MSI-X MMIO support for KVM

index b5021db..7d313e0 100644
@@ -98,6 +98,29 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
+struct kvm_io_device;
+
+/**
+ * kvm_io_device_ops are called under kvm slots_lock.
+ * read and write handlers return 0 if the transaction has been handled,
+ * or non-zero to have it passed to the next device.
+ **/
+struct kvm_io_device_ops {
+	int (*read)(struct kvm_io_device *this,
+		    gpa_t addr,
+		    int len,
+		    void *val);
+	int (*write)(struct kvm_io_device *this,
+		     gpa_t addr,
+		     int len,
+		     const void *val);
+	void (*destructor)(struct kvm_io_device *this);
+};
+
+struct kvm_io_device {
+	const struct kvm_io_device_ops *ops;
+};
+
 struct kvm_vcpu {
 	struct kvm *kvm;
 #ifdef CONFIG_PREEMPT_NOTIFIERS

index 12fd3ca..d1f5651 100644
@@ -17,32 +17,9 @@
 #define __KVM_IODEV_H__
 
 #include <linux/kvm_types.h>
+#include <linux/kvm_host.h>
 #include <asm/errno.h>
 
-struct kvm_io_device;
-
-/**
- * kvm_io_device_ops are called under kvm slots_lock.
- * read and write handlers return 0 if the transaction has been handled,
- * or non-zero to have it passed to the next device.
- **/
-struct kvm_io_device_ops {
-	int (*read)(struct kvm_io_device *this,
-		    gpa_t addr,
-		    int len,
-		    void *val);
-	int (*write)(struct kvm_io_device *this,
-		     gpa_t addr,
-		     int len,
-		     const void *val);
-	void (*destructor)(struct kvm_io_device *this);
-};
-
-
-struct kvm_io_device {
-	const struct kvm_io_device_ops *ops;
-};
-
 static inline void kvm_iodevice_init(struct kvm_io_device *dev,
 				     const struct kvm_io_device_ops *ops)
 {

index efad723..bd8f0c5 100644
@@ -439,7 +439,8 @@ static inline int pit_in_range(gpa_t addr)
 }
 
 static int pit_ioport_write(struct kvm_io_device *this,
-			    gpa_t addr, int len, const void *data)
+			    gpa_t addr, int len, const void *data,
+			    struct kvm_io_ext_data *ext_data)
 {
 	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;

@@ -585,7 +586,8 @@ static int pit_ioport_read(struct kvm_io_device *this,
 }
 
 static int speaker_ioport_write(struct kvm_io_device *this,
-				gpa_t addr, int len, const void *data)
+				gpa_t addr, int len, const void *data,
+				struct kvm_io_ext_data *ext_data)
 {
 	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;

index 3cece05..96b1070 100644
@@ -480,7 +480,8 @@ static inline struct kvm_pic *to_pic(struct kvm_io_device *dev)
 }
 
 static int picdev_write(struct kvm_io_device *this,
-			 gpa_t addr, int len, const void *val)
+			 gpa_t addr, int len, const void *val,
+			 struct kvm_io_ext_data *ext_data)
 {
 	struct kvm_pic *s = to_pic(this);
 	unsigned char data = *(unsigned char *)val;

index 93cf9d0..f413e9c 100644
@@ -836,7 +836,8 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 }
 
 static int apic_mmio_write(struct kvm_io_device *this,
-			    gpa_t address, int len, const void *data)
+			    gpa_t address, int len, const void *data,
+			    struct kvm_io_ext_data *ext_data)
 {
 	struct kvm_lapic *apic = to_lapic(this);
 	unsigned int offset = address - apic->base_address;

index fa708c9..21b84e2 100644
@@ -3571,13 +3571,14 @@ static void kvm_init_msr_list(void)
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
-			   const void *v)
+			   const void *v, struct kvm_io_ext_data *ext_data)
 {
 	if (vcpu->arch.apic &&
-	    !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v))
+	    !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v, ext_data))
 		return 0;
 
-	return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
+	return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS,
+				addr, len, v, ext_data);
 }
 
 static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)

@@ -3807,6 +3808,7 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 					   struct kvm_vcpu *vcpu)
 {
 	gpa_t                 gpa;
+	struct kvm_io_ext_data ext_data;
 
 	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, exception);
 

@@ -3825,7 +3827,7 @@ mmio:
 	/*
 	 * Is this MMIO handled locally?
 	 */
-	if (!vcpu_mmio_write(vcpu, gpa, bytes, val))
+	if (!vcpu_mmio_write(vcpu, gpa, bytes, val, &ext_data))
 		return X86EMUL_CONTINUE;
 
 	vcpu->mmio_needed = 1;

@@ -3940,6 +3942,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 {
 	/* TODO: String I/O for in kernel device */
 	int r;
+	struct kvm_io_ext_data ext_data;
 
 	if (vcpu->arch.pio.in)
 		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,

@@ -3947,7 +3950,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 	else
 		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
 				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
+				     pd, &ext_data);
 	return r;
 }
 

index 7d313e0..6bb211d 100644
@@ -68,8 +68,15 @@ enum kvm_bus {
 	KVM_NR_BUSES
 };
 
+struct kvm_io_ext_data {
+	int type;
+	union {
+		char padding[256];
+	};
+};
+
 int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
-		     int len, const void *val);
+		     int len, const void *val, struct kvm_io_ext_data *data);
 int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len,
 		    void *val);
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,

@@ -113,7 +120,8 @@ struct kvm_io_device_ops {
 	int (*write)(struct kvm_io_device *this,
 		     gpa_t addr,
 		     int len,
-		     const void *val);
+		     const void *val,
+		     struct kvm_io_ext_data *data);
 	void (*destructor)(struct kvm_io_device *this);
 };
 

index fc84875..37b254c 100644
@@ -59,7 +59,8 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
 }
 
 static int coalesced_mmio_write(struct kvm_io_device *this,
-				gpa_t addr, int len, const void *val)
+				gpa_t addr, int len, const void *val,
+				struct kvm_io_ext_data *ext_data)
 {
 	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;

index 2ca4535..8edd757 100644
@@ -483,7 +483,7 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
 /* MMIO/PIO writes trigger an event if the addr/val match */
 static int
 ioeventfd_write(struct kvm_io_device *this, gpa_t addr, int len,
-		const void *val)
+		const void *val, struct kvm_io_ext_data *ext_data)
 {
 	struct _ioeventfd *p = to_ioeventfd(this);
 

index 0b9df83..6a027ef 100644
@@ -321,7 +321,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 }
 
 static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
-			     const void *val)
+			     const void *val, struct kvm_io_ext_data *ext_data)
 {
 	struct kvm_ioapic *ioapic = to_ioapic(this);
 	u32 data;

index d1f5651..340ab79 100644
@@ -33,9 +33,11 @@ static inline int kvm_iodevice_read(struct kvm_io_device *dev,
 }
 
 static inline int kvm_iodevice_write(struct kvm_io_device *dev,
-				     gpa_t addr, int l, const void *v)
+				     gpa_t addr, int l, const void *v,
+				     struct kvm_io_ext_data *data)
 {
-	return dev->ops->write ? dev->ops->write(dev, addr, l, v) : -EOPNOTSUPP;
+	return dev->ops->write ?
+		dev->ops->write(dev, addr, l, v, data) : -EOPNOTSUPP;
 }
 
 static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)

index b1b6cbb..a61f90e 100644
@@ -2221,14 +2221,14 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 
 /* kvm_io_bus_write - called under kvm->slots_lock */
 int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
-		     int len, const void *val)
+		     int len, const void *val, struct kvm_io_ext_data *ext_data)
 {
 	int i;
 	struct kvm_io_bus *bus;
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
 	for (i = 0; i < bus->dev_count; i++)
-		if (!kvm_iodevice_write(bus->devs[i], addr, len, val))
+		if (!kvm_iodevice_write(bus->devs[i], addr, len, val, ext_data))
 			return 0;
 	return -EOPNOTSUPP;
 }

index 21b84e2..43a5e70 100644
@@ -1966,6 +1966,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
 	case KVM_CAP_XSAVE:
 	case KVM_CAP_ASYNC_PF:
+	case KVM_CAP_MSIX_MMIO:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

@@ -3809,6 +3810,7 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 {
 	gpa_t                 gpa;
 	struct kvm_io_ext_data ext_data;
+	int r;
 
 	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, exception);
 

@@ -3824,18 +3826,31 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 
 mmio:
 	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
+	r = vcpu_mmio_write(vcpu, gpa, bytes, val, &ext_data);
 	/*
 	 * Is this MMIO handled locally?
 	 */
-	if (!vcpu_mmio_write(vcpu, gpa, bytes, val, &ext_data))
+	if (!r)
 		return X86EMUL_CONTINUE;
 
-	vcpu->mmio_needed = 1;
-	vcpu->run->exit_reason = KVM_EXIT_MMIO;
-	vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
-	vcpu->run->mmio.len = vcpu->mmio_size = bytes;
-	vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1;
-	memcpy(vcpu->run->mmio.data, val, bytes);
+	if (r == -ENOTSYNC) {
+		vcpu->run->exit_reason = KVM_EXIT_MSIX_ROUTING_UPDATE;
+		vcpu->run->msix_routing.dev_id =
+			ext_data.msix_routing.dev_id;
+		vcpu->run->msix_routing.type =
+			ext_data.msix_routing.type;
+		vcpu->run->msix_routing.entry_idx =
+			ext_data.msix_routing.entry_idx;
+		vcpu->run->msix_routing.flags =
+			ext_data.msix_routing.flags;
+	} else  {
+		vcpu->mmio_needed = 1;
+		vcpu->run->exit_reason = KVM_EXIT_MMIO;
+		vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
+		vcpu->run->mmio.len = vcpu->mmio_size = bytes;
+		vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1;
+		memcpy(vcpu->run->mmio.data, val, bytes);
+	}
 
 	return X86EMUL_CONTINUE;
 }

index ea2dc1a..4393e4e 100644
@@ -161,6 +161,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_NMI              16
 #define KVM_EXIT_INTERNAL_ERROR   17
 #define KVM_EXIT_OSI              18
+#define KVM_EXIT_MSIX_ROUTING_UPDATE 19
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1

@@ -264,6 +265,13 @@ struct kvm_run {
 		struct {
 			__u64 gprs[32];
 		} osi;
+		/* KVM_EXIT_MSIX_ROUTING_UPDATE*/
+		struct {
+			__u32 dev_id;
+			__u16 type;
+			__u16 entry_idx;
+			__u64 flags;
+		} msix_routing;
 		/* Fix the size of the union. */
 		char padding[256];
 	};

@@ -541,6 +549,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_GET_PVINFO 57
 #define KVM_CAP_PPC_IRQ_LEVEL 58
 #define KVM_CAP_ASYNC_PF 59
+#define KVM_CAP_MSIX_MMIO 60
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -672,6 +681,9 @@ struct kvm_clock_data {
 #define KVM_XEN_HVM_CONFIG        _IOW(KVMIO,  0x7a, struct kvm_xen_hvm_config)
 #define KVM_SET_CLOCK             _IOW(KVMIO,  0x7b, struct kvm_clock_data)
 #define KVM_GET_CLOCK             _IOR(KVMIO,  0x7c, struct kvm_clock_data)
+/* Available with KVM_CAP_MSIX_MMIO */
+#define KVM_REGISTER_MSIX_MMIO    _IOW(KVMIO,  0x7d, struct kvm_msix_mmio_user)
+#define KVM_UNREGISTER_MSIX_MMIO  _IOW(KVMIO,  0x7e, struct kvm_msix_mmio_user)
 /* Available with KVM_CAP_PIT_STATE2 */
 #define KVM_GET_PIT2              _IOR(KVMIO,  0x9f, struct kvm_pit_state2)
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)

@@ -795,4 +807,20 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+#define KVM_MSIX_MMIO_TYPE_ASSIGNED_DEV	    (1 << 0)
+
+#define KVM_MSIX_MMIO_TYPE_BASE_TABLE	    (1 << 8)
+
+#define KVM_MSIX_MMIO_TYPE_DEV_MASK	    0x00ff
+#define KVM_MSIX_MMIO_TYPE_BASE_MASK	    0xff00
+struct kvm_msix_mmio_user {
+	__u32 dev_id;
+	__u16 type;
+	__u16 max_entries_nr;
+	__u64 base_addr;
+	__u64 base_va;
+	__u64 flags;
+	__u64 reserved[4];
+};
+
 #endif /* __LINUX_KVM_H */

index 6bb211d..d6d8654 100644
@@ -68,9 +68,16 @@ enum kvm_bus {
 	KVM_NR_BUSES
 };
 
+#define KVM_IO_EXT_DATA_TYPE_MSIX_ROUTING   1
 struct kvm_io_ext_data {
 	int type;
 	union {
+		struct {
+			u32 dev_id;
+			u16 type;
+			u16 entry_idx;
+			u64 flags;
+		} msix_routing;
 		char padding[256];
 	};
 };

@@ -241,6 +248,27 @@ struct kvm_memslots {
 					KVM_PRIVATE_MEM_SLOTS];
 };
 
