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

Pull more kvm updates from Paolo Bonzini:
 "The main batch of ARM + RISC-V changes, and a few fixes and cleanups
  for x86 (PMU virtualization and selftests).

  ARM:

   - Fixes for single-stepping in the presence of an async exception as
     well as the preservation of PSTATE.SS

   - Better handling of AArch32 ID registers on AArch64-only systems

   - Fixes for the dirty-ring API, allowing it to work on architectures
     with relaxed memory ordering

   - Advertise the new kvmarm mailing list

   - Various minor cleanups and spelling fixes

  RISC-V:

   - Improved instruction encoding infrastructure for instructions not
     yet supported by binutils

   - Svinval support for both KVM Host and KVM Guest

   - Zihintpause support for KVM Guest

   - Zicbom support for KVM Guest

   - Record number of signal exits as a VCPU stat

   - Use generic guest entry infrastructure

  x86:

   - Misc PMU fixes and cleanups.

   - selftests: fixes for Hyper-V hypercall

   - selftests: fix nx_huge_pages_test on TDP-disabled hosts

   - selftests: cleanups for fix_hypercall_test"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (57 commits)
  riscv: select HAVE_POSIX_CPU_TIMERS_TASK_WORK
  RISC-V: KVM: Use generic guest entry infrastructure
  RISC-V: KVM: Record number of signal exits as a vCPU stat
  RISC-V: KVM: add __init annotation to riscv_kvm_init()
  RISC-V: KVM: Expose Zicbom to the guest
  RISC-V: KVM: Provide UAPI for Zicbom block size
  RISC-V: KVM: Make ISA ext mappings explicit
  RISC-V: KVM: Allow Guest use Zihintpause extension
  RISC-V: KVM: Allow Guest use Svinval extension
  RISC-V: KVM: Use Svinval for local TLB maintenance when available
  RISC-V: Probe Svinval extension form ISA string
  RISC-V: KVM: Change the SBI specification version to v1.0
  riscv: KVM: Apply insn-def to hlv encodings
  riscv: KVM: Apply insn-def to hfence encodings
  riscv: Introduce support for defining instructions
  riscv: Add X register names to gpr-nums
  KVM: arm64: Advertise new kvmarm mailing list
  kvm: vmx: keep constant definition format consistent
  kvm: mmu: fix typos in struct kvm_arch
  KVM: selftests: Fix nx_huge_pages_test on TDP-disabled hosts
  ...

Documentation/virt/kvm/api.rst

@@ -7918,8 +7918,8 @@ guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
 (0x40000001). Otherwise, a guest may use the paravirtual features
 regardless of what has actually been exposed through the CPUID leaf.
 
-8.29 KVM_CAP_DIRTY_LOG_RING
----------------------------
+8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
+----------------------------------------------------------
 
 :Architectures: x86
 :Parameters: args[0] - size of the dirty log ring
@@ -7977,6 +7977,11 @@ on to the next GFN.  The userspace should continue to do this until the
 flags of a GFN have the DIRTY bit cleared, meaning that it has harvested
 all the dirty GFNs that were available.
 
+Note that on weakly ordered architectures, userspace accesses to the
+ring buffer (and more specifically the 'flags' field) must be ordered,
+using load-acquire/store-release accessors when available, or any
+other memory barrier that will ensure this ordering.
+
 It's not necessary for userspace to harvest the all dirty GFNs at once.
 However it must collect the dirty GFNs in sequence, i.e., the userspace
 program cannot skip one dirty GFN to collect the one next to it.
@@ -8005,6 +8010,14 @@ KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual
 machine will switch to ring-buffer dirty page tracking and further
 KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail.
 
+NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that
+should be exposed by weakly ordered architecture, in order to indicate
+the additional memory ordering requirements imposed on userspace when
+reading the state of an entry and mutating it from DIRTY to HARVESTED.
+Architecture with TSO-like ordering (such as x86) are allowed to
+expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL
+to userspace.
+
 8.30 KVM_CAP_XEN_HVM
 --------------------
 

MAINTAINERS

@@ -11204,7 +11204,8 @@ R:	Alexandru Elisei <alexandru.elisei@arm.com>
 R:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Oliver Upton <oliver.upton@linux.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	kvmarm@lists.cs.columbia.edu (moderated for non-subscribers)
+L:	kvmarm@lists.linux.dev
+L:	kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
 F:	arch/arm64/include/asm/kvm*

arch/arm64/include/asm/kvm_host.h

@@ -393,6 +393,7 @@ struct kvm_vcpu_arch {
 	 */
 	struct {
 		u32	mdscr_el1;
+		bool	pstate_ss;
 	} guest_debug_preserved;
 
 	/* vcpu power state */
@@ -535,6 +536,9 @@ struct kvm_vcpu_arch {
 #define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))
 /* vcpu system registers loaded on physical CPU */
 #define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
+/* Software step state is Active-pending */
+#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
+
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
 #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) +	\

arch/arm64/kvm/arm.c

@@ -2269,6 +2269,16 @@ static int __init early_kvm_mode_cfg(char *arg)
 	if (!arg)
 		return -EINVAL;
 
+	if (strcmp(arg, "none") == 0) {
+		kvm_mode = KVM_MODE_NONE;
+		return 0;
+	}
+
+	if (!is_hyp_mode_available()) {
+		pr_warn_once("KVM is not available. Ignoring kvm-arm.mode\n");
+		return 0;
+	}
+
 	if (strcmp(arg, "protected") == 0) {
 		if (!is_kernel_in_hyp_mode())
 			kvm_mode = KVM_MODE_PROTECTED;
@@ -2283,11 +2293,6 @@ static int __init early_kvm_mode_cfg(char *arg)
 		return 0;
 	}
 
-	if (strcmp(arg, "none") == 0) {
-		kvm_mode = KVM_MODE_NONE;
-		return 0;
-	}
-
 	return -EINVAL;
 }
 early_param("kvm-arm.mode", early_kvm_mode_cfg);

arch/arm64/kvm/debug.c

@@ -32,6 +32,10 @@ static DEFINE_PER_CPU(u64, mdcr_el2);
  *
  * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled
  * after we have restored the preserved value to the main context.
+ *
+ * When single-step is enabled by userspace, we tweak PSTATE.SS on every
+ * guest entry. Preserve PSTATE.SS so we can restore the original value
+ * for the vcpu after the single-step is disabled.
  */
 static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
 {
@@ -41,6 +45,9 @@ static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
 
 	trace_kvm_arm_set_dreg32("Saved MDSCR_EL1",
 				vcpu->arch.guest_debug_preserved.mdscr_el1);
+
+	vcpu->arch.guest_debug_preserved.pstate_ss =
+					(*vcpu_cpsr(vcpu) & DBG_SPSR_SS);
 }
 
 static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
@@ -51,6 +58,11 @@ static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
 
 	trace_kvm_arm_set_dreg32("Restored MDSCR_EL1",
 				vcpu_read_sys_reg(vcpu, MDSCR_EL1));
+
+	if (vcpu->arch.guest_debug_preserved.pstate_ss)
+		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
+	else
+		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
 }
 
 /**
@@ -188,7 +200,18 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 		 * debugging the system.
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+			/*
+			 * If the software step state at the last guest exit
+			 * was Active-pending, we don't set DBG_SPSR_SS so
+			 * that the state is maintained (to not run another
+			 * single-step until the pending Software Step
+			 * exception is taken).
+			 */
+			if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING))
 				*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
+			else
+				*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+
 			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
 			mdscr |= DBG_MDSCR_SS;
 			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
@@ -262,6 +285,15 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 	 * Restore the guest's debug registers if we were using them.
 	 */
 	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
+		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+			if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS))
+				/*
+				 * Mark the vcpu as ACTIVE_PENDING
+				 * until Software Step exception is taken.
+				 */
+				vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING);
+		}
+
 		restore_guest_debug_regs(vcpu);
 
 		/*

arch/arm64/kvm/guest.c

@@ -937,6 +937,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	} else {
 		/* If not enabled clear all flags */
 		vcpu->guest_debug = 0;
+		vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING);
 	}
 
 out:

arch/arm64/kvm/handle_exit.c

@@ -152,8 +152,14 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 	run->debug.arch.hsr_high = upper_32_bits(esr);
 	run->flags = KVM_DEBUG_ARCH_HSR_HIGH_VALID;
 
-	if (ESR_ELx_EC(esr) == ESR_ELx_EC_WATCHPT_LOW)
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
+		break;
+	case ESR_ELx_EC_SOFTSTP_LOW:
+		vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING);
+		break;
+	}
 
 	return 0;
 }

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -143,7 +143,7 @@ static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
 	}
 }
 
-/* Restore VGICv3 state on non_VEH systems */
+/* Restore VGICv3 state on non-VHE systems */
 static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 {
 	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {

arch/arm64/kvm/sys_regs.c

@@ -1063,13 +1063,12 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 }
 
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
-static u64 read_id_reg(const struct kvm_vcpu *vcpu,
-		struct sys_reg_desc const *r, bool raz)
+static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r)
 {
 	u32 id = reg_to_encoding(r);
 	u64 val;
 
-	if (raz)
+	if (sysreg_visible_as_raz(vcpu, r))
 		return 0;
 
 	val = read_sanitised_ftr_reg(id);
@@ -1145,34 +1144,37 @@ static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/* cpufeature ID register access trap handlers */
-
-static bool __access_id_reg(struct kvm_vcpu *vcpu,
-			    struct sys_reg_params *p,
-			    const struct sys_reg_desc *r,
-			    bool raz)
+static unsigned int aa32_id_visibility(const struct kvm_vcpu *vcpu,
+				       const struct sys_reg_desc *r)
 {
-	if (p->is_write)
-		return write_to_read_only(vcpu, p, r);
+	/*
+	 * AArch32 ID registers are UNKNOWN if AArch32 isn't implemented at any
+	 * EL. Promote to RAZ/WI in order to guarantee consistency between
+	 * systems.
+	 */
+	if (!kvm_supports_32bit_el0())
+		return REG_RAZ | REG_USER_WI;
 
-	p->regval = read_id_reg(vcpu, r, raz);
-	return true;
+	return id_visibility(vcpu, r);
 }
 
-static bool access_id_reg(struct kvm_vcpu *vcpu,
-			  struct sys_reg_params *p,
+static unsigned int raz_visibility(const struct kvm_vcpu *vcpu,
 				   const struct sys_reg_desc *r)
 {
-	bool raz = sysreg_visible_as_raz(vcpu, r);
-
-	return __access_id_reg(vcpu, p, r, raz);
+	return REG_RAZ;
 }
 
-static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
+/* cpufeature ID register access trap handlers */
+
+static bool access_id_reg(struct kvm_vcpu *vcpu,
 			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	return __access_id_reg(vcpu, p, r, true);
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = read_id_reg(vcpu, r);
+	return true;
 }
 
 /* Visibility overrides for SVE-specific control registers */
@@ -1208,9 +1210,9 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	/* We can only differ with CSV[23], and anything else is an error */
-	val ^= read_id_reg(vcpu, rd, false);
-	val &= ~((0xFUL << ID_AA64PFR0_EL1_CSV2_SHIFT) |
-		 (0xFUL << ID_AA64PFR0_EL1_CSV3_SHIFT));
+	val ^= read_id_reg(vcpu, rd);
+	val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) |
+		 ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3));
 	if (val)
 		return -EINVAL;
 
@@ -1227,45 +1229,21 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
  * are stored, and for set_id_reg() we don't allow the effective value
  * to be changed.
  */
-static int __get_id_reg(const struct kvm_vcpu *vcpu,
-			const struct sys_reg_desc *rd, u64 *val,
-			bool raz)
-{
-	*val = read_id_reg(vcpu, rd, raz);
-	return 0;
-}
-
-static int __set_id_reg(const struct kvm_vcpu *vcpu,
-			const struct sys_reg_desc *rd, u64 val,
-			bool raz)
-{
-	/* This is what we mean by invariant: you can't change it. */
-	if (val != read_id_reg(vcpu, rd, raz))
-		return -EINVAL;
-
-	return 0;
-}
-
 static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      u64 *val)
 {
-	bool raz = sysreg_visible_as_raz(vcpu, rd);
-
-	return __get_id_reg(vcpu, rd, val, raz);
+	*val = read_id_reg(vcpu, rd);
+	return 0;
 }
 
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      u64 val)
 {
-	bool raz = sysreg_visible_as_raz(vcpu, rd);
-
-	return __set_id_reg(vcpu, rd, val, raz);
-}
+	/* This is what we mean by invariant: you can't change it. */
+	if (val != read_id_reg(vcpu, rd))
+		return -EINVAL;
 
-static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-			  u64 val)
-{
-	return __set_id_reg(vcpu, rd, val, true);
+	return 0;
 }
 
 static int get_raz_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
@@ -1367,6 +1345,15 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
 	.visibility = id_visibility,		\
 }
 
+/* sys_reg_desc initialiser for known cpufeature ID registers */
+#define AA32_ID_SANITISED(name) {		\
+	SYS_DESC(SYS_##name),			\
+	.access	= access_id_reg,		\
+	.get_user = get_id_reg,			\
+	.set_user = set_id_reg,			\
+	.visibility = aa32_id_visibility,	\
+}
+
 /*
  * sys_reg_desc initialiser for architecturally unallocated cpufeature ID
  * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2
@@ -1374,9 +1361,10 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
  */
 #define ID_UNALLOCATED(crm, op2) {			\
 	Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2),	\
-	.access = access_raz_id_reg,			\
-	.get_user = get_raz_reg,			\
-	.set_user = set_raz_id_reg,			\
+	.access = access_id_reg,			\
+	.get_user = get_id_reg,				\
+	.set_user = set_id_reg,				\
+	.visibility = raz_visibility			\
 }
 
 /*
@@ -1386,9 +1374,10 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
  */
 #define ID_HIDDEN(name) {			\
 	SYS_DESC(SYS_##name),			\
-	.access = access_raz_id_reg,		\
-	.get_user = get_raz_reg,		\
-	.set_user = set_raz_id_reg,		\
+	.access = access_id_reg,		\
+	.get_user = get_id_reg,			\
+	.set_user = set_id_reg,			\
+	.visibility = raz_visibility,		\
 }
 
 /*
@@ -1452,33 +1441,33 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
-	ID_SANITISED(ID_PFR0_EL1),
-	ID_SANITISED(ID_PFR1_EL1),
-	ID_SANITISED(ID_DFR0_EL1),
+	AA32_ID_SANITISED(ID_PFR0_EL1),
+	AA32_ID_SANITISED(ID_PFR1_EL1),
+	AA32_ID_SANITISED(ID_DFR0_EL1),
 	ID_HIDDEN(ID_AFR0_EL1),
-	ID_SANITISED(ID_MMFR0_EL1),
-	ID_SANITISED(ID_MMFR1_EL1),
-	ID_SANITISED(ID_MMFR2_EL1),
-	ID_SANITISED(ID_MMFR3_EL1),
+	AA32_ID_SANITISED(ID_MMFR0_EL1),
+	AA32_ID_SANITISED(ID_MMFR1_EL1),
+	AA32_ID_SANITISED(ID_MMFR2_EL1),
+	AA32_ID_SANITISED(ID_MMFR3_EL1),
 
 	/* CRm=2 */
-	ID_SANITISED(ID_ISAR0_EL1),
-	ID_SANITISED(ID_ISAR1_EL1),
-	ID_SANITISED(ID_ISAR2_EL1),
-	ID_SANITISED(ID_ISAR3_EL1),
-	ID_SANITISED(ID_ISAR4_EL1),
-	ID_SANITISED(ID_ISAR5_EL1),
-	ID_SANITISED(ID_MMFR4_EL1),
-	ID_SANITISED(ID_ISAR6_EL1),
+	AA32_ID_SANITISED(ID_ISAR0_EL1),
+	AA32_ID_SANITISED(ID_ISAR1_EL1),
+	AA32_ID_SANITISED(ID_ISAR2_EL1),
+	AA32_ID_SANITISED(ID_ISAR3_EL1),
+	AA32_ID_SANITISED(ID_ISAR4_EL1),
+	AA32_ID_SANITISED(ID_ISAR5_EL1),
+	AA32_ID_SANITISED(ID_MMFR4_EL1),
+	AA32_ID_SANITISED(ID_ISAR6_EL1),
 
 	/* CRm=3 */
-	ID_SANITISED(MVFR0_EL1),
-	ID_SANITISED(MVFR1_EL1),
-	ID_SANITISED(MVFR2_EL1),
+	AA32_ID_SANITISED(MVFR0_EL1),
+	AA32_ID_SANITISED(MVFR1_EL1),
+	AA32_ID_SANITISED(MVFR2_EL1),
 	ID_UNALLOCATED(3,3),
-	ID_SANITISED(ID_PFR2_EL1),
+	AA32_ID_SANITISED(ID_PFR2_EL1),
 	ID_HIDDEN(ID_DFR1_EL1),
-	ID_SANITISED(ID_MMFR5_EL1),
+	AA32_ID_SANITISED(ID_MMFR5_EL1),
 	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */
@@ -2809,6 +2798,9 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
 	if (!r)
 		return -ENOENT;
 
+	if (sysreg_user_write_ignore(vcpu, r))
+		return 0;
+
 	if (r->set_user) {
 		ret = (r->set_user)(vcpu, r, val);
 	} else {

arch/arm64/kvm/sys_regs.h

@@ -86,6 +86,7 @@ struct sys_reg_desc {
 
 #define REG_HIDDEN		(1 << 0) /* hidden from userspace and guest */
 #define REG_RAZ			(1 << 1) /* RAZ from userspace and guest */
+#define REG_USER_WI		(1 << 2) /* WI from userspace only */
 
 static __printf(2, 3)
 inline void print_sys_reg_msg(const struct sys_reg_params *p,
@@ -136,22 +137,31 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r
 	__vcpu_sys_reg(vcpu, r->reg) = r->val;
 }
 
-static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
+static inline unsigned int sysreg_visibility(const struct kvm_vcpu *vcpu,
 					     const struct sys_reg_desc *r)
 {
 	if (likely(!r->visibility))
-		return false;
+		return 0;
+
+	return r->visibility(vcpu, r);
+}
 
-	return r->visibility(vcpu, r) & REG_HIDDEN;
+static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
+				 const struct sys_reg_desc *r)
+{
+	return sysreg_visibility(vcpu, r) & REG_HIDDEN;
 }
 
 static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu,
 					 const struct sys_reg_desc *r)
 {
-	if (likely(!r->visibility))
-		return false;
+	return sysreg_visibility(vcpu, r) & REG_RAZ;
+}
 
-	return r->visibility(vcpu, r) & REG_RAZ;
+static inline bool sysreg_user_write_ignore(const struct kvm_vcpu *vcpu,
+					    const struct sys_reg_desc *r)
+{
+	return sysreg_visibility(vcpu, r) & REG_USER_WI;
 }
 
 static inline int cmp_sys_reg(const struct sys_reg_desc *i1,

arch/arm64/kvm/vgic/vgic-its.c

@@ -406,7 +406,7 @@ static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its,
 	struct its_ite *ite;
 
 	for_each_lpi_its(device, ite, its) {
-		if (!ite->collection || coll != ite->collection)
+		if (ite->collection != coll)
 			continue;
 
 		update_affinity_ite(kvm, ite);

arch/riscv/Kconfig

@@ -104,6 +104,7 @@ config RISCV
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_STACKPROTECTOR
@@ -228,6 +229,9 @@ config RISCV_DMA_NONCOHERENT
 	select ARCH_HAS_SETUP_DMA_OPS
 	select DMA_DIRECT_REMAP
 
+config AS_HAS_INSN
+	def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero)
+
 source "arch/riscv/Kconfig.socs"
 source "arch/riscv/Kconfig.erratas"
 

arch/riscv/include/asm/gpr-num.h

@@ -3,6 +3,11 @@
 #define __ASM_GPR_NUM_H
 
 #ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+	.equ	.L__gpr_num_x\num, \num
+	.endr
+
 	.equ	.L__gpr_num_zero,	0
 	.equ	.L__gpr_num_ra,		1
 	.equ	.L__gpr_num_sp,		2
@@ -39,6 +44,9 @@
 #else /* __ASSEMBLY__ */
 
 #define __DEFINE_ASM_GPR_NUMS					\
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31\n" \
+"	.equ	.L__gpr_num_x\\num, \\num\n"			\
+"	.endr\n"						\
 "	.equ	.L__gpr_num_zero,	0\n"			\
 "	.equ	.L__gpr_num_ra,		1\n"			\
 "	.equ	.L__gpr_num_sp,		2\n"			\

arch/riscv/include/asm/hwcap.h

@@ -58,6 +58,7 @@ enum riscv_isa_ext_id {
 	RISCV_ISA_EXT_ZICBOM,
 	RISCV_ISA_EXT_ZIHINTPAUSE,
 	RISCV_ISA_EXT_SSTC,
+	RISCV_ISA_EXT_SVINVAL,
 	RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
 };
 
@@ -69,6 +70,7 @@ enum riscv_isa_ext_id {
 enum riscv_isa_ext_key {
 	RISCV_ISA_EXT_KEY_FPU,		/* For 'F' and 'D' */
 	RISCV_ISA_EXT_KEY_ZIHINTPAUSE,
+	RISCV_ISA_EXT_KEY_SVINVAL,
 	RISCV_ISA_EXT_KEY_MAX,
 };
 
@@ -90,6 +92,8 @@ static __always_inline int riscv_isa_ext2key(int num)
 		return RISCV_ISA_EXT_KEY_FPU;
 	case RISCV_ISA_EXT_ZIHINTPAUSE:
 		return RISCV_ISA_EXT_KEY_ZIHINTPAUSE;
+	case RISCV_ISA_EXT_SVINVAL:
+		return RISCV_ISA_EXT_KEY_SVINVAL;
 	default:
 		return -EINVAL;
 	}

arch/riscv/include/asm/insn-def.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_INSN_DEF_H
+#define __ASM_INSN_DEF_H
+
+#include <asm/asm.h>
+
+#define INSN_R_FUNC7_SHIFT		25
+#define INSN_R_RS2_SHIFT		20
+#define INSN_R_RS1_SHIFT		15
+#define INSN_R_FUNC3_SHIFT		12
+#define INSN_R_RD_SHIFT			 7
+#define INSN_R_OPCODE_SHIFT		 0
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_AS_HAS_INSN
+
+	.macro insn_r, opcode, func3, func7, rd, rs1, rs2
+	.insn	r \opcode, \func3, \func7, \rd, \rs1, \rs2
+	.endm
+
+#else
+
+#include <asm/gpr-num.h>
+
+	.macro insn_r, opcode, func3, func7, rd, rs1, rs2
+	.4byte	((\opcode << INSN_R_OPCODE_SHIFT) |		\
+		 (\func3 << INSN_R_FUNC3_SHIFT) |		\
+		 (\func7 << INSN_R_FUNC7_SHIFT) |		\
+		 (.L__gpr_num_\rd << INSN_R_RD_SHIFT) |		\
+		 (.L__gpr_num_\rs1 << INSN_R_RS1_SHIFT) |	\
+		 (.L__gpr_num_\rs2 << INSN_R_RS2_SHIFT))
+	.endm
+
+#endif
+
+#define __INSN_R(...)	insn_r __VA_ARGS__
+
+#else /* ! __ASSEMBLY__ */
+
+#ifdef CONFIG_AS_HAS_INSN
+
+#define __INSN_R(opcode, func3, func7, rd, rs1, rs2)	\
+	".insn	r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n"
+
+#else
+
+#include <linux/stringify.h>
+#include <asm/gpr-num.h>
+
+#define DEFINE_INSN_R							\
+	__DEFINE_ASM_GPR_NUMS						\
+"	.macro insn_r, opcode, func3, func7, rd, rs1, rs2\n"		\
+"	.4byte	((\\opcode << " __stringify(INSN_R_OPCODE_SHIFT) ") |"	\
+"		 (\\func3 << " __stringify(INSN_R_FUNC3_SHIFT) ") |"	\
+"		 (\\func7 << " __stringify(INSN_R_FUNC7_SHIFT) ") |"	\
+"		 (.L__gpr_num_\\rd << " __stringify(INSN_R_RD_SHIFT) ") |"    \
+"		 (.L__gpr_num_\\rs1 << " __stringify(INSN_R_RS1_SHIFT) ") |"  \
+"		 (.L__gpr_num_\\rs2 << " __stringify(INSN_R_RS2_SHIFT) "))\n" \
+"	.endm\n"
+
+#define UNDEFINE_INSN_R							\
+"	.purgem insn_r\n"
+
+#define __INSN_R(opcode, func3, func7, rd, rs1, rs2)			\
+	DEFINE_INSN_R							\
+	"insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \
+	UNDEFINE_INSN_R
+
+#endif
+
+#endif /* ! __ASSEMBLY__ */
+
+#define INSN_R(opcode, func3, func7, rd, rs1, rs2)		\
+	__INSN_R(RV_##opcode, RV_##func3, RV_##func7,		\
+		 RV_##rd, RV_##rs1, RV_##rs2)
+
+#define RV_OPCODE(v)		__ASM_STR(v)
+#define RV_FUNC3(v)		__ASM_STR(v)
+#define RV_FUNC7(v)		__ASM_STR(v)
+#define RV_RD(v)		__ASM_STR(v)
+#define RV_RS1(v)		__ASM_STR(v)
+#define RV_RS2(v)		__ASM_STR(v)
+#define __RV_REG(v)		__ASM_STR(x ## v)
+#define RV___RD(v)		__RV_REG(v)
+#define RV___RS1(v)		__RV_REG(v)
+#define RV___RS2(v)		__RV_REG(v)
+
+#define RV_OPCODE_SYSTEM	RV_OPCODE(115)
+
+#define HFENCE_VVMA(vaddr, asid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(17),		\
+	       __RD(0), RS1(vaddr), RS2(asid))
+
+#define HFENCE_GVMA(gaddr, vmid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(49),		\
+	       __RD(0), RS1(gaddr), RS2(vmid))
+
+#define HLVX_HU(dest, addr)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(50),		\
+	       RD(dest), RS1(addr), __RS2(3))
+
+#define HLV_W(dest, addr)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(52),		\
+	       RD(dest), RS1(addr), __RS2(0))
+
+#ifdef CONFIG_64BIT
+#define HLV_D(dest, addr)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(54),		\
+	       RD(dest), RS1(addr), __RS2(0))
+#else
+#define HLV_D(dest, addr)					\
+	__ASM_STR(.error "hlv.d requires 64-bit support")
+#endif
+
+#define SINVAL_VMA(vaddr, asid)					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(11),		\
+	       __RD(0), RS1(vaddr), RS2(asid))
+
+#define SFENCE_W_INVAL()					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12),		\
+	       __RD(0), __RS1(0), __RS2(0))
+
+#define SFENCE_INVAL_IR()					\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12),		\
+	       __RD(0), __RS1(0), __RS2(1))
+
+#define HINVAL_VVMA(vaddr, asid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(19),		\
+	       __RD(0), RS1(vaddr), RS2(asid))
+
+#define HINVAL_GVMA(gaddr, vmid)				\
+	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51),		\
+	       __RD(0), RS1(gaddr), RS2(vmid))
+
+#endif /* __ASM_INSN_DEF_H */

arch/riscv/include/asm/kvm_host.h

@@ -67,6 +67,7 @@ struct kvm_vcpu_stat {
 	u64 mmio_exit_kernel;
 	u64 csr_exit_user;
 	u64 csr_exit_kernel;
+	u64 signal_exits;
 	u64 exits;
 };
 

arch/riscv/include/asm/kvm_vcpu_sbi.h

@@ -11,8 +11,8 @@
 
 #define KVM_SBI_IMPID 3
 
-#define KVM_SBI_VERSION_MAJOR 0
-#define KVM_SBI_VERSION_MINOR 3
+#define KVM_SBI_VERSION_MAJOR 1
+#define KVM_SBI_VERSION_MINOR 0
 
 struct kvm_vcpu_sbi_extension {
 	unsigned long extid_start;

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

@@ -48,6 +48,7 @@ struct kvm_sregs {
 /* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
 struct kvm_riscv_config {
 	unsigned long isa;
+	unsigned long zicbom_block_size;
 };
 
 /* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
@@ -98,6 +99,9 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_M,
 	KVM_RISCV_ISA_EXT_SVPBMT,
 	KVM_RISCV_ISA_EXT_SSTC,
+	KVM_RISCV_ISA_EXT_SVINVAL,
+	KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
+	KVM_RISCV_ISA_EXT_ZICBOM,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 

arch/riscv/kernel/cpu.c

@@ -93,6 +93,7 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
 static struct riscv_isa_ext_data isa_ext_arr[] = {
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
 	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
+	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
 	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),

arch/riscv/kernel/cpufeature.c

@@ -204,6 +204,7 @@ void __init riscv_fill_hwcap(void)
 				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
 				SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
 				SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC);
+				SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL);
 			}
 #undef SET_ISA_EXT_MAP
 		}

arch/riscv/kvm/Kconfig

@@ -24,6 +24,7 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
+	select KVM_XFER_TO_GUEST_WORK
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select HAVE_KVM_EVENTFD
 	select SRCU

arch/riscv/kvm/main.c

@@ -122,7 +122,7 @@ void kvm_arch_exit(void)
 {
 }
 
-static int riscv_kvm_init(void)
+static int __init riscv_kvm_init(void)
 {
 	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 }

arch/riscv/kvm/tlb.c

@@ -12,22 +12,11 @@
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/insn-def.h>
 
-/*
- * Instruction encoding of hfence.gvma is:
- * HFENCE.GVMA rs1, rs2
- * HFENCE.GVMA zero, rs2
- * HFENCE.GVMA rs1
- * HFENCE.GVMA
- *
- * rs1!=zero and rs2!=zero ==> HFENCE.GVMA rs1, rs2
- * rs1==zero and rs2!=zero ==> HFENCE.GVMA zero, rs2
- * rs1!=zero and rs2==zero ==> HFENCE.GVMA rs1
- * rs1==zero and rs2==zero ==> HFENCE.GVMA
- *
- * Instruction encoding of HFENCE.GVMA is:
- * 0110001 rs2(5) rs1(5) 000 00000 1110011
- */
+#define has_svinval()	\
+	static_branch_unlikely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_SVINVAL])
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
 					  gpa_t gpa, gpa_t gpsz,
@@ -40,32 +29,22 @@ void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
 		return;
 	}
 
-	for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) {
-		/*
-		 * rs1 = a0 (GPA >> 2)
-		 * rs2 = a1 (VMID)
-		 * HFENCE.GVMA a0, a1
-		 * 0110001 01011 01010 000 00000 1110011
-		 */
-		asm volatile ("srli a0, %0, 2\n"
-			      "add a1, %1, zero\n"
-			      ".word 0x62b50073\n"
-			      :: "r" (pos), "r" (vmid)
-			      : "a0", "a1", "memory");
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile (HINVAL_GVMA(%0, %1)
+			: : "r" (pos >> 2), "r" (vmid) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile (HFENCE_GVMA(%0, %1)
+			: : "r" (pos >> 2), "r" (vmid) : "memory");
 	}
 }
 
 void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid)
 {
-	/*
-	 * rs1 = zero
-	 * rs2 = a0 (VMID)
-	 * HFENCE.GVMA zero, a0
-	 * 0110001 01010 00000 000 00000 1110011
-	 */
-	asm volatile ("add a0, %0, zero\n"
-		      ".word 0x62a00073\n"
-		      :: "r" (vmid) : "a0", "memory");
+	asm volatile(HFENCE_GVMA(zero, %0) : : "r" (vmid) : "memory");
 }
 
 void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
@@ -78,46 +57,24 @@ void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
 		return;
 	}
 
-	for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) {
-		/*
-		 * rs1 = a0 (GPA >> 2)
-		 * rs2 = zero
-		 * HFENCE.GVMA a0
-		 * 0110001 00000 01010 000 00000 1110011
-		 */
-		asm volatile ("srli a0, %0, 2\n"
-			      ".word 0x62050073\n"
-			      :: "r" (pos) : "a0", "memory");
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile(HINVAL_GVMA(%0, zero)
+			: : "r" (pos >> 2) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order))
+			asm volatile(HFENCE_GVMA(%0, zero)
+			: : "r" (pos >> 2) : "memory");
 	}
 }
 
 void kvm_riscv_local_hfence_gvma_all(void)
 {
-	/*
-	 * rs1 = zero
-	 * rs2 = zero
-	 * HFENCE.GVMA
-	 * 0110001 00000 00000 000 00000 1110011
-	 */
-	asm volatile (".word 0x62000073" ::: "memory");
+	asm volatile(HFENCE_GVMA(zero, zero) : : : "memory");
 }
 
-/*
- * Instruction encoding of hfence.gvma is:
- * HFENCE.VVMA rs1, rs2
- * HFENCE.VVMA zero, rs2
- * HFENCE.VVMA rs1
- * HFENCE.VVMA
- *
- * rs1!=zero and rs2!=zero ==> HFENCE.VVMA rs1, rs2
- * rs1==zero and rs2!=zero ==> HFENCE.VVMA zero, rs2
- * rs1!=zero and rs2==zero ==> HFENCE.VVMA rs1
- * rs1==zero and rs2==zero ==> HFENCE.VVMA
- *
- * Instruction encoding of HFENCE.VVMA is:
- * 0010001 rs2(5) rs1(5) 000 00000 1110011
- */
-
 void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
 					  unsigned long asid,
 					  unsigned long gva,
@@ -133,18 +90,16 @@ void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
 
 	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
 
-	for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) {
-		/*
-		 * rs1 = a0 (GVA)
-		 * rs2 = a1 (ASID)
-		 * HFENCE.VVMA a0, a1
-		 * 0010001 01011 01010 000 00000 1110011
-		 */
-		asm volatile ("add a0, %0, zero\n"
-			      "add a1, %1, zero\n"
-			      ".word 0x22b50073\n"
-			      :: "r" (pos), "r" (asid)
-			      : "a0", "a1", "memory");
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HINVAL_VVMA(%0, %1)
+			: : "r" (pos), "r" (asid) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HFENCE_VVMA(%0, %1)
+			: : "r" (pos), "r" (asid) : "memory");
 	}
 
 	csr_write(CSR_HGATP, hgatp);
@@ -157,15 +112,7 @@ void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
 
 	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
 
-	/*
-	 * rs1 = zero
-	 * rs2 = a0 (ASID)
-	 * HFENCE.VVMA zero, a0
-	 * 0010001 01010 00000 000 00000 1110011
-	 */
-	asm volatile ("add a0, %0, zero\n"
-		      ".word 0x22a00073\n"
-		      :: "r" (asid) : "a0", "memory");
+	asm volatile(HFENCE_VVMA(zero, %0) : : "r" (asid) : "memory");
 
 	csr_write(CSR_HGATP, hgatp);
 }
@@ -183,16 +130,16 @@ void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
 
 	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
 
-	for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) {
-		/*
-		 * rs1 = a0 (GVA)
-		 * rs2 = zero
-		 * HFENCE.VVMA a0
-		 * 0010001 00000 01010 000 00000 1110011
-		 */
-		asm volatile ("add a0, %0, zero\n"
-			      ".word 0x22050073\n"
-			      :: "r" (pos) : "a0", "memory");
+	if (has_svinval()) {
+		asm volatile (SFENCE_W_INVAL() ::: "memory");
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HINVAL_VVMA(%0, zero)
+			: : "r" (pos) : "memory");
+		asm volatile (SFENCE_INVAL_IR() ::: "memory");
+	} else {
+		for (pos = gva; pos < (gva + gvsz); pos += BIT(order))
+			asm volatile(HFENCE_VVMA(%0, zero)
+			: : "r" (pos) : "memory");
 	}
 
 	csr_write(CSR_HGATP, hgatp);
@@ -204,13 +151,7 @@ void kvm_riscv_local_hfence_vvma_all(unsigned long vmid)
 
 	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
 
-	/*
-	 * rs1 = zero
-	 * rs2 = zero
-	 * HFENCE.VVMA
-	 * 0010001 00000 00000 000 00000 1110011
-	 */
-	asm volatile (".word 0x22000073" ::: "memory");
+	asm volatile(HFENCE_VVMA(zero, zero) : : : "memory");
 
 	csr_write(CSR_HGATP, hgatp);
 }

arch/riscv/kvm/vcpu.c

@@ -7,6 +7,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/entry-kvm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kdebug.h>
@@ -18,6 +19,7 @@
 #include <linux/fs.h>
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
+#include <asm/cacheflush.h>
 #include <asm/hwcap.h>
 
 const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
@@ -28,6 +30,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, mmio_exit_kernel),
 	STATS_DESC_COUNTER(VCPU, csr_exit_user),
 	STATS_DESC_COUNTER(VCPU, csr_exit_kernel),
+	STATS_DESC_COUNTER(VCPU, signal_exits),
 	STATS_DESC_COUNTER(VCPU, exits)
 };
 
@@ -42,17 +45,23 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
 
 #define KVM_RISCV_BASE_ISA_MASK		GENMASK(25, 0)
 
+#define KVM_ISA_EXT_ARR(ext)		[KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext
+
 /* Mapping between KVM ISA Extension ID & Host ISA extension ID */
 static const unsigned long kvm_isa_ext_arr[] = {
-	RISCV_ISA_EXT_a,
-	RISCV_ISA_EXT_c,
-	RISCV_ISA_EXT_d,
-	RISCV_ISA_EXT_f,
-	RISCV_ISA_EXT_h,
-	RISCV_ISA_EXT_i,
-	RISCV_ISA_EXT_m,
-	RISCV_ISA_EXT_SVPBMT,
-	RISCV_ISA_EXT_SSTC,
+	[KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a,
+	[KVM_RISCV_ISA_EXT_C] = RISCV_ISA_EXT_c,
+	[KVM_RISCV_ISA_EXT_D] = RISCV_ISA_EXT_d,
+	[KVM_RISCV_ISA_EXT_F] = RISCV_ISA_EXT_f,
+	[KVM_RISCV_ISA_EXT_H] = RISCV_ISA_EXT_h,
+	[KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i,
+	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
+
+	KVM_ISA_EXT_ARR(SSTC),
+	KVM_ISA_EXT_ARR(SVINVAL),
+	KVM_ISA_EXT_ARR(SVPBMT),
+	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
+	KVM_ISA_EXT_ARR(ZICBOM),
 };
 
 static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -87,6 +96,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_I:
 	case KVM_RISCV_ISA_EXT_M:
 	case KVM_RISCV_ISA_EXT_SSTC:
+	case KVM_RISCV_ISA_EXT_SVINVAL:
+	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 		return false;
 	default:
 		break;
@@ -254,6 +265,11 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_CONFIG_REG(isa):
 		reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK;
 		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOM))
+			return -EINVAL;
+		reg_val = riscv_cbom_block_size;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -311,6 +327,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 			return -EOPNOTSUPP;
 		}
 		break;
+	case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size):
+		return -EOPNOTSUPP;
 	default:
 		return -EINVAL;
 	}
@@ -784,11 +802,15 @@ static void kvm_riscv_vcpu_update_config(const unsigned long *isa)
 {
 	u64 henvcfg = 0;
 
-	if (__riscv_isa_extension_available(isa, RISCV_ISA_EXT_SVPBMT))
+	if (riscv_isa_extension_available(isa, SVPBMT))
 		henvcfg |= ENVCFG_PBMTE;
 
-	if (__riscv_isa_extension_available(isa, RISCV_ISA_EXT_SSTC))
+	if (riscv_isa_extension_available(isa, SSTC))
 		henvcfg |= ENVCFG_STCE;
+
+	if (riscv_isa_extension_available(isa, ZICBOM))
+		henvcfg |= (ENVCFG_CBIE | ENVCFG_CBCFE);
+
 	csr_write(CSR_HENVCFG, henvcfg);
 #ifdef CONFIG_32BIT
 	csr_write(CSR_HENVCFGH, henvcfg >> 32);
@@ -958,7 +980,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	while (ret > 0) {
 		/* Check conditions before entering the guest */
-		cond_resched();
+		ret = xfer_to_guest_mode_handle_work(vcpu);
+		if (!ret)
+			ret = 1;
 
 		kvm_riscv_gstage_vmid_update(vcpu);
 
@@ -966,15 +990,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 		local_irq_disable();
 
-		/*
-		 * Exit if we have a signal pending so that we can deliver
-		 * the signal to user space.
-		 */
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			run->exit_reason = KVM_EXIT_INTR;
-		}
-
 		/*
 		 * Ensure we set mode to IN_GUEST_MODE after we disable
 		 * interrupts and before the final VCPU requests check.
@@ -997,7 +1012,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 		if (ret <= 0 ||
 		    kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
-		    kvm_request_pending(vcpu)) {
+		    kvm_request_pending(vcpu) ||
+		    xfer_to_guest_mode_work_pending()) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			local_irq_enable();
 			kvm_vcpu_srcu_read_lock(vcpu);

arch/riscv/kvm/vcpu_exit.c

@@ -8,6 +8,7 @@
 
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
+#include <asm/insn-def.h>
 
 static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			     struct kvm_cpu_trap *trap)
@@ -62,11 +63,7 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu,
 {
 	register unsigned long taddr asm("a0") = (unsigned long)trap;
 	register unsigned long ttmp asm("a1");
-	register unsigned long val asm("t0");
-	register unsigned long tmp asm("t1");
-	register unsigned long addr asm("t2") = guest_addr;
-	unsigned long flags;
-	unsigned long old_stvec, old_hstatus;
+	unsigned long flags, val, tmp, old_stvec, old_hstatus;
 
 	local_irq_save(flags);
 
@@ -82,29 +79,19 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu,
 			".option push\n"
 			".option norvc\n"
 			"add %[ttmp], %[taddr], 0\n"
-			/*
-			 * HLVX.HU %[val], (%[addr])
-			 * HLVX.HU t0, (t2)
-			 * 0110010 00011 00111 100 00101 1110011
-			 */
-			".word 0x6433c2f3\n"
+			HLVX_HU(%[val], %[addr])
 			"andi %[tmp], %[val], 3\n"
 			"addi %[tmp], %[tmp], -3\n"
 			"bne %[tmp], zero, 2f\n"
 			"addi %[addr], %[addr], 2\n"
-			/*
-			 * HLVX.HU %[tmp], (%[addr])
-			 * HLVX.HU t1, (t2)
-			 * 0110010 00011 00111 100 00110 1110011
-			 */
-			".word 0x6433c373\n"
+			HLVX_HU(%[tmp], %[addr])
 			"sll %[tmp], %[tmp], 16\n"
 			"add %[val], %[val], %[tmp]\n"
 			"2:\n"
 			".option pop"
 		: [val] "=&r" (val), [tmp] "=&r" (tmp),
 		  [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp),
-		  [addr] "+&r" (addr) : : "memory");
+		  [addr] "+&r" (guest_addr) : : "memory");
 
 		if (trap->scause == EXC_LOAD_PAGE_FAULT)
 			trap->scause = EXC_INST_PAGE_FAULT;
@@ -121,24 +108,14 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu,
 			".option norvc\n"
 			"add %[ttmp], %[taddr], 0\n"
 #ifdef CONFIG_64BIT
-			/*
-			 * HLV.D %[val], (%[addr])
-			 * HLV.D t0, (t2)
-			 * 0110110 00000 00111 100 00101 1110011
-			 */
-			".word 0x6c03c2f3\n"
+			HLV_D(%[val], %[addr])
 #else
-			/*
-			 * HLV.W %[val], (%[addr])
-			 * HLV.W t0, (t2)
-			 * 0110100 00000 00111 100 00101 1110011
-			 */
-			".word 0x6803c2f3\n"
+			HLV_W(%[val], %[addr])
 #endif
 			".option pop"
 		: [val] "=&r" (val),
 		  [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp)
-		: [addr] "r" (addr) : "memory");
+		: [addr] "r" (guest_addr) : "memory");
 	}
 
 	csr_write(CSR_STVEC, old_stvec);

arch/riscv/mm/dma-noncoherent.c

@@ -13,6 +13,8 @@
 #include <asm/cacheflush.h>
 
 unsigned int riscv_cbom_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
+
 static bool noncoherent_supported;
 
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,

arch/x86/include/asm/kvm_host.h

@@ -1280,8 +1280,8 @@ struct kvm_arch {
 	bool tdp_mmu_enabled;
 
 	/*
-	 * List of struct kvm_mmu_pages being used as roots.
-	 * All struct kvm_mmu_pages in the list should have
+	 * List of kvm_mmu_page structs being used as roots.
+	 * All kvm_mmu_page structs in the list should have
 	 * tdp_mmu_page set.
 	 *
 	 * For reads, this list is protected by:
@@ -1300,8 +1300,8 @@ struct kvm_arch {
 	struct list_head tdp_mmu_roots;
 
 	/*
-	 * List of struct kvmp_mmu_pages not being used as roots.
-	 * All struct kvm_mmu_pages in the list should have
+	 * List of kvm_mmu_page structs not being used as roots.
+	 * All kvm_mmu_page structs in the list should have
 	 * tdp_mmu_page set and a tdp_mmu_root_count of 0.
 	 */
 	struct list_head tdp_mmu_pages;
@@ -1311,9 +1311,9 @@ struct kvm_arch {
 	 * is held in read mode:
 	 *  - tdp_mmu_roots (above)
 	 *  - tdp_mmu_pages (above)
-	 *  - the link field of struct kvm_mmu_pages used by the TDP MMU
+	 *  - the link field of kvm_mmu_page structs used by the TDP MMU
 	 *  - lpage_disallowed_mmu_pages
-	 *  - the lpage_disallowed_link field of struct kvm_mmu_pages used
+	 *  - the lpage_disallowed_link field of kvm_mmu_page structs used
 	 *    by the TDP MMU
 	 * It is acceptable, but not necessary, to acquire this lock when
 	 * the thread holds the MMU lock in write mode.

arch/x86/include/asm/vmx.h

@@ -309,7 +309,7 @@ enum vmcs_field {
 	GUEST_LDTR_AR_BYTES             = 0x00004820,
 	GUEST_TR_AR_BYTES               = 0x00004822,
 	GUEST_INTERRUPTIBILITY_INFO     = 0x00004824,
-	GUEST_ACTIVITY_STATE            = 0X00004826,
+	GUEST_ACTIVITY_STATE            = 0x00004826,
 	GUEST_SYSENTER_CS               = 0x0000482A,
 	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
 	HOST_IA32_SYSENTER_CS           = 0x00004c00,

arch/x86/kvm/Kconfig

@@ -28,7 +28,8 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
 	select HAVE_KVM_IRQFD
-	select HAVE_KVM_DIRTY_RING
+	select HAVE_KVM_DIRTY_RING_TSO
+	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING

arch/x86/kvm/pmu.c

@@ -106,9 +106,19 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 		return;
 
 	if (pmc->perf_event && pmc->perf_event->attr.precise_ip) {
+		if (!in_pmi) {
+			/*
+			 * TODO: KVM is currently _choosing_ to not generate records
+			 * for emulated instructions, avoiding BUFFER_OVF PMI when
+			 * there are no records. Strictly speaking, it should be done
+			 * as well in the right context to improve sampling accuracy.
+			 */
+			skip_pmi = true;
+		} else {
 			/* Indicate PEBS overflow PMI to guest. */
 			skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT,
 						      (unsigned long *)&pmu->global_status);
+		}
 	} else {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 	}
@@ -227,8 +237,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 			      get_sample_period(pmc, pmc->counter)))
 		return false;
 
-	if (!test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) &&
-	    pmc->perf_event->attr.precise_ip)
+	if (test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) !=
+	    (!!pmc->perf_event->attr.precise_ip))
 		return false;
 
 	/* reuse perf_event to serve as pmc_reprogram_counter() does*/

arch/x86/kvm/svm/pmu.c

@@ -23,107 +23,52 @@ enum pmu_type {
 	PMU_TYPE_EVNTSEL,
 };
 
-enum index {
-	INDEX_ZERO = 0,
-	INDEX_ONE,
-	INDEX_TWO,
-	INDEX_THREE,
-	INDEX_FOUR,
-	INDEX_FIVE,
-	INDEX_ERROR,
-};
-
-static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type)
+static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 {
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int num_counters = pmu->nr_arch_gp_counters;
 
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
-		if (type == PMU_TYPE_COUNTER)
-			return MSR_F15H_PERF_CTR;
-		else
-			return MSR_F15H_PERF_CTL;
-	} else {
-		if (type == PMU_TYPE_COUNTER)
-			return MSR_K7_PERFCTR0;
-		else
-			return MSR_K7_EVNTSEL0;
-	}
-}
+	if (pmc_idx >= num_counters)
+		return NULL;
 
-static enum index msr_to_index(u32 msr)
-{
-	switch (msr) {
-	case MSR_F15H_PERF_CTL0:
-	case MSR_F15H_PERF_CTR0:
-	case MSR_K7_EVNTSEL0:
-	case MSR_K7_PERFCTR0:
-		return INDEX_ZERO;
-	case MSR_F15H_PERF_CTL1:
-	case MSR_F15H_PERF_CTR1:
-	case MSR_K7_EVNTSEL1:
-	case MSR_K7_PERFCTR1:
-		return INDEX_ONE;
-	case MSR_F15H_PERF_CTL2:
-	case MSR_F15H_PERF_CTR2:
-	case MSR_K7_EVNTSEL2:
-	case MSR_K7_PERFCTR2:
-		return INDEX_TWO;
-	case MSR_F15H_PERF_CTL3:
-	case MSR_F15H_PERF_CTR3:
-	case MSR_K7_EVNTSEL3:
-	case MSR_K7_PERFCTR3:
-		return INDEX_THREE;
-	case MSR_F15H_PERF_CTL4:
-	case MSR_F15H_PERF_CTR4:
-		return INDEX_FOUR;
-	case MSR_F15H_PERF_CTL5:
-	case MSR_F15H_PERF_CTR5:
-		return INDEX_FIVE;
-	default:
-		return INDEX_ERROR;
-	}
+	return &pmu->gp_counters[array_index_nospec(pmc_idx, num_counters)];
 }
 
 static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 					     enum pmu_type type)
 {
 	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int idx;
 
 	if (!vcpu->kvm->arch.enable_pmu)
 		return NULL;
 
 	switch (msr) {
-	case MSR_F15H_PERF_CTL0:
-	case MSR_F15H_PERF_CTL1:
-	case MSR_F15H_PERF_CTL2:
-	case MSR_F15H_PERF_CTL3:
-	case MSR_F15H_PERF_CTL4:
-	case MSR_F15H_PERF_CTL5:
+	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
 		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
 			return NULL;
-		fallthrough;
+		/*
+		 * Each PMU counter has a pair of CTL and CTR MSRs. CTLn
+		 * MSRs (accessed via EVNTSEL) are even, CTRn MSRs are odd.
+		 */
+		idx = (unsigned int)((msr - MSR_F15H_PERF_CTL0) / 2);
+		if (!(msr & 0x1) != (type == PMU_TYPE_EVNTSEL))
+			return NULL;
+		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 		if (type != PMU_TYPE_EVNTSEL)
 			return NULL;
+		idx = msr - MSR_K7_EVNTSEL0;
 		break;
-	case MSR_F15H_PERF_CTR0:
-	case MSR_F15H_PERF_CTR1:
-	case MSR_F15H_PERF_CTR2:
-	case MSR_F15H_PERF_CTR3:
-	case MSR_F15H_PERF_CTR4:
-	case MSR_F15H_PERF_CTR5:
-		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
-			return NULL;
-		fallthrough;
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 		if (type != PMU_TYPE_COUNTER)
 			return NULL;
+		idx = msr - MSR_K7_PERFCTR0;
 		break;
 	default:
 		return NULL;
 	}
 
-	return &pmu->gp_counters[msr_to_index(msr)];
+	return amd_pmc_idx_to_pmc(pmu, idx);
 }
 
 static bool amd_hw_event_available(struct kvm_pmc *pmc)
@@ -139,22 +84,6 @@ static bool amd_pmc_is_enabled(struct kvm_pmc *pmc)
 	return true;
 }
 
-static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
-{
-	unsigned int base = get_msr_base(pmu, PMU_TYPE_COUNTER);
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
-		/*
-		 * The idx is contiguous. The MSRs are not. The counter MSRs
-		 * are interleaved with the event select MSRs.
-		 */
-		pmc_idx *= 2;
-	}
-
-	return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER);
-}
-
 static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -168,15 +97,7 @@ static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	unsigned int idx, u64 *mask)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *counters;
-
-	idx &= ~(3u << 30);
-	if (idx >= pmu->nr_arch_gp_counters)
-		return NULL;
-	counters = pmu->gp_counters;
-
-	return &counters[idx];
+	return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30));
 }
 
 static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)

arch/x86/kvm/vmx/pmu_intel.c

@@ -68,15 +68,11 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 	}
 }
 
-/* function is called when global control register has been updated. */
-static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+static void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
 {
 	int bit;
-	u64 diff = pmu->global_ctrl ^ data;
 	struct kvm_pmc *pmc;
 
-	pmu->global_ctrl = data;
-
 	for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) {
 		pmc = intel_pmc_idx_to_pmc(pmu, bit);
 		if (pmc)
@@ -397,7 +393,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct kvm_pmc *pmc;
 	u32 msr = msr_info->index;
 	u64 data = msr_info->data;
-	u64 reserved_bits;
+	u64 reserved_bits, diff;
 
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -418,7 +414,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->global_ctrl == data)
 			return 0;
 		if (kvm_valid_perf_global_ctrl(pmu, data)) {
-			global_ctrl_changed(pmu, data);
+			diff = pmu->global_ctrl ^ data;
+			pmu->global_ctrl = data;
+			reprogram_counters(pmu, diff);
 			return 0;
 		}
 		break;
@@ -433,7 +431,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->pebs_enable == data)
 			return 0;
 		if (!(data & pmu->pebs_enable_mask)) {
+			diff = pmu->pebs_enable ^ data;
 			pmu->pebs_enable = data;
+			reprogram_counters(pmu, diff);
 			return 0;
 		}
 		break;
@@ -776,20 +776,23 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
 void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
 {
 	struct kvm_pmc *pmc = NULL;
-	int bit;
+	int bit, hw_idx;
 
 	for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl,
 			 X86_PMC_IDX_MAX) {
 		pmc = intel_pmc_idx_to_pmc(pmu, bit);
 
 		if (!pmc || !pmc_speculative_in_use(pmc) ||
-		    !intel_pmc_is_enabled(pmc))
+		    !intel_pmc_is_enabled(pmc) || !pmc->perf_event)
 			continue;
 
-		if (pmc->perf_event && pmc->idx != pmc->perf_event->hw.idx) {
-			pmu->host_cross_mapped_mask |=
-				BIT_ULL(pmc->perf_event->hw.idx);
-		}
+		/*
+		 * A negative index indicates the event isn't mapped to a
+		 * physical counter in the host, e.g. due to contention.
+		 */
+		hw_idx = pmc->perf_event->hw.idx;
+		if (hw_idx != pmc->idx && hw_idx > -1)
+			pmu->host_cross_mapped_mask |= BIT_ULL(hw_idx);
 	}
 }
 

include/uapi/linux/kvm.h

@@ -1177,6 +1177,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
 #define KVM_CAP_S390_ZPCI_OP 221
 #define KVM_CAP_S390_CPU_TOPOLOGY 222
+#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/testing/selftests/kvm/.gitignore

 # SPDX-License-Identifier: GPL-2.0-only
+/aarch64/aarch32_id_regs
 /aarch64/arch_timer
 /aarch64/debug-exceptions
 /aarch64/get-reg-list

tools/testing/selftests/kvm/Makefile

@@ -147,6 +147,7 @@ TEST_GEN_PROGS_x86_64 += system_counter_offset_test
 # Compiled outputs used by test targets
 TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test
 
+TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs
 TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list

tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * aarch32_id_regs - Test for ID register behavior on AArch64-only systems
+ *
+ * Copyright (c) 2022 Google LLC.
+ *
+ * Test that KVM handles the AArch64 views of the AArch32 ID registers as RAZ
+ * and WI from userspace.
+ */
+
+#include <stdint.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define BAD_ID_REG_VAL	0x1badc0deul
+
+#define GUEST_ASSERT_REG_RAZ(reg)	GUEST_ASSERT_EQ(read_sysreg_s(reg), 0)
+
+static void guest_main(void)
+{
+	GUEST_ASSERT_REG_RAZ(SYS_ID_PFR0_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_PFR1_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_DFR0_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_AFR0_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_MMFR0_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_MMFR1_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_MMFR2_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_MMFR3_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR0_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR1_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR2_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR3_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR4_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR5_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_MMFR4_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_ISAR6_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_MVFR0_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_MVFR1_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_MVFR2_EL1);
+	GUEST_ASSERT_REG_RAZ(sys_reg(3, 0, 0, 3, 3));
+	GUEST_ASSERT_REG_RAZ(SYS_ID_PFR2_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_DFR1_EL1);
+	GUEST_ASSERT_REG_RAZ(SYS_ID_MMFR5_EL1);
+	GUEST_ASSERT_REG_RAZ(sys_reg(3, 0, 0, 3, 7));
+
+	GUEST_DONE();
+}
+
+static void test_guest_raz(struct kvm_vcpu *vcpu)
+{
+	struct ucall uc;
+
+	vcpu_run(vcpu);
+
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	case UCALL_DONE:
+		break;
+	default:
+		TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
+	}
+}
+
+static uint64_t raz_wi_reg_ids[] = {
+	KVM_ARM64_SYS_REG(SYS_ID_PFR0_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_PFR1_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_DFR0_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_MMFR0_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_MMFR1_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_MMFR2_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_MMFR3_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR0_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR1_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR2_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR3_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR4_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR5_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_MMFR4_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_ISAR6_EL1),
+	KVM_ARM64_SYS_REG(SYS_MVFR0_EL1),
+	KVM_ARM64_SYS_REG(SYS_MVFR1_EL1),
+	KVM_ARM64_SYS_REG(SYS_MVFR2_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_PFR2_EL1),
+	KVM_ARM64_SYS_REG(SYS_ID_MMFR5_EL1),
+};
+
+static void test_user_raz_wi(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(raz_wi_reg_ids); i++) {
+		uint64_t reg_id = raz_wi_reg_ids[i];
+		uint64_t val;
+
+		vcpu_get_reg(vcpu, reg_id, &val);
+		ASSERT_EQ(val, 0);
+
+		/*
+		 * Expect the ioctl to succeed with no effect on the register
+		 * value.
+		 */
+		vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL);
+
+		vcpu_get_reg(vcpu, reg_id, &val);
+		ASSERT_EQ(val, 0);
+	}
+}
+
+static uint64_t raz_invariant_reg_ids[] = {
+	KVM_ARM64_SYS_REG(SYS_ID_AFR0_EL1),
+	KVM_ARM64_SYS_REG(sys_reg(3, 0, 0, 3, 3)),
+	KVM_ARM64_SYS_REG(SYS_ID_DFR1_EL1),
+	KVM_ARM64_SYS_REG(sys_reg(3, 0, 0, 3, 7)),
+};
+
+static void test_user_raz_invariant(struct kvm_vcpu *vcpu)
+{
+	int i, r;
+
+	for (i = 0; i < ARRAY_SIZE(raz_invariant_reg_ids); i++) {
+		uint64_t reg_id = raz_invariant_reg_ids[i];
+		uint64_t val;
+
+		vcpu_get_reg(vcpu, reg_id, &val);
+		ASSERT_EQ(val, 0);
+
+		r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL);
+		TEST_ASSERT(r < 0 && errno == EINVAL,
+			    "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno);
+
+		vcpu_get_reg(vcpu, reg_id, &val);
+		ASSERT_EQ(val, 0);
+	}
+}
+
+
+
+static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
+{
+	uint64_t val, el0;
+
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
+
+	el0 = (val & ARM64_FEATURE_MASK(ID_AA64PFR0_EL0)) >> ID_AA64PFR0_EL0_SHIFT;
+	return el0 == ID_AA64PFR0_ELx_64BIT_ONLY;
+}
+
+int main(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
+
+	TEST_REQUIRE(vcpu_aarch64_only(vcpu));
+
+	ucall_init(vm, NULL);
+
+	test_user_raz_wi(vcpu);
+	test_user_raz_invariant(vcpu);
+	test_guest_raz(vcpu);
+
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+}

tools/testing/selftests/kvm/aarch64/debug-exceptions.c

@@ -22,6 +22,7 @@
 #define SPSR_SS		(1 << 21)
 
 extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start;
+extern unsigned char iter_ss_begin, iter_ss_end;
 static volatile uint64_t sw_bp_addr, hw_bp_addr;
 static volatile uint64_t wp_addr, wp_data_addr;
 static volatile uint64_t svc_addr;
@@ -238,6 +239,46 @@ static void guest_svc_handler(struct ex_regs *regs)
 	svc_addr = regs->pc;
 }
 
+enum single_step_op {
+	SINGLE_STEP_ENABLE = 0,
+	SINGLE_STEP_DISABLE = 1,
+};
+
+static void guest_code_ss(int test_cnt)
+{
+	uint64_t i;
+	uint64_t bvr, wvr, w_bvr, w_wvr;
+
+	for (i = 0; i < test_cnt; i++) {
+		/* Bits [1:0] of dbg{b,w}vr are RES0 */
+		w_bvr = i << 2;
+		w_wvr = i << 2;
+
+		/* Enable Single Step execution */
+		GUEST_SYNC(SINGLE_STEP_ENABLE);
+
+		/*
+		 * The userspace will veriry that the pc is as expected during
+		 * single step execution between iter_ss_begin and iter_ss_end.
+		 */
+		asm volatile("iter_ss_begin:nop\n");
+
+		write_sysreg(w_bvr, dbgbvr0_el1);
+		write_sysreg(w_wvr, dbgwvr0_el1);
+		bvr = read_sysreg(dbgbvr0_el1);
+		wvr = read_sysreg(dbgwvr0_el1);
+
+		asm volatile("iter_ss_end:\n");
+
+		/* Disable Single Step execution */
+		GUEST_SYNC(SINGLE_STEP_DISABLE);
+
+		GUEST_ASSERT(bvr == w_bvr);
+		GUEST_ASSERT(wvr == w_wvr);
+	}
+	GUEST_DONE();
+}
+
 static int debug_version(struct kvm_vcpu *vcpu)
 {
 	uint64_t id_aa64dfr0;
@@ -246,7 +287,7 @@ static int debug_version(struct kvm_vcpu *vcpu)
 	return id_aa64dfr0 & 0xf;
 }
 
-int main(int argc, char *argv[])
+static void test_guest_debug_exceptions(void)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
@@ -259,9 +300,6 @@ int main(int argc, char *argv[])
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vcpu);
 
-	__TEST_REQUIRE(debug_version(vcpu) >= 6,
-		       "Armv8 debug architecture not supported.");
-
 	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
 				ESR_EC_BRK_INS, guest_sw_bp_handler);
 	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
@@ -294,5 +332,108 @@ int main(int argc, char *argv[])
 
 done:
 	kvm_vm_free(vm);
+}
+
+void test_single_step_from_userspace(int test_cnt)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	struct kvm_run *run;
+	uint64_t pc, cmd;
+	uint64_t test_pc = 0;
+	bool ss_enable = false;
+	struct kvm_guest_debug debug = {};
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_ss);
+	ucall_init(vm, NULL);
+	run = vcpu->run;
+	vcpu_args_set(vcpu, 1, test_cnt);
+
+	while (1) {
+		vcpu_run(vcpu);
+		if (run->exit_reason != KVM_EXIT_DEBUG) {
+			cmd = get_ucall(vcpu, &uc);
+			if (cmd == UCALL_ABORT) {
+				REPORT_GUEST_ASSERT(uc);
+				/* NOT REACHED */
+			} else if (cmd == UCALL_DONE) {
+				break;
+			}
+
+			TEST_ASSERT(cmd == UCALL_SYNC,
+				    "Unexpected ucall cmd 0x%lx", cmd);
+
+			if (uc.args[1] == SINGLE_STEP_ENABLE) {
+				debug.control = KVM_GUESTDBG_ENABLE |
+						KVM_GUESTDBG_SINGLESTEP;
+				ss_enable = true;
+			} else {
+				debug.control = SINGLE_STEP_DISABLE;
+				ss_enable = false;
+			}
+
+			vcpu_guest_debug_set(vcpu, &debug);
+			continue;
+		}
+
+		TEST_ASSERT(ss_enable, "Unexpected KVM_EXIT_DEBUG");
+
+		/* Check if the current pc is expected. */
+		vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc);
+		TEST_ASSERT(!test_pc || pc == test_pc,
+			    "Unexpected pc 0x%lx (expected 0x%lx)",
+			    pc, test_pc);
+
+		/*
+		 * If the current pc is between iter_ss_bgin and
+		 * iter_ss_end, the pc for the next KVM_EXIT_DEBUG should
+		 * be the current pc + 4.
+		 */
+		if ((pc >= (uint64_t)&iter_ss_begin) &&
+		    (pc < (uint64_t)&iter_ss_end))
+			test_pc = pc + 4;
+		else
+			test_pc = 0;
+	}
+
+	kvm_vm_free(vm);
+}
+
+static void help(char *name)
+{
+	puts("");
+	printf("Usage: %s [-h] [-i iterations of the single step test]\n", name);
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	int opt;
+	int ss_iteration = 10000;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+	__TEST_REQUIRE(debug_version(vcpu) >= 6,
+		       "Armv8 debug architecture not supported.");
+	kvm_vm_free(vm);
+
+	while ((opt = getopt(argc, argv, "i:")) != -1) {
+		switch (opt) {
+		case 'i':
+			ss_iteration = atoi(optarg);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	test_guest_debug_exceptions();
+	test_single_step_from_userspace(ss_iteration);
+
 	return 0;
 }

tools/testing/selftests/kvm/aarch64/psci_test.c

 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the
- * CPU_ON PSCI call matches what the caller requested.
+ * psci_test - Tests relating to KVM's PSCI implementation.
  *
  * Copyright (c) 2021 Google LLC.
  *
- * This is a regression test for a race between KVM servicing the PSCI call and
- * userspace reading the vCPUs registers.
+ * This test includes:
+ *  - A regression test for a race between KVM servicing the PSCI CPU_ON call
+ *    and userspace reading the targeted vCPU's registers.
+ *  - A test for KVM's handling of PSCI SYSTEM_SUSPEND and the associated
+ *    KVM_SYSTEM_EVENT_SUSPEND UAPI.
  */
 
 #define _GNU_SOURCE

tools/testing/selftests/kvm/dirty_log_test.c

@@ -17,6 +17,7 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/atomic.h>
+#include <asm/barrier.h>
 
 #include "kvm_util.h"
 #include "test_util.h"
@@ -264,7 +265,8 @@ static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 
 static bool dirty_ring_supported(void)
 {
-	return kvm_has_cap(KVM_CAP_DIRTY_LOG_RING);
+	return (kvm_has_cap(KVM_CAP_DIRTY_LOG_RING) ||
+		kvm_has_cap(KVM_CAP_DIRTY_LOG_RING_ACQ_REL));
 }
 
 static void dirty_ring_create_vm_done(struct kvm_vm *vm)
@@ -279,12 +281,12 @@ static void dirty_ring_create_vm_done(struct kvm_vm *vm)
 
 static inline bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn)
 {
-	return gfn->flags == KVM_DIRTY_GFN_F_DIRTY;
+	return smp_load_acquire(&gfn->flags) == KVM_DIRTY_GFN_F_DIRTY;
 }
 
 static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn)
 {
-	gfn->flags = KVM_DIRTY_GFN_F_RESET;
+	smp_store_release(&gfn->flags, KVM_DIRTY_GFN_F_RESET);
 }
 
 static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,

tools/testing/selftests/kvm/include/kvm_util_base.h

@@ -175,6 +175,10 @@ extern const struct vm_guest_mode_params vm_guest_mode_params[];
 
 int open_path_or_exit(const char *path, int flags);
 int open_kvm_dev_path_or_exit(void);
+
+bool get_kvm_intel_param_bool(const char *param);
+bool get_kvm_amd_param_bool(const char *param);
+
 unsigned int kvm_check_cap(long cap);
 
 static inline bool kvm_has_cap(long cap)

tools/testing/selftests/kvm/include/test_util.h

@@ -63,8 +63,10 @@ void test_assert(bool exp, const char *exp_str,
 		    #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
 } while (0)
 
-#define TEST_FAIL(fmt, ...) \
-	TEST_ASSERT(false, fmt, ##__VA_ARGS__)
+#define TEST_FAIL(fmt, ...) do { \
+	TEST_ASSERT(false, fmt, ##__VA_ARGS__); \
+	__builtin_unreachable(); \
+} while (0)
 
 size_t parse_size(const char *size);
 

tools/testing/selftests/kvm/include/x86_64/processor.h

@@ -825,6 +825,8 @@ static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val)
 	return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr));
 }
 
+bool kvm_is_tdp_enabled(void);
+
 uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
 				 uint64_t vaddr);
 void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
@@ -855,6 +857,8 @@ enum pg_level {
 #define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
 
 void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
+void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+		    uint64_t nr_bytes, int level);
 
 /*
  * Basic CPU control in CR0

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -50,6 +50,45 @@ int open_kvm_dev_path_or_exit(void)
 	return _open_kvm_dev_path_or_exit(O_RDONLY);
 }
 
+static bool get_module_param_bool(const char *module_name, const char *param)
+{
+	const int path_size = 128;
+	char path[path_size];
+	char value;
+	ssize_t r;
+	int fd;
+
+	r = snprintf(path, path_size, "/sys/module/%s/parameters/%s",
+		     module_name, param);
+	TEST_ASSERT(r < path_size,
+		    "Failed to construct sysfs path in %d bytes.", path_size);
+
+	fd = open_path_or_exit(path, O_RDONLY);
+
+	r = read(fd, &value, 1);
+	TEST_ASSERT(r == 1, "read(%s) failed", path);
+
+	r = close(fd);
+	TEST_ASSERT(!r, "close(%s) failed", path);
+
+	if (value == 'Y')
+		return true;
+	else if (value == 'N')
+		return false;
+
+	TEST_FAIL("Unrecognized value '%c' for boolean module param", value);
+}
+
+bool get_kvm_intel_param_bool(const char *param)
+{
+	return get_module_param_bool("kvm_intel", param);
+}
+
+bool get_kvm_amd_param_bool(const char *param)
+{
+	return get_module_param_bool("kvm_amd", param);
+}
+
 /*
  * Capability
  *
@@ -82,6 +121,9 @@ unsigned int kvm_check_cap(long cap)
 
 void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
 {
+	if (vm_check_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL))
+		vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL, ring_size);
+	else
 		vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING, ring_size);
 	vm->dirty_ring_size = ring_size;
 }

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -111,6 +111,14 @@ static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent)
 	}
 }
 
+bool kvm_is_tdp_enabled(void)
+{
+	if (is_intel_cpu())
+		return get_kvm_intel_param_bool("ept");
+	else
+		return get_kvm_amd_param_bool("npt");
+}
+
 void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
@@ -214,6 +222,25 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 	__virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K);
 }
 
+void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+		    uint64_t nr_bytes, int level)
+{
+	uint64_t pg_size = PG_LEVEL_SIZE(level);
+	uint64_t nr_pages = nr_bytes / pg_size;
+	int i;
+
+	TEST_ASSERT(nr_bytes % pg_size == 0,
+		    "Region size not aligned: nr_bytes: 0x%lx, page size: 0x%lx",
+		    nr_bytes, pg_size);
+
+	for (i = 0; i < nr_pages; i++) {
+		__virt_pg_map(vm, vaddr, paddr, level);
+
+		vaddr += pg_size;
+		paddr += pg_size;
+	}
+}
+
 static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm,
 					  struct kvm_vcpu *vcpu,
 					  uint64_t vaddr)
@@ -1294,20 +1321,9 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
 /* Returns true if kvm_intel was loaded with unrestricted_guest=1. */
 bool vm_is_unrestricted_guest(struct kvm_vm *vm)
 {
-	char val = 'N';
-	size_t count;
-	FILE *f;
-
 	/* Ensure that a KVM vendor-specific module is loaded. */
 	if (vm == NULL)
 		close(open_kvm_dev_path_or_exit());
 
-	f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r");
-	if (f) {
-		count = fread(&val, sizeof(char), 1, f);
-		TEST_ASSERT(count == 1, "Unable to read from param file.");
-		fclose(f);
-	}
-
-	return val == 'Y';
+	return get_kvm_intel_param_bool("unrestricted_guest");
 }

tools/testing/selftests/kvm/lib/x86_64/svm.c

@@ -60,18 +60,6 @@ static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector,
 	seg->base = base;
 }
 
-/*
- * Avoid using memset to clear the vmcb, since libc may not be
- * available in L1 (and, even if it is, features that libc memset may
- * want to use, like AVX, may not be enabled).
- */
-static void clear_vmcb(struct vmcb *vmcb)
-{
-	int n = sizeof(*vmcb) / sizeof(u32);
-
-	asm volatile ("rep stosl" : "+c"(n), "+D"(vmcb) : "a"(0) : "memory");
-}
-
 void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp)
 {
 	struct vmcb *vmcb = svm->vmcb;
@@ -88,7 +76,7 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r
 	wrmsr(MSR_EFER, efer | EFER_SVME);
 	wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa);
 
-	clear_vmcb(vmcb);
+	memset(vmcb, 0, sizeof(*vmcb));
 	asm volatile ("vmsave %0\n\t" : : "a" (vmcb_gpa) : "memory");
 	vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr);
 	vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr);

tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c

@@ -17,84 +17,70 @@
 /* VMCALL and VMMCALL are both 3-byte opcodes. */
 #define HYPERCALL_INSN_SIZE	3
 
-static bool ud_expected;
+static bool quirk_disabled;
 
 static void guest_ud_handler(struct ex_regs *regs)
 {
-	GUEST_ASSERT(ud_expected);
-	GUEST_DONE();
+	regs->rax = -EFAULT;
+	regs->rip += HYPERCALL_INSN_SIZE;
 }
 
