Adding upstream version 6.9.7.upstream/6.9.7upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

13 files changed, 115 insertions, 40 deletions

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 3cf156f70..027a8c7a2 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -215,7 +215,14 @@ out:
 
 int amd_smn_read(u16 node, u32 address, u32 *value)
 {
-	return __amd_smn_rw(node, address, value, false);
+	int err = __amd_smn_rw(node, address, value, false);
+
+	if (PCI_POSSIBLE_ERROR(*value)) {
+		err = -ENODEV;
+		*value = 0;
+	}
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(amd_smn_read);
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 185738c72..29cd0543f 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -1036,7 +1036,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd)
 			add_timer_on(&cl->timer, cpu);
 		}
 	} else {
-		apicd->prev_vector = 0;
+		pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu);
+		free_moved_vector(apicd);
 	}
 	raw_spin_unlock(&vector_lock);
 }
@@ -1073,6 +1074,7 @@ void irq_complete_move(struct irq_cfg *cfg)
  */
 void irq_force_complete_move(struct irq_desc *desc)
 {
+	unsigned int cpu = smp_processor_id();
 	struct apic_chip_data *apicd;
 	struct irq_data *irqd;
 	unsigned int vector;
@@ -1097,10 +1099,11 @@ void irq_force_complete_move(struct irq_desc *desc)
 		goto unlock;
 
 	/*
-	 * If prev_vector is empty, no action required.
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
 	 */
 	vector = apicd->prev_vector;
-	if (!vector)
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
 		goto unlock;
 
 	/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 605c26c00..198200782 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1053,18 +1053,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
-	bool vp_bits_from_cpuid = true;
 
 	if (!cpu_has(c, X86_FEATURE_CPUID) ||
-	    (c->extended_cpuid_level < 0x80000008))
-		vp_bits_from_cpuid = false;
-
-	if (vp_bits_from_cpuid) {
-		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
-
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-	} else {
+	    (c->extended_cpuid_level < 0x80000008)) {
 		if (IS_ENABLED(CONFIG_X86_64)) {
 			c->x86_clflush_size = 64;
 			c->x86_phys_bits = 36;
@@ -1078,7 +1069,17 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 			    cpu_has(c, X86_FEATURE_PSE36))
 				c->x86_phys_bits = 36;
 		}
+	} else {
+		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
+
+		/* Provide a sane default if not enumerated: */
+		if (!c->x86_clflush_size)
+			c->x86_clflush_size = 32;
 	}
+
 	c->x86_cache_bits = c->x86_phys_bits;
 	c->x86_cache_alignment = c->x86_clflush_size;
 }
@@ -1589,6 +1590,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	if (have_cpuid_p()) {
 		cpu_detect(c);
 		get_cpu_vendor(c);
+		intel_unlock_cpuid_leafs(c);
 		get_cpu_cap(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
 		get_cpu_address_sizes(c);
@@ -1748,7 +1750,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	cpu_detect(c);
 
 	get_cpu_vendor(c);
-
+	intel_unlock_cpuid_leafs(c);
 	get_cpu_cap(c);
 
 	get_cpu_address_sizes(c);
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index ea9e07d57..1beccefba 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -61,9 +61,11 @@ extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
 
 extern void __init tsx_init(void);
 void tsx_ap_init(void);
+void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c);
 #else
 static inline void tsx_init(void) { }
 static inline void tsx_ap_init(void) { }
+static inline void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) { }
 #endif /* CONFIG_CPU_SUP_INTEL */
 
 extern void init_spectral_chicken(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index be30d7fa2..93efd9edc 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -268,19 +268,26 @@ detect_keyid_bits:
 	c->x86_phys_bits -= keyid_bits;
 }
 
+void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return;
+
+	if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd))
+		return;
+
+	/*
+	 * The BIOS can have limited CPUID to leaf 2, which breaks feature
+	 * enumeration. Unlock it and update the maximum leaf info.
+	 */
+	if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0)
+		c->cpuid_level = cpuid_eax(0);
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
 
-	/* Unmask CPUID levels if masked: */
-	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
-				  MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
-			c->cpuid_level = cpuid_eax(0);
-			get_cpu_cap(c);
-		}
-	}
-
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index ad6776081..ae71b8ef9 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -39,9 +39,7 @@ 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/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 13b45b9c8..620f0af71 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -465,7 +465,7 @@ static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, siz
 	return !__apply_microcode_amd(mc);
 }
 
-static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
+static bool get_builtin_microcode(struct cpio_data *cp, u8 family)
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct firmware fw;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c34a35ec0..2ce5f4913 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -508,7 +508,8 @@ void free_rmid(u32 closid, u32 rmid)
 	 * allows architectures that ignore the closid parameter to avoid an
 	 * unnecessary check.
 	 */
-	if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+	if (!resctrl_arch_mon_capable() ||
+	    idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
 						RESCTRL_RESERVED_RMID))
 		return;
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index d17c9b71e..621a151cc 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/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index ce2d507c3..5ee6373d4 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -84,9 +84,9 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb)
 
 	/*
 	 * If leaf 0xb is available, then the domain shifts are set
-	 * already and nothing to do here.
+	 * already and nothing to do here. Only valid for family >= 0x17.
 	 */
-	if (!has_0xb) {
+	if (!has_0xb && tscan->c->x86 >= 0x17) {
 		/*
 		 * Leaf 0x80000008 set the CORE domain shift already.
 		 * Update the SMT domain, but do not propagate it.
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index dd2ec14ad..15af7e98e 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe_ctlblk *kcb;
 	int bit;
 
+	if (unlikely(kprobe_ftrace_disabled))
+		return;
+
 	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index b180d8e49..cc0f7f70b 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -295,8 +295,15 @@ void machine_kexec_cleanup(struct kimage *image)
 void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
-	void *control_page;
+	unsigned int host_mem_enc_active;
 	int save_ftrace_enabled;
+	void *control_page;
+
+	/*
+	 * This must be done before load_segments() since if call depth tracking
+	 * is used then GS must be valid to make any function calls.
+	 */
+	host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT);
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (image->preserve_context)
@@ -358,7 +365,7 @@ void machine_kexec(struct kimage *image)
 				       (unsigned long)page_list,
 				       image->start,
 				       image->preserve_context,
-				       cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT));
+				       host_mem_enc_active);
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (image->preserve_context)
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 1123ef3cc..433403365 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -193,11 +193,9 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
 	cur->warned = false;
 
 	/*
-	 * If a non-zero TSC value for socket 0 may be valid then the default
-	 * adjusted value cannot assumed to be zero either.
+	 * The default adjust value cannot be assumed to be zero on any socket.
 	 */
-	if (tsc_async_resets)
-		cur->adjusted = bootval;
+	cur->adjusted = bootval;
 
 	/*
 	 * Check whether this CPU is the first in a package to come up. In