Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - some cleanups
   - direct physical timer assignment
   - cache sanitization for 32-bit guests

  s390:
   - interrupt cleanup
   - introduction of the Guest Information Block
   - preparation for processor subfunctions in cpu models

  PPC:
   - bug fixes and improvements, especially related to machine checks
     and protection keys

  x86:
   - many, many cleanups, including removing a bunch of MMU code for
     unnecessary optimizations
   - AVIC fixes

  Generic:
   - memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (147 commits)
  kvm: vmx: fix formatting of a comment
  KVM: doc: Document the life cycle of a VM and its resources
  MAINTAINERS: Add KVM selftests to existing KVM entry
  Revert "KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()"
  KVM: PPC: Book3S: Add count cache flush parameters to kvmppc_get_cpu_char()
  KVM: PPC: Fix compilation when KVM is not enabled
  KVM: Minor cleanups for kvm_main.c
  KVM: s390: add debug logging for cpu model subfunctions
  KVM: s390: implement subfunction processor calls
  arm64: KVM: Fix architecturally invalid reset value for FPEXC32_EL2
  KVM: arm/arm64: Remove unused timer variable
  KVM: PPC: Book3S: Improve KVM reference counting
  KVM: PPC: Book3S HV: Fix build failure without IOMMU support
  Revert "KVM: Eliminate extra function calls in kvm_get_dirty_log_protect()"
  x86: kvmguest: use TSC clocksource if invariant TSC is exposed
  KVM: Never start grow vCPU halt_poll_ns from value below halt_poll_ns_grow_start
  KVM: Expose the initial start value in grow_halt_poll_ns() as a module parameter
  KVM: grow_halt_poll_ns() should never shrink vCPU halt_poll_ns
  KVM: x86/mmu: Consolidate kvm_mmu_zap_all() and kvm_mmu_zap_mmio_sptes()
  KVM: x86/mmu: WARN if zapping a MMIO spte results in zapping children
  ...

6 files changed, 114 insertions, 76 deletions

diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 0f2a135ba15b..690e033a91c0 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -3,9 +3,7 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-ccflags-y += -Iarch/arm64/kvm -Ivirt/kvm/arm/vgic
-CFLAGS_arm.o := -I.
-CFLAGS_mmu.o := -I.
+ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic
 
 KVM=../../../virt/kvm
 
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index f39801e4136c..fd917d6d12af 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -76,7 +76,7 @@ static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
 
 void kvm_arm_init_debug(void)
 {
-	__this_cpu_write(mdcr_el2, kvm_call_hyp(__kvm_get_mdcr_el2));
+	__this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2));
 }
 
 /**
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 952f6cb9cf72..2845aa680841 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -40,9 +40,6 @@
  * arch/arm64/kernel/hyp_stub.S.
  */
 ENTRY(__kvm_call_hyp)
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	hvc	#0
 	ret
-alternative_else_nop_endif
-	b	__vhe_hyp_call
 ENDPROC(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 73c1b483ec39..2b1e686772bf 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -43,18 +43,6 @@
 	ldr	lr, [sp], #16
 .endm
 
-ENTRY(__vhe_hyp_call)
-	do_el2_call
-	/*
-	 * We used to rely on having an exception return to get
-	 * an implicit isb. In the E2H case, we don't have it anymore.
-	 * rather than changing all the leaf functions, just do it here
-	 * before returning to the rest of the kernel.
-	 */
-	isb
-	ret
-ENDPROC(__vhe_hyp_call)
-
 el1_sync:				// Guest trapped into EL2
 
 	mrs	x0, esr_el2
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index b426e2cf973c..c52a8451637c 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -53,7 +53,6 @@ static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 
 static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(sctlr);
 	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c936aa40c3f4..539feecda5b8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -982,6 +982,10 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+#define reg_to_encoding(x)						\
+	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2);
+
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
@@ -1003,44 +1007,38 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
-static bool access_cntp_tval(struct kvm_vcpu *vcpu,
-		struct sys_reg_params *p,
-		const struct sys_reg_desc *r)
+static bool access_arch_timer(struct kvm_vcpu *vcpu,
+			      struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
 {
-	u64 now = kvm_phys_timer_read();
-	u64 cval;
+	enum kvm_arch_timers tmr;
+	enum kvm_arch_timer_regs treg;
+	u64 reg = reg_to_encoding(r);
 
-	if (p->is_write) {
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL,
-				      p->regval + now);
-	} else {
-		cval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
-		p->regval = cval - now;
+	switch (reg) {
+	case SYS_CNTP_TVAL_EL0:
+	case SYS_AARCH32_CNTP_TVAL:
+		tmr = TIMER_PTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+	case SYS_CNTP_CTL_EL0:
+	case SYS_AARCH32_CNTP_CTL:
+		tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+	case SYS_CNTP_CVAL_EL0:
+	case SYS_AARCH32_CNTP_CVAL:
+		tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+	default:
+		BUG();
 	}
 
