Merge branch 'for-upstream' of http://github.com/agraf/linux-2.6 into queue

* 'for-upstream' of http://github.com/agraf/linux-2.6: (56 commits)
  arch/powerpc/kvm/e500_tlb.c: fix error return code
  KVM: PPC: Book3S HV: Provide a way for userspace to get/set per-vCPU areas
  KVM: PPC: Book3S: Get/set guest FP regs using the GET/SET_ONE_REG interface
  KVM: PPC: Book3S: Get/set guest SPRs using the GET/SET_ONE_REG interface
  KVM: PPC: set IN_GUEST_MODE before checking requests
  KVM: PPC: e500: MMU API: fix leak of shared_tlb_pages
  KVM: PPC: e500: fix allocation size error on g2h_tlb1_map
  KVM: PPC: Book3S HV: Fix calculation of guest phys address for MMIO emulation
  KVM: PPC: Book3S HV: Remove bogus update of physical thread IDs
  KVM: PPC: Book3S HV: Fix updates of vcpu->cpu
  KVM: Move some PPC ioctl definitions to the correct place
  KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly
  KVM: PPC: Move kvm->arch.slot_phys into memslot.arch
  KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots
  KVM: PPC: bookehv: Allow duplicate calls of DO_KVM macro
  KVM: PPC: BookE: Support FPU on non-hv systems
  KVM: PPC: 440: Implement mfdcrx
  KVM: PPC: 440: Implement mtdcrx
  Document IACx/DACx registers access using ONE_REG API
  KVM: PPC: E500: Remove E500_TLB_DIRTY flag
  ...

Documentation/virtual/kvm/api.txt

@@ -1194,12 +1194,15 @@ struct kvm_ppc_pvinfo {
 This ioctl fetches PV specific information that need to be passed to the guest
 using the device tree or other means from vm context.
 
-For now the only implemented piece of information distributed here is an array
-of 4 instructions that make up a hypercall.
+The hcall array defines 4 instructions that make up a hypercall.
 
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
+The flags bitmap is defined as:
+
+   /* the host supports the ePAPR idle hcall
+   #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
 
 4.48 KVM_ASSIGN_PCI_DEVICE
 
@@ -1731,7 +1734,45 @@ registers, find a list below:
   Arch  |       Register        | Width (bits)
         |                       |
   PPC   | KVM_REG_PPC_HIOR      | 64
-
+  PPC   | KVM_REG_PPC_IAC1      | 64
+  PPC   | KVM_REG_PPC_IAC2      | 64
+  PPC   | KVM_REG_PPC_IAC3      | 64
+  PPC   | KVM_REG_PPC_IAC4      | 64
+  PPC   | KVM_REG_PPC_DAC1      | 64
+  PPC   | KVM_REG_PPC_DAC2      | 64
+  PPC   | KVM_REG_PPC_DABR      | 64
+  PPC   | KVM_REG_PPC_DSCR      | 64
+  PPC   | KVM_REG_PPC_PURR      | 64
+  PPC   | KVM_REG_PPC_SPURR     | 64
+  PPC   | KVM_REG_PPC_DAR       | 64
+  PPC   | KVM_REG_PPC_DSISR     | 32
+  PPC   | KVM_REG_PPC_AMR       | 64
+  PPC   | KVM_REG_PPC_UAMOR     | 64
+  PPC   | KVM_REG_PPC_MMCR0     | 64
+  PPC   | KVM_REG_PPC_MMCR1     | 64
+  PPC   | KVM_REG_PPC_MMCRA     | 64
+  PPC   | KVM_REG_PPC_PMC1      | 32
+  PPC   | KVM_REG_PPC_PMC2      | 32
+  PPC   | KVM_REG_PPC_PMC3      | 32
+  PPC   | KVM_REG_PPC_PMC4      | 32
+  PPC   | KVM_REG_PPC_PMC5      | 32
+  PPC   | KVM_REG_PPC_PMC6      | 32
+  PPC   | KVM_REG_PPC_PMC7      | 32
+  PPC   | KVM_REG_PPC_PMC8      | 32
+  PPC   | KVM_REG_PPC_FPR0      | 64
+          ...
+  PPC   | KVM_REG_PPC_FPR31     | 64
+  PPC   | KVM_REG_PPC_VR0       | 128
+          ...
+  PPC   | KVM_REG_PPC_VR31      | 128
+  PPC   | KVM_REG_PPC_VSR0      | 128
+          ...
+  PPC   | KVM_REG_PPC_VSR31     | 128
+  PPC   | KVM_REG_PPC_FPSCR     | 64
+  PPC   | KVM_REG_PPC_VSCR      | 32
+  PPC   | KVM_REG_PPC_VPA_ADDR  | 64
+  PPC   | KVM_REG_PPC_VPA_SLB   | 128
+  PPC   | KVM_REG_PPC_VPA_DTL   | 128
 
 4.69 KVM_GET_ONE_REG
 
@@ -1747,7 +1788,7 @@ kvm_one_reg struct passed in. On success, the register value can be found
 at the memory location pointed to by "addr".
 
 The list of registers accessible using this interface is identical to the
-list in 4.64.
+list in 4.68.
 
 
 4.70 KVM_KVMCLOCK_CTRL

arch/powerpc/include/asm/Kbuild

@@ -34,5 +34,6 @@ header-y += termios.h
 header-y += types.h
 header-y += ucontext.h
 header-y += unistd.h
+header-y += epapr_hcalls.h
 
 generic-y += rwsem.h

arch/powerpc/include/asm/epapr_hcalls.h

@@ -50,10 +50,6 @@
 #ifndef _EPAPR_HCALLS_H
 #define _EPAPR_HCALLS_H
 
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <asm/byteorder.h>
-
 #define EV_BYTE_CHANNEL_SEND		1
 #define EV_BYTE_CHANNEL_RECEIVE		2
 #define EV_BYTE_CHANNEL_POLL		3
@@ -88,7 +84,8 @@
 #define _EV_HCALL_TOKEN(id, num) (((id) << 16) | (num))
 #define EV_HCALL_TOKEN(hcall_num) _EV_HCALL_TOKEN(EV_EPAPR_VENDOR_ID, hcall_num)
 
-/* epapr error codes */
+/* epapr return codes */
+#define EV_SUCCESS		0
 #define EV_EPERM		1	/* Operation not permitted */
 #define EV_ENOENT		2	/*  Entry Not Found */
 #define EV_EIO			3	/* I/O error occured */
@@ -108,6 +105,11 @@
 #define EV_UNIMPLEMENTED	12	/* Unimplemented hypercall */
 #define EV_BUFFER_OVERFLOW	13	/* Caller-supplied buffer too small */
 
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/byteorder.h>
+
 /*
  * Hypercall register clobber list
  *
@@ -193,7 +195,7 @@ static inline unsigned int ev_int_set_config(unsigned int interrupt,
 	r5  = priority;
 	r6  = destination;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6)
 		: : EV_HCALL_CLOBBERS4
 	);
@@ -222,7 +224,7 @@ static inline unsigned int ev_int_get_config(unsigned int interrupt,
 	r11 = EV_HCALL_TOKEN(EV_INT_GET_CONFIG);
 	r3 = interrupt;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "=r" (r4), "=r" (r5), "=r" (r6)
 		: : EV_HCALL_CLOBBERS4
 	);
@@ -252,7 +254,7 @@ static inline unsigned int ev_int_set_mask(unsigned int interrupt,
 	r3 = interrupt;
 	r4 = mask;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -277,7 +279,7 @@ static inline unsigned int ev_int_get_mask(unsigned int interrupt,
 	r11 = EV_HCALL_TOKEN(EV_INT_GET_MASK);
 	r3 = interrupt;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "=r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -305,7 +307,7 @@ static inline unsigned int ev_int_eoi(unsigned int interrupt)
 	r11 = EV_HCALL_TOKEN(EV_INT_EOI);
 	r3 = interrupt;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -344,7 +346,7 @@ static inline unsigned int ev_byte_channel_send(unsigned int handle,
 	r7 = be32_to_cpu(p[2]);
 	r8 = be32_to_cpu(p[3]);
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3),
 		  "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7), "+r" (r8)
 		: : EV_HCALL_CLOBBERS6
@@ -383,7 +385,7 @@ static inline unsigned int ev_byte_channel_receive(unsigned int handle,
 	r3 = handle;
 	r4 = *count;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4),
 		  "=r" (r5), "=r" (r6), "=r" (r7), "=r" (r8)
 		: : EV_HCALL_CLOBBERS6
@@ -421,7 +423,7 @@ static inline unsigned int ev_byte_channel_poll(unsigned int handle,
 	r11 = EV_HCALL_TOKEN(EV_BYTE_CHANNEL_POLL);
 	r3 = handle;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "=r" (r4), "=r" (r5)
 		: : EV_HCALL_CLOBBERS3
 	);
@@ -454,7 +456,7 @@ static inline unsigned int ev_int_iack(unsigned int handle,
 	r11 = EV_HCALL_TOKEN(EV_INT_IACK);
 	r3 = handle;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "=r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -478,7 +480,7 @@ static inline unsigned int ev_doorbell_send(unsigned int handle)
 	r11 = EV_HCALL_TOKEN(EV_DOORBELL_SEND);
 	r3 = handle;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -498,12 +500,12 @@ static inline unsigned int ev_idle(void)
 
 	r11 = EV_HCALL_TOKEN(EV_IDLE);
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "=r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
 
 	return r3;
 }
-
+#endif /* !__ASSEMBLY__ */
 #endif

arch/powerpc/include/asm/fsl_hcalls.h

@@ -96,7 +96,7 @@ static inline unsigned int fh_send_nmi(unsigned int vcpu_mask)
 	r11 = FH_HCALL_TOKEN(FH_SEND_NMI);
 	r3 = vcpu_mask;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -151,7 +151,7 @@ static inline unsigned int fh_partition_get_dtprop(int handle,
 	r9 = (uint32_t)propvalue_addr;
 	r10 = *propvalue_len;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11),
 		  "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7),
 		  "+r" (r8), "+r" (r9), "+r" (r10)
@@ -205,7 +205,7 @@ static inline unsigned int fh_partition_set_dtprop(int handle,
 	r9 = (uint32_t)propvalue_addr;
 	r10 = propvalue_len;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11),
 		  "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7),
 		  "+r" (r8), "+r" (r9), "+r" (r10)
@@ -229,7 +229,7 @@ static inline unsigned int fh_partition_restart(unsigned int partition)
 	r11 = FH_HCALL_TOKEN(FH_PARTITION_RESTART);
 	r3 = partition;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -262,7 +262,7 @@ static inline unsigned int fh_partition_get_status(unsigned int partition,
 	r11 = FH_HCALL_TOKEN(FH_PARTITION_GET_STATUS);
 	r3 = partition;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "=r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -295,7 +295,7 @@ static inline unsigned int fh_partition_start(unsigned int partition,
 	r4 = entry_point;
 	r5 = load;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4), "+r" (r5)
 		: : EV_HCALL_CLOBBERS3
 	);
@@ -317,7 +317,7 @@ static inline unsigned int fh_partition_stop(unsigned int partition)
 	r11 = FH_HCALL_TOKEN(FH_PARTITION_STOP);
 	r3 = partition;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -376,7 +376,7 @@ static inline unsigned int fh_partition_memcpy(unsigned int source,
 #endif
 	r7 = count;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11),
 		  "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7)
 		: : EV_HCALL_CLOBBERS5
@@ -399,7 +399,7 @@ static inline unsigned int fh_dma_enable(unsigned int liodn)
 	r11 = FH_HCALL_TOKEN(FH_DMA_ENABLE);
 	r3 = liodn;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -421,7 +421,7 @@ static inline unsigned int fh_dma_disable(unsigned int liodn)
 	r11 = FH_HCALL_TOKEN(FH_DMA_DISABLE);
 	r3 = liodn;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -447,7 +447,7 @@ static inline unsigned int fh_vmpic_get_msir(unsigned int interrupt,
 	r11 = FH_HCALL_TOKEN(FH_VMPIC_GET_MSIR);
 	r3 = interrupt;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "=r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -469,7 +469,7 @@ static inline unsigned int fh_system_reset(void)
 
 	r11 = FH_HCALL_TOKEN(FH_SYSTEM_RESET);
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "=r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -506,7 +506,7 @@ static inline unsigned int fh_err_get_info(int queue, uint32_t *bufsize,
 	r6 = addr_lo;
 	r7 = peek;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6),
 		  "+r" (r7)
 		: : EV_HCALL_CLOBBERS5
@@ -542,7 +542,7 @@ static inline unsigned int fh_get_core_state(unsigned int handle,
 	r3 = handle;
 	r4 = vcpu;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -572,7 +572,7 @@ static inline unsigned int fh_enter_nap(unsigned int handle, unsigned int vcpu)
 	r3 = handle;
 	r4 = vcpu;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -597,7 +597,7 @@ static inline unsigned int fh_exit_nap(unsigned int handle, unsigned int vcpu)
 	r3 = handle;
 	r4 = vcpu;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3), "+r" (r4)
 		: : EV_HCALL_CLOBBERS2
 	);
@@ -618,7 +618,7 @@ static inline unsigned int fh_claim_device(unsigned int handle)
 	r11 = FH_HCALL_TOKEN(FH_CLAIM_DEVICE);
 	r3 = handle;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);
@@ -645,7 +645,7 @@ static inline unsigned int fh_partition_stop_dma(unsigned int handle)
 	r11 = FH_HCALL_TOKEN(FH_PARTITION_STOP_DMA);
 	r3 = handle;
 
-	__asm__ __volatile__ ("sc 1"
+	asm volatile("bl	epapr_hypercall_start"
 		: "+r" (r11), "+r" (r3)
 		: : EV_HCALL_CLOBBERS1
 	);

arch/powerpc/include/asm/kvm.h

@@ -221,6 +221,12 @@ struct kvm_sregs {
 
 			__u32 dbsr;	/* KVM_SREGS_E_UPDATE_DBSR */
 			__u32 dbcr[3];
+			/*
+			 * iac/dac registers are 64bit wide, while this API
+			 * interface provides only lower 32 bits on 64 bit
+			 * processors. ONE_REG interface is added for 64bit
+			 * iac/dac registers.
+			 */
 			__u32 iac[4];
 			__u32 dac[2];
 			__u32 dvc[2];
@@ -326,5 +332,58 @@ struct kvm_book3e_206_tlb_params {
 };
 
 #define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+#define KVM_REG_PPC_IAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_PPC_IAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_PPC_IAC3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_PPC_IAC4	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_PPC_DAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_PPC_DAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_PPC_DABR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_PPC_DSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9)
+#define KVM_REG_PPC_PURR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa)
+#define KVM_REG_PPC_SPURR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb)
+#define KVM_REG_PPC_DAR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc)
+#define KVM_REG_PPC_DSISR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xd)
+#define KVM_REG_PPC_AMR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xe)
+#define KVM_REG_PPC_UAMOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xf)
+
+#define KVM_REG_PPC_MMCR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
+#define KVM_REG_PPC_MMCR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
+#define KVM_REG_PPC_MMCRA	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+
+#define KVM_REG_PPC_PMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
+#define KVM_REG_PPC_PMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
+#define KVM_REG_PPC_PMC3	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1a)
+#define KVM_REG_PPC_PMC4	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1b)
+#define KVM_REG_PPC_PMC5	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1c)
+#define KVM_REG_PPC_PMC6	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1d)
+#define KVM_REG_PPC_PMC7	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1e)
+#define KVM_REG_PPC_PMC8	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1f)
+
+/* 32 floating-point registers */
+#define KVM_REG_PPC_FPR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x20)
+#define KVM_REG_PPC_FPR(n)	(KVM_REG_PPC_FPR0 + (n))
+#define KVM_REG_PPC_FPR31	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3f)
+
+/* 32 VMX/Altivec vector registers */
+#define KVM_REG_PPC_VR0		(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x40)
+#define KVM_REG_PPC_VR(n)	(KVM_REG_PPC_VR0 + (n))
+#define KVM_REG_PPC_VR31	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x5f)
+
+/* 32 double-width FP registers for VSX */
+/* High-order halves overlap with FP regs */
+#define KVM_REG_PPC_VSR0	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x60)
+#define KVM_REG_PPC_VSR(n)	(KVM_REG_PPC_VSR0 + (n))
+#define KVM_REG_PPC_VSR31	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x7f)
+
+/* FP and vector status/control registers */
+#define KVM_REG_PPC_FPSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x80)
+#define KVM_REG_PPC_VSCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x81)
+
+/* Virtual processor areas */
+/* For SLB & DTL, address in high (first) half, length in low half */
+#define KVM_REG_PPC_VPA_ADDR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x82)
+#define KVM_REG_PPC_VPA_SLB	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x83)
+#define KVM_REG_PPC_VPA_DTL	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
 
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/include/asm/kvm_book3s.h

@@ -160,7 +160,7 @@ extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 			long pte_index, unsigned long pteh, unsigned long ptel);
 extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
-			struct kvm_memory_slot *memslot);
+			struct kvm_memory_slot *memslot, unsigned long *map);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);

arch/powerpc/include/asm/kvm_booke_hv_asm.h

@@ -38,9 +38,9 @@
 #ifdef CONFIG_KVM_BOOKE_HV
 BEGIN_FTR_SECTION
 	mtocrf	0x80, r11	/* check MSR[GS] without clobbering reg */
-	bf	3, kvmppc_resume_\intno\()_\srr1
+	bf	3, 1975f
 	b	kvmppc_handler_\intno\()_\srr1
-kvmppc_resume_\intno\()_\srr1:
+1975:
 END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 #endif
 .endm

arch/powerpc/include/asm/kvm_host.h

@@ -46,7 +46,7 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#if !defined(CONFIG_KVM_440)
 #include <linux/mmu_notifier.h>
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
@@ -204,7 +204,7 @@ struct revmap_entry {
 };
 
 /*
- * We use the top bit of each memslot->rmap entry as a lock bit,
+ * We use the top bit of each memslot->arch.rmap entry as a lock bit,
  * and bit 32 as a present flag.  The bottom 32 bits are the
  * index in the guest HPT of a HPTE that points to the page.
  */
@@ -215,14 +215,17 @@ struct revmap_entry {
 #define KVMPPC_RMAP_PRESENT	0x100000000ul
 #define KVMPPC_RMAP_INDEX	0xfffffffful
 
-/* Low-order bits in kvm->arch.slot_phys[][] */
+/* Low-order bits in memslot->arch.slot_phys[] */
 #define KVMPPC_PAGE_ORDER_MASK	0x1f
 #define KVMPPC_PAGE_NO_CACHE	HPTE_R_I	/* 0x20 */
 #define KVMPPC_PAGE_WRITETHRU	HPTE_R_W	/* 0x40 */
 #define KVMPPC_GOT_PAGE		0x80
 
 struct kvm_arch_memory_slot {
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long *rmap;
+	unsigned long *slot_phys;
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
 struct kvm_arch {
@@ -246,8 +249,6 @@ struct kvm_arch {
 	unsigned long hpt_npte;
 	unsigned long hpt_mask;
 	spinlock_t slot_phys_lock;
-	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
-	int slot_npages[KVM_MEM_SLOTS_NUM];
 	unsigned short last_vcpu[NR_CPUS];
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	struct kvmppc_linear_info *hpt_li;
@@ -346,6 +347,27 @@ struct kvmppc_slb {
 	bool class	: 1;
 };
 
+# ifdef CONFIG_PPC_FSL_BOOK3E
+#define KVMPPC_BOOKE_IAC_NUM	2
+#define KVMPPC_BOOKE_DAC_NUM	2
+# else
+#define KVMPPC_BOOKE_IAC_NUM	4
+#define KVMPPC_BOOKE_DAC_NUM	2
+# endif
+#define KVMPPC_BOOKE_MAX_IAC	4
+#define KVMPPC_BOOKE_MAX_DAC	2
+
+struct kvmppc_booke_debug_reg {
+	u32 dbcr0;
+	u32 dbcr1;
+	u32 dbcr2;
+#ifdef CONFIG_KVM_E500MC
+	u32 dbcr4;
+#endif
+	u64 iac[KVMPPC_BOOKE_MAX_IAC];
+	u64 dac[KVMPPC_BOOKE_MAX_DAC];
+};
+
 struct kvm_vcpu_arch {
 	ulong host_stack;
 	u32 host_pid;
@@ -440,8 +462,6 @@ struct kvm_vcpu_arch {
 
 	u32 ccr0;
 	u32 ccr1;
-	u32 dbcr0;
-	u32 dbcr1;
 	u32 dbsr;
 
 	u64 mmcr[3];
@@ -471,9 +491,12 @@ struct kvm_vcpu_arch {
 	ulong fault_esr;
 	ulong queued_dear;
 	ulong queued_esr;
+	spinlock_t wdt_lock;
+	struct timer_list wdt_timer;
 	u32 tlbcfg[4];
 	u32 mmucfg;
 	u32 epr;
+	struct kvmppc_booke_debug_reg dbg_reg;
 #endif
 	gpa_t paddr_accessed;
 	gva_t vaddr_accessed;
@@ -486,6 +509,7 @@ struct kvm_vcpu_arch {
 	u8 osi_needed;
 	u8 osi_enabled;
 	u8 papr_enabled;
+	u8 watchdog_enabled;
 	u8 sane;
 	u8 cpu_type;
 	u8 hcall_needed;

arch/powerpc/include/asm/kvm_para.h

@@ -75,9 +75,10 @@ struct kvm_vcpu_arch_shared {
 };
 
 #define KVM_SC_MAGIC_R0		0x4b564d21 /* "KVM!" */
-#define HC_VENDOR_KVM		(42 << 16)
-#define HC_EV_SUCCESS		0
-#define HC_EV_UNIMPLEMENTED	12
+
+#define KVM_HCALL_TOKEN(num)     _EV_HCALL_TOKEN(EV_KVM_VENDOR_ID, num)
+
+#include <asm/epapr_hcalls.h>
 
 #define KVM_FEATURE_MAGIC_PAGE	1
 
@@ -121,7 +122,7 @@ static unsigned long kvm_hypercall(unsigned long *in,
 				   unsigned long *out,
 				   unsigned long nr)
 {
-	return HC_EV_UNIMPLEMENTED;
+	return EV_UNIMPLEMENTED;
 }
 
 #endif
@@ -132,7 +133,7 @@ static inline long kvm_hypercall0_1(unsigned int nr, unsigned long *r2)
 	unsigned long out[8];
 	unsigned long r;
 
-	r = kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	r = kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr));
 	*r2 = out[0];
 
 	return r;
@@ -143,7 +144,7 @@ static inline long kvm_hypercall0(unsigned int nr)
 	unsigned long in[8];
 	unsigned long out[8];
 
-	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr));
 }
 
 static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
@@ -152,7 +153,7 @@ static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
 	unsigned long out[8];
 
 	in[0] = p1;
-	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr));
 }
 
 static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
@@ -163,7 +164,7 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
 
 	in[0] = p1;
 	in[1] = p2;
-	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr));
 }
 
 static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
@@ -175,7 +176,7 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
 	in[0] = p1;
 	in[1] = p2;
 	in[2] = p3;
-	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr));
 }
 
 static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
@@ -189,7 +190,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	in[1] = p2;
 	in[2] = p3;
 	in[3] = p4;
-	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr));
 }
 
 

arch/powerpc/include/asm/kvm_ppc.h

@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
+#include <linux/bug.h>
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/kvm_book3s.h>
 #else
@@ -68,6 +69,8 @@ extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb);
 extern void kvmppc_decrementer_func(unsigned long data);
 extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu);
+extern int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 /* Core-specific hooks */
 
@@ -104,6 +107,7 @@ extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
 extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
                                          struct kvm_interrupt *irq);
+extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu);
 
 extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                   unsigned int op, int *advance);
@@ -111,6 +115,7 @@ extern int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn,
 				     ulong val);
 extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn,
 				     ulong *val);
+extern int kvmppc_core_check_requests(struct kvm_vcpu *vcpu);
 
 extern int kvmppc_booke_init(void);
 extern void kvmppc_booke_exit(void);
@@ -139,16 +144,26 @@ extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
 extern void kvm_release_hpt(struct kvmppc_linear_info *li);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
+extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+				     struct kvm_memory_slot *dont);
+extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+				      unsigned long npages);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem);
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
 				      struct kvm_ppc_smmu_info *info);
+extern void kvmppc_core_flush_memslot(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot);
 
 extern int kvmppc_bookehv_init(void);
 extern void kvmppc_bookehv_exit(void);
 
+extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
@@ -182,6 +197,41 @@ static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value)
 	return r;
 }
 
+union kvmppc_one_reg {
+	u32	wval;
+	u64	dval;
+	vector128 vval;
+	u64	vsxval[2];
+	struct {
+		u64	addr;
+		u64	length;
+	}	vpaval;
+};
+
+#define one_reg_size(id)	\
+	(1ul << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+#define get_reg_val(id, reg)	({		\
+	union kvmppc_one_reg __u;		\
+	switch (one_reg_size(id)) {		\
+	case 4: __u.wval = (reg); break;	\
+	case 8: __u.dval = (reg); break;	\
+	default: BUG();				\
+	}					\
+	__u;					\
+})
+
+
+#define set_reg_val(id, val)	({		\
+	u64 __v;				\
+	switch (one_reg_size(id)) {		\
+	case 4: __v = (val).wval; break;	\
+	case 8: __v = (val).dval; break;	\
+	default: BUG();				\
+	}					\
+	__v;					\
+})
+
 void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
@@ -190,6 +240,8 @@ int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
 int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *);
+int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *);
 
 void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
@@ -230,5 +282,15 @@ static inline void kvmppc_mmu_flush_icache(pfn_t pfn)
 	}
 }
 
+/* Please call after prepare_to_enter. This function puts the lazy ee state
+   back to normal mode, without actually enabling interrupts. */
+static inline void kvmppc_lazy_ee_enable(void)
+{
+#ifdef CONFIG_PPC64
+	/* Only need to enable IRQs by hard enabling them after this */
+	local_paca->irq_happened = 0;
+	local_paca->soft_enabled = 1;
+#endif
+}
 
 #endif /* __POWERPC_KVM_PPC_H__ */

arch/powerpc/include/asm/reg_booke.h

@@ -539,6 +539,13 @@
 #define TCR_FIE		0x00800000	/* FIT Interrupt Enable */
 #define TCR_ARE		0x00400000	/* Auto Reload Enable */
 
+#ifdef CONFIG_E500
+#define TCR_GET_WP(tcr)  ((((tcr) & 0xC0000000) >> 30) | \
+			      (((tcr) & 0x1E0000) >> 15))
+#else
+#define TCR_GET_WP(tcr)  (((tcr) & 0xC0000000) >> 30)
+#endif
+
 /* Bit definitions for the TSR. */
 #define TSR_ENW		0x80000000	/* Enable Next Watchdog */
 #define TSR_WIS		0x40000000	/* WDT Interrupt Status */

arch/powerpc/kernel/epapr_hcalls.S

@@ -8,13 +8,41 @@
  */
 
 #include <linux/threads.h>
+#include <asm/epapr_hcalls.h>
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/cputable.h>
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
+#include <asm/asm-compat.h>
 #include <asm/asm-offsets.h>
 
+/* epapr_ev_idle() was derived from e500_idle() */
+_GLOBAL(epapr_ev_idle)
+	CURRENT_THREAD_INFO(r3, r1)
+	PPC_LL	r4, TI_LOCAL_FLAGS(r3)	/* set napping bit */
+	ori	r4, r4,_TLF_NAPPING	/* so when we take an exception */
+	PPC_STL	r4, TI_LOCAL_FLAGS(r3)	/* it will return to our caller */
+
+	wrteei	1
+
+idle_loop:
+	LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE))
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+	li	r3, -1
+	nop
+	nop
+	nop
+
+	/*
+	 * Guard against spurious wakeups from a hypervisor --
+	 * only interrupt will cause us to return to LR due to
+	 * _TLF_NAPPING.
+	 */
+	b	idle_loop
+
 /* Hypercall entry point. Will be patched with device tree instructions. */
 .global epapr_hypercall_start
 epapr_hypercall_start:

arch/powerpc/kernel/epapr_paravirt.c

@@ -21,6 +21,10 @@
 #include <asm/epapr_hcalls.h>
 #include <asm/cacheflush.h>
 #include <asm/code-patching.h>
+#include <asm/machdep.h>
+
+extern void epapr_ev_idle(void);
+extern u32 epapr_ev_idle_start[];
 
 bool epapr_paravirt_enabled;
 
@@ -41,8 +45,13 @@ static int __init epapr_paravirt_init(void)
 	if (len % 4 || len > (4 * 4))
 		return -ENODEV;
 
-	for (i = 0; i < (len / 4); i++)
+	for (i = 0; i < (len / 4); i++) {
 		patch_instruction(epapr_hypercall_start + i, insts[i]);
+		patch_instruction(epapr_ev_idle_start + i, insts[i]);
+	}
+
+	if (of_get_property(hyper_node, "has-idle", NULL))
+		ppc_md.power_save = epapr_ev_idle;
 
 	epapr_paravirt_enabled = true;
 

arch/powerpc/kernel/kvm.c

@@ -419,7 +419,7 @@ static void kvm_map_magic_page(void *data)
 	in[0] = KVM_MAGIC_PAGE;
 	in[1] = KVM_MAGIC_PAGE;
 
-	kvm_hypercall(in, out, HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE);
+	kvm_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE));
 
 	*features = out[0];
 }

arch/powerpc/kernel/ppc_ksyms.c

@@ -43,6 +43,7 @@
 #include <asm/dcr.h>
 #include <asm/ftrace.h>
 #include <asm/switch_to.h>
+#include <asm/epapr_hcalls.h>
 
 #ifdef CONFIG_PPC32
 extern void transfer_to_handler(void);
@@ -192,3 +193,7 @@ EXPORT_SYMBOL(__arch_hweight64);
 #ifdef CONFIG_PPC_BOOK3S_64
 EXPORT_SYMBOL_GPL(mmu_psize_defs);
 #endif
+
+#ifdef CONFIG_EPAPR_PARAVIRT
+EXPORT_SYMBOL(epapr_hypercall_start);
+#endif

arch/powerpc/kvm/44x.c

@@ -83,6 +83,7 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu_44x->shadow_refs[i].gtlb_index = -1;
 
 	vcpu->arch.cpu_type = KVM_CPU_440;
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
 
 	return 0;
 }

arch/powerpc/kvm/44x_emulate.c

@@ -27,12 +27,68 @@
 #include "booke.h"
 #include "44x_tlb.h"
 
+#define XOP_MFDCRX  259
 #define XOP_MFDCR   323
+#define XOP_MTDCRX  387
 #define XOP_MTDCR   451
 #define XOP_TLBSX   914
 #define XOP_ICCCI   966
 #define XOP_TLBWE   978
 
+static int emulate_mtdcr(struct kvm_vcpu *vcpu, int rs, int dcrn)
+{
+	/* emulate some access in kernel */
+	switch (dcrn) {
+	case DCRN_CPR0_CONFIG_ADDR:
+		vcpu->arch.cpr0_cfgaddr = kvmppc_get_gpr(vcpu, rs);
+		return EMULATE_DONE;
+	default:
+		vcpu->run->dcr.dcrn = dcrn;
+		vcpu->run->dcr.data = kvmppc_get_gpr(vcpu, rs);
+		vcpu->run->dcr.is_write = 1;
+		vcpu->arch.dcr_needed = 1;
+		kvmppc_account_exit(vcpu, DCR_EXITS);
+		return EMULATE_DO_DCR;
+	}
+}
+
+static int emulate_mfdcr(struct kvm_vcpu *vcpu, int rt, int dcrn)
+{
+	/* The guest may access CPR0 registers to determine the timebase
+	 * frequency, and it must know the real host frequency because it
+	 * can directly access the timebase registers.
+	 *
+	 * It would be possible to emulate those accesses in userspace,
+	 * but userspace can really only figure out the end frequency.
+	 * We could decompose that into the factors that compute it, but
+	 * that's tricky math, and it's easier to just report the real
+	 * CPR0 values.
+	 */
+	switch (dcrn) {
+	case DCRN_CPR0_CONFIG_ADDR:
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.cpr0_cfgaddr);
+		break;
+	case DCRN_CPR0_CONFIG_DATA:
+		local_irq_disable();
+		mtdcr(DCRN_CPR0_CONFIG_ADDR,
+			  vcpu->arch.cpr0_cfgaddr);
+		kvmppc_set_gpr(vcpu, rt,
+			       mfdcr(DCRN_CPR0_CONFIG_DATA));
+		local_irq_enable();
+		break;
+	default:
+		vcpu->run->dcr.dcrn = dcrn;
+		vcpu->run->dcr.data =  0;
+		vcpu->run->dcr.is_write = 0;
+		vcpu->arch.io_gpr = rt;
+		vcpu->arch.dcr_needed = 1;
+		kvmppc_account_exit(vcpu, DCR_EXITS);
+		return EMULATE_DO_DCR;
+	}
+
+	return EMULATE_DONE;
+}
+
 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
@@ -50,55 +106,21 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		switch (get_xop(inst)) {
 
 		case XOP_MFDCR:
-			/* The guest may access CPR0 registers to determine the timebase
-			 * frequency, and it must know the real host frequency because it
-			 * can directly access the timebase registers.
-			 *
-			 * It would be possible to emulate those accesses in userspace,
-			 * but userspace can really only figure out the end frequency.
-			 * We could decompose that into the factors that compute it, but
-			 * that's tricky math, and it's easier to just report the real
-			 * CPR0 values.
-			 */
-			switch (dcrn) {
-			case DCRN_CPR0_CONFIG_ADDR:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.cpr0_cfgaddr);
-				break;
-			case DCRN_CPR0_CONFIG_DATA:
-				local_irq_disable();
-				mtdcr(DCRN_CPR0_CONFIG_ADDR,
-					  vcpu->arch.cpr0_cfgaddr);
-				kvmppc_set_gpr(vcpu, rt,
-					       mfdcr(DCRN_CPR0_CONFIG_DATA));
-				local_irq_enable();
-				break;
-			default:
-				run->dcr.dcrn = dcrn;
-				run->dcr.data =  0;
-				run->dcr.is_write = 0;
-				vcpu->arch.io_gpr = rt;
-				vcpu->arch.dcr_needed = 1;
-				kvmppc_account_exit(vcpu, DCR_EXITS);
-				emulated = EMULATE_DO_DCR;
-			}
+			emulated = emulate_mfdcr(vcpu, rt, dcrn);
+			break;
 
+		case XOP_MFDCRX:
+			emulated = emulate_mfdcr(vcpu, rt,
+					kvmppc_get_gpr(vcpu, ra));
 			break;
 
 		case XOP_MTDCR:
-			/* emulate some access in kernel */
-			switch (dcrn) {
-			case DCRN_CPR0_CONFIG_ADDR:
-				vcpu->arch.cpr0_cfgaddr = kvmppc_get_gpr(vcpu, rs);
-				break;
-			default:
-				run->dcr.dcrn = dcrn;
-				run->dcr.data = kvmppc_get_gpr(vcpu, rs);
-				run->dcr.is_write = 1;
-				vcpu->arch.dcr_needed = 1;
-				kvmppc_account_exit(vcpu, DCR_EXITS);
-				emulated = EMULATE_DO_DCR;
-			}
+			emulated = emulate_mtdcr(vcpu, rs, dcrn);
+			break;
 
+		case XOP_MTDCRX:
+			emulated = emulate_mtdcr(vcpu, rs,
+					kvmppc_get_gpr(vcpu, ra));
 			break;
 
 		case XOP_TLBWE:

arch/powerpc/kvm/Kconfig

@@ -36,6 +36,7 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR
 	bool
 	select KVM_MMIO
+	select MMU_NOTIFIER
 
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
@@ -123,6 +124,7 @@ config KVM_E500V2
 	depends on EXPERIMENTAL && E500 && !PPC_E500MC
 	select KVM
 	select KVM_MMIO
+	select MMU_NOTIFIER
 	---help---
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -138,6 +140,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
+	select MMU_NOTIFIER
 	---help---
 	  Support running unmodified E500MC/E5500 (32-bit) guest kernels in
 	  virtual machines on E500MC/E5500 host processors.

arch/powerpc/kvm/book3s.c

@@ -411,6 +411,15 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
@@ -476,6 +485,122 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return -ENOTSUPP;
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r;
+	union kvmppc_one_reg val;
+	int size;
+	long int i;
+
+	size = one_reg_size(reg->id);
+	if (size > sizeof(val))
+		return -EINVAL;
+
+	r = kvmppc_get_one_reg(vcpu, reg->id, &val);
+
+	if (r == -EINVAL) {
+		r = 0;
+		switch (reg->id) {
+		case KVM_REG_PPC_DAR:
+			val = get_reg_val(reg->id, vcpu->arch.shared->dar);
+			break;
+		case KVM_REG_PPC_DSISR:
+			val = get_reg_val(reg->id, vcpu->arch.shared->dsisr);
+			break;
+		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
+			i = reg->id - KVM_REG_PPC_FPR0;
+			val = get_reg_val(reg->id, vcpu->arch.fpr[i]);
+			break;
+		case KVM_REG_PPC_FPSCR:
+			val = get_reg_val(reg->id, vcpu->arch.fpscr);
+			break;
+#ifdef CONFIG_ALTIVEC
+		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			val.vval = vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0];
+			break;
+		case KVM_REG_PPC_VSCR:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
+			break;
+#endif /* CONFIG_ALTIVEC */
+		default:
+			r = -EINVAL;
+			break;
+		}
+	}
+	if (r)
+		return r;
+
+	if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size))
+		r = -EFAULT;
+
+	return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r;
+	union kvmppc_one_reg val;
+	int size;
+	long int i;
+
+	size = one_reg_size(reg->id);
+	if (size > sizeof(val))
+		return -EINVAL;
+
+	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
+		return -EFAULT;
+
+	r = kvmppc_set_one_reg(vcpu, reg->id, &val);
+
+	if (r == -EINVAL) {
+		r = 0;
+		switch (reg->id) {
+		case KVM_REG_PPC_DAR:
+			vcpu->arch.shared->dar = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_DSISR:
+			vcpu->arch.shared->dsisr = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
+			i = reg->id - KVM_REG_PPC_FPR0;
+			vcpu->arch.fpr[i] = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_FPSCR:
+			vcpu->arch.fpscr = set_reg_val(reg->id, val);
+			break;
+#ifdef CONFIG_ALTIVEC
+		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			break;
+		case KVM_REG_PPC_VSCR:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val);
+			break;
+#endif /* CONFIG_ALTIVEC */
+		default:
+			r = -EINVAL;
+			break;
+		}
+	}
+
+	return r;
+}
+
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
                                   struct kvm_translation *tr)
 {

arch/powerpc/kvm/book3s_32_mmu_host.c

@@ -254,6 +254,7 @@ next_pteg:
 
 	kvmppc_mmu_hpte_cache_map(vcpu, pte);
 
+	kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
 out:
 	return r;
 }

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -168,6 +168,7 @@ map_again:
 
 		kvmppc_mmu_hpte_cache_map(vcpu, pte);
 	}
+	kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
 
 out:
 	return r;

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
+#include <linux/srcu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -260,7 +261,7 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 
 /*
  * This is called to get a reference to a guest page if there isn't
- * one already in the kvm->arch.slot_phys[][] arrays.
+ * one already in the memslot->arch.slot_phys[] array.
  */
 static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 				  struct kvm_memory_slot *memslot,
@@ -275,7 +276,7 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	struct vm_area_struct *vma;
 	unsigned long pfn, i, npages;
 
-	physp = kvm->arch.slot_phys[memslot->id];
+	physp = memslot->arch.slot_phys;
 	if (!physp)
 		return -EINVAL;
 	if (physp[gfn - memslot->base_gfn])
@@ -570,7 +571,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hptep, hpte[3], r;
 	unsigned long mmu_seq, psize, pte_size;
-	unsigned long gfn, hva, pfn;
+	unsigned long gpa, gfn, hva, pfn;
 	struct kvm_memory_slot *memslot;
 	unsigned long *rmap;
 	struct revmap_entry *rev;
@@ -608,15 +609,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	/* Translate the logical address and get the page */
 	psize = hpte_page_size(hpte[0], r);
-	gfn = hpte_rpn(r, psize);
+	gpa = (r & HPTE_R_RPN & ~(psize - 1)) | (ea & (psize - 1));
+	gfn = gpa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(kvm, gfn);
 
 	/* No memslot means it's an emulated MMIO region */
-	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
-		unsigned long gpa = (gfn << PAGE_SHIFT) | (ea & (psize - 1));
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
 					      dsisr & DSISR_ISSTORE);
-	}
 
 	if (!kvm->arch.using_mmu_notifiers)
 		return -EFAULT;		/* should never get here */
@@ -850,7 +850,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 		psize = hpte_page_size(hptep[0], ptel);
 		if ((hptep[0] & HPTE_V_VALID) &&
 		    hpte_rpn(ptel, psize) == gfn) {
-			hptep[0] |= HPTE_V_ABSENT;
+			if (kvm->arch.using_mmu_notifiers)
+				hptep[0] |= HPTE_V_ABSENT;
 			kvmppc_invalidate_hpte(kvm, hptep, i);
 			/* Harvest R and C */
 			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
@@ -877,6 +878,28 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return 0;
 }
 
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	unsigned long *rmapp;
+	unsigned long gfn;
+	unsigned long n;
+
+	rmapp = memslot->arch.rmap;
+	gfn = memslot->base_gfn;
+	for (n = memslot->npages; n; --n) {
+		/*
+		 * Testing the present bit without locking is OK because
+		 * the memslot has been marked invalid already, and hence
+		 * no new HPTEs referencing this page can be created,
+		 * thus the present bit can't go from 0 to 1.
+		 */
+		if (*rmapp & KVMPPC_RMAP_PRESENT)
+			kvm_unmap_rmapp(kvm, rmapp, gfn);
+		++rmapp;
+		++gfn;
+	}
+}
+
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			 unsigned long gfn)
 {
@@ -1030,16 +1053,16 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
 	return ret;
 }
 
-long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			     unsigned long *map)
 {
 	unsigned long i;
-	unsigned long *rmapp, *map;
+	unsigned long *rmapp;
 
 	preempt_disable();
 	rmapp = memslot->arch.rmap;
-	map = memslot->dirty_bitmap;
 	for (i = 0; i < memslot->npages; ++i) {
-		if (kvm_test_clear_dirty(kvm, rmapp))
+		if (kvm_test_clear_dirty(kvm, rmapp) && map)
 			__set_bit_le(i, map);
 		++rmapp;
 	}
@@ -1057,20 +1080,22 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 	unsigned long hva, psize, offset;
 	unsigned long pa;
 	unsigned long *physp;
+	int srcu_idx;
 
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	memslot = gfn_to_memslot(kvm, gfn);
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
-		return NULL;
+		goto err;
 	if (!kvm->arch.using_mmu_notifiers) {
-		physp = kvm->arch.slot_phys[memslot->id];
+		physp = memslot->arch.slot_phys;
 		if (!physp)
-			return NULL;
+			goto err;
 		physp += gfn - memslot->base_gfn;
 		pa = *physp;
 		if (!pa) {
 			if (kvmppc_get_guest_page(kvm, gfn, memslot,
 						  PAGE_SIZE) < 0)
-				return NULL;
+				goto err;
 			pa = *physp;
 		}
 		page = pfn_to_page(pa >> PAGE_SHIFT);
@@ -1079,9 +1104,11 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 		hva = gfn_to_hva_memslot(memslot, gfn);
 		npages = get_user_pages_fast(hva, 1, 1, pages);
 		if (npages < 1)
-			return NULL;
+			goto err;
 		page = pages[0];
 	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
 	psize = PAGE_SIZE;
 	if (PageHuge(page)) {
 		page = compound_head(page);
@@ -1091,6 +1118,10 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 	if (nb_ret)
 		*nb_ret = psize - offset;
 	return page_address(page) + offset;
+
+ err:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return NULL;
 }
 
 void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)

arch/powerpc/kvm/book3s_hv.c

@@ -30,6 +30,7 @@
 #include <linux/cpumask.h>
 #include <linux/spinlock.h>
 #include <linux/page-flags.h>
+#include <linux/srcu.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -142,6 +143,22 @@ static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
 	vpa->yield_count = 1;
 }
 
+static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v,
+		   unsigned long addr, unsigned long len)
+{
+	/* check address is cacheline aligned */
+	if (addr & (L1_CACHE_BYTES - 1))
+		return -EINVAL;
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	if (v->next_gpa != addr || v->len != len) {
+		v->next_gpa = addr;
+		v->len = addr ? len : 0;
+		v->update_pending = 1;
+	}
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+	return 0;
+}
+
 /* Length for a per-processor buffer is passed in at offset 4 in the buffer */
 struct reg_vpa {
 	u32 dummy;
@@ -320,7 +337,8 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
-		init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+		if (vcpu->arch.vpa.pinned_addr)
+			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
 	}
 	if (vcpu->arch.dtl.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
@@ -366,13 +384,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	unsigned long req = kvmppc_get_gpr(vcpu, 3);
 	unsigned long target, ret = H_SUCCESS;
 	struct kvm_vcpu *tvcpu;
+	int idx;
 
 	switch (req) {
 	case H_ENTER:
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
 					      kvmppc_get_gpr(vcpu, 5),
 					      kvmppc_get_gpr(vcpu, 6),
 					      kvmppc_get_gpr(vcpu, 7));
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	case H_CEDE:
 		break;
@@ -411,6 +432,7 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			      struct task_struct *tsk)
 {
 	int r = RESUME_HOST;
+	int srcu_idx;
 
 	vcpu->stat.sum_exits++;
 
@@ -470,12 +492,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * have been handled already.
 	 */
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvmppc_book3s_hv_page_fault(run, vcpu,
 				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvmppc_book3s_hv_page_fault(run, vcpu,
 				kvmppc_get_pc(vcpu), 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		break;
 	/*
 	 * This occurs if the guest executes an illegal instruction.
@@ -535,36 +561,175 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 {
-	int r = -EINVAL;
+	int r = 0;
+	long int i;
 
-	switch (reg->id) {
+	switch (id) {
 	case KVM_REG_PPC_HIOR:
-		r = put_user(0, (u64 __user *)reg->addr);
+		*val = get_reg_val(id, 0);
+		break;
+	case KVM_REG_PPC_DABR:
+		*val = get_reg_val(id, vcpu->arch.dabr);
+		break;
+	case KVM_REG_PPC_DSCR:
+		*val = get_reg_val(id, vcpu->arch.dscr);
+		break;
+	case KVM_REG_PPC_PURR:
+		*val = get_reg_val(id, vcpu->arch.purr);
+		break;
+	case KVM_REG_PPC_SPURR:
+		*val = get_reg_val(id, vcpu->arch.spurr);
+		break;
+	case KVM_REG_PPC_AMR:
+		*val = get_reg_val(id, vcpu->arch.amr);
+		break;
+	case KVM_REG_PPC_UAMOR:
+		*val = get_reg_val(id, vcpu->arch.uamor);
+		break;
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+		i = id - KVM_REG_PPC_MMCR0;
+		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
+		break;
+	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
+		i = id - KVM_REG_PPC_PMC1;
+		*val = get_reg_val(id, vcpu->arch.pmc[i]);
+		break;
+#ifdef CONFIG_VSX
+	case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
+		if (cpu_has_feature(CPU_FTR_VSX)) {
+			/* VSX => FP reg i is stored in arch.vsr[2*i] */
+			long int i = id - KVM_REG_PPC_FPR0;
+			*val = get_reg_val(id, vcpu->arch.vsr[2 * i]);
+		} else {
+			/* let generic code handle it */
+			r = -EINVAL;
+		}
+		break;
+	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
+		if (cpu_has_feature(CPU_FTR_VSX)) {
+			long int i = id - KVM_REG_PPC_VSR0;
+			val->vsxval[0] = vcpu->arch.vsr[2 * i];
+			val->vsxval[1] = vcpu->arch.vsr[2 * i + 1];
+		} else {
+			r = -ENXIO;
+		}
+		break;
+#endif /* CONFIG_VSX */
+	case KVM_REG_PPC_VPA_ADDR:
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+		break;
+	case KVM_REG_PPC_VPA_SLB:
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		val->vpaval.addr = vcpu->arch.slb_shadow.next_gpa;
+		val->vpaval.length = vcpu->arch.slb_shadow.len;
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+		break;
+	case KVM_REG_PPC_VPA_DTL:
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		val->vpaval.addr = vcpu->arch.dtl.next_gpa;
+		val->vpaval.length = vcpu->arch.dtl.len;
+		spin_unlock(&vcpu->arch.vpa_update_lock);
 		break;
 	default:
+		r = -EINVAL;
 		break;
 	}
 
 	return r;
 }
 
-int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 {
-	int r = -EINVAL;
+	int r = 0;
+	long int i;
+	unsigned long addr, len;
 
-	switch (reg->id) {
+	switch (id) {
 	case KVM_REG_PPC_HIOR:
-	{
-		u64 hior;
 		/* Only allow this to be set to zero */
-		r = get_user(hior, (u64 __user *)reg->addr);
-		if (!r && (hior != 0))
+		if (set_reg_val(id, *val))
 			r = -EINVAL;
 		break;
-	}
+	case KVM_REG_PPC_DABR:
+		vcpu->arch.dabr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DSCR:
+		vcpu->arch.dscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PURR:
+		vcpu->arch.purr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SPURR:
+		vcpu->arch.spurr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_AMR:
+		vcpu->arch.amr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_UAMOR:
+		vcpu->arch.uamor = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+		i = id - KVM_REG_PPC_MMCR0;
+		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
+		i = id - KVM_REG_PPC_PMC1;
+		vcpu->arch.pmc[i] = set_reg_val(id, *val);
+		break;
+#ifdef CONFIG_VSX
+	case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
+		if (cpu_has_feature(CPU_FTR_VSX)) {
+			/* VSX => FP reg i is stored in arch.vsr[2*i] */
+			long int i = id - KVM_REG_PPC_FPR0;
+			vcpu->arch.vsr[2 * i] = set_reg_val(id, *val);
+		} else {
+			/* let generic code handle it */
+			r = -EINVAL;
+		}
+		break;
+	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
+		if (cpu_has_feature(CPU_FTR_VSX)) {
+			long int i = id - KVM_REG_PPC_VSR0;
+			vcpu->arch.vsr[2 * i] = val->vsxval[0];
+			vcpu->arch.vsr[2 * i + 1] = val->vsxval[1];
+		} else {
+			r = -ENXIO;
+		}
+		break;
+#endif /* CONFIG_VSX */
+	case KVM_REG_PPC_VPA_ADDR:
+		addr = set_reg_val(id, *val);
+		r = -EINVAL;
+		if (!addr && (vcpu->arch.slb_shadow.next_gpa ||
+			      vcpu->arch.dtl.next_gpa))
+			break;
+		r = set_vpa(vcpu, &vcpu->arch.vpa, addr, sizeof(struct lppaca));
+		break;
+	case KVM_REG_PPC_VPA_SLB:
+		addr = val->vpaval.addr;
+		len = val->vpaval.length;
+		r = -EINVAL;
+		if (addr && !vcpu->arch.vpa.next_gpa)
+			break;
+		r = set_vpa(vcpu, &vcpu->arch.slb_shadow, addr, len);
+		break;
+	case KVM_REG_PPC_VPA_DTL:
+		addr = val->vpaval.addr;
+		len = val->vpaval.length;
+		r = -EINVAL;
+		if (len < sizeof(struct dtl_entry))
+			break;
+		if (addr && !vcpu->arch.vpa.next_gpa)
+			break;
+		len -= len % sizeof(struct dtl_entry);
+		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
+		break;
 	default:
+		r = -EINVAL;
 		break;
 	}
 
@@ -697,17 +862,11 @@ extern void xics_wake_cpu(int cpu);
 static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 				   struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *v;
-
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 	--vc->n_runnable;
 	++vc->n_busy;
-	/* decrement the physical thread id of each following vcpu */
-	v = vcpu;
-	list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list)
-		--v->arch.ptid;
 	list_del(&vcpu->arch.run_list);
 }
 
@@ -820,6 +979,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	long ret;
 	u64 now;
 	int ptid, i, need_vpa_update;
+	int srcu_idx;
 
 	/* don't start if any threads have a signal pending */
 	need_vpa_update = 0;
@@ -898,6 +1058,9 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	spin_unlock(&vc->lock);
 
 	kvm_guest_enter();
+
+	srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
+
 	__kvmppc_vcore_entry(NULL, vcpu0);
 	for (i = 0; i < threads_per_core; ++i)
 		kvmppc_release_hwthread(vc->pcpu + i);
@@ -913,6 +1076,8 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->vcore_state = VCORE_EXITING;
 	spin_unlock(&vc->lock);
 
+	srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx);
+
 	/* make sure updates to secondary vcpu structs are visible now */
 	smp_mb();
 	kvm_guest_exit();
@@ -1273,7 +1438,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	n = kvm_dirty_bitmap_bytes(memslot);
 	memset(memslot->dirty_bitmap, 0, n);
 
-	r = kvmppc_hv_get_dirty_log(kvm, memslot);
+	r = kvmppc_hv_get_dirty_log(kvm, memslot, memslot->dirty_bitmap);
 	if (r)
 		goto out;
 
@@ -1299,53 +1464,86 @@ static unsigned long slb_pgsize_encoding(unsigned long psize)
 	return senc;
 }
 
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+static void unpin_slot(struct kvm_memory_slot *memslot)
 {
-	unsigned long npages;
-	unsigned long *phys;
+	unsigned long *physp;
+	unsigned long j, npages, pfn;
+	struct page *page;
 
