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

* 'for-upstream' of https://github.com/agraf/linux-2.6: (28 commits)
  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
  KVM: PPC: Book3S HV: Handle guest-caused machine checks on POWER7 without panicking
  KVM: PPC: Book3S HV: Improve handling of local vs. global TLB invalidations
  MAINTAINERS: Add git tree link for PPC KVM
  KVM: PPC: Book3S PR: MSR_DE doesn't exist on Book 3S
  KVM: PPC: Book3S PR: Fix VSX handling
  KVM: PPC: Book3S PR: Emulate PURR, SPURR and DSCR registers
  KVM: PPC: Book3S HV: Don't give the guest RW access to RO pages
  KVM: PPC: Book3S HV: Report correct HPT entry index when reading HPT
  ...

Documentation/virtual/kvm/api.txt

@@ -1773,6 +1773,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VPA_ADDR  | 64
   PPC   | KVM_REG_PPC_VPA_SLB   | 128
   PPC   | KVM_REG_PPC_VPA_DTL   | 128
+  PPC   | KVM_REG_PPC_EPCR	| 32
 
 4.69 KVM_GET_ONE_REG
 
@@ -2071,6 +2072,60 @@ KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
+4.78 KVM_PPC_GET_HTAB_FD
+
+Capability: KVM_CAP_PPC_HTAB_FD
+Architectures: powerpc
+Type: vm ioctl
+Parameters: Pointer to struct kvm_get_htab_fd (in)
+Returns: file descriptor number (>= 0) on success, -1 on error
+
+This returns a file descriptor that can be used either to read out the
+entries in the guest's hashed page table (HPT), or to write entries to
+initialize the HPT.  The returned fd can only be written to if the
+KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
+can only be read if that bit is clear.  The argument struct looks like
+this:
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+The `start_index' field gives the index in the HPT of the entry at
+which to start reading.  It is ignored when writing.
+
+Reads on the fd will initially supply information about all
+"interesting" HPT entries.  Interesting entries are those with the
+bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
+all entries.  When the end of the HPT is reached, the read() will
+return.  If read() is called again on the fd, it will start again from
+the beginning of the HPT, but will only return HPT entries that have
+changed since they were last read.
+
+Data read or written is structured as a header (8 bytes) followed by a
+series of valid HPT entries (16 bytes) each.  The header indicates how
+many valid HPT entries there are and how many invalid entries follow
+the valid entries.  The invalid entries are not represented explicitly
+in the stream.  The header format is:
+
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
+Writes to the fd create HPT entries starting at the index given in the
+header; first `n_valid' valid entries with contents from the data
+written, then `n_invalid' invalid entries, invalidating any previously
+valid entries found.
+
 
 5. The kvm_run structure
 ------------------------

MAINTAINERS

@@ -4253,6 +4253,7 @@ KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
 M:	Alexander Graf <agraf@suse.de>
 L:	kvm-ppc@vger.kernel.org
 W:	http://kvm.qumranet.com
+T:	git git://github.com/agraf/linux-2.6.git
 S:	Supported
 F:	arch/powerpc/include/asm/kvm*
 F:	arch/powerpc/kvm/

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;
@@ -157,8 +159,12 @@ 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, unsigned long *map);
 

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;
@@ -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__ */

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
@@ -33,6 +34,30 @@
  *   *(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

arch/powerpc/include/asm/kvm_host.h

@@ -246,10 +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 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 */
@@ -274,6 +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;
@@ -403,13 +406,18 @@ struct kvm_vcpu_arch {
 	u32 host_mas4;
 	u32 host_mas6;
 	u32 shadow_epcr;
-	u32 epcr;
 	u32 shadow_msrp;
 	u32 eplc;
 	u32 epsc;
 	u32 oldpir;
 #endif
 
+#if defined(CONFIG_BOOKE)
+#if defined(CONFIG_KVM_BOOKE_HV) || defined(CONFIG_64BIT)
+	u32 epcr;
+#endif
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S
 	/* For Gekko paired singles */
 	u32 qpr[32];
@@ -522,7 +530,6 @@ struct kvm_vcpu_arch {
 	u64 dec_jiffies;
 	u64 dec_expires;
 	unsigned long pending_exceptions;
-	u16 last_cpu;
 	u8 ceded;
 	u8 prodded;
 	u32 last_inst;

arch/powerpc/include/asm/kvm_ppc.h

@@ -164,6 +164,8 @@ extern void kvmppc_bookehv_exit(void);
 
 extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu);
 
+extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
@@ -293,4 +295,25 @@ static inline void kvmppc_lazy_ee_enable(void)
 #endif
 }
 
+static inline ulong kvmppc_get_ea_indexed(struct kvm_vcpu *vcpu, int ra, int rb)
+{
+	ulong ea;
+	ulong msr_64bit = 0;
+
+	ea = kvmppc_get_gpr(vcpu, rb);
+	if (ra)
+		ea += kvmppc_get_gpr(vcpu, ra);
+
+#if defined(CONFIG_PPC_BOOK3E_64)
+	msr_64bit = MSR_CM;
+#elif defined(CONFIG_PPC_BOOK3S_64)
+	msr_64bit = MSR_SF;
+#endif
+
+	if (!(vcpu->arch.shared->msr & msr_64bit))
+		ea = (uint32_t)ea;
+
+	return ea;
+}
+
 #endif /* __POWERPC_KVM_PPC_H__ */

arch/powerpc/include/asm/mmu-book3e.h

@@ -59,7 +59,7 @@
 #define MAS1_TSIZE_SHIFT	7
 #define MAS1_TSIZE(x)		(((x) << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
 
-#define MAS2_EPN		0xFFFFF000
+#define MAS2_EPN		(~0xFFFUL)
 #define MAS2_X0			0x00000040
 #define MAS2_X1			0x00000020
 #define MAS2_W			0x00000010

arch/powerpc/include/asm/mmu-hash64.h

@@ -121,6 +121,16 @@ extern char initial_stab[];
 #define PP_RXRX 3	/* Supervisor read,       User read */
 #define PP_RXXX	(HPTE_R_PP0 | 2)	/* Supervisor read, user none */
 
+/* Fields for tlbiel instruction in architecture 2.06 */
+#define TLBIEL_INVAL_SEL_MASK	0xc00	/* invalidation selector */
+#define  TLBIEL_INVAL_PAGE	0x000	/* invalidate a single page */
+#define  TLBIEL_INVAL_SET_LPID	0x800	/* invalidate a set for current LPID */
+#define  TLBIEL_INVAL_SET	0xc00	/* invalidate a set for all LPIDs */
+#define TLBIEL_INVAL_SET_MASK	0xfff000	/* set number to inval. */
+#define TLBIEL_INVAL_SET_SHIFT	12
+
+#define POWER7_TLB_SETS		128	/* # sets in POWER7 TLB */
+
 #ifndef __ASSEMBLY__
 
 struct hash_pte {

arch/powerpc/include/asm/reg.h

@@ -518,6 +518,7 @@
 #define	  SRR1_WS_DEEPER	0x00020000 /* Some resources not maintained */
 #define	  SRR1_WS_DEEP		0x00010000 /* All resources maintained */
 #define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
+#define   SRR1_PROGILL		0x00080000 /* Illegal instruction */
 #define   SRR1_PROGPRIV		0x00040000 /* Privileged instruction */
 #define   SRR1_PROGTRAP		0x00020000 /* Trap */
 #define   SRR1_PROGADDR		0x00010000 /* SRR0 contains subsequent addr */

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

@@ -331,6 +331,31 @@ struct kvm_book3e_206_tlb_params {
 	__u32 reserved[8];
 };
 
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+/*
+ * Data read on the file descriptor is formatted as a series of
+ * records, each consisting of a header followed by a series of
+ * `n_valid' HPTEs (16 bytes each), which are all valid.  Following
+ * those valid HPTEs there are `n_invalid' invalid HPTEs, which
+ * are not represented explicitly in the stream.  The same format
+ * is used for writing.
+ */
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
 #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)
@@ -386,4 +411,6 @@ struct kvm_book3e_206_tlb_params {
 #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)
 
+#define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/kernel/asm-offsets.c

@@ -441,8 +441,7 @@ int main(void)
 	DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
 	DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
 	DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
-	DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter));
-	DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
+	DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
 	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
 	DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
 	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
@@ -470,7 +469,6 @@ int main(void)
 	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
 	DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
 	DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
-	DEFINE(VCPU_LAST_CPU, offsetof(struct kvm_vcpu, arch.last_cpu));
 	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
 	DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));

arch/powerpc/kvm/Kconfig

@@ -20,6 +20,7 @@ config KVM
 	bool
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_EVENTFD
 
 config KVM_BOOK3S_HANDLER
 	bool

arch/powerpc/kvm/Makefile

@@ -6,7 +6,8 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm
 
-common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
+common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o \
+						eventfd.o)
 
 CFLAGS_44x_tlb.o  := -I.
 CFLAGS_e500_tlb.o := -I.
@@ -72,10 +73,12 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
 	book3s_64_vio_hv.o \
+	book3s_hv_ras.o \
 	book3s_hv_builtin.o
 
 kvm-book3s_64-module-objs := \
 	../../../virt/kvm/kvm_main.o \
+	../../../virt/kvm/eventfd.o \
 	powerpc.o \
 	emulate.o \
 	book3s.o \

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -25,6 +25,8 @@
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
 #include <linux/srcu.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -41,6 +43,11 @@
 /* Power architecture requires HPT is at least 256kB */
 #define PPC_MIN_HPT_ORDER	18
 
