Merge tag 'x86-urgent-2024-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:

 - Fix regressions of the new x86 CPU VFM (vendor/family/model)
   enumeration/matching code

 - Fix crash kernel detection on buggy firmware with
   non-compliant ACPI MADT tables

 - Address Kconfig warning

* tag 'x86-urgent-2024-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Fix x86_match_cpu() to match just X86_VENDOR_INTEL
  crypto: x86/aes-xts - switch to new Intel CPU model defines
  x86/topology: Handle bogus ACPI tables correctly
  x86/kconfig: Select ARCH_WANT_FRAME_POINTERS again when UNWINDER_FRAME_POINTER=y

6 files changed, 67 insertions, 18 deletions

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index c5d614d28a75..74777a97e394 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -248,6 +248,7 @@ config UNWINDER_ORC
 
 config UNWINDER_FRAME_POINTER
 	bool "Frame pointer unwinder"
+	select ARCH_WANT_FRAME_POINTERS
 	select FRAME_POINTER
 	help
 	  This option enables the frame pointer unwinder for unwinding kernel
@@ -271,7 +272,3 @@ config UNWINDER_GUESS
 	  overhead.
 
 endchoice
-
-config FRAME_POINTER
-	depends on !UNWINDER_ORC && !UNWINDER_GUESS
-	bool
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 5b25d2a58aeb..ef031655b2d3 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1223,14 +1223,14 @@ DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800);
  * implementation with ymm registers (256-bit vectors) will be used instead.
  */
 static const struct x86_cpu_id zmm_exclusion_list[] = {
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_SKYLAKE_X },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_X },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_D },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_L },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_NNPI },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE_L },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE },
+	X86_MATCH_VFM(INTEL_SKYLAKE_X,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_X,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_D,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_L,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_NNPI,	0),
+	X86_MATCH_VFM(INTEL_TIGERLAKE_L,	0),
+	X86_MATCH_VFM(INTEL_TIGERLAKE,		0),
 	/* Allow Rocket Lake and later, and Sapphire Rapids and later. */
 	/* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */
 	{},
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 970a232009c3..b6325ee30871 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -53,6 +53,9 @@
 #define X86_CENTAUR_FAM6_C7_D		0xd
 #define X86_CENTAUR_FAM6_NANO		0xf
 
+/* x86_cpu_id::flags */
+#define X86_CPU_ID_FLAG_ENTRY_VALID	BIT(0)
+
 #define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
  * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
@@ -79,6 +82,7 @@
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
+	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
 	.driver_data	= (unsigned long) _data				\
 }
 
@@ -89,6 +93,7 @@
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
+	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
 	.driver_data	= (unsigned long) _data				\
 }
 
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 8651643bddae..8e7de733320a 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -38,9 +38,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	const struct x86_cpu_id *m;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	for (m = match;
-	     m->vendor | m->family | m->model | m->steppings | m->feature;
-	     m++) {
+	for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) {
 		if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
 			continue;
 		if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index d17c9b71eb4a..621a151ccf7d 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -128,6 +128,9 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id)
 
 static __init bool check_for_real_bsp(u32 apic_id)
 {
+	bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6;
+	u64 msr;
+
 	/*
 	 * There is no real good way to detect whether this a kdump()
 	 * kernel, but except on the Voyager SMP monstrosity which is not
@@ -144,17 +147,61 @@ static __init bool check_for_real_bsp(u32 apic_id)
 	if (topo_info.real_bsp_apic_id != BAD_APICID)
 		return false;
 
+	/*
+	 * Check whether the enumeration order is broken by evaluating the
+	 * BSP bit in the APICBASE MSR. If the CPU does not have the
+	 * APICBASE MSR then the BSP detection is not possible and the
+	 * kernel must rely on the firmware enumeration order.
+	 */
+	if (has_apic_base) {
+		rdmsrl(MSR_IA32_APICBASE, msr);
+		is_bsp = !!(msr & MSR_IA32_APICBASE_BSP);
+	}
+
 	if (apic_id == topo_info.boot_cpu_apic_id) {
-		topo_info.real_bsp_apic_id = apic_id;
-		return false;
+		/*
+		 * If the boot CPU has the APIC BSP bit set then the
+		 * firmware enumeration is agreeing. If the CPU does not
+		 * have the APICBASE MSR then the only choice is to trust
+		 * the enumeration order.
+		 */
+		if (is_bsp || !has_apic_base) {
+			topo_info.real_bsp_apic_id = apic_id;
+			return false;
+		}
+		/*
+		 * If the boot APIC is enumerated first, but the APICBASE
+		 * MSR does not have the BSP bit set, then there is no way
+		 * to discover the real BSP here. Assume a crash kernel and
+		 * limit the number of CPUs to 1 as an INIT to the real BSP
+		 * would reset the machine.
+		 */
+		pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id);
+		pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n");
+		set_nr_cpu_ids(1);
+		goto fwbug;
 	}
 
-	pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n",
+	pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n",
 		topo_info.boot_cpu_apic_id, apic_id);
+
+	if (is_bsp) {
+		/*
+		 * The boot CPU has the APIC BSP bit set. Use it and complain
+		 * about the broken firmware enumeration.
+		 */
+		topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id;
+		goto fwbug;
+	}
+
 	pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n");
 
 	topo_info.real_bsp_apic_id = apic_id;
 	return true;
+
+fwbug:
+	pr_warn(FW_BUG "APIC enumeration order not specification compliant\n");
+	return false;
 }
 
 static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level,
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 7a9a07ea451b..4338b1b4ac44 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -690,6 +690,8 @@ struct x86_cpu_id {
 	__u16 model;
 	__u16 steppings;
 	__u16 feature;	/* bit index */
+	/* Solely for kernel-internal use: DO NOT EXPORT to userspace! */
+	__u16 flags;
 	kernel_ulong_t driver_data;
 };