;
+
+		r = -EFAULT;
+		if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
+			break;
+		if (irq_state.len > VCPU_IRQS_MAX_BUF ||
+		    irq_state.len == 0 ||
+		    irq_state.len % sizeof(struct kvm_s390_irq) > 0) {
+			r = -EINVAL;
+			break;
+		}
+		r = kvm_s390_set_irq_state(vcpu,
+					   (void __user *) irq_state.buf,
+					   irq_state.len);
+		break;
+	}
+	case KVM_S390_GET_IRQ_STATE: {
+		struct kvm_s390_irq_state irq_state;
+
+		r = -EFAULT;
+		if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
+			break;
+		if (irq_state.len == 0) {
+			r = -EINVAL;
+			break;
+		}
+		r = kvm_s390_get_irq_state(vcpu,
+					   (__u8 __user *)  irq_state.buf,
+					   irq_state.len);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}

arch/s390/kvm/kvm-s390.h

@@ -178,7 +178,7 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 				      struct kvm_s390_irq *irq);
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
-						    u64 cr6, u64 schid);
+						    u64 isc_mask, u32 schid);
 int kvm_s390_reinject_io_int(struct kvm *kvm,
 			     struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
@@ -272,6 +272,10 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
 extern struct kvm_device_ops kvm_flic_ops;
 int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
+int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
+			   void __user *buf, int len);
+int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu,
+			   __u8 __user *buf, int len);
 
 /* implemented in guestdbg.c */
 void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);

arch/s390/kvm/priv.c

@@ -294,10 +294,13 @@ reinject_interrupt:
 
 static int handle_tsch(struct kvm_vcpu *vcpu)
 {
-	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_interrupt_info *inti = NULL;
+	const u64 isc_mask = 0xffUL << 24; /* all iscs set */
 
-	inti = kvm_s390_get_io_int(vcpu->kvm, 0,
+	/* a valid schid has at least one bit set */
-				   vcpu->run->s.regs.gprs[1]);
+	if (vcpu->run->s.regs.gprs[1])
+		inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask,
+					   vcpu->run->s.regs.gprs[1]);
 
 	/*
 	 * Prepare exit to userspace.

include/uapi/linux/kvm.h

@@ -558,6 +558,13 @@ struct kvm_s390_irq {
 	} u;
 };
 
+struct kvm_s390_irq_state {
+	__u64 buf;
+	__u32 flags;
+	__u32 len;
+	__u32 reserved[4];
+};
+
 /* for KVM_SET_GUEST_DEBUG */
 
 #define KVM_GUESTDBG_ENABLE		0x00000001
@@ -804,6 +811,8 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_S390_SKEYS 110
 #define KVM_CAP_MIPS_FPU 111
 #define KVM_CAP_MIPS_MSA 112
+#define KVM_CAP_S390_INJECT_IRQ 113
+#define KVM_CAP_S390_IRQ_STATE 114
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1184,6 +1193,11 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_S390_SKEYS */
 #define KVM_S390_GET_SKEYS      _IOW(KVMIO, 0xb2, struct kvm_s390_skeys)
 #define KVM_S390_SET_SKEYS      _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
+/* Available with KVM_CAP_S390_INJECT_IRQ */
+#define KVM_S390_IRQ              _IOW(KVMIO,  0xb4, struct kvm_s390_irq)
+/* Available with KVM_CAP_S390_IRQ_STATE */
+#define KVM_S390_SET_IRQ_STATE	  _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state)
+#define KVM_S390_GET_IRQ_STATE	  _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)

virt/kvm/kvm_main.c

@@ -2113,7 +2113,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,
 	 * so vcpu_load() would break it.
 	 */
-	if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT)
+	if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_S390_IRQ || ioctl == KVM_INTERRUPT)
 		return kvm_arch_vcpu_ioctl(filp, ioctl, arg);
 #endif