+static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
+				long pte_index, unsigned long pteh,
+				unsigned long ptel, unsigned long *pte_idx_ret);
+static void kvmppc_rmap_reset(struct kvm *kvm);
+
 long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
 	unsigned long hpt;
@@ -138,10 +145,11 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
 		/* Set the entire HPT to 0, i.e. invalid HPTEs */
 		memset((void *)kvm->arch.hpt_virt, 0, 1ul << order);
 		/*
-		 * Set the whole last_vcpu array to an invalid vcpu number.
-		 * This ensures that each vcpu will flush its TLB on next entry.
+		 * Reset all the reverse-mapping chains for all memslots
 		 */
-		memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu));
+		kvmppc_rmap_reset(kvm);
+		/* Ensure that each vcpu will flush its TLB on next entry. */
+		cpumask_setall(&kvm->arch.need_tlb_flush);
 		*htab_orderp = order;
 		err = 0;
 	} else {
@@ -185,6 +193,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	unsigned long addr, hash;
 	unsigned long psize;
 	unsigned long hp0, hp1;
+	unsigned long idx_ret;
 	long ret;
 	struct kvm *kvm = vcpu->kvm;
 
@@ -216,7 +225,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 		hash = (hash << 3) + 7;
 		hp_v = hp0 | ((addr >> 16) & ~0x7fUL);
 		hp_r = hp1 | addr;
-		ret = kvmppc_virtmode_h_enter(vcpu, H_EXACT, hash, hp_v, hp_r);
+		ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, hash, hp_v, hp_r,
+						 &idx_ret);
 		if (ret != H_SUCCESS) {
 			pr_err("KVM: map_vrma at %lx failed, ret=%ld\n",
 			       addr, ret);
@@ -354,15 +364,10 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	return err;
 }
 
-/*
- * We come here on a H_ENTER call from the guest when we are not
- * using mmu notifiers and we don't have the requested page pinned
- * already.
- */
-long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
-			long pte_index, unsigned long pteh, unsigned long ptel)
+long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
+				long pte_index, unsigned long pteh,
+				unsigned long ptel, unsigned long *pte_idx_ret)
 {
-	struct kvm *kvm = vcpu->kvm;
 	unsigned long psize, gpa, gfn;
 	struct kvm_memory_slot *memslot;
 	long ret;
@@ -390,8 +395,8 @@ long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
  do_insert:
 	/* Protect linux PTE lookup from page table destruction */
 	rcu_read_lock_sched();	/* this disables preemption too */
-	vcpu->arch.pgdir = current->mm->pgd;
-	ret = kvmppc_h_enter(vcpu, flags, pte_index, pteh, ptel);
+	ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel,
+				current->mm->pgd, false, pte_idx_ret);
 	rcu_read_unlock_sched();
 	if (ret == H_TOO_HARD) {
 		/* this can't happen */
@@ -402,6 +407,19 @@ long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 
 }
 
+/*
+ * We come here on a H_ENTER call from the guest when we are not
+ * using mmu notifiers and we don't have the requested page pinned
+ * already.
+ */
+long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+			     long pte_index, unsigned long pteh,
+			     unsigned long ptel)
+{
+	return kvmppc_virtmode_do_h_enter(vcpu->kvm, flags, pte_index,
+					  pteh, ptel, &vcpu->arch.gpr[4]);
+}
+
 static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu,
 							 gva_t eaddr)
 {
@@ -756,6 +774,25 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	goto out_put;
 }
 
+static void kvmppc_rmap_reset(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int srcu_idx;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	slots = kvm->memslots;
+	kvm_for_each_memslot(memslot, slots) {
+		/*
+		 * This assumes it is acceptable to lose reference and
+		 * change bits across a reset.
+		 */
+		memset(memslot->arch.rmap, 0,
+		       memslot->npages * sizeof(*memslot->arch.rmap));
+	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+}
+
 static int kvm_handle_hva_range(struct kvm *kvm,
 				unsigned long start,
 				unsigned long end,
@@ -1131,6 +1168,348 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 	put_page(page);
 }
 
+/*
+ * Functions for reading and writing the hash table via reads and
+ * writes on a file descriptor.
+ *
+ * Reads return the guest view of the hash table, which has to be
+ * pieced together from the real hash table and the guest_rpte
+ * values in the revmap array.
+ *
+ * On writes, each HPTE written is considered in turn, and if it
+ * is valid, it is written to the HPT as if an H_ENTER with the
+ * exact flag set was done.  When the invalid count is non-zero
+ * in the header written to the stream, the kernel will make
+ * sure that that many HPTEs are invalid, and invalidate them
+ * if not.
+ */
+
+struct kvm_htab_ctx {
+	unsigned long	index;
+	unsigned long	flags;
+	struct kvm	*kvm;
+	int		first_pass;
+};
+
+#define HPTE_SIZE	(2 * sizeof(unsigned long))
+
+static long record_hpte(unsigned long flags, unsigned long *hptp,
+			unsigned long *hpte, struct revmap_entry *revp,
+			int want_valid, int first_pass)
+{
+	unsigned long v, r;
+	int ok = 1;
+	int valid, dirty;
+
+	/* Unmodified entries are uninteresting except on the first pass */
+	dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+	if (!first_pass && !dirty)
+		return 0;
+
+	valid = 0;
+	if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+		valid = 1;
+		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) &&
+		    !(hptp[0] & HPTE_V_BOLTED))
+			valid = 0;
+	}
+	if (valid != want_valid)
+		return 0;
+
+	v = r = 0;
+	if (valid || dirty) {
+		/* lock the HPTE so it's stable and read it */
+		preempt_disable();
+		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+			cpu_relax();
+		v = hptp[0];
+		if (v & HPTE_V_ABSENT) {
+			v &= ~HPTE_V_ABSENT;
+			v |= HPTE_V_VALID;
+		}
+		/* re-evaluate valid and dirty from synchronized HPTE value */
+		valid = !!(v & HPTE_V_VALID);
+		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && !(v & HPTE_V_BOLTED))
+			valid = 0;
+		r = revp->guest_rpte | (hptp[1] & (HPTE_R_R | HPTE_R_C));
+		dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+		/* only clear modified if this is the right sort of entry */
+		if (valid == want_valid && dirty) {
+			r &= ~HPTE_GR_MODIFIED;
+			revp->guest_rpte = r;
+		}
+		asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+		hptp[0] &= ~HPTE_V_HVLOCK;
+		preempt_enable();
+		if (!(valid == want_valid && (first_pass || dirty)))
+			ok = 0;
+	}
+	hpte[0] = v;
+	hpte[1] = r;
+	return ok;
+}
+
+static ssize_t kvm_htab_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct kvm_htab_ctx *ctx = file->private_data;
+	struct kvm *kvm = ctx->kvm;
+	struct kvm_get_htab_header hdr;
+	unsigned long *hptp;
+	struct revmap_entry *revp;
+	unsigned long i, nb, nw;
+	unsigned long __user *lbuf;
+	struct kvm_get_htab_header __user *hptr;
+	unsigned long flags;
+	int first_pass;
+	unsigned long hpte[2];
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	first_pass = ctx->first_pass;
+	flags = ctx->flags;
+
+	i = ctx->index;
+	hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+	revp = kvm->arch.revmap + i;
+	lbuf = (unsigned long __user *)buf;
+
+	nb = 0;
+	while (nb + sizeof(hdr) + HPTE_SIZE < count) {
+		/* Initialize header */
+		hptr = (struct kvm_get_htab_header __user *)buf;
+		hdr.n_valid = 0;
+		hdr.n_invalid = 0;
+		nw = nb;
+		nb += sizeof(hdr);
+		lbuf = (unsigned long __user *)(buf + sizeof(hdr));
+
+		/* Skip uninteresting entries, i.e. clean on not-first pass */
+		if (!first_pass) {
+			while (i < kvm->arch.hpt_npte &&
+			       !(revp->guest_rpte & HPTE_GR_MODIFIED)) {
+				++i;
+				hptp += 2;
+				++revp;
+			}
+		}
+		hdr.index = i;
+
+		/* Grab a series of valid entries */
+		while (i < kvm->arch.hpt_npte &&
+		       hdr.n_valid < 0xffff &&
+		       nb + HPTE_SIZE < count &&
+		       record_hpte(flags, hptp, hpte, revp, 1, first_pass)) {
+			/* valid entry, write it out */
+			++hdr.n_valid;
+			if (__put_user(hpte[0], lbuf) ||
+			    __put_user(hpte[1], lbuf + 1))
+				return -EFAULT;
+			nb += HPTE_SIZE;
+			lbuf += 2;
+			++i;
+			hptp += 2;
+			++revp;
+		}
+		/* Now skip invalid entries while we can */
+		while (i < kvm->arch.hpt_npte &&
+		       hdr.n_invalid < 0xffff &&
+		       record_hpte(flags, hptp, hpte, revp, 0, first_pass)) {
+			/* found an invalid entry */
+			++hdr.n_invalid;
+			++i;
+			hptp += 2;
+			++revp;
+		}
+
+		if (hdr.n_valid || hdr.n_invalid) {
+			/* write back the header */
+			if (__copy_to_user(hptr, &hdr, sizeof(hdr)))
+				return -EFAULT;
+			nw = nb;
+			buf = (char __user *)lbuf;
+		} else {
+			nb = nw;
+		}
+
+		/* Check if we've wrapped around the hash table */
+		if (i >= kvm->arch.hpt_npte) {
+			i = 0;
+			ctx->first_pass = 0;
+			break;
+		}
+	}
+
+	ctx->index = i;
+
+	return nb;
+}
+
+static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct kvm_htab_ctx *ctx = file->private_data;
+	struct kvm *kvm = ctx->kvm;
+	struct kvm_get_htab_header hdr;
+	unsigned long i, j;
+	unsigned long v, r;
+	unsigned long __user *lbuf;
+	unsigned long *hptp;
+	unsigned long tmp[2];
+	ssize_t nb;
+	long int err, ret;
+	int rma_setup;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	/* lock out vcpus from running while we're doing this */
+	mutex_lock(&kvm->lock);
+	rma_setup = kvm->arch.rma_setup_done;
+	if (rma_setup) {
+		kvm->arch.rma_setup_done = 0;	/* temporarily */
+		/* order rma_setup_done vs. vcpus_running */
+		smp_mb();
+		if (atomic_read(&kvm->arch.vcpus_running)) {
+			kvm->arch.rma_setup_done = 1;
+			mutex_unlock(&kvm->lock);
+			return -EBUSY;
+		}
+	}
+
+	err = 0;
+	for (nb = 0; nb + sizeof(hdr) <= count; ) {
+		err = -EFAULT;
+		if (__copy_from_user(&hdr, buf, sizeof(hdr)))
+			break;
+
+		err = 0;
+		if (nb + hdr.n_valid * HPTE_SIZE > count)
+			break;
+
+		nb += sizeof(hdr);
+		buf += sizeof(hdr);
+
+		err = -EINVAL;
+		i = hdr.index;
+		if (i >= kvm->arch.hpt_npte ||
+		    i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte)
+			break;
+
+		hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+		lbuf = (unsigned long __user *)buf;
+		for (j = 0; j < hdr.n_valid; ++j) {
+			err = -EFAULT;
+			if (__get_user(v, lbuf) || __get_user(r, lbuf + 1))
+				goto out;
+			err = -EINVAL;
+			if (!(v & HPTE_V_VALID))
+				goto out;
+			lbuf += 2;
+			nb += HPTE_SIZE;
+
+			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
+			err = -EIO;
+			ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, i, v, r,
+							 tmp);
+			if (ret != H_SUCCESS) {
+				pr_err("kvm_htab_write ret %ld i=%ld v=%lx "
+				       "r=%lx\n", ret, i, v, r);
+				goto out;
+			}
+			if (!rma_setup && is_vrma_hpte(v)) {
+				unsigned long psize = hpte_page_size(v, r);
+				unsigned long senc = slb_pgsize_encoding(psize);
+				unsigned long lpcr;
+
+				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
+					(VRMA_VSID << SLB_VSID_SHIFT_1T);
+				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
+				lpcr |= senc << (LPCR_VRMASD_SH - 4);
+				kvm->arch.lpcr = lpcr;
+				rma_setup = 1;
+			}
+			++i;
+			hptp += 2;
+		}
+
+		for (j = 0; j < hdr.n_invalid; ++j) {
+			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
+			++i;
+			hptp += 2;
+		}
+		err = 0;
+	}
+
+ out:
+	/* Order HPTE updates vs. rma_setup_done */
+	smp_wmb();
+	kvm->arch.rma_setup_done = rma_setup;
+	mutex_unlock(&kvm->lock);
+
+	if (err)
+		return err;
+	return nb;
+}
+
+static int kvm_htab_release(struct inode *inode, struct file *filp)
+{
+	struct kvm_htab_ctx *ctx = filp->private_data;
+
+	filp->private_data = NULL;
+	if (!(ctx->flags & KVM_GET_HTAB_WRITE))
+		atomic_dec(&ctx->kvm->arch.hpte_mod_interest);
+	kvm_put_kvm(ctx->kvm);
+	kfree(ctx);
+	return 0;
+}
+
+static struct file_operations kvm_htab_fops = {
+	.read		= kvm_htab_read,
+	.write		= kvm_htab_write,
+	.llseek		= default_llseek,
+	.release	= kvm_htab_release,
+};
+
+int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
+{
+	int ret;
+	struct kvm_htab_ctx *ctx;
+	int rwflag;
+
+	/* reject flags we don't recognize */
+	if (ghf->flags & ~(KVM_GET_HTAB_BOLTED_ONLY | KVM_GET_HTAB_WRITE))
+		return -EINVAL;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	kvm_get_kvm(kvm);
+	ctx->kvm = kvm;
+	ctx->index = ghf->start_index;
+	ctx->flags = ghf->flags;
+	ctx->first_pass = 1;
+
+	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
+	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
+	if (ret < 0) {
+		kvm_put_kvm(kvm);
+		return ret;
+	}
+
+	if (rwflag == O_RDONLY) {
+		mutex_lock(&kvm->slots_lock);
+		atomic_inc(&kvm->arch.hpte_mod_interest);
+		/* make sure kvmppc_do_h_enter etc. see the increment */
+		synchronize_srcu_expedited(&kvm->srcu);
+		mutex_unlock(&kvm->slots_lock);
+	}
+
+	return ret;
+}
+
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;

arch/powerpc/kvm/book3s_emulate.c

@@ -22,6 +22,7 @@
 #include <asm/kvm_book3s.h>
 #include <asm/reg.h>
 #include <asm/switch_to.h>
+#include <asm/time.h>
 
 #define OP_19_XOP_RFID		18
 #define OP_19_XOP_RFI		50
@@ -395,6 +396,12 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		    (mfmsr() & MSR_HV))
 			vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
 		break;
+	case SPRN_PURR:
+		to_book3s(vcpu)->purr_offset = spr_val - get_tb();
+		break;
+	case SPRN_SPURR:
+		to_book3s(vcpu)->spurr_offset = spr_val - get_tb();
+		break;
 	case SPRN_GQR0:
 	case SPRN_GQR1:
 	case SPRN_GQR2:
@@ -412,6 +419,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_CTRLF:
 	case SPRN_CTRLT:
 	case SPRN_L2CR:
+	case SPRN_DSCR:
 	case SPRN_MMCR0_GEKKO:
 	case SPRN_MMCR1_GEKKO:
 	case SPRN_PMC1_GEKKO:
@@ -483,9 +491,15 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 		*spr_val = to_book3s(vcpu)->hid[5];
 		break;
 	case SPRN_CFAR:
-	case SPRN_PURR:
+	case SPRN_DSCR:
 		*spr_val = 0;
 		break;
+	case SPRN_PURR:
+		*spr_val = get_tb() + to_book3s(vcpu)->purr_offset;
+		break;
+	case SPRN_SPURR:
+		*spr_val = get_tb() + to_book3s(vcpu)->purr_offset;
+		break;
 	case SPRN_GQR0:
 	case SPRN_GQR1:
 	case SPRN_GQR2:

arch/powerpc/kvm/book3s_exports.c

@@ -28,8 +28,5 @@ EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec);
 #endif
-#ifdef CONFIG_VSX
-EXPORT_SYMBOL_GPL(kvmppc_load_up_vsx);
-#endif
 #endif
 

arch/powerpc/kvm/book3s_hv.c

@@ -545,6 +545,17 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_PERFMON:
 		r = RESUME_GUEST;
 		break;
+	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+		/*
+		 * Deliver a machine check interrupt to the guest.
+		 * We have to do this, even if the host has handled the
+		 * machine check, because machine checks use SRR0/1 and
+		 * the interrupt might have trashed guest state in them.
+		 */
+		kvmppc_book3s_queue_irqprio(vcpu,
+					    BOOK3S_INTERRUPT_MACHINE_CHECK);
+		r = RESUME_GUEST;
+		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
 		ulong flags;
@@ -853,7 +864,6 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 		goto free_vcpu;
 
 	vcpu->arch.shared = &vcpu->arch.shregs;
-	vcpu->arch.last_cpu = -1;
 	vcpu->arch.mmcr[0] = MMCR0_FC;
 	vcpu->arch.ctrl = CTRL_RUNLATCH;
 	/* default to host PVR, since we can't spoof it */
@@ -880,6 +890,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			vcore->preempt_tb = TB_NIL;
 		}
 		kvm->arch.vcores[core] = vcore;
+		kvm->arch.online_vcores++;
 	}
 	mutex_unlock(&kvm->lock);
 
@@ -1563,18 +1574,6 @@ out:
 	return r;
 }
 
-static 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 void unpin_slot(struct kvm_memory_slot *memslot)
 {
 	unsigned long *physp;
@@ -1814,6 +1813,13 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 		return -ENOMEM;
 	kvm->arch.lpid = lpid;
 
+	/*
+	 * Since we don't flush the TLB when tearing down a VM,
+	 * and this lpid might have previously been used,
+	 * make sure we flush on each core before running the new VM.
+	 */
+	cpumask_setall(&kvm->arch.need_tlb_flush);
+
 	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 
 	kvm->arch.rma = NULL;

arch/powerpc/kvm/book3s_hv_ras.c

@@ -0,0 +1,144 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright 2012 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/kernel.h>
+#include <asm/opal.h>
+
+/* SRR1 bits for machine check on POWER7 */
+#define SRR1_MC_LDSTERR		(1ul << (63-42))
+#define SRR1_MC_IFETCH_SH	(63-45)
+#define SRR1_MC_IFETCH_MASK	0x7
+#define SRR1_MC_IFETCH_SLBPAR		2	/* SLB parity error */
+#define SRR1_MC_IFETCH_SLBMULTI		3	/* SLB multi-hit */
+#define SRR1_MC_IFETCH_SLBPARMULTI	4	/* SLB parity + multi-hit */
+#define SRR1_MC_IFETCH_TLBMULTI		5	/* I-TLB multi-hit */
+
+/* DSISR bits for machine check on POWER7 */
+#define DSISR_MC_DERAT_MULTI	0x800		/* D-ERAT multi-hit */
+#define DSISR_MC_TLB_MULTI	0x400		/* D-TLB multi-hit */
+#define DSISR_MC_SLB_PARITY	0x100		/* SLB parity error */
+#define DSISR_MC_SLB_MULTI	0x080		/* SLB multi-hit */
+#define DSISR_MC_SLB_PARMULTI	0x040		/* SLB parity + multi-hit */
+
+/* POWER7 SLB flush and reload */
+static void reload_slb(struct kvm_vcpu *vcpu)
+{
+	struct slb_shadow *slb;
+	unsigned long i, n;
+
+	/* First clear out SLB */
+	asm volatile("slbmte %0,%0; slbia" : : "r" (0));
+
+	/* Do they have an SLB shadow buffer registered? */
+	slb = vcpu->arch.slb_shadow.pinned_addr;
+	if (!slb)
+		return;
+
+	/* Sanity check */
+	n = min_t(u32, slb->persistent, SLB_MIN_SIZE);
+	if ((void *) &slb->save_area[n] > vcpu->arch.slb_shadow.pinned_end)
+		return;
+
+	/* Load up the SLB from that */
+	for (i = 0; i < n; ++i) {
+		unsigned long rb = slb->save_area[i].esid;
+		unsigned long rs = slb->save_area[i].vsid;
+
+		rb = (rb & ~0xFFFul) | i;	/* insert entry number */
+		asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb));
+	}
+}
+
+/* POWER7 TLB flush */
+static void flush_tlb_power7(struct kvm_vcpu *vcpu)
+{
+	unsigned long i, rb;
+
+	rb = TLBIEL_INVAL_SET_LPID;
+	for (i = 0; i < POWER7_TLB_SETS; ++i) {
+		asm volatile("tlbiel %0" : : "r" (rb));
+		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
+	}
+}
+
+/*
+ * On POWER7, see if we can handle a machine check that occurred inside
+ * the guest in real mode, without switching to the host partition.
+ *
+ * Returns: 0 => exit guest, 1 => deliver machine check to guest
+ */
+static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
+{
+	unsigned long srr1 = vcpu->arch.shregs.msr;
+	struct opal_machine_check_event *opal_evt;
+	long handled = 1;
+
+	if (srr1 & SRR1_MC_LDSTERR) {
+		/* error on load/store */
+		unsigned long dsisr = vcpu->arch.shregs.dsisr;
+
+		if (dsisr & (DSISR_MC_SLB_PARMULTI | DSISR_MC_SLB_MULTI |
+			     DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI)) {
+			/* flush and reload SLB; flushes D-ERAT too */
+			reload_slb(vcpu);
+			dsisr &= ~(DSISR_MC_SLB_PARMULTI | DSISR_MC_SLB_MULTI |
+				   DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI);
+		}
+		if (dsisr & DSISR_MC_TLB_MULTI) {
+			flush_tlb_power7(vcpu);
+			dsisr &= ~DSISR_MC_TLB_MULTI;
+		}
+		/* Any other errors we don't understand? */
+		if (dsisr & 0xffffffffUL)
+			handled = 0;
+	}
+
+	switch ((srr1 >> SRR1_MC_IFETCH_SH) & SRR1_MC_IFETCH_MASK) {
+	case 0:
+		break;
+	case SRR1_MC_IFETCH_SLBPAR:
+	case SRR1_MC_IFETCH_SLBMULTI:
+	case SRR1_MC_IFETCH_SLBPARMULTI:
+		reload_slb(vcpu);
+		break;
+	case SRR1_MC_IFETCH_TLBMULTI:
+		flush_tlb_power7(vcpu);
+		break;
+	default:
+		handled = 0;
+	}
+
+	/*
+	 * See if OPAL has already handled the condition.
+	 * We assume that if the condition is recovered then OPAL
+	 * will have generated an error log event that we will pick
+	 * up and log later.
+	 */
+	opal_evt = local_paca->opal_mc_evt;
+	if (opal_evt->version == OpalMCE_V1 &&
+	    (opal_evt->severity == OpalMCE_SEV_NO_ERROR ||
+	     opal_evt->disposition == OpalMCE_DISPOSITION_RECOVERED))
+		handled = 1;
+
+	if (handled)
+		opal_evt->in_use = 0;
+
+	return handled;
+}
+
+long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_206))
+		return kvmppc_realmode_mc_power7(vcpu);
+
+	return 0;
+}

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -35,6 +35,37 @@ static void *real_vmalloc_addr(void *x)
 	return __va(addr);
 }
 
+/* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */
+static int global_invalidates(struct kvm *kvm, unsigned long flags)
+{
+	int global;
+
+	/*
+	 * If there is only one vcore, and it's currently running,
+	 * we can use tlbiel as long as we mark all other physical
+	 * cores as potentially having stale TLB entries for this lpid.
+	 * If we're not using MMU notifiers, we never take pages away
+	 * from the guest, so we can use tlbiel if requested.
+	 * Otherwise, don't use tlbiel.
+	 */
+	if (kvm->arch.online_vcores == 1 && local_paca->kvm_hstate.kvm_vcore)
+		global = 0;
+	else if (kvm->arch.using_mmu_notifiers)
+		global = 1;
+	else
+		global = !(flags & H_LOCAL);
+
+	if (!global) {
+		/* any other core might now have stale TLB entries... */
+		smp_wmb();
+		cpumask_setall(&kvm->arch.need_tlb_flush);
+		cpumask_clear_cpu(local_paca->kvm_hstate.kvm_vcore->pcpu,
+				  &kvm->arch.need_tlb_flush);
+	}
+
+	return global;
+}
+
 /*
  * Add this HPTE into the chain for the real page.
  * Must be called with the chain locked; it unlocks the chain.
@@ -59,13 +90,24 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 		head->back = pte_index;
 	} else {
 		rev->forw = rev->back = pte_index;
-		i = pte_index;
+		*rmap = (*rmap & ~KVMPPC_RMAP_INDEX) |
+			pte_index | KVMPPC_RMAP_PRESENT;
 	}
-	smp_wmb();
-	*rmap = i | KVMPPC_RMAP_REFERENCED | KVMPPC_RMAP_PRESENT; /* unlock */
+	unlock_rmap(rmap);
 }
 EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
 
+/*
+ * Note modification of an HPTE; set the HPTE modified bit
+ * if anyone is interested.
+ */
+static inline void note_hpte_modification(struct kvm *kvm,
+					  struct revmap_entry *rev)
+{
+	if (atomic_read(&kvm->arch.hpte_mod_interest))
+		rev->guest_rpte |= HPTE_GR_MODIFIED;
+}
+
 /* Remove this HPTE from the chain for a real page */
 static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 				struct revmap_entry *rev,
@@ -103,14 +145,14 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	unlock_rmap(rmap);
 }
 
-static pte_t lookup_linux_pte(struct kvm_vcpu *vcpu, unsigned long hva,
+static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva,
 			      int writing, unsigned long *pte_sizep)
 {
 	pte_t *ptep;
 	unsigned long ps = *pte_sizep;
 	unsigned int shift;
 
-	ptep = find_linux_pte_or_hugepte(vcpu->arch.pgdir, hva, &shift);
+	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift);
 	if (!ptep)
 		return __pte(0);
 	if (shift)
@@ -130,15 +172,15 @@ static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v)
 	hpte[0] = hpte_v;
 }
 
-long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
-		    long pte_index, unsigned long pteh, unsigned long ptel)
+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 *pte_idx_ret)
 {
-	struct kvm *kvm = vcpu->kvm;
 	unsigned long i, pa, gpa, gfn, psize;
 	unsigned long slot_fn, hva;
 	unsigned long *hpte;
 	struct revmap_entry *rev;
-	unsigned long g_ptel = ptel;
+	unsigned long g_ptel;
 	struct kvm_memory_slot *memslot;
 	unsigned long *physp, pte_size;
 	unsigned long is_io;
@@ -147,13 +189,14 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	unsigned int writing;
 	unsigned long mmu_seq;
 	unsigned long rcbits;
-	bool realmode = vcpu->arch.vcore->vcore_state == VCORE_RUNNING;
 
 	psize = hpte_page_size(pteh, ptel);
 	if (!psize)
 		return H_PARAMETER;
 	writing = hpte_is_writable(ptel);
 	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+	ptel &= ~HPTE_GR_RESERVED;
+	g_ptel = ptel;
 
 	/* used later to detect if we might have been invalidated */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -201,7 +244,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 
 		/* Look up the Linux PTE for the backing page */
 		pte_size = psize;
-		pte = lookup_linux_pte(vcpu, hva, writing, &pte_size);
+		pte = lookup_linux_pte(pgdir, hva, writing, &pte_size);
 		if (pte_present(pte)) {
 			if (writing && !pte_write(pte))
 				/* make the actual HPTE be read-only */
@@ -210,6 +253,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 			pa = pte_pfn(pte) << PAGE_SHIFT;
 		}
 	}
+
 	if (pte_size < psize)
 		return H_PARAMETER;
 	if (pa && pte_size > psize)
@@ -287,8 +331,10 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	rev = &kvm->arch.revmap[pte_index];
 	if (realmode)
 		rev = real_vmalloc_addr(rev);
-	if (rev)
+	if (rev) {
 		rev->guest_rpte = g_ptel;
+		note_hpte_modification(kvm, rev);
+	}
 
 	/* Link HPTE into reverse-map chain */
 	if (pteh & HPTE_V_VALID) {
@@ -297,7 +343,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 		lock_rmap(rmap);
 		/* Check for pending invalidations under the rmap chain lock */
 		if (kvm->arch.using_mmu_notifiers &&
-		    mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
+		    mmu_notifier_retry(kvm, mmu_seq)) {
 			/* inval in progress, write a non-present HPTE */
 			pteh |= HPTE_V_ABSENT;
 			pteh &= ~HPTE_V_VALID;
@@ -318,10 +364,17 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	hpte[0] = pteh;
 	asm volatile("ptesync" : : : "memory");
 
-	vcpu->arch.gpr[4] = pte_index;
+	*pte_idx_ret = pte_index;
 	return H_SUCCESS;
 }
-EXPORT_SYMBOL_GPL(kvmppc_h_enter);
+EXPORT_SYMBOL_GPL(kvmppc_do_h_enter);
+
+long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+		    long pte_index, unsigned long pteh, unsigned long ptel)
+{
+	return kvmppc_do_h_enter(vcpu->kvm, flags, pte_index, pteh, ptel,
+				 vcpu->arch.pgdir, true, &vcpu->arch.gpr[4]);
+}
 
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
 
@@ -343,11 +396,10 @@ static inline int try_lock_tlbie(unsigned int *lock)
 	return old == 0;
 }
 
-long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
-		     unsigned long pte_index, unsigned long avpn,
-		     unsigned long va)
+long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
+			unsigned long pte_index, unsigned long avpn,
+			unsigned long *hpret)
 {
-	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hpte;
 	unsigned long v, r, rb;
 	struct revmap_entry *rev;
@@ -369,7 +421,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		hpte[0] &= ~HPTE_V_VALID;
 		rb = compute_tlbie_rb(v, hpte[1], pte_index);
-		if (!(flags & H_LOCAL) && atomic_read(&kvm->online_vcpus) > 1) {
+		if (global_invalidates(kvm, flags)) {
 			while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
 				cpu_relax();
 			asm volatile("ptesync" : : : "memory");
@@ -385,13 +437,22 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 		/* Read PTE low word after tlbie to get final R/C values */
 		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
-	r = rev->guest_rpte;
+	r = rev->guest_rpte & ~HPTE_GR_RESERVED;
+	note_hpte_modification(kvm, rev);
 	unlock_hpte(hpte, 0);
 
-	vcpu->arch.gpr[4] = v;
-	vcpu->arch.gpr[5] = r;
+	hpret[0] = v;
+	hpret[1] = r;
 	return H_SUCCESS;
 }
+EXPORT_SYMBOL_GPL(kvmppc_do_h_remove);
+
+long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
+		     unsigned long pte_index, unsigned long avpn)
+{
+	return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
+				  &vcpu->arch.gpr[4]);
+}
 
 long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 {
@@ -459,6 +520,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 
 			args[j] = ((0x80 | flags) << 56) + pte_index;
 			rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+			note_hpte_modification(kvm, rev);
 
 			if (!(hp[0] & HPTE_V_VALID)) {
 				/* insert R and C bits from PTE */
@@ -534,8 +596,6 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 		return H_NOT_FOUND;
 	}
 
-	if (atomic_read(&kvm->online_vcpus) == 1)
-		flags |= H_LOCAL;
 	v = hpte[0];
 	bits = (flags << 55) & HPTE_R_PP0;
 	bits |= (flags << 48) & HPTE_R_KEY_HI;
@@ -548,6 +608,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (rev) {
 		r = (rev->guest_rpte & ~mask) | bits;
 		rev->guest_rpte = r;
+		note_hpte_modification(kvm, rev);
 	}
 	r = (hpte[1] & ~mask) | bits;
 
@@ -555,7 +616,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		rb = compute_tlbie_rb(v, r, pte_index);
 		hpte[0] = v & ~HPTE_V_VALID;
-		if (!(flags & H_LOCAL)) {
+		if (global_invalidates(kvm, flags)) {
 			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
 				cpu_relax();
 			asm volatile("ptesync" : : : "memory");
@@ -568,6 +629,28 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 			asm volatile("tlbiel %0" : : "r" (rb));
 			asm volatile("ptesync" : : : "memory");
 		}
+		/*
+		 * If the host has this page as readonly but the guest
+		 * wants to make it read/write, reduce the permissions.
+		 * Checking the host permissions involves finding the
+		 * memslot and then the Linux PTE for the page.
+		 */
+		if (hpte_is_writable(r) && kvm->arch.using_mmu_notifiers) {
+			unsigned long psize, gfn, hva;
+			struct kvm_memory_slot *memslot;
+			pgd_t *pgdir = vcpu->arch.pgdir;
+			pte_t pte;
+
+			psize = hpte_page_size(v, r);
+			gfn = ((r & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
+			memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+			if (memslot) {
+				hva = __gfn_to_hva_memslot(memslot, gfn);
+				pte = lookup_linux_pte(pgdir, hva, 1, &psize);
+				if (pte_present(pte) && !pte_write(pte))
+					r = hpte_make_readonly(r);
+			}
+		}
 	}
 	hpte[1] = r;
 	eieio();
@@ -599,8 +682,10 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 			v &= ~HPTE_V_ABSENT;
 			v |= HPTE_V_VALID;
 		}
-		if (v & HPTE_V_VALID)
+		if (v & HPTE_V_VALID) {
 			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
+			r &= ~HPTE_GR_RESERVED;
+		}
 		vcpu->arch.gpr[4 + i * 2] = v;
 		vcpu->arch.gpr[5 + i * 2] = r;
 	}

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -27,6 +27,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/exception-64s.h>
 #include <asm/kvm_book3s_asm.h>
+#include <asm/mmu-hash64.h>
 
 /*****************************************************************************
  *                                                                           *
@@ -313,7 +314,33 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
+
+	/* See if we need to flush the TLB */
+	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
+	clrldi	r7,r6,64-6		/* extract bit number (6 bits) */
+	srdi	r6,r6,6			/* doubleword number */
+	sldi	r6,r6,3			/* address offset */
+	add	r6,r6,r9
+	addi	r6,r6,KVM_NEED_FLUSH	/* dword in kvm->arch.need_tlb_flush */
 	li	r0,1
+	sld	r0,r0,r7
+	ld	r7,0(r6)
+	and.	r7,r7,r0
+	beq	22f
+23:	ldarx	r7,0,r6			/* if set, clear the bit */
+	andc	r7,r7,r0
+	stdcx.	r7,0,r6
+	bne	23b
+	li	r6,128			/* and flush the TLB */
+	mtctr	r6
+	li	r7,0x800		/* IS field = 0b10 */
+	ptesync
+28:	tlbiel	r7
+	addi	r7,r7,0x1000
+	bdnz	28b
+	ptesync
+
+22:	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -336,36 +363,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mr	r9,r4
 	blt	hdec_soon
 
-	/*
-	 * Invalidate the TLB if we could possibly have stale TLB
-	 * entries for this partition on this core due to the use
-	 * of tlbiel.
-	 * XXX maybe only need this on primary thread?
-	 */
-	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
-	lwz	r5,VCPU_VCPUID(r4)
-	lhz	r6,PACAPACAINDEX(r13)
-	rldimi	r6,r5,0,62		/* XXX map as if threads 1:1 p:v */
-	lhz	r8,VCPU_LAST_CPU(r4)
-	sldi	r7,r6,1			/* see if this is the same vcpu */
-	add	r7,r7,r9		/* as last ran on this pcpu */
-	lhz	r0,KVM_LAST_VCPU(r7)
-	cmpw	r6,r8			/* on the same cpu core as last time? */
-	bne	3f
-	cmpw	r0,r5			/* same vcpu as this core last ran? */
-	beq	1f
-3:	sth	r6,VCPU_LAST_CPU(r4)	/* if not, invalidate partition TLB */
-	sth	r5,KVM_LAST_VCPU(r7)
-	li	r6,128
-	mtctr	r6
-	li	r7,0x800		/* IS field = 0b10 */
-	ptesync
-2:	tlbiel	r7
-	addi	r7,r7,0x1000
-	bdnz	2b
-	ptesync
-1:
-
 	/* Save purr/spurr */
 	mfspr	r5,SPRN_PURR
 	mfspr	r6,SPRN_SPURR
@@ -682,8 +679,7 @@ BEGIN_FTR_SECTION
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
-nohpte_cont:
-hcall_real_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
+guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	/* Save DEC */
 	mfspr	r5,SPRN_DEC
 	mftb	r6
@@ -704,6 +700,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	std	r6, VCPU_FAULT_DAR(r9)
 	stw	r7, VCPU_FAULT_DSISR(r9)
 
+	/* See if it is a machine check */
+	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	beq	machine_check_realmode
+mc_cont:
+
 	/* Save guest CTRL register, set runlatch to 1 */
 6:	mfspr	r6,SPRN_CTRLF
 	stw	r6,VCPU_CTRL(r9)
@@ -1116,38 +1117,41 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	/*
 	 * For external and machine check interrupts, we need
 	 * to call the Linux handler to process the interrupt.
-	 * We do that by jumping to the interrupt vector address
-	 * which we have in r12.  The [h]rfid at the end of the
+	 * We do that by jumping to absolute address 0x500 for
+	 * external interrupts, or the machine_check_fwnmi label
+	 * for machine checks (since firmware might have patched
+	 * the vector area at 0x200).  The [h]rfid at the end of the
 	 * handler will return to the book3s_hv_interrupts.S code.
 	 * For other interrupts we do the rfid to get back
-	 * to the book3s_interrupts.S code here.
+	 * to the book3s_hv_interrupts.S code here.
 	 */
 	ld	r8, HSTATE_VMHANDLER(r13)
 	ld	r7, HSTATE_HOST_MSR(r13)
 
+	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
 	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+BEGIN_FTR_SECTION
 	beq	11f
-	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 	/* RFI into the highmem handler, or branch to interrupt handler */
-12:	mfmsr	r6
-	mtctr	r12
+	mfmsr	r6
 	li	r0, MSR_RI
 	andc	r6, r6, r0
 	mtmsrd	r6, 1			/* Clear RI in MSR */
 	mtsrr0	r8
 	mtsrr1	r7
-	beqctr
+	beqa	0x500			/* external interrupt (PPC970) */
+	beq	cr1, 13f		/* machine check */
 	RFI
 
-11:
-BEGIN_FTR_SECTION
-	b	12b
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	mtspr	SPRN_HSRR0, r8
+	/* On POWER7, we have external interrupts set to use HSRR0/1 */
+11:	mtspr	SPRN_HSRR0, r8
 	mtspr	SPRN_HSRR1, r7
 	ba	0x500
 
+13:	b	machine_check_fwnmi
+
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
  * If it is an HPTE not found fault that is due to the guest accessing
@@ -1180,7 +1184,7 @@ kvmppc_hdsi:
 	cmpdi	r3, 0			/* retry the instruction */
 	beq	6f
 	cmpdi	r3, -1			/* handle in kernel mode */
-	beq	nohpte_cont
+	beq	guest_exit_cont
 	cmpdi	r3, -2			/* MMIO emulation; need instr word */
 	beq	2f
 
@@ -1194,6 +1198,7 @@ kvmppc_hdsi:
 	li	r10, BOOK3S_INTERRUPT_DATA_STORAGE
 	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
 	rotldi	r11, r11, 63
+fast_interrupt_c_return:
 6:	ld	r7, VCPU_CTR(r9)
 	lwz	r8, VCPU_XER(r9)
 	mtctr	r7
@@ -1226,7 +1231,7 @@ kvmppc_hdsi:
 	/* Unset guest mode. */
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
-	b	nohpte_cont
+	b	guest_exit_cont
 
 /*
  * Similarly for an HISI, reflect it to the guest as an ISI unless
@@ -1252,9 +1257,9 @@ kvmppc_hisi:
 	ld	r11, VCPU_MSR(r9)
 	li	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
 	cmpdi	r3, 0			/* retry the instruction */
-	beq	6f
+	beq	fast_interrupt_c_return
 	cmpdi	r3, -1			/* handle in kernel mode */
-	beq	nohpte_cont
+	beq	guest_exit_cont
 
 	/* Synthesize an ISI for the guest */
 	mr	r11, r3
@@ -1263,12 +1268,7 @@ kvmppc_hisi:
 	li	r10, BOOK3S_INTERRUPT_INST_STORAGE
 	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
 	rotldi	r11, r11, 63
-6:	ld	r7, VCPU_CTR(r9)
-	lwz	r8, VCPU_XER(r9)
-	mtctr	r7
-	mtxer	r8
-	mr	r4, r9
-	b	fast_guest_return
+	b	fast_interrupt_c_return
 
 3:	ld	r6, VCPU_KVM(r9)	/* not relocated, use VRMA */
 	ld	r5, KVM_VRMA_SLB_V(r6)
@@ -1284,14 +1284,14 @@ kvmppc_hisi:
 hcall_try_real_mode:
 	ld	r3,VCPU_GPR(R3)(r9)
 	andi.	r0,r11,MSR_PR
-	bne	hcall_real_cont
+	bne	guest_exit_cont
 	clrrdi	r3,r3,2
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
-	bge	hcall_real_cont
+	bge	guest_exit_cont
 	LOAD_REG_ADDR(r4, hcall_real_table)
 	lwzx	r3,r3,r4
 	cmpwi	r3,0
-	beq	hcall_real_cont
+	beq	guest_exit_cont
 	add	r3,r3,r4
 	mtctr	r3
 	mr	r3,r9		/* get vcpu pointer */
@@ -1312,7 +1312,7 @@ hcall_real_fallback:
 	li	r12,BOOK3S_INTERRUPT_SYSCALL
 	ld	r9, HSTATE_KVM_VCPU(r13)
 
-	b	hcall_real_cont
+	b	guest_exit_cont
 
 	.globl	hcall_real_table
 hcall_real_table:
@@ -1571,6 +1571,21 @@ kvm_cede_exit:
 	li	r3,H_TOO_HARD
 	blr
 
+	/* Try to handle a machine check in real mode */
+machine_check_realmode:
+	mr	r3, r9		/* get vcpu pointer */
+	bl	.kvmppc_realmode_machine_check
+	nop
+	cmpdi	r3, 0		/* continue exiting from guest? */
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	beq	mc_cont
+	/* If not, deliver a machine check.  SRR0/1 are already set */
+	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
+	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
+	rotldi	r11, r11, 63
+	b	fast_interrupt_c_return
+
 secondary_too_late:
 	ld	r5,HSTATE_KVM_VCORE(r13)
 	HMT_LOW

arch/powerpc/kvm/book3s_pr.c

@@ -81,9 +81,7 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	svcpu_put(svcpu);
 #endif
 
-	kvmppc_giveup_ext(vcpu, MSR_FP);
-	kvmppc_giveup_ext(vcpu, MSR_VEC);
-	kvmppc_giveup_ext(vcpu, MSR_VSX);
+	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
 	vcpu->cpu = -1;
 }
 
@@ -147,7 +145,7 @@ static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 	ulong smsr = vcpu->arch.shared->msr;
 
 	/* Guest MSR values */
-	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE;
+	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE;
 	/* Process MSR values */
 	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
 	/* External providers the guest reserved */
@@ -433,10 +431,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 static inline int get_fpr_index(int i)
 {
-#ifdef CONFIG_VSX
-	i *= 2;
-#endif
-	return i;
+	return i * TS_FPRWIDTH;
 }
 
 /* Give up external provider (FPU, Altivec, VSX) */
@@ -450,41 +445,49 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 	u64 *thread_fpr = (u64*)t->fpr;
 	int i;
 
-	if (!(vcpu->arch.guest_owned_ext & msr))
+	/*
+	 * VSX instructions can access FP and vector registers, so if
+	 * we are giving up VSX, make sure we give up FP and VMX as well.
+	 */
+	if (msr & MSR_VSX)
+		msr |= MSR_FP | MSR_VEC;
+
+	msr &= vcpu->arch.guest_owned_ext;
+	if (!msr)
 		return;
 
 #ifdef DEBUG_EXT
 	printk(KERN_INFO "Giving up ext 0x%lx\n", msr);
 #endif
 
-	switch (msr) {
-	case MSR_FP:
+	if (msr & MSR_FP) {
+		/*
+		 * Note that on CPUs with VSX, giveup_fpu stores
+		 * both the traditional FP registers and the added VSX
+		 * registers into thread.fpr[].
+		 */
 		giveup_fpu(current);
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
 
 		vcpu->arch.fpscr = t->fpscr.val;
-		break;
-	case MSR_VEC:
+
+#ifdef CONFIG_VSX
+		if (cpu_has_feature(CPU_FTR_VSX))
+			for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
+				vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
+#endif
+	}
+
 #ifdef CONFIG_ALTIVEC
+	if (msr & MSR_VEC) {
 		giveup_altivec(current);
 		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
 		vcpu->arch.vscr = t->vscr;
-#endif
-		break;
-	case MSR_VSX:
-#ifdef CONFIG_VSX
-		__giveup_vsx(current);
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
-			vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
-#endif
-		break;
-	default:
-		BUG();
 	}
+#endif
 
-	vcpu->arch.guest_owned_ext &= ~msr;
-	current->thread.regs->msr &= ~msr;
+	vcpu->arch.guest_owned_ext &= ~(msr | MSR_VSX);
 	kvmppc_recalc_shadow_msr(vcpu);
 }
 
@@ -544,47 +547,56 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 		return RESUME_GUEST;
 	}
 
-	/* We already own the ext */
-	if (vcpu->arch.guest_owned_ext & msr) {
-		return RESUME_GUEST;
+	if (msr == MSR_VSX) {
+		/* No VSX?  Give an illegal instruction interrupt */
+#ifdef CONFIG_VSX
+		if (!cpu_has_feature(CPU_FTR_VSX))
+#endif
+		{
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			return RESUME_GUEST;
+		}
+
+		/*
+		 * We have to load up all the FP and VMX registers before
+		 * we can let the guest use VSX instructions.
+		 */
+		msr = MSR_FP | MSR_VEC | MSR_VSX;
 	}
 
+	/* See if we already own all the ext(s) needed */
+	msr &= ~vcpu->arch.guest_owned_ext;
+	if (!msr)
+		return RESUME_GUEST;
+
 #ifdef DEBUG_EXT
 	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
 #endif
 
 	current->thread.regs->msr |= msr;
 
-	switch (msr) {
-	case MSR_FP:
+	if (msr & MSR_FP) {
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
-
+#ifdef CONFIG_VSX
+		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
+			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
+#endif
 		t->fpscr.val = vcpu->arch.fpscr;
 		t->fpexc_mode = 0;
 		kvmppc_load_up_fpu();
-		break;
-	case MSR_VEC:
+	}
+
+	if (msr & MSR_VEC) {
 #ifdef CONFIG_ALTIVEC
 		memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
 		t->vscr = vcpu->arch.vscr;
 		t->vrsave = -1;
 		kvmppc_load_up_altivec();
 #endif
-		break;
-	case MSR_VSX:
-#ifdef CONFIG_VSX
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
-			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
-		kvmppc_load_up_vsx();
-#endif
-		break;
-	default:
-		BUG();
 	}
 
 	vcpu->arch.guest_owned_ext |= msr;
-
 	kvmppc_recalc_shadow_msr(vcpu);
 
 	return RESUME_GUEST;
@@ -1134,7 +1146,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* Save VSX state in stack */
 	used_vsr = current->thread.used_vsr;
 	if (used_vsr && (current->thread.regs->msr & MSR_VSX))
-			__giveup_vsx(current);
+		__giveup_vsx(current);
 #endif
 
 	/* Remember the MSR with disabled extensions */
@@ -1151,14 +1163,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* 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;
-
 	/* Make sure we save the guest FPU/Altivec/VSX state */
-	kvmppc_giveup_ext(vcpu, MSR_FP);
-	kvmppc_giveup_ext(vcpu, MSR_VEC);
-	kvmppc_giveup_ext(vcpu, MSR_VSX);
+	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
+
+	current->thread.regs->msr = ext_msr;
 
-	/* Restore FPU state from stack */
+	/* Restore FPU/VSX state from stack */
 	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
 	current->thread.fpscr.val = fpscr;
 	current->thread.fpexc_mode = fpexc_mode;

arch/powerpc/kvm/book3s_rmhandlers.S

@@ -234,8 +234,5 @@ define_load_up(fpu)
 #ifdef CONFIG_ALTIVEC
 define_load_up(altivec)
 #endif
-#ifdef CONFIG_VSX
-define_load_up(vsx)
-#endif
 
 #include "book3s_segment.S"

arch/powerpc/kvm/booke.c

@@ -36,6 +36,7 @@
 #include <asm/dbell.h>
 #include <asm/hw_irq.h>
 #include <asm/irq.h>
+#include <asm/time.h>
 
 #include "timing.h"
 #include "booke.h"
@@ -311,6 +312,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	bool crit;
 	bool keep_irq = false;
 	enum int_class int_class;
+	ulong new_msr = vcpu->arch.shared->msr;
 
 	/* Truncate crit indicators in 32 bit mode */
 	if (!(vcpu->arch.shared->msr & MSR_SF)) {
@@ -406,7 +408,13 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 			set_guest_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
 			set_guest_dear(vcpu, vcpu->arch.queued_dear);
-		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
+
+		new_msr &= msr_mask;
+#if defined(CONFIG_64BIT)
+		if (vcpu->arch.epcr & SPRN_EPCR_ICM)
+			new_msr |= MSR_CM;
+#endif
+		kvmppc_set_msr(vcpu, new_msr);
 
 		if (!keep_irq)
 			clear_bit(priority, &vcpu->arch.pending_exceptions);
@@ -1380,6 +1388,11 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				 &vcpu->arch.dbg_reg.dac[dac], sizeof(u64));
 		break;
 	}
+#if defined(CONFIG_64BIT)
+	case KVM_REG_PPC_EPCR:
+		r = put_user(vcpu->arch.epcr, (u32 __user *)(long)reg->addr);
+		break;
+#endif
 	default:
 		break;
 	}
@@ -1407,6 +1420,15 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			     (u64 __user *)(long)reg->addr, sizeof(u64));
 		break;
 	}
+#if defined(CONFIG_64BIT)
+	case KVM_REG_PPC_EPCR: {
+		u32 new_epcr;
+		r = get_user(new_epcr, (u32 __user *)(long)reg->addr);
+		if (r == 0)
+			kvmppc_set_epcr(vcpu, new_epcr);
+		break;
+	}
+#endif
 	default:
 		break;
 	}
@@ -1465,6 +1487,18 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
+void kvmppc_set_epcr(struct kvm_vcpu *vcpu, u32 new_epcr)
+{
+#if defined(CONFIG_64BIT)
+	vcpu->arch.epcr = new_epcr;
+#ifdef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_epcr &= ~SPRN_EPCR_GICM;
+	if (vcpu->arch.epcr  & SPRN_EPCR_ICM)
+		vcpu->arch.shadow_epcr |= SPRN_EPCR_GICM;
+#endif
+#endif
+}
+
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
 {
 	vcpu->arch.tcr = new_tcr;

arch/powerpc/kvm/booke.h

@@ -69,6 +69,7 @@ extern unsigned long kvmppc_booke_handlers;
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr);
 void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr);
 
+void kvmppc_set_epcr(struct kvm_vcpu *vcpu, u32 new_epcr);
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr);
 void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
 void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);

arch/powerpc/kvm/booke_emulate.c

@@ -240,7 +240,14 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_MCSR:
 		vcpu->arch.mcsr &= ~spr_val;
 		break;
-
+#if defined(CONFIG_64BIT)
+	case SPRN_EPCR:
+		kvmppc_set_epcr(vcpu, spr_val);
+#ifdef CONFIG_KVM_BOOKE_HV
+		mtspr(SPRN_EPCR, vcpu->arch.shadow_epcr);
+#endif
+		break;
+#endif
 	default:
 		emulated = EMULATE_FAIL;
 	}
@@ -335,6 +342,11 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_MCSR:
 		*spr_val = vcpu->arch.mcsr;
 		break;
+#if defined(CONFIG_64BIT)
+	case SPRN_EPCR:
+		*spr_val = vcpu->arch.epcr;
+		break;
+#endif
 
 	default:
 		emulated = EMULATE_FAIL;

arch/powerpc/kvm/bookehv_interrupts.S

@@ -16,6 +16,7 @@
  *
  * Author: Varun Sethi <varun.sethi@freescale.com>
  * Author: Scott Wood <scotwood@freescale.com>
+ * Author: Mihai Caraman <mihai.caraman@freescale.com>
  *
  * This file is derived from arch/powerpc/kvm/booke_interrupts.S
  */
@@ -30,31 +31,33 @@
 #include <asm/bitsperlong.h>
 #include <asm/thread_info.h>
 
+#ifdef CONFIG_64BIT
+#include <asm/exception-64e.h>
+#else
 #include "../kernel/head_booke.h" /* for THREAD_NORMSAVE() */
-
-#define GET_VCPU(vcpu, thread)	\
-	PPC_LL	vcpu, THREAD_KVM_VCPU(thread)
+#endif
 
 #define LONGBYTES		(BITS_PER_LONG / 8)
 
 #define VCPU_GUEST_SPRG(n)	(VCPU_GUEST_SPRGS + (n * LONGBYTES))
 
 /* The host stack layout: */
-#define HOST_R1         (0 * LONGBYTES) /* Implied by stwu. */
-#define HOST_CALLEE_LR  (1 * LONGBYTES)
-#define HOST_RUN        (2 * LONGBYTES) /* struct kvm_run */
+#define HOST_R1         0 /* Implied by stwu. */
+#define HOST_CALLEE_LR  PPC_LR_STKOFF
+#define HOST_RUN        (HOST_CALLEE_LR + LONGBYTES)
 /*
  * r2 is special: it holds 'current', and it made nonvolatile in the
  * kernel with the -ffixed-r2 gcc option.
  */
-#define HOST_R2         (3 * LONGBYTES)
-#define HOST_CR         (4 * LONGBYTES)
-#define HOST_NV_GPRS    (5 * LONGBYTES)
+#define HOST_R2         (HOST_RUN + LONGBYTES)
+#define HOST_CR         (HOST_R2 + LONGBYTES)
+#define HOST_NV_GPRS    (HOST_CR + LONGBYTES)
 #define __HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * LONGBYTES))
 #define HOST_NV_GPR(n)  __HOST_NV_GPR(__REG_##n)
 #define HOST_MIN_STACK_SIZE (HOST_NV_GPR(R31) + LONGBYTES)
 #define HOST_STACK_SIZE ((HOST_MIN_STACK_SIZE + 15) & ~15) /* Align. */
-#define HOST_STACK_LR   (HOST_STACK_SIZE + LONGBYTES) /* In caller stack frame. */
+/* LR in caller stack frame. */
+#define HOST_STACK_LR	(HOST_STACK_SIZE + PPC_LR_STKOFF)
 
 #define NEED_EMU		0x00000001 /* emulation -- save nv regs */
 #define NEED_DEAR		0x00000002 /* save faulting DEAR */
@@ -201,12 +204,128 @@
 	b	kvmppc_resume_host
 .endm
 
+#ifdef CONFIG_64BIT
+/* Exception types */
+#define EX_GEN			1
+#define EX_GDBELL		2
+#define EX_DBG			3
+#define EX_MC			4
+#define EX_CRIT			5
+#define EX_TLB			6
+
+/*
+ * For input register values, see arch/powerpc/include/asm/kvm_booke_hv_asm.h
+ */
+.macro kvm_handler intno type scratch, paca_ex, ex_r10, ex_r11, srr0, srr1, flags
+ _GLOBAL(kvmppc_handler_\intno\()_\srr1)
+	mr	r11, r4
+	/*
+	 * Get vcpu from Paca: paca->__current.thread->kvm_vcpu
+	 */
+	PPC_LL	r4, PACACURRENT(r13)
+	PPC_LL	r4, (THREAD + THREAD_KVM_VCPU)(r4)
+	stw	r10, VCPU_CR(r4)
+	PPC_STL r11, VCPU_GPR(R4)(r4)
+	PPC_STL	r5, VCPU_GPR(R5)(r4)
+	.if \type == EX_CRIT
+	PPC_LL	r5, (\paca_ex + EX_R13)(r13)
+	.else
+	mfspr	r5, \scratch
+	.endif
+	PPC_STL	r6, VCPU_GPR(R6)(r4)
+	PPC_STL	r8, VCPU_GPR(R8)(r4)
+	PPC_STL	r9, VCPU_GPR(R9)(r4)
+	PPC_STL r5, VCPU_GPR(R13)(r4)
+	PPC_LL	r6, (\paca_ex + \ex_r10)(r13)
+	PPC_LL	r8, (\paca_ex + \ex_r11)(r13)
+	PPC_STL r3, VCPU_GPR(R3)(r4)
+	PPC_STL r7, VCPU_GPR(R7)(r4)
+	PPC_STL r12, VCPU_GPR(R12)(r4)
+	PPC_STL r6, VCPU_GPR(R10)(r4)
+	PPC_STL r8, VCPU_GPR(R11)(r4)
+	mfctr	r5
+	PPC_STL	r5, VCPU_CTR(r4)
+	mfspr	r5, \srr0
+	mfspr	r6, \srr1
+	kvm_handler_common \intno, \srr0, \flags
+.endm
+
+#define EX_PARAMS(type) \
+	EX_##type, \
+	SPRN_SPRG_##type##_SCRATCH, \
+	PACA_EX##type, \
+	EX_R10, \
+	EX_R11
+
+#define EX_PARAMS_TLB \
+	EX_TLB, \
+	SPRN_SPRG_GEN_SCRATCH, \
+	PACA_EXTLB, \
+	EX_TLB_R10, \
+	EX_TLB_R11
+
+kvm_handler BOOKE_INTERRUPT_CRITICAL, EX_PARAMS(CRIT), \
+	SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_MACHINE_CHECK, EX_PARAMS(MC), \
+	SPRN_MCSRR0, SPRN_MCSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1,(NEED_EMU | NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_INST_STORAGE, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, NEED_ESR
+kvm_handler BOOKE_INTERRUPT_EXTERNAL, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_ALIGNMENT, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1,(NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_PROGRAM, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1,NEED_ESR
+kvm_handler BOOKE_INTERRUPT_FP_UNAVAIL, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_AP_UNAVAIL, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DECREMENTER, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_FIT, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_WATCHDOG, EX_PARAMS(CRIT),\
+	SPRN_CSRR0, SPRN_CSRR1, 0
+/*
+ * Only bolted TLB miss exception handlers are supported for now
+ */
+kvm_handler BOOKE_INTERRUPT_DTLB_MISS, EX_PARAMS_TLB, \
+	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_ITLB_MISS, EX_PARAMS_TLB, \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_UNAVAIL, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_FP_DATA, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_FP_ROUND, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_PERFORMANCE_MONITOR, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DOORBELL, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DOORBELL_CRITICAL, EX_PARAMS(CRIT), \
+	SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_HV_PRIV, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, NEED_EMU
+kvm_handler BOOKE_INTERRUPT_HV_SYSCALL, EX_PARAMS(GEN), \
+	SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_GUEST_DBELL, EX_PARAMS(GDBELL), \
+	SPRN_GSRR0, SPRN_GSRR1, 0
+kvm_handler BOOKE_INTERRUPT_GUEST_DBELL_CRIT, EX_PARAMS(CRIT), \
+	SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DEBUG, EX_PARAMS(DBG), \
+	SPRN_DSRR0, SPRN_DSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DEBUG, EX_PARAMS(CRIT), \
+	SPRN_CSRR0, SPRN_CSRR1, 0
+#else
 /*
  * For input register values, see arch/powerpc/include/asm/kvm_booke_hv_asm.h
  */
 .macro kvm_handler intno srr0, srr1, flags
 _GLOBAL(kvmppc_handler_\intno\()_\srr1)
-	GET_VCPU(r11, r10)
+	PPC_LL	r11, THREAD_KVM_VCPU(r10)
 	PPC_STL r3, VCPU_GPR(R3)(r11)
 	mfspr	r3, SPRN_SPRG_RSCRATCH0
 	PPC_STL	r4, VCPU_GPR(R4)(r11)
@@ -233,7 +352,7 @@ _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 .macro kvm_lvl_handler intno scratch srr0, srr1, flags
 _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 	mfspr	r10, SPRN_SPRG_THREAD
-	GET_VCPU(r11, r10)
+	PPC_LL	r11, THREAD_KVM_VCPU(r10)
 	PPC_STL r3, VCPU_GPR(R3)(r11)
 	mfspr	r3, \scratch
 	PPC_STL	r4, VCPU_GPR(R4)(r11)
@@ -295,7 +414,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
 	SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
 kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
 	SPRN_SPRG_RSCRATCH_DBG, SPRN_DSRR0, SPRN_DSRR1, 0
-
+#endif
 
 /* Registers:
  *  SPRG_SCRATCH0: guest r10

arch/powerpc/kvm/e500.h

@@ -129,9 +129,9 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500,
 				ulong value);
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu);
 int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu);
-int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb);
-int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int rt, int ra, int rb);
-int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb);
+int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, gva_t ea);
+int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int type, gva_t ea);
+int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, gva_t ea);
 int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500);
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
 
@@ -154,7 +154,7 @@ get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
 
 static inline gva_t get_tlb_eaddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
-	return tlbe->mas2 & 0xfffff000;
+	return tlbe->mas2 & MAS2_EPN;
 }
 
 static inline u64 get_tlb_bytes(const struct kvm_book3e_206_tlb_entry *tlbe)

arch/powerpc/kvm/e500_emulate.c

@@ -89,6 +89,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	int ra = get_ra(inst);
 	int rb = get_rb(inst);
 	int rt = get_rt(inst);
+	gva_t ea;
 
 	switch (get_op(inst)) {
 	case 31:
@@ -113,15 +114,20 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_TLBSX:
-			emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
+			ea = kvmppc_get_ea_indexed(vcpu, ra, rb);
+			emulated = kvmppc_e500_emul_tlbsx(vcpu, ea);
 			break;
 
-		case XOP_TLBILX:
-			emulated = kvmppc_e500_emul_tlbilx(vcpu, rt, ra, rb);
+		case XOP_TLBILX: {
+			int type = rt & 0x3;
+			ea = kvmppc_get_ea_indexed(vcpu, ra, rb);
+			emulated = kvmppc_e500_emul_tlbilx(vcpu, type, ea);
 			break;
+		}
 
 		case XOP_TLBIVAX:
-			emulated = kvmppc_e500_emul_tlbivax(vcpu, ra, rb);
+			ea = kvmppc_get_ea_indexed(vcpu, ra, rb);
+			emulated = kvmppc_e500_emul_tlbivax(vcpu, ea);
 			break;
 
 		default:

arch/powerpc/kvm/e500_tlb.c

@@ -415,7 +415,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	struct tlbe_ref *ref)
 {
 	struct kvm_memory_slot *slot;
-	unsigned long pfn, hva;
+	unsigned long pfn = 0; /* silence GCC warning */
+	unsigned long hva;
 	int pfnmap = 0;
 	int tsize = BOOK3E_PAGESZ_4K;
 
@@ -688,14 +689,11 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
 	return EMULATE_DONE;
 }
 
-int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
+int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, gva_t ea)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	unsigned int ia;
 	int esel, tlbsel;
-	gva_t ea;
-
-	ea = ((ra) ? kvmppc_get_gpr(vcpu, ra) : 0) + kvmppc_get_gpr(vcpu, rb);
 
 	ia = (ea >> 2) & 0x1;
 
@@ -722,7 +720,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 }
 
 static void tlbilx_all(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
-		       int pid, int rt)
+		       int pid, int type)
 {
 	struct kvm_book3e_206_tlb_entry *tlbe;
 	int tid, esel;
@@ -731,7 +729,7 @@ static void tlbilx_all(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 	for (esel = 0; esel < vcpu_e500->gtlb_params[tlbsel].entries; esel++) {
 		tlbe = get_entry(vcpu_e500, tlbsel, esel);
 		tid = get_tlb_tid(tlbe);
-		if (rt == 0 || tid == pid) {
+		if (type == 0 || tid == pid) {
 			inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
 		}
@@ -739,14 +737,9 @@ static void tlbilx_all(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 }
 
 static void tlbilx_one(struct kvmppc_vcpu_e500 *vcpu_e500, int pid,
-		       int ra, int rb)
+		       gva_t ea)
 {
 	int tlbsel, esel;
-	gva_t ea;
-
-	ea = kvmppc_get_gpr(&vcpu_e500->vcpu, rb);
-	if (ra)
-		ea += kvmppc_get_gpr(&vcpu_e500->vcpu, ra);
 
 	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
 		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, -1);
@@ -758,16 +751,16 @@ static void tlbilx_one(struct kvmppc_vcpu_e500 *vcpu_e500, int pid,
 	}
 }
 
-int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int rt, int ra, int rb)
+int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int type, gva_t ea)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int pid = get_cur_spid(vcpu);
 
-	if (rt == 0 || rt == 1) {
-		tlbilx_all(vcpu_e500, 0, pid, rt);
-		tlbilx_all(vcpu_e500, 1, pid, rt);
-	} else if (rt == 3) {
-		tlbilx_one(vcpu_e500, pid, ra, rb);
+	if (type == 0 || type == 1) {
+		tlbilx_all(vcpu_e500, 0, pid, type);
+		tlbilx_all(vcpu_e500, 1, pid, type);
+	} else if (type == 3) {
+		tlbilx_one(vcpu_e500, pid, ea);
 	}
 
 	return EMULATE_DONE;
@@ -792,16 +785,13 @@ int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
-int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
+int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, gva_t ea)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int as = !!get_cur_sas(vcpu);
 	unsigned int pid = get_cur_spid(vcpu);
 	int esel, tlbsel;
 	struct kvm_book3e_206_tlb_entry *gtlbe = NULL;
-	gva_t ea;
-
-	ea = kvmppc_get_gpr(vcpu, rb);
 
 	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
 		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
@@ -881,6 +871,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 
 	gtlbe->mas1 = vcpu->arch.shared->mas1;
 	gtlbe->mas2 = vcpu->arch.shared->mas2;
+	if (!(vcpu->arch.shared->msr & MSR_CM))
+		gtlbe->mas2 &= 0xffffffffUL;
 	gtlbe->mas7_3 = vcpu->arch.shared->mas7_3;
 
 	trace_kvm_booke206_gtlb_write(vcpu->arch.shared->mas0, gtlbe->mas1,

arch/powerpc/kvm/powerpc.c

@@ -314,6 +314,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_IRQ_LEVEL:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_ONE_REG:
+	case KVM_CAP_IOEVENTFD:
 		r = 1;
 		break;
 #ifndef CONFIG_KVM_BOOK3S_64_HV
@@ -353,6 +354,12 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 1;
 #else
 		r = 0;
+		break;
+#endif
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_CAP_PPC_HTAB_FD:
+		r = 1;
+		break;
 #endif
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -618,6 +625,13 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	vcpu->mmio_is_write = 0;
 	vcpu->arch.mmio_sign_extend = 0;
 
+	if (!kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr,
+			     bytes, &run->mmio.data)) {
+		kvmppc_complete_mmio_load(vcpu, run);
+		vcpu->mmio_needed = 0;
+		return EMULATE_DONE;
+	}
+
 	return EMULATE_DO_MMIO;
 }
 
@@ -627,8 +641,8 @@ int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
 {
 	int r;
 
-	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian);
 	vcpu->arch.mmio_sign_extend = 1;
+	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian);
 
 	return r;
 }
@@ -666,6 +680,13 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		}
 	}
 
+	if (!kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr,
+			      bytes, &run->mmio.data)) {
+		kvmppc_complete_mmio_load(vcpu, run);
+		vcpu->mmio_needed = 0;
+		return EMULATE_DONE;
+	}
+
 	return EMULATE_DO_MMIO;
 }
 
@@ -939,6 +960,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+
+	case KVM_PPC_GET_HTAB_FD: {
+		struct kvm *kvm = filp->private_data;
+		struct kvm_get_htab_fd ghf;
+
+		r = -EFAULT;
+		if (copy_from_user(&ghf, argp, sizeof(ghf)))
+			break;
+		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
+		break;
+	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #ifdef CONFIG_PPC_BOOK3S_64

include/linux/kvm_host.h

@@ -901,10 +901,20 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 #ifdef CONFIG_HAVE_KVM_EVENTFD
 
 void kvm_eventfd_init(struct kvm *kvm);
+int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
+
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
-int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
+#else
+static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	return -EINVAL;
+}
+
+static inline void kvm_irqfd_release(struct kvm *kvm) {}
+#endif
 
 #else
 

include/uapi/linux/kvm.h

@@ -634,6 +634,7 @@ struct kvm_ppc_smmu_info {
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_HTAB_FD 84
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -859,6 +860,8 @@ struct kvm_s390_ucas_mapping {
 #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_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD	  _IOW(KVMIO,  0xaa, struct kvm_get_htab_fd)
 
 /*
  * ioctls for vcpu fds

virt/kvm/eventfd.c

@@ -35,6 +35,7 @@
 
 #include "iodev.h"
 
+#ifdef __KVM_HAVE_IOAPIC
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -425,17 +426,21 @@ fail:
 	kfree(irqfd);
 	return ret;
 }
+#endif
 
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
+#ifdef __KVM_HAVE_IOAPIC
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
 	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
+#ifdef __KVM_HAVE_IOAPIC
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -555,6 +560,7 @@ static void __exit irqfd_module_exit(void)
 
 module_init(irqfd_module_init);
 module_exit(irqfd_module_exit);
+#endif
 
 /*
  * --------------------------------------------------------------------