Merge: update the ACPI subsystem to Linux v6.17 for RHEL-9.8

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7359

JIRA: https://issues.redhat.com/browse/RHEL-82671
JIRA: https://issues.redhat.com/browse/RHEL-114091

Resolves: 82671
Resolves: 114091

Omitted-fix: 0674188 "ACPI: EC: Enable EC support on LoongArch by default"
Fix applies to LoongArch, which is not supported.

Omitted-fix: 058de16 "platform/x86: dell-ddv: Implement the battery matching algorithm"
This isn't a fix, this is a new feature that changes how some Dell laptop batteries are handled. It needs more time to be tested upstream.

Omitted-fix: d4e8378 "platform/x86: dell-ddv: Fix taking the psy->extensions_sem lock twice"
This is a fix for the previous commit, which is not being added at this time.

Update the ACPI subsystem from Linux v6.12 to Linux v6.17. The extensive v6.14 commits to drivers/acpi/platform_profile.c and drivers/acpi/acpi_platform.c are deeply intertwined with updates to drivers/platform/x86 and are excluded for now. They may be added in a separate JIRA and MR.

various updates for GCC-15 dealing with -Wunterminated-string-initialization and -Wflex-array-member were skipped as unnecessary at this time.

various updates to constify various function arguments were skipped as RHEL-9.8 doesn't have the necessary infrastruture.

Updates to APEI-EINJ that depend of the faux bus were skipped to minimize merge conflicts with MR !7309.

Signed-off-by: Mark Langsdorf <mlangsdo@redhat.com>

Approved-by: Ivan Vecera <ivecera@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>
Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: Audra Mitchell <aubaker@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

Documentation/ABI/testing/sysfs-firmware-acpi

@@ -108,15 +108,15 @@ Description:
 		number of a "General Purpose Events" (GPE).
 
 		A GPE vectors to a specified handler in AML, which
-		can do a anything the BIOS writer wants from
+		can do anything the BIOS writer wants from
 		OS context.  GPE 0x12, for example, would vector
 		to a level or edge handler called _L12 or _E12.
 		The handler may do its business and return.
-		Or the handler may send send a Notify event
+		Or the handler may send a Notify event
 		to a Linux device driver registered on an ACPI device,
 		such as a battery, or a processor.
 
-		To figure out where all the SCI's are coming from,
+		To figure out where all the SCIs are coming from,
 		/sys/firmware/acpi/interrupts contains a file listing
 		every possible source, and the count of how many
 		times it has triggered::

Documentation/firmware-guide/acpi/gpio-properties.rst

@@ -79,8 +79,8 @@ Up           Low          as high, assuming non-active
 Up           High         as high, assuming active
 =========  =============  ==============
 
-That said, for our above example the both GPIOs, since the bias setting
-is explicit and _DSD is present, will be treated as active with a high
+That said, for our above example, since the bias setting is explicit and
+_DSD is present, both GPIOs will be treated as active with a high
 polarity and Linux will configure the pins in this state until a driver
 reprograms them differently.
 

arch/powerpc/platforms/cell/axon_msi.c

@@ -111,7 +111,7 @@ static void axon_msi_cascade(struct irq_desc *desc)
 		pr_devel("axon_msi: woff %x roff %x msi %x\n",
 			  write_offset, msic->read_offset, msi);
 
-		if (msi < nr_irqs && irq_get_chip_data(msi) == msic) {
+		if (msi < irq_get_nr_irqs() && irq_get_chip_data(msi) == msic) {
 			generic_handle_irq(msi);
 			msic->fifo_virt[idx] = cpu_to_le32(0xffffffff);
 		} else {

arch/s390/kernel/irq.c

@@ -253,7 +253,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 		goto out;
 	}
-	if (index < nr_irqs) {
+	if (index < irq_get_nr_irqs()) {
 		show_msi_interrupt(p, index);
 		goto out;
 	}

arch/x86/Kconfig

@@ -36,6 +36,7 @@ config X86_64
 	select SWIOTLB
 	select ARCH_HAS_ELFCORE_COMPAT
 	select ZONE_DMA32
+	select ACPI_MRMM if ACPI
 
 config FORCE_DYNAMIC_FTRACE
 	def_bool y

arch/x86/kernel/acpi/boot.c

@@ -1171,7 +1171,8 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 	}
 
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE,
-				      acpi_parse_int_src_ovr, nr_irqs);
+				      acpi_parse_int_src_ovr,
+				      irq_get_nr_irqs());
 	if (count < 0) {
 		pr_err("Error parsing interrupt source overrides entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
@@ -1191,7 +1192,8 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 	mp_config_acpi_legacy_irqs();
 
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE,
-				      acpi_parse_nmi_src, nr_irqs);
+				      acpi_parse_nmi_src,
+				      irq_get_nr_irqs());
 	if (count < 0) {
 		pr_err("Error parsing NMI SRC entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */

arch/x86/kernel/acpi/cppc.c

@@ -88,29 +88,24 @@ static void amd_set_max_freq_ratio(void)
 
 	rc = cppc_get_perf_caps(0, &perf_caps);
 	if (rc) {
-		pr_debug("Could not retrieve perf counters (%d)\n", rc);
+		pr_warn("Could not retrieve perf counters (%d)\n", rc);
 		return;
 	}
 
 	rc = amd_get_boost_ratio_numerator(0, &numerator);
 	if (rc) {
-		pr_debug("Could not retrieve highest performance (%d)\n", rc);
+		pr_warn("Could not retrieve highest performance (%d)\n", rc);
 		return;
 	}
 	nominal_perf = perf_caps.nominal_perf;
 
 	if (!nominal_perf) {
-		pr_debug("Could not retrieve nominal performance\n");
+		pr_warn("Could not retrieve nominal performance\n");
 		return;
 	}
 
-	perf_ratio = div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf);
 	/* midpoint between max_boost and max_P */
-	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
-	if (!perf_ratio) {
-		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
-		return;
-	}
+	perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1;
 
 	freq_invariance_set_perf_ratio(perf_ratio, false);
 }
@@ -246,8 +241,10 @@ EXPORT_SYMBOL_GPL(amd_detect_prefcore);
  */
 int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 {
+	enum x86_topology_cpu_type core_type = get_topology_cpu_type(&cpu_data(cpu));
 	bool prefcore;
 	int ret;
+	u32 tmp;
 
 	ret = amd_detect_prefcore(&prefcore);
 	if (ret)
@@ -273,6 +270,27 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 			break;
 		}
 	}
+
+	/* detect if running on heterogeneous design */
+	if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) {
+		switch (core_type) {
+		case TOPO_CPU_TYPE_UNKNOWN:
+			pr_warn("Undefined core type found for cpu %d\n", cpu);
+			break;
+		case TOPO_CPU_TYPE_PERFORMANCE:
+			/* use the max scale for performance cores */
+			*numerator = CPPC_HIGHEST_PERF_PERFORMANCE;
+			return 0;
+		case TOPO_CPU_TYPE_EFFICIENCY:
+			/* use the highest perf value for efficiency cores */
+			ret = amd_get_highest_perf(cpu, &tmp);
+			if (ret)
+				return ret;
+			*numerator = tmp;
+			return 0;
+		}
+	}
+
 	*numerator = CPPC_HIGHEST_PERF_PREFCORE;
 
 	return 0;

arch/x86/kernel/apic/vector.c

@@ -712,8 +712,8 @@ int __init arch_probe_nr_irqs(void)
 {
 	int nr;
 
-	if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
-		nr_irqs = NR_VECTORS * nr_cpu_ids;
+	if (irq_get_nr_irqs() > NR_VECTORS * nr_cpu_ids)
+		irq_set_nr_irqs(NR_VECTORS * nr_cpu_ids);
 
 	nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
 #if defined(CONFIG_PCI_MSI)
@@ -725,8 +725,8 @@ int __init arch_probe_nr_irqs(void)
 	else
 		nr += gsi_top * 16;
 #endif
-	if (nr < nr_irqs)
-		nr_irqs = nr;
+	if (nr < irq_get_nr_irqs())
+		irq_set_nr_irqs(nr);
 
 	/*
 	 * We don't know if PIC is present at this point so we need to do

arch/x86/kernel/cpu/aperfmperf.c

@@ -306,7 +306,7 @@ static void freq_invariance_enable(void)
 		WARN_ON_ONCE(1);
 		return;
 	}
-	static_branch_enable(&arch_scale_freq_key);
+	static_branch_enable_cpuslocked(&arch_scale_freq_key);
 	register_freq_invariance_syscore_ops();
 	pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
 }
@@ -323,8 +323,10 @@ static void __init bp_init_freq_invariance(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return;
 
-	if (intel_set_max_freq_ratio())
+	if (intel_set_max_freq_ratio()) {
+		guard(cpus_read_lock)();
 		freq_invariance_enable();
+	}
 }
 
 static void disable_freq_invariance_workfn(struct work_struct *work)

arch/x86/kernel/setup.c

@@ -259,6 +259,7 @@ static void __init relocate_initrd(void)
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
+	int ret = 0;
 
 	/* We need to move the initrd down into directly mapped mem */
 	u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0,
@@ -272,7 +273,9 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
 	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
-	copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
+	ret = copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
+	if (ret)
+		panic("Copy RAMDISK failed\n");
 
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",