Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Marcelo Tosatti:
 "Considerable KVM/PPC work, x86 kvmclock vsyscall support,
  IA32_TSC_ADJUST MSR emulation, amongst others."

Fix up trivial conflict in kernel/sched/core.c due to cross-cpu
migration notifier added next to rq migration call-back.

* tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (156 commits)
  KVM: emulator: fix real mode segment checks in address linearization
  VMX: remove unneeded enable_unrestricted_guest check
  KVM: VMX: fix DPL during entry to protected mode
  x86/kexec: crash_vmclear_local_vmcss needs __rcu
  kvm: Fix irqfd resampler list walk
  KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump
  x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary
  KVM: MMU: optimize for set_spte
  KVM: PPC: booke: Get/set guest EPCR register using ONE_REG interface
  KVM: PPC: bookehv: Add EPCR support in mtspr/mfspr emulation
  KVM: PPC: bookehv: Add guest computation mode for irq delivery
  KVM: PPC: Make EPCR a valid field for booke64 and bookehv
  KVM: PPC: booke: Extend MAS2 EPN mask for 64-bit
  KVM: PPC: e500: Mask MAS2 EPN high 32-bits in 32/64 tlbwe emulation
  KVM: PPC: Mask ea's high 32-bits in 32/64 instr emulation
  KVM: PPC: e500: Add emulation helper for getting instruction ea
  KVM: PPC: bookehv64: Add support for interrupt handling
  KVM: PPC: bookehv: Remove GET_VCPU macro from exception handler
  KVM: PPC: booke: Fix get_tb() compile error on 64-bit
  KVM: PPC: e500: Silence bogus GCC warning in tlb code
  ...

56 files changed, 3287 insertions, 850 deletions

diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 2d62b484b3f..650757c300d 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,5 +1,4 @@
 
-
 generic-y += clkdev.h
 generic-y += rwsem.h
 generic-y += trace_clock.h
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index bf2c06c3387..d3d634274d2 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -50,64 +50,13 @@
 #ifndef _EPAPR_HCALLS_H
 #define _EPAPR_HCALLS_H
 
+#include <uapi/asm/epapr_hcalls.h>
+
+#ifndef __ASSEMBLY__
 #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
-#define EV_INT_SET_CONFIG		4
-#define EV_INT_GET_CONFIG		5
-#define EV_INT_SET_MASK			6
-#define EV_INT_GET_MASK			7
-#define EV_INT_IACK			9
-#define EV_INT_EOI			10
-#define EV_INT_SEND_IPI			11
-#define EV_INT_SET_TASK_PRIORITY	12
-#define EV_INT_GET_TASK_PRIORITY	13
-#define EV_DOORBELL_SEND		14
-#define EV_MSGSND			15
-#define EV_IDLE				16
-
-/* vendor ID: epapr */
-#define EV_LOCAL_VENDOR_ID		0	/* for private use */
-#define EV_EPAPR_VENDOR_ID		1
-#define EV_FSL_VENDOR_ID		2	/* Freescale Semiconductor */
-#define EV_IBM_VENDOR_ID		3	/* IBM */
-#define EV_GHS_VENDOR_ID		4	/* Green Hills Software */
-#define EV_ENEA_VENDOR_ID		5	/* Enea */
-#define EV_WR_VENDOR_ID			6	/* Wind River Systems */
-#define EV_AMCC_VENDOR_ID		7	/* Applied Micro Circuits */
-#define EV_KVM_VENDOR_ID		42	/* KVM */
-
-/* The max number of bytes that a byte channel can send or receive per call */
-#define EV_BYTE_CHANNEL_MAX_BYTES	16
-
-
-#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 */
-#define EV_EPERM		1	/* Operation not permitted */
-#define EV_ENOENT		2	/*  Entry Not Found */
-#define EV_EIO			3	/* I/O error occured */
-#define EV_EAGAIN		4	/* The operation had insufficient
-					 * resources to complete and should be
-					 * retried
-					 */
-#define EV_ENOMEM		5	/* There was insufficient memory to
-					 * complete the operation */
-#define EV_EFAULT		6	/* Bad guest address */
-#define EV_ENODEV		7	/* No such device */
-#define EV_EINVAL		8	/* An argument supplied to the hcall
-					   was out of range or invalid */
-#define EV_INTERNAL		9	/* An internal error occured */
-#define EV_CONFIG		10	/* A configuration error was detected */
-#define EV_INVALID_STATE	11	/* The object is in an invalid state */
-#define EV_UNIMPLEMENTED	12	/* Unimplemented hypercall */
-#define EV_BUFFER_OVERFLOW	13	/* Caller-supplied buffer too small */
-
 /*
  * Hypercall register clobber list
  *
@@ -193,7 +142,7 @@ 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 +171,7 @@ 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 +201,7 @@ 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 +226,7 @@ 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 +254,7 @@ 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 +293,7 @@ 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 +332,7 @@ 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 +370,7 @@ 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 +403,7 @@ 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 +427,7 @@ 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 +447,12 @@ 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
+#endif /* !__ASSEMBLY__ */
+#endif /* _EPAPR_HCALLS_H */
diff --git a/arch/powerpc/include/asm/fsl_hcalls.h b/arch/powerpc/include/asm/fsl_hcalls.h
index 922d9b5fe3d..3abb58394da 100644
--- a/arch/powerpc/include/asm/fsl_hcalls.h
+++ b/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
 	);
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 76fdcfef088..aabcdba8f6b 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -118,6 +118,7 @@
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
+#define RESUME_FLAG_ARCH1	(1<<2)
 
 #define RESUME_GUEST            0
 #define RESUME_GUEST_NV         RESUME_FLAG_NV
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 7aefdb3e1ce..5a56e1c5f85 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -81,6 +81,8 @@ struct kvmppc_vcpu_book3s {
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
+	u64 purr_offset;
+	u64 spurr_offset;
 #ifdef CONFIG_PPC_BOOK3S_32
 	u32 vsid_pool[VSID_POOL_SIZE];
 	u32 vsid_next;
@@ -157,10 +159,14 @@ extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr,
 extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr);
 extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 			long pte_index, unsigned long pteh, unsigned long ptel);
-extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
-			long pte_index, unsigned long pteh, unsigned long ptel);
+extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
+			long pte_index, unsigned long pteh, unsigned long ptel,
+			pgd_t *pgdir, bool realmode, unsigned long *idx_ret);
+extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
+			unsigned long pte_index, unsigned long avpn,
+			unsigned long *hpret);
 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);
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 0dd1d86d3e3..38bec1dc992 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -50,6 +50,15 @@ extern int kvm_hpt_order;		/* order of preallocated HPTs */
 #define HPTE_V_HVLOCK	0x40UL
 #define HPTE_V_ABSENT	0x20UL
 
+/*
+ * We use this bit in the guest_rpte field of the revmap entry
+ * to indicate a modified HPTE.
+ */
+#define HPTE_GR_MODIFIED	(1ul << 62)
+
+/* These bits are reserved in the guest view of the HPTE */
+#define HPTE_GR_RESERVED	HPTE_GR_MODIFIED
+
 static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
 {
 	unsigned long tmp, old;
@@ -60,7 +69,7 @@ static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
 		     "	ori	%0,%0,%4\n"
 		     "  stdcx.	%0,0,%2\n"
 		     "	beq+	2f\n"
-		     "	li	%1,%3\n"
+		     "	mr	%1,%3\n"
 		     "2:	isync"
 		     : "=&r" (tmp), "=&r" (old)
 		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
@@ -237,4 +246,26 @@ static inline bool slot_is_aligned(struct kvm_memory_slot *memslot,
 	return !(memslot->base_gfn & mask) && !(memslot->npages & mask);
 }
 
+/*
+ * This works for 4k, 64k and 16M pages on POWER7,
+ * and 4k and 16M pages on PPC970.
+ */
+static inline unsigned long slb_pgsize_encoding(unsigned long psize)
+{
+	unsigned long senc = 0;
+
+	if (psize > 0x1000) {
+		senc = SLB_VSID_L;
+		if (psize == 0x10000)
+			senc |= SLB_VSID_LP_01;
+	}
+	return senc;
+}
+
+static inline int is_vrma_hpte(unsigned long hpte_v)
+{
+	return (hpte_v & ~0xffffffUL) ==
+		(HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)));
+}
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_booke_hv_asm.h b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
index 30a600fa1b6..3a79f532571 100644
--- a/arch/powerpc/include/asm/kvm_booke_hv_asm.h
+++ b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
@@ -17,6 +17,7 @@
  * there are no exceptions for which we fall through directly to
  * the normal host handler.
  *
+ * 32-bit host
  * Expected inputs (normal exceptions):
  *   SCRATCH0 = saved r10
  *   r10 = thread struct
@@ -33,14 +34,38 @@
  *   *(r8 + GPR9) = saved r9
  *   *(r8 + GPR10) = saved r10 (r10 not yet clobbered)
  *   *(r8 + GPR11) = saved r11
+ *
+ * 64-bit host
+ * Expected inputs (GEN/GDBELL/DBG/MC exception types):
+ *  r10 = saved CR
+ *  r13 = PACA_POINTER
+ *  *(r13 + PACA_EX##type + EX_R10) = saved r10
+ *  *(r13 + PACA_EX##type + EX_R11) = saved r11
+ *  SPRN_SPRG_##type##_SCRATCH = saved r13
+ *
+  * Expected inputs (CRIT exception type):
+ *  r10 = saved CR
+ *  r13 = PACA_POINTER
+ *  *(r13 + PACA_EX##type + EX_R10) = saved r10
+ *  *(r13 + PACA_EX##type + EX_R11) = saved r11
+ *  *(r13 + PACA_EX##type + EX_R13) = saved r13
+ *
+ * Expected inputs (TLB exception type):
+ *  r10 = saved CR
+ *  r13 = PACA_POINTER
+ *  *(r13 + PACA_EX##type + EX_TLB_R10) = saved r10
+ *  *(r13 + PACA_EX##type + EX_TLB_R11) = saved r11
+ *  SPRN_SPRG_GEN_SCRATCH = saved r13
+ *
+ * Only the bolted version of TLB miss exception handlers is supported now.
  */
 .macro DO_KVM intno srr1
 #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
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 28e8f5e5c63..ca9bf459db6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/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 {
@@ -243,12 +246,12 @@ struct kvm_arch {
 	int using_mmu_notifiers;
 	u32 hpt_order;
 	atomic_t vcpus_running;
+	u32 online_vcores;
 	unsigned long hpt_npte;
 	unsigned long hpt_mask;
+	atomic_t hpte_mod_interest;
 	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];
+	cpumask_t need_tlb_flush;
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	struct kvmppc_linear_info *hpt_li;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
@@ -273,6 +276,7 @@ struct kvmppc_vcore {
 	int nap_count;
 	int napping_threads;
 	u16 pcpu;
+	u16 last_cpu;
 	u8 vcore_state;
 	u8 in_guest;
 	struct list_head runnable_threads;
@@ -288,9 +292,10 @@ struct kvmppc_vcore {