-	/* Allocate a slot_phys array */
-	phys = kvm->arch.slot_phys[mem->slot];
-	if (!kvm->arch.using_mmu_notifiers && !phys) {
-		npages = mem->memory_size >> PAGE_SHIFT;
-		phys = vzalloc(npages * sizeof(unsigned long));
-		if (!phys)
-			return -ENOMEM;
-		kvm->arch.slot_phys[mem->slot] = phys;
-		kvm->arch.slot_npages[mem->slot] = npages;
+	physp = memslot->arch.slot_phys;
+	npages = memslot->npages;
+	if (!physp)
+		return;
+	for (j = 0; j < npages; j++) {
+		if (!(physp[j] & KVMPPC_GOT_PAGE))
+			continue;
+		pfn = physp[j] >> PAGE_SHIFT;
+		page = pfn_to_page(pfn);
+		SetPageDirty(page);
+		put_page(page);
 	}
+}
+
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+	if (!dont || free->arch.rmap != dont->arch.rmap) {
+		vfree(free->arch.rmap);
+		free->arch.rmap = NULL;
+	}
+	if (!dont || free->arch.slot_phys != dont->arch.slot_phys) {
+		unpin_slot(free);
+		vfree(free->arch.slot_phys);
+		free->arch.slot_phys = NULL;
+	}
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
+	if (!slot->arch.rmap)
+		return -ENOMEM;
+	slot->arch.slot_phys = NULL;
 
 	return 0;
 }
 
-static void unpin_slot(struct kvm *kvm, int slot_id)
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot,
+				      struct kvm_userspace_memory_region *mem)
 {
-	unsigned long *physp;
-	unsigned long j, npages, pfn;
-	struct page *page;
+	unsigned long *phys;
 
-	physp = kvm->arch.slot_phys[slot_id];
-	npages = kvm->arch.slot_npages[slot_id];
-	if (physp) {
-		spin_lock(&kvm->arch.slot_phys_lock);
-		for (j = 0; j < npages; j++) {
-			if (!(physp[j] & KVMPPC_GOT_PAGE))
-				continue;
-			pfn = physp[j] >> PAGE_SHIFT;
-			page = pfn_to_page(pfn);
-			SetPageDirty(page);
-			put_page(page);
-		}
-		kvm->arch.slot_phys[slot_id] = NULL;
-		spin_unlock(&kvm->arch.slot_phys_lock);
-		vfree(physp);
+	/* Allocate a slot_phys array if needed */
+	phys = memslot->arch.slot_phys;
+	if (!kvm->arch.using_mmu_notifiers && !phys && memslot->npages) {
+		phys = vzalloc(memslot->npages * sizeof(unsigned long));
+		if (!phys)
+			return -ENOMEM;
+		memslot->arch.slot_phys = phys;
 	}
+
+	return 0;
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+				      struct kvm_userspace_memory_region *mem,
+				      struct kvm_memory_slot old)
 {
+	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	if (npages && old.npages) {
+		/*
+		 * If modifying a memslot, reset all the rmap dirty bits.
+		 * If this is a new memslot, we don't need to do anything
+		 * since the rmap array starts out as all zeroes,
+		 * i.e. no pages are dirty.
+		 */
+		memslot = id_to_memslot(kvm->memslots, mem->slot);
+		kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
+	}
 }
 
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
@@ -1362,6 +1560,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	unsigned long rmls;
 	unsigned long *physp;
 	unsigned long i, npages;
+	int srcu_idx;
 
 	mutex_lock(&kvm->lock);
 	if (kvm->arch.rma_setup_done)
@@ -1377,12 +1576,13 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	}
 
 	/* Look up the memslot for guest physical address 0 */
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	memslot = gfn_to_memslot(kvm, 0);
 
 	/* We must have some memory at 0 by now */
 	err = -EINVAL;
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
-		goto out;
+		goto out_srcu;
 
 	/* Look up the VMA for the start of this memory slot */
 	hva = memslot->userspace_addr;
@@ -1406,14 +1606,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		err = -EPERM;
 		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 			pr_err("KVM: CPU requires an RMO\n");
-			goto out;
+			goto out_srcu;
 		}
 
 		/* We can handle 4k, 64k or 16M pages in the VRMA */
 		err = -EINVAL;
 		if (!(psize == 0x1000 || psize == 0x10000 ||
 		      psize == 0x1000000))
-			goto out;
+			goto out_srcu;
 
 		/* Update VRMASD field in the LPCR */
 		senc = slb_pgsize_encoding(psize);
@@ -1436,7 +1636,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		err = -EINVAL;
 		if (rmls < 0) {
 			pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
-			goto out;
+			goto out_srcu;
 		}
 		atomic_inc(&ri->use_count);
 		kvm->arch.rma = ri;
@@ -1465,17 +1665,24 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		/* Initialize phys addrs of pages in RMO */
 		npages = ri->npages;
 		porder = __ilog2(npages);
-		physp = kvm->arch.slot_phys[memslot->id];
-		spin_lock(&kvm->arch.slot_phys_lock);
-		for (i = 0; i < npages; ++i)
-			physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) + porder;
-		spin_unlock(&kvm->arch.slot_phys_lock);
+		physp = memslot->arch.slot_phys;
+		if (physp) {
+			if (npages > memslot->npages)
+				npages = memslot->npages;
+			spin_lock(&kvm->arch.slot_phys_lock);
+			for (i = 0; i < npages; ++i)
+				physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) +
+					porder;
+			spin_unlock(&kvm->arch.slot_phys_lock);
+		}
 	}
 
 	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
 	smp_wmb();
 	kvm->arch.rma_setup_done = 1;
 	err = 0;
+ out_srcu:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
  out:
 	mutex_unlock(&kvm->lock);
 	return err;
@@ -1528,12 +1735,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	unsigned long i;
-
-	if (!kvm->arch.using_mmu_notifiers)
-		for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
-			unpin_slot(kvm, i);
-
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -157,8 +157,8 @@ static void __init kvm_linear_init_one(ulong size, int count, int type)
 	linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
 	for (i = 0; i < count; ++i) {
 		linear = alloc_bootmem_align(size, size);
-		pr_info("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
-			size >> 20);
+		pr_debug("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
+			 size >> 20);
 		linear_info[i].base_virt = linear;
 		linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT;
 		linear_info[i].npages = npages;

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -81,7 +81,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	ptel = rev->guest_rpte |= rcbits;
 	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
 	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
-	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+	if (!memslot)
 		return;
 
 	rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);
@@ -183,7 +183,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	rmap = &memslot->arch.rmap[slot_fn];
 
 	if (!kvm->arch.using_mmu_notifiers) {
-		physp = kvm->arch.slot_phys[memslot->id];
+		physp = memslot->arch.slot_phys;
 		if (!physp)
 			return H_PARAMETER;
 		physp += slot_fn;

arch/powerpc/kvm/book3s_mmu_hpte.c

@@ -114,11 +114,6 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_del_init_rcu(&pte->list_vpte);
 	hlist_del_init_rcu(&pte->list_vpte_long);
 
-	if (pte->pte.may_write)
-		kvm_release_pfn_dirty(pte->pfn);
-	else
-		kvm_release_pfn_clean(pte->pfn);
-
 	spin_unlock(&vcpu3s->mmu_lock);
 
 	vcpu3s->hpte_cache_count--;

arch/powerpc/kvm/book3s_pr.c

@@ -52,8 +52,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #define MSR_USER32 MSR_USER
 #define MSR_USER64 MSR_USER
 #define HW_PAGE_SIZE PAGE_SIZE
-#define __hard_irq_disable local_irq_disable
-#define __hard_irq_enable local_irq_enable
 #endif
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -66,7 +64,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
 	svcpu_put(svcpu);
 #endif
-
+	vcpu->cpu = smp_processor_id();
 #ifdef CONFIG_PPC_BOOK3S_32
 	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
 #endif
@@ -86,8 +84,64 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	kvmppc_giveup_ext(vcpu, MSR_FP);
 	kvmppc_giveup_ext(vcpu, MSR_VEC);
 	kvmppc_giveup_ext(vcpu, MSR_VSX);
+	vcpu->cpu = -1;
+}
+
+int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
+{
+	int r = 1; /* Indicate we want to get back into the guest */
+
+	/* We misuse TLB_FLUSH to indicate that we want to clear
+	   all shadow cache entries */
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
+		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+
+	return r;
+}
+
+/************* MMU Notifiers *************/
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_unmap_hva(hva);
+
+	/*
+	 * Flush all shadow tlb entries everywhere. This is slow, but
+	 * we are 100% sure that we catch the to be unmapped page
+	 */
+	kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	/* kvm_unmap_hva flushes everything anyways */
+	kvm_unmap_hva(kvm, start);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	/* The page will get remapped properly on its next fault */
+	kvm_unmap_hva(kvm, hva);
 }
 
+/*****************************************/
+
 static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 {
 	ulong smsr = vcpu->arch.shared->msr;
@@ -540,18 +594,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
 	int r = RESUME_HOST;
+	int s;
 
 	vcpu->stat.sum_exits++;
 
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 
-	/* We get here with MSR.EE=0, so enable it to be a nice citizen */
-	__hard_irq_enable();
+	/* We get here with MSR.EE=1 */
+
+	trace_kvm_exit(exit_nr, vcpu);
+	kvm_guest_exit();
 
-	trace_kvm_book3s_exit(exit_nr, vcpu);
-	preempt_enable();
-	kvm_resched(vcpu);
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
 	{
@@ -802,7 +856,6 @@ program_interrupt:
 	}
 	}
 
-	preempt_disable();
 	if (!(r & RESUME_HOST)) {
 		/* To avoid clobbering exit_reason, only check for signals if
 		 * we aren't already exiting to userspace for some other
@@ -814,20 +867,13 @@ program_interrupt:
 		 * and if we really did time things so badly, then we just exit
 		 * again due to a host external interrupt.
 		 */
-		__hard_irq_disable();
-		if (signal_pending(current)) {
-			__hard_irq_enable();
-#ifdef EXIT_DEBUG
-			printk(KERN_EMERG "KVM: Going back to host\n");
-#endif
-			vcpu->stat.signal_exits++;
-			run->exit_reason = KVM_EXIT_INTR;
-			r = -EINTR;
+		local_irq_disable();
+		s = kvmppc_prepare_to_enter(vcpu);
+		if (s <= 0) {
+			local_irq_enable();
+			r = s;
 		} else {
-			/* In case an interrupt came in that was triggered
-			 * from userspace (like DEC), we need to check what
-			 * to inject now! */
-			kvmppc_core_prepare_to_enter(vcpu);
+			kvmppc_lazy_ee_enable();
 		}
 	}
 
@@ -899,34 +945,59 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 {
-	int r = -EINVAL;
+	int r = 0;
 
-	switch (reg->id) {
+	switch (id) {
 	case KVM_REG_PPC_HIOR:
-		r = copy_to_user((u64 __user *)(long)reg->addr,
-				&to_book3s(vcpu)->hior, sizeof(u64));
+		*val = get_reg_val(id, to_book3s(vcpu)->hior);
+		break;
+#ifdef CONFIG_VSX
+	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: {
+		long int i = id - KVM_REG_PPC_VSR0;
+
+		if (!cpu_has_feature(CPU_FTR_VSX)) {
+			r = -ENXIO;
+			break;
+		}
+		val->vsxval[0] = vcpu->arch.fpr[i];
+		val->vsxval[1] = vcpu->arch.vsr[i];
 		break;
+	}
+#endif /* CONFIG_VSX */
 	default:
+		r = -EINVAL;
 		break;
 	}
 
 	return r;
 }
 
-int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 {
-	int r = -EINVAL;
+	int r = 0;
 
-	switch (reg->id) {
+	switch (id) {
 	case KVM_REG_PPC_HIOR:
-		r = copy_from_user(&to_book3s(vcpu)->hior,
-				   (u64 __user *)(long)reg->addr, sizeof(u64));
-		if (!r)
-			to_book3s(vcpu)->hior_explicit = true;
+		to_book3s(vcpu)->hior = set_reg_val(id, *val);
+		to_book3s(vcpu)->hior_explicit = true;
+		break;
+#ifdef CONFIG_VSX
+	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: {
+		long int i = id - KVM_REG_PPC_VSR0;
+
+		if (!cpu_has_feature(CPU_FTR_VSX)) {
+			r = -ENXIO;
+			break;
+		}
+		vcpu->arch.fpr[i] = val->vsxval[0];
+		vcpu->arch.vsr[i] = val->vsxval[1];
 		break;
+	}
+#endif /* CONFIG_VSX */
 	default:
+		r = -EINVAL;
 		break;
 	}
 
@@ -1020,8 +1091,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 	ulong ext_msr;
 
-	preempt_disable();
-
 	/* Check if we can run the vcpu at all */
 	if (!vcpu->arch.sane) {
 		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -1029,21 +1098,16 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	kvmppc_core_prepare_to_enter(vcpu);
-
 	/*
 	 * Interrupts could be timers for the guest which we have to inject
 	 * again, so let's postpone them until we're in the guest and if we
 	 * really did time things so badly, then we just exit again due to
 	 * a host external interrupt.
 	 */
-	__hard_irq_disable();
-
-	/* No need to go into the guest when all we do is going out */
-	if (signal_pending(current)) {
-		__hard_irq_enable();
-		kvm_run->exit_reason = KVM_EXIT_INTR;
-		ret = -EINTR;
+	local_irq_disable();
+	ret = kvmppc_prepare_to_enter(vcpu);
+	if (ret <= 0) {
+		local_irq_enable();
 		goto out;
 	}
 
@@ -1080,11 +1144,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
-	kvm_guest_enter();
+	kvmppc_lazy_ee_enable();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
-	kvm_guest_exit();
+	/* No need for kvm_guest_exit. It's done in handle_exit.
+	   We also get here with interrupts enabled. */
 
 	current->thread.regs->msr = ext_msr;
 
@@ -1113,7 +1178,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 
 out:
-	preempt_enable();
+	vcpu->mode = OUTSIDE_GUEST_MODE;
 	return ret;
 }
 
@@ -1181,14 +1246,31 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 }
 #endif /* CONFIG_PPC64 */
 
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	return 0;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot,
 				      struct kvm_userspace_memory_region *mem)
 {
 	return 0;
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old)
+{
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 

arch/powerpc/kvm/book3s_rmhandlers.S

@@ -170,20 +170,21 @@ kvmppc_handler_skip_ins:
  * Call kvmppc_handler_trampoline_enter in real mode
  *
  * On entry, r4 contains the guest shadow MSR
+ * MSR.EE has to be 0 when calling this function
  */
 _GLOBAL(kvmppc_entry_trampoline)
 	mfmsr	r5
 	LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter)
 	toreal(r7)
 
-	li	r9, MSR_RI
-	ori	r9, r9, MSR_EE
-	andc	r9, r5, r9	/* Clear EE and RI in MSR value */
 	li	r6, MSR_IR | MSR_DR
-	ori	r6, r6, MSR_EE
-	andc	r6, r5, r6	/* Clear EE, DR and IR in MSR value */
-	MTMSR_EERI(r9)		/* Clear EE and RI in MSR */
-	mtsrr0	r7		/* before we set srr0/1 */
+	andc	r6, r5, r6	/* Clear DR and IR in MSR value */
+	/*
+	 * Set EE in HOST_MSR so that it's enabled when we get into our
+	 * C exit handler function
+	 */
+	ori	r5, r5, MSR_EE
+	mtsrr0	r7
 	mtsrr1	r6
 	RFI
 

arch/powerpc/kvm/booke.c

@@ -39,6 +39,7 @@
 
 #include "timing.h"
 #include "booke.h"
+#include "trace.h"
 
 unsigned long kvmppc_booke_handlers;
 
@@ -62,6 +63,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "doorbell", VCPU_STAT(dbell_exits) },
 	{ "guest doorbell", VCPU_STAT(gdbell_exits) },
+	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ NULL }
 };
 
@@ -120,6 +122,16 @@ static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu)
 }
 #endif
 
+static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu)
+{
+#if defined(CONFIG_PPC_FPU) && !defined(CONFIG_KVM_BOOKE_HV)
+	/* We always treat the FP bit as enabled from the host
+	   perspective, so only need to adjust the shadow MSR */
+	vcpu->arch.shadow_msr &= ~MSR_FP;
+	vcpu->arch.shadow_msr |= vcpu->arch.shared->msr & MSR_FP;
+#endif
+}
+
 /*
  * Helper function for "full" MSR writes.  No need to call this if only
  * EE/CE/ME/DE/RI are changing.
@@ -136,11 +148,13 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 
 	kvmppc_mmu_msr_notify(vcpu, old_msr);
 	kvmppc_vcpu_sync_spe(vcpu);
+	kvmppc_vcpu_sync_fpu(vcpu);
 }
 
 static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
                                        unsigned int priority)
 {
+	trace_kvm_booke_queue_irqprio(vcpu, priority);
 	set_bit(priority, &vcpu->arch.pending_exceptions);
 }
 
@@ -206,6 +220,16 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
 }
 
+static void kvmppc_core_queue_watchdog(struct kvm_vcpu *vcpu)
+{
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_WATCHDOG);
+}
+
+static void kvmppc_core_dequeue_watchdog(struct kvm_vcpu *vcpu)
+{
+	clear_bit(BOOKE_IRQPRIO_WATCHDOG, &vcpu->arch.pending_exceptions);
+}
+
 static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
 {
 #ifdef CONFIG_KVM_BOOKE_HV
@@ -325,6 +349,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		msr_mask = MSR_CE | MSR_ME | MSR_DE;
 		int_class = INT_CLASS_NONCRIT;
 		break;
+	case BOOKE_IRQPRIO_WATCHDOG:
 	case BOOKE_IRQPRIO_CRITICAL:
 	case BOOKE_IRQPRIO_DBELL_CRIT:
 		allowed = vcpu->arch.shared->msr & MSR_CE;
@@ -404,12 +429,121 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	return allowed;
 }
 
+/*
+ * Return the number of jiffies until the next timeout.  If the timeout is
+ * longer than the NEXT_TIMER_MAX_DELTA, then return NEXT_TIMER_MAX_DELTA
+ * because the larger value can break the timer APIs.
+ */
+static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
+{
+	u64 tb, wdt_tb, wdt_ticks = 0;
+	u64 nr_jiffies = 0;
+	u32 period = TCR_GET_WP(vcpu->arch.tcr);
+
+	wdt_tb = 1ULL << (63 - period);
+	tb = get_tb();
+	/*
+	 * The watchdog timeout will hapeen when TB bit corresponding
+	 * to watchdog will toggle from 0 to 1.
+	 */
+	if (tb & wdt_tb)
+		wdt_ticks = wdt_tb;
+
+	wdt_ticks += wdt_tb - (tb & (wdt_tb - 1));
+
+	/* Convert timebase ticks to jiffies */
+	nr_jiffies = wdt_ticks;
+
+	if (do_div(nr_jiffies, tb_ticks_per_jiffy))
+		nr_jiffies++;
+
+	return min_t(unsigned long long, nr_jiffies, NEXT_TIMER_MAX_DELTA);
+}
+
+static void arm_next_watchdog(struct kvm_vcpu *vcpu)
+{
+	unsigned long nr_jiffies;
+	unsigned long flags;
+
+	/*
+	 * If TSR_ENW and TSR_WIS are not set then no need to exit to
+	 * userspace, so clear the KVM_REQ_WATCHDOG request.
+	 */
+	if ((vcpu->arch.tsr & (TSR_ENW | TSR_WIS)) != (TSR_ENW | TSR_WIS))
+		clear_bit(KVM_REQ_WATCHDOG, &vcpu->requests);
+
+	spin_lock_irqsave(&vcpu->arch.wdt_lock, flags);
+	nr_jiffies = watchdog_next_timeout(vcpu);
+	/*
+	 * If the number of jiffies of watchdog timer >= NEXT_TIMER_MAX_DELTA
+	 * then do not run the watchdog timer as this can break timer APIs.
+	 */
+	if (nr_jiffies < NEXT_TIMER_MAX_DELTA)
+		mod_timer(&vcpu->arch.wdt_timer, jiffies + nr_jiffies);
+	else
+		del_timer(&vcpu->arch.wdt_timer);
+	spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags);
+}
+
+void kvmppc_watchdog_func(unsigned long data)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+	u32 tsr, new_tsr;
+	int final;
+
+	do {
+		new_tsr = tsr = vcpu->arch.tsr;
+		final = 0;
+
+		/* Time out event */
+		if (tsr & TSR_ENW) {
+			if (tsr & TSR_WIS)
+				final = 1;
+			else
+				new_tsr = tsr | TSR_WIS;
+		} else {
+			new_tsr = tsr | TSR_ENW;
+		}
+	} while (cmpxchg(&vcpu->arch.tsr, tsr, new_tsr) != tsr);
+
+	if (new_tsr & TSR_WIS) {
+		smp_wmb();
+		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+		kvm_vcpu_kick(vcpu);
+	}
+
+	/*
+	 * If this is final watchdog expiry and some action is required
+	 * then exit to userspace.
+	 */
+	if (final && (vcpu->arch.tcr & TCR_WRC_MASK) &&
+	    vcpu->arch.watchdog_enabled) {
+		smp_wmb();
+		kvm_make_request(KVM_REQ_WATCHDOG, vcpu);
+		kvm_vcpu_kick(vcpu);
+	}
+
+	/*
+	 * Stop running the watchdog timer after final expiration to
+	 * prevent the host from being flooded with timers if the
+	 * guest sets a short period.
+	 * Timers will resume when TSR/TCR is updated next time.
+	 */
+	if (!final)
+		arm_next_watchdog(vcpu);
+}
+
 static void update_timer_ints(struct kvm_vcpu *vcpu)
 {
 	if ((vcpu->arch.tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS))
 		kvmppc_core_queue_dec(vcpu);
 	else
 		kvmppc_core_dequeue_dec(vcpu);
+
+	if ((vcpu->arch.tcr & TCR_WIE) && (vcpu->arch.tsr & TSR_WIS))
+		kvmppc_core_queue_watchdog(vcpu);
+	else
+		kvmppc_core_dequeue_watchdog(vcpu);
 }
 
 static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
@@ -417,13 +551,6 @@ static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
 	unsigned int priority;
 
-	if (vcpu->requests) {
-		if (kvm_check_request(KVM_REQ_PENDING_TIMER, vcpu)) {
-			smp_mb();
-			update_timer_ints(vcpu);
-		}
-	}
-
 	priority = __ffs(*pending);
 	while (priority < BOOKE_IRQPRIO_MAX) {
 		if (kvmppc_booke_irqprio_deliver(vcpu, priority))
@@ -459,37 +586,20 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 	return r;
 }
 
-/*
- * Common checks before entering the guest world.  Call with interrupts
- * disabled.
- *
- * returns !0 if a signal is pending and check_signal is true
- */
-static int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
+int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 {
-	int r = 0;
-
-	WARN_ON_ONCE(!irqs_disabled());
-	while (true) {
-		if (need_resched()) {
-			local_irq_enable();
-			cond_resched();
-			local_irq_disable();
-			continue;
-		}
-
-		if (signal_pending(current)) {
-			r = 1;
-			break;
-		}
+	int r = 1; /* Indicate we want to get back into the guest */
 
-		if (kvmppc_core_prepare_to_enter(vcpu)) {
-			/* interrupts got enabled in between, so we
-			   are back at square 1 */
-			continue;
-		}
+	if (kvm_check_request(KVM_REQ_PENDING_TIMER, vcpu))
+		update_timer_ints(vcpu);
+#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
+		kvmppc_core_flush_tlb(vcpu);
+#endif
 
-		break;
+	if (kvm_check_request(KVM_REQ_WATCHDOG, vcpu)) {
+		vcpu->run->exit_reason = KVM_EXIT_WATCHDOG;
+		r = 0;
 	}
 
 	return r;
@@ -497,7 +607,7 @@ static int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
-	int ret;
+	int ret, s;
 #ifdef CONFIG_PPC_FPU
 	unsigned int fpscr;
 	int fpexc_mode;
@@ -510,11 +620,13 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	}
 
 	local_irq_disable();
-	if (kvmppc_prepare_to_enter(vcpu)) {
-		kvm_run->exit_reason = KVM_EXIT_INTR;
-		ret = -EINTR;
+	s = kvmppc_prepare_to_enter(vcpu);
+	if (s <= 0) {
+		local_irq_enable();
+		ret = s;
 		goto out;
 	}
+	kvmppc_lazy_ee_enable();
 
 	kvm_guest_enter();
 
@@ -542,6 +654,9 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
+	/* No need for kvm_guest_exit. It's done in handle_exit.
+	   We also get here with interrupts enabled. */
+
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);
 
@@ -557,10 +672,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	current->thread.fpexc_mode = fpexc_mode;
 #endif
 
-	kvm_guest_exit();
-
 out:
-	local_irq_enable();
+	vcpu->mode = OUTSIDE_GUEST_MODE;
 	return ret;
 }
 
@@ -668,6 +781,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
 	int r = RESUME_HOST;
+	int s;
 
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
@@ -677,6 +791,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	local_irq_enable();
 
+	trace_kvm_exit(exit_nr, vcpu);
+	kvm_guest_exit();
+
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 
@@ -971,10 +1088,12 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	if (!(r & RESUME_HOST)) {
 		local_irq_disable();
-		if (kvmppc_prepare_to_enter(vcpu)) {
-			run->exit_reason = KVM_EXIT_INTR;
-			r = (-EINTR << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
-			kvmppc_account_exit(vcpu, SIGNAL_EXITS);
+		s = kvmppc_prepare_to_enter(vcpu);
+		if (s <= 0) {
+			local_irq_enable();
+			r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
+		} else {
+			kvmppc_lazy_ee_enable();
 		}
 	}
 
@@ -1011,6 +1130,21 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	/* setup watchdog timer once */
+	spin_lock_init(&vcpu->arch.wdt_lock);
+	setup_timer(&vcpu->arch.wdt_timer, kvmppc_watchdog_func,
+		    (unsigned long)vcpu);
+
+	return 0;
+}
+
+void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+	del_timer_sync(&vcpu->arch.wdt_timer);
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
@@ -1106,7 +1240,13 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
 	}
 
 	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
+		u32 old_tsr = vcpu->arch.tsr;
+
 		vcpu->arch.tsr = sregs->u.e.tsr;
+
+		if ((old_tsr ^ vcpu->arch.tsr) & (TSR_ENW | TSR_WIS))
+			arm_next_watchdog(vcpu);
+
 		update_timer_ints(vcpu);
 	}
 
@@ -1221,12 +1361,56 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 {
-	return -EINVAL;
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_IAC1:
+	case KVM_REG_PPC_IAC2:
+	case KVM_REG_PPC_IAC3:
+	case KVM_REG_PPC_IAC4: {
+		int iac = reg->id - KVM_REG_PPC_IAC1;
+		r = copy_to_user((u64 __user *)(long)reg->addr,
+				 &vcpu->arch.dbg_reg.iac[iac], sizeof(u64));
+		break;
+	}
+	case KVM_REG_PPC_DAC1:
+	case KVM_REG_PPC_DAC2: {
+		int dac = reg->id - KVM_REG_PPC_DAC1;
+		r = copy_to_user((u64 __user *)(long)reg->addr,
+				 &vcpu->arch.dbg_reg.dac[dac], sizeof(u64));
+		break;
+	}
+	default:
+		break;
+	}
+	return r;
 }
 
 int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 {
-	return -EINVAL;
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_IAC1:
+	case KVM_REG_PPC_IAC2:
+	case KVM_REG_PPC_IAC3:
+	case KVM_REG_PPC_IAC4: {
+		int iac = reg->id - KVM_REG_PPC_IAC1;
+		r = copy_from_user(&vcpu->arch.dbg_reg.iac[iac],
+			     (u64 __user *)(long)reg->addr, sizeof(u64));
+		break;
+	}
+	case KVM_REG_PPC_DAC1:
+	case KVM_REG_PPC_DAC2: {
+		int dac = reg->id - KVM_REG_PPC_DAC1;
+		r = copy_from_user(&vcpu->arch.dbg_reg.dac[dac],
+			     (u64 __user *)(long)reg->addr, sizeof(u64));
+		break;
+	}
+	default:
+		break;
+	}
+	return r;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
@@ -1253,20 +1437,38 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return -ENOTSUPP;
 }
 
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	return 0;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot,
 				      struct kvm_userspace_memory_region *mem)
 {
 	return 0;
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old)
+{
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
 {
 	vcpu->arch.tcr = new_tcr;
+	arm_next_watchdog(vcpu);
 	update_timer_ints(vcpu);
 }
 
@@ -1281,6 +1483,14 @@ void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 {
 	clear_bits(tsr_bits, &vcpu->arch.tsr);
+
+	/*
+	 * We may have stopped the watchdog due to
+	 * being stuck on final expiration.
+	 */
+	if (tsr_bits & (TSR_ENW | TSR_WIS))
+		arm_next_watchdog(vcpu);
+
 	update_timer_ints(vcpu);
 }
 
@@ -1298,12 +1508,14 @@ void kvmppc_decrementer_func(unsigned long data)
 
 void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	vcpu->cpu = smp_processor_id();
 	current->thread.kvm_vcpu = vcpu;
 }
 
 void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	current->thread.kvm_vcpu = NULL;
+	vcpu->cpu = -1;
 }
 
 int __init kvmppc_booke_init(void)

arch/powerpc/kvm/booke_emulate.c

@@ -133,10 +133,10 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		vcpu->arch.csrr1 = spr_val;
 		break;
 	case SPRN_DBCR0:
-		vcpu->arch.dbcr0 = spr_val;
+		vcpu->arch.dbg_reg.dbcr0 = spr_val;
 		break;
 	case SPRN_DBCR1:
-		vcpu->arch.dbcr1 = spr_val;
+		vcpu->arch.dbg_reg.dbcr1 = spr_val;
 		break;
 	case SPRN_DBSR:
 		vcpu->arch.dbsr &= ~spr_val;
@@ -145,6 +145,14 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		kvmppc_clr_tsr_bits(vcpu, spr_val);
 		break;
 	case SPRN_TCR:
+		/*
+		 * WRC is a 2-bit field that is supposed to preserve its
+		 * value once written to non-zero.
+		 */
+		if (vcpu->arch.tcr & TCR_WRC_MASK) {
+			spr_val &= ~TCR_WRC_MASK;
+			spr_val |= vcpu->arch.tcr & TCR_WRC_MASK;
+		}
 		kvmppc_set_tcr(vcpu, spr_val);
 		break;
 
@@ -229,6 +237,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_IVOR15:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = spr_val;
 		break;
+	case SPRN_MCSR:
+		vcpu->arch.mcsr &= ~spr_val;
+		break;
 
 	default:
 		emulated = EMULATE_FAIL;
@@ -258,10 +269,10 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 		*spr_val = vcpu->arch.csrr1;
 		break;
 	case SPRN_DBCR0:
-		*spr_val = vcpu->arch.dbcr0;
+		*spr_val = vcpu->arch.dbg_reg.dbcr0;
 		break;
 	case SPRN_DBCR1:
-		*spr_val = vcpu->arch.dbcr1;
+		*spr_val = vcpu->arch.dbg_reg.dbcr1;
 		break;
 	case SPRN_DBSR:
 		*spr_val = vcpu->arch.dbsr;
@@ -321,6 +332,9 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_IVOR15:
 		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
 		break;
+	case SPRN_MCSR:
+		*spr_val = vcpu->arch.mcsr;
+		break;
 
 	default:
 		emulated = EMULATE_FAIL;

arch/powerpc/kvm/e500.h

@@ -27,8 +27,7 @@
 #define E500_TLB_NUM   2
 
 #define E500_TLB_VALID 1
-#define E500_TLB_DIRTY 2
-#define E500_TLB_BITMAP 4
+#define E500_TLB_BITMAP 2
 
 struct tlbe_ref {
 	pfn_t pfn;

arch/powerpc/kvm/e500_tlb.c

@@ -304,17 +304,13 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 	ref->flags = E500_TLB_VALID;
 
 	if (tlbe_is_writable(gtlbe))
-		ref->flags |= E500_TLB_DIRTY;
+		kvm_set_pfn_dirty(pfn);
 }
 
 static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
 	if (ref->flags & E500_TLB_VALID) {
-		if (ref->flags & E500_TLB_DIRTY)
-			kvm_release_pfn_dirty(ref->pfn);
-		else
-			kvm_release_pfn_clean(ref->pfn);
-
+		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
 		ref->flags = 0;
 	}
 }
@@ -357,6 +353,13 @@ static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
 	clear_tlb_privs(vcpu_e500);
 }
 
+void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	clear_tlb_refs(vcpu_e500);
+	clear_tlb1_bitmap(vcpu_e500);
+}
+
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		unsigned int eaddr, int as)
 {
@@ -541,6 +544,9 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	/* Clear i-cache for new pages */
 	kvmppc_mmu_flush_icache(pfn);
+
+	/* Drop refcount on page, so that mmu notifiers can clear it */
+	kvm_release_pfn_clean(pfn);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -1039,8 +1045,12 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 		sesel = 0; /* unused */
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
-		kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
-					&priv->ref, eaddr, &stlbe);
+		/* Only triggers after clear_tlb_refs */
+		if (unlikely(!(priv->ref.flags & E500_TLB_VALID)))
+			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+		else
+			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
+						&priv->ref, eaddr, &stlbe);
 		break;
 
 	case 1: {
@@ -1060,6 +1070,49 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 }
 
+/************* MMU Notifiers *************/
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_unmap_hva(hva);
+
+	/*
+	 * Flush all shadow tlb entries everywhere. This is slow, but
+	 * we are 100% sure that we catch the to be unmapped page
+	 */
+	kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	/* kvm_unmap_hva flushes everything anyways */
+	kvm_unmap_hva(kvm, start);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	/* The page will get remapped properly on its next fault */
+	kvm_unmap_hva(kvm, hva);
+}
+
+/*****************************************/
+
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int i;
@@ -1081,6 +1134,8 @@ static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 		}
 
 		vcpu_e500->num_shared_tlb_pages = 0;
+
+		kfree(vcpu_e500->shared_tlb_pages);
 		vcpu_e500->shared_tlb_pages = NULL;
 	} else {
 		kfree(vcpu_e500->gtlb_arch);
@@ -1178,21 +1233,27 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	}
 
 	virt = vmap(pages, num_pages, VM_MAP, PAGE_KERNEL);
-	if (!virt)
+	if (!virt) {
+		ret = -ENOMEM;
 		goto err_put_page;
+	}
 
 	privs[0] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[0],
 			   GFP_KERNEL);
 	privs[1] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[1],
 			   GFP_KERNEL);
 
-	if (!privs[0] || !privs[1])
-		goto err_put_page;
+	if (!privs[0] || !privs[1]) {
+		ret = -ENOMEM;
+		goto err_privs;
+	}
 
 	g2h_bitmap = kzalloc(sizeof(u64) * params.tlb_sizes[1],
 	                     GFP_KERNEL);
-	if (!g2h_bitmap)
-		goto err_put_page;
+	if (!g2h_bitmap) {
+		ret = -ENOMEM;
+		goto err_privs;
+	}
 
 	free_gtlb(vcpu_e500);
 
@@ -1232,10 +1293,11 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	return 0;
 
-err_put_page:
+err_privs:
 	kfree(privs[0]);
 	kfree(privs[1]);
 
+err_put_page:
 	for (i = 0; i < num_pages; i++)
 		put_page(pages[i]);
 
@@ -1332,7 +1394,7 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (!vcpu_e500->gtlb_priv[1])
 		goto err;
 
-	vcpu_e500->g2h_tlb1_map = kzalloc(sizeof(unsigned int) *
+	vcpu_e500->g2h_tlb1_map = kzalloc(sizeof(u64) *
 					  vcpu_e500->gtlb_params[1].entries,
 					  GFP_KERNEL);
 	if (!vcpu_e500->g2h_tlb1_map)

arch/powerpc/kvm/powerpc.c

@@ -30,6 +30,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/tlbflush.h>
 #include <asm/cputhreads.h>
+#include <asm/irqflags.h>
 #include "timing.h"
 #include "../mm/mmu_decl.h"
 
@@ -38,8 +39,7 @@
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !(v->arch.shared->msr & MSR_WE) ||
-	       !!(v->arch.pending_exceptions) ||
+	return !!(v->arch.pending_exceptions) ||
 	       v->requests;
 }
 
@@ -48,6 +48,85 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+#ifndef CONFIG_KVM_BOOK3S_64_HV
+/*
+ * Common checks before entering the guest world.  Call with interrupts
+ * disabled.
+ *
+ * returns:
+ *
+ * == 1 if we're ready to go into guest state
+ * <= 0 if we need to go back to the host with return value
+ */
+int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
+{
+	int r = 1;
+
+	WARN_ON_ONCE(!irqs_disabled());
+	while (true) {
+		if (need_resched()) {
+			local_irq_enable();
+			cond_resched();
+			local_irq_disable();
+			continue;
+		}
+
+		if (signal_pending(current)) {
+			kvmppc_account_exit(vcpu, SIGNAL_EXITS);
+			vcpu->run->exit_reason = KVM_EXIT_INTR;
+			r = -EINTR;
+			break;
+		}
+
+		vcpu->mode = IN_GUEST_MODE;
+
+		/*
+		 * Reading vcpu->requests must happen after setting vcpu->mode,
+		 * so we don't miss a request because the requester sees
+		 * OUTSIDE_GUEST_MODE and assumes we'll be checking requests
+		 * before next entering the guest (and thus doesn't IPI).
+		 */
+		smp_mb();
+
+		if (vcpu->requests) {
+			/* Make sure we process requests preemptable */
+			local_irq_enable();
+			trace_kvm_check_requests(vcpu);
+			r = kvmppc_core_check_requests(vcpu);
+			local_irq_disable();
+			if (r > 0)
+				continue;
+			break;
+		}
+
+		if (kvmppc_core_prepare_to_enter(vcpu)) {
+			/* interrupts got enabled in between, so we
+			   are back at square 1 */
+			continue;
+		}
+
+#ifdef CONFIG_PPC64
+		/* lazy EE magic */
+		hard_irq_disable();
+		if (lazy_irq_pending()) {
+			/* Got an interrupt in between, try again */
+			local_irq_enable();
+			local_irq_disable();
+			kvm_guest_exit();
+			continue;
+		}
+
+		trace_hardirqs_on();
+#endif
+
+		kvm_guest_enter();
+		break;
+	}
+
+	return r;
+}
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
+
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 {
 	int nr = kvmppc_get_gpr(vcpu, 11);
@@ -67,18 +146,18 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 	}
 
 	switch (nr) {
-	case HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE:
+	case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
 	{
 		vcpu->arch.magic_page_pa = param1;
 		vcpu->arch.magic_page_ea = param2;
 
 		r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
 
-		r = HC_EV_SUCCESS;
+		r = EV_SUCCESS;
 		break;
 	}
-	case HC_VENDOR_KVM | KVM_HC_FEATURES:
-		r = HC_EV_SUCCESS;
+	case KVM_HCALL_TOKEN(KVM_HC_FEATURES):
+		r = EV_SUCCESS;
 #if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
 		/* XXX Missing magic page on 44x */
 		r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
@@ -86,8 +165,13 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 
 		/* Second return value is in r4 */
 		break;
+	case EV_HCALL_TOKEN(EV_IDLE):
+		r = EV_SUCCESS;
+		kvm_vcpu_block(vcpu);
+		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+		break;
 	default:
-		r = HC_EV_UNIMPLEMENTED;
+		r = EV_UNIMPLEMENTED;
 		break;
 	}
 
@@ -220,6 +304,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	switch (ext) {
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_SREGS:
+	case KVM_CAP_PPC_BOOKE_WATCHDOG:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
 	case KVM_CAP_PPC_HIOR:
@@ -260,10 +345,16 @@ int kvm_dev_ioctl_check_extension(long ext)
 		if (cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
 		break;
+#endif
 	case KVM_CAP_SYNC_MMU:
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 		r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
-		break;
+#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+		r = 1;
+#else
+		r = 0;
 #endif
+		break;
 	case KVM_CAP_NR_VCPUS:
 		/*
 		 * Recommending a number of CPUs is somewhat arbitrary; we
@@ -302,19 +393,12 @@ long kvm_arch_dev_ioctl(struct file *filp,
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
-	if (!dont || free->arch.rmap != dont->arch.rmap) {
-		vfree(free->arch.rmap);
-		free->arch.rmap = NULL;
-	}
+	kvmppc_core_free_memslot(free, dont);
 }
 
 int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 {
-	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
-	if (!slot->arch.rmap)
-		return -ENOMEM;
-
-	return 0;
+	return kvmppc_core_create_memslot(slot, npages);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -323,7 +407,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_userspace_memory_region *mem,
                                    int user_alloc)
 {
-	return kvmppc_core_prepare_memory_region(kvm, mem);
+	return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
@@ -331,7 +415,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
                struct kvm_memory_slot old,
                int user_alloc)
 {
-	kvmppc_core_commit_memory_region(kvm, mem);
+	kvmppc_core_commit_memory_region(kvm, mem, old);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -341,6 +425,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	kvmppc_core_flush_memslot(kvm, slot);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
@@ -390,6 +475,8 @@ enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	int ret;
+
 	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
 	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
@@ -398,13 +485,14 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);
 #endif
-
-	return 0;
+	ret = kvmppc_subarch_vcpu_init(vcpu);
+	return ret;
 }
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_destroy(vcpu);
+	kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -420,7 +508,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
 #endif
 	kvmppc_core_vcpu_load(vcpu, cpu);
-	vcpu->cpu = smp_processor_id();
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -429,7 +516,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_BOOKE
 	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
 #endif
-	vcpu->cpu = -1;
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
@@ -649,6 +735,12 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+#ifdef CONFIG_BOOKE
+	case KVM_CAP_PPC_BOOKE_WATCHDOG:
+		r = 0;
+		vcpu->arch.watchdog_enabled = true;
+		break;
+#endif
 #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_CAP_SW_TLB: {
 		struct kvm_config_tlb cfg;
@@ -751,9 +843,16 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 
 static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
 {
+	u32 inst_nop = 0x60000000;
+#ifdef CONFIG_KVM_BOOKE_HV
+	u32 inst_sc1 = 0x44000022;
+	pvinfo->hcall[0] = inst_sc1;
+	pvinfo->hcall[1] = inst_nop;
+	pvinfo->hcall[2] = inst_nop;
+	pvinfo->hcall[3] = inst_nop;
+#else
 	u32 inst_lis = 0x3c000000;
 	u32 inst_ori = 0x60000000;
-	u32 inst_nop = 0x60000000;
 	u32 inst_sc = 0x44000002;
 	u32 inst_imm_mask = 0xffff;
 
@@ -770,6 +869,9 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
 	pvinfo->hcall[1] = inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask);
 	pvinfo->hcall[2] = inst_sc;
 	pvinfo->hcall[3] = inst_nop;
+#endif
+
+	pvinfo->flags = KVM_PPC_PVINFO_FLAGS_EV_IDLE;
 
 	return 0;
 }

arch/powerpc/kvm/trace.h

@@ -31,6 +31,126 @@ TRACE_EVENT(kvm_ppc_instr,
 		  __entry->inst, __entry->pc, __entry->emulate)
 );
 
+#ifdef CONFIG_PPC_BOOK3S
+#define kvm_trace_symbol_exit \
+	{0x100, "SYSTEM_RESET"}, \
+	{0x200, "MACHINE_CHECK"}, \
+	{0x300, "DATA_STORAGE"}, \
+	{0x380, "DATA_SEGMENT"}, \
+	{0x400, "INST_STORAGE"}, \
+	{0x480, "INST_SEGMENT"}, \
+	{0x500, "EXTERNAL"}, \
+	{0x501, "EXTERNAL_LEVEL"}, \
+	{0x502, "EXTERNAL_HV"}, \
+	{0x600, "ALIGNMENT"}, \
+	{0x700, "PROGRAM"}, \
+	{0x800, "FP_UNAVAIL"}, \
+	{0x900, "DECREMENTER"}, \
+	{0x980, "HV_DECREMENTER"}, \
+	{0xc00, "SYSCALL"}, \
+	{0xd00, "TRACE"}, \
+	{0xe00, "H_DATA_STORAGE"}, \
+	{0xe20, "H_INST_STORAGE"}, \
+	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xf00, "PERFMON"}, \
+	{0xf20, "ALTIVEC"}, \
+	{0xf40, "VSX"}
+#else
+#define kvm_trace_symbol_exit \
+	{0, "CRITICAL"}, \
+	{1, "MACHINE_CHECK"}, \
+	{2, "DATA_STORAGE"}, \
+	{3, "INST_STORAGE"}, \
+	{4, "EXTERNAL"}, \
+	{5, "ALIGNMENT"}, \
+	{6, "PROGRAM"}, \
+	{7, "FP_UNAVAIL"}, \
+	{8, "SYSCALL"}, \
+	{9, "AP_UNAVAIL"}, \
+	{10, "DECREMENTER"}, \
+	{11, "FIT"}, \
+	{12, "WATCHDOG"}, \
+	{13, "DTLB_MISS"}, \
+	{14, "ITLB_MISS"}, \
+	{15, "DEBUG"}, \
+	{32, "SPE_UNAVAIL"}, \
+	{33, "SPE_FP_DATA"}, \
+	{34, "SPE_FP_ROUND"}, \
+	{35, "PERFORMANCE_MONITOR"}, \
+	{36, "DOORBELL"}, \
+	{37, "DOORBELL_CRITICAL"}, \
+	{38, "GUEST_DBELL"}, \
+	{39, "GUEST_DBELL_CRIT"}, \
+	{40, "HV_SYSCALL"}, \
+	{41, "HV_PRIV"}
+#endif
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_nr, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_nr		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned long,	msr		)
+		__field(	unsigned long,	dar		)
+#ifdef CONFIG_KVM_BOOK3S_PR
+		__field(	unsigned long,	srr1		)
+#endif
+		__field(	unsigned long,	last_inst	)
+	),
+
+	TP_fast_assign(
+#ifdef CONFIG_KVM_BOOK3S_PR
+		struct kvmppc_book3s_shadow_vcpu *svcpu;
+#endif
+		__entry->exit_nr	= exit_nr;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+		__entry->dar		= kvmppc_get_fault_dar(vcpu);
+		__entry->msr		= vcpu->arch.shared->msr;
+#ifdef CONFIG_KVM_BOOK3S_PR
+		svcpu = svcpu_get(vcpu);
+		__entry->srr1		= svcpu->shadow_srr1;
+		svcpu_put(svcpu);
+#endif
+		__entry->last_inst	= vcpu->arch.last_inst;
+	),
+
+	TP_printk("exit=%s"
+		" | pc=0x%lx"
+		" | msr=0x%lx"
+		" | dar=0x%lx"
+#ifdef CONFIG_KVM_BOOK3S_PR
+		" | srr1=0x%lx"
+#endif
+		" | last_inst=0x%lx"
+		,
+		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
+		__entry->pc,
+		__entry->msr,
+		__entry->dar,
+#ifdef CONFIG_KVM_BOOK3S_PR
+		__entry->srr1,
+#endif
+		__entry->last_inst
+		)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("unmap hva 0x%lx\n", __entry->hva)
+);
+
 TRACE_EVENT(kvm_stlb_inval,
 	TP_PROTO(unsigned int stlb_index),
 	TP_ARGS(stlb_index),
@@ -98,41 +218,31 @@ TRACE_EVENT(kvm_gtlb_write,
 		__entry->word1, __entry->word2)
 );
 
-
-/*************************************************************************
- *                         Book3S trace points                           *
- *************************************************************************/
-
-#ifdef CONFIG_KVM_BOOK3S_PR
-
-TRACE_EVENT(kvm_book3s_exit,
-	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
-	TP_ARGS(exit_nr, vcpu),
+TRACE_EVENT(kvm_check_requests,
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
 
 	TP_STRUCT__entry(
-		__field(	unsigned int,	exit_nr		)
-		__field(	unsigned long,	pc		)
-		__field(	unsigned long,	msr		)
-		__field(	unsigned long,	dar		)
-		__field(	unsigned long,	srr1		)
+		__field(	__u32,	cpu_nr		)
+		__field(	__u32,	requests	)
 	),
 
 	TP_fast_assign(
-		struct kvmppc_book3s_shadow_vcpu *svcpu;
-		__entry->exit_nr	= exit_nr;
-		__entry->pc		= kvmppc_get_pc(vcpu);
-		__entry->dar		= kvmppc_get_fault_dar(vcpu);
-		__entry->msr		= vcpu->arch.shared->msr;
-		svcpu = svcpu_get(vcpu);
-		__entry->srr1		= svcpu->shadow_srr1;
-		svcpu_put(svcpu);
+		__entry->cpu_nr		= vcpu->vcpu_id;
+		__entry->requests	= vcpu->requests;
 	),
 
-	TP_printk("exit=0x%x | pc=0x%lx | msr=0x%lx | dar=0x%lx | srr1=0x%lx",
-		  __entry->exit_nr, __entry->pc, __entry->msr, __entry->dar,
-		  __entry->srr1)
+	TP_printk("vcpu=%x requests=%x",
+		__entry->cpu_nr, __entry->requests)
 );
 
+
+/*************************************************************************
+ *                         Book3S trace points                           *
+ *************************************************************************/
+
+#ifdef CONFIG_KVM_BOOK3S_PR
+
 TRACE_EVENT(kvm_book3s_reenter,
 	TP_PROTO(int r, struct kvm_vcpu *vcpu),
 	TP_ARGS(r, vcpu),
@@ -395,6 +505,44 @@ TRACE_EVENT(kvm_booke206_gtlb_write,
 		__entry->mas2, __entry->mas7_3)
 );
 
+TRACE_EVENT(kvm_booke206_ref_release,
+	TP_PROTO(__u64 pfn, __u32 flags),
+	TP_ARGS(pfn, flags),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	pfn		)
+		__field(	__u32,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->pfn		= pfn;
+		__entry->flags		= flags;
+	),
+
+	TP_printk("pfn=%llx flags=%x",
+		__entry->pfn, __entry->flags)
+);
+
+TRACE_EVENT(kvm_booke_queue_irqprio,
+	TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority),
+	TP_ARGS(vcpu, priority),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	cpu_nr		)
+		__field(	__u32,	priority		)
+		__field(	unsigned long,	pending		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu_nr		= vcpu->vcpu_id;
+		__entry->priority	= priority;
+		__entry->pending	= vcpu->arch.pending_exceptions;
+	),
+
+	TP_printk("vcpu=%x prio=%x pending=%lx",
+		__entry->cpu_nr, __entry->priority, __entry->pending)
+);
+
 #endif
 
 #endif /* _TRACE_KVM_H */

arch/powerpc/platforms/Kconfig

@@ -90,6 +90,7 @@ config MPIC
 config PPC_EPAPR_HV_PIC
 	bool
 	default n
+	select EPAPR_PARAVIRT
 
 config MPIC_WEIRD
 	bool

arch/powerpc/sysdev/fsl_msi.c

@@ -236,7 +236,6 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
 	u32 intr_index;
 	u32 have_shift = 0;
 	struct fsl_msi_cascade_data *cascade_data;
-	unsigned int ret;
 
 	cascade_data = irq_get_handler_data(irq);
 	msi_data = cascade_data->msi_data;
@@ -268,7 +267,9 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
 	case FSL_PIC_IP_IPIC:
 		msir_value = fsl_msi_read(msi_data->msi_regs, msir_index * 0x4);
 		break;
-	case FSL_PIC_IP_VMPIC:
+#ifdef CONFIG_EPAPR_PARAVIRT
+	case FSL_PIC_IP_VMPIC: {
+		unsigned int ret;
 		ret = fh_vmpic_get_msir(virq_to_hw(irq), &msir_value);
 		if (ret) {
 			pr_err("fsl-msi: fh_vmpic_get_msir() failed for "
@@ -277,6 +278,8 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
 		}
 		break;
 	}
+#endif
+	}
 
 	while (msir_value) {
 		intr_index = ffs(msir_value) - 1;
@@ -508,10 +511,12 @@ static const struct of_device_id fsl_of_msi_ids[] = {
 		.compatible = "fsl,ipic-msi",
 		.data = &ipic_msi_feature,
 	},
+#ifdef CONFIG_EPAPR_PARAVIRT
 	{
 		.compatible = "fsl,vmpic-msi",
 		.data = &vmpic_msi_feature,
 	},
+#endif
 	{}
 };
 

arch/powerpc/sysdev/fsl_soc.c

@@ -253,6 +253,7 @@ struct platform_diu_data_ops diu_ops;
 EXPORT_SYMBOL(diu_ops);
 #endif
 
+#ifdef CONFIG_EPAPR_PARAVIRT
 /*
  * Restart the current partition
  *
@@ -278,3 +279,4 @@ void fsl_hv_halt(void)
 	pr_info("hv exit\n");
 	fh_partition_stop(-1);
 }
+#endif

drivers/tty/Kconfig

@@ -357,6 +357,7 @@ config TRACE_SINK
 config PPC_EPAPR_HV_BYTECHAN
 	tristate "ePAPR hypervisor byte channel driver"
 	depends on PPC
+	select EPAPR_PARAVIRT
 	help
 	  This driver creates /dev entries for each ePAPR hypervisor byte
 	  channel, thereby allowing applications to communicate with byte

drivers/virt/Kconfig

@@ -15,6 +15,7 @@ if VIRT_DRIVERS
 config FSL_HV_MANAGER
 	tristate "Freescale hypervisor management driver"
 	depends on FSL_SOC
+	select EPAPR_PARAVIRT
 	help
           The Freescale hypervisor management driver provides several services
 	  to drivers and applications related to the Freescale hypervisor:

include/linux/kvm.h

@@ -167,6 +167,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL	  19
 #define KVM_EXIT_S390_UCONTROL	  20
+#define KVM_EXIT_WATCHDOG         21
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -477,6 +478,8 @@ struct kvm_ppc_smmu_info {
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -626,6 +629,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_READONLY_MEM 81
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
+#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -848,6 +852,9 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_SMMU_INFO	  _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
 /* Available with KVM_CAP_PPC_ALLOC_HTAB */
 #define KVM_PPC_ALLOCATE_HTAB	  _IOWR(KVMIO, 0xa7, __u32)
+#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
+/* Available with KVM_CAP_RMA */
+#define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
 
 /*
  * ioctls for vcpu fds
@@ -911,9 +918,6 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_XCRS */
 #define KVM_GET_XCRS		  _IOR(KVMIO,  0xa6, struct kvm_xcrs)
 #define KVM_SET_XCRS		  _IOW(KVMIO,  0xa7, struct kvm_xcrs)
-#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
-/* Available with KVM_CAP_RMA */
-#define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
 /* Available with KVM_CAP_SW_TLB */
 #define KVM_DIRTY_TLB		  _IOW(KVMIO,  0xaa, struct kvm_dirty_tlb)
 /* Available with KVM_CAP_ONE_REG */

include/linux/kvm_host.h

@@ -118,6 +118,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_IMMEDIATE_EXIT    15
 #define KVM_REQ_PMU               16
 #define KVM_REQ_PMI               17
+#define KVM_REQ_WATCHDOG          18
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1