Merge tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights include
  - full big real mode emulation on pre-Westmere Intel hosts (can be
    disabled with emulate_invalid_guest_state=0)
  - relatively small ppc and s390 updates
  - PCID/INVPCID support in guests
  - EOI avoidance; 3.6 guests should perform better on 3.6 hosts on
    interrupt intensive workloads)
  - Lockless write faults during live migration
  - EPT accessed/dirty bits support for new Intel processors"

Fix up conflicts in:
 - Documentation/virtual/kvm/api.txt:

   Stupid subchapter numbering, added next to each other.

 - arch/powerpc/kvm/booke_interrupts.S:

   PPC asm changes clashing with the KVM fixes

 - arch/s390/include/asm/sigp.h, arch/s390/kvm/sigp.c:

   Duplicated commits through the kvm tree and the s390 tree, with
   subsequent edits in the KVM tree.

* tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  KVM: fix race with level interrupts
  x86, hyper: fix build with !CONFIG_KVM_GUEST
  Revert "apic: fix kvm build on UP without IOAPIC"
  KVM guest: switch to apic_set_eoi_write, apic_write
  apic: add apic_set_eoi_write for PV use
  KVM: VMX: Implement PCID/INVPCID for guests with EPT
  KVM: Add x86_hyper_kvm to complete detect_hypervisor_platform check
  KVM: PPC: Critical interrupt emulation support
  KVM: PPC: e500mc: Fix tlbilx emulation for 64-bit guests
  KVM: PPC64: booke: Set interrupt computation mode for 64-bit host
  KVM: PPC: bookehv: Add ESR flag to Data Storage Interrupt
  KVM: PPC: bookehv64: Add support for std/ld emulation.
  booke: Added crit/mc exception handler for e500v2
  booke/bookehv: Add host crit-watchdog exception support
  KVM: MMU: document mmu-lock and fast page fault
  KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint
  KVM: MMU: trace fast page fault
  KVM: MMU: fast path of handling guest page fault
  KVM: MMU: introduce SPTE_MMU_WRITEABLE bit
  KVM: MMU: fold tlb flush judgement into mmu_spte_update
  ...

9 files changed, 59 insertions, 5 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 88093c1d44f..3ea51a84a0e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -465,6 +465,8 @@ static inline u32 safe_apic_wait_icr_idle(void)
 	return apic->safe_wait_icr_idle();
 }
 
+extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v));
+
 #else /* CONFIG_X86_LOCAL_APIC */
 
 static inline u32 apic_read(u32 reg) { return 0; }
@@ -474,6 +476,7 @@ static inline u64 apic_icr_read(void) { return 0; }
 static inline void apic_icr_write(u32 low, u32 high) { }
 static inline void apic_wait_icr_idle(void) { }
 static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {}
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index a6983b27722..72f5009deb5 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -264,6 +264,13 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
  * This operation is non-atomic and can be reordered.
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
+ *
+ * Note: the operation is performed atomically with respect to
+ * the local CPU, but not other CPUs. Portable code should not
+ * rely on this behaviour.
+ * KVM relies on this behaviour on x86 for modifying memory that is also
+ * accessed from a hypervisor on the same CPU if running in a VM: don't change
+ * this without also updating arch/x86/kernel/kvm.c
  */
 static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 7a15153c675..b518c750993 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -49,6 +49,7 @@ extern const struct hypervisor_x86 *x86_hyper;
 extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
 extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+extern const struct hypervisor_x86 x86_hyper_kvm;
 
 static inline bool hypervisor_x2apic_available(void)
 {
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index e7d1c194d27..246617efd67 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -12,6 +12,7 @@
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_PIT
 #define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_DEVICE_ASSIGNMENT
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 1ac46c22dd5..c764f43b71c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -192,8 +192,8 @@ struct x86_emulate_ops {
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
 
-	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
-			 u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -280,9 +280,9 @@ struct x86_emulate_ctxt {
 	u8 modrm_seg;
 	bool rip_relative;
 	unsigned long _eip;
+	struct operand memop;
 	/* Fields above regs are cleared together. */
 	unsigned long regs[NR_VCPU_REGS];
-	struct operand memop;
 	struct operand *memopp;
 	struct fetch_cache fetch;
 	struct read_cache io_read;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2da88c0cda1..09155d64cf7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -48,12 +48,13 @@
 
