Merge branch 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Avi Kivity:
 "Changes include timekeeping improvements, support for assigning host
  PCI devices that share interrupt lines, s390 user-controlled guests, a
  large ppc update, and random fixes."

This is with the sign-off's fixed, hopefully next merge window we won't
have rebased commits.

* 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: Convert intx_mask_lock to spin lock
  KVM: x86: fix kvm_write_tsc() TSC matching thinko
  x86: kvmclock: abstract save/restore sched_clock_state
  KVM: nVMX: Fix erroneous exception bitmap check
  KVM: Ignore the writes to MSR_K7_HWCR(3)
  KVM: MMU: make use of ->root_level in reset_rsvds_bits_mask
  KVM: PMU: add proper support for fixed counter 2
  KVM: PMU: Fix raw event check
  KVM: PMU: warn when pin control is set in eventsel msr
  KVM: VMX: Fix delayed load of shared MSRs
  KVM: use correct tlbs dirty type in cmpxchg
  KVM: Allow host IRQ sharing for assigned PCI 2.3 devices
  KVM: Ensure all vcpus are consistent with in-kernel irqchip settings
  KVM: x86 emulator: Allow PM/VM86 switch during task switch
  KVM: SVM: Fix CPL updates
  KVM: x86 emulator: VM86 segments must have DPL 3
  KVM: x86 emulator: Fix task switch privilege checks
  arch/powerpc/kvm/book3s_hv.c: included linux/sched.h twice
  KVM: x86 emulator: correctly mask pmc index bits in RDPMC instruction emulation
  KVM: mmu_notifier: Flush TLBs before releasing mmu_lock
  ...

76 files changed, 5173 insertions, 1495 deletions

diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index bc90c75adf6..b9f82c84f09 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -261,4 +261,8 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #endif
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 2689ee54a1c..e35b3a84a40 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -459,6 +459,9 @@ struct kvm_sal_data {
 	unsigned long boot_gp;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch {
 	spinlock_t dirty_log_lock;
 
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 40505200249..f5104b7c52c 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -809,10 +809,13 @@ static void kvm_build_io_pmt(struct kvm *kvm)
 #define GUEST_PHYSICAL_RR4	0x2739
 #define VMM_INIT_RR		0x1660
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	BUG_ON(!kvm);
 
+	if (type)
+		return -EINVAL;
+
 	kvm->arch.is_sn2 = ia64_platform_is("sn2");
 
 	kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;
@@ -1169,6 +1172,11 @@ out:
 
 #define PALE_RESET_ENTRY    0x80000000ffffffb0UL
 
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+	return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu *v;
@@ -1563,6 +1571,21 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f7727d91ac6..b921c3f4892 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -265,12 +265,9 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
-#define KVM_REG_MASK		0x001f
-#define KVM_REG_EXT_MASK	0xffe0
-#define KVM_REG_GPR		0x0000
-#define KVM_REG_FPR		0x0020
-#define KVM_REG_QPR		0x0040
-#define KVM_REG_FQPR		0x0060
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
 
 #define KVM_INTERRUPT_SET	-1U
 #define KVM_INTERRUPT_UNSET	-2U
@@ -292,4 +289,41 @@ struct kvm_allocate_rma {
 	__u64 rma_size;
 };
 
+struct kvm_book3e_206_tlb_entry {
+	__u32 mas8;
+	__u32 mas1;
+	__u64 mas2;
+	__u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+	/*
+	 * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+	 *
+	 * - The number of ways of TLB0 must be a power of two between 2 and
+	 *   16.
+	 * - TLB1 must be fully associative.
+	 * - The size of TLB0 must be a multiple of the number of ways, and
+	 *   the number of sets must be a power of two.
+	 * - The size of TLB1 may not exceed 64 entries.
+	 * - TLB0 supports 4 KiB pages.
+	 * - The page sizes supported by TLB1 are as indicated by
+	 *   TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+	 *   as returned by KVM_GET_SREGS.
+	 * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+	 *   and tlb_ways[] must be zero.
+	 *
+	 * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+	 *
+	 * KVM will adjust TLBnCFG based on the sizes configured here,
+	 * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+	 * set to zero.
+	 */
+	__u32 tlb_sizes[4];
+	__u32 tlb_ways[4];
+	__u32 reserved[8];
+};
+
+#define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 69c7377d207..aa795ccef29 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -90,6 +90,8 @@ struct kvmppc_vcpu_book3s {
 #endif
 	int context_id[SID_CONTEXTS];
 
+	bool hior_explicit;		/* HIOR is set by ioctl, not PVR */
+
 	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
 	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
@@ -119,6 +121,11 @@ extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
+extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run,
+			struct kvm_vcpu *vcpu, unsigned long addr,
+			unsigned long status);
+extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr,
+			unsigned long slb_v, unsigned long valid);
 
 extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
@@ -138,6 +145,21 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
+			unsigned long *rmap, long pte_index, int realmode);
+extern void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
+			unsigned long pte_index);
+void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
+			unsigned long pte_index);
+extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr,
+			unsigned long *nb_ret);
+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_hv_get_dirty_log(struct kvm *kvm,
+			struct kvm_memory_slot *memslot);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
@@ -183,7 +205,9 @@ static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
 	if ( num < 14 ) {
-		to_svcpu(vcpu)->gpr[num] = val;
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		svcpu->gpr[num] = val;
+		svcpu_put(svcpu);
 		to_book3s(vcpu)->shadow_vcpu->gpr[num] = val;
 	} else
 		vcpu->arch.gpr[num] = val;
@@ -191,80 +215,120 @@ static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-	if ( num < 14 )
-		return to_svcpu(vcpu)->gpr[num];
-	else
+	if ( num < 14 ) {
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		ulong r = svcpu->gpr[num];
+		svcpu_put(svcpu);
+		return r;
+	} else
 		return vcpu->arch.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-	to_svcpu(vcpu)->cr = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->cr = val;
+	svcpu_put(svcpu);
 	to_book3s(vcpu)->shadow_vcpu->cr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->cr;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+	r = svcpu->cr;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
 {
-	to_svcpu(vcpu)->xer = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->xer = val;
 	to_book3s(vcpu)->shadow_vcpu->xer = val;
+	svcpu_put(svcpu);
 }
 
 static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->xer;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+	r = svcpu->xer;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
-	to_svcpu(vcpu)->ctr = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->ctr = val;
+	svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->ctr;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->ctr;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
-	to_svcpu(vcpu)->lr = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->lr = val;
+	svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->lr;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->lr;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
-	to_svcpu(vcpu)->pc = val;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	svcpu->pc = val;
+	svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->pc;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->pc;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 {
 	ulong pc = kvmppc_get_pc(vcpu);
-	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
 
 	/* Load the instruction manually if it failed to do so in the
 	 * exit path */
 	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
 		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
 
-	return svcpu->last_inst;
+	r = svcpu->last_inst;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
-	return to_svcpu(vcpu)->fault_dar;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	ulong r;
+	r = svcpu->fault_dar;
+	svcpu_put(svcpu);
+	return r;
 }
 
 static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h
index de604db135f..38040ff8206 100644
--- a/arch/powerpc/include/asm/kvm_book3s_32.h
+++ b/arch/powerpc/include/asm/kvm_book3s_32.h
@@ -20,11 +20,15 @@
 #ifndef __ASM_KVM_BOOK3S_32_H__
 #define __ASM_KVM_BOOK3S_32_H__
 
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
 	return to_book3s(vcpu)->shadow_vcpu;
 }
 
+static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+}
+
 #define PTE_SIZE	12
 #define VSID_ALL	0
 #define SR_INVALID	0x00000001	/* VSID 1 should always be unused */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d0ac94f98f9..b0c08b14277 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -21,14 +21,56 @@
 #define __ASM_KVM_BOOK3S_64_H__
 
 #ifdef CONFIG_KVM_BOOK3S_PR
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
+	preempt_disable();
 	return &get_paca()->shadow_vcpu;
 }
+
+static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+	preempt_enable();
+}
 #endif
 
 #define SPAPR_TCE_SHIFT		12
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+/* For now use fixed-size 16MB page table */
+#define HPT_ORDER	24
+#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
+#define HPT_NPTE	(HPT_NPTEG << 3)		/* 8 PTEs per PTEG */
+#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+#endif
+
+#define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
+
+/*
+ * We use a lock bit in HPTE dword 0 to synchronize updates and
+ * accesses to each HPTE, and another bit to indicate non-present
+ * HPTEs.
+ */
+#define HPTE_V_HVLOCK	0x40UL
+#define HPTE_V_ABSENT	0x20UL
+
+static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
+{
+	unsigned long tmp, old;
+
+	asm volatile("	ldarx	%0,0,%2\n"
+		     "	and.	%1,%0,%3\n"
+		     "	bne	2f\n"
+		     "	ori	%0,%0,%4\n"
+		     "  stdcx.	%0,0,%2\n"
+		     "	beq+	2f\n"
+		     "	li	%1,%3\n"
+		     "2:	isync"
+		     : "=&r" (tmp), "=&r" (old)
+		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
+		     : "cc", "memory");
+	return old == 0;
+}
+
 static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 					     unsigned long pte_index)
 {
@@ -62,4 +104,140 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	/* only handle 4k, 64k and 16M pages for now */
+	if (!(h & HPTE_V_LARGE))
+		return 1ul << 12;		/* 4k page */
+	if ((l & 0xf000) == 0x1000 && cpu_has_feature(CPU_FTR_ARCH_206))
+		return 1ul << 16;		/* 64k page */
+	if ((l & 0xff000) == 0)
+		return 1ul << 24;		/* 16M page */
+	return 0;				/* error */
+}
+
+static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
+{
+	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
+}
+
+static inline int hpte_is_writable(unsigned long ptel)
+{
+	unsigned long pp = ptel & (HPTE_R_PP0 | HPTE_R_PP);
+
+	return pp != PP_RXRX && pp != PP_RXXX;
+}
+
+static inline unsigned long hpte_make_readonly(unsigned long ptel)
+{
+	if ((ptel & HPTE_R_PP0) || (ptel & HPTE_R_PP) == PP_RWXX)
+		ptel = (ptel & ~HPTE_R_PP) | PP_RXXX;
+	else
+		ptel |= PP_RXRX;
+	return pte