-extern uint8_t svm_hypercall_insn[HYPERCALL_INSN_SIZE];
-static uint64_t svm_do_sched_yield(uint8_t apic_id)
-{
-	uint64_t ret;
+static const uint8_t vmx_vmcall[HYPERCALL_INSN_SIZE]  = { 0x0f, 0x01, 0xc1 };
+static const uint8_t svm_vmmcall[HYPERCALL_INSN_SIZE] = { 0x0f, 0x01, 0xd9 };
 
-	asm volatile("mov %1, %%rax\n\t"
-		     "mov %2, %%rbx\n\t"
-		     "svm_hypercall_insn:\n\t"
-		     "vmmcall\n\t"
-		     "mov %%rax, %0\n\t"
-		     : "=r"(ret)
-		     : "r"((uint64_t)KVM_HC_SCHED_YIELD), "r"((uint64_t)apic_id)
-		     : "rax", "rbx", "memory");
-
-	return ret;
-}
-
-extern uint8_t vmx_hypercall_insn[HYPERCALL_INSN_SIZE];
-static uint64_t vmx_do_sched_yield(uint8_t apic_id)
+extern uint8_t hypercall_insn[HYPERCALL_INSN_SIZE];
+static uint64_t do_sched_yield(uint8_t apic_id)
 {
 	uint64_t ret;
 
-	asm volatile("mov %1, %%rax\n\t"
-		     "mov %2, %%rbx\n\t"
-		     "vmx_hypercall_insn:\n\t"
-		     "vmcall\n\t"
-		     "mov %%rax, %0\n\t"
-		     : "=r"(ret)
-		     : "r"((uint64_t)KVM_HC_SCHED_YIELD), "r"((uint64_t)apic_id)
-		     : "rax", "rbx", "memory");
+	asm volatile("hypercall_insn:\n\t"
+		     ".byte 0xcc,0xcc,0xcc\n\t"
+		     : "=a"(ret)
+		     : "a"((uint64_t)KVM_HC_SCHED_YIELD), "b"((uint64_t)apic_id)
+		     : "memory");
 
 	return ret;
 }
 
 static void guest_main(void)
 {
-	uint8_t *native_hypercall_insn, *hypercall_insn;
-	uint8_t apic_id;
-
-	apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID));
+	const uint8_t *native_hypercall_insn;
+	const uint8_t *other_hypercall_insn;
+	uint64_t ret;
 
 	if (is_intel_cpu()) {
-		native_hypercall_insn = vmx_hypercall_insn;
-		hypercall_insn = svm_hypercall_insn;
-		svm_do_sched_yield(apic_id);
+		native_hypercall_insn = vmx_vmcall;
+		other_hypercall_insn  = svm_vmmcall;
 	} else if (is_amd_cpu()) {
-		native_hypercall_insn = svm_hypercall_insn;
-		hypercall_insn = vmx_hypercall_insn;
-		vmx_do_sched_yield(apic_id);
+		native_hypercall_insn = svm_vmmcall;
+		other_hypercall_insn  = vmx_vmcall;
 	} else {
 		GUEST_ASSERT(0);
 		/* unreachable */
 		return;
 	}
 
+	memcpy(hypercall_insn, other_hypercall_insn, HYPERCALL_INSN_SIZE);
+
+	ret = do_sched_yield(GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID)));
+
 	/*
-	 * The hypercall didn't #UD (guest_ud_handler() signals "done" if a #UD
-	 * occurs).  Verify that a #UD is NOT expected and that KVM patched in
-	 * the native hypercall.
+	 * If the quirk is disabled, verify that guest_ud_handler() "returned"
+	 * -EFAULT and that KVM did NOT patch the hypercall.  If the quirk is
+	 * enabled, verify that the hypercall succeeded and that KVM patched in
+	 * the "right" hypercall.
 	 */
-	GUEST_ASSERT(!ud_expected);
-	GUEST_ASSERT(!memcmp(native_hypercall_insn, hypercall_insn, HYPERCALL_INSN_SIZE));
-	GUEST_DONE();
-}
+	if (quirk_disabled) {
+		GUEST_ASSERT(ret == (uint64_t)-EFAULT);
+		GUEST_ASSERT(!memcmp(other_hypercall_insn, hypercall_insn,
+			     HYPERCALL_INSN_SIZE));
+	} else {
+		GUEST_ASSERT(!ret);
+		GUEST_ASSERT(!memcmp(native_hypercall_insn, hypercall_insn,
+			     HYPERCALL_INSN_SIZE));
+	}
 
-static void setup_ud_vector(struct kvm_vcpu *vcpu)
-{
-	vm_init_descriptor_tables(vcpu->vm);
-	vcpu_init_descriptor_tables(vcpu);
-	vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler);
+	GUEST_DONE();
 }
 
 static void enter_guest(struct kvm_vcpu *vcpu)
@@ -117,35 +103,23 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void test_fix_hypercall(void)
+static void test_fix_hypercall(bool disable_quirk)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
-	setup_ud_vector(vcpu);
-
-	ud_expected = false;
-	sync_global_to_guest(vm, ud_expected);
-
-	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
-
-	enter_guest(vcpu);
-}
 
-static void test_fix_hypercall_disabled(void)
-{
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-
-	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
-	setup_ud_vector(vcpu);
+	vm_init_descriptor_tables(vcpu->vm);
+	vcpu_init_descriptor_tables(vcpu);
+	vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler);
 
+	if (disable_quirk)
 		vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2,
 			      KVM_X86_QUIRK_FIX_HYPERCALL_INSN);
 
-	ud_expected = true;
-	sync_global_to_guest(vm, ud_expected);
+	quirk_disabled = disable_quirk;
+	sync_global_to_guest(vm, quirk_disabled);
 
 	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
 
@@ -156,6 +130,6 @@ int main(void)
 {
 	TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN);
 
-	test_fix_hypercall();
-	test_fix_hypercall_disabled();
+	test_fix_hypercall(false);
+	test_fix_hypercall(true);
 }

tools/testing/selftests/kvm/x86_64/hyperv_features.c

@@ -26,7 +26,8 @@ static inline uint8_t hypercall(u64 control, vm_vaddr_t input_address,
 		     : "=a" (*hv_status),
 		       "+c" (control), "+d" (input_address),
 		       KVM_ASM_SAFE_OUTPUTS(vector)
-		     : [output_address] "r"(output_address)
+		     : [output_address] "r"(output_address),
+		       "a" (-EFAULT)
 		     : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS);
 	return vector;
 }
@@ -81,13 +82,13 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 	}
 
 	vector = hypercall(hcall->control, input, output, &res);
-	if (hcall->ud_expected)
+	if (hcall->ud_expected) {
 		GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector);
-	else
+	} else {
 		GUEST_ASSERT_2(!vector, hcall->control, vector);
+		GUEST_ASSERT_2(res == hcall->expect, hcall->expect, res);
+	}
 
-	GUEST_ASSERT_2(!hcall->ud_expected || res == hcall->expect,
-			hcall->expect, res);
 	GUEST_DONE();
 }
 
@@ -507,7 +508,7 @@ static void guest_test_hcalls_access(void)
 		switch (stage) {
 		case 0:
 			feat->eax |= HV_MSR_HYPERCALL_AVAILABLE;
-			hcall->control = 0xdeadbeef;
+			hcall->control = 0xbeef;
 			hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE;
 			break;
 

tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c

@@ -112,6 +112,7 @@ void run_test(int reclaim_period_ms, bool disable_nx_huge_pages,
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
+	uint64_t nr_bytes;
 	void *hva;
 	int r;
 
@@ -134,10 +135,24 @@ void run_test(int reclaim_period_ms, bool disable_nx_huge_pages,
 				    HPAGE_GPA, HPAGE_SLOT,
 				    HPAGE_SLOT_NPAGES, 0);
 
-	virt_map(vm, HPAGE_GVA, HPAGE_GPA, HPAGE_SLOT_NPAGES);
+	nr_bytes = HPAGE_SLOT_NPAGES * vm->page_size;
+
+	/*
+	 * Ensure that KVM can map HPAGE_SLOT with huge pages by mapping the
+	 * region into the guest with 2MiB pages whenever TDP is disabled (i.e.
+	 * whenever KVM is shadowing the guest page tables).
+	 *
+	 * When TDP is enabled, KVM should be able to map HPAGE_SLOT with huge
+	 * pages irrespective of the guest page size, so map with 4KiB pages
+	 * to test that that is the case.
+	 */
+	if (kvm_is_tdp_enabled())
+		virt_map_level(vm, HPAGE_GVA, HPAGE_GPA, nr_bytes, PG_LEVEL_4K);
+	else
+		virt_map_level(vm, HPAGE_GVA, HPAGE_GPA, nr_bytes, PG_LEVEL_2M);
 
 	hva = addr_gpa2hva(vm, HPAGE_GPA);
-	memset(hva, RETURN_OPCODE, HPAGE_SLOT_NPAGES * PAGE_SIZE);
+	memset(hva, RETURN_OPCODE, nr_bytes);
 
 	check_2m_page_count(vm, 0);
 	check_split_count(vm, 0);

virt/kvm/Kconfig

@@ -19,6 +19,20 @@ config HAVE_KVM_IRQ_ROUTING
 config HAVE_KVM_DIRTY_RING
        bool
 
+# Only strongly ordered architectures can select this, as it doesn't
+# put any explicit constraint on userspace ordering. They can also
+# select the _ACQ_REL version.
+config HAVE_KVM_DIRTY_RING_TSO
+       bool
+       select HAVE_KVM_DIRTY_RING
+       depends on X86
+
+# Weakly ordered architectures can only select this, advertising
+# to userspace the additional ordering requirements.
+config HAVE_KVM_DIRTY_RING_ACQ_REL
+       bool
+       select HAVE_KVM_DIRTY_RING
+
 config HAVE_KVM_EVENTFD
        bool
        select EVENTFD

virt/kvm/dirty_ring.c

@@ -74,7 +74,7 @@ int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
 
 static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
 {
-	gfn->flags = 0;
+	smp_store_release(&gfn->flags, 0);
 }
 
 static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
@@ -84,7 +84,7 @@ static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
 
 static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
 {
-	return gfn->flags & KVM_DIRTY_GFN_F_RESET;
+	return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET;
 }
 
 int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)

virt/kvm/kvm_main.c

@@ -4473,7 +4473,13 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
 	case KVM_CAP_DIRTY_LOG_RING:
-#ifdef CONFIG_HAVE_KVM_DIRTY_RING
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO
+		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+		return 0;
+#endif
+	case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL
 		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
 #else
 		return 0;
@@ -4578,6 +4584,7 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 		return 0;
 	}
 	case KVM_CAP_DIRTY_LOG_RING:
+	case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
 		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);