-	return true;
-}
-
-static bool access_cntp_ctl(struct kvm_vcpu *vcpu,
-		struct sys_reg_params *p,
-		const struct sys_reg_desc *r)
-{
-	if (p->is_write)
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, p->regval);
-	else
-		p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL);
-
-	return true;
-}
-
-static bool access_cntp_cval(struct kvm_vcpu *vcpu,
-		struct sys_reg_params *p,
-		const struct sys_reg_desc *r)
-{
 	if (p->is_write)
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, p->regval);
+		kvm_arm_timer_write_sysreg(vcpu, tmr, treg, p->regval);
 	else
-		p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		p->regval = kvm_arm_timer_read_sysreg(vcpu, tmr, treg);
 
 	return true;
 }
@@ -1160,6 +1158,64 @@ static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	return __set_id_reg(rd, uaddr, true);
 }
 
+static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+		       const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = read_sanitised_ftr_reg(SYS_CTR_EL0);
+	return true;
+}
+
+static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = read_sysreg(clidr_el1);
+	return true;
+}
+
+static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+	return true;
+}
+
+static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	u32 csselr;
+
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1);
+	p->regval = get_ccsidr(csselr);
+
+	/*
+	 * Guests should not be doing cache operations by set/way at all, and
+	 * for this reason, we trap them and attempt to infer the intent, so
+	 * that we can flush the entire guest's address space at the appropriate
+	 * time.
+	 * To prevent this trapping from causing performance problems, let's
+	 * expose the geometry of all data and unified caches (which are
+	 * guaranteed to be PIPT and thus non-aliasing) as 1 set and 1 way.
+	 * [If guests should attempt to infer aliasing properties from the
+	 * geometry (which is not permitted by the architecture), they would
+	 * only do so for virtually indexed caches.]
+	 */
+	if (!(csselr & 1)) // data or unified cache
+		p->regval &= ~GENMASK(27, 3);
+	return true;
+}
+
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	SYS_DESC(SYS_##name),			\
@@ -1377,7 +1433,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
 
-	{ SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 },
+	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
+	{ SYS_DESC(SYS_CLIDR_EL1), access_clidr },
+	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
+	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
 
 	{ SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, },
 	{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
@@ -1400,9 +1459,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
 
-	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_cntp_tval },
-	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_cntp_ctl },
-	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_cntp_cval },
+	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
 
 	/* PMEVCNTRn_EL0 */
 	PMU_PMEVCNTR_EL0(0),
@@ -1476,7 +1535,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
 	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
-	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x70 },
+	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 },
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
@@ -1677,6 +1736,7 @@ static const struct sys_reg_desc cp14_64_regs[] = {
  * register).
  */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr },
 	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, 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 },
@@ -1723,10 +1783,9 @@ static const struct sys_reg_desc cp15_regs[] = {
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
 
-	/* CNTP_TVAL */
-	{ Op1( 0), CRn(14), CRm( 2), Op2( 0), access_cntp_tval },
-	/* CNTP_CTL */
-	{ Op1( 0), CRn(14), CRm( 2), Op2( 1), access_cntp_ctl },
+	/* Arch Tmers */
+	{ SYS_DESC(SYS_AARCH32_CNTP_TVAL), access_arch_timer },
+	{ SYS_DESC(SYS_AARCH32_CNTP_CTL), access_arch_timer },
 
 	/* PMEVCNTRn */
 	PMU_PMEVCNTR(0),
@@ -1794,6 +1853,10 @@ static const struct sys_reg_desc cp15_regs[] = {
 	PMU_PMEVTYPER(30),
 	/* PMCCFILTR */
 	{ Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper },
+
+	{ Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr },
+	{ Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr },
+	{ Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, c0_CSSELR },
 };
 
 static const struct sys_reg_desc cp15_64_regs[] = {
@@ -1803,7 +1866,7 @@ static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 	{ Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */
 	{ Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */
-	{ Op1( 2), CRn( 0), CRm(14), Op2( 0), access_cntp_cval },
+	{ SYS_DESC(SYS_AARCH32_CNTP_CVAL),    access_arch_timer },
 };
 
 /* Target specific emulation tables */
@@ -1832,30 +1895,19 @@ static const struct sys_reg_desc *get_target_table(unsigned target,
 	}
 }
 
-#define reg_to_match_value(x)						\
-	({								\
-		unsigned long val;					\
-		val  = (x)->Op0 << 14;					\
-		val |= (x)->Op1 << 11;					\
-		val |= (x)->CRn << 7;					\
-		val |= (x)->CRm << 3;					\
-		val |= (x)->Op2;					\
-		val;							\
-	 })
-
 static int match_sys_reg(const void *key, const void *elt)
 {
 	const unsigned long pval = (unsigned long)key;
 	const struct sys_reg_desc *r = elt;
 
-	return pval - reg_to_match_value(r);
+	return pval - reg_to_encoding(r);
 }
 
 static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
 					 const struct sys_reg_desc table[],
 					 unsigned int num)
 {
-	unsigned long pval = reg_to_match_value(params);
+	unsigned long pval = reg_to_encoding(params);
 
 	return bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
 }
@@ -2218,11 +2270,15 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	}
 
 FUNCTION_INVARIANT(midr_el1)
-FUNCTION_INVARIANT(ctr_el0)
 FUNCTION_INVARIANT(revidr_el1)
 FUNCTION_INVARIANT(clidr_el1)
 FUNCTION_INVARIANT(aidr_el1)
 
+static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r)
+{
+	((struct sys_reg_desc *)r)->val = read_sanitised_ftr_reg(SYS_CTR_EL0);
+}
+
 /* ->val is filled in by kvm_sys_reg_table_init() */
 static struct sys_reg_desc invariant_sys_regs[] = {
 	{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },