Merge tag 'kvmarm-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 5.19

- Add support for the ARMv8.6 WFxT extension

- Guard pages for the EL2 stacks

- Trap and emulate AArch32 ID registers to hide unsupported features

- Ability to select and save/restore the set of hypercalls exposed
  to the guest

- Support for PSCI-initiated suspend in collaboration with userspace

- GICv3 register-based LPI invalidation support

- Move host PMU event merging into the vcpu data structure

- GICv3 ITS save/restore fixes

- The usual set of small-scale cleanups and fixes

[Due to the conflict, KVM_SYSTEM_EVENT_SEV_TERM is relocated
 from 4 to 6. - Paolo]

9 files changed, 120 insertions, 31 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ed4417500700..e342ae4db3c4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1855,6 +1855,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
 	update_srbds_msr();
+
+	tsx_ap_init();
 }
 
 static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index ee6f23f7587d..2a8e584fc991 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -55,11 +55,10 @@ enum tsx_ctrl_states {
 extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
 
 extern void __init tsx_init(void);
-extern void tsx_enable(void);
-extern void tsx_disable(void);
-extern void tsx_clear_cpuid(void);
+void tsx_ap_init(void);
 #else
 static inline void tsx_init(void) { }
+static inline void tsx_ap_init(void) { }
 #endif /* CONFIG_CPU_SUP_INTEL */
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8321c43554a1..f7a5370a9b3b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -717,13 +717,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_intel_misc_features(c);
 
-	if (tsx_ctrl_state == TSX_CTRL_ENABLE)
-		tsx_enable();
-	else if (tsx_ctrl_state == TSX_CTRL_DISABLE)
-		tsx_disable();
-	else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT)
-		tsx_clear_cpuid();
-
 	split_lock_init();
 	bus_lock_init();
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index f955d25076ba..239ff5fcec6a 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = {
 };
 
 /**
- * mc_bp_resume - Update boot CPU microcode during resume.
+ * microcode_bsp_resume - Update boot CPU microcode during resume.
  */
-static void mc_bp_resume(void)
+void microcode_bsp_resume(void)
 {
 	int cpu = smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
@@ -772,7 +772,7 @@ static void mc_bp_resume(void)
 }
 
 static struct syscore_ops mc_syscore_ops = {
-	.resume			= mc_bp_resume,
+	.resume			= microcode_bsp_resume,
 };
 
 static int mc_cpu_starting(unsigned int cpu)
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index 9c7a5f049292..ec7bbac3a9f2 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -19,7 +19,7 @@
 
 enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED;
 
-void tsx_disable(void)
+static void tsx_disable(void)
 {
 	u64 tsx;
 
@@ -39,7 +39,7 @@ void tsx_disable(void)
 	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
 }
 
-void tsx_enable(void)
+static void tsx_enable(void)
 {
 	u64 tsx;
 
@@ -58,7 +58,7 @@ void tsx_enable(void)
 	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
 }
 
-static bool __init tsx_ctrl_is_supported(void)
+static bool tsx_ctrl_is_supported(void)
 {
 	u64 ia32_cap = x86_read_arch_cap_msr();
 
@@ -84,7 +84,45 @@ static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
 	return TSX_CTRL_ENABLE;
 }
 
-void tsx_clear_cpuid(void)
+/*
+ * Disabling TSX is not a trivial business.
+ *
+ * First of all, there's a CPUID bit: X86_FEATURE_RTM_ALWAYS_ABORT
+ * which says that TSX is practically disabled (all transactions are
+ * aborted by default). When that bit is set, the kernel unconditionally
+ * disables TSX.
+ *
+ * In order to do that, however, it needs to dance a bit:
+ *
+ * 1. The first method to disable it is through MSR_TSX_FORCE_ABORT and
+ * the MSR is present only when *two* CPUID bits are set:
+ *
+ * - X86_FEATURE_RTM_ALWAYS_ABORT
+ * - X86_FEATURE_TSX_FORCE_ABORT
+ *
+ * 2. The second method is for CPUs which do not have the above-mentioned
+ * MSR: those use a different MSR - MSR_IA32_TSX_CTRL and disable TSX
+ * through that one. Those CPUs can also have the initially mentioned
+ * CPUID bit X86_FEATURE_RTM_ALWAYS_ABORT set and for those the same strategy
+ * applies: TSX gets disabled unconditionally.
+ *
+ * When either of the two methods are present, the kernel disables TSX and
+ * clears the respective RTM and HLE feature flags.
+ *
+ * An additional twist in the whole thing presents late microcode loading
+ * which, when done, may cause for the X86_FEATURE_RTM_ALWAYS_ABORT CPUID
+ * bit to be set after the update.
+ *
+ * A subsequent hotplug operation on any logical CPU except the BSP will
+ * cause for the supported CPUID feature bits to get re-detected and, if
+ * RTM and HLE get cleared all of a sudden, but, userspace did consult
+ * them before the update, then funny explosions will happen. Long story
+ * short: the kernel doesn't modify CPUID feature bits after booting.
+ *
+ * That's why, this function's call in init_intel() doesn't clear the
+ * feature flags.
+ */
+static void tsx_clear_cpuid(void)
 {
 	u64 msr;
 
@@ -97,6 +135,39 @@ void tsx_clear_cpuid(void)
 		rdmsrl(MSR_TSX_FORCE_ABORT, msr);
 		msr |= MSR_TFA_TSX_CPUID_CLEAR;
 		wrmsrl(MSR_TSX_FORCE_ABORT, msr);
+	} else if (tsx_ctrl_is_supported()) {
+		rdmsrl(MSR_IA32_TSX_CTRL, msr);
+		msr |= TSX_CTRL_CPUID_CLEAR;
+		wrmsrl(MSR_IA32_TSX_CTRL, msr);
+	}
+}
+
+/*
+ * Disable TSX development mode
+ *
+ * When the microcode released in Feb 2022 is applied, TSX will be disabled by
+ * default on some processors. MSR 0x122 (TSX_CTRL) and MSR 0x123
+ * (IA32_MCU_OPT_CTRL) can be used to re-enable TSX for development, doing so is
+ * not recommended for production deployments. In particular, applying MD_CLEAR
+ * flows for mitigation of the Intel TSX Asynchronous Abort (TAA) transient
+ * execution attack may not be effective on these processors when Intel TSX is
+ * enabled with updated microcode.
+ */
+static void tsx_dev_mode_disable(void)
+{
+	u64 mcu_opt_ctrl;
+
+	/* Check if RTM_ALLOW exists */
+	if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() ||
+	    !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL))
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+
+	if (mcu_opt_ctrl & RTM_ALLOW) {
+		mcu_opt_ctrl &= ~RTM_ALLOW;
+		wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+		setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT);
 	}
 }
 
@@ -105,14 +176,14 @@ void __init tsx_init(void)
 	char arg[5] = {};
 	int ret;
 
+	tsx_dev_mode_disable();
+
 	/*
-	 * Hardware will always abort a TSX transaction if both CPUID bits
-	 * RTM_ALWAYS_ABORT and TSX_FORCE_ABORT are set. In this case, it is
-	 * better not to enumerate CPUID.RTM and CPUID.HLE bits. Clear them
-	 * here.
+	 * Hardware will always abort a TSX transaction when the CPUID bit
+	 * RTM_ALWAYS_ABORT is set. In this case, it is better not to enumerate
+	 * CPUID.RTM and CPUID.HLE bits. Clear them here.
 	 */
-	if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) &&
-	    boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
+	if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT)) {
 		tsx_ctrl_state = TSX_CTRL_RTM_ALWAYS_ABORT;
 		tsx_clear_cpuid();
 		setup_clear_cpu_cap(X86_FEATURE_RTM);
@@ -175,3 +246,16 @@ void __init tsx_init(void)
 		setup_force_cpu_cap(X86_FEATURE_HLE);
 	}
 }
+
+void tsx_ap_init(void)
+{
+	tsx_dev_mode_disable();
+
+	if (tsx_ctrl_state == TSX_CTRL_ENABLE)
+		tsx_enable();
+	else if (tsx_ctrl_state == TSX_CTRL_DISABLE)
+		tsx_disable();
+	else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT)
+		/* See comment over that function for more details. */
+		tsx_clear_cpuid();
+}
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index a7f617a3981d..97529552dd24 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -37,7 +37,6 @@ static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 	} else
 		memcpy(buf, vaddr + offset, csize);
 
-	set_iounmap_nonlazy();
 	iounmap((void __iomem *)vaddr);
 	return csize;
 }
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d0bb2b3fb305..b48ce07756ca 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align
 DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
+static int has_guest_poll = 0;
 /*
  * No need for any "IO delay" on KVM
  */
@@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
 static int kvm_suspend(void)
 {
+	u64 val = 0;
+
 	kvm_guest_cpu_offline(false);
 
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+	has_guest_poll = !(val & 1);
+#endif
 	return 0;
 }
 
 static void kvm_resume(void)
 {
 	kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
 }
 
 static struct syscore_ops kvm_syscore_ops = {
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 531fb4cbb63f..aa72cefdd5be 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -12,10 +12,9 @@ enum insn_type {
 };
 
 /*
- * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax
- * The REX.W cancels the effect of any data16.
+ * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax
  */
-static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
+static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 794fdef2501a..38185aedf7d1 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
 	struct stack_info *info = &state->stack_info;
 	void *addr = (void *)_addr;
 
-	if (!on_stack(info, addr, len) &&
-	    (get_stack_info(addr, state->task, info, &state->stack_mask)))
-		return false;
+	if (on_stack(info, addr, len))
+		return true;
 
-	return true;
+	return !get_stack_info(addr, state->task, info, &state->stack_mask) &&
+		on_stack(info, addr, len);
 }
 
 static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,