+#define KVM_MSIX_MMIO_MAX    32
+
+struct kvm_msix_mmio {
+	u32 dev_id;
+	u16 type;
+	u16 max_entries_nr;
+	u64 flags;
+	gpa_t table_base_addr;
+	hva_t table_base_va;
+	gpa_t pba_base_addr;
+	hva_t pba_base_va;
+};
+
+struct kvm_msix_mmio_dev {
+	struct kvm *kvm;
+	struct kvm_io_device table_dev;
+	int mmio_nr;
+	struct kvm_msix_mmio mmio[KVM_MSIX_MMIO_MAX];
+	struct mutex lock;
+};
+
 struct kvm {
 	spinlock_t mmu_lock;
 	raw_spinlock_t requests_lock;

@@ -289,6 +317,7 @@ struct kvm {
 	long mmu_notifier_count;
 #endif
 	long tlbs_dirty;
+	struct kvm_msix_mmio_dev msix_mmio_dev;
 };
 
 /* The guest did something we don't support. */

@@ -561,6 +590,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 
+int kvm_assigned_device_update_msix_mask_bit(struct kvm *kvm,
+			int assigned_dev_id, int entry, bool mask);
+
 /* For vcpu->arch.iommu_flags */
 #define KVM_IOMMU_CACHE_COHERENCY	0x1
 

65 lines not on this page · raw message

index a61f90e..f211e49 100644
@@ -56,6 +56,7 @@
 
 #include "coalesced_mmio.h"
 #include "async_pf.h"
+#include "msix_mmio.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>

@@ -509,6 +510,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	struct mm_struct *mm = kvm->mm;
 
 	kvm_arch_sync_events(kvm);
+	kvm_unregister_msix_mmio_dev(kvm);
 	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
 	spin_unlock(&kvm_lock);

@@ -1877,6 +1879,24 @@ static long kvm_vm_ioctl(struct file *filp,
 		mutex_unlock(&kvm->lock);
 		break;
 #endif
+	case KVM_REGISTER_MSIX_MMIO: {
+		struct kvm_msix_mmio_user mmio_user;
+
+		r = -EFAULT;
+		if (copy_from_user(&mmio_user, argp, sizeof mmio_user))
+			goto out;
+		r = kvm_vm_ioctl_register_msix_mmio(kvm, &mmio_user);
+		break;
+	}
+	case KVM_UNREGISTER_MSIX_MMIO: {
+		struct kvm_msix_mmio_user mmio_user;
+
+		r = -EFAULT;
+		if (copy_from_user(&mmio_user, argp, sizeof mmio_user))
+			goto out;
+		r = kvm_vm_ioctl_unregister_msix_mmio(kvm, &mmio_user);
+		break;
+	}
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)

@@ -1988,6 +2008,12 @@ static int kvm_dev_ioctl_create_vm(void)
 		return r;
 	}
 #endif
+	r = kvm_register_msix_mmio_dev(kvm);
+	if (r < 0) {
+		kvm_put_kvm(kvm);
+		return r;
+	}
+
 	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
 	if (r < 0)
 		kvm_put_kvm(kvm);

@@ -2223,14 +2249,18 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val, struct kvm_io_ext_data *ext_data)
 {
-	int i;
+	int i, r = -EOPNOTSUPP;
 	struct kvm_io_bus *bus;
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	for (i = 0; i < bus->dev_count; i++)
-		if (!kvm_iodevice_write(bus->devs[i], addr, len, val, ext_data))
+	for (i = 0; i < bus->dev_count; i++) {
+		r = kvm_iodevice_write(bus->devs[i], addr, len, val, ext_data);
+		if (r == -ENOTSYNC)
+			break;
+		else if (!r)
 			return 0;
-	return -EOPNOTSUPP;
+	}
+	return r;
 }
 
 /* kvm_io_bus_read - called under kvm->slots_lock */

293 lines not on this page · raw message

new file mode 100644
index 0000000..01b6587
@@ -0,0 +1,25 @@
+#ifndef __KVM_MSIX_MMIO_H__
+#define __KVM_MSIX_MMIO_H__
+/*
+ * MSI-X MMIO emulation
+ *
+ * Copyright (c) 2010 Intel Corporation
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Author:
+ *   Sheng Yang <[email protected]>
+ */
+
+#include <linux/pci.h>
+
+int kvm_register_msix_mmio_dev(struct kvm *kvm);
+int kvm_unregister_msix_mmio_dev(struct kvm *kvm);
+int kvm_vm_ioctl_register_msix_mmio(struct kvm *kvm,
+				    struct kvm_msix_mmio_user *mmio_user);
+int kvm_vm_ioctl_unregister_msix_mmio(struct kvm *kvm,
+				      struct kvm_msix_mmio_user *mmio_user);
+int kvm_free_msix_mmio(struct kvm *kvm, struct kvm_msix_mmio *mmio_user);
+
+#endif