Merge tag 'x86_urgent_for_v5.15_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - A FPU fix to properly handle invalid MXCSR values: 32-bit masks them
   out due to historical reasons and 64-bit kernels reject them

 - A fix to clear X86_FEATURE_SMAP when support for is not
   config-enabled

 - Three fixes correcting misspelled Kconfig symbols used in code

 - Two resctrl object cleanup fixes

 - Yet another attempt at fixing the neverending saga of botched x86
   timers, this time because some incredibly smart hardware decides to
   turn off the HPET timer in a low power state - who cares if the OS is
   relying on it...

 - Check the full return value range of an SEV VMGEXIT call to determine
   whether it returned an error

* tag 'x86_urgent_for_v5.15_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Restore the masking out of reserved MXCSR bits
  x86/Kconfig: Correct reference to MWINCHIP3D
  x86/platform/olpc: Correct ifdef symbol to intended CONFIG_OLPC_XO15_SCI
  x86/entry: Clear X86_FEATURE_SMAP when CONFIG_X86_SMAP=n
  x86/entry: Correct reference to intended CONFIG_64_BIT
  x86/resctrl: Fix kfree() of the wrong type in domain_add_cpu()
  x86/resctrl: Free the ctrlval arrays when domain_setup_mon_state() fails
  x86/hpet: Use another crystalball to evaluate HPET usability
  x86/sev: Return an error on a returned non-zero SW_EXITINFO1[31:0]

arch/x86/Kconfig

@@ -1405,7 +1405,7 @@ config HIGHMEM4G
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
+	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6
 	select X86_PAE
 	help
 	  Select this if you have a 32-bit processor and more than 4

arch/x86/include/asm/entry-common.h

@@ -25,7 +25,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 		 * For !SMAP hardware we patch out CLAC on entry.
 		 */
 		if (boot_cpu_has(X86_FEATURE_SMAP) ||
-		    (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
+		    (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
 			mask |= X86_EFLAGS_AC;
 
 		WARN_ON_ONCE(flags & mask);

arch/x86/kernel/cpu/common.c

@@ -326,6 +326,7 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_SMAP
 		cr4_set_bits(X86_CR4_SMAP);
 #else
+		clear_cpu_cap(c, X86_FEATURE_SMAP);
 		cr4_clear_bits(X86_CR4_SMAP);
 #endif
 	}

arch/x86/kernel/cpu/resctrl/core.c

@@ -527,12 +527,14 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	rdt_domain_reconfigure_cdp(r);
 
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
-		kfree(d);
+		kfree(hw_dom);
 		return;
 	}
 
 	if (r->mon_capable && domain_setup_mon_state(r, d)) {
-		kfree(d);
+		kfree(hw_dom->ctrl_val);
+		kfree(hw_dom->mbps_val);
+		kfree(hw_dom);
 		return;
 	}
 

arch/x86/kernel/early-quirks.c

@@ -714,12 +714,6 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x3e20,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x8a12,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
 	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}

arch/x86/kernel/fpu/signal.c

@@ -379,9 +379,14 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 				     sizeof(fpu->state.fxsave)))
 			return -EFAULT;
 
-		/* Reject invalid MXCSR values. */
-		if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
-			return -EINVAL;
+		if (IS_ENABLED(CONFIG_X86_64)) {
+			/* Reject invalid MXCSR values. */
+			if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
+				return -EINVAL;
+		} else {
+			/* Mask invalid bits out for historical reasons (broken hardware). */
+			fpu->state.fxsave.mxcsr &= ~mxcsr_feature_mask;
+		}
 
 		/* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */
 		if (use_xsave())

arch/x86/kernel/hpet.c

@@ -10,6 +10,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/mwait.h>
 
 #undef  pr_fmt
 #define pr_fmt(fmt) "hpet: " fmt
@@ -916,6 +917,83 @@ static bool __init hpet_counting(void)
 	return false;
 }
 
+static bool __init mwait_pc10_supported(void)
+{
+	unsigned int eax, ebx, ecx, mwait_substates;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MWAIT))
+		return false;
+
+	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return false;
+
+	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
+
+	return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) &&
+	       (ecx & CPUID5_ECX_INTERRUPT_BREAK) &&
+	       (mwait_substates & (0xF << 28));
+}
+
+/*
+ * Check whether the system supports PC10. If so force disable HPET as that
+ * stops counting in PC10. This check is overbroad as it does not take any
+ * of the following into account:
+ *
+ *	- ACPI tables
+ *	- Enablement of intel_idle
+ *	- Command line arguments which limit intel_idle C-state support
+ *
+ * That's perfectly fine. HPET is a piece of hardware designed by committee
+ * and the only reasons why it is still in use on modern systems is the
+ * fact that it is impossible to reliably query TSC and CPU frequency via
+ * CPUID or firmware.
+ *
+ * If HPET is functional it is useful for calibrating TSC, but this can be
+ * done via PMTIMER as well which seems to be the last remaining timer on
+ * X86/INTEL platforms that has not been completely wreckaged by feature
+ * creep.
+ *
+ * In theory HPET support should be removed altogether, but there are older
+ * systems out there which depend on it because TSC and APIC timer are
+ * dysfunctional in deeper C-states.
+ *
+ * It's only 20 years now that hardware people have been asked to provide
+ * reliable and discoverable facilities which can be used for timekeeping
+ * and per CPU timer interrupts.
+ *
+ * The probability that this problem is going to be solved in the
+ * forseeable future is close to zero, so the kernel has to be cluttered
+ * with heuristics to keep up with the ever growing amount of hardware and
+ * firmware trainwrecks. Hopefully some day hardware people will understand
+ * that the approach of "This can be fixed in software" is not sustainable.
+ * Hope dies last...
+ */
+static bool __init hpet_is_pc10_damaged(void)
+{
+	unsigned long long pcfg;
+
+	/* Check whether PC10 substates are supported */
+	if (!mwait_pc10_supported())
+		return false;
+
+	/* Check whether PC10 is enabled in PKG C-state limit */
+	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
+	if ((pcfg & 0xF) < 8)
+		return false;
+
+	if (hpet_force_user) {
+		pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n");
+		return false;
+	}
+
+	pr_info("HPET dysfunctional in PC10. Force disabled.\n");
+	boot_hpet_disable = true;
+	return true;
+}
+
 /**
  * hpet_enable - Try to setup the HPET timer. Returns 1 on success.
  */
@@ -929,6 +1007,9 @@ int __init hpet_enable(void)
 	if (!is_hpet_capable())
 		return 0;
 
+	if (hpet_is_pc10_damaged())
+		return 0;
+
 	hpet_set_mapping();
 	if (!hpet_virt_address)
 		return 0;

arch/x86/kernel/sev-shared.c

@@ -130,6 +130,8 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 		} else {
 			ret = ES_VMM_ERROR;
 		}
+	} else if (ghcb->save.sw_exit_info_1 & 0xffffffff) {
+		ret = ES_VMM_ERROR;
 	} else {
 		ret = ES_OK;
 	}

arch/x86/platform/olpc/olpc.c

@@ -274,7 +274,7 @@ static struct olpc_ec_driver ec_xo1_driver = {
 
 static struct olpc_ec_driver ec_xo1_5_driver = {
 	.ec_cmd = olpc_xo1_ec_cmd,
-#ifdef CONFIG_OLPC_XO1_5_SCI
+#ifdef CONFIG_OLPC_XO15_SCI
 	/*
 	 * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is
 	 * compiled in