Merge tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "PPC and ARM do not have much going on this time.  Most of the cool
  stuff, instead, is in s390 and (after a few releases) x86.

  ARM has some caching fixes and PPC has transactional memory support in
  guests.  MIPS has some fixes, with more probably coming in 3.16 as
  QEMU will soon get support for MIPS KVM.

  For x86 there are optimizations for debug registers, which trigger on
  some Windows games, and other important fixes for Windows guests.  We
  now expose to the guest Broadwell instruction set extensions and also
  Intel MPX.  There's also a fix/workaround for OS X guests, nested
  virtualization features (preemption timer), and a couple kvmclock
  refinements.

  For s390, the main news is asynchronous page faults, together with
  improvements to IRQs (floating irqs and adapter irqs) that speed up
  virtio devices"

* tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (96 commits)
  KVM: PPC: Book3S HV: Save/restore host PMU registers that are new in POWER8
  KVM: PPC: Book3S HV: Fix decrementer timeouts with non-zero TB offset
  KVM: PPC: Book3S HV: Don't use kvm_memslots() in real mode
  KVM: PPC: Book3S HV: Return ENODEV error rather than EIO
  KVM: PPC: Book3S: Trim top 4 bits of physical address in RTAS code
  KVM: PPC: Book3S HV: Add get/set_one_reg for new TM state
  KVM: PPC: Book3S HV: Add transactional memory support
  KVM: Specify byte order for KVM_EXIT_MMIO
  KVM: vmx: fix MPX detection
  KVM: PPC: Book3S HV: Fix KVM hang with CONFIG_KVM_XICS=n
  KVM: PPC: Book3S: Introduce hypervisor call H_GET_TCE
  KVM: PPC: Book3S HV: Fix incorrect userspace exit on ioeventfd write
  KVM: s390: clear local interrupts at cpu initial reset
  KVM: s390: Fix possible memory leak in SIGP functions
  KVM: s390: fix calculation of idle_mask array size
  KVM: s390: randomize sca address
  KVM: ioapic: reinject pending interrupts on KVM_SET_IRQCHIP
  KVM: Bump KVM_MAX_IRQ_ROUTES for s390
  KVM: s390: irq routing for adapter interrupts.
  KVM: s390: adapter interrupt sources
  ...

5 files changed, 111 insertions, 18 deletions

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 21ef48d32ff2..3d6903006a8a 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -62,6 +62,7 @@
  * RW:		64bit by default, can be overriden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * TSW:		Trap cache operations by set/way
  * TWE:		Trap WFE
  * TWI:		Trap WFI
@@ -74,7 +75,7 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
-			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_IMO | HCR_FMO | \
 			 HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b25763bc0ec4..9fcd54b1e16d 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -79,7 +79,8 @@
 #define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
 #define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
 #define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
-#define c10_AMAIR	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
 #define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
 #define NR_CP15_REGS	(NR_SYS_REGS * 2)
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 7f1f9408ff66..7d29847a893b 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -106,7 +106,6 @@ static inline bool kvm_is_write_fault(unsigned long esr)
 	return true;
 }
 
-static inline void kvm_clean_dcache_area(void *addr, size_t size) {}
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
@@ -122,11 +121,25 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= PMD_S2_RDWR;
 }
 
+#define kvm_pgd_addr_end(addr, end)	pgd_addr_end(addr, end)
+#define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
+#define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
-					      unsigned long size)
+#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
+	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					     unsigned long size)
+{
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
+
 	if (!icache_is_aliasing()) {		/* PIPT */
 		flush_icache_range(hva, hva + size);
 	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
@@ -135,8 +148,9 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
 #define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
 
+void stage2_flush_vm(struct kvm *kvm);
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 02e9d09e1d80..03244582bc55 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -27,6 +27,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <trace/events/kvm.h>
@@ -121,6 +122,48 @@ done:
 }
 
 /*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	unsigned long val;
+
+	BUG_ON(!p->is_write);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	if (!p->is_aarch32) {
+		vcpu_sys_reg(vcpu, r->reg) = val;
+	} else {
+		vcpu_cp15(vcpu, r->reg) = val & 0xffffffffUL;
+		if (!p->is_32bit)
+			vcpu_cp15(vcpu, r->reg + 1) = val >> 32;
+	}
+	return true;
+}
+
+/*
+ * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ */
+static bool access_sctlr(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr_el2 &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+/*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
  * NAKed, so it will read the PMCR anyway.
@@ -185,32 +228,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_mpidr, MPIDR_EL1 },
 	/* SCTLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, SCTLR_EL1, 0x00C50078 },
+	  access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
 	/* CPACR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
 	  NULL, reset_val, CPACR_EL1, 0 },
 	/* TTBR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, TTBR0_EL1 },
+	  access_vm_reg, reset_unknown, TTBR0_EL1 },
 	/* TTBR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
-	  NULL, reset_unknown, TTBR1_EL1 },
+	  access_vm_reg, reset_unknown, TTBR1_EL1 },
 	/* TCR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
-	  NULL, reset_val, TCR_EL1, 0 },
+	  access_vm_reg, reset_val, TCR_EL1, 0 },
 
 	/* AFSR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
-	  NULL, reset_unknown, AFSR0_EL1 },
+	  access_vm_reg, reset_unknown, AFSR0_EL1 },
 	/* AFSR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
-	  NULL, reset_unknown, AFSR1_EL1 },
+	  access_vm_reg, reset_unknown, AFSR1_EL1 },
 	/* ESR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, ESR_EL1 },
+	  access_vm_reg, reset_unknown, ESR_EL1 },
 	/* FAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, FAR_EL1 },
+	  access_vm_reg, reset_unknown, FAR_EL1 },
 	/* PAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
 	  NULL, reset_unknown, PAR_EL1 },
@@ -224,17 +267,17 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, MAIR_EL1 },
+	  access_vm_reg, reset_unknown, MAIR_EL1 },
 	/* AMAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
-	  NULL, reset_amair_el1, AMAIR_EL1 },
+	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
 	/* VBAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, VBAR_EL1, 0 },
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
-	  NULL, reset_val, CONTEXTIDR_EL1, 0 },
+	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	/* TPIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
 	  NULL, reset_unknown, TPIDR_EL1 },
@@ -305,14 +348,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_val, FPEXC32_EL2, 0x70 },
 };
 
-/* Trapped cp15 registers */
+/*
+ * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
+ * depending on the way they are accessed (as a 32bit or a 64bit
+ * register).
+ */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
+	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+
 	/*
 	 * DC{C,I,CI}SW operations:
 	 */
 	{ Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
+
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake },
@@ -326,6 +387,14 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake },
+
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+
+	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 
 /* Target specific emulation tables */
@@ -437,6 +506,8 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	int Rt2 = (hsr >> 10) & 0xf;
 
+	params.is_aarch32 = true;
+	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -480,6 +551,8 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = true;
+	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt  = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -549,6 +622,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = false;
+	params.is_32bit = false;
 	params.Op0 = (esr >> 20) & 3;
 	params.Op1 = (esr >> 14) & 0x7;
 	params.CRn = (esr >> 10) & 0xf;
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index d50d3722998e..d411e251412c 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -30,6 +30,8 @@ struct sys_reg_params {
 	u8	Op2;
 	u8	Rt;
 	bool	is_write;
+	bool	is_aarch32;
+	bool	is_32bit;	/* Only valid if is_aarch32 is true */
 };
 
 struct sys_reg_desc {