From 36b921637e900c77f5f9bd5b45db522124068a96 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 29 May 2024 14:34:34 +0100 Subject: ACPI: processor: Add acpi_get_processor_handle() helper If CONFIG_ACPI_PROCESSOR provide a helper to retrieve the acpi_handle for a given CPU allowing access to methods in DSDT. Tested-by: Miguel Luis Reviewed-by: Gavin Shan Acked-by: Rafael J. Wysocki Signed-off-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240529133446.28446-8-Jonathan.Cameron@huawei.com Signed-off-by: Catalin Marinas --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 28c3fb2bef0d..fd45bfab66b8 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -304,6 +304,8 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +acpi_handle acpi_get_processor_handle(int cpu); + #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif @@ -1076,6 +1078,11 @@ static inline bool acpi_sleep_state_supported(u8 sleep_state) return false; } +static inline acpi_handle acpi_get_processor_handle(int cpu) +{ + return NULL; +} + #endif /* !CONFIG_ACPI */ extern void arch_post_acpi_subsys_init(void); -- cgit v1.2.3 From d633da5d3ab1a0eb26a2213d65da1e189e82f8ab Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 29 May 2024 14:34:41 +0100 Subject: irqchip/gic-v3: Add support for ACPI's disabled but 'online capable' CPUs To support virtual CPU hotplug, ACPI has added an 'online capable' bit to the MADT GICC entries. This indicates a disabled CPU entry may not be possible to online via PSCI until firmware has set enabled bit in _STA. This means that a "usable" GIC redistributor is one that is marked as either enabled, or online capable. The meaning of the acpi_gicc_is_usable() would become less clear than just checking the pair of flags at call sites. As such, drop that helper function. The test in gic_acpi_match_gicc() remains as testing just the enabled bit so the count of enabled distributors is correct. What about the redistributor in the GICC entry? ACPI doesn't want to say. Assume the worst: When a redistributor is described in the GICC entry, but the entry is marked as disabled at boot, assume the redistributor is inaccessible. The GICv3 driver doesn't support late online of redistributors, so this means the corresponding CPU can't be brought online either. Rather than modifying cpu masks that may already have been used, register a new cpuhp callback to fail this case. This must run earlier than the main gic_starting_cpu() so that this case can be rejected before the section of cpuhp that runs on the CPU that is coming up as that is not allowed to fail. This solution keeps the handling of this broken firmware corner case local to the GIC driver. As precise ordering of this callback doesn't need to be controlled as long as it is in that initial prepare phase, use CPUHP_BP_PREPARE_DYN. Systems that want CPU hotplug in a VM can ensure their redistributors are always-on, and describe them that way with a GICR entry in the MADT. Suggested-by: Marc Zyngier Signed-off-by: James Morse Signed-off-by: Russell King (Oracle) Tested-by: Miguel Luis Co-developed-by: Jonathan Cameron Signed-off-by: Jonathan Cameron Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20240529133446.28446-15-Jonathan.Cameron@huawei.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/smp.c | 3 ++- drivers/acpi/processor_core.c | 3 ++- drivers/irqchip/irq-gic-v3.c | 46 +++++++++++++++++++++++++++++++++++++++---- include/linux/acpi.h | 5 ----- 4 files changed, 46 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 31c8b3094dd7..6b0572daa9da 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -530,7 +530,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) { u64 hwid = processor->arm_mpidr; - if (!acpi_gicc_is_usable(processor)) { + if (!(processor->flags & + (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) { pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid); return; } diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index b203cfe28550..b04b684f3190 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -90,7 +90,8 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry, struct acpi_madt_generic_interrupt *gicc = container_of(entry, struct acpi_madt_generic_interrupt, header); - if (!acpi_gicc_is_usable(gicc)) + if (!(gicc->flags & + (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) return -ENODEV; /* device_declaration means Device object in DSDT, in the diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 10af15f93d4d..cc81515c1413 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -44,6 +44,8 @@ #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) +static struct cpumask broken_rdists __read_mostly; + struct redist_region { void __iomem *redist_base; phys_addr_t phys_base; @@ -1293,6 +1295,18 @@ static void gic_cpu_init(void) #define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT) #define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL) +/* + * gic_starting_cpu() is called after the last point where cpuhp is allowed + * to fail. So pre check for problems earlier. + */ +static int gic_check_rdist(unsigned int cpu) +{ + if (cpumask_test_cpu(cpu, &broken_rdists)) + return -EINVAL; + + return 0; +} + static int gic_starting_cpu(unsigned int cpu) { gic_cpu_init(); @@ -1384,6 +1398,10 @@ static void __init gic_smp_init(void) }; int base_sgi; + cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN, + "irqchip/arm/gicv3:checkrdist", + gic_check_rdist, NULL); + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING, "irqchip/arm/gicv3:starting", gic_starting_cpu, NULL); @@ -2365,8 +2383,24 @@ gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2; void __iomem *redist_base; - if (!acpi_gicc_is_usable(gicc)) + /* Neither enabled or online capable means it doesn't exist, skip it */ + if (!(gicc->flags & (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) + return 0; + + /* + * Capable but disabled CPUs can be brought online later. What about + * the redistributor? ACPI doesn't want to say! + * Virtual hotplug systems can use the MADT's "always-on" GICR entries. + * Otherwise, prevent such CPUs from being brought online. + */ + if (!(gicc->flags & ACPI_MADT_ENABLED)) { + int cpu = get_cpu_for_acpi_id(gicc->uid); + + pr_warn("CPU %u's redistributor is inaccessible: this CPU can't be brought online\n", cpu); + if (cpu >= 0) + cpumask_set_cpu(cpu, &broken_rdists); return 0; + } redist_base = ioremap(gicc->gicr_base_address, size); if (!redist_base) @@ -2413,9 +2447,12 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, /* * If GICC is enabled and has valid gicr base address, then it means - * GICR base is presented via GICC + * GICR base is presented via GICC. The redistributor is only known to + * be accessible if the GICC is marked as enabled. If this bit is not + * set, we'd need to add the redistributor at runtime, which isn't + * supported. */ - if (acpi_gicc_is_usable(gicc) && gicc->gicr_base_address) + if (gicc->flags & ACPI_MADT_ENABLED && gicc->gicr_base_address) acpi_data.enabled_rdists++; return 0; @@ -2474,7 +2511,8 @@ static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *hea int maint_irq_mode; static int first_madt = true; - if (!acpi_gicc_is_usable(gicc)) + if (!(gicc->flags & + (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) return 0; maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ? diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fd45bfab66b8..9f8c9d29b035 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -237,11 +237,6 @@ acpi_table_parse_cedt(enum acpi_cedt_type id, int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); -static inline bool acpi_gicc_is_usable(struct acpi_madt_generic_interrupt *gicc) -{ - return gicc->flags & ACPI_MADT_ENABLED; -} - #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else -- cgit v1.2.3 From 4e1a7df4548003fc081360b0f4edce3f7a991bfc Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 29 May 2024 14:34:46 +0100 Subject: cpumask: Add enabled cpumask for present CPUs that can be brought online The 'offline' file in sysfs shows all offline CPUs, including those that aren't present. User-space is expected to remove not-present CPUs from this list to learn which CPUs could be brought online. CPUs can be present but not-enabled. These CPUs can't be brought online until the firmware policy changes, which comes with an ACPI notification that will register the CPUs. With only the offline and present files, user-space is unable to determine which CPUs it can try to bring online. Add a new CPU mask that shows this based on all the registered CPUs. Signed-off-by: James Morse Tested-by: Miguel Luis Tested-by: Vishnu Pajjuri Tested-by: Jianyong Wu Acked-by: Thomas Gleixner Signed-off-by: Russell King (Oracle) Reviewed-by: Gavin Shan Signed-off-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240529133446.28446-20-Jonathan.Cameron@huawei.com Signed-off-by: Catalin Marinas --- Documentation/ABI/testing/sysfs-devices-system-cpu | 6 ++++++ drivers/base/cpu.c | 10 +++++++++ include/linux/cpumask.h | 25 ++++++++++++++++++++++ kernel/cpu.c | 3 +++ 4 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index e7e160954e79..53ed1a803422 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -694,3 +694,9 @@ Description: (RO) indicates whether or not the kernel directly supports modifying the crash elfcorehdr for CPU hot un/plug and/or on/offline changes. + +What: /sys/devices/system/cpu/enabled +Date: Nov 2022 +Contact: Linux kernel mailing list +Description: + (RO) the list of CPUs that can be brought online. diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 1487cd9761a4..b57326fd48d4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -95,6 +95,7 @@ void unregister_cpu(struct cpu *cpu) { int logical_cpu = cpu->dev.id; + set_cpu_enabled(logical_cpu, false); unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu)); device_unregister(&cpu->dev); @@ -273,6 +274,13 @@ static ssize_t print_cpus_offline(struct device *dev, } static DEVICE_ATTR(offline, 0444, print_cpus_offline, NULL); +static ssize_t print_cpus_enabled(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpu_enabled_mask)); +} +static DEVICE_ATTR(enabled, 0444, print_cpus_enabled, NULL); + static ssize_t print_cpus_isolated(struct device *dev, struct device_attribute *attr, char *buf) { @@ -413,6 +421,7 @@ int register_cpu(struct cpu *cpu, int num) register_cpu_under_node(num, cpu_to_node(num)); dev_pm_qos_expose_latency_limit(&cpu->dev, PM_QOS_RESUME_LATENCY_NO_CONSTRAINT); + set_cpu_enabled(num, true); return 0; } @@ -494,6 +503,7 @@ static struct attribute *cpu_root_attrs[] = { &cpu_attrs[2].attr.attr, &dev_attr_kernel_max.attr, &dev_attr_offline.attr, + &dev_attr_enabled.attr, &dev_attr_isolated.attr, #ifdef CONFIG_NO_HZ_FULL &dev_attr_nohz_full.attr, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 23686bed441d..954d4adc8f81 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -93,6 +93,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated + * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * @@ -125,11 +126,13 @@ static inline void set_nr_cpu_ids(unsigned int nr) extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; +extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) +#define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) @@ -1075,6 +1078,7 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) +#define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif @@ -1092,6 +1096,15 @@ set_cpu_possible(unsigned int cpu, bool possible) cpumask_clear_cpu(cpu, &__cpu_possible_mask); } +static inline void +set_cpu_enabled(unsigned int cpu, bool can_be_onlined) +{ + if (can_be_onlined) + cpumask_set_cpu(cpu, &__cpu_enabled_mask); + else + cpumask_clear_cpu(cpu, &__cpu_enabled_mask); +} + static inline void set_cpu_present(unsigned int cpu, bool present) { @@ -1173,6 +1186,7 @@ static __always_inline unsigned int num_online_cpus(void) return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) +#define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) @@ -1181,6 +1195,11 @@ static inline bool cpu_online(unsigned int cpu) return cpumask_test_cpu(cpu, cpu_online_mask); } +static inline bool cpu_enabled(unsigned int cpu) +{ + return cpumask_test_cpu(cpu, cpu_enabled_mask); +} + static inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); @@ -1205,6 +1224,7 @@ static inline bool cpu_dying(unsigned int cpu) #define num_online_cpus() 1U #define num_possible_cpus() 1U +#define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U @@ -1218,6 +1238,11 @@ static inline bool cpu_possible(unsigned int cpu) return cpu == 0; } +static inline bool cpu_enabled(unsigned int cpu) +{ + return cpu == 0; +} + static inline bool cpu_present(unsigned int cpu) { return cpu == 0; diff --git a/kernel/cpu.c b/kernel/cpu.c index 563877d6c28b..a2f3ad276814 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -3069,6 +3069,9 @@ EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); +struct cpumask __cpu_enabled_mask __read_mostly; +EXPORT_SYMBOL(__cpu_enabled_mask); + struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); -- cgit v1.2.3