Merge tag 'kvm-ppc-next-5.2-2' of...

Merge tag 'kvm-ppc-next-5.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

PPC KVM update for 5.2

* Support for guests to access the new POWER9 XIVE interrupt controller
  hardware directly, reducing interrupt latency and overhead for guests.

* In-kernel implementation of the H_PAGE_INIT hypercall.

* Reduce memory usage of sparsely-populated IOMMU tables.

* Several bug fixes.

Second PPC KVM update for 5.2

* Fix a bug, fix a spelling mistake, remove some useless code.

Documentation/powerpc/DAWR-POWER9.txt

@@ -56,3 +56,35 @@ POWER9. Loads and stores to the watchpoint locations will not be
 trapped in GDB. The watchpoint is remembered, so if the guest is
 migrated back to the POWER8 host, it will start working again.
 
+Force enabling the DAWR
+=============================
+Kernels (since ~v5.2) have an option to force enable the DAWR via:
+
+  echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous
+
+This enables the DAWR even on POWER9.
+
+This is a dangerous setting, USE AT YOUR OWN RISK.
+
+Some users may not care about a bad user crashing their box
+(ie. single user/desktop systems) and really want the DAWR.  This
+allows them to force enable DAWR.
+
+This flag can also be used to disable DAWR access. Once this is
+cleared, all DAWR access should be cleared immediately and your
+machine once again safe from crashing.
+
+Userspace may get confused by toggling this. If DAWR is force
+enabled/disabled between getting the number of breakpoints (via
+PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an
+inconsistent view of what's available. Similarly for guests.
+
+For the DAWR to be enabled in a KVM guest, the DAWR needs to be force
+enabled in the host AND the guest. For this reason, this won't work on
+POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the
+dawr_enable_dangerous file will fail if the hypervisor doesn't support
+writing the DAWR.
+
+To double check the DAWR is working, run this kernel selftest:
+  tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
+Any errors/failures/skips mean something is wrong.

Documentation/virtual/kvm/api.txt

@@ -1967,6 +1967,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB3PS            | 32
   PPC   | KVM_REG_PPC_EPTCFG            | 32
   PPC   | KVM_REG_PPC_ICP_STATE         | 64
+  PPC   | KVM_REG_PPC_VP_STATE          | 128
   PPC   | KVM_REG_PPC_TB_OFFSET         | 64
   PPC   | KVM_REG_PPC_SPMC1             | 32
   PPC   | KVM_REG_PPC_SPMC2             | 32
@@ -4487,6 +4488,15 @@ struct kvm_sync_regs {
         struct kvm_vcpu_events events;
 };
 
+6.75 KVM_CAP_PPC_IRQ_XIVE
+
+Architectures: ppc
+Target: vcpu
+Parameters: args[0] is the XIVE device fd
+            args[1] is the XIVE CPU number (server ID) for this vcpu
+
+This capability connects the vcpu to an in-kernel XIVE device.
+
 7. Capabilities that can be enabled on VMs
 ------------------------------------------
 

Documentation/virtual/kvm/devices/xive.txt

+POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1)
+==========================================================
+
+Device types supported:
+  KVM_DEV_TYPE_XIVE     POWER9 XIVE Interrupt Controller generation 1
+
+This device acts as a VM interrupt controller. It provides the KVM
+interface to configure the interrupt sources of a VM in the underlying
+POWER9 XIVE interrupt controller.
+
+Only one XIVE instance may be instantiated. A guest XIVE device
+requires a POWER9 host and the guest OS should have support for the
+XIVE native exploitation interrupt mode. If not, it should run using
+the legacy interrupt mode, referred as XICS (POWER7/8).
+
+* Device Mappings
+
+  The KVM device exposes different MMIO ranges of the XIVE HW which
+  are required for interrupt management. These are exposed to the
+  guest in VMAs populated with a custom VM fault handler.
+
+  1. Thread Interrupt Management Area (TIMA)
+
+  Each thread has an associated Thread Interrupt Management context
+  composed of a set of registers. These registers let the thread
+  handle priority management and interrupt acknowledgment. The most
+  important are :
+
+      - Interrupt Pending Buffer     (IPB)
+      - Current Processor Priority   (CPPR)
+      - Notification Source Register (NSR)
+
+  They are exposed to software in four different pages each proposing
+  a view with a different privilege. The first page is for the
+  physical thread context and the second for the hypervisor. Only the
+  third (operating system) and the fourth (user level) are exposed the
+  guest.
+
+  2. Event State Buffer (ESB)
+
+  Each source is associated with an Event State Buffer (ESB) with
+  either a pair of even/odd pair of pages which provides commands to
+  manage the source: to trigger, to EOI, to turn off the source for
+  instance.
+
+  3. Device pass-through
+
+  When a device is passed-through into the guest, the source
+  interrupts are from a different HW controller (PHB4) and the ESB
+  pages exposed to the guest should accommadate this change.
+
+  The passthru_irq helpers, kvmppc_xive_set_mapped() and
+  kvmppc_xive_clr_mapped() are called when the device HW irqs are
+  mapped into or unmapped from the guest IRQ number space. The KVM
+  device extends these helpers to clear the ESB pages of the guest IRQ
+  number being mapped and then lets the VM fault handler repopulate.
+  The handler will insert the ESB page corresponding to the HW
+  interrupt of the device being passed-through or the initial IPI ESB
+  page if the device has being removed.
+
+  The ESB remapping is fully transparent to the guest and the OS
+  device driver. All handling is done within VFIO and the above
+  helpers in KVM-PPC.
+
+* Groups:
+
+  1. KVM_DEV_XIVE_GRP_CTRL
+  Provides global controls on the device
+  Attributes:
+    1.1 KVM_DEV_XIVE_RESET (write only)
+    Resets the interrupt controller configuration for sources and event
+    queues. To be used by kexec and kdump.
+    Errors: none
+
+    1.2 KVM_DEV_XIVE_EQ_SYNC (write only)
+    Sync all the sources and queues and mark the EQ pages dirty. This
+    to make sure that a consistent memory state is captured when
+    migrating the VM.
+    Errors: none
+
+  2. KVM_DEV_XIVE_GRP_SOURCE (write only)
+  Initializes a new source in the XIVE device and mask it.
+  Attributes:
+    Interrupt source number  (64-bit)
+  The kvm_device_attr.addr points to a __u64 value:
+  bits:     | 63   ....  2 |   1   |   0
+  values:   |    unused    | level | type
+  - type:  0:MSI 1:LSI
+  - level: assertion level in case of an LSI.
+  Errors:
+    -E2BIG:  Interrupt source number is out of range
+    -ENOMEM: Could not create a new source block
+    -EFAULT: Invalid user pointer for attr->addr.
+    -ENXIO:  Could not allocate underlying HW interrupt
+
+  3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only)
+  Configures source targeting
+  Attributes:
+    Interrupt source number  (64-bit)
+  The kvm_device_attr.addr points to a __u64 value:
+  bits:     | 63   ....  33 |  32  | 31 .. 3 |  2 .. 0
+  values:   |    eisn       | mask |  server | priority
+  - priority: 0-7 interrupt priority level
+  - server: CPU number chosen to handle the interrupt
+  - mask: mask flag (unused)
+  - eisn: Effective Interrupt Source Number
+  Errors:
+    -ENOENT: Unknown source number
+    -EINVAL: Not initialized source number
+    -EINVAL: Invalid priority
+    -EINVAL: Invalid CPU number.
+    -EFAULT: Invalid user pointer for attr->addr.
+    -ENXIO:  CPU event queues not configured or configuration of the
+             underlying HW interrupt failed
+    -EBUSY:  No CPU available to serve interrupt
+
+  4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
+  Configures an event queue of a CPU
+  Attributes:
+    EQ descriptor identifier (64-bit)
+  The EQ descriptor identifier is a tuple (server, priority) :
+  bits:     | 63   ....  32 | 31 .. 3 |  2 .. 0
+  values:   |    unused     |  server | priority
+  The kvm_device_attr.addr points to :
+    struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+    };
+  - flags: queue flags
+    KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
+	forces notification without using the coalescing mechanism
+	provided by the XIVE END ESBs.
+  - qshift: queue size (power of 2)
+  - qaddr: real address of queue
+  - qtoggle: current queue toggle bit
+  - qindex: current queue index
+  - pad: reserved for future use
+  Errors:
+    -ENOENT: Invalid CPU number
+    -EINVAL: Invalid priority
+    -EINVAL: Invalid flags
+    -EINVAL: Invalid queue size
+    -EINVAL: Invalid queue address
+    -EFAULT: Invalid user pointer for attr->addr.
+    -EIO:    Configuration of the underlying HW failed
+
+  5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only)
+  Synchronize the source to flush event notifications
+  Attributes:
+    Interrupt source number  (64-bit)
+  Errors:
+    -ENOENT: Unknown source number
+    -EINVAL: Not initialized source number
+
+* VCPU state
+
+  The XIVE IC maintains VP interrupt state in an internal structure
+  called the NVT. When a VP is not dispatched on a HW processor
+  thread, this structure can be updated by HW if the VP is the target
+  of an event notification.
+
+  It is important for migration to capture the cached IPB from the NVT
+  as it synthesizes the priorities of the pending interrupts. We
+  capture a bit more to report debug information.
+
+  KVM_REG_PPC_VP_STATE (2 * 64bits)
+  bits:     |  63  ....  32  |  31  ....  0  |
+  values:   |   TIMA word0   |   TIMA word1  |
+  bits:     | 127       ..........       64  |
+  values:   |            unused              |
+
+* Migration:
+
+  Saving the state of a VM using the XIVE native exploitation mode
+  should follow a specific sequence. When the VM is stopped :
+
+  1. Mask all sources (PQ=01) to stop the flow of events.
+
+  2. Sync the XIVE device with the KVM control KVM_DEV_XIVE_EQ_SYNC to
+  flush any in-flight event notification and to stabilize the EQs. At
+  this stage, the EQ pages are marked dirty to make sure they are
+  transferred in the migration sequence.
+
+  3. Capture the state of the source targeting, the EQs configuration
+  and the state of thread interrupt context registers.
+
+  Restore is similar :
+
+  1. Restore the EQ configuration. As targeting depends on it.
+  2. Restore targeting
+  3. Restore the thread interrupt contexts
+  4. Restore the source states
+  5. Let the vCPU run

arch/powerpc/include/asm/hw_breakpoint.h

@@ -90,10 +90,18 @@ static inline void hw_breakpoint_disable(void)
 extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs);
 int hw_breakpoint_handler(struct die_args *args);
 
+extern int set_dawr(struct arch_hw_breakpoint *brk);
+extern bool dawr_force_enable;
+static inline bool dawr_enabled(void)
+{
+	return dawr_force_enable;
+}
+
 #else	/* CONFIG_HAVE_HW_BREAKPOINT */
 static inline void hw_breakpoint_disable(void) { }
 static inline void thread_change_pc(struct task_struct *tsk,
 					struct pt_regs *regs) { }
+static inline bool dawr_enabled(void) { return false; }
 #endif	/* CONFIG_HAVE_HW_BREAKPOINT */
 #endif	/* __KERNEL__ */
 #endif	/* _PPC_BOOK3S_64_HW_BREAKPOINT_H */

arch/powerpc/include/asm/kvm_host.h

@@ -201,6 +201,8 @@ struct kvmppc_spapr_tce_iommu_table {
 	struct kref kref;
 };
 
+#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+
 struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
@@ -210,6 +212,7 @@ struct kvmppc_spapr_tce_table {
 	u64 offset;		/* in pages */
 	u64 size;		/* window size in pages */
 	struct list_head iommu_tables;
+	struct mutex alloc_lock;
 	struct page *pages[0];
 };
 
@@ -222,6 +225,7 @@ extern struct kvm_device_ops kvm_xics_ops;
 struct kvmppc_xive;
 struct kvmppc_xive_vcpu;
 extern struct kvm_device_ops kvm_xive_ops;
+extern struct kvm_device_ops kvm_xive_native_ops;
 
 struct kvmppc_passthru_irqmap;
 
@@ -312,7 +316,11 @@ struct kvm_arch {
 #endif
 #ifdef CONFIG_KVM_XICS
 	struct kvmppc_xics *xics;
-	struct kvmppc_xive *xive;
+	struct kvmppc_xive *xive;    /* Current XIVE device in use */
+	struct {
+		struct kvmppc_xive *native;
+		struct kvmppc_xive *xics_on_xive;
+	} xive_devices;
 	struct kvmppc_passthru_irqmap *pimap;
 #endif
 	struct kvmppc_ops *kvm_ops;
@@ -449,6 +457,7 @@ struct kvmppc_passthru_irqmap {
 #define KVMPPC_IRQ_DEFAULT	0
 #define KVMPPC_IRQ_MPIC		1
 #define KVMPPC_IRQ_XICS		2 /* Includes a XIVE option */
+#define KVMPPC_IRQ_XIVE		3 /* XIVE native exploitation mode */
 
 #define MMIO_HPTE_CACHE_SIZE	4
 

arch/powerpc/include/asm/kvm_ppc.h

@@ -197,10 +197,6 @@ extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
 		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
 				(stt)->size, (ioba), (npages)) ?        \
 				H_PARAMETER : H_SUCCESS)
-extern long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
-		unsigned long *ua, unsigned long **prmap);
-extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
-		unsigned long idx, unsigned long tce);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
 extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
@@ -273,6 +269,7 @@ union kvmppc_one_reg {
 		u64	addr;
 		u64	length;
 	}	vpaval;
+	u64	xive_timaval[2];
 };
 
 struct kvmppc_ops {
@@ -480,6 +477,9 @@ extern void kvm_hv_vm_activated(void);
 extern void kvm_hv_vm_deactivated(void);
 extern bool kvm_hv_mode_active(void);
 
+extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+					struct kvm_nested_guest *nested);
+
 #else
 static inline void __init kvm_cma_reserve(void)
 {}
@@ -594,6 +594,22 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
 extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 			       int level, bool line_status);
 extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
+
+static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.irq_type == KVMPPC_IRQ_XIVE;
+}
+
+extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+					   struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
+extern void kvmppc_xive_native_init_module(void);
+extern void kvmppc_xive_native_exit_module(void);
+extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
+				     union kvmppc_one_reg *val);
+extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
+				     union kvmppc_one_reg *val);
+
 #else
 static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
 				       u32 priority) { return -1; }
@@ -617,6 +633,21 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur
 static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 				      int level, bool line_status) { return -ENODEV; }
 static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
+
+static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
+	{ return 0; }
+static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+			  struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
+static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
+static inline void kvmppc_xive_native_init_module(void) { }
+static inline void kvmppc_xive_native_exit_module(void) { }
+static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
+					    union kvmppc_one_reg *val)
+{ return 0; }
+static inline int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
+					    union kvmppc_one_reg *val)
+{ return -ENOENT; }
+
 #endif /* CONFIG_KVM_XIVE */
 
 #if defined(CONFIG_PPC_POWERNV) && defined(CONFIG_KVM_BOOK3S_64_HANDLER)
@@ -665,6 +696,8 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
                         unsigned long pte_index);
 long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
                         unsigned long pte_index);
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src);
 long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
                           unsigned long slb_v, unsigned int status, bool data);
 unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);

arch/powerpc/include/asm/opal-api.h

@@ -186,8 +186,8 @@
 #define OPAL_XIVE_FREE_IRQ			140
 #define OPAL_XIVE_SYNC				141
 #define OPAL_XIVE_DUMP				142
-#define OPAL_XIVE_RESERVED3			143
-#define OPAL_XIVE_RESERVED4			144
+#define OPAL_XIVE_GET_QUEUE_STATE		143
+#define OPAL_XIVE_SET_QUEUE_STATE		144
 #define OPAL_SIGNAL_SYSTEM_RESET		145
 #define OPAL_NPU_INIT_CONTEXT			146
 #define OPAL_NPU_DESTROY_CONTEXT		147
@@ -210,7 +210,8 @@
 #define OPAL_PCI_GET_PBCQ_TUNNEL_BAR		164
 #define OPAL_PCI_SET_PBCQ_TUNNEL_BAR		165
 #define	OPAL_NX_COPROC_INIT			167
-#define OPAL_LAST				167
+#define OPAL_XIVE_GET_VP_STATE			170
+#define OPAL_LAST				170
 
 #define QUIESCE_HOLD			1 /* Spin all calls at entry */
 #define QUIESCE_REJECT			2 /* Fail all calls with OPAL_BUSY */

arch/powerpc/include/asm/opal.h

@@ -279,6 +279,13 @@ int64_t opal_xive_allocate_irq(uint32_t chip_id);
 int64_t opal_xive_free_irq(uint32_t girq);
 int64_t opal_xive_sync(uint32_t type, uint32_t id);
 int64_t opal_xive_dump(uint32_t type, uint32_t id);
+int64_t opal_xive_get_queue_state(uint64_t vp, uint32_t prio,
+				  __be32 *out_qtoggle,
+				  __be32 *out_qindex);
+int64_t opal_xive_set_queue_state(uint64_t vp, uint32_t prio,
+				  uint32_t qtoggle,
+				  uint32_t qindex);
+int64_t opal_xive_get_vp_state(uint64_t vp, __be64 *out_w01);
 int64_t opal_pci_set_p2p(uint64_t phb_init, uint64_t phb_target,
 			uint64_t desc, uint16_t pe_number);
 

arch/powerpc/include/asm/xive.h

@@ -23,6 +23,7 @@
  * same offset regardless of where the code is executing
  */
 extern void __iomem *xive_tima;
+extern unsigned long xive_tima_os;
 
 /*
  * Offset in the TM area of our current execution level (provided by
@@ -73,6 +74,8 @@ struct xive_q {
 	u32			esc_irq;
 	atomic_t		count;
 	atomic_t		pending_count;
+	u64			guest_qaddr;
+	u32			guest_qshift;
 };
 
 /* Global enable flags for the XIVE support */
@@ -109,12 +112,26 @@ extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
 extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
 
 extern void xive_native_sync_source(u32 hw_irq);
+extern void xive_native_sync_queue(u32 hw_irq);
 extern bool is_xive_irq(struct irq_chip *chip);
 extern int xive_native_enable_vp(u32 vp_id, bool single_escalation);
 extern int xive_native_disable_vp(u32 vp_id);
 extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
 extern bool xive_native_has_single_escalation(void);
 
+extern int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
+				      u64 *out_qpage,
+				      u64 *out_qsize,
+				      u64 *out_qeoi_page,
+				      u32 *out_escalate_irq,
+				      u64 *out_qflags);
+
+extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle,
+				       u32 *qindex);
+extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle,
+				       u32 qindex);
+extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state);
+
 #else
 
 static inline bool xive_enabled(void) { return false; }

arch/powerpc/include/uapi/asm/kvm.h

@@ -482,6 +482,8 @@ struct kvm_ppc_cpu_char {
 #define  KVM_REG_PPC_ICP_PPRI_SHIFT	16	/* pending irq priority */
 #define  KVM_REG_PPC_ICP_PPRI_MASK	0xff
 
+#define KVM_REG_PPC_VP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x8d)
+
 /* Device control API: PPC-specific devices */
 #define KVM_DEV_MPIC_GRP_MISC		1
 #define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
@@ -677,4 +679,48 @@ struct kvm_ppc_cpu_char {
 #define  KVM_XICS_PRESENTED		(1ULL << 43)
 #define  KVM_XICS_QUEUED		(1ULL << 44)
 
+/* POWER9 XIVE Native Interrupt Controller */
+#define KVM_DEV_XIVE_GRP_CTRL		1
+#define   KVM_DEV_XIVE_RESET		1
+#define   KVM_DEV_XIVE_EQ_SYNC		2
+#define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_SYNC	5       /* 64-bit source identifier */
+
+/* Layout of 64-bit XIVE source attribute values */
+#define KVM_XIVE_LEVEL_SENSITIVE	(1ULL << 0)
+#define KVM_XIVE_LEVEL_ASSERTED		(1ULL << 1)
+
+/* Layout of 64-bit XIVE source configuration attribute values */
+#define KVM_XIVE_SOURCE_PRIORITY_SHIFT	0
+#define KVM_XIVE_SOURCE_PRIORITY_MASK	0x7
+#define KVM_XIVE_SOURCE_SERVER_SHIFT	3
+#define KVM_XIVE_SOURCE_SERVER_MASK	0xfffffff8ULL
+#define KVM_XIVE_SOURCE_MASKED_SHIFT	32
+#define KVM_XIVE_SOURCE_MASKED_MASK	0x100000000ULL
+#define KVM_XIVE_SOURCE_EISN_SHIFT	33
+#define KVM_XIVE_SOURCE_EISN_MASK	0xfffffffe00000000ULL
+
+/* Layout of 64-bit EQ identifier */
+#define KVM_XIVE_EQ_PRIORITY_SHIFT	0
+#define KVM_XIVE_EQ_PRIORITY_MASK	0x7
+#define KVM_XIVE_EQ_SERVER_SHIFT	3
+#define KVM_XIVE_EQ_SERVER_MASK		0xfffffff8ULL
+
+/* Layout of EQ configuration values (64 bytes) */
+struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+};
+
+#define KVM_XIVE_EQ_ALWAYS_NOTIFY	0x00000001
+
+#define KVM_XIVE_TIMA_PAGE_OFFSET	0
+#define KVM_XIVE_ESB_PAGE_OFFSET	4
+
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/kernel/hw_breakpoint.c

@@ -29,11 +29,15 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
 
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/hvcall.h>
 #include <linux/uaccess.h>
 
 /*
@@ -174,7 +178,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 	if (!ppc_breakpoint_available())
 		return -ENODEV;
 	length_max = 8; /* DABR */
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
 		if ((attr->bp_addr >> 9) !=
@@ -376,3 +380,59 @@ void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
+
+bool dawr_force_enable;
+EXPORT_SYMBOL_GPL(dawr_force_enable);
+
+static ssize_t dawr_write_file_bool(struct file *file,
+				    const char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct arch_hw_breakpoint null_brk = {0, 0, 0};
+	size_t rc;
+
+	/* Send error to user if they hypervisor won't allow us to write DAWR */
+	if ((!dawr_force_enable) &&
+	    (firmware_has_feature(FW_FEATURE_LPAR)) &&
+	    (set_dawr(&null_brk) != H_SUCCESS))
+		return -1;
+
+	rc = debugfs_write_file_bool(file, user_buf, count, ppos);
+	if (rc)
+		return rc;
+
+	/* If we are clearing, make sure all CPUs have the DAWR cleared */
+	if (!dawr_force_enable)
+		smp_call_function((smp_call_func_t)set_dawr, &null_brk, 0);
+
+	return rc;
+}
+
+static const struct file_operations dawr_enable_fops = {
+	.read =		debugfs_read_file_bool,
+	.write =	dawr_write_file_bool,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int __init dawr_force_setup(void)
+{
+	dawr_force_enable = false;
+
+	if (cpu_has_feature(CPU_FTR_DAWR)) {
+		/* Don't setup sysfs file for user control on P8 */
+		dawr_force_enable = true;
+		return 0;
+	}
+
+	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
+		/* Turn DAWR off by default, but allow admin to turn it on */
+		dawr_force_enable = false;
+		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
+					   powerpc_debugfs_root,
+					   &dawr_force_enable,
+					   &dawr_enable_fops);
+	}
+	return 0;
+}
+arch_initcall(dawr_force_setup);

arch/powerpc/kernel/process.c

@@ -67,6 +67,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/asm-prototypes.h>
 #include <asm/stacktrace.h>
+#include <asm/hw_breakpoint.h>
 
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -784,7 +785,7 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk)
 	return __set_dabr(dabr, dabrx);
 }
 
-static inline int set_dawr(struct arch_hw_breakpoint *brk)
+int set_dawr(struct arch_hw_breakpoint *brk)
 {
 	unsigned long dawr, dawrx, mrd;
 
@@ -816,7 +817,7 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
-	if (cpu_has_feature(CPU_FTR_DAWR))
+	if (dawr_enabled())
 		// Power8 or later
 		set_dawr(brk);
 	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
@@ -830,8 +831,8 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 /* Check if we have DAWR or DABR hardware */
 bool ppc_breakpoint_available(void)
 {
-	if (cpu_has_feature(CPU_FTR_DAWR))
-		return true; /* POWER8 DAWR */
+	if (dawr_enabled())
+		return true; /* POWER8 DAWR or POWER9 forced DAWR */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		return false; /* POWER9 with DAWR disabled */
 	/* DABR: Everything but POWER8 and POWER9 */

arch/powerpc/kernel/ptrace.c

@@ -43,6 +43,7 @@
 #include <asm/tm.h>
 #include <asm/asm-prototypes.h>
 #include <asm/debug.h>
+#include <asm/hw_breakpoint.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -3088,7 +3089,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		dbginfo.sizeof_condition = 0;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
-		if (cpu_has_feature(CPU_FTR_DAWR))
+		if (dawr_enabled())
 			dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
 #else
 		dbginfo.features = 0;

arch/powerpc/kvm/Makefile

@@ -94,7 +94,7 @@ endif
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o book3s_xive_native.o
 kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
 
 kvm-book3s_64-module-objs := \

arch/powerpc/kvm/book3s.c

@@ -651,6 +651,18 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 				*val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_get_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
@@ -724,6 +736,18 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 				r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_set_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			vcpu->arch.fscr = set_reg_val(id, *val);
 			break;
@@ -891,6 +915,17 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 	kvmppc_rtas_tokens_free(kvm);
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 #endif
+
+#ifdef CONFIG_KVM_XICS
+	/*
+	 * Free the XIVE devices which are not directly freed by the
+	 * device 'release' method
+	 */
+	kfree(kvm->arch.xive_devices.native);
+	kvm->arch.xive_devices.native = NULL;
+	kfree(kvm->arch.xive_devices.xics_on_xive);
+	kvm->arch.xive_devices.xics_on_xive = NULL;
+#endif /* CONFIG_KVM_XICS */
 }
 
 int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
@@ -1050,6 +1085,9 @@ static int kvmppc_book3s_init(void)
 	if (xics_on_xive()) {
 		kvmppc_xive_init_module();
 		kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+		kvmppc_xive_native_init_module();
+		kvm_register_device_ops(&kvm_xive_native_ops,
+					KVM_DEV_TYPE_XIVE);
 	} else
 #endif
 		kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
@@ -1060,8 +1098,10 @@ static int kvmppc_book3s_init(void)
 static void kvmppc_book3s_exit(void)
 {
 #ifdef CONFIG_KVM_XICS
-	if (xics_on_xive())
+	if (xics_on_xive()) {
 		kvmppc_xive_exit_module();
+		kvmppc_xive_native_exit_module();
+	}
 #endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();

arch/powerpc/kvm/book3s_64_vio.c

@@ -228,11 +228,33 @@ static void release_spapr_tce_table(struct rcu_head *head)
 	unsigned long i, npages = kvmppc_tce_pages(stt->size);
 
 	for (i = 0; i < npages; i++)
+		if (stt->pages[i])
 			__free_page(stt->pages[i]);
 
 	kfree(stt);
 }
 
+static struct page *kvm_spapr_get_tce_page(struct kvmppc_spapr_tce_table *stt,
+		unsigned long sttpage)
+{
+	struct page *page = stt->pages[sttpage];
+
+	if (page)
+		return page;
+
+	mutex_lock(&stt->alloc_lock);
+	page = stt->pages[sttpage];
+	if (!page) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		WARN_ON_ONCE(!page);
+		if (page)
+			stt->pages[sttpage] = page;
+	}
+	mutex_unlock(&stt->alloc_lock);
+
+	return page;
+}
+
 static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 {
 	struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data;
@@ -241,7 +263,10 @@ static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 	if (vmf->pgoff >= kvmppc_tce_pages(stt->size))
 		return VM_FAULT_SIGBUS;
 
-	page = stt->pages[vmf->pgoff];
+	page = kvm_spapr_get_tce_page(stt, vmf->pgoff);
+	if (!page)
+		return VM_FAULT_OOM;
+
 	get_page(page);
 	vmf->page = page;
 	return 0;
@@ -296,7 +321,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
-	int i;
 
 	if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
@@ -318,14 +342,9 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	mutex_init(&stt->alloc_lock);
 	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
 	mutex_lock(&kvm->lock);
 
 	/* Check this LIOBN hasn't been previously allocated */
@@ -352,17 +371,28 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	if (ret >= 0)
 		return ret;
 
- fail:
-	for (i = 0; i < npages; i++)
-		if (stt->pages[i])
-			__free_page(stt->pages[i]);
-
 	kfree(stt);
  fail_acct:
 	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
 	return ret;
 }
 
+static long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	return 0;
+}
+
 static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 		unsigned long tce)
 {
@@ -378,7 +408,7 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_TOO_HARD;
 
-	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua))
 		return H_TOO_HARD;
 
 	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
@@ -397,6 +427,36 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	return H_SUCCESS;
 }
 
+/*
+ * Handles TCE requests for emulated devices.
+ * Puts guest TCE values to the table and expects user space to convert them.
+ * Cannot fail so kvmppc_tce_validate must be called before it.
+ */
+static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+		unsigned long idx, unsigned long tce)
+{
+	struct page *page;
+	u64 *tbl;
+	unsigned long sttpage;
+
+	idx -= stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	page = stt->pages[sttpage];
+
+	if (!page) {
+		/* We allow any TCE, not just with read|write permissions */
+		if (!tce)
+			return;
+
+		page = kvm_spapr_get_tce_page(stt, sttpage);
+		if (!page)
+			return;
+	}
+	tbl = page_to_virt(page);
+
+	tbl[idx % TCES_PER_PAGE] = tce;
+}
+
 static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry)
 {
@@ -543,15 +603,15 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	ret = kvmppc_tce_validate(stt, tce);
 	if (ret != H_SUCCESS)
-		return ret;
+		goto unlock_exit;
 
 	dir = iommu_tce_direction(tce);
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-
-	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
 	}
@@ -612,7 +672,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		return ret;
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL)) {
+	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua)) {
 		ret = H_TOO_HARD;
 		goto unlock_exit;
 	}
@@ -647,7 +707,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		}
 		tce = be64_to_cpu(tce);
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua))
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -66,8 +66,6 @@
 
 #endif
 
-#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
-
 /*
  * Finds a TCE table descriptor by LIOBN.
  *
@@ -88,6 +86,25 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua, unsigned long **prmap)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots_raw(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	if (prmap)
+		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+
+	return 0;
+}
+
 /*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
@@ -111,7 +128,7 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
-	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua, NULL))
 		return H_TOO_HARD;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -129,7 +146,6 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 
 	return H_SUCCESS;
 }
-#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 /* Note on the use of page_address() in real mode,
  *
@@ -161,13 +177,9 @@ static u64 *kvmppc_page_address(struct page *page)
 /*
  * Handles TCE requests for emulated devices.
  * Puts guest TCE values to the table and expects user space to convert them.
- * Called in both real and virtual modes.
- * Cannot fail so kvmppc_tce_validate must be called before it.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
+ * Cannot fail so kvmppc_rm_tce_validate must be called before it.
  */
-void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt,
 		unsigned long idx, unsigned long tce)
 {
 	struct page *page;
@@ -175,35 +187,48 @@ void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
 
 	idx -= stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	/*
+	 * page must not be NULL in real mode,
+	 * kvmppc_rm_ioba_validate() must have taken care of this.
+	 */
+	WARN_ON_ONCE_RM(!page);
 	tbl = kvmppc_page_address(page);
 
 	tbl[idx % TCES_PER_PAGE] = tce;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_put);
 
-long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
-		unsigned long *ua, unsigned long **prmap)
+/*
+ * TCEs pages are allocated in kvmppc_rm_tce_put() which won't be able to do so
+ * in real mode.
+ * Check if kvmppc_rm_tce_put() can succeed in real mode, i.e. a TCEs page is
+ * allocated or not required (when clearing a tce entry).
+ */
+static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long ioba, unsigned long npages, bool clearing)
 {
-	unsigned long gfn = tce >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot;
+	unsigned long i, idx, sttpage, sttpages;
+	unsigned long ret = kvmppc_ioba_validate(stt, ioba, npages);
 
-	memslot = search_memslots(kvm_memslots(kvm), gfn);
-	if (!memslot)
-		return -EINVAL;
-
-	*ua = __gfn_to_hva_memslot(memslot, gfn) |
-		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+	if (ret)
+		return ret;
+	/*
+	 * clearing==true says kvmppc_rm_tce_put won't be allocating pages
+	 * for empty tces.
+	 */
+	if (clearing)
+		return H_SUCCESS;
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	if (prmap)
-		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
-#endif
+	idx = (ioba >> stt->page_shift) - stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
+			TCES_PER_PAGE;
+	for (i = sttpage; i < sttpage + sttpages; ++i)
+		if (!stt->pages[i])
+			return H_TOO_HARD;
 
-	return 0;
+	return H_SUCCESS;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_to_ua);
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
@@ -381,7 +406,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, 1, tce == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -390,7 +415,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		return ret;
 
 	dir = iommu_tce_direction(tce);
-	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 		return H_PARAMETER;
 
 	entry = ioba >> stt->page_shift;
@@ -409,7 +434,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		}
 	}
 
-	kvmppc_tce_put(stt, entry, tce);
+	kvmppc_rm_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -480,7 +505,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (tce_list & (SZ_4K - 1))
 		return H_PARAMETER;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, false);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -492,7 +517,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 */
 		struct mm_iommu_table_group_mem_t *mem;
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
 			return H_TOO_HARD;
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
@@ -508,7 +533,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 * We do not require memory to be preregistered in this case
 		 * so lock rmap and do __find_linux_pte_or_hugepte().
 		 */
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
 			return H_TOO_HARD;
 
 		rmap = (void *) vmalloc_to_phys(rmap);
@@ -542,7 +567,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
 		ua = 0;
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -557,7 +582,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			}
 		}
 
-		kvmppc_tce_put(stt, entry + i, tce);
+		kvmppc_rm_tce_put(stt, entry + i, tce);
 	}
 
 unlock_exit:
@@ -583,7 +608,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, tce_value == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -610,7 +635,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
-		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
+		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
 	return H_SUCCESS;
 }
@@ -635,6 +660,10 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	if (!page) {
+		vcpu->arch.regs.gpr[4] = 0;
+		return H_SUCCESS;
+	}
 	tbl = (u64 *)page_address(page);
 
 	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];

arch/powerpc/kvm/book3s_hv.c

@@ -74,6 +74,7 @@
 #include <asm/opal.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
+#include <asm/hw_breakpoint.h>
 
 #include "book3s.h"
 
@@ -749,7 +750,7 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu)
 	/*
 	 * Ensure that the read of vcore->dpdes comes after the read
 	 * of vcpu->doorbell_request.  This barrier matches the
-	 * smb_wmb() in kvmppc_guest_entry_inject().
+	 * smp_wmb() in kvmppc_guest_entry_inject().
 	 */
 	smp_rmb();
 	vc = vcpu->arch.vcore;
@@ -801,6 +802,80 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 	}
 }
 
+/* Copy guest memory in place - must reside within a single memslot */
+static int kvmppc_copy_guest(struct kvm *kvm, gpa_t to, gpa_t from,
+				  unsigned long len)
+{
+	struct kvm_memory_slot *to_memslot = NULL;
+	struct kvm_memory_slot *from_memslot = NULL;
+	unsigned long to_addr, from_addr;
+	int r;
+
+	/* Get HPA for from address */
+	from_memslot = gfn_to_memslot(kvm, from >> PAGE_SHIFT);
+	if (!from_memslot)
+		return -EFAULT;
+	if ((from + len) >= ((from_memslot->base_gfn + from_memslot->npages)
+			     << PAGE_SHIFT))
+		return -EINVAL;
+	from_addr = gfn_to_hva_memslot(from_memslot, from >> PAGE_SHIFT);
+	if (kvm_is_error_hva(from_addr))
+		return -EFAULT;
+	from_addr |= (from & (PAGE_SIZE - 1));
+
+	/* Get HPA for to address */
+	to_memslot = gfn_to_memslot(kvm, to >> PAGE_SHIFT);
+	if (!to_memslot)
+		return -EFAULT;
+	if ((to + len) >= ((to_memslot->base_gfn + to_memslot->npages)
+			   << PAGE_SHIFT))
+		return -EINVAL;
+	to_addr = gfn_to_hva_memslot(to_memslot, to >> PAGE_SHIFT);
+	if (kvm_is_error_hva(to_addr))
+		return -EFAULT;
+	to_addr |= (to & (PAGE_SIZE - 1));
+
+	/* Perform copy */
+	r = raw_copy_in_user((void __user *)to_addr, (void __user *)from_addr,
+			     len);
+	if (r)
+		return -EFAULT;
+	mark_page_dirty(kvm, to >> PAGE_SHIFT);
+	return 0;
+}
+
+static long kvmppc_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			       unsigned long dest, unsigned long src)
+{
+	u64 pg_sz = SZ_4K;		/* 4K page size */
+	u64 pg_mask = SZ_4K - 1;
+	int ret;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE) {
+		ret = kvmppc_copy_guest(vcpu->kvm, dest, src, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	} else if (flags & H_ZERO_PAGE) {
+		ret = kvm_clear_guest(vcpu->kvm, dest, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	}
+
+	/* We can ignore the remaining flags */
+
+	return H_SUCCESS;
+}
+
 static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct kvmppc_vcore *vcore = target->arch.vcore;
@@ -1003,6 +1078,11 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (nesting_enabled(vcpu->kvm))
 			ret = kvmhv_copy_tofrom_guest_nested(vcpu);
 		break;
+	case H_PAGE_INIT:
+		ret = kvmppc_h_page_init(vcpu, kvmppc_get_gpr(vcpu, 4),
+					 kvmppc_get_gpr(vcpu, 5),
+					 kvmppc_get_gpr(vcpu, 6));
+		break;
 	default:
 		return RESUME_HOST;
 	}
@@ -1047,6 +1127,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_IPOLL:
 	case H_XIRR_X:
 #endif
+	case H_PAGE_INIT:
 		return 1;
 	}
 
@@ -2504,37 +2585,6 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
 	}
 }
 
-static void kvmppc_radix_check_need_tlb_flush(struct kvm *kvm, int pcpu,
-					      struct kvm_nested_guest *nested)
-{
-	cpumask_t *need_tlb_flush;
-	int lpid;
-
-	if (!cpu_has_feature(CPU_FTR_HVMODE))
-		return;
-
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pcpu &= ~0x3UL;
-
-	if (nested) {
-		lpid = nested->shadow_lpid;
-		need_tlb_flush = &nested->need_tlb_flush;
-	} else {
-		lpid = kvm->arch.lpid;
-		need_tlb_flush = &kvm->arch.need_tlb_flush;
-	}
-
-	mtspr(SPRN_LPID, lpid);
-	isync();
-	smp_mb();
-
-	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
-		radix__local_flush_tlb_lpid_guest(lpid);
-		/* Clear the bit after the TLB flush */
-		cpumask_clear_cpu(pcpu, need_tlb_flush);
-	}
-}
-
 static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
 {
 	int cpu;
@@ -3228,19 +3278,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	for (sub = 0; sub < core_info.n_subcores; ++sub)
 		spin_unlock(&core_info.vc[sub]->lock);
 
-	if (kvm_is_radix(vc->kvm)) {
-		/*
-		 * Do we need to flush the process scoped TLB for the LPAR?
-		 *
-		 * On POWER9, individual threads can come in here, but the
-		 * TLB is shared between the 4 threads in a core, hence
-		 * invalidating on one thread invalidates for all.
-		 * Thus we make all 4 threads use the same bit here.
-		 *
-		 * Hash must be flushed in realmode in order to use tlbiel.
-		 */
-		kvmppc_radix_check_need_tlb_flush(vc->kvm, pcpu, NULL);
-	}
+	guest_enter_irqoff();
+
+	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
+
+	this_cpu_disable_ftrace();
 
 	/*
 	 * Interrupts will be enabled once we get into the guest,
@@ -3248,19 +3290,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	trace_hardirqs_on();
 
-	guest_enter_irqoff();
-
-	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
-
-	this_cpu_disable_ftrace();
-
 	trap = __kvmppc_vcore_entry();
 
+	trace_hardirqs_off();
+
 	this_cpu_enable_ftrace();
 
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
-	trace_hardirqs_off();
 	set_irq_happened(trap);
 
 	spin_lock(&vc->lock);
@@ -3374,7 +3411,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	mtspr(SPRN_PURR, vcpu->arch.purr);
 	mtspr(SPRN_SPURR, vcpu->arch.spurr);
 
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		mtspr(SPRN_DAWR, vcpu->arch.dawr);
 		mtspr(SPRN_DAWRX, vcpu->arch.dawrx);
 	}
@@ -3423,7 +3460,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
 	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
 
-	mtspr(SPRN_PSSCR, host_psscr);
+	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+	mtspr(SPRN_PSSCR, host_psscr |
+	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
 	mtspr(SPRN_HFSCR, host_hfscr);
 	mtspr(SPRN_CIABR, host_ciabr);
 	mtspr(SPRN_DAWR, host_dawr);
@@ -3511,6 +3550,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 #ifdef CONFIG_ALTIVEC
 	load_vr_state(&vcpu->arch.vr);
 #endif
+	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
 
 	mtspr(SPRN_DSCR, vcpu->arch.dscr);
 	mtspr(SPRN_IAMR, vcpu->arch.iamr);
@@ -3602,6 +3642,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 #ifdef CONFIG_ALTIVEC
 	store_vr_state(&vcpu->arch.vr);
 #endif
+	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
 
 	if (cpu_has_feature(CPU_FTR_TM) ||
 	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
@@ -3967,7 +4008,7 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 			  unsigned long lpcr)
 {
 	int trap, r, pcpu;
-	int srcu_idx;
+	int srcu_idx, lpid;
 	struct kvmppc_vcore *vc;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_nested_guest *nested = vcpu->arch.nested;
@@ -4043,8 +4084,12 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 	vc->vcore_state = VCORE_RUNNING;
 	trace_kvmppc_run_core(vc, 0);
 
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		kvmppc_radix_check_need_tlb_flush(kvm, pcpu, nested);
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
+		mtspr(SPRN_LPID, lpid);
+		isync();
+		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
+	}
 
 	trace_hardirqs_on();
 	guest_enter_irqoff();

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -805,3 +805,60 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 		vcpu->arch.doorbell_request = 0;
 	}
 }
+
+static void flush_guest_tlb(struct kvm *kvm)
+{
+	unsigned long rb, set;
+
+	rb = PPC_BIT(52);	/* IS = 2 */
+	if (kvm_is_radix(kvm)) {
+		/* R=1 PRS=1 RIC=2 */
+		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+			     : : "r" (rb), "i" (1), "i" (1), "i" (2),
+			       "r" (0) : "memory");
+		for (set = 1; set < kvm->arch.tlb_sets; ++set) {
+			rb += PPC_BIT(51);	/* increment set number */
+			/* R=1 PRS=1 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
+				       "r" (0) : "memory");
+		}
+	} else {
+		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
+			/* R=0 PRS=0 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (0), "i" (0), "i" (0),
+				       "r" (0) : "memory");
+			rb += PPC_BIT(51);	/* increment set number */
+		}
+	}
+	asm volatile("ptesync": : :"memory");
+}
+
+void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+				 struct kvm_nested_guest *nested)
+{
+	cpumask_t *need_tlb_flush;
+
+	/*
+	 * On POWER9, individual threads can come in here, but the
+	 * TLB is shared between the 4 threads in a core, hence
+	 * invalidating on one thread invalidates for all.
+	 * Thus we make all 4 threads use the same bit.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pcpu = cpu_first_thread_sibling(pcpu);
+
+	if (nested)
+		need_tlb_flush = &nested->need_tlb_flush;
+	else
+		need_tlb_flush = &kvm->arch.need_tlb_flush;
+
+	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+		flush_guest_tlb(kvm);
+
+		/* Clear the bit after the TLB flush */
+		cpumask_clear_cpu(pcpu, need_tlb_flush);
+	}
+}
+EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>
 #include <linux/module.h>
 #include <linux/log2.h>
+#include <linux/sizes.h>
 
 #include <asm/trace.h>
 #include <asm/kvm_ppc.h>
@@ -867,6 +868,149 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
 	return ret;
 }
 
+static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa,
+			  int writing, unsigned long *hpa,
+			  struct kvm_memory_slot **memslot_p)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memory_slot *memslot;
+	unsigned long gfn, hva, pa, psize = PAGE_SHIFT;
+	unsigned int shift;
+	pte_t *ptep, pte;
+
+	/* Find the memslot for this address */
+	gfn = gpa >> PAGE_SHIFT;
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		return H_PARAMETER;
+
+	/* Translate to host virtual address */
+	hva = __gfn_to_hva_memslot(memslot, gfn);
+
+	/* Try to find the host pte for that virtual address */
+	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	if (!ptep)
+		return H_TOO_HARD;
+	pte = kvmppc_read_update_linux_pte(ptep, writing);
+	if (!pte_present(pte))
+		return H_TOO_HARD;
+
+	/* Convert to a physical address */
+	if (shift)
+		psize = 1UL << shift;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+	pa |= hva & (psize - 1);
+	pa |= gpa & ~PAGE_MASK;
+
+	if (hpa)
+		*hpa = pa;
+	if (memslot_p)
+		*memslot_p = memslot;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
+				       unsigned long dest)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long pa, mmu_seq;
+	long ret = H_SUCCESS;
+	int i;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &pa, &memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Zero the page */
+	for (i = 0; i < SZ_4K; i += L1_CACHE_BYTES, pa += L1_CACHE_BYTES)
+		dcbz((void *)pa);
+	kvmppc_update_dirty_map(memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
+				       unsigned long dest, unsigned long src)
+{
+	unsigned long dest_pa, src_pa, mmu_seq;
+	struct kvm_memory_slot *dest_memslot;
+	struct kvm *kvm = vcpu->kvm;
+	long ret = H_SUCCESS;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &dest_pa, &dest_memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+	ret = kvmppc_get_hpa(vcpu, src, 0, &src_pa, NULL);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Copy the page */
+	memcpy((void *)dest_pa, (void *)src_pa, SZ_4K);
+
+	kvmppc_update_dirty_map(dest_memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 pg_mask = SZ_4K - 1;	/* 4K page size */
+	long ret = H_SUCCESS;
+
+	/* Don't handle radix mode here, go up to the virtual mode handler */
+	if (kvm_is_radix(kvm))
+		return H_TOO_HARD;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE)
+		ret = kvmppc_do_h_page_init_copy(vcpu, dest, src);
+	else if (flags & H_ZERO_PAGE)
+		ret = kvmppc_do_h_page_init_zero(vcpu, dest);
+
+	/* We can ignore the other flags */
+
+	return ret;
+}
+
 void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index)
 {

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -581,11 +581,8 @@ kvmppc_hv_entry:
 1:
 #endif
 
-	/* Use cr7 as an indication of radix mode */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	ld	r9, VCORE_KVM(r5)	/* pointer to struct kvm */
-	lbz	r0, KVM_RADIX(r9)
-	cmpwi	cr7, r0, 0
 
 	/*
 	 * POWER7/POWER8 host -> guest partition switch code.
@@ -608,9 +605,6 @@ kvmppc_hv_entry:
 	cmpwi	r6,0
 	bne	10f
 
-	/* Radix has already switched LPID and flushed core TLB */
-	bne	cr7, 22f
-
 	lwz	r7,KVM_LPID(r9)
 BEGIN_FTR_SECTION
 	ld	r6,KVM_SDR1(r9)
@@ -622,41 +616,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
-	/* See if we need to flush the TLB. Hash has to be done in RM */
-	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
-BEGIN_FTR_SECTION
-	/*
-	 * On POWER9, individual threads can come in here, but the
-	 * TLB is shared between the 4 threads in a core, hence
-	 * invalidating on one thread invalidates for all.
-	 * Thus we make all 4 threads use the same bit here.
-	 */
-	clrrdi	r6,r6,2
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	clrldi	r7,r6,64-6		/* extract bit number (6 bits) */
-	srdi	r6,r6,6			/* doubleword number */
-	sldi	r6,r6,3			/* address offset */
-	add	r6,r6,r9
-	addi	r6,r6,KVM_NEED_FLUSH	/* dword in kvm->arch.need_tlb_flush */
-	li	r8,1
-	sld	r8,r8,r7
-	ld	r7,0(r6)
-	and.	r7,r7,r8
-	beq	22f
-	/* Flush the TLB of any entries for this LPID */
-	lwz	r0,KVM_TLB_SETS(r9)
-	mtctr	r0
-	li	r7,0x800		/* IS field = 0b10 */
-	ptesync
-	li	r0,0			/* RS for P9 version of tlbiel */
-28:	tlbiel	r7			/* On P9, rs=0, RIC=0, PRS=0, R=0 */
-	addi	r7,r7,0x1000
-	bdnz	28b
-	ptesync
-23:	ldarx	r7,0,r6			/* clear the bit after TLB flushed */
-	andc	r7,r7,r8
-	stdcx.	r7,0,r6
-	bne	23b
+	/* See if we need to flush the TLB. */
+	mr	r3, r9			/* kvm pointer */
+	lhz	r4, PACAPACAINDEX(r13)	/* physical cpu number */
+	li	r5, 0			/* nested vcpu pointer */
+	bl	kvmppc_check_need_tlb_flush
+	nop
+	ld	r5, HSTATE_KVM_VCORE(r13)
 
 	/* Add timebase offset onto timebase */
 22:	ld	r8,VCORE_TB_OFFSET(r5)
@@ -822,18 +788,21 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_IAMR, r5
 	mtspr	SPRN_PSPB, r6
 	mtspr	SPRN_FSCR, r7
-	ld	r5, VCPU_DAWR(r4)
-	ld	r6, VCPU_DAWRX(r4)
-	ld	r7, VCPU_CIABR(r4)
-	ld	r8, VCPU_TAR(r4)
 	/*
 	 * Handle broken DAWR case by not writing it. This means we
 	 * can still store the DAWR register for migration.
 	 */
-BEGIN_FTR_SECTION
+	LOAD_REG_ADDR(r5, dawr_force_enable)
+	lbz	r5, 0(r5)
+	cmpdi	r5, 0
+	beq	1f
+	ld	r5, VCPU_DAWR(r4)
+	ld	r6, VCPU_DAWRX(r4)
 	mtspr	SPRN_DAWR, r5
 	mtspr	SPRN_DAWRX, r6
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
+1:
+	ld	r7, VCPU_CIABR(r4)
+	ld	r8, VCPU_TAR(r4)
 	mtspr	SPRN_CIABR, r7
 	mtspr	SPRN_TAR, r8
 	ld	r5, VCPU_IC(r4)
@@ -969,17 +938,27 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
-	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, 0
-	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
+	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
+	li	r7, TM_QW1_OS + TM_WORD2
+	mfmsr	r0
+	andi.	r0, r0, MSR_DR		/* in real mode? */
+	beq	2f
+	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
+	cmpldi	cr1, r10, 0
+	beq     cr1, no_xive
+	eieio
+	stdx	r11,r9,r10
+	stwx	r8,r7,r10
+	b	3f
+2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
+	cmpldi	cr1, r10, 0
+	beq	cr1, no_xive
 	eieio
 	stdcix	r11,r9,r10
-	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
-	li	r9, TM_QW1_OS + TM_WORD2
-	stwcix	r11,r9,r10
-	li	r9, 1
+	stwcix	r8,r7,r10
+3:	li	r9, 1
 	stb	r9, VCPU_XIVE_PUSHED(r4)
 	eieio
 
@@ -998,12 +977,16 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	 * on, we mask it.
 	 */
 	lbz	r0, VCPU_XIVE_ESC_ON(r4)
-	cmpwi	r0,0
-	beq	1f
-	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
+	cmpwi	cr1, r0,0
+	beq	cr1, 1f
 	li	r9, XIVE_ESB_SET_PQ_01
+	beq	4f			/* in real mode? */
+	ld	r10, VCPU_XIVE_ESC_VADDR(r4)
+	ldx	r0, r10, r9
+	b	5f
+4:	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
 	ldcix	r0, r10, r9
-	sync
+5:	sync
 
 	/* We have a possible subtle race here: The escalation interrupt might
 	 * have fired and be on its way to the host queue while we mask it,
@@ -2281,7 +2264,7 @@ hcall_real_table:
 #endif
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
-	.long	0		/* 0x2c */
+	.long	DOTSYM(kvmppc_rm_h_page_init) - hcall_real_table
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
 	.long	0		/* 0x38 */
@@ -2513,11 +2496,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	blr
 
 2:
-BEGIN_FTR_SECTION
-	/* POWER9 with disabled DAWR */
+	LOAD_REG_ADDR(r11, dawr_force_enable)
+	lbz	r11, 0(r11)
+	cmpdi	r11, 0
 	li	r3, H_HARDWARE
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
+	beqlr
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
 	rlwimi	r5, r4, 2, DAWRX_WT

arch/powerpc/kvm/book3s_xive.c

@@ -166,7 +166,8 @@ static irqreturn_t xive_esc_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct xive_q *q = &xc->queues[prio];
@@ -185,7 +186,7 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 		return -EIO;
 	}
 
-	if (xc->xive->single_escalation)
+	if (single_escalation)
 		name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
 				 vcpu->kvm->arch.lpid, xc->server_num);
 	else
@@ -217,7 +218,7 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 	 * interrupt, thus leaving it effectively masked after
 	 * it fires once.
 	 */
-	if (xc->xive->single_escalation) {
+	if (single_escalation) {
 		struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]);
 		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
 
@@ -291,7 +292,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio)
 			continue;
 		rc = xive_provision_queue(vcpu, prio);
 		if (rc == 0 && !xive->single_escalation)
-			xive_attach_escalation(vcpu, prio);
+			kvmppc_xive_attach_escalation(vcpu, prio,
+						      xive->single_escalation);
 		if (rc)
 			return rc;
 	}
@@ -342,7 +344,7 @@ static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio)
 	return atomic_add_unless(&q->count, 1, max) ? 0 : -EBUSY;
 }
 
-static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
+int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 {
 	struct kvm_vcpu *vcpu;
 	int i, rc;
@@ -380,11 +382,6 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 	return -EBUSY;
 }
 
-static u32 xive_vp(struct kvmppc_xive *xive, u32 server)
-{
-	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
-}
-
 static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 			     struct kvmppc_xive_src_block *sb,
 			     struct kvmppc_xive_irq_state *state)
@@ -430,7 +427,7 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive_vp(xive, state->act_server),
+				kvmppc_xive_vp(xive, state->act_server),
 				MASKED, state->number);
 		/* set old_p so we can track if an H_EOI was done */
 		state->old_p = true;
@@ -486,7 +483,7 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive_vp(xive, state->act_server),
+				kvmppc_xive_vp(xive, state->act_server),
 				state->act_priority, state->number);
 		/* If an EOI is needed, do it here */
 		if (!state->old_p)
@@ -535,7 +532,7 @@ static int xive_target_interrupt(struct kvm *kvm,
 	 * priority. The count for that new target will have
 	 * already been incremented.
 	 */
-	rc = xive_select_target(kvm, &server, prio);
+	rc = kvmppc_xive_select_target(kvm, &server, prio);
 
 	/*
 	 * We failed to find a target ? Not much we can do
@@ -563,7 +560,7 @@ static int xive_target_interrupt(struct kvm *kvm,
 	kvmppc_xive_select_irq(state, &hw_num, NULL);
 
 	return xive_native_configure_irq(hw_num,
-					 xive_vp(xive, server),
+					 kvmppc_xive_vp(xive, server),
 					 prio, state->number);
 }
 
@@ -849,7 +846,8 @@ int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
 
 	/*
 	 * We can't update the state of a "pushed" VCPU, but that
-	 * shouldn't happen.
+	 * shouldn't happen because the vcpu->mutex makes running a
+	 * vcpu mutually exclusive with doing one_reg get/set on it.
 	 */
 	if (WARN_ON(vcpu->arch.xive_pushed))
 		return -EIO;
@@ -940,6 +938,13 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	/* Turn the IPI hard off */
 	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped)
+		xive->ops->reset_mapped(kvm, guest_irq);
+
 	/* Grab info about irq */
 	state->pt_number = hw_irq;
 	state->pt_data = irq_data_get_irq_handler_data(host_data);
@@ -951,7 +956,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	 * which is fine for a never started interrupt.
 	 */
 	xive_native_configure_irq(hw_irq,
-				  xive_vp(xive, state->act_server),
+				  kvmppc_xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -1025,9 +1030,17 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 	state->pt_number = 0;
 	state->pt_data = NULL;
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped) {
+		xive->ops->reset_mapped(kvm, guest_irq);
+	}
+
 	/* Reconfigure the IPI */
 	xive_native_configure_irq(state->ipi_number,
-				  xive_vp(xive, state->act_server),
+				  kvmppc_xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -1049,7 +1062,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 }
 EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
 
-static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
+void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct kvm *kvm = vcpu->kvm;
@@ -1083,14 +1096,35 @@ static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
 			arch_spin_unlock(&sb->lock);
 		}
 	}
+
+	/* Disable vcpu's escalation interrupt */
+	if (vcpu->arch.xive_esc_on) {
+		__raw_readq((void __iomem *)(vcpu->arch.xive_esc_vaddr +
+					     XIVE_ESB_SET_PQ_01));
+		vcpu->arch.xive_esc_on = false;
+	}
+
+	/*
+	 * Clear pointers to escalation interrupt ESB.
+	 * This is safe because the vcpu->mutex is held, preventing
+	 * any other CPU from concurrently executing a KVM_RUN ioctl.
+	 */
+	vcpu->arch.xive_esc_vaddr = 0;
+	vcpu->arch.xive_esc_raddr = 0;
 }
 
 void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
-	struct kvmppc_xive *xive = xc->xive;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
 	int i;
 
+	if (!kvmppc_xics_enabled(vcpu))
+		return;
+
+	if (!xc)
+		return;
+
 	pr_devel("cleanup_vcpu(cpu=%d)\n", xc->server_num);
 
 	/* Ensure no interrupt is still routed to that VP */
@@ -1129,6 +1163,10 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	}
 	/* Free the VP */
 	kfree(xc);
+
+	/* Cleanup the vcpu */
+	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
+	vcpu->arch.xive_vcpu = NULL;
 }
 
 int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
@@ -1146,7 +1184,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	}
 	if (xive->kvm != vcpu->kvm)
 		return -EPERM;
-	if (vcpu->arch.irq_type)
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
 	if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
 		pr_devel("Duplicate !\n");
@@ -1166,7 +1204,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = xive_vp(xive, cpu);
+	xc->vp_id = kvmppc_xive_vp(xive, cpu);
 	xc->mfrr = 0xff;
 	xc->valid = true;
 
@@ -1219,7 +1257,8 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		if (xive->qmap & (1 << i)) {
 			r = xive_provision_queue(vcpu, i);
 			if (r == 0 && !xive->single_escalation)
-				xive_attach_escalation(vcpu, i);
+				kvmppc_xive_attach_escalation(
+					vcpu, i, xive->single_escalation);
 			if (r)
 				goto bail;
 		} else {
@@ -1234,7 +1273,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	}
 
 	/* If not done above, attach priority 0 escalation */
-	r = xive_attach_escalation(vcpu, 0);
+	r = kvmppc_xive_attach_escalation(vcpu, 0, xive->single_escalation);
 	if (r)
 		goto bail;
 
@@ -1485,8 +1524,8 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	return 0;
 }
 
-static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
-							   int irq)
+struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
+	struct kvmppc_xive *xive, int irq)
 {
 	struct kvm *kvm = xive->kvm;
 	struct kvmppc_xive_src_block *sb;
@@ -1509,6 +1548,7 @@ static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *x
 
 	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
 		sb->irq_state[i].number = (bid << KVMPPC_XICS_ICS_SHIFT) | i;
+		sb->irq_state[i].eisn = 0;
 		sb->irq_state[i].guest_priority = MASKED;
 		sb->irq_state[i].saved_priority = MASKED;
 		sb->irq_state[i].act_priority = MASKED;
@@ -1565,7 +1605,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	sb = kvmppc_xive_find_source(xive, irq, &idx);
 	if (!sb) {
 		pr_devel("No source, creating source block...\n");
-		sb = xive_create_src_block(xive, irq);
+		sb = kvmppc_xive_create_src_block(xive, irq);
 		if (!sb) {
 			pr_devel("Failed to create block...\n");
 			return -ENOMEM;
@@ -1789,7 +1829,7 @@ static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd)
 	xive_cleanup_irq_data(xd);
 }
 
-static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
+void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
 {
 	int i;
 
@@ -1810,15 +1850,54 @@ static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
 	}
 }
 
-static void kvmppc_xive_free(struct kvm_device *dev)
+/*
+ * Called when device fd is closed.  kvm->lock is held.
+ */
+static void kvmppc_xive_release(struct kvm_device *dev)
 {
 	struct kvmppc_xive *xive = dev->private;
 	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
 	int i;
+	int was_ready;
+
+	pr_devel("Releasing xive device\n");
 
 	debugfs_remove(xive->dentry);
 
-	if (kvm)
+	/*
+	 * Clearing mmu_ready temporarily while holding kvm->lock
+	 * is a way of ensuring that no vcpus can enter the guest
+	 * until we drop kvm->lock.  Doing kick_all_cpus_sync()
+	 * ensures that any vcpu executing inside the guest has
+	 * exited the guest.  Once kick_all_cpus_sync() has finished,
+	 * we know that no vcpu can be executing the XIVE push or
+	 * pull code, or executing a XICS hcall.
+	 *
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd referring to the
+	 * device.  Therefore there can not be any of the device
+	 * attribute set/get functions being executed concurrently,
+	 * and similarly, the connect_vcpu and set/clr_mapped
+	 * functions also cannot be being executed.
+	 */
+	was_ready = kvm->arch.mmu_ready;
+	kvm->arch.mmu_ready = 0;
+	kick_all_cpus_sync();
+
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xive_[gs]et_icp) can be done concurrently.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xive_cleanup_vcpu(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
 	kvm->arch.xive = NULL;
 
 	/* Mask and free interrupts */
@@ -1832,11 +1911,47 @@ static void kvmppc_xive_free(struct kvm_device *dev)
 	if (xive->vp_base != XIVE_INVALID_VP)
 		xive_native_free_vp_block(xive->vp_base);
 
+	kvm->arch.mmu_ready = was_ready;
+
+	/*
+	 * A reference of the kvmppc_xive pointer is now kept under
+	 * the xive_devices struct of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
 
-	kfree(xive);
 	kfree(dev);
 }
 
+/*
+ * When the guest chooses the interrupt mode (XICS legacy or XIVE
+ * native), the VM will switch of KVM device. The previous device will
+ * be "released" before the new one is created.
+ *
+ * Until we are sure all execution paths are well protected, provide a
+ * fail safe (transitional) method for device destruction, in which
+ * the XIVE device pointer is recycled and not directly freed.
+ */
+struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type)
+{
+	struct kvmppc_xive **kvm_xive_device = type == KVM_DEV_TYPE_XIVE ?
+		&kvm->arch.xive_devices.native :
+		&kvm->arch.xive_devices.xics_on_xive;
+	struct kvmppc_xive *xive = *kvm_xive_device;
+
+	if (!xive) {
+		xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+		*kvm_xive_device = xive;
+	} else {
+		memset(xive, 0, sizeof(*xive));
+	}
+
+	return xive;
+}
+
+/*
+ * Create a XICS device with XIVE backend.  kvm->lock is held.
+ */
 static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xive *xive;
@@ -1845,7 +1960,7 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 
 	pr_devel("Creating xive for partition\n");
 
-	xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+	xive = kvmppc_xive_get_device(kvm, type);
 	if (!xive)
 		return -ENOMEM;
 
@@ -1883,6 +1998,43 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	return 0;
 }
 
+int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	unsigned int i;
+
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		struct xive_q *q = &xc->queues[i];
+		u32 i0, i1, idx;
+
+		if (!q->qpage && !xc->esc_virq[i])
+			continue;
+
+		seq_printf(m, " [q%d]: ", i);
+
+		if (q->qpage) {
+			idx = q->idx;
+			i0 = be32_to_cpup(q->qpage + idx);
+			idx = (idx + 1) & q->msk;
+			i1 = be32_to_cpup(q->qpage + idx);
+			seq_printf(m, "T=%d %08x %08x...\n", q->toggle,
+				   i0, i1);
+		}
+		if (xc->esc_virq[i]) {
+			struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
+			struct xive_irq_data *xd =
+				irq_data_get_irq_handler_data(d);
+			u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
+
+			seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
+				   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
+				   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
+				   xc->esc_virq[i], pq, xd->eoi_page);
+			seq_puts(m, "\n");
+		}
+	}
+	return 0;
+}
 
 static int xive_debug_show(struct seq_file *m, void *private)
 {
@@ -1908,7 +2060,6 @@ static int xive_debug_show(struct seq_file *m, void *private)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
-		unsigned int i;
 
 		if (!xc)
 			continue;
@@ -1918,33 +2069,8 @@ static int xive_debug_show(struct seq_file *m, void *private)
 			   xc->server_num, xc->cppr, xc->hw_cppr,
 			   xc->mfrr, xc->pending,
 			   xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
-		for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
-			struct xive_q *q = &xc->queues[i];
-			u32 i0, i1, idx;
 
-			if (!q->qpage && !xc->esc_virq[i])
-				continue;
-
-			seq_printf(m, " [q%d]: ", i);
-
-			if (q->qpage) {
-				idx = q->idx;
-				i0 = be32_to_cpup(q->qpage + idx);
-				idx = (idx + 1) & q->msk;
-				i1 = be32_to_cpup(q->qpage + idx);
-				seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1);
-			}
-			if (xc->esc_virq[i]) {
-				struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
-				struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
-				u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
-				seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
-					   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
-					   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
-					   xc->esc_virq[i], pq, xd->eoi_page);
-				seq_printf(m, "\n");
-			}
-		}
+		kvmppc_xive_debug_show_queues(m, vcpu);
 
 		t_rm_h_xirr += xc->stat_rm_h_xirr;
 		t_rm_h_ipoll += xc->stat_rm_h_ipoll;
@@ -1999,7 +2125,7 @@ struct kvm_device_ops kvm_xive_ops = {
 	.name = "kvm-xive",
 	.create = kvmppc_xive_create,
 	.init = kvmppc_xive_init,
-	.destroy = kvmppc_xive_free,
+	.release = kvmppc_xive_release,
 	.set_attr = xive_set_attr,
 	.get_attr = xive_get_attr,
 	.has_attr = xive_has_attr,

arch/powerpc/kvm/book3s_xive.h

@@ -12,6 +12,13 @@
 #ifdef CONFIG_KVM_XICS
 #include "book3s_xics.h"
 
+/*
+ * The XIVE Interrupt source numbers are within the range 0 to
+ * KVMPPC_XICS_NR_IRQS.
+ */
+#define KVMPPC_XIVE_FIRST_IRQ	0
+#define KVMPPC_XIVE_NR_IRQS	KVMPPC_XICS_NR_IRQS
+
 /*
  * State for one guest irq source.
  *
@@ -54,6 +61,9 @@ struct kvmppc_xive_irq_state {
 	bool saved_p;
 	bool saved_q;
 	u8 saved_scan_prio;
+
+	/* Xive native */
+	u32 eisn;			/* Guest Effective IRQ number */
 };
 
 /* Select the "right" interrupt (IPI vs. passthrough) */
@@ -84,6 +94,11 @@ struct kvmppc_xive_src_block {
 	struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
 };
 
+struct kvmppc_xive;
+
+struct kvmppc_xive_ops {
+	int (*reset_mapped)(struct kvm *kvm, unsigned long guest_irq);
+};
 
 struct kvmppc_xive {
 	struct kvm *kvm;
@@ -122,6 +137,10 @@ struct kvmppc_xive {
 
 	/* Flags */
 	u8	single_escalation;
+
+	struct kvmppc_xive_ops *ops;
+	struct address_space   *mapping;
+	struct mutex mapping_lock;
 };
 
 #define KVMPPC_XIVE_Q_COUNT	8
@@ -198,6 +217,11 @@ static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmpp
 	return xive->src_blocks[bid];
 }
 
+static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
+{
+	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
+}
+
 /*
  * Mapping between guest priorities and host priorities
  * is as follow.
@@ -248,5 +272,18 @@ extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
 extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
 extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
 
+/*
+ * Common Xive routines for XICS-over-XIVE and XIVE native
+ */
+void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu);
+int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu);
+struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
+	struct kvmppc_xive *xive, int irq);
+void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb);
+int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio);
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation);
+struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type);
+
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */

arch/powerpc/kvm/book3s_xive_native.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2019, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "xive-kvm: " fmt
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/file.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/opal.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "book3s_xive.h"
+
+static u8 xive_vm_esb_load(struct xive_irq_data *xd, u32 offset)
+{
+	u64 val;
+
+	if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+		offset |= offset << 4;
+
+	val = in_be64(xd->eoi_mmio + offset);
+	return (u8)val;
+}
+
+static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct xive_q *q = &xc->queues[prio];
+
+	xive_native_disable_queue(xc->vp_id, q, prio);
+	if (q->qpage) {
+		put_page(virt_to_page(q->qpage));
+		q->qpage = NULL;
+	}
+}
+
+void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	int i;
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return;
+
+	if (!xc)
+		return;
+
+	pr_devel("native_cleanup_vcpu(cpu=%d)\n", xc->server_num);
+
+	/* Ensure no interrupt is still routed to that VP */
+	xc->valid = false;
+	kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
+
+	/* Free the queues & associated interrupts */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		/* Free the escalation irq */
+		if (xc->esc_virq[i]) {
+			free_irq(xc->esc_virq[i], vcpu);
+			irq_dispose_mapping(xc->esc_virq[i]);
+			kfree(xc->esc_virq_names[i]);
+			xc->esc_virq[i] = 0;
+		}
+
+		/* Free the queue */
+		kvmppc_xive_native_cleanup_queue(vcpu, i);
+	}
+
+	/* Free the VP */
+	kfree(xc);
+
+	/* Cleanup the vcpu */
+	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
+	vcpu->arch.xive_vcpu = NULL;
+}
+
+int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+				    struct kvm_vcpu *vcpu, u32 server_num)
+{
+	struct kvmppc_xive *xive = dev->private;
+	struct kvmppc_xive_vcpu *xc = NULL;
+	int rc;
+
+	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
+
+	if (dev->ops != &kvm_xive_native_ops) {
+		pr_devel("Wrong ops !\n");
+		return -EPERM;
+	}
+	if (xive->kvm != vcpu->kvm)
+		return -EPERM;
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
+		return -EBUSY;
+	if (server_num >= KVM_MAX_VCPUS) {
+		pr_devel("Out of bounds !\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&vcpu->kvm->lock);
+
+	if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
+		pr_devel("Duplicate !\n");
+		rc = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		rc = -ENOMEM;
+		goto bail;
+	}
+
+	vcpu->arch.xive_vcpu = xc;
+	xc->xive = xive;
+	xc->vcpu = vcpu;
+	xc->server_num = server_num;
+
+	xc->vp_id = kvmppc_xive_vp(xive, server_num);
+	xc->valid = true;
+	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
+
+	rc = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
+	if (rc) {
+		pr_err("Failed to get VP info from OPAL: %d\n", rc);
+		goto bail;
+	}
+
+	/*
+	 * Enable the VP first as the single escalation mode will
+	 * affect escalation interrupts numbering
+	 */
+	rc = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+	if (rc) {
+		pr_err("Failed to enable VP in OPAL: %d\n", rc);
+		goto bail;
+	}
+
+	/* Configure VCPU fields for use by assembly push/pull */
+	vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
+	vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
+
+	/* TODO: reset all queues to a clean state ? */
+bail:
+	mutex_unlock(&vcpu->kvm->lock);
+	if (rc)
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+
+	return rc;
+}
+
+/*
+ * Device passthrough support
+ */
+static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq)
+{
+	struct kvmppc_xive *xive = kvm->arch.xive;
+
+	if (irq >= KVMPPC_XIVE_NR_IRQS)
+		return -EINVAL;
+
+	/*
+	 * Clear the ESB pages of the IRQ number being mapped (or
+	 * unmapped) into the guest and let the the VM fault handler
+	 * repopulate with the appropriate ESB pages (device or IC)
+	 */
+	pr_debug("clearing esb pages for girq 0x%lx\n", irq);
+	mutex_lock(&xive->mapping_lock);
+	if (xive->mapping)
+		unmap_mapping_range(xive->mapping,
+				    irq * (2ull << PAGE_SHIFT),
+				    2ull << PAGE_SHIFT, 1);
+	mutex_unlock(&xive->mapping_lock);
+	return 0;
+}
+
+static struct kvmppc_xive_ops kvmppc_xive_native_ops =  {
+	.reset_mapped = kvmppc_xive_native_reset_mapped,
+};
+
+static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct kvm_device *dev = vma->vm_file->private_data;
+	struct kvmppc_xive *xive = dev->private;
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	struct xive_irq_data *xd;
+	u32 hw_num;
+	u16 src;
+	u64 page;
+	unsigned long irq;
+	u64 page_offset;
+
+	/*
+	 * Linux/KVM uses a two pages ESB setting, one for trigger and
+	 * one for EOI
+	 */
+	page_offset = vmf->pgoff - vma->vm_pgoff;
+	irq = page_offset / 2;
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb) {
+		pr_devel("%s: source %lx not found !\n", __func__, irq);
+		return VM_FAULT_SIGBUS;
+	}
+
+	state = &sb->irq_state[src];
+	kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+	arch_spin_lock(&sb->lock);
+
+	/*
+	 * first/even page is for trigger
+	 * second/odd page is for EOI and management.
+	 */
+	page = page_offset % 2 ? xd->eoi_page : xd->trig_page;
+	arch_spin_unlock(&sb->lock);
+
+	if (WARN_ON(!page)) {
+		pr_err("%s: accessing invalid ESB page for source %lx !\n",
+		       __func__, irq);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf_insert_pfn(vma, vmf->address, page >> PAGE_SHIFT);
+	return VM_FAULT_NOPAGE;
+}
+
+static const struct vm_operations_struct xive_native_esb_vmops = {
+	.fault = xive_native_esb_fault,
+};
+
+static vm_fault_t xive_native_tima_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+
+	switch (vmf->pgoff - vma->vm_pgoff) {
+	case 0: /* HW - forbid access */
+	case 1: /* HV - forbid access */
+		return VM_FAULT_SIGBUS;
+	case 2: /* OS */
+		vmf_insert_pfn(vma, vmf->address, xive_tima_os >> PAGE_SHIFT);
+		return VM_FAULT_NOPAGE;
+	case 3: /* USER - TODO */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+}
+
+static const struct vm_operations_struct xive_native_tima_vmops = {
+	.fault = xive_native_tima_fault,
+};
+
+static int kvmppc_xive_native_mmap(struct kvm_device *dev,
+				   struct vm_area_struct *vma)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	/* We only allow mappings at fixed offset for now */
+	if (vma->vm_pgoff == KVM_XIVE_TIMA_PAGE_OFFSET) {
+		if (vma_pages(vma) > 4)
+			return -EINVAL;
+		vma->vm_ops = &xive_native_tima_vmops;
+	} else if (vma->vm_pgoff == KVM_XIVE_ESB_PAGE_OFFSET) {
+		if (vma_pages(vma) > KVMPPC_XIVE_NR_IRQS * 2)
+			return -EINVAL;
+		vma->vm_ops = &xive_native_esb_vmops;
+	} else {
+		return -EINVAL;
+	}
+
+	vma->vm_flags |= VM_IO | VM_PFNMAP;
+	vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
+
+	/*
+	 * Grab the KVM device file address_space to be able to clear
+	 * the ESB pages mapping when a device is passed-through into
+	 * the guest.
+	 */
+	xive->mapping = vma->vm_file->f_mapping;
+	return 0;
+}
+
+static int kvmppc_xive_native_set_source(struct kvmppc_xive *xive, long irq,
+					 u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	u64 __user *ubufp = (u64 __user *) addr;
+	u64 val;
+	u16 idx;
+	int rc;
+
+	pr_devel("%s irq=0x%lx\n", __func__, irq);
+
+	if (irq < KVMPPC_XIVE_FIRST_IRQ || irq >= KVMPPC_XIVE_NR_IRQS)
+		return -E2BIG;
+
+	sb = kvmppc_xive_find_source(xive, irq, &idx);
+	if (!sb) {
+		pr_debug("No source, creating source block...\n");
+		sb = kvmppc_xive_create_src_block(xive, irq);
+		if (!sb) {
+			pr_err("Failed to create block...\n");
+			return -ENOMEM;
+		}
+	}
+	state = &sb->irq_state[idx];
+
+	if (get_user(val, ubufp)) {
+		pr_err("fault getting user info !\n");
+		return -EFAULT;
+	}
+
+	arch_spin_lock(&sb->lock);
+
+	/*
+	 * If the source doesn't already have an IPI, allocate
+	 * one and get the corresponding data
+	 */
+	if (!state->ipi_number) {
+		state->ipi_number = xive_native_alloc_irq();
+		if (state->ipi_number == 0) {
+			pr_err("Failed to allocate IRQ !\n");
+			rc = -ENXIO;
+			goto unlock;
+		}
+		xive_native_populate_irq_data(state->ipi_number,
+					      &state->ipi_data);
+		pr_debug("%s allocated hw_irq=0x%x for irq=0x%lx\n", __func__,
+			 state->ipi_number, irq);
+	}
+
+	/* Restore LSI state */
+	if (val & KVM_XIVE_LEVEL_SENSITIVE) {
+		state->lsi = true;
+		if (val & KVM_XIVE_LEVEL_ASSERTED)
+			state->asserted = true;
+		pr_devel("  LSI ! Asserted=%d\n", state->asserted);
+	}
+
+	/* Mask IRQ to start with */
+	state->act_server = 0;
+	state->act_priority = MASKED;
+	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+	xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+
+	/* Increment the number of valid sources and mark this one valid */
+	if (!state->valid)
+		xive->src_count++;
+	state->valid = true;
+
+	rc = 0;
+
+unlock:
+	arch_spin_unlock(&sb->lock);
+
+	return rc;
+}
+
+static int kvmppc_xive_native_update_source_config(struct kvmppc_xive *xive,
+					struct kvmppc_xive_src_block *sb,
+					struct kvmppc_xive_irq_state *state,
+					u32 server, u8 priority, bool masked,
+					u32 eisn)
+{
+	struct kvm *kvm = xive->kvm;
+	u32 hw_num;
+	int rc = 0;
+
+	arch_spin_lock(&sb->lock);
+
+	if (state->act_server == server && state->act_priority == priority &&
+	    state->eisn == eisn)
+		goto unlock;
+
+	pr_devel("new_act_prio=%d new_act_server=%d mask=%d act_server=%d act_prio=%d\n",
+		 priority, server, masked, state->act_server,
+		 state->act_priority);
+
+	kvmppc_xive_select_irq(state, &hw_num, NULL);
+
+	if (priority != MASKED && !masked) {
+		rc = kvmppc_xive_select_target(kvm, &server, priority);
+		if (rc)
+			goto unlock;
+
+		state->act_priority = priority;
+		state->act_server = server;
+		state->eisn = eisn;
+
+		rc = xive_native_configure_irq(hw_num,
+					       kvmppc_xive_vp(xive, server),
+					       priority, eisn);
+	} else {
+		state->act_priority = MASKED;
+		state->act_server = 0;
+		state->eisn = 0;
+
+		rc = xive_native_configure_irq(hw_num, 0, MASKED, 0);
+	}
+
+unlock:
+	arch_spin_unlock(&sb->lock);
+	return rc;
+}
+
+static int kvmppc_xive_native_set_source_config(struct kvmppc_xive *xive,
+						long irq, u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	u64 __user *ubufp = (u64 __user *) addr;
+	u16 src;
+	u64 kvm_cfg;
+	u32 server;
+	u8 priority;
+	bool masked;
+	u32 eisn;
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb)
+		return -ENOENT;
+
+	state = &sb->irq_state[src];
+
+	if (!state->valid)
+		return -EINVAL;
+
+	if (get_user(kvm_cfg, ubufp))
+		return -EFAULT;
+
+	pr_devel("%s irq=0x%lx cfg=%016llx\n", __func__, irq, kvm_cfg);
+
+	priority = (kvm_cfg & KVM_XIVE_SOURCE_PRIORITY_MASK) >>
+		KVM_XIVE_SOURCE_PRIORITY_SHIFT;
+	server = (kvm_cfg & KVM_XIVE_SOURCE_SERVER_MASK) >>
+		KVM_XIVE_SOURCE_SERVER_SHIFT;
+	masked = (kvm_cfg & KVM_XIVE_SOURCE_MASKED_MASK) >>
+		KVM_XIVE_SOURCE_MASKED_SHIFT;
+	eisn = (kvm_cfg & KVM_XIVE_SOURCE_EISN_MASK) >>
+		KVM_XIVE_SOURCE_EISN_SHIFT;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("invalid priority for queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+
+	return kvmppc_xive_native_update_source_config(xive, sb, state, server,
+						       priority, masked, eisn);
+}
+
+static int kvmppc_xive_native_sync_source(struct kvmppc_xive *xive,
+					  long irq, u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	struct xive_irq_data *xd;
+	u32 hw_num;
+	u16 src;
+	int rc = 0;
+
+	pr_devel("%s irq=0x%lx", __func__, irq);
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb)
+		return -ENOENT;
+
+	state = &sb->irq_state[src];
+
+	rc = -EINVAL;
+
+	arch_spin_lock(&sb->lock);
+
+	if (state->valid) {
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+		xive_native_sync_source(hw_num);
+		rc = 0;
+	}
+
+	arch_spin_unlock(&sb->lock);
+	return rc;
+}
+
+static int xive_native_validate_queue_size(u32 qshift)
+{
+	/*
+	 * We only support 64K pages for the moment. This is also
+	 * advertised in the DT property "ibm,xive-eq-sizes"
+	 */
+	switch (qshift) {
+	case 0: /* EQ reset */
+	case 16:
+		return 0;
+	case 12:
+	case 21:
+	case 24:
+	default:
+		return -EINVAL;
+	}
+}
+
+static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
+					       long eq_idx, u64 addr)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_xive_vcpu *xc;
+	void __user *ubufp = (void __user *) addr;
+	u32 server;
+	u8 priority;
+	struct kvm_ppc_xive_eq kvm_eq;
+	int rc;
+	__be32 *qaddr = 0;
+	struct page *page;
+	struct xive_q *q;
+	gfn_t gfn;
+	unsigned long page_size;
+
+	/*
+	 * Demangle priority/server tuple from the EQ identifier
+	 */
+	priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
+		KVM_XIVE_EQ_PRIORITY_SHIFT;
+	server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
+		KVM_XIVE_EQ_SERVER_SHIFT;
+
+	if (copy_from_user(&kvm_eq, ubufp, sizeof(kvm_eq)))
+		return -EFAULT;
+
+	vcpu = kvmppc_xive_find_server(kvm, server);
+	if (!vcpu) {
+		pr_err("Can't find server %d\n", server);
+		return -ENOENT;
+	}
+	xc = vcpu->arch.xive_vcpu;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("Trying to restore invalid queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+	q = &xc->queues[priority];
+
+	pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
+		 __func__, server, priority, kvm_eq.flags,
+		 kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
+
+	/*
+	 * sPAPR specifies a "Unconditional Notify (n) flag" for the
+	 * H_INT_SET_QUEUE_CONFIG hcall which forces notification
+	 * without using the coalescing mechanisms provided by the
+	 * XIVE END ESBs. This is required on KVM as notification
+	 * using the END ESBs is not supported.
+	 */
+	if (kvm_eq.flags != KVM_XIVE_EQ_ALWAYS_NOTIFY) {
+		pr_err("invalid flags %d\n", kvm_eq.flags);
+		return -EINVAL;
+	}
+
+	rc = xive_native_validate_queue_size(kvm_eq.qshift);
+	if (rc) {
+		pr_err("invalid queue size %d\n", kvm_eq.qshift);
+		return rc;
+	}
+
+	/* reset queue and disable queueing */
+	if (!kvm_eq.qshift) {
+		q->guest_qaddr  = 0;
+		q->guest_qshift = 0;
+
+		rc = xive_native_configure_queue(xc->vp_id, q, priority,
+						 NULL, 0, true);
+		if (rc) {
+			pr_err("Failed to reset queue %d for VCPU %d: %d\n",
+			       priority, xc->server_num, rc);
+			return rc;
+		}
+
+		if (q->qpage) {
+			put_page(virt_to_page(q->qpage));
+			q->qpage = NULL;
+		}
+
+		return 0;
+	}
+
+	if (kvm_eq.qaddr & ((1ull << kvm_eq.qshift) - 1)) {
+		pr_err("queue page is not aligned %llx/%llx\n", kvm_eq.qaddr,
+		       1ull << kvm_eq.qshift);
+		return -EINVAL;
+	}
+
+	gfn = gpa_to_gfn(kvm_eq.qaddr);
+	page = gfn_to_page(kvm, gfn);
+	if (is_error_page(page)) {
+		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
+		return -EINVAL;
+	}
+
+	page_size = kvm_host_page_size(kvm, gfn);
+	if (1ull << kvm_eq.qshift > page_size) {
+		pr_warn("Incompatible host page size %lx!\n", page_size);
+		return -EINVAL;
+	}
+
+	qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK);
+
+	/*
+	 * Backup the queue page guest address to the mark EQ page
+	 * dirty for migration.
+	 */
+	q->guest_qaddr  = kvm_eq.qaddr;
+	q->guest_qshift = kvm_eq.qshift;
+
+	 /*
+	  * Unconditional Notification is forced by default at the
+	  * OPAL level because the use of END ESBs is not supported by
+	  * Linux.
+	  */
+	rc = xive_native_configure_queue(xc->vp_id, q, priority,
+					 (__be32 *) qaddr, kvm_eq.qshift, true);
+	if (rc) {
+		pr_err("Failed to configure queue %d for VCPU %d: %d\n",
+		       priority, xc->server_num, rc);
+		put_page(page);
+		return rc;
+	}
+
+	/*
+	 * Only restore the queue state when needed. When doing the
+	 * H_INT_SET_SOURCE_CONFIG hcall, it should not.
+	 */
+	if (kvm_eq.qtoggle != 1 || kvm_eq.qindex != 0) {
+		rc = xive_native_set_queue_state(xc->vp_id, priority,
+						 kvm_eq.qtoggle,
+						 kvm_eq.qindex);
+		if (rc)
+			goto error;
+	}
+
+	rc = kvmppc_xive_attach_escalation(vcpu, priority,
+					   xive->single_escalation);
+error:
+	if (rc)
+		kvmppc_xive_native_cleanup_queue(vcpu, priority);
+	return rc;
+}
+
+static int kvmppc_xive_native_get_queue_config(struct kvmppc_xive *xive,
+					       long eq_idx, u64 addr)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_xive_vcpu *xc;
+	struct xive_q *q;
+	void __user *ubufp = (u64 __user *) addr;
+	u32 server;
+	u8 priority;
+	struct kvm_ppc_xive_eq kvm_eq;
+	u64 qaddr;
+	u64 qshift;
+	u64 qeoi_page;
+	u32 escalate_irq;
+	u64 qflags;
+	int rc;
+
+	/*
+	 * Demangle priority/server tuple from the EQ identifier
+	 */
+	priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
+		KVM_XIVE_EQ_PRIORITY_SHIFT;
+	server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
+		KVM_XIVE_EQ_SERVER_SHIFT;
+
+	vcpu = kvmppc_xive_find_server(kvm, server);
+	if (!vcpu) {
+		pr_err("Can't find server %d\n", server);
+		return -ENOENT;
+	}
+	xc = vcpu->arch.xive_vcpu;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("invalid priority for queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+	q = &xc->queues[priority];
+
+	memset(&kvm_eq, 0, sizeof(kvm_eq));
+
+	if (!q->qpage)
+		return 0;
+
+	rc = xive_native_get_queue_info(xc->vp_id, priority, &qaddr, &qshift,
+					&qeoi_page, &escalate_irq, &qflags);
+	if (rc)
+		return rc;
+
+	kvm_eq.flags = 0;
+	if (qflags & OPAL_XIVE_EQ_ALWAYS_NOTIFY)
+		kvm_eq.flags |= KVM_XIVE_EQ_ALWAYS_NOTIFY;
+
+	kvm_eq.qshift = q->guest_qshift;
+	kvm_eq.qaddr  = q->guest_qaddr;
+
+	rc = xive_native_get_queue_state(xc->vp_id, priority, &kvm_eq.qtoggle,
+					 &kvm_eq.qindex);
+	if (rc)
+		return rc;
+
+	pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
+		 __func__, server, priority, kvm_eq.flags,
+		 kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
+
+	if (copy_to_user(ubufp, &kvm_eq, sizeof(kvm_eq)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void kvmppc_xive_reset_sources(struct kvmppc_xive_src_block *sb)
+{
+	int i;
+
+	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+
+		if (!state->valid)
+			continue;
+
+		if (state->act_priority == MASKED)
+			continue;
+
+		state->eisn = 0;
+		state->act_server = 0;
+		state->act_priority = MASKED;
+		xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+		xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+		if (state->pt_number) {
+			xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
+			xive_native_configure_irq(state->pt_number,
+						  0, MASKED, 0);
+		}
+	}
+}
+
+static int kvmppc_xive_reset(struct kvmppc_xive *xive)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	pr_devel("%s\n", __func__);
+
+	mutex_lock(&kvm->lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+		unsigned int prio;
+
+		if (!xc)
+			continue;
+
+		kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+		for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+
+			/* Single escalation, no queue 7 */
+			if (prio == 7 && xive->single_escalation)
+				break;
+
+			if (xc->esc_virq[prio]) {
+				free_irq(xc->esc_virq[prio], vcpu);
+				irq_dispose_mapping(xc->esc_virq[prio]);
+				kfree(xc->esc_virq_names[prio]);
+				xc->esc_virq[prio] = 0;
+			}
+
+			kvmppc_xive_native_cleanup_queue(vcpu, prio);
+		}
+	}
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_reset_sources(sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
+	mutex_unlock(&kvm->lock);
+
+	return 0;
+}
+
+static void kvmppc_xive_native_sync_sources(struct kvmppc_xive_src_block *sb)
+{
+	int j;
+
+	for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
+		struct xive_irq_data *xd;
+		u32 hw_num;
+
+		if (!state->valid)
+			continue;
+
+		/*
+		 * The struct kvmppc_xive_irq_state reflects the state
+		 * of the EAS configuration and not the state of the
+		 * source. The source is masked setting the PQ bits to
+		 * '-Q', which is what is being done before calling
+		 * the KVM_DEV_XIVE_EQ_SYNC control.
+		 *
+		 * If a source EAS is configured, OPAL syncs the XIVE
+		 * IC of the source and the XIVE IC of the previous
+		 * target if any.
+		 *
+		 * So it should be fine ignoring MASKED sources as
+		 * they have been synced already.
+		 */
+		if (state->act_priority == MASKED)
+			continue;
+
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+		xive_native_sync_source(hw_num);
+		xive_native_sync_queue(hw_num);
+	}
+}
+
+static int kvmppc_xive_native_vcpu_eq_sync(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	unsigned int prio;
+
+	if (!xc)
+		return -ENOENT;
+
+	for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+		struct xive_q *q = &xc->queues[prio];
+
+		if (!q->qpage)
+			continue;
+
+		/* Mark EQ page dirty for migration */
+		mark_page_dirty(vcpu->kvm, gpa_to_gfn(q->guest_qaddr));
+	}
+	return 0;
+}
+
+static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	pr_devel("%s\n", __func__);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_native_sync_sources(sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		kvmppc_xive_native_vcpu_eq_sync(vcpu);
+	}
+	mutex_unlock(&kvm->lock);
+
+	return 0;
+}
+
+static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XIVE_RESET:
+			return kvmppc_xive_reset(xive);
+		case KVM_DEV_XIVE_EQ_SYNC:
+			return kvmppc_xive_native_eq_sync(xive);
+		}
+		break;
+	case KVM_DEV_XIVE_GRP_SOURCE:
+		return kvmppc_xive_native_set_source(xive, attr->attr,
+						     attr->addr);
+	case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
+		return kvmppc_xive_native_set_source_config(xive, attr->attr,
+							    attr->addr);
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return kvmppc_xive_native_set_queue_config(xive, attr->attr,
+							   attr->addr);
+	case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
+		return kvmppc_xive_native_sync_source(xive, attr->attr,
+						      attr->addr);
+	}
+	return -ENXIO;
+}
+
+static int kvmppc_xive_native_get_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return kvmppc_xive_native_get_queue_config(xive, attr->attr,
+							   attr->addr);
+	}
+	return -ENXIO;
+}
+
+static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XIVE_RESET:
+		case KVM_DEV_XIVE_EQ_SYNC:
+			return 0;
+		}
+		break;
+	case KVM_DEV_XIVE_GRP_SOURCE:
+	case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
+	case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
+		if (attr->attr >= KVMPPC_XIVE_FIRST_IRQ &&
+		    attr->attr < KVMPPC_XIVE_NR_IRQS)
+			return 0;
+		break;
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return 0;
+	}
+	return -ENXIO;
+}
+
+/*
+ * Called when device fd is closed
+ */
+static void kvmppc_xive_native_release(struct kvm_device *dev)
+{
+	struct kvmppc_xive *xive = dev->private;
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	int i;
+	int was_ready;
+
+	debugfs_remove(xive->dentry);
+
+	pr_devel("Releasing xive native device\n");
+
+	/*
+	 * Clearing mmu_ready temporarily while holding kvm->lock
+	 * is a way of ensuring that no vcpus can enter the guest
+	 * until we drop kvm->lock.  Doing kick_all_cpus_sync()
+	 * ensures that any vcpu executing inside the guest has
+	 * exited the guest.  Once kick_all_cpus_sync() has finished,
+	 * we know that no vcpu can be executing the XIVE push or
+	 * pull code or accessing the XIVE MMIO regions.
+	 *
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd or mmap referring to
+	 * the device.  Therefore there can not be any of the
+	 * device attribute set/get, mmap, or page fault functions
+	 * being executed concurrently, and similarly, the
+	 * connect_vcpu and set/clr_mapped functions also cannot
+	 * be being executed.
+	 */
+	was_ready = kvm->arch.mmu_ready;
+	kvm->arch.mmu_ready = 0;
+	kick_all_cpus_sync();
+
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xive_native_[gs]et_vp) can be being done.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
+	kvm->arch.xive = NULL;
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		if (xive->src_blocks[i])
+			kvmppc_xive_free_sources(xive->src_blocks[i]);
+		kfree(xive->src_blocks[i]);
+		xive->src_blocks[i] = NULL;
+	}
+
+	if (xive->vp_base != XIVE_INVALID_VP)
+		xive_native_free_vp_block(xive->vp_base);
+
+	kvm->arch.mmu_ready = was_ready;
+
+	/*
+	 * A reference of the kvmppc_xive pointer is now kept under
+	 * the xive_devices struct of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
+
+	kfree(dev);
+}
+
+/*
+ * Create a XIVE device.  kvm->lock is held.
+ */
+static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
+{
+	struct kvmppc_xive *xive;
+	struct kvm *kvm = dev->kvm;
+	int ret = 0;
+
+	pr_devel("Creating xive native device\n");
+
+	if (kvm->arch.xive)
+		return -EEXIST;
+
+	xive = kvmppc_xive_get_device(kvm, type);
+	if (!xive)
+		return -ENOMEM;
+
+	dev->private = xive;
+	xive->dev = dev;
+	xive->kvm = kvm;
+	kvm->arch.xive = xive;
+	mutex_init(&xive->mapping_lock);
+
+	/*
+	 * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for
+	 * a default. Getting the max number of CPUs the VM was
+	 * configured with would improve our usage of the XIVE VP space.
+	 */
+	xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
+	pr_devel("VP_Base=%x\n", xive->vp_base);
+
+	if (xive->vp_base == XIVE_INVALID_VP)
+		ret = -ENXIO;
+
+	xive->single_escalation = xive_native_has_single_escalation();
+	xive->ops = &kvmppc_xive_native_ops;
+
+	if (ret)
+		kfree(xive);
+
+	return ret;
+}
+
+/*
+ * Interrupt Pending Buffer (IPB) offset
+ */
+#define TM_IPB_SHIFT 40
+#define TM_IPB_MASK  (((u64) 0xFF) << TM_IPB_SHIFT)
+
+int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	u64 opal_state;
+	int rc;
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return -EPERM;
+
+	if (!xc)
+		return -ENOENT;
+
+	/* Thread context registers. We only care about IPB and CPPR */
+	val->xive_timaval[0] = vcpu->arch.xive_saved_state.w01;
+
+	/* Get the VP state from OPAL */
+	rc = xive_native_get_vp_state(xc->vp_id, &opal_state);
+	if (rc)
+		return rc;
+
+	/*
+	 * Capture the backup of IPB register in the NVT structure and
+	 * merge it in our KVM VP state.
+	 */
+	val->xive_timaval[0] |= cpu_to_be64(opal_state & TM_IPB_MASK);
+
+	pr_devel("%s NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x opal=%016llx\n",
+		 __func__,
+		 vcpu->arch.xive_saved_state.nsr,
+		 vcpu->arch.xive_saved_state.cppr,
+		 vcpu->arch.xive_saved_state.ipb,
+		 vcpu->arch.xive_saved_state.pipr,
+		 vcpu->arch.xive_saved_state.w01,
+		 (u32) vcpu->arch.xive_cam_word, opal_state);
+
+	return 0;
+}
+
+int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+
+	pr_devel("%s w01=%016llx vp=%016llx\n", __func__,
+		 val->xive_timaval[0], val->xive_timaval[1]);
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return -EPERM;
+
+	if (!xc || !xive)
+		return -ENOENT;
+
+	/* We can't update the state of a "pushed" VCPU	 */
+	if (WARN_ON(vcpu->arch.xive_pushed))
+		return -EBUSY;
+
+	/*
+	 * Restore the thread context registers. IPB and CPPR should
+	 * be the only ones that matter.
+	 */
+	vcpu->arch.xive_saved_state.w01 = val->xive_timaval[0];
+
+	/*
+	 * There is no need to restore the XIVE internal state (IPB
+	 * stored in the NVT) as the IPB register was merged in KVM VP
+	 * state when captured.
+	 */
+	return 0;
+}
+
+static int xive_native_debug_show(struct seq_file *m, void *private)
+{
+	struct kvmppc_xive *xive = m->private;
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	if (!kvm)
+		return 0;
+
+	seq_puts(m, "=========\nVCPU state\n=========\n");
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+		if (!xc)
+			continue;
+
+		seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
+			   xc->server_num,
+			   vcpu->arch.xive_saved_state.nsr,
+			   vcpu->arch.xive_saved_state.cppr,
+			   vcpu->arch.xive_saved_state.ipb,
+			   vcpu->arch.xive_saved_state.pipr,
+			   vcpu->arch.xive_saved_state.w01,
+			   (u32) vcpu->arch.xive_cam_word);
+
+		kvmppc_xive_debug_show_queues(m, vcpu);
+	}
+
+	return 0;
+}
+
+static int xive_native_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, xive_native_debug_show, inode->i_private);
+}
+
+static const struct file_operations xive_native_debug_fops = {
+	.open = xive_native_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void xive_native_debugfs_init(struct kvmppc_xive *xive)
+{
+	char *name;
+
+	name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
+	if (!name) {
+		pr_err("%s: no memory for name\n", __func__);
+		return;
+	}
+
+	xive->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
+					   xive, &xive_native_debug_fops);
+
+	pr_debug("%s: created %s\n", __func__, name);
+	kfree(name);
+}
+
+static void kvmppc_xive_native_init(struct kvm_device *dev)
+{
+	struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
+
+	/* Register some debug interfaces */
+	xive_native_debugfs_init(xive);
+}
+
+struct kvm_device_ops kvm_xive_native_ops = {
+	.name = "kvm-xive-native",
+	.create = kvmppc_xive_native_create,
+	.init = kvmppc_xive_native_init,
+	.release = kvmppc_xive_native_release,
+	.set_attr = kvmppc_xive_native_set_attr,
+	.get_attr = kvmppc_xive_native_get_attr,
+	.has_attr = kvmppc_xive_native_has_attr,
+	.mmap = kvmppc_xive_native_mmap,
+};
+
+void kvmppc_xive_native_init_module(void)
+{
+	;
+}
+
+void kvmppc_xive_native_exit_module(void)
+{
+	;
+}

arch/powerpc/kvm/book3s_xive_template.c

@@ -130,24 +130,14 @@ static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
 		 */
 		prio = ffs(pending) - 1;
 
-		/*
-		 * If the most favoured prio we found pending is less
-		 * favored (or equal) than a pending IPI, we return
-		 * the IPI instead.
-		 *
-		 * Note: If pending was 0 and mfrr is 0xff, we will
-		 * not spurriously take an IPI because mfrr cannot
-		 * then be smaller than cppr.
-		 */
-		if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+		/* Don't scan past the guest cppr */
+		if (prio >= xc->cppr || prio > 7) {
+			if (xc->mfrr < xc->cppr) {
 				prio = xc->mfrr;
 				hirq = XICS_IPI;
-			break;
 			}
-
-		/* Don't scan past the guest cppr */
-		if (prio >= xc->cppr || prio > 7)
 			break;
+		}
 
 		/* Grab queue and pointers */
 		q = &xc->queues[prio];
@@ -184,9 +174,12 @@ static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
 		 * been set and another occurrence of the IPI will trigger.
 		 */
 		if (hirq == XICS_IPI || (prio == 0 && !qpage)) {
-			if (scan_type == scan_fetch)
+			if (scan_type == scan_fetch) {
 				GLUE(X_PFX,source_eoi)(xc->vp_ipi,
 						       &xc->vp_ipi_data);
+				q->idx = idx;
+				q->toggle = toggle;
+			}
 			/* Loop back on same queue with updated idx/toggle */
 #ifdef XIVE_RUNTIME_CHECKS
 			WARN_ON(hirq && hirq != XICS_IPI);
@@ -199,17 +192,8 @@ static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
 		if (hirq == XICS_DUMMY)
 			goto skip_ipi;
 
-		/* If fetching, update queue pointers */
-		if (scan_type == scan_fetch) {
-			q->idx = idx;
-			q->toggle = toggle;
-		}
-
-		/* Something found, stop searching */
-		if (hirq)
-			break;
-
-		/* Clear the pending bit on the now empty queue */
+		/* Clear the pending bit if the queue is now empty */
+		if (!hirq) {
 			pending &= ~(1 << prio);
 
 			/*
@@ -227,6 +211,24 @@ static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
 			}
 		}
 
+		/*
+		 * If the most favoured prio we found pending is less
+		 * favored (or equal) than a pending IPI, we return
+		 * the IPI instead.
+		 */
+		if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+			prio = xc->mfrr;
+			hirq = XICS_IPI;
+			break;
+		}
+
+		/* If fetching, update queue pointers */
+		if (scan_type == scan_fetch) {
+			q->idx = idx;
+			q->toggle = toggle;
+		}
+	}
+
 	/* If we are just taking a "peek", do nothing else */
 	if (scan_type == scan_poll)
 		return hirq;

arch/powerpc/kvm/powerpc.c

@@ -570,6 +570,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
+#ifdef CONFIG_KVM_XIVE
+	case KVM_CAP_PPC_IRQ_XIVE:
+		/*
+		 * We need XIVE to be enabled on the platform (implies
+		 * a POWER9 processor) and the PowerNV platform, as
+		 * nested is not yet supported.
+		 */
+		r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE);
+		break;
+#endif
 
 	case KVM_CAP_PPC_ALLOC_HTAB:
 		r = hv_enabled;
@@ -750,6 +760,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 		else
 			kvmppc_xics_free_icp(vcpu);
 		break;
+	case KVMPPC_IRQ_XIVE:
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+		break;
 	}
 
 	kvmppc_core_vcpu_free(vcpu);
@@ -1938,6 +1951,30 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		break;
 	}
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+	case KVM_CAP_PPC_IRQ_XIVE: {
+		struct fd f;
+		struct kvm_device *dev;
+
+		r = -EBADF;
+		f = fdget(cap->args[0]);
+		if (!f.file)
+			break;
+
+		r = -ENXIO;
+		if (!xive_enabled())
+			break;
+
+		r = -EPERM;
+		dev = kvm_device_from_filp(f.file);
+		if (dev)
+			r = kvmppc_xive_native_connect_vcpu(dev, vcpu,
+							    cap->args[1]);
+
+		fdput(f);
+		break;
+	}
+#endif /* CONFIG_KVM_XIVE */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_FWNMI:
 		r = -EINVAL;

arch/powerpc/platforms/powernv/opal-call.c

@@ -260,6 +260,9 @@ OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
 OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
 OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
 OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
+OPAL_CALL(opal_xive_get_queue_state,		OPAL_XIVE_GET_QUEUE_STATE);
+OPAL_CALL(opal_xive_set_queue_state,		OPAL_XIVE_SET_QUEUE_STATE);
+OPAL_CALL(opal_xive_get_vp_state,		OPAL_XIVE_GET_VP_STATE);
 OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
 OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
 OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);

arch/powerpc/sysdev/xive/native.c

@@ -437,6 +437,12 @@ void xive_native_sync_source(u32 hw_irq)
 }
 EXPORT_SYMBOL_GPL(xive_native_sync_source);
 
+void xive_native_sync_queue(u32 hw_irq)
+{
+	opal_xive_sync(XIVE_SYNC_QUEUE, hw_irq);
+}
+EXPORT_SYMBOL_GPL(xive_native_sync_queue);
+
 static const struct xive_ops xive_native_ops = {
 	.populate_irq_data	= xive_native_populate_irq_data,
 	.configure_irq		= xive_native_configure_irq,
@@ -515,6 +521,9 @@ u32 xive_native_default_eq_shift(void)
 }
 EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
 
+unsigned long xive_tima_os;
+EXPORT_SYMBOL_GPL(xive_tima_os);
+
 bool __init xive_native_init(void)
 {
 	struct device_node *np;
@@ -567,6 +576,14 @@ bool __init xive_native_init(void)
 	for_each_possible_cpu(cpu)
 		kvmppc_set_xive_tima(cpu, r.start, tima);
 
+	/* Resource 2 is OS window */
+	if (of_address_to_resource(np, 2, &r)) {
+		pr_err("Failed to get thread mgmnt area resource\n");
+		return false;
+	}
+
+	xive_tima_os = r.start;
+
 	/* Grab size of provisionning pages */
 	xive_parse_provisioning(np);
 
@@ -711,3 +728,96 @@ bool xive_native_has_single_escalation(void)
 	return xive_has_single_esc;
 }
 EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
+
+int xive_native_get_queue_info(u32 vp_id, u32 prio,
+			       u64 *out_qpage,
+			       u64 *out_qsize,
+			       u64 *out_qeoi_page,
+			       u32 *out_escalate_irq,
+			       u64 *out_qflags)
+{
+	__be64 qpage;
+	__be64 qsize;
+	__be64 qeoi_page;
+	__be32 escalate_irq;
+	__be64 qflags;
+	s64 rc;
+
+	rc = opal_xive_get_queue_info(vp_id, prio, &qpage, &qsize,
+				      &qeoi_page, &escalate_irq, &qflags);
+	if (rc) {
+		pr_err("OPAL failed to get queue info for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	if (out_qpage)
+		*out_qpage = be64_to_cpu(qpage);
+	if (out_qsize)
+		*out_qsize = be32_to_cpu(qsize);
+	if (out_qeoi_page)
+		*out_qeoi_page = be64_to_cpu(qeoi_page);
+	if (out_escalate_irq)
+		*out_escalate_irq = be32_to_cpu(escalate_irq);
+	if (out_qflags)
+		*out_qflags = be64_to_cpu(qflags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_info);
+
+int xive_native_get_queue_state(u32 vp_id, u32 prio, u32 *qtoggle, u32 *qindex)
+{
+	__be32 opal_qtoggle;
+	__be32 opal_qindex;
+	s64 rc;
+
+	rc = opal_xive_get_queue_state(vp_id, prio, &opal_qtoggle,
+				       &opal_qindex);
+	if (rc) {
+		pr_err("OPAL failed to get queue state for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	if (qtoggle)
+		*qtoggle = be32_to_cpu(opal_qtoggle);
+	if (qindex)
+		*qindex = be32_to_cpu(opal_qindex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_state);
+
+int xive_native_set_queue_state(u32 vp_id, u32 prio, u32 qtoggle, u32 qindex)
+{
+	s64 rc;
+
+	rc = opal_xive_set_queue_state(vp_id, prio, qtoggle, qindex);
+	if (rc) {
+		pr_err("OPAL failed to set queue state for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_set_queue_state);
+
+int xive_native_get_vp_state(u32 vp_id, u64 *out_state)
+{
+	__be64 state;
+	s64 rc;
+
+	rc = opal_xive_get_vp_state(vp_id, &state);
+	if (rc) {
+		pr_err("OPAL failed to get vp state for VCPU %d : %lld\n",
+		       vp_id, rc);
+		return -EIO;
+	}
+
+	if (out_state)
+		*out_state = be64_to_cpu(state);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_state);

include/linux/kvm_host.h

@@ -1270,11 +1270,21 @@ struct kvm_device_ops {
 	 */
 	void (*destroy)(struct kvm_device *dev);
 
+	/*
+	 * Release is an alternative method to free the device. It is
+	 * called when the device file descriptor is closed. Once
+	 * release is called, the destroy method will not be called
+	 * anymore as the device is removed from the device list of
+	 * the VM. kvm->lock is held.
+	 */
+	void (*release)(struct kvm_device *dev);
+
 	int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
 	int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
 	int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
 	long (*ioctl)(struct kvm_device *dev, unsigned int ioctl,
 		      unsigned long arg);
+	int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma);
 };
 
 void kvm_device_get(struct kvm_device *dev);

include/uapi/linux/kvm.h

@@ -989,6 +989,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */
 #define KVM_CAP_HYPERV_CPUID 167
 #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168
+#define KVM_CAP_PPC_IRQ_XIVE 169
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1212,6 +1213,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_V3	KVM_DEV_TYPE_ARM_VGIC_V3
 	KVM_DEV_TYPE_ARM_VGIC_ITS,
 #define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
+	KVM_DEV_TYPE_XIVE,
+#define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
 	KVM_DEV_TYPE_MAX,
 };
 

virt/kvm/kvm_main.c

@@ -2950,6 +2950,16 @@ static long kvm_vcpu_compat_ioctl(struct file *filp,
 }
 #endif
 
+static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct kvm_device *dev = filp->private_data;
+
+	if (dev->ops->mmap)
+		return dev->ops->mmap(dev, vma);
+
+	return -ENODEV;
+}
+
 static int kvm_device_ioctl_attr(struct kvm_device *dev,
 				 int (*accessor)(struct kvm_device *dev,
 						 struct kvm_device_attr *attr),
@@ -2994,6 +3004,13 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
 	struct kvm_device *dev = filp->private_data;
 	struct kvm *kvm = dev->kvm;
 
+	if (dev->ops->release) {
+		mutex_lock(&kvm->lock);
+		list_del(&dev->vm_node);
+		dev->ops->release(dev);
+		mutex_unlock(&kvm->lock);
+	}
+
 	kvm_put_kvm(kvm);
 	return 0;
 }
@@ -3002,6 +3019,7 @@ static const struct file_operations kvm_device_fops = {
 	.unlocked_ioctl = kvm_device_ioctl,
 	.release = kvm_device_release,
 	KVM_COMPAT(kvm_device_ioctl),
+	.mmap = kvm_device_mmap,
 };
 
 struct kvm_device *kvm_device_from_filp(struct file *filp)