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
+#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
 				  0xFFFFFF0000000000ULL)
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
-			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR  \
+			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_RDWRGSFS \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
 
@@ -175,6 +176,13 @@ enum {
 
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
+/*
+ * The following bit is set with PV-EOI, unset on EOI.
+ * We detect PV-EOI changes by guest by comparing
+ * this bit with PV-EOI in guest memory.
+ * See the implementation in apic_update_pv_eoi.
+ */
+#define KVM_APIC_PV_EOI_PENDING	1
 
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
@@ -484,6 +492,11 @@ struct kvm_vcpu_arch {
 		u64 length;
 		u64 status;
 	} osvw;
+
+	struct {
+		u64 msr_val;
+		struct gfn_to_hva_cache data;
+	} pv_eoi;
 };
 
 struct kvm_lpage_info {
@@ -661,6 +674,7 @@ struct kvm_x86_ops {
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
+	bool (*invpcid_supported)(void);
 	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host);
 
 	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -802,7 +816,20 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
-int kvm_pic_set_irq(void *opaque, int irq, int level);
+static inline int __kvm_irq_line_state(unsigned long *irq_state,
+				       int irq_source_id, int level)
+{
+	/* Logical OR for level trig interrupt */
+	if (level)
+		__set_bit(irq_source_id, irq_state);
+	else
+		__clear_bit(irq_source_id, irq_state);
+
+	return !!(*irq_state);
+}
+
+int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
+void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 63ab1661d00..2f7712e08b1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -22,6 +22,7 @@
 #define KVM_FEATURE_CLOCKSOURCE2        3
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
+#define KVM_FEATURE_PV_EOI		6
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -37,6 +38,7 @@
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 #define MSR_KVM_STEAL_TIME  0x4b564d03
+#define MSR_KVM_PV_EOI_EN      0x4b564d04
 
 struct kvm_steal_time {
 	__u64 steal;
@@ -89,6 +91,11 @@ struct kvm_vcpu_pv_apf_data {
 	__u32 enabled;
 };
 
+#define KVM_PV_EOI_BIT 0
+#define KVM_PV_EOI_MASK (0x1 << KVM_PV_EOI_BIT)
+#define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
+#define KVM_PV_EOI_DISABLED 0x0
+
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index f8ab3eaad12..aea1d1d848c 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -44,6 +44,7 @@
  */
 #define X86_CR3_PWT	0x00000008 /* Page Write Through */
 #define X86_CR3_PCD	0x00000010 /* Page Cache Disable */
+#define X86_CR3_PCID_MASK 0x00000fff /* PCID Mask */
 
 /*
  * Intel CPU features in CR4
@@ -61,6 +62,7 @@
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
 #define X86_CR4_RDWRGSFS 0x00010000 /* enable RDWRGSFS support */
+#define X86_CR4_PCIDE	0x00020000 /* enable PCID support */
 #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
 #define X86_CR4_SMEP	0x00100000 /* enable SMEP support */
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 31f180c21ce..74fcb963595 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -60,6 +60,7 @@
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
+#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -281,6 +282,7 @@ enum vmcs_field {
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD		54
 #define EXIT_REASON_XSETBV		55
+#define EXIT_REASON_INVPCID		58
 
 /*
  * Interruption-information format
@@ -404,6 +406,7 @@ enum vmcs_field {
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT			(1ull << 17)
+#define VMX_EPT_AD_BIT					(1ull << 21)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
@@ -415,11 +418,14 @@ enum vmcs_field {
 #define VMX_EPT_MAX_GAW				0x4
 #define VMX_EPT_MT_EPTE_SHIFT			3
 #define VMX_EPT_GAW_EPTP_SHIFT			3
+#define VMX_EPT_AD_ENABLE_BIT			(1ull << 6)
 #define VMX_EPT_DEFAULT_MT			0x6ull
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull
 #define VMX_EPT_IPAT_BIT    			(1ull << 6)
+#define VMX_EPT_ACCESS_BIT				(1ull << 8)
+#define VMX_EPT_DIRTY_BIT				(1ull << 9)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul