diff --git a/Documentation/admin-guide/media/vivid.rst b/Documentation/admin-guide/media/vivid.rst index 1306f19ecb5a..c9d301ab46a3 100644 --- a/Documentation/admin-guide/media/vivid.rst +++ b/Documentation/admin-guide/media/vivid.rst @@ -328,7 +328,7 @@ and an HDMI input, one input for each input type. Those are described in more detail below. Special attention has been given to the rate at which new frames become -available. The jitter will be around 1 jiffie (that depends on the HZ +available. The jitter will be around 1 jiffy (that depends on the HZ configuration of your kernel, so usually 1/100, 1/250 or 1/1000 of a second), but the long-term behavior is exactly following the framerate. So a framerate of 59.94 Hz is really different from 60 Hz. If the framerate diff --git a/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml b/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml index 698588e9aa86..4be9b596a790 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml @@ -31,13 +31,25 @@ description: | This device also represents the FIQ interrupt sources on platforms using AIC, which do not go through a discrete interrupt controller. + IPIs may be performed via MMIO registers on all variants of AIC. Starting + from A11, system registers may also be used for "fast" IPIs. Starting from + M1, even faster IPIs within the same cluster may be achieved by writing to + a "local" fast IPI register as opposed to using the "global" fast IPI + register. + allOf: - $ref: /schemas/interrupt-controller.yaml# properties: compatible: items: - - const: apple,t8103-aic + - enum: + - apple,s5l8960x-aic + - apple,t7000-aic + - apple,s8000-aic + - apple,t8010-aic + - apple,t8015-aic + - apple,t8103-aic - const: apple,aic interrupt-controller: true diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml index 19e56b7577a0..6d0eb0014eee 100644 --- a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml +++ b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml @@ -24,6 +24,7 @@ properties: - rockchip,rk3228-timer - rockchip,rk3229-timer - rockchip,rk3368-timer + - rockchip,rk3576-timer - rockchip,rk3588-timer - rockchip,px30-timer - const: rockchip,rk3288-timer diff --git a/Documentation/timers/timers-howto.rst b/Documentation/timers/timers-howto.rst index 5c169e3d29a8..ef7a4652ccc9 100644 --- a/Documentation/timers/timers-howto.rst +++ b/Documentation/timers/timers-howto.rst @@ -19,7 +19,7 @@ it really need to delay in atomic context?" If so... ATOMIC CONTEXT: You must use the `*delay` family of functions. These - functions use the jiffie estimation of clock speed + functions use the jiffy estimation of clock speed and will busy wait for enough loop cycles to achieve the desired delay: diff --git a/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst b/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst index 90a153cad4e8..731c266beb1a 100644 --- a/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst +++ b/Documentation/translations/sp_SP/scheduler/sched-design-CFS.rst @@ -109,7 +109,7 @@ para que se ejecute, y la tarea en ejecución es interrumpida. ================================== CFS usa una granularidad de nanosegundos y no depende de ningún -jiffie o detalles como HZ. De este modo, el gestor de tareas CFS no tiene +jiffy o detalles como HZ. De este modo, el gestor de tareas CFS no tiene noción de "ventanas de tiempo" de la forma en que tenía el gestor de tareas previo, y tampoco tiene heurísticos. Únicamente hay un parámetro central ajustable (se ha de cambiar en CONFIG_SCHED_DEBUG): diff --git a/arch/arm/mach-versatile/spc.c b/arch/arm/mach-versatile/spc.c index 5e44170e1a9a..790092734cf6 100644 --- a/arch/arm/mach-versatile/spc.c +++ b/arch/arm/mach-versatile/spc.c @@ -73,7 +73,7 @@ /* * Even though the SPC takes max 3-5 ms to complete any OPP/COMMS - * operation, the operation could start just before jiffie is about + * operation, the operation could start just before jiffy is about * to be incremented. So setting timeout value of 20ms = 2jiffies@100Hz */ #define TIMEOUT_US 20000 diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 70f169210b52..0e3abf7b0bd3 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -85,6 +85,7 @@ config LOONGARCH select GENERIC_ENTRY select GENERIC_GETTIMEOFDAY select GENERIC_IOREMAP if !ARCH_IOREMAP + select GENERIC_IRQ_MATRIX_ALLOCATOR select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index 2eafe6a6aca8..16a716f88a5c 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -65,5 +65,6 @@ #define cpu_has_guestid cpu_opt(LOONGARCH_CPU_GUESTID) #define cpu_has_hypervisor cpu_opt(LOONGARCH_CPU_HYPERVISOR) #define cpu_has_ptw cpu_opt(LOONGARCH_CPU_PTW) +#define cpu_has_avecint cpu_opt(LOONGARCH_CPU_AVECINT) #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 48b9f7168bcc..843f9c4ec980 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -99,6 +99,7 @@ enum cpu_type_enum { #define CPU_FEATURE_GUESTID 24 /* CPU has GuestID feature */ #define CPU_FEATURE_HYPERVISOR 25 /* CPU has hypervisor (running in VM) */ #define CPU_FEATURE_PTW 26 /* CPU has hardware page table walker */ +#define CPU_FEATURE_AVECINT 27 /* CPU has avec interrupt */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) @@ -127,5 +128,6 @@ enum cpu_type_enum { #define LOONGARCH_CPU_GUESTID BIT_ULL(CPU_FEATURE_GUESTID) #define LOONGARCH_CPU_HYPERVISOR BIT_ULL(CPU_FEATURE_HYPERVISOR) #define LOONGARCH_CPU_PTW BIT_ULL(CPU_FEATURE_PTW) +#define LOONGARCH_CPU_AVECINT BIT_ULL(CPU_FEATURE_AVECINT) #endif /* _ASM_CPU_H */ diff --git a/arch/loongarch/include/asm/hardirq.h b/arch/loongarch/include/asm/hardirq.h index 1d7feb719515..10da8d6961cb 100644 --- a/arch/loongarch/include/asm/hardirq.h +++ b/arch/loongarch/include/asm/hardirq.h @@ -12,12 +12,13 @@ extern void ack_bad_irq(unsigned int irq); #define ack_bad_irq ack_bad_irq -#define NR_IPI 3 +#define NR_IPI 4 enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNCTION, IPI_IRQ_WORK, + IPI_CLEAR_VECTOR, }; typedef struct { diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 480418bc5071..9c2ca785faa9 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -39,11 +39,22 @@ void spurious_interrupt(void); #define NR_IRQS_LEGACY 16 +/* + * 256 Vectors Mapping for AVECINTC: + * + * 0 - 15: Mapping classic IPs, e.g. IP0-12. + * 16 - 255: Mapping vectors for external IRQ. + * + */ +#define NR_VECTORS 256 +#define NR_LEGACY_VECTORS 16 +#define IRQ_MATRIX_BITS NR_VECTORS + #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace void arch_trigger_cpumask_backtrace(const struct cpumask *mask, int exclude_cpu); #define MAX_IO_PICS 2 -#define NR_IRQS (64 + (256 * MAX_IO_PICS)) +#define NR_IRQS (64 + NR_VECTORS * (NR_CPUS + MAX_IO_PICS)) struct acpi_vector_group { int node; @@ -65,7 +76,7 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS]; #define LOONGSON_LPC_LAST_IRQ (LOONGSON_LPC_IRQ_BASE + 15) #define LOONGSON_CPU_IRQ_BASE 16 -#define LOONGSON_CPU_LAST_IRQ (LOONGSON_CPU_IRQ_BASE + 14) +#define LOONGSON_CPU_LAST_IRQ (LOONGSON_CPU_IRQ_BASE + 15) #define LOONGSON_PCH_IRQ_BASE 64 #define LOONGSON_PCH_ACPI_IRQ (LOONGSON_PCH_IRQ_BASE + 47) @@ -88,20 +99,8 @@ struct acpi_madt_bio_pic; struct acpi_madt_msi_pic; struct acpi_madt_lpc_pic; -int liointc_acpi_init(struct irq_domain *parent, - struct acpi_madt_lio_pic *acpi_liointc); -int eiointc_acpi_init(struct irq_domain *parent, - struct acpi_madt_eio_pic *acpi_eiointc); +void complete_irq_moving(void); -int htvec_acpi_init(struct irq_domain *parent, - struct acpi_madt_ht_pic *acpi_htvec); -int pch_lpc_acpi_init(struct irq_domain *parent, - struct acpi_madt_lpc_pic *acpi_pchlpc); -int pch_msi_acpi_init(struct irq_domain *parent, - struct acpi_madt_msi_pic *acpi_pchmsi); -int pch_pic_acpi_init(struct irq_domain *parent, - struct acpi_madt_bio_pic *acpi_pchpic); -int find_pch_pic(u32 gsi); struct fwnode_handle *get_pch_msi_handle(int pci_segment); extern struct acpi_madt_lio_pic *acpi_liointc; diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 24a3f4925cfb..04bf1a7f903a 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -246,8 +246,8 @@ #define CSR_ESTAT_EXC_WIDTH 6 #define CSR_ESTAT_EXC (_ULCAST_(0x3f) << CSR_ESTAT_EXC_SHIFT) #define CSR_ESTAT_IS_SHIFT 0 -#define CSR_ESTAT_IS_WIDTH 14 -#define CSR_ESTAT_IS (_ULCAST_(0x3fff) << CSR_ESTAT_IS_SHIFT) +#define CSR_ESTAT_IS_WIDTH 15 +#define CSR_ESTAT_IS (_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT) #define LOONGARCH_CSR_ERA 0x6 /* ERA */ @@ -642,6 +642,13 @@ #define LOONGARCH_CSR_CTAG 0x98 /* TagLo + TagHi */ +#define LOONGARCH_CSR_ISR0 0xa0 +#define LOONGARCH_CSR_ISR1 0xa1 +#define LOONGARCH_CSR_ISR2 0xa2 +#define LOONGARCH_CSR_ISR3 0xa3 + +#define LOONGARCH_CSR_IRR 0xa4 + #define LOONGARCH_CSR_PRID 0xc0 /* Shadow MCSR : 0xc0 ~ 0xff */ @@ -1004,7 +1011,7 @@ /* * CSR_ECFG IM */ -#define ECFG0_IM 0x00001fff +#define ECFG0_IM 0x00005fff #define ECFGB_SIP0 0 #define ECFGF_SIP0 (_ULCAST_(1) << ECFGB_SIP0) #define ECFGB_SIP1 1 @@ -1047,6 +1054,7 @@ #define IOCSRF_EIODECODE BIT_ULL(9) #define IOCSRF_FLATMODE BIT_ULL(10) #define IOCSRF_VM BIT_ULL(11) +#define IOCSRF_AVEC BIT_ULL(15) #define LOONGARCH_IOCSR_VENDOR 0x10 @@ -1058,6 +1066,7 @@ #define IOCSR_MISC_FUNC_SOFT_INT BIT_ULL(10) #define IOCSR_MISC_FUNC_TIMER_RESET BIT_ULL(21) #define IOCSR_MISC_FUNC_EXT_IOI_EN BIT_ULL(48) +#define IOCSR_MISC_FUNC_AVEC_EN BIT_ULL(51) #define LOONGARCH_IOCSR_CPUTEMP 0x428 @@ -1380,9 +1389,10 @@ __BUILD_CSR_OP(tlbidx) #define INT_TI 11 /* Timer */ #define INT_IPI 12 #define INT_NMI 13 +#define INT_AVEC 14 /* ExcCodes corresponding to interrupts */ -#define EXCCODE_INT_NUM (INT_NMI + 1) +#define EXCCODE_INT_NUM (INT_AVEC + 1) #define EXCCODE_INT_START 64 #define EXCCODE_INT_END (EXCCODE_INT_START + EXCCODE_INT_NUM - 1) diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 50db503f44e3..3383c9d24e94 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -70,10 +70,12 @@ extern int __cpu_logical_map[NR_CPUS]; #define ACTION_RESCHEDULE 1 #define ACTION_CALL_FUNCTION 2 #define ACTION_IRQ_WORK 3 +#define ACTION_CLEAR_VECTOR 4 #define SMP_BOOT_CPU BIT(ACTION_BOOT_CPU) #define SMP_RESCHEDULE BIT(ACTION_RESCHEDULE) #define SMP_CALL_FUNCTION BIT(ACTION_CALL_FUNCTION) #define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK) +#define SMP_CLEAR_VECTOR BIT(ACTION_CLEAR_VECTOR) struct secondary_data { unsigned long stack; diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 55320813ee08..14f0449f5452 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -106,7 +106,6 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) elf_hwcap |= HWCAP_LOONGARCH_CRC32; } - config = read_cpucfg(LOONGARCH_CPUCFG2); if (config & CPUCFG2_LAM) { c->options |= LOONGARCH_CPU_LAM; @@ -174,6 +173,8 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options |= LOONGARCH_CPU_FLATMODE; if (config & IOCSRF_EIODECODE) c->options |= LOONGARCH_CPU_EIODECODE; + if (config & IOCSRF_AVEC) + c->options |= LOONGARCH_CPU_AVECINT; if (config & IOCSRF_VM) c->options |= LOONGARCH_CPU_HYPERVISOR; diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index adac8fcbb2ac..d129039b368b 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -87,6 +87,18 @@ static void __init init_vec_parent_group(void) acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse); } +int __init arch_probe_nr_irqs(void) +{ + int nr_io_pics = bitmap_weight(loongson_sysconf.cores_io_master, NR_CPUS); + + if (!cpu_has_avecint) + nr_irqs = (64 + NR_VECTORS * nr_io_pics); + else + nr_irqs = (64 + NR_VECTORS * (nr_cpu_ids + nr_io_pics)); + + return NR_IRQS_LEGACY; +} + void __init init_IRQ(void) { int i; diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c index 708eda025ed8..a5fc61f8b348 100644 --- a/arch/loongarch/kernel/paravirt.c +++ b/arch/loongarch/kernel/paravirt.c @@ -135,6 +135,11 @@ static irqreturn_t pv_ipi_interrupt(int irq, void *dev) info->ipi_irqs[IPI_IRQ_WORK]++; } + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + info->ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 482b3c7e3042..9afc2d8b3414 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -72,6 +72,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNCTION] = "Function call interrupts", [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_CLEAR_VECTOR] = "Clear vector interrupts", }; void show_ipi_list(struct seq_file *p, int prec) @@ -248,6 +249,11 @@ static irqreturn_t loongson_ipi_interrupt(int irq, void *dev) per_cpu(irq_stat, cpu).ipi_irqs[IPI_IRQ_WORK]++; } + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + per_cpu(irq_stat, cpu).ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c index 10f1f294e91f..14b774b9d308 100644 --- a/arch/m68k/q40/q40ints.c +++ b/arch/m68k/q40/q40ints.c @@ -106,7 +106,7 @@ void __init q40_init_IRQ(void) * this stuff doesn't really belong here.. */ -int ql_ticks; /* 200Hz ticks since last jiffie */ +int ql_ticks; /* 200Hz ticks since last jiffy */ static int sound_ticks; #define SVOL 45 diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 0362fc5df7b0..39e193cad2b9 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -439,7 +439,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } /* preload SMP state for boot cpu */ -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { if (mp_ops->prepare_boot_cpu) mp_ops->prepare_boot_cpu(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 46e6d2cd7a2d..4ab9b8cee77a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1166,7 +1166,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) cpu_smt_set_num_threads(num_threads, threads_per_core); } -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { BUG_ON(smp_processor_id() != boot_cpuid); #ifdef CONFIG_PPC64 diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index a05ac0716ecf..a3aa0199222e 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -314,7 +314,7 @@ static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, /* * Need to give user space some time to set everything up, - * so do it a jiffie or two later everywhere. + * so do it a jiffy or two later everywhere. */ schedule_timeout(2); diff --git a/block/blk-mq.c b/block/blk-mq.c index 3f1f7d0b3ff3..831c5cf5d874 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1128,7 +1128,7 @@ static void blk_complete_reqs(struct llist_head *list) rq->q->mq_ops->complete(rq); } -static __latent_entropy void blk_done_softirq(struct softirq_action *h) +static __latent_entropy void blk_done_softirq(void) { blk_complete_reqs(this_cpu_ptr(&blk_cpu_done)); } diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 96ad571d041a..e093028391af 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -980,7 +980,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, ipmi_ssif_unlock_cond(ssif_info, flags); start_get(ssif_info); } else { - /* Wait a jiffie then request the next message */ + /* Wait a jiffy then request the next message */ ssif_info->waiting_alert = true; ssif_info->retries_left = SSIF_RECV_RETRIES; if (!ssif_info->stopping) diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 82338773602c..b4330a01a566 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -25,6 +25,10 @@ #include #include +static void *suspend_resume_cb_data; + +static void (*suspend_resume_callback)(void *data, bool suspend); + /* * The I/O port the PMTMR resides at. * The location is detected during setup_arch(), @@ -58,6 +62,32 @@ u32 acpi_pm_read_verified(void) return v2; } +void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data) +{ + suspend_resume_callback = cb; + suspend_resume_cb_data = data; +} +EXPORT_SYMBOL_GPL(acpi_pmtmr_register_suspend_resume_callback); + +void acpi_pmtmr_unregister_suspend_resume_callback(void) +{ + suspend_resume_callback = NULL; + suspend_resume_cb_data = NULL; +} +EXPORT_SYMBOL_GPL(acpi_pmtmr_unregister_suspend_resume_callback); + +static void acpi_pm_suspend(struct clocksource *cs) +{ + if (suspend_resume_callback) + suspend_resume_callback(suspend_resume_cb_data, true); +} + +static void acpi_pm_resume(struct clocksource *cs) +{ + if (suspend_resume_callback) + suspend_resume_callback(suspend_resume_cb_data, false); +} + static u64 acpi_pm_read(struct clocksource *cs) { return (u64)read_pmtmr(); @@ -69,6 +99,8 @@ static struct clocksource clocksource_acpi_pm = { .read = acpi_pm_read, .mask = (u64)ACPI_PM_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .suspend = acpi_pm_suspend, + .resume = acpi_pm_resume, }; diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index aeafc74181f0..03733101e231 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -1594,7 +1594,6 @@ static int __init arch_timer_mem_of_init(struct device_node *np) { struct arch_timer_mem *timer_mem; struct arch_timer_mem_frame *frame; - struct device_node *frame_node; struct resource res; int ret = -EINVAL; u32 rate; @@ -1608,33 +1607,29 @@ static int __init arch_timer_mem_of_init(struct device_node *np) timer_mem->cntctlbase = res.start; timer_mem->size = resource_size(&res); - for_each_available_child_of_node(np, frame_node) { + for_each_available_child_of_node_scoped(np, frame_node) { u32 n; struct arch_timer_mem_frame *frame; if (of_property_read_u32(frame_node, "frame-number", &n)) { pr_err(FW_BUG "Missing frame-number.\n"); - of_node_put(frame_node); goto out; } if (n >= ARCH_TIMER_MEM_MAX_FRAMES) { pr_err(FW_BUG "Wrong frame-number, only 0-%u are permitted.\n", ARCH_TIMER_MEM_MAX_FRAMES - 1); - of_node_put(frame_node); goto out; } frame = &timer_mem->frame[n]; if (frame->valid) { pr_err(FW_BUG "Duplicated frame-number.\n"); - of_node_put(frame_node); goto out; } - if (of_address_to_resource(frame_node, 0, &res)) { - of_node_put(frame_node); + if (of_address_to_resource(frame_node, 0, &res)) goto out; - } + frame->cntbase = res.start; frame->size = resource_size(&res); diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c index 5b39d3701fa3..8f97ab0b01ec 100644 --- a/drivers/clocksource/asm9260_timer.c +++ b/drivers/clocksource/asm9260_timer.c @@ -210,6 +210,7 @@ static int __init asm9260_timer_init(struct device_node *np) DRIVER_NAME, &event_dev); if (ret) { pr_err("Failed to setup irq!\n"); + clk_disable_unprepare(clk); return ret; } diff --git a/drivers/clocksource/ingenic-ost.c b/drivers/clocksource/ingenic-ost.c index 9f7c280a1336..e0ec33307c84 100644 --- a/drivers/clocksource/ingenic-ost.c +++ b/drivers/clocksource/ingenic-ost.c @@ -93,14 +93,10 @@ static int __init ingenic_ost_probe(struct platform_device *pdev) return PTR_ERR(map); } - ost->clk = devm_clk_get(dev, "ost"); + ost->clk = devm_clk_get_enabled(dev, "ost"); if (IS_ERR(ost->clk)) return PTR_ERR(ost->clk); - err = clk_prepare_enable(ost->clk); - if (err) - return err; - /* Clear counter high/low registers */ if (soc_info->is64bit) regmap_write(map, TCU_REG_OST_CNTL, 0); @@ -129,7 +125,6 @@ static int __init ingenic_ost_probe(struct platform_device *pdev) err = clocksource_register_hz(cs, rate); if (err) { dev_err(dev, "clocksource registration failed"); - clk_disable_unprepare(ost->clk); return err; } diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c index a4a991101fa3..a3fe98cd3838 100644 --- a/drivers/clocksource/jcore-pit.c +++ b/drivers/clocksource/jcore-pit.c @@ -120,7 +120,7 @@ static int jcore_pit_local_init(unsigned cpu) static irqreturn_t jcore_timer_interrupt(int irq, void *dev_id) { - struct jcore_pit *pit = this_cpu_ptr(dev_id); + struct jcore_pit *pit = dev_id; if (clockevent_state_oneshot(&pit->ced)) jcore_pit_disable(pit); @@ -168,9 +168,8 @@ static int __init jcore_pit_init(struct device_node *node) return -ENOMEM; } - err = request_irq(pit_irq, jcore_timer_interrupt, - IRQF_TIMER | IRQF_PERCPU, - "jcore_pit", jcore_pit_percpu); + err = request_percpu_irq(pit_irq, jcore_timer_interrupt, + "jcore_pit", jcore_pit_percpu); if (err) { pr_err("pit irq request failed: %d\n", err); free_percpu(jcore_pit_percpu); diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c index ca7a06489c40..b8a1cf59b9d6 100644 --- a/drivers/clocksource/timer-cadence-ttc.c +++ b/drivers/clocksource/timer-cadence-ttc.c @@ -435,7 +435,7 @@ static int __init ttc_setup_clockevent(struct clk *clk, &ttcce->ttc.clk_rate_change_nb); if (err) { pr_warn("Unable to register clock notifier.\n"); - goto out_kfree; + goto out_clk_unprepare; } ttcce->ttc.freq = clk_get_rate(ttcce->ttc.clk); @@ -465,13 +465,15 @@ static int __init ttc_setup_clockevent(struct clk *clk, err = request_irq(irq, ttc_clock_event_interrupt, IRQF_TIMER, ttcce->ce.name, ttcce); if (err) - goto out_kfree; + goto out_clk_unprepare; clockevents_config_and_register(&ttcce->ce, ttcce->ttc.freq / PRESCALE, 1, 0xfffe); return 0; +out_clk_unprepare: + clk_disable_unprepare(ttcce->ttc.clk); out_kfree: kfree(ttcce); return err; diff --git a/drivers/clocksource/timer-qcom.c b/drivers/clocksource/timer-qcom.c index b4afe3a67583..eac4c95c6127 100644 --- a/drivers/clocksource/timer-qcom.c +++ b/drivers/clocksource/timer-qcom.c @@ -233,6 +233,7 @@ static int __init msm_dt_timer_init(struct device_node *np) } if (of_property_read_u32(np, "clock-frequency", &freq)) { + iounmap(cpu0_base); pr_err("Unknown frequency\n"); return -EINVAL; } @@ -243,7 +244,11 @@ static int __init msm_dt_timer_init(struct device_node *np) freq /= 4; writel_relaxed(DGT_CLK_CTL_DIV_4, source_base + DGT_CLK_CTL); - return msm_timer_init(freq, 32, irq, !!percpu_offset); + ret = msm_timer_init(freq, 32, irq, !!percpu_offset); + if (ret) + iounmap(cpu0_base); + + return ret; } TIMER_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init); TIMER_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init); diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c index 6a1bfcd0cc21..cf2ce3744ce6 100644 --- a/drivers/dma-buf/st-dma-fence.c +++ b/drivers/dma-buf/st-dma-fence.c @@ -402,7 +402,7 @@ static int test_wait_timeout(void *arg) if (dma_fence_wait_timeout(wt.f, false, 2) == -ETIME) { if (timer_pending(&wt.timer)) { - pr_notice("Timer did not fire within the jiffie!\n"); + pr_notice("Timer did not fire within the jiffy!\n"); err = 0; /* not our fault! */ } else { pr_err("Wait reported incomplete after timeout\n"); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index d4b918fb11ce..1f55e62044a4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -266,7 +266,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns)) args->timeout_ns = 0; - /* Asked to wait beyond the jiffie/scheduler precision? */ + /* Asked to wait beyond the jiffy/scheduler precision? */ if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; } diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 4202df5b8c12..222ca7c44951 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -93,7 +93,7 @@ static int wait_for_reset(struct intel_engine_cs *engine, return -EINVAL; } - /* Give the request a jiffie to complete after flushing the worker */ + /* Give the request a jiffy to complete after flushing the worker */ if (i915_request_wait(rq, 0, max(0l, (long)(timeout - jiffies)) + 1) < 0) { pr_err("%s: hanging request %llx:%lld did not complete\n", @@ -3426,7 +3426,7 @@ static int live_preempt_timeout(void *arg) cpu_relax(); saved_timeout = engine->props.preempt_timeout_ms; - engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffie */ + engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffy */ i915_request_get(rq); i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index 6f9e7b354b54..f2ba51c20e97 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -110,7 +110,7 @@ void set_timer_ms(struct timer_list *t, unsigned long timeout) * Paranoia to make sure the compiler computes the timeout before * loading 'jiffies' as jiffies is volatile and may be updated in * the background by a timer tick. All to reduce the complexity - * of the addition and reduce the risk of losing a jiffie. + * of the addition and reduce the risk of losing a jiffy. */ barrier(); diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c index a165cbcdd27b..9eafe53a8f41 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -279,7 +279,7 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, else args->timeout_ns = 0; - /* Asked to wait beyond the jiffie/scheduler precision? */ + /* Asked to wait beyond the jiffy/scheduler precision? */ if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index d078bdc48c38..341cd9ca5a05 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -685,6 +685,7 @@ config LOONGSON_PCH_MSI depends on PCI default MACH_LOONGSON64 select IRQ_DOMAIN_HIERARCHY + select IRQ_MSI_LIB select PCI_MSI help Support for the Loongson PCH MSI Controller. diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 15635812b2d6..e3679ec2b9f7 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -110,7 +110,7 @@ obj-$(CONFIG_LS1X_IRQ) += irq-ls1x.o obj-$(CONFIG_TI_SCI_INTR_IRQCHIP) += irq-ti-sci-intr.o obj-$(CONFIG_TI_SCI_INTA_IRQCHIP) += irq-ti-sci-inta.o obj-$(CONFIG_TI_PRUSS_INTC) += irq-pruss-intc.o -obj-$(CONFIG_IRQ_LOONGARCH_CPU) += irq-loongarch-cpu.o +obj-$(CONFIG_IRQ_LOONGARCH_CPU) += irq-loongarch-cpu.o irq-loongarch-avec.o obj-$(CONFIG_LOONGSON_LIOINTC) += irq-loongson-liointc.o obj-$(CONFIG_LOONGSON_EIOINTC) += irq-loongson-eiointc.o obj-$(CONFIG_LOONGSON_HTPIC) += irq-loongson-htpic.o diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index 5c534d9fd2b0..da5250f0155c 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -234,7 +234,10 @@ enum fiq_hwirq { AIC_NR_FIQ }; +/* True if UNCORE/UNCORE2 and Sn_... IPI registers are present and used (A11+) */ static DEFINE_STATIC_KEY_TRUE(use_fast_ipi); +/* True if SYS_IMP_APL_IPI_RR_LOCAL_EL1 exists for local fast IPIs (M1+) */ +static DEFINE_STATIC_KEY_TRUE(use_local_fast_ipi); struct aic_info { int version; @@ -252,6 +255,7 @@ struct aic_info { /* Features */ bool fast_ipi; + bool local_fast_ipi; }; static const struct aic_info aic1_info __initconst = { @@ -270,17 +274,32 @@ static const struct aic_info aic1_fipi_info __initconst = { .fast_ipi = true, }; +static const struct aic_info aic1_local_fipi_info __initconst = { + .version = 1, + + .event = AIC_EVENT, + .target_cpu = AIC_TARGET_CPU, + + .fast_ipi = true, + .local_fast_ipi = true, +}; + static const struct aic_info aic2_info __initconst = { .version = 2, .irq_cfg = AIC2_IRQ_CFG, .fast_ipi = true, + .local_fast_ipi = true, }; static const struct of_device_id aic_info_match[] = { { .compatible = "apple,t8103-aic", + .data = &aic1_local_fipi_info, + }, + { + .compatible = "apple,t8015-aic", .data = &aic1_fipi_info, }, { @@ -532,14 +551,9 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs) * we check for everything here, even things we don't support yet. */ - if (read_sysreg_s(SYS_IMP_APL_IPI_SR_EL1) & IPI_SR_PENDING) { - if (static_branch_likely(&use_fast_ipi)) { - aic_handle_ipi(regs); - } else { - pr_err_ratelimited("Fast IPI fired. Acking.\n"); - write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1); - } - } + if (static_branch_likely(&use_fast_ipi) && + (read_sysreg_s(SYS_IMP_APL_IPI_SR_EL1) & IPI_SR_PENDING)) + aic_handle_ipi(regs); if (TIMER_FIRING(read_sysreg(cntp_ctl_el0))) generic_handle_domain_irq(aic_irqc->hw_domain, @@ -574,8 +588,9 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs) AIC_FIQ_HWIRQ(irq)); } - if (FIELD_GET(UPMCR0_IMODE, read_sysreg_s(SYS_IMP_APL_UPMCR0_EL1)) == UPMCR0_IMODE_FIQ && - (read_sysreg_s(SYS_IMP_APL_UPMSR_EL1) & UPMSR_IACT)) { + if (static_branch_likely(&use_fast_ipi) && + (FIELD_GET(UPMCR0_IMODE, read_sysreg_s(SYS_IMP_APL_UPMCR0_EL1)) == UPMCR0_IMODE_FIQ) && + (read_sysreg_s(SYS_IMP_APL_UPMSR_EL1) & UPMSR_IACT)) { /* Same story with uncore PMCs */ pr_err_ratelimited("Uncore PMC FIQ fired. Masking.\n"); sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE, @@ -750,12 +765,12 @@ static void aic_ipi_send_fast(int cpu) u64 cluster = MPIDR_CLUSTER(mpidr); u64 idx = MPIDR_CPU(mpidr); - if (MPIDR_CLUSTER(my_mpidr) == cluster) - write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx), - SYS_IMP_APL_IPI_RR_LOCAL_EL1); - else + if (static_branch_likely(&use_local_fast_ipi) && MPIDR_CLUSTER(my_mpidr) == cluster) { + write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx), SYS_IMP_APL_IPI_RR_LOCAL_EL1); + } else { write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx) | FIELD_PREP(IPI_RR_CLUSTER, cluster), SYS_IMP_APL_IPI_RR_GLOBAL_EL1); + } isb(); } @@ -811,7 +826,8 @@ static int aic_init_cpu(unsigned int cpu) /* Mask all hard-wired per-CPU IRQ/FIQ sources */ /* Pending Fast IPI FIQs */ - write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1); + if (static_branch_likely(&use_fast_ipi)) + write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1); /* Timer FIQs */ sysreg_clear_set(cntp_ctl_el0, 0, ARCH_TIMER_CTRL_IT_MASK); @@ -832,8 +848,10 @@ static int aic_init_cpu(unsigned int cpu) FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_OFF)); /* Uncore PMC FIQ */ - sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE, - FIELD_PREP(UPMCR0_IMODE, UPMCR0_IMODE_OFF)); + if (static_branch_likely(&use_fast_ipi)) { + sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE, + FIELD_PREP(UPMCR0_IMODE, UPMCR0_IMODE_OFF)); + } /* Commit all of the above */ isb(); @@ -987,11 +1005,12 @@ static int __init aic_of_ic_init(struct device_node *node, struct device_node *p off += sizeof(u32) * (irqc->max_irq >> 5); /* MASK_CLR */ off += sizeof(u32) * (irqc->max_irq >> 5); /* HW_STATE */ - if (irqc->info.fast_ipi) - static_branch_enable(&use_fast_ipi); - else + if (!irqc->info.fast_ipi) static_branch_disable(&use_fast_ipi); + if (!irqc->info.local_fast_ipi) + static_branch_disable(&use_local_fast_ipi); + irqc->info.die_stride = off - start_off; irqc->hw_domain = irq_domain_create_tree(of_node_to_fwnode(node), diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index dce2b80bf439..d7c5ef248474 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell Armada 370 and Armada XP SoC IRQ handling * @@ -7,13 +8,11 @@ * Gregory CLEMENT * Thomas Petazzoni * Ben Dooks - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ +#include #include +#include #include #include #include @@ -66,19 +65,17 @@ * device * * The "global interrupt mask/unmask" is modified using the - * ARMADA_370_XP_INT_SET_ENABLE_OFFS and - * ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS registers, which are relative - * to "main_int_base". + * MPIC_INT_SET_ENABLE and MPIC_INT_CLEAR_ENABLE + * registers, which are relative to "mpic->base". * - * The "per-CPU mask/unmask" is modified using the - * ARMADA_370_XP_INT_SET_MASK_OFFS and - * ARMADA_370_XP_INT_CLEAR_MASK_OFFS registers, which are relative to - * "per_cpu_int_base". This base address points to a special address, + * The "per-CPU mask/unmask" is modified using the MPIC_INT_SET_MASK + * and MPIC_INT_CLEAR_MASK registers, which are relative to + * "mpic->per_cpu". This base address points to a special address, * which automatically accesses the registers of the current CPU. * * The per-CPU mask/unmask can also be adjusted using the global - * per-interrupt ARMADA_370_XP_INT_SOURCE_CTL register, which we use - * to configure interrupt affinity. + * per-interrupt MPIC_INT_SOURCE_CTL register, which we use to + * configure interrupt affinity. * * Due to this model, all interrupts need to be mask/unmasked at two * different levels: at the global level and at the per-CPU level. @@ -92,9 +89,8 @@ * the current CPU, running the ->map() code. This allows to have * the interrupt unmasked at this level in non-SMP * configurations. In SMP configurations, the ->set_affinity() - * callback is called, which using the - * ARMADA_370_XP_INT_SOURCE_CTL() readjusts the per-CPU mask/unmask - * for the interrupt. + * callback is called, which using the MPIC_INT_SOURCE_CTL() + * readjusts the per-CPU mask/unmask for the interrupt. * * The ->mask() and ->unmask() operations only mask/unmask the * interrupt at the "global" level. @@ -116,58 +112,84 @@ * at the per-CPU level. */ -/* Registers relative to main_int_base */ -#define ARMADA_370_XP_INT_CONTROL (0x00) -#define ARMADA_370_XP_SW_TRIG_INT_OFFS (0x04) -#define ARMADA_370_XP_INT_SET_ENABLE_OFFS (0x30) -#define ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS (0x34) -#define ARMADA_370_XP_INT_SOURCE_CTL(irq) (0x100 + irq*4) -#define ARMADA_370_XP_INT_SOURCE_CPU_MASK 0xF -#define ARMADA_370_XP_INT_IRQ_FIQ_MASK(cpuid) ((BIT(0) | BIT(8)) << cpuid) +/* Registers relative to mpic->base */ +#define MPIC_INT_CONTROL 0x00 +#define MPIC_INT_CONTROL_NUMINT_MASK GENMASK(12, 2) +#define MPIC_SW_TRIG_INT 0x04 +#define MPIC_INT_SET_ENABLE 0x30 +#define MPIC_INT_CLEAR_ENABLE 0x34 +#define MPIC_INT_SOURCE_CTL(hwirq) (0x100 + (hwirq) * 4) +#define MPIC_INT_SOURCE_CPU_MASK GENMASK(3, 0) +#define MPIC_INT_IRQ_FIQ_MASK(cpuid) ((BIT(0) | BIT(8)) << (cpuid)) -/* Registers relative to per_cpu_int_base */ -#define ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS (0x08) -#define ARMADA_370_XP_IN_DRBEL_MSK_OFFS (0x0c) -#define ARMADA_375_PPI_CAUSE (0x10) -#define ARMADA_370_XP_CPU_INTACK_OFFS (0x44) -#define ARMADA_370_XP_INT_SET_MASK_OFFS (0x48) -#define ARMADA_370_XP_INT_CLEAR_MASK_OFFS (0x4C) -#define ARMADA_370_XP_INT_FABRIC_MASK_OFFS (0x54) -#define ARMADA_370_XP_INT_CAUSE_PERF(cpu) (1 << cpu) +/* Registers relative to mpic->per_cpu */ +#define MPIC_IN_DRBEL_CAUSE 0x08 +#define MPIC_IN_DRBEL_MASK 0x0c +#define MPIC_PPI_CAUSE 0x10 +#define MPIC_CPU_INTACK 0x44 +#define MPIC_CPU_INTACK_IID_MASK GENMASK(9, 0) +#define MPIC_INT_SET_MASK 0x48 +#define MPIC_INT_CLEAR_MASK 0x4C +#define MPIC_INT_FABRIC_MASK 0x54 +#define MPIC_INT_CAUSE_PERF(cpu) BIT(cpu) -#define ARMADA_370_XP_MAX_PER_CPU_IRQS (28) +#define MPIC_PER_CPU_IRQS_NR 29 /* IPI and MSI interrupt definitions for IPI platforms */ -#define IPI_DOORBELL_START (0) -#define IPI_DOORBELL_END (8) -#define IPI_DOORBELL_MASK 0xFF -#define PCI_MSI_DOORBELL_START (16) -#define PCI_MSI_DOORBELL_NR (16) -#define PCI_MSI_DOORBELL_END (32) -#define PCI_MSI_DOORBELL_MASK 0xFFFF0000 +#define IPI_DOORBELL_NR 8 +#define IPI_DOORBELL_MASK GENMASK(7, 0) +#define PCI_MSI_DOORBELL_START 16 +#define PCI_MSI_DOORBELL_NR 16 +#define PCI_MSI_DOORBELL_MASK GENMASK(31, 16) /* MSI interrupt definitions for non-IPI platforms */ #define PCI_MSI_FULL_DOORBELL_START 0 #define PCI_MSI_FULL_DOORBELL_NR 32 -#define PCI_MSI_FULL_DOORBELL_END 32 #define PCI_MSI_FULL_DOORBELL_MASK GENMASK(31, 0) #define PCI_MSI_FULL_DOORBELL_SRC0_MASK GENMASK(15, 0) #define PCI_MSI_FULL_DOORBELL_SRC1_MASK GENMASK(31, 16) -static void __iomem *per_cpu_int_base; -static void __iomem *main_int_base; -static struct irq_domain *armada_370_xp_mpic_domain; -static u32 doorbell_mask_reg; -static int parent_irq; -#ifdef CONFIG_PCI_MSI -static struct irq_domain *armada_370_xp_msi_domain; -static struct irq_domain *armada_370_xp_msi_inner_domain; -static DECLARE_BITMAP(msi_used, PCI_MSI_FULL_DOORBELL_NR); -static DEFINE_MUTEX(msi_used_lock); -static phys_addr_t msi_doorbell_addr; +/** + * struct mpic - MPIC private data structure + * @base: MPIC registers base address + * @per_cpu: per-CPU registers base address + * @parent_irq: parent IRQ if MPIC is not top-level interrupt controller + * @domain: MPIC main interrupt domain + * @ipi_domain: IPI domain + * @msi_domain: MSI domain + * @msi_inner_domain: MSI inner domain + * @msi_used: bitmap of used MSI numbers + * @msi_lock: mutex serializing access to @msi_used + * @msi_doorbell_addr: physical address of MSI doorbell register + * @msi_doorbell_mask: mask of available doorbell bits for MSIs (either PCI_MSI_DOORBELL_MASK or + * PCI_MSI_FULL_DOORBELL_MASK) + * @msi_doorbell_start: first set bit in @msi_doorbell_mask + * @msi_doorbell_size: number of set bits in @msi_doorbell_mask + * @doorbell_mask: doorbell mask of MSIs and IPIs, stored on suspend, restored on resume + */ +struct mpic { + void __iomem *base; + void __iomem *per_cpu; + int parent_irq; + struct irq_domain *domain; +#ifdef CONFIG_SMP + struct irq_domain *ipi_domain; #endif +#ifdef CONFIG_PCI_MSI + struct irq_domain *msi_domain; + struct irq_domain *msi_inner_domain; + DECLARE_BITMAP(msi_used, PCI_MSI_FULL_DOORBELL_NR); + struct mutex msi_lock; + phys_addr_t msi_doorbell_addr; + u32 msi_doorbell_mask; + unsigned int msi_doorbell_start, msi_doorbell_size; +#endif + u32 doorbell_mask; +}; -static inline bool is_ipi_available(void) +static struct mpic *mpic_data __ro_after_init; + +static inline bool mpic_is_ipi_available(struct mpic *mpic) { /* * We distinguish IPI availability in the IC by the IC not having a @@ -175,39 +197,12 @@ static inline bool is_ipi_available(void) * interrupt controller (e.g. GIC) that takes care of inter-processor * interrupts. */ - return parent_irq <= 0; + return mpic->parent_irq <= 0; } -static inline u32 msi_doorbell_mask(void) +static inline bool mpic_is_percpu_irq(irq_hw_number_t hwirq) { - return is_ipi_available() ? PCI_MSI_DOORBELL_MASK : - PCI_MSI_FULL_DOORBELL_MASK; -} - -static inline unsigned int msi_doorbell_start(void) -{ - return is_ipi_available() ? PCI_MSI_DOORBELL_START : - PCI_MSI_FULL_DOORBELL_START; -} - -static inline unsigned int msi_doorbell_size(void) -{ - return is_ipi_available() ? PCI_MSI_DOORBELL_NR : - PCI_MSI_FULL_DOORBELL_NR; -} - -static inline unsigned int msi_doorbell_end(void) -{ - return is_ipi_available() ? PCI_MSI_DOORBELL_END : - PCI_MSI_FULL_DOORBELL_END; -} - -static inline bool is_percpu_irq(irq_hw_number_t irq) -{ - if (irq <= ARMADA_370_XP_MAX_PER_CPU_IRQS) - return true; - - return false; + return hwirq < MPIC_PER_CPU_IRQS_NR; } /* @@ -215,55 +210,53 @@ static inline bool is_percpu_irq(irq_hw_number_t irq) * For shared global interrupts, mask/unmask global enable bit * For CPU interrupts, mask/unmask the calling CPU's bit */ -static void armada_370_xp_irq_mask(struct irq_data *d) +static void mpic_irq_mask(struct irq_data *d) { + struct mpic *mpic = irq_data_get_irq_chip_data(d); irq_hw_number_t hwirq = irqd_to_hwirq(d); - if (!is_percpu_irq(hwirq)) - writel(hwirq, main_int_base + - ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS); + if (!mpic_is_percpu_irq(hwirq)) + writel(hwirq, mpic->base + MPIC_INT_CLEAR_ENABLE); else - writel(hwirq, per_cpu_int_base + - ARMADA_370_XP_INT_SET_MASK_OFFS); + writel(hwirq, mpic->per_cpu + MPIC_INT_SET_MASK); } -static void armada_370_xp_irq_unmask(struct irq_data *d) +static void mpic_irq_unmask(struct irq_data *d) { + struct mpic *mpic = irq_data_get_irq_chip_data(d); irq_hw_number_t hwirq = irqd_to_hwirq(d); - if (!is_percpu_irq(hwirq)) - writel(hwirq, main_int_base + - ARMADA_370_XP_INT_SET_ENABLE_OFFS); + if (!mpic_is_percpu_irq(hwirq)) + writel(hwirq, mpic->base + MPIC_INT_SET_ENABLE); else - writel(hwirq, per_cpu_int_base + - ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + writel(hwirq, mpic->per_cpu + MPIC_INT_CLEAR_MASK); } #ifdef CONFIG_PCI_MSI -static struct irq_chip armada_370_xp_msi_irq_chip = { - .name = "MPIC MSI", - .irq_mask = pci_msi_mask_irq, - .irq_unmask = pci_msi_unmask_irq, +static struct irq_chip mpic_msi_irq_chip = { + .name = "MPIC MSI", + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; -static struct msi_domain_info armada_370_xp_msi_domain_info = { +static struct msi_domain_info mpic_msi_domain_info = { .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX), - .chip = &armada_370_xp_msi_irq_chip, + .chip = &mpic_msi_irq_chip, }; -static void armada_370_xp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +static void mpic_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) { - unsigned int cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + unsigned int cpu = cpumask_first(irq_data_get_effective_affinity_mask(d)); + struct mpic *mpic = irq_data_get_irq_chip_data(d); - msg->address_lo = lower_32_bits(msi_doorbell_addr); - msg->address_hi = upper_32_bits(msi_doorbell_addr); - msg->data = BIT(cpu + 8) | (data->hwirq + msi_doorbell_start()); + msg->address_lo = lower_32_bits(mpic->msi_doorbell_addr); + msg->address_hi = upper_32_bits(mpic->msi_doorbell_addr); + msg->data = BIT(cpu + 8) | (d->hwirq + mpic->msi_doorbell_start); } -static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) +static int mpic_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force) { unsigned int cpu; @@ -275,33 +268,34 @@ static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data, if (cpu >= nr_cpu_ids) return -EINVAL; - irq_data_update_effective_affinity(irq_data, cpumask_of(cpu)); + irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK; } -static struct irq_chip armada_370_xp_msi_bottom_irq_chip = { +static struct irq_chip mpic_msi_bottom_irq_chip = { .name = "MPIC MSI", - .irq_compose_msi_msg = armada_370_xp_compose_msi_msg, - .irq_set_affinity = armada_370_xp_msi_set_affinity, + .irq_compose_msi_msg = mpic_compose_msi_msg, + .irq_set_affinity = mpic_msi_set_affinity, }; -static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs, void *args) +static int mpic_msi_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, + void *args) { - int hwirq, i; + struct mpic *mpic = domain->host_data; + int hwirq; - mutex_lock(&msi_used_lock); - hwirq = bitmap_find_free_region(msi_used, msi_doorbell_size(), + mutex_lock(&mpic->msi_lock); + hwirq = bitmap_find_free_region(mpic->msi_used, mpic->msi_doorbell_size, order_base_2(nr_irqs)); - mutex_unlock(&msi_used_lock); + mutex_unlock(&mpic->msi_lock); if (hwirq < 0) return -ENOSPC; - for (i = 0; i < nr_irqs; i++) { + for (unsigned int i = 0; i < nr_irqs; i++) { irq_domain_set_info(domain, virq + i, hwirq + i, - &armada_370_xp_msi_bottom_irq_chip, + &mpic_msi_bottom_irq_chip, domain->host_data, handle_simple_irq, NULL, NULL); } @@ -309,76 +303,84 @@ static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq, return 0; } -static void armada_370_xp_msi_free(struct irq_domain *domain, - unsigned int virq, unsigned int nr_irqs) +static void mpic_msi_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct mpic *mpic = domain->host_data; - mutex_lock(&msi_used_lock); - bitmap_release_region(msi_used, d->hwirq, order_base_2(nr_irqs)); - mutex_unlock(&msi_used_lock); + mutex_lock(&mpic->msi_lock); + bitmap_release_region(mpic->msi_used, d->hwirq, order_base_2(nr_irqs)); + mutex_unlock(&mpic->msi_lock); } -static const struct irq_domain_ops armada_370_xp_msi_domain_ops = { - .alloc = armada_370_xp_msi_alloc, - .free = armada_370_xp_msi_free, +static const struct irq_domain_ops mpic_msi_domain_ops = { + .alloc = mpic_msi_alloc, + .free = mpic_msi_free, }; -static void armada_370_xp_msi_reenable_percpu(void) +static void mpic_msi_reenable_percpu(struct mpic *mpic) { u32 reg; /* Enable MSI doorbell mask and combined cpu local interrupt */ - reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); - reg |= msi_doorbell_mask(); - writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + reg = readl(mpic->per_cpu + MPIC_IN_DRBEL_MASK); + reg |= mpic->msi_doorbell_mask; + writel(reg, mpic->per_cpu + MPIC_IN_DRBEL_MASK); /* Unmask local doorbell interrupt */ - writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + writel(1, mpic->per_cpu + MPIC_INT_CLEAR_MASK); } -static int armada_370_xp_msi_init(struct device_node *node, - phys_addr_t main_int_phys_base) +static int __init mpic_msi_init(struct mpic *mpic, struct device_node *node, + phys_addr_t main_int_phys_base) { - msi_doorbell_addr = main_int_phys_base + - ARMADA_370_XP_SW_TRIG_INT_OFFS; + mpic->msi_doorbell_addr = main_int_phys_base + MPIC_SW_TRIG_INT; - armada_370_xp_msi_inner_domain = - irq_domain_add_linear(NULL, msi_doorbell_size(), - &armada_370_xp_msi_domain_ops, NULL); - if (!armada_370_xp_msi_inner_domain) + mutex_init(&mpic->msi_lock); + + if (mpic_is_ipi_available(mpic)) { + mpic->msi_doorbell_start = PCI_MSI_DOORBELL_START; + mpic->msi_doorbell_size = PCI_MSI_DOORBELL_NR; + mpic->msi_doorbell_mask = PCI_MSI_DOORBELL_MASK; + } else { + mpic->msi_doorbell_start = PCI_MSI_FULL_DOORBELL_START; + mpic->msi_doorbell_size = PCI_MSI_FULL_DOORBELL_NR; + mpic->msi_doorbell_mask = PCI_MSI_FULL_DOORBELL_MASK; + } + + mpic->msi_inner_domain = irq_domain_add_linear(NULL, mpic->msi_doorbell_size, + &mpic_msi_domain_ops, mpic); + if (!mpic->msi_inner_domain) return -ENOMEM; - armada_370_xp_msi_domain = - pci_msi_create_irq_domain(of_node_to_fwnode(node), - &armada_370_xp_msi_domain_info, - armada_370_xp_msi_inner_domain); - if (!armada_370_xp_msi_domain) { - irq_domain_remove(armada_370_xp_msi_inner_domain); + mpic->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(node), &mpic_msi_domain_info, + mpic->msi_inner_domain); + if (!mpic->msi_domain) { + irq_domain_remove(mpic->msi_inner_domain); return -ENOMEM; } - armada_370_xp_msi_reenable_percpu(); + mpic_msi_reenable_percpu(mpic); /* Unmask low 16 MSI irqs on non-IPI platforms */ - if (!is_ipi_available()) - writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + if (!mpic_is_ipi_available(mpic)) + writel(0, mpic->per_cpu + MPIC_INT_CLEAR_MASK); return 0; } #else -static __maybe_unused void armada_370_xp_msi_reenable_percpu(void) {} +static __maybe_unused void mpic_msi_reenable_percpu(struct mpic *mpic) {} -static inline int armada_370_xp_msi_init(struct device_node *node, - phys_addr_t main_int_phys_base) +static inline int mpic_msi_init(struct mpic *mpic, struct device_node *node, + phys_addr_t main_int_phys_base) { return 0; } #endif -static void armada_xp_mpic_perf_init(void) +static void mpic_perf_init(struct mpic *mpic) { - unsigned long cpuid; + u32 cpuid; /* * This Performance Counter Overflow interrupt is specific for @@ -390,38 +392,39 @@ static void armada_xp_mpic_perf_init(void) cpuid = cpu_logical_map(smp_processor_id()); /* Enable Performance Counter Overflow interrupts */ - writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid), - per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS); + writel(MPIC_INT_CAUSE_PERF(cpuid), mpic->per_cpu + MPIC_INT_FABRIC_MASK); } #ifdef CONFIG_SMP -static struct irq_domain *ipi_domain; - -static void armada_370_xp_ipi_mask(struct irq_data *d) +static void mpic_ipi_mask(struct irq_data *d) { + struct mpic *mpic = irq_data_get_irq_chip_data(d); u32 reg; - reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + + reg = readl(mpic->per_cpu + MPIC_IN_DRBEL_MASK); reg &= ~BIT(d->hwirq); - writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + writel(reg, mpic->per_cpu + MPIC_IN_DRBEL_MASK); } -static void armada_370_xp_ipi_unmask(struct irq_data *d) +static void mpic_ipi_unmask(struct irq_data *d) { + struct mpic *mpic = irq_data_get_irq_chip_data(d); u32 reg; - reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + + reg = readl(mpic->per_cpu + MPIC_IN_DRBEL_MASK); reg |= BIT(d->hwirq); - writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + writel(reg, mpic->per_cpu + MPIC_IN_DRBEL_MASK); } -static void armada_370_xp_ipi_send_mask(struct irq_data *d, - const struct cpumask *mask) +static void mpic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask) { - unsigned long map = 0; - int cpu; + struct mpic *mpic = irq_data_get_irq_chip_data(d); + unsigned int cpu; + u32 map = 0; /* Convert our logical CPU mask into a physical one. */ for_each_cpu(cpu, mask) - map |= 1 << cpu_logical_map(cpu); + map |= BIT(cpu_logical_map(cpu)); /* * Ensure that stores to Normal memory are visible to the @@ -430,451 +433,465 @@ static void armada_370_xp_ipi_send_mask(struct irq_data *d, dsb(); /* submit softirq */ - writel((map << 8) | d->hwirq, main_int_base + - ARMADA_370_XP_SW_TRIG_INT_OFFS); + writel((map << 8) | d->hwirq, mpic->base + MPIC_SW_TRIG_INT); } -static void armada_370_xp_ipi_ack(struct irq_data *d) +static void mpic_ipi_ack(struct irq_data *d) { - writel(~BIT(d->hwirq), per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); + struct mpic *mpic = irq_data_get_irq_chip_data(d); + + writel(~BIT(d->hwirq), mpic->per_cpu + MPIC_IN_DRBEL_CAUSE); } -static struct irq_chip ipi_irqchip = { +static struct irq_chip mpic_ipi_irqchip = { .name = "IPI", - .irq_ack = armada_370_xp_ipi_ack, - .irq_mask = armada_370_xp_ipi_mask, - .irq_unmask = armada_370_xp_ipi_unmask, - .ipi_send_mask = armada_370_xp_ipi_send_mask, + .irq_ack = mpic_ipi_ack, + .irq_mask = mpic_ipi_mask, + .irq_unmask = mpic_ipi_unmask, + .ipi_send_mask = mpic_ipi_send_mask, }; -static int armada_370_xp_ipi_alloc(struct irq_domain *d, - unsigned int virq, - unsigned int nr_irqs, void *args) +static int mpic_ipi_alloc(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs, void *args) { - int i; - - for (i = 0; i < nr_irqs; i++) { + for (unsigned int i = 0; i < nr_irqs; i++) { irq_set_percpu_devid(virq + i); - irq_domain_set_info(d, virq + i, i, &ipi_irqchip, - d->host_data, - handle_percpu_devid_irq, - NULL, NULL); + irq_domain_set_info(d, virq + i, i, &mpic_ipi_irqchip, d->host_data, + handle_percpu_devid_irq, NULL, NULL); } return 0; } -static void armada_370_xp_ipi_free(struct irq_domain *d, - unsigned int virq, - unsigned int nr_irqs) +static void mpic_ipi_free(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs) { /* Not freeing IPIs */ } -static const struct irq_domain_ops ipi_domain_ops = { - .alloc = armada_370_xp_ipi_alloc, - .free = armada_370_xp_ipi_free, +static const struct irq_domain_ops mpic_ipi_domain_ops = { + .alloc = mpic_ipi_alloc, + .free = mpic_ipi_free, }; -static void ipi_resume(void) +static void mpic_ipi_resume(struct mpic *mpic) { - int i; + for (irq_hw_number_t i = 0; i < IPI_DOORBELL_NR; i++) { + unsigned int virq = irq_find_mapping(mpic->ipi_domain, i); + struct irq_data *d; - for (i = 0; i < IPI_DOORBELL_END; i++) { - int irq; - - irq = irq_find_mapping(ipi_domain, i); - if (irq <= 0) + if (!virq || !irq_percpu_is_enabled(virq)) continue; - if (irq_percpu_is_enabled(irq)) { - struct irq_data *d; - d = irq_domain_get_irq_data(ipi_domain, irq); - armada_370_xp_ipi_unmask(d); - } + + d = irq_domain_get_irq_data(mpic->ipi_domain, virq); + mpic_ipi_unmask(d); } } -static __init void armada_xp_ipi_init(struct device_node *node) +static int __init mpic_ipi_init(struct mpic *mpic, struct device_node *node) { int base_ipi; - ipi_domain = irq_domain_create_linear(of_node_to_fwnode(node), - IPI_DOORBELL_END, - &ipi_domain_ops, NULL); - if (WARN_ON(!ipi_domain)) - return; + mpic->ipi_domain = irq_domain_create_linear(of_node_to_fwnode(node), IPI_DOORBELL_NR, + &mpic_ipi_domain_ops, mpic); + if (WARN_ON(!mpic->ipi_domain)) + return -ENOMEM; - irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI); - base_ipi = irq_domain_alloc_irqs(ipi_domain, IPI_DOORBELL_END, NUMA_NO_NODE, NULL); + irq_domain_update_bus_token(mpic->ipi_domain, DOMAIN_BUS_IPI); + base_ipi = irq_domain_alloc_irqs(mpic->ipi_domain, IPI_DOORBELL_NR, NUMA_NO_NODE, NULL); if (WARN_ON(!base_ipi)) - return; + return -ENOMEM; - set_smp_ipi_range(base_ipi, IPI_DOORBELL_END); + set_smp_ipi_range(base_ipi, IPI_DOORBELL_NR); + + return 0; } -static int armada_xp_set_affinity(struct irq_data *d, - const struct cpumask *mask_val, bool force) +static int mpic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { + struct mpic *mpic = irq_data_get_irq_chip_data(d); irq_hw_number_t hwirq = irqd_to_hwirq(d); - int cpu; + unsigned int cpu; /* Select a single core from the affinity mask which is online */ cpu = cpumask_any_and(mask_val, cpu_online_mask); - atomic_io_modify(main_int_base + ARMADA_370_XP_INT_SOURCE_CTL(hwirq), - ARMADA_370_XP_INT_SOURCE_CPU_MASK, - BIT(cpu_logical_map(cpu))); + atomic_io_modify(mpic->base + MPIC_INT_SOURCE_CTL(hwirq), + MPIC_INT_SOURCE_CPU_MASK, BIT(cpu_logical_map(cpu))); irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK; } -static void armada_xp_mpic_smp_cpu_init(void) +static void mpic_smp_cpu_init(struct mpic *mpic) { - u32 control; - int nr_irqs, i; + for (irq_hw_number_t i = 0; i < mpic->domain->hwirq_max; i++) + writel(i, mpic->per_cpu + MPIC_INT_SET_MASK); - control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL); - nr_irqs = (control >> 2) & 0x3ff; - - for (i = 0; i < nr_irqs; i++) - writel(i, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); - - if (!is_ipi_available()) + if (!mpic_is_ipi_available(mpic)) return; /* Disable all IPIs */ - writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + writel(0, mpic->per_cpu + MPIC_IN_DRBEL_MASK); /* Clear pending IPIs */ - writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); + writel(0, mpic->per_cpu + MPIC_IN_DRBEL_CAUSE); /* Unmask IPI interrupt */ - writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + writel(0, mpic->per_cpu + MPIC_INT_CLEAR_MASK); } -static void armada_xp_mpic_reenable_percpu(void) +static void mpic_reenable_percpu(struct mpic *mpic) { - unsigned int irq; - /* Re-enable per-CPU interrupts that were enabled before suspend */ - for (irq = 0; irq < ARMADA_370_XP_MAX_PER_CPU_IRQS; irq++) { - struct irq_data *data; - int virq; + for (irq_hw_number_t i = 0; i < MPIC_PER_CPU_IRQS_NR; i++) { + unsigned int virq = irq_linear_revmap(mpic->domain, i); + struct irq_data *d; - virq = irq_linear_revmap(armada_370_xp_mpic_domain, irq); - if (virq == 0) + if (!virq || !irq_percpu_is_enabled(virq)) continue; - data = irq_get_irq_data(virq); - - if (!irq_percpu_is_enabled(virq)) - continue; - - armada_370_xp_irq_unmask(data); + d = irq_get_irq_data(virq); + mpic_irq_unmask(d); } - if (is_ipi_available()) - ipi_resume(); + if (mpic_is_ipi_available(mpic)) + mpic_ipi_resume(mpic); - armada_370_xp_msi_reenable_percpu(); + mpic_msi_reenable_percpu(mpic); } -static int armada_xp_mpic_starting_cpu(unsigned int cpu) +static int mpic_starting_cpu(unsigned int cpu) { - armada_xp_mpic_perf_init(); - armada_xp_mpic_smp_cpu_init(); - armada_xp_mpic_reenable_percpu(); + struct mpic *mpic = irq_get_default_host()->host_data; + + mpic_perf_init(mpic); + mpic_smp_cpu_init(mpic); + mpic_reenable_percpu(mpic); + return 0; } static int mpic_cascaded_starting_cpu(unsigned int cpu) { - armada_xp_mpic_perf_init(); - armada_xp_mpic_reenable_percpu(); - enable_percpu_irq(parent_irq, IRQ_TYPE_NONE); + struct mpic *mpic = mpic_data; + + mpic_perf_init(mpic); + mpic_reenable_percpu(mpic); + enable_percpu_irq(mpic->parent_irq, IRQ_TYPE_NONE); + return 0; } #else -static void armada_xp_mpic_smp_cpu_init(void) {} -static void ipi_resume(void) {} +static void mpic_smp_cpu_init(struct mpic *mpic) {} +static void mpic_ipi_resume(struct mpic *mpic) {} #endif -static struct irq_chip armada_370_xp_irq_chip = { +static struct irq_chip mpic_irq_chip = { .name = "MPIC", - .irq_mask = armada_370_xp_irq_mask, - .irq_mask_ack = armada_370_xp_irq_mask, - .irq_unmask = armada_370_xp_irq_unmask, + .irq_mask = mpic_irq_mask, + .irq_mask_ack = mpic_irq_mask, + .irq_unmask = mpic_irq_unmask, #ifdef CONFIG_SMP - .irq_set_affinity = armada_xp_set_affinity, + .irq_set_affinity = mpic_set_affinity, #endif .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; -static int armada_370_xp_mpic_irq_map(struct irq_domain *h, - unsigned int virq, irq_hw_number_t hw) +static int mpic_irq_map(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq) { + struct mpic *mpic = domain->host_data; + /* IRQs 0 and 1 cannot be mapped, they are handled internally */ - if (hw <= 1) + if (hwirq <= 1) return -EINVAL; - armada_370_xp_irq_mask(irq_get_irq_data(virq)); - if (!is_percpu_irq(hw)) - writel(hw, per_cpu_int_base + - ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + irq_set_chip_data(virq, mpic); + + mpic_irq_mask(irq_get_irq_data(virq)); + if (!mpic_is_percpu_irq(hwirq)) + writel(hwirq, mpic->per_cpu + MPIC_INT_CLEAR_MASK); else - writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); + writel(hwirq, mpic->base + MPIC_INT_SET_ENABLE); irq_set_status_flags(virq, IRQ_LEVEL); - if (is_percpu_irq(hw)) { + if (mpic_is_percpu_irq(hwirq)) { irq_set_percpu_devid(virq); - irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip, - handle_percpu_devid_irq); + irq_set_chip_and_handler(virq, &mpic_irq_chip, handle_percpu_devid_irq); } else { - irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip, - handle_level_irq); + irq_set_chip_and_handler(virq, &mpic_irq_chip, handle_level_irq); irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq))); } irq_set_probe(virq); - return 0; } -static const struct irq_domain_ops armada_370_xp_mpic_irq_ops = { - .map = armada_370_xp_mpic_irq_map, - .xlate = irq_domain_xlate_onecell, +static const struct irq_domain_ops mpic_irq_ops = { + .map = mpic_irq_map, + .xlate = irq_domain_xlate_onecell, }; #ifdef CONFIG_PCI_MSI -static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained) +static void mpic_handle_msi_irq(struct mpic *mpic) { - u32 msimask, msinr; + unsigned long cause; + unsigned int i; - msimask = readl_relaxed(per_cpu_int_base + - ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); - msimask &= msi_doorbell_mask(); + cause = readl_relaxed(mpic->per_cpu + MPIC_IN_DRBEL_CAUSE); + cause &= mpic->msi_doorbell_mask; + writel(~cause, mpic->per_cpu + MPIC_IN_DRBEL_CAUSE); - writel(~msimask, per_cpu_int_base + - ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); - - for (msinr = msi_doorbell_start(); - msinr < msi_doorbell_end(); msinr++) { - unsigned int irq; - - if (!(msimask & BIT(msinr))) - continue; - - irq = msinr - msi_doorbell_start(); - - generic_handle_domain_irq(armada_370_xp_msi_inner_domain, irq); - } + for_each_set_bit(i, &cause, BITS_PER_LONG) + generic_handle_domain_irq(mpic->msi_inner_domain, i - mpic->msi_doorbell_start); } #else -static void armada_370_xp_handle_msi_irq(struct pt_regs *r, bool b) {} +static void mpic_handle_msi_irq(struct mpic *mpic) {} #endif -static void armada_370_xp_mpic_handle_cascade_irq(struct irq_desc *desc) +#ifdef CONFIG_SMP +static void mpic_handle_ipi_irq(struct mpic *mpic) { + unsigned long cause; + irq_hw_number_t i; + + cause = readl_relaxed(mpic->per_cpu + MPIC_IN_DRBEL_CAUSE); + cause &= IPI_DOORBELL_MASK; + + for_each_set_bit(i, &cause, IPI_DOORBELL_NR) + generic_handle_domain_irq(mpic->ipi_domain, i); +} +#else +static inline void mpic_handle_ipi_irq(struct mpic *mpic) {} +#endif + +static void mpic_handle_cascade_irq(struct irq_desc *desc) +{ + struct mpic *mpic = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned long irqmap, irqn, irqsrc, cpuid; + unsigned long cause; + u32 irqsrc, cpuid; + irq_hw_number_t i; chained_irq_enter(chip, desc); - irqmap = readl_relaxed(per_cpu_int_base + ARMADA_375_PPI_CAUSE); + cause = readl_relaxed(mpic->per_cpu + MPIC_PPI_CAUSE); cpuid = cpu_logical_map(smp_processor_id()); - for_each_set_bit(irqn, &irqmap, BITS_PER_LONG) { - irqsrc = readl_relaxed(main_int_base + - ARMADA_370_XP_INT_SOURCE_CTL(irqn)); + for_each_set_bit(i, &cause, MPIC_PER_CPU_IRQS_NR) { + irqsrc = readl_relaxed(mpic->base + MPIC_INT_SOURCE_CTL(i)); /* Check if the interrupt is not masked on current CPU. * Test IRQ (0-1) and FIQ (8-9) mask bits. */ - if (!(irqsrc & ARMADA_370_XP_INT_IRQ_FIQ_MASK(cpuid))) + if (!(irqsrc & MPIC_INT_IRQ_FIQ_MASK(cpuid))) continue; - if (irqn == 0 || irqn == 1) { - armada_370_xp_handle_msi_irq(NULL, true); + if (i == 0 || i == 1) { + mpic_handle_msi_irq(mpic); continue; } - generic_handle_domain_irq(armada_370_xp_mpic_domain, irqn); + generic_handle_domain_irq(mpic->domain, i); } chained_irq_exit(chip, desc); } -static void __exception_irq_entry -armada_370_xp_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry mpic_handle_irq(struct pt_regs *regs) { - u32 irqstat, irqnr; + struct mpic *mpic = irq_get_default_host()->host_data; + irq_hw_number_t i; + u32 irqstat; do { - irqstat = readl_relaxed(per_cpu_int_base + - ARMADA_370_XP_CPU_INTACK_OFFS); - irqnr = irqstat & 0x3FF; + irqstat = readl_relaxed(mpic->per_cpu + MPIC_CPU_INTACK); + i = FIELD_GET(MPIC_CPU_INTACK_IID_MASK, irqstat); - if (irqnr > 1022) + if (i > 1022) break; - if (irqnr > 1) { - generic_handle_domain_irq(armada_370_xp_mpic_domain, - irqnr); - continue; - } + if (i > 1) + generic_handle_domain_irq(mpic->domain, i); /* MSI handling */ - if (irqnr == 1) - armada_370_xp_handle_msi_irq(regs, false); + if (i == 1) + mpic_handle_msi_irq(mpic); -#ifdef CONFIG_SMP /* IPI Handling */ - if (irqnr == 0) { - unsigned long ipimask; - int ipi; - - ipimask = readl_relaxed(per_cpu_int_base + - ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS) - & IPI_DOORBELL_MASK; - - for_each_set_bit(ipi, &ipimask, IPI_DOORBELL_END) - generic_handle_domain_irq(ipi_domain, ipi); - } -#endif - + if (i == 0) + mpic_handle_ipi_irq(mpic); } while (1); } -static int armada_370_xp_mpic_suspend(void) +static int mpic_suspend(void) { - doorbell_mask_reg = readl(per_cpu_int_base + - ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + struct mpic *mpic = mpic_data; + + mpic->doorbell_mask = readl(mpic->per_cpu + MPIC_IN_DRBEL_MASK); + return 0; } -static void armada_370_xp_mpic_resume(void) +static void mpic_resume(void) { + struct mpic *mpic = mpic_data; bool src0, src1; - int nirqs; - irq_hw_number_t irq; /* Re-enable interrupts */ - nirqs = (readl(main_int_base + ARMADA_370_XP_INT_CONTROL) >> 2) & 0x3ff; - for (irq = 0; irq < nirqs; irq++) { - struct irq_data *data; - int virq; + for (irq_hw_number_t i = 0; i < mpic->domain->hwirq_max; i++) { + unsigned int virq = irq_linear_revmap(mpic->domain, i); + struct irq_data *d; - virq = irq_linear_revmap(armada_370_xp_mpic_domain, irq); - if (virq == 0) + if (!virq) continue; - data = irq_get_irq_data(virq); + d = irq_get_irq_data(virq); - if (!is_percpu_irq(irq)) { + if (!mpic_is_percpu_irq(i)) { /* Non per-CPU interrupts */ - writel(irq, per_cpu_int_base + - ARMADA_370_XP_INT_CLEAR_MASK_OFFS); - if (!irqd_irq_disabled(data)) - armada_370_xp_irq_unmask(data); + writel(i, mpic->per_cpu + MPIC_INT_CLEAR_MASK); + if (!irqd_irq_disabled(d)) + mpic_irq_unmask(d); } else { /* Per-CPU interrupts */ - writel(irq, main_int_base + - ARMADA_370_XP_INT_SET_ENABLE_OFFS); + writel(i, mpic->base + MPIC_INT_SET_ENABLE); /* - * Re-enable on the current CPU, - * armada_xp_mpic_reenable_percpu() will take - * care of secondary CPUs when they come up. + * Re-enable on the current CPU, mpic_reenable_percpu() + * will take care of secondary CPUs when they come up. */ if (irq_percpu_is_enabled(virq)) - armada_370_xp_irq_unmask(data); + mpic_irq_unmask(d); } } /* Reconfigure doorbells for IPIs and MSIs */ - writel(doorbell_mask_reg, - per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + writel(mpic->doorbell_mask, mpic->per_cpu + MPIC_IN_DRBEL_MASK); - if (is_ipi_available()) { - src0 = doorbell_mask_reg & IPI_DOORBELL_MASK; - src1 = doorbell_mask_reg & PCI_MSI_DOORBELL_MASK; + if (mpic_is_ipi_available(mpic)) { + src0 = mpic->doorbell_mask & IPI_DOORBELL_MASK; + src1 = mpic->doorbell_mask & PCI_MSI_DOORBELL_MASK; } else { - src0 = doorbell_mask_reg & PCI_MSI_FULL_DOORBELL_SRC0_MASK; - src1 = doorbell_mask_reg & PCI_MSI_FULL_DOORBELL_SRC1_MASK; + src0 = mpic->doorbell_mask & PCI_MSI_FULL_DOORBELL_SRC0_MASK; + src1 = mpic->doorbell_mask & PCI_MSI_FULL_DOORBELL_SRC1_MASK; } if (src0) - writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + writel(0, mpic->per_cpu + MPIC_INT_CLEAR_MASK); if (src1) - writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + writel(1, mpic->per_cpu + MPIC_INT_CLEAR_MASK); - if (is_ipi_available()) - ipi_resume(); + if (mpic_is_ipi_available(mpic)) + mpic_ipi_resume(mpic); } -static struct syscore_ops armada_370_xp_mpic_syscore_ops = { - .suspend = armada_370_xp_mpic_suspend, - .resume = armada_370_xp_mpic_resume, +static struct syscore_ops mpic_syscore_ops = { + .suspend = mpic_suspend, + .resume = mpic_resume, }; -static int __init armada_370_xp_mpic_of_init(struct device_node *node, - struct device_node *parent) +static int __init mpic_map_region(struct device_node *np, int index, + void __iomem **base, phys_addr_t *phys_base) { - struct resource main_int_res, per_cpu_int_res; - int nr_irqs, i; - u32 control; + struct resource res; + int err; - BUG_ON(of_address_to_resource(node, 0, &main_int_res)); - BUG_ON(of_address_to_resource(node, 1, &per_cpu_int_res)); + err = of_address_to_resource(np, index, &res); + if (WARN_ON(err)) + goto fail; - BUG_ON(!request_mem_region(main_int_res.start, - resource_size(&main_int_res), - node->full_name)); - BUG_ON(!request_mem_region(per_cpu_int_res.start, - resource_size(&per_cpu_int_res), - node->full_name)); + if (WARN_ON(!request_mem_region(res.start, resource_size(&res), np->full_name))) { + err = -EBUSY; + goto fail; + } - main_int_base = ioremap(main_int_res.start, - resource_size(&main_int_res)); - BUG_ON(!main_int_base); + *base = ioremap(res.start, resource_size(&res)); + if (WARN_ON(!*base)) { + err = -ENOMEM; + goto fail; + } - per_cpu_int_base = ioremap(per_cpu_int_res.start, - resource_size(&per_cpu_int_res)); - BUG_ON(!per_cpu_int_base); + if (phys_base) + *phys_base = res.start; - control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL); - nr_irqs = (control >> 2) & 0x3ff; + return 0; - for (i = 0; i < nr_irqs; i++) - writel(i, main_int_base + ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS); +fail: + pr_err("%pOF: Unable to map resource %d: %pE\n", np, index, ERR_PTR(err)); + return err; +} - armada_370_xp_mpic_domain = - irq_domain_add_linear(node, nr_irqs, - &armada_370_xp_mpic_irq_ops, NULL); - BUG_ON(!armada_370_xp_mpic_domain); - irq_domain_update_bus_token(armada_370_xp_mpic_domain, DOMAIN_BUS_WIRED); +static int __init mpic_of_init(struct device_node *node, struct device_node *parent) +{ + phys_addr_t phys_base; + unsigned int nr_irqs; + struct mpic *mpic; + int err; + + mpic = kzalloc(sizeof(*mpic), GFP_KERNEL); + if (WARN_ON(!mpic)) + return -ENOMEM; + + mpic_data = mpic; + + err = mpic_map_region(node, 0, &mpic->base, &phys_base); + if (err) + return err; + + err = mpic_map_region(node, 1, &mpic->per_cpu, NULL); + if (err) + return err; + + nr_irqs = FIELD_GET(MPIC_INT_CONTROL_NUMINT_MASK, readl(mpic->base + MPIC_INT_CONTROL)); + + for (irq_hw_number_t i = 0; i < nr_irqs; i++) + writel(i, mpic->base + MPIC_INT_CLEAR_ENABLE); /* - * Initialize parent_irq before calling any other functions, since it is - * used to distinguish between IPI and non-IPI platforms. + * Initialize mpic->parent_irq before calling any other functions, since + * it is used to distinguish between IPI and non-IPI platforms. */ - parent_irq = irq_of_parse_and_map(node, 0); + mpic->parent_irq = irq_of_parse_and_map(node, 0); + + /* + * On non-IPI platforms the driver currently supports only the per-CPU + * interrupts (the first 29 interrupts). See mpic_handle_cascade_irq(). + */ + if (!mpic_is_ipi_available(mpic)) + nr_irqs = MPIC_PER_CPU_IRQS_NR; + + mpic->domain = irq_domain_add_linear(node, nr_irqs, &mpic_irq_ops, mpic); + if (!mpic->domain) { + pr_err("%pOF: Unable to add IRQ domain\n", node); + return -ENOMEM; + } + + irq_domain_update_bus_token(mpic->domain, DOMAIN_BUS_WIRED); /* Setup for the boot CPU */ - armada_xp_mpic_perf_init(); - armada_xp_mpic_smp_cpu_init(); + mpic_perf_init(mpic); + mpic_smp_cpu_init(mpic); - armada_370_xp_msi_init(node, main_int_res.start); + err = mpic_msi_init(mpic, node, phys_base); + if (err) { + pr_err("%pOF: Unable to initialize MSI domain\n", node); + return err; + } - if (parent_irq <= 0) { - irq_set_default_host(armada_370_xp_mpic_domain); - set_handle_irq(armada_370_xp_handle_irq); + if (mpic_is_ipi_available(mpic)) { + irq_set_default_host(mpic->domain); + set_handle_irq(mpic_handle_irq); #ifdef CONFIG_SMP - armada_xp_ipi_init(node); + err = mpic_ipi_init(mpic, node); + if (err) { + pr_err("%pOF: Unable to initialize IPI domain\n", node); + return err; + } + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING, "irqchip/armada/ipi:starting", - armada_xp_mpic_starting_cpu, NULL); + mpic_starting_cpu, NULL); #endif } else { #ifdef CONFIG_SMP @@ -882,13 +899,13 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node, "irqchip/armada/cascade:starting", mpic_cascaded_starting_cpu, NULL); #endif - irq_set_chained_handler(parent_irq, - armada_370_xp_mpic_handle_cascade_irq); + irq_set_chained_handler_and_data(mpic->parent_irq, + mpic_handle_cascade_irq, mpic); } - register_syscore_ops(&armada_370_xp_mpic_syscore_ops); + register_syscore_ops(&mpic_syscore_ops); return 0; } -IRQCHIP_DECLARE(armada_370_xp_mpic, "marvell,mpic", armada_370_xp_mpic_of_init); +IRQCHIP_DECLARE(marvell_mpic, "marvell,mpic", mpic_of_init); diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c index 4631f6847953..3839ad79ad31 100644 --- a/drivers/irqchip/irq-atmel-aic.c +++ b/drivers/irqchip/irq-atmel-aic.c @@ -57,8 +57,7 @@ static struct irq_domain *aic_domain; -static asmlinkage void __exception_irq_entry -aic_handle(struct pt_regs *regs) +static void __exception_irq_entry aic_handle(struct pt_regs *regs) { struct irq_domain_chip_generic *dgc = aic_domain->gc; struct irq_chip_generic *gc = dgc->gc[0]; diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c index 145535bd7560..c0f55dc7b050 100644 --- a/drivers/irqchip/irq-atmel-aic5.c +++ b/drivers/irqchip/irq-atmel-aic5.c @@ -67,8 +67,7 @@ static struct irq_domain *aic5_domain; -static asmlinkage void __exception_irq_entry -aic5_handle(struct pt_regs *regs) +static void __exception_irq_entry aic5_handle(struct pt_regs *regs) { struct irq_chip_generic *bgc = irq_get_domain_generic_chip(aic5_domain, 0); u32 irqnr; diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c index e731e0784f7e..806ebb1de201 100644 --- a/drivers/irqchip/irq-clps711x.c +++ b/drivers/irqchip/irq-clps711x.c @@ -69,7 +69,7 @@ static struct { struct irq_domain_ops ops; } *clps711x_intc; -static asmlinkage void __exception_irq_entry clps711x_irqh(struct pt_regs *regs) +static void __exception_irq_entry clps711x_irqh(struct pt_regs *regs) { u32 irqstat; diff --git a/drivers/irqchip/irq-davinci-cp-intc.c b/drivers/irqchip/irq-davinci-cp-intc.c index 7482c8ed34b2..f4f8e9fadbbf 100644 --- a/drivers/irqchip/irq-davinci-cp-intc.c +++ b/drivers/irqchip/irq-davinci-cp-intc.c @@ -116,8 +116,7 @@ static struct irq_chip davinci_cp_intc_irq_chip = { .flags = IRQCHIP_SKIP_SET_WAKE, }; -static asmlinkage void __exception_irq_entry -davinci_cp_intc_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry davinci_cp_intc_handle_irq(struct pt_regs *regs) { int gpir, irqnr, none; diff --git a/drivers/irqchip/irq-ftintc010.c b/drivers/irqchip/irq-ftintc010.c index 359efc1d1be7..b91c358ea6db 100644 --- a/drivers/irqchip/irq-ftintc010.c +++ b/drivers/irqchip/irq-ftintc010.c @@ -125,7 +125,7 @@ static struct irq_chip ft010_irq_chip = { /* Local static for the IRQ entry call */ static struct ft010_irq_data firq; -static asmlinkage void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *regs) { struct ft010_irq_data *f = &firq; int irq; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index f3f3978880e9..050bff49731f 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -931,7 +931,7 @@ static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs) __gic_handle_nmi(irqnr, regs); } -static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) { if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs))) __gic_handle_irq_from_irqsoff(regs); diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index ca32ac19d284..58c28895f8c4 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -97,7 +97,7 @@ bool gic_cpuif_has_vsgi(void) fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64PFR0_EL1_GIC_SHIFT); - return fld >= 0x3; + return fld >= ID_AA64PFR0_EL1_GIC_V4P1; } #else bool gic_cpuif_has_vsgi(void) diff --git a/drivers/irqchip/irq-ixp4xx.c b/drivers/irqchip/irq-ixp4xx.c index 5fba907b9052..f23b02f62a5c 100644 --- a/drivers/irqchip/irq-ixp4xx.c +++ b/drivers/irqchip/irq-ixp4xx.c @@ -105,8 +105,7 @@ static void ixp4xx_irq_unmask(struct irq_data *d) } } -static asmlinkage void __exception_irq_entry -ixp4xx_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry ixp4xx_handle_irq(struct pt_regs *regs) { struct ixp4xx_irq *ixi = &ixirq; unsigned long status; diff --git a/drivers/irqchip/irq-loongarch-avec.c b/drivers/irqchip/irq-loongarch-avec.c new file mode 100644 index 000000000000..0f6e465dd309 --- /dev/null +++ b/drivers/irqchip/irq-loongarch-avec.c @@ -0,0 +1,425 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020-2024 Loongson Technologies, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "irq-msi-lib.h" +#include "irq-loongson.h" + +#define VECTORS_PER_REG 64 +#define IRR_VECTOR_MASK 0xffUL +#define IRR_INVALID_MASK 0x80000000UL +#define AVEC_MSG_OFFSET 0x100000 + +#ifdef CONFIG_SMP +struct pending_list { + struct list_head head; +}; + +static struct cpumask intersect_mask; +static DEFINE_PER_CPU(struct pending_list, pending_list); +#endif + +static DEFINE_PER_CPU(struct irq_desc * [NR_VECTORS], irq_map); + +struct avecintc_chip { + raw_spinlock_t lock; + struct fwnode_handle *fwnode; + struct irq_domain *domain; + struct irq_matrix *vector_matrix; + phys_addr_t msi_base_addr; +}; + +static struct avecintc_chip loongarch_avec; + +struct avecintc_data { + struct list_head entry; + unsigned int cpu; + unsigned int vec; + unsigned int prev_cpu; + unsigned int prev_vec; + unsigned int moving; +}; + +static inline void avecintc_ack_irq(struct irq_data *d) +{ +} + +static inline void avecintc_mask_irq(struct irq_data *d) +{ +} + +static inline void avecintc_unmask_irq(struct irq_data *d) +{ +} + +#ifdef CONFIG_SMP +static inline void pending_list_init(int cpu) +{ + struct pending_list *plist = per_cpu_ptr(&pending_list, cpu); + + INIT_LIST_HEAD(&plist->head); +} + +static void avecintc_sync(struct avecintc_data *adata) +{ + struct pending_list *plist; + + if (cpu_online(adata->prev_cpu)) { + plist = per_cpu_ptr(&pending_list, adata->prev_cpu); + list_add_tail(&adata->entry, &plist->head); + adata->moving = 1; + mp_ops.send_ipi_single(adata->prev_cpu, ACTION_CLEAR_VECTOR); + } +} + +static int avecintc_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force) +{ + int cpu, ret, vector; + struct avecintc_data *adata; + + scoped_guard(raw_spinlock, &loongarch_avec.lock) { + adata = irq_data_get_irq_chip_data(data); + + if (adata->moving) + return -EBUSY; + + if (cpu_online(adata->cpu) && cpumask_test_cpu(adata->cpu, dest)) + return 0; + + cpumask_and(&intersect_mask, dest, cpu_online_mask); + + ret = irq_matrix_alloc(loongarch_avec.vector_matrix, &intersect_mask, false, &cpu); + if (ret < 0) + return ret; + + vector = ret; + adata->cpu = cpu; + adata->vec = vector; + per_cpu_ptr(irq_map, adata->cpu)[adata->vec] = irq_data_to_desc(data); + avecintc_sync(adata); + } + + irq_data_update_effective_affinity(data, cpumask_of(cpu)); + + return IRQ_SET_MASK_OK; +} + +static int avecintc_cpu_online(unsigned int cpu) +{ + if (!loongarch_avec.vector_matrix) + return 0; + + guard(raw_spinlock)(&loongarch_avec.lock); + + irq_matrix_online(loongarch_avec.vector_matrix); + + pending_list_init(cpu); + + return 0; +} + +static int avecintc_cpu_offline(unsigned int cpu) +{ + struct pending_list *plist = per_cpu_ptr(&pending_list, cpu); + + if (!loongarch_avec.vector_matrix) + return 0; + + guard(raw_spinlock)(&loongarch_avec.lock); + + if (!list_empty(&plist->head)) + pr_warn("CPU#%d vector is busy\n", cpu); + + irq_matrix_offline(loongarch_avec.vector_matrix); + + return 0; +} + +void complete_irq_moving(void) +{ + struct pending_list *plist = this_cpu_ptr(&pending_list); + struct avecintc_data *adata, *tdata; + int cpu, vector, bias; + uint64_t isr; + + guard(raw_spinlock)(&loongarch_avec.lock); + + list_for_each_entry_safe(adata, tdata, &plist->head, entry) { + cpu = adata->prev_cpu; + vector = adata->prev_vec; + bias = vector / VECTORS_PER_REG; + switch (bias) { + case 0: + isr = csr_read64(LOONGARCH_CSR_ISR0); + break; + case 1: + isr = csr_read64(LOONGARCH_CSR_ISR1); + break; + case 2: + isr = csr_read64(LOONGARCH_CSR_ISR2); + break; + case 3: + isr = csr_read64(LOONGARCH_CSR_ISR3); + break; + } + + if (isr & (1UL << (vector % VECTORS_PER_REG))) { + mp_ops.send_ipi_single(cpu, ACTION_CLEAR_VECTOR); + continue; + } + list_del(&adata->entry); + irq_matrix_free(loongarch_avec.vector_matrix, cpu, vector, false); + this_cpu_write(irq_map[vector], NULL); + adata->moving = 0; + adata->prev_cpu = adata->cpu; + adata->prev_vec = adata->vec; + } +} +#endif + +static void avecintc_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) +{ + struct avecintc_data *adata = irq_data_get_irq_chip_data(d); + + msg->address_hi = 0x0; + msg->address_lo = (loongarch_avec.msi_base_addr | (adata->vec & 0xff) << 4) + | ((cpu_logical_map(adata->cpu & 0xffff)) << 12); + msg->data = 0x0; +} + +static struct irq_chip avec_irq_controller = { + .name = "AVECINTC", + .irq_ack = avecintc_ack_irq, + .irq_mask = avecintc_mask_irq, + .irq_unmask = avecintc_unmask_irq, +#ifdef CONFIG_SMP + .irq_set_affinity = avecintc_set_affinity, +#endif + .irq_compose_msi_msg = avecintc_compose_msi_msg, +}; + +static void avecintc_irq_dispatch(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct irq_desc *d; + + chained_irq_enter(chip, desc); + + while (true) { + unsigned long vector = csr_read64(LOONGARCH_CSR_IRR); + if (vector & IRR_INVALID_MASK) + break; + + vector &= IRR_VECTOR_MASK; + + d = this_cpu_read(irq_map[vector]); + if (d) { + generic_handle_irq_desc(d); + } else { + spurious_interrupt(); + pr_warn("Unexpected IRQ occurs on CPU#%d [vector %ld]\n", smp_processor_id(), vector); + } + } + + chained_irq_exit(chip, desc); +} + +static int avecintc_alloc_vector(struct irq_data *irqd, struct avecintc_data *adata) +{ + int cpu, ret; + + guard(raw_spinlock_irqsave)(&loongarch_avec.lock); + + ret = irq_matrix_alloc(loongarch_avec.vector_matrix, cpu_online_mask, false, &cpu); + if (ret < 0) + return ret; + + adata->prev_cpu = adata->cpu = cpu; + adata->prev_vec = adata->vec = ret; + per_cpu_ptr(irq_map, adata->cpu)[adata->vec] = irq_data_to_desc(irqd); + + return 0; +} + +static int avecintc_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + for (unsigned int i = 0; i < nr_irqs; i++) { + struct irq_data *irqd = irq_domain_get_irq_data(domain, virq + i); + struct avecintc_data *adata = kzalloc(sizeof(*adata), GFP_KERNEL); + int ret; + + if (!adata) + return -ENOMEM; + + ret = avecintc_alloc_vector(irqd, adata); + if (ret < 0) { + kfree(adata); + return ret; + } + + irq_domain_set_info(domain, virq + i, virq + i, &avec_irq_controller, + adata, handle_edge_irq, NULL, NULL); + irqd_set_single_target(irqd); + irqd_set_affinity_on_activate(irqd); + } + + return 0; +} + +static void avecintc_free_vector(struct irq_data *irqd, struct avecintc_data *adata) +{ + guard(raw_spinlock_irqsave)(&loongarch_avec.lock); + + per_cpu(irq_map, adata->cpu)[adata->vec] = NULL; + irq_matrix_free(loongarch_avec.vector_matrix, adata->cpu, adata->vec, false); + +#ifdef CONFIG_SMP + if (!adata->moving) + return; + + per_cpu(irq_map, adata->prev_cpu)[adata->prev_vec] = NULL; + irq_matrix_free(loongarch_avec.vector_matrix, adata->prev_cpu, adata->prev_vec, false); + list_del_init(&adata->entry); +#endif +} + +static void avecintc_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + for (unsigned int i = 0; i < nr_irqs; i++) { + struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); + + if (d) { + struct avecintc_data *adata = irq_data_get_irq_chip_data(d); + + avecintc_free_vector(d, adata); + irq_domain_reset_irq_data(d); + kfree(adata); + } + } +} + +static const struct irq_domain_ops avecintc_domain_ops = { + .alloc = avecintc_domain_alloc, + .free = avecintc_domain_free, + .select = msi_lib_irq_domain_select, +}; + +static int __init irq_matrix_init(void) +{ + loongarch_avec.vector_matrix = irq_alloc_matrix(NR_VECTORS, 0, NR_VECTORS); + if (!loongarch_avec.vector_matrix) + return -ENOMEM; + + for (int i = 0; i < NR_LEGACY_VECTORS; i++) + irq_matrix_assign_system(loongarch_avec.vector_matrix, i, false); + + irq_matrix_online(loongarch_avec.vector_matrix); + + return 0; +} + +static int __init avecintc_init(struct irq_domain *parent) +{ + int ret, parent_irq; + unsigned long value; + + raw_spin_lock_init(&loongarch_avec.lock); + + loongarch_avec.fwnode = irq_domain_alloc_named_fwnode("AVECINTC"); + if (!loongarch_avec.fwnode) { + pr_err("Unable to allocate domain handle\n"); + ret = -ENOMEM; + goto out; + } + + loongarch_avec.domain = irq_domain_create_tree(loongarch_avec.fwnode, + &avecintc_domain_ops, NULL); + if (!loongarch_avec.domain) { + pr_err("Unable to create IRQ domain\n"); + ret = -ENOMEM; + goto out_free_handle; + } + + parent_irq = irq_create_mapping(parent, INT_AVEC); + if (!parent_irq) { + pr_err("Failed to mapping hwirq\n"); + ret = -EINVAL; + goto out_remove_domain; + } + + ret = irq_matrix_init(); + if (ret < 0) { + pr_err("Failed to init irq matrix\n"); + goto out_remove_domain; + } + irq_set_chained_handler_and_data(parent_irq, avecintc_irq_dispatch, NULL); + +#ifdef CONFIG_SMP + pending_list_init(0); + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_AVECINTC_STARTING, + "irqchip/loongarch/avecintc:starting", + avecintc_cpu_online, avecintc_cpu_offline); +#endif + value = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); + value |= IOCSR_MISC_FUNC_AVEC_EN; + iocsr_write64(value, LOONGARCH_IOCSR_MISC_FUNC); + + return ret; + +out_remove_domain: + irq_domain_remove(loongarch_avec.domain); +out_free_handle: + irq_domain_free_fwnode(loongarch_avec.fwnode); +out: + return ret; +} + +static int __init pch_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_msi_pic *pchmsi_entry = (struct acpi_madt_msi_pic *)header; + + loongarch_avec.msi_base_addr = pchmsi_entry->msg_address - AVEC_MSG_OFFSET; + + return pch_msi_acpi_init_avec(loongarch_avec.domain); +} + +static inline int __init acpi_cascade_irqdomain_init(void) +{ + return acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1); +} + +int __init avecintc_acpi_init(struct irq_domain *parent) +{ + int ret = avecintc_init(parent); + if (ret < 0) { + pr_err("Failed to init IRQ domain\n"); + return ret; + } + + ret = acpi_cascade_irqdomain_init(); + if (ret < 0) { + pr_err("Failed to init cascade IRQ domain\n"); + return ret; + } + + return ret; +} diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c index b35903a06902..e62dab4c97fc 100644 --- a/drivers/irqchip/irq-loongarch-cpu.c +++ b/drivers/irqchip/irq-loongarch-cpu.c @@ -13,6 +13,8 @@ #include #include +#include "irq-loongson.h" + static struct irq_domain *irq_domain; struct fwnode_handle *cpuintc_handle; @@ -140,7 +142,10 @@ static int __init acpi_cascade_irqdomain_init(void) if (r < 0) return r; - return 0; + if (cpu_has_avecint) + r = avecintc_acpi_init(irq_domain); + + return r; } static int __init cpuintc_acpi_init(union acpi_subtable_headers *header, diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index b1f2080be2be..e24db71a8783 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -17,6 +17,8 @@ #include #include +#include "irq-loongson.h" + #define EIOINTC_REG_NODEMAP 0x14a0 #define EIOINTC_REG_IPMAP 0x14c0 #define EIOINTC_REG_ENABLE 0x1600 @@ -360,6 +362,9 @@ static int __init acpi_cascade_irqdomain_init(void) if (r < 0) return r; + if (cpu_has_avecint) + return 0; + r = acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1); if (r < 0) return r; @@ -396,8 +401,8 @@ static int __init eiointc_init(struct eiointc_priv *priv, int parent_irq, if (nr_pics == 1) { register_syscore_ops(&eiointc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, - "irqchip/loongarch/intc:starting", + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_EIOINTC_STARTING, + "irqchip/loongarch/eiointc:starting", eiointc_router_init, NULL); } diff --git a/drivers/irqchip/irq-loongson-htvec.c b/drivers/irqchip/irq-loongson-htvec.c index 0bff728b25e3..5da02c7ad0b3 100644 --- a/drivers/irqchip/irq-loongson-htvec.c +++ b/drivers/irqchip/irq-loongson-htvec.c @@ -17,6 +17,8 @@ #include #include +#include "irq-loongson.h" + /* Registers */ #define HTVEC_EN_OFF 0x20 #define HTVEC_MAX_PARENT_IRQ 8 diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 7c4fe7ab4b83..2b1bd4a96665 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -22,6 +22,8 @@ #include #endif +#include "irq-loongson.h" + #define LIOINTC_CHIP_IRQ 32 #define LIOINTC_NUM_PARENT 4 #define LIOINTC_NUM_CORES 4 diff --git a/drivers/irqchip/irq-loongson-pch-lpc.c b/drivers/irqchip/irq-loongson-pch-lpc.c index 9b35492fb6be..2d4c3ec128b8 100644 --- a/drivers/irqchip/irq-loongson-pch-lpc.c +++ b/drivers/irqchip/irq-loongson-pch-lpc.c @@ -15,6 +15,8 @@ #include #include +#include "irq-loongson.h" + /* Registers */ #define LPC_INT_CTL 0x00 #define LPC_INT_ENA 0x04 diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c index dd4d699170f4..bd337ecddb40 100644 --- a/drivers/irqchip/irq-loongson-pch-msi.c +++ b/drivers/irqchip/irq-loongson-pch-msi.c @@ -15,6 +15,9 @@ #include #include +#include "irq-msi-lib.h" +#include "irq-loongson.h" + static int nr_pics; struct pch_msi_data { @@ -27,26 +30,6 @@ struct pch_msi_data { static struct fwnode_handle *pch_msi_handle[MAX_IO_PICS]; -static void pch_msi_mask_msi_irq(struct irq_data *d) -{ - pci_msi_mask_irq(d); - irq_chip_mask_parent(d); -} - -static void pch_msi_unmask_msi_irq(struct irq_data *d) -{ - irq_chip_unmask_parent(d); - pci_msi_unmask_irq(d); -} - -static struct irq_chip pch_msi_irq_chip = { - .name = "PCH PCI MSI", - .irq_mask = pch_msi_mask_msi_irq, - .irq_unmask = pch_msi_unmask_msi_irq, - .irq_ack = irq_chip_ack_parent, - .irq_set_affinity = irq_chip_set_affinity_parent, -}; - static int pch_msi_allocate_hwirq(struct pch_msi_data *priv, int num_req) { int first; @@ -85,12 +68,6 @@ static void pch_msi_compose_msi_msg(struct irq_data *data, msg->data = data->hwirq; } -static struct msi_domain_info pch_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, - .chip = &pch_msi_irq_chip, -}; - static struct irq_chip middle_irq_chip = { .name = "PCH MSI", .irq_mask = irq_chip_mask_parent, @@ -155,13 +132,31 @@ static void pch_msi_middle_domain_free(struct irq_domain *domain, static const struct irq_domain_ops pch_msi_middle_domain_ops = { .alloc = pch_msi_middle_domain_alloc, .free = pch_msi_middle_domain_free, + .select = msi_lib_irq_domain_select, +}; + +#define PCH_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) + +#define PCH_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX | \ + MSI_FLAG_MULTI_PCI_MSI) + +static struct msi_parent_ops pch_msi_parent_ops = { + .required_flags = PCH_MSI_FLAGS_REQUIRED, + .supported_flags = PCH_MSI_FLAGS_SUPPORTED, + .bus_select_mask = MATCH_PCI_MSI, + .bus_select_token = DOMAIN_BUS_NEXUS, + .prefix = "PCH-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; static int pch_msi_init_domains(struct pch_msi_data *priv, struct irq_domain *parent, struct fwnode_handle *domain_handle) { - struct irq_domain *middle_domain, *msi_domain; + struct irq_domain *middle_domain; middle_domain = irq_domain_create_hierarchy(parent, 0, priv->num_irqs, domain_handle, @@ -174,14 +169,8 @@ static int pch_msi_init_domains(struct pch_msi_data *priv, irq_domain_update_bus_token(middle_domain, DOMAIN_BUS_NEXUS); - msi_domain = pci_msi_create_irq_domain(domain_handle, - &pch_msi_domain_info, - middle_domain); - if (!msi_domain) { - pr_err("Failed to create PCI MSI domain\n"); - irq_domain_remove(middle_domain); - return -ENOMEM; - } + middle_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + middle_domain->msi_parent_ops = &pch_msi_parent_ops; return 0; } @@ -266,17 +255,17 @@ IRQCHIP_DECLARE(pch_msi, "loongson,pch-msi-1.0", pch_msi_of_init); #ifdef CONFIG_ACPI struct fwnode_handle *get_pch_msi_handle(int pci_segment) { - int i; + if (cpu_has_avecint) + return pch_msi_handle[0]; - for (i = 0; i < MAX_IO_PICS; i++) { + for (int i = 0; i < MAX_IO_PICS; i++) { if (msi_group[i].pci_segment == pci_segment) return pch_msi_handle[i]; } - return NULL; + return pch_msi_handle[0]; } -int __init pch_msi_acpi_init(struct irq_domain *parent, - struct acpi_madt_msi_pic *acpi_pchmsi) +int __init pch_msi_acpi_init(struct irq_domain *parent, struct acpi_madt_msi_pic *acpi_pchmsi) { int ret; struct fwnode_handle *domain_handle; @@ -289,4 +278,18 @@ int __init pch_msi_acpi_init(struct irq_domain *parent, return ret; } + +int __init pch_msi_acpi_init_avec(struct irq_domain *parent) +{ + if (pch_msi_handle[0]) + return 0; + + pch_msi_handle[0] = parent->fwnode; + irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS); + + parent->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + parent->msi_parent_ops = &pch_msi_parent_ops; + + return 0; +} #endif diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c index cbaef65e804c..69efda35a8e7 100644 --- a/drivers/irqchip/irq-loongson-pch-pic.c +++ b/drivers/irqchip/irq-loongson-pch-pic.c @@ -17,6 +17,8 @@ #include #include +#include "irq-loongson.h" + /* Registers */ #define PCH_PIC_MASK 0x20 #define PCH_PIC_HTMSI_EN 0x40 diff --git a/drivers/irqchip/irq-loongson.h b/drivers/irqchip/irq-loongson.h new file mode 100644 index 000000000000..11fa138d1f44 --- /dev/null +++ b/drivers/irqchip/irq-loongson.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#ifndef _DRIVERS_IRQCHIP_IRQ_LOONGSON_H +#define _DRIVERS_IRQCHIP_IRQ_LOONGSON_H + +int find_pch_pic(u32 gsi); + +int liointc_acpi_init(struct irq_domain *parent, + struct acpi_madt_lio_pic *acpi_liointc); +int eiointc_acpi_init(struct irq_domain *parent, + struct acpi_madt_eio_pic *acpi_eiointc); +int avecintc_acpi_init(struct irq_domain *parent); + +int htvec_acpi_init(struct irq_domain *parent, + struct acpi_madt_ht_pic *acpi_htvec); +int pch_lpc_acpi_init(struct irq_domain *parent, + struct acpi_madt_lpc_pic *acpi_pchlpc); +int pch_pic_acpi_init(struct irq_domain *parent, + struct acpi_madt_bio_pic *acpi_pchpic); +int pch_msi_acpi_init(struct irq_domain *parent, + struct acpi_madt_msi_pic *acpi_pchmsi); +int pch_msi_acpi_init_avec(struct irq_domain *parent); + +#endif /* _DRIVERS_IRQCHIP_IRQ_LOONGSON_H */ diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index 53cc08387588..6f69f4e5dbac 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -234,37 +234,27 @@ static int mbigen_of_create_domain(struct platform_device *pdev, struct mbigen_device *mgn_chip) { struct platform_device *child; - struct device_node *np; u32 num_pins; - int ret = 0; - for_each_child_of_node(pdev->dev.of_node, np) { + for_each_child_of_node_scoped(pdev->dev.of_node, np) { if (!of_property_read_bool(np, "interrupt-controller")) continue; child = of_platform_device_create(np, NULL, NULL); - if (!child) { - ret = -ENOMEM; - break; - } + if (!child) + return -ENOMEM; if (of_property_read_u32(child->dev.of_node, "num-pins", &num_pins) < 0) { dev_err(&pdev->dev, "No num-pins property\n"); - ret = -EINVAL; - break; + return -EINVAL; } - if (!mbigen_create_device_domain(&child->dev, num_pins, mgn_chip)) { - ret = -ENOMEM; - break; - } + if (!mbigen_create_device_domain(&child->dev, num_pins, mgn_chip)) + return -ENOMEM; } - if (ret) - of_node_put(np); - - return ret; + return 0; } #ifdef CONFIG_ACPI diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c index dc82162ba763..ad84a2f03368 100644 --- a/drivers/irqchip/irq-omap-intc.c +++ b/drivers/irqchip/irq-omap-intc.c @@ -325,8 +325,7 @@ static int __init omap_init_irq(u32 base, struct device_node *node) return ret; } -static asmlinkage void __exception_irq_entry -omap_intc_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry omap_intc_handle_irq(struct pt_regs *regs) { extern unsigned long irq_err_count; u32 irqnr; diff --git a/drivers/irqchip/irq-sa11x0.c b/drivers/irqchip/irq-sa11x0.c index 31c202a1ae62..9d0b80271949 100644 --- a/drivers/irqchip/irq-sa11x0.c +++ b/drivers/irqchip/irq-sa11x0.c @@ -127,8 +127,7 @@ static int __init sa1100irq_init_devicefs(void) device_initcall(sa1100irq_init_devicefs); -static asmlinkage void __exception_irq_entry -sa1100_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry sa1100_handle_irq(struct pt_regs *regs) { uint32_t icip, icmr, mask; diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c index 5018a06060e6..ca471c6fee99 100644 --- a/drivers/irqchip/irq-versatile-fpga.c +++ b/drivers/irqchip/irq-versatile-fpga.c @@ -128,7 +128,7 @@ static int handle_one_fpga(struct fpga_irq_data *f, struct pt_regs *regs) * Keep iterating over all registered FPGA IRQ controllers until there are * no pending interrupts. */ -static asmlinkage void __exception_irq_entry fpga_handle_irq(struct pt_regs *regs) +static void __exception_irq_entry fpga_handle_irq(struct pt_regs *regs) { int i, handled; diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 61cb45c5d0d8..53fad9487574 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -82,7 +82,7 @@ * - has multiple clocks. * - has no usable clock due to jitter or packet loss (VoIP). * In this case the system's clock is used. The clock resolution depends on - * the jiffie resolution. + * the jiffy resolution. * * If a member joins a conference: * diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 9190eff6c0bb..e1d003fdbc2e 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -104,7 +104,7 @@ static int orion_mdio_wait_ready(const struct orion_mdio_ops *ops, return 0; } else { /* wait_event_timeout does not guarantee a delay of at - * least one whole jiffie, so timeout must be no less + * least one whole jiffy, so timeout must be no less * than two. */ timeout = max(usecs_to_jiffies(MVMDIO_SMI_TIMEOUT), 2); diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c index e7878558fd90..9d9c07f44ff6 100644 --- a/drivers/platform/x86/intel/pmc/adl.c +++ b/drivers/platform/x86/intel/pmc/adl.c @@ -295,6 +295,8 @@ const struct pmc_reg_map adl_reg_map = { .ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, + .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, + .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED, .lpm_num_modes = ADL_LPM_NUM_MODES, .lpm_num_maps = ADL_LPM_NUM_MAPS, diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c index dd72974bf71e..513c02670c5a 100644 --- a/drivers/platform/x86/intel/pmc/cnp.c +++ b/drivers/platform/x86/intel/pmc/cnp.c @@ -200,6 +200,8 @@ const struct pmc_reg_map cnp_reg_map = { .ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, + .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, + .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = CNP_NUM_IP_IGN_ALLOWED, .etr3_offset = ETR3_OFFSET, }; diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 01ae71c6df59..e2b4c74ce7f6 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -1208,6 +1209,38 @@ static bool pmc_core_is_pson_residency_enabled(struct pmc_dev *pmcdev) return val == 1; } +/* + * Enable or disable ACPI PM Timer + * + * This function is intended to be a callback for ACPI PM suspend/resume event. + * The ACPI PM Timer is enabled on resume only if it was enabled during suspend. + */ +static void pmc_core_acpi_pm_timer_suspend_resume(void *data, bool suspend) +{ + struct pmc_dev *pmcdev = data; + struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; + const struct pmc_reg_map *map = pmc->map; + bool enabled; + u32 reg; + + if (!map->acpi_pm_tmr_ctl_offset) + return; + + guard(mutex)(&pmcdev->lock); + + if (!suspend && !pmcdev->enable_acpi_pm_timer_on_resume) + return; + + reg = pmc_core_reg_read(pmc, map->acpi_pm_tmr_ctl_offset); + enabled = !(reg & map->acpi_pm_tmr_disable_bit); + if (suspend) + reg |= map->acpi_pm_tmr_disable_bit; + else + reg &= ~map->acpi_pm_tmr_disable_bit; + pmc_core_reg_write(pmc, map->acpi_pm_tmr_ctl_offset, reg); + + pmcdev->enable_acpi_pm_timer_on_resume = suspend && enabled; +} static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) { @@ -1404,6 +1437,7 @@ static int pmc_core_probe(struct platform_device *pdev) struct pmc_dev *pmcdev; const struct x86_cpu_id *cpu_id; int (*core_init)(struct pmc_dev *pmcdev); + const struct pmc_reg_map *map; struct pmc *primary_pmc; int ret; @@ -1462,6 +1496,11 @@ static int pmc_core_probe(struct platform_device *pdev) pm_report_max_hw_sleep(FIELD_MAX(SLP_S0_RES_COUNTER_MASK) * pmc_core_adjust_slp_s0_step(primary_pmc, 1)); + map = primary_pmc->map; + if (map->acpi_pm_tmr_ctl_offset) + acpi_pmtmr_register_suspend_resume_callback(pmc_core_acpi_pm_timer_suspend_resume, + pmcdev); + device_initialized = true; dev_info(&pdev->dev, " initialized\n"); @@ -1471,6 +1510,12 @@ static int pmc_core_probe(struct platform_device *pdev) static void pmc_core_remove(struct platform_device *pdev) { struct pmc_dev *pmcdev = platform_get_drvdata(pdev); + const struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; + const struct pmc_reg_map *map = pmc->map; + + if (map->acpi_pm_tmr_ctl_offset) + acpi_pmtmr_unregister_suspend_resume_callback(); + pmc_core_dbgfs_unregister(pmcdev); pmc_core_clean_structure(pdev); } diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index ea04de7eb9e8..4d37ef7113d7 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -68,6 +68,8 @@ struct telem_endpoint; #define SPT_PMC_LTR_SCC 0x3A0 #define SPT_PMC_LTR_ISH 0x3A4 +#define SPT_PMC_ACPI_PM_TMR_CTL_OFFSET 0x18FC + /* Sunrise Point: PGD PFET Enable Ack Status Registers */ enum ppfear_regs { SPT_PMC_XRAM_PPFEAR0A = 0x590, @@ -148,6 +150,8 @@ enum ppfear_regs { #define SPT_PMC_VRIC1_SLPS0LVEN BIT(13) #define SPT_PMC_VRIC1_XTALSDQDIS BIT(22) +#define SPT_PMC_BIT_ACPI_PM_TMR_DISABLE BIT(1) + /* Cannonlake Power Management Controller register offsets */ #define CNP_PMC_SLPS0_DBG_OFFSET 0x10B4 #define CNP_PMC_PM_CFG_OFFSET 0x1818 @@ -351,6 +355,8 @@ struct pmc_reg_map { const u8 *lpm_reg_index; const u32 pson_residency_offset; const u32 pson_residency_counter_step; + const u32 acpi_pm_tmr_ctl_offset; + const u32 acpi_pm_tmr_disable_bit; }; /** @@ -424,6 +430,8 @@ struct pmc_dev { u32 die_c6_offset; struct telem_endpoint *punit_ep; struct pmc_info *regmap_list; + + bool enable_acpi_pm_timer_on_resume; }; enum pmc_index { diff --git a/drivers/platform/x86/intel/pmc/icl.c b/drivers/platform/x86/intel/pmc/icl.c index 71b0fd6cb7d8..cbbd44054468 100644 --- a/drivers/platform/x86/intel/pmc/icl.c +++ b/drivers/platform/x86/intel/pmc/icl.c @@ -46,6 +46,8 @@ const struct pmc_reg_map icl_reg_map = { .ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, + .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, + .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = ICL_NUM_IP_IGN_ALLOWED, .etr3_offset = ETR3_OFFSET, }; diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c index c7d15d864039..91f2fa728f5c 100644 --- a/drivers/platform/x86/intel/pmc/mtl.c +++ b/drivers/platform/x86/intel/pmc/mtl.c @@ -462,6 +462,8 @@ const struct pmc_reg_map mtl_socm_reg_map = { .ppfear_buckets = MTL_SOCM_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, + .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, + .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .lpm_num_maps = ADL_LPM_NUM_MAPS, .ltr_ignore_max = MTL_SOCM_NUM_IP_IGN_ALLOWED, .lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2, diff --git a/drivers/platform/x86/intel/pmc/spt.c b/drivers/platform/x86/intel/pmc/spt.c index ab993a69e33e..2cd2b3c68e46 100644 --- a/drivers/platform/x86/intel/pmc/spt.c +++ b/drivers/platform/x86/intel/pmc/spt.c @@ -130,6 +130,8 @@ const struct pmc_reg_map spt_reg_map = { .ppfear_buckets = SPT_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = SPT_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = SPT_PMC_READ_DISABLE_BIT, + .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, + .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = SPT_NUM_IP_IGN_ALLOWED, .pm_vric1_offset = SPT_PMC_VRIC1_OFFSET, }; diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c index e0580de18077..371b4e30f142 100644 --- a/drivers/platform/x86/intel/pmc/tgl.c +++ b/drivers/platform/x86/intel/pmc/tgl.c @@ -197,6 +197,8 @@ const struct pmc_reg_map tgl_reg_map = { .ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, + .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, + .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = TGL_NUM_IP_IGN_ALLOWED, .lpm_num_maps = TGL_LPM_NUM_MAPS, .lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2, diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 29e4b83e0376..5f9f06911795 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -423,11 +423,11 @@ static int univ8250_console_setup(struct console *co, char *options) port = &serial8250_ports[co->index].port; /* link port to console */ - port->cons = co; + uart_port_set_cons(port, co); retval = serial8250_console_setup(port, options, false); if (retval != 0) - port->cons = NULL; + uart_port_set_cons(port, NULL); return retval; } @@ -485,7 +485,7 @@ static int univ8250_console_match(struct console *co, char *name, int idx, continue; co->index = i; - port->cons = co; + uart_port_set_cons(port, co); return serial8250_console_setup(port, options, true); } diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 8b1644f5411e..7d0134ecd82f 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2480,7 +2480,7 @@ static int pl011_console_match(struct console *co, char *name, int idx, continue; co->index = i; - port->cons = co; + uart_port_set_cons(port, co); return pl011_console_setup(co, options); } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 5bea3af46abc..1e3e28e364df 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3176,8 +3176,15 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u state->uart_port = uport; uport->state = state; + /* + * If this port is in use as a console then the spinlock is already + * initialised. + */ + if (!uart_console_registered(uport)) + uart_port_spin_lock_init(uport); + state->pm_state = UART_PM_STATE_UNDEFINED; - uport->cons = drv->cons; + uart_port_set_cons(uport, drv->cons); uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name, drv->tty_driver->name_base + uport->line); @@ -3186,13 +3193,6 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u goto out; } - /* - * If this port is in use as a console then the spinlock is already - * initialised. - */ - if (!uart_console_registered(uport)) - uart_port_spin_lock_init(uport); - if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 7ae0c8934f42..abc2708d4ac5 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3573,7 +3573,7 @@ static ssize_t show_cons_active(struct device *dev, for_each_console(c) { if (!c->device) continue; - if (!c->write) + if (!(c->flags & CON_NBCON) && !c->write) continue; if ((c->flags & CON_ENABLED) == 0) continue; diff --git a/fs/proc/base.c b/fs/proc/base.c index 92f9ead78067..0d737b1ca5cc 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2514,13 +2514,13 @@ static void *timers_start(struct seq_file *m, loff_t *pos) if (!tp->sighand) return ERR_PTR(-ESRCH); - return seq_list_start(&tp->task->signal->posix_timers, *pos); + return seq_hlist_start(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; - return seq_list_next(v, &tp->task->signal->posix_timers, pos); + return seq_hlist_next(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) @@ -2549,7 +2549,7 @@ static int show_timer(struct seq_file *m, void *v) [SIGEV_THREAD] = "thread", }; - timer = list_entry((struct list_head *)v, struct k_itimer, list); + timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); notify = timer->it_sigev_notify; seq_printf(m, "ID: %d\n", timer->it_id); @@ -2627,10 +2627,11 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, } task_lock(p); - if (slack_ns == 0) - p->timer_slack_ns = p->default_timer_slack_ns; - else - p->timer_slack_ns = slack_ns; + if (task_is_realtime(p)) + slack_ns = 0; + else if (slack_ns == 0) + slack_ns = p->default_timer_slack_ns; + p->timer_slack_ns = slack_ns; task_unlock(p); out: diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c index e0758fe7936d..b7cab1ad990d 100644 --- a/fs/proc/consoles.c +++ b/fs/proc/consoles.c @@ -21,6 +21,7 @@ static int show_console_dev(struct seq_file *m, void *v) { CON_ENABLED, 'E' }, { CON_CONSDEV, 'C' }, { CON_BOOT, 'B' }, + { CON_NBCON, 'N' }, { CON_PRINTBUFFER, 'p' }, { CON_BRL, 'b' }, { CON_ANYTIME, 'a' }, @@ -58,8 +59,8 @@ static int show_console_dev(struct seq_file *m, void *v) seq_printf(m, "%s%d", con->name, con->index); seq_pad(m, ' '); seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-', - con->write ? 'W' : '-', con->unblank ? 'U' : '-', - flags); + ((con->flags & CON_NBCON) || con->write) ? 'W' : '-', + con->unblank ? 'U' : '-', flags); if (dev) seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev)); @@ -68,6 +69,7 @@ static int show_console_dev(struct seq_file *m, void *v) } static void *c_start(struct seq_file *m, loff_t *pos) + __acquires(&console_mutex) { struct console *con; loff_t off = 0; @@ -94,6 +96,7 @@ static void *c_next(struct seq_file *m, void *v, loff_t *pos) } static void c_stop(struct seq_file *m, void *v) + __releases(&console_mutex) { console_list_unlock(); } diff --git a/fs/select.c b/fs/select.c index 3e5173a98fca..8cf7814bfe8f 100644 --- a/fs/select.c +++ b/fs/select.c @@ -77,19 +77,16 @@ u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; + u64 slack = current->timer_slack_ns; - /* - * Realtime tasks get a slack of 0 for obvious reasons. - */ - - if (rt_task(current)) + if (slack == 0) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); - if (ret < current->timer_slack_ns) - return current->timer_slack_ns; + if (ret < slack) + return slack; return ret; } diff --git a/fs/signalfd.c b/fs/signalfd.c index ec7b2da2477a..d0333bce015e 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -159,7 +159,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info DECLARE_WAITQUEUE(wait, current); spin_lock_irq(¤t->sighand->siglock); - ret = dequeue_signal(current, &ctx->sigmask, info, &type); + ret = dequeue_signal(&ctx->sigmask, info, &type); switch (ret) { case 0: if (!nonblock) @@ -174,7 +174,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info add_wait_queue(¤t->sighand->signalfd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); - ret = dequeue_signal(current, &ctx->sigmask, info, &type); + ret = dequeue_signal(&ctx->sigmask, info, &type); if (ret != 0) break; if (signal_pending(current)) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index b1580644501f..209a389f2abc 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -210,7 +210,7 @@ struct xfs_buf { * success the write is considered to be failed permanently and the * iodone handler will take appropriate action. * - * For retry timeouts, we record the jiffie of the first failure. This + * For retry timeouts, we record the jiffy of the first failure. This * means that we can change the retry timeout for buffers already under * I/O and thus avoid getting stuck in a retry loop with a long timeout. * diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h index 50d88bf1498d..0ded9220d379 100644 --- a/include/linux/acpi_pmtmr.h +++ b/include/linux/acpi_pmtmr.h @@ -26,6 +26,19 @@ static inline u32 acpi_pm_read_early(void) return acpi_pm_read_verified() & ACPI_PM_MASK; } +/** + * Register callback for suspend and resume event + * + * @cb Callback triggered on suspend and resume + * @data Data passed with the callback + */ +void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data); + +/** + * Remove registered callback for suspend and resume event + */ +void acpi_pmtmr_unregister_suspend_resume_callback(void); + #else static inline u32 acpi_pm_read_early(void) diff --git a/include/linux/console.h b/include/linux/console.h index 31a8f5b85f5d..eba367bf605d 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,7 +16,9 @@ #include #include +#include #include +#include #include #include @@ -303,7 +305,7 @@ struct nbcon_write_context { /** * struct console - The console descriptor structure * @name: The name of the console driver - * @write: Write callback to output messages (Optional) + * @write: Legacy write callback to output messages (Optional) * @read: Read callback for console input (Optional) * @device: The underlying TTY device driver (Optional) * @unblank: Callback to unblank the console (Optional) @@ -320,10 +322,14 @@ struct nbcon_write_context { * @data: Driver private data * @node: hlist node for the console list * - * @write_atomic: Write callback for atomic context * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print + * @nbcon_device_ctxt: Context available for non-printing operations + * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer + * @kthread: Printer kthread for this console + * @rcuwait: RCU-safe wait object for @kthread waking + * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; @@ -345,11 +351,121 @@ struct console { struct hlist_node node; /* nbcon console specific members */ - bool (*write_atomic)(struct console *con, - struct nbcon_write_context *wctxt); + + /** + * @write_atomic: + * + * NBCON callback to write out text in any context. (Optional) + * + * This callback is called with the console already acquired. However, + * a higher priority context is allowed to take it over by default. + * + * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() + * around any code where the takeover is not safe, for example, when + * manipulating the serial port registers. + * + * nbcon_enter_unsafe() will fail if the context has lost the console + * ownership in the meantime. In this case, the callback is no longer + * allowed to go forward. It must back out immediately and carefully. + * The buffer content is also no longer trusted since it no longer + * belongs to the context. + * + * The callback should allow the takeover whenever it is safe. It + * increases the chance to see messages when the system is in trouble. + * If the driver must reacquire ownership in order to finalize or + * revert hardware changes, nbcon_reacquire_nobuf() can be used. + * However, on reacquire the buffer content is no longer available. A + * reacquire cannot be used to resume printing. + * + * The callback can be called from any context (including NMI). + * Therefore it must avoid usage of any locking and instead rely + * on the console ownership for synchronization. + */ + void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); + + /** + * @write_thread: + * + * NBCON callback to write out text in task context. + * + * This callback must be called only in task context with both + * device_lock() and the nbcon console acquired with + * NBCON_PRIO_NORMAL. + * + * The same rules for console ownership verification and unsafe + * sections handling applies as with write_atomic(). + * + * The console ownership handling is necessary for synchronization + * against write_atomic() which is synchronized only via the context. + * + * The device_lock() provides the primary serialization for operations + * on the device. It might be as relaxed (mutex)[*] or as tight + * (disabled preemption and interrupts) as needed. It allows + * the kthread to operate in the least restrictive mode[**]. + * + * [*] Standalone nbcon_context_try_acquire() is not safe with + * the preemption enabled, see nbcon_owner_matches(). But it + * can be safe when always called in the preemptive context + * under the device_lock(). + * + * [**] The device_lock() makes sure that nbcon_context_try_acquire() + * would never need to spin which is important especially with + * PREEMPT_RT. + */ + void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); + + /** + * @device_lock: + * + * NBCON callback to begin synchronization with driver code. + * + * Console drivers typically must deal with access to the hardware + * via user input/output (such as an interactive login shell) and + * output of kernel messages via printk() calls. This callback is + * called by the printk-subsystem whenever it needs to synchronize + * with hardware access by the driver. It should be implemented to + * use whatever synchronization mechanism the driver is using for + * itself (for example, the port lock for uart serial consoles). + * + * The callback is always called from task context. It may use any + * synchronization method required by the driver. + * + * IMPORTANT: The callback MUST disable migration. The console driver + * may be using a synchronization mechanism that already takes + * care of this (such as spinlocks). Otherwise this function must + * explicitly call migrate_disable(). + * + * The flags argument is provided as a convenience to the driver. It + * will be passed again to device_unlock(). It can be ignored if the + * driver does not need it. + */ + void (*device_lock)(struct console *con, unsigned long *flags); + + /** + * @device_unlock: + * + * NBCON callback to finish synchronization with driver code. + * + * It is the counterpart to device_lock(). + * + * This callback is always called from task context. It must + * appropriately re-enable migration (depending on how device_lock() + * disabled migration). + * + * The flags argument is the value of the same variable that was + * passed to device_lock(). + */ + void (*device_unlock)(struct console *con, unsigned long flags); + atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; + struct nbcon_context __private nbcon_device_ctxt; + atomic_long_t __private nbcon_prev_seq; + struct printk_buffers *pbufs; + struct task_struct *kthread; + struct rcuwait rcuwait; + struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP @@ -378,28 +494,34 @@ extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; /** - * console_srcu_read_flags - Locklessly read the console flags + * console_srcu_read_flags - Locklessly read flags of a possibly registered + * console * @con: struct console pointer of console to read flags from * - * This function provides the necessary READ_ONCE() and data_race() - * notation for locklessly reading the console flags. The READ_ONCE() - * in this function matches the WRITE_ONCE() when @flags are modified - * for registered consoles with console_srcu_write_flags(). + * Locklessly reading @con->flags provides a consistent read value because + * there is at most one CPU modifying @con->flags and that CPU is using only + * read-modify-write operations to do so. * - * Only use this function to read console flags when locklessly - * iterating the console list via srcu. + * Requires console_srcu_read_lock to be held, which implies that @con might + * be a registered console. The purpose of holding console_srcu_read_lock is + * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) + * and that no exit/cleanup routines will run if the console is currently + * undergoing unregistration. + * + * If the caller is holding the console_list_lock or it is _certain_ that + * @con is not and will not become registered, the caller may read + * @con->flags directly instead. * * Context: Any context. + * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* - * Locklessly reading console->flags provides a consistent - * read value because there is at most one CPU modifying - * console->flags and that CPU is using only read-modify-write - * operations to do so. + * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified + * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } @@ -477,13 +599,19 @@ static inline bool console_is_registered(const struct console *con) hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK +extern void nbcon_cpu_emergency_enter(void); +extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); +extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); #else +static inline void nbcon_cpu_emergency_enter(void) { } +static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } +static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } #endif extern int console_set_on_cmdline; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 9316c39260e0..f39186738d81 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -144,7 +144,8 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, - CPUHP_AP_IRQ_LOONGARCH_STARTING, + CPUHP_AP_IRQ_EIOINTC_STARTING, + CPUHP_AP_IRQ_AVECINTC_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 3f30c88e0b4c..457151f9f263 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -276,7 +276,7 @@ struct irq_affinity_notify { #define IRQ_AFFINITY_MAX_SETS 4 /** - * struct irq_affinity - Description for automatic irq affinity assignements + * struct irq_affinity - Description for automatic irq affinity assignments * @pre_vectors: Don't apply affinity to @pre_vectors at beginning of * the MSI(-X) vector space * @post_vectors: Don't apply affinity to @post_vectors at end of @@ -594,7 +594,7 @@ extern const char * const softirq_to_name[NR_SOFTIRQS]; struct softirq_action { - void (*action)(struct softirq_action *); + void (*action)(void); }; asmlinkage void do_softirq(void); @@ -609,7 +609,7 @@ static inline void do_softirq_post_smp_call_flush(unsigned int unused) } #endif -extern void open_softirq(int nr, void (*action)(struct softirq_action *)); +extern void open_softirq(int nr, void (*action)(void)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); diff --git a/include/linux/irq.h b/include/linux/irq.h index 1f5dbf1f92c9..fa711f80957b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -991,7 +991,6 @@ void irq_init_desc(unsigned int irq); * @ack: Ack register offset to reg_base * @eoi: Eoi register offset to reg_base * @type: Type configuration register offset to reg_base - * @polarity: Polarity configuration register offset to reg_base */ struct irq_chip_regs { unsigned long enable; @@ -1000,7 +999,6 @@ struct irq_chip_regs { unsigned long ack; unsigned long eoi; unsigned long type; - unsigned long polarity; }; /** @@ -1040,8 +1038,6 @@ struct irq_chip_type { * @irq_base: Interrupt base nr for this chip * @irq_cnt: Number of interrupts handled by this chip * @mask_cache: Cached mask register shared between all chip types - * @type_cache: Cached type register - * @polarity_cache: Cached polarity register * @wake_enabled: Interrupt can wakeup from suspend * @wake_active: Interrupt is marked as an wakeup from suspend source * @num_ct: Number of available irq_chip_type instances (usually 1) @@ -1068,8 +1064,6 @@ struct irq_chip_generic { unsigned int irq_base; unsigned int irq_cnt; u32 mask_cache; - u32 type_cache; - u32 polarity_cache; u32 wake_enabled; u32 wake_active; unsigned int num_ct; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index de6105f68fec..e432b6a12a32 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -291,7 +291,12 @@ struct irq_domain_chip_generic_info; * @hwirq_max: Maximum number of interrupts supported by controller * @direct_max: Maximum value of direct maps; * Use ~0 for no limit; 0 for no direct mapping + * @hwirq_base: The first hardware interrupt number (legacy domains only) + * @virq_base: The first Linux interrupt number for legacy domains to + * immediately associate the interrupts after domain creation * @bus_token: Domain bus token + * @name_suffix: Optional name suffix to avoid collisions when multiple + * domains are added using same fwnode * @ops: Domain operation callbacks * @host_data: Controller private data pointer * @dgc_info: Geneneric chip information structure pointer used to @@ -307,7 +312,10 @@ struct irq_domain_info { unsigned int size; irq_hw_number_t hwirq_max; int direct_max; + unsigned int hwirq_base; + unsigned int virq_base; enum irq_domain_bus_token bus_token; + const char *name_suffix; const struct irq_domain_ops *ops; void *host_data; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d9f1435a5a13..1220f0fbe5bf 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -418,7 +418,7 @@ extern unsigned long preset_lpj; #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) /* - * The maximum jiffie value is (MAX_INT >> 1). Here we translate that + * The maximum jiffy value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, * so use the messy SH_DIV macro to do it. Still all constants. */ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index dc7b738de299..453691710839 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -158,7 +158,7 @@ static inline void posix_cputimers_init_work(void) { } * @rcu: RCU head for freeing the timer. */ struct k_itimer { - struct list_head list; + struct hlist_node list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; diff --git a/include/linux/printk.h b/include/linux/printk.h index b937cefcb31c..eca9bb2ee637 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -9,6 +9,8 @@ #include #include +struct console; + extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -161,15 +163,16 @@ int _printk(const char *fmt, ...); */ __printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); -extern void __printk_safe_enter(void); -extern void __printk_safe_exit(void); +extern void __printk_deferred_enter(void); +extern void __printk_deferred_exit(void); + /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts * must be disabled for the deferred duration. */ -#define printk_deferred_enter __printk_safe_enter -#define printk_deferred_exit __printk_safe_exit +#define printk_deferred_enter() __printk_deferred_enter() +#define printk_deferred_exit() __printk_deferred_exit() /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -197,6 +200,10 @@ extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); void console_try_replay_all(void); +void printk_legacy_allow_panic_sync(void); +extern bool nbcon_device_try_acquire(struct console *con); +extern void nbcon_device_release(struct console *con); +void nbcon_atomic_flush_unsafe(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -279,6 +286,24 @@ static inline void printk_trigger_flush(void) static inline void console_try_replay_all(void) { } + +static inline void printk_legacy_allow_panic_sync(void) +{ +} + +static inline bool nbcon_device_try_acquire(struct console *con) +{ + return false; +} + +static inline void nbcon_device_release(struct console *con) +{ +} + +static inline void nbcon_atomic_flush_unsafe(void) +{ +} + #endif bool this_cpu_in_panic(void); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0a0e23c45406..c8ed09ac29ac 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -137,7 +137,7 @@ struct signal_struct { /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; - struct list_head posix_timers; + struct hlist_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; @@ -276,8 +276,7 @@ static inline void signal_set_stop_flags(struct signal_struct *sig, extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, sigset_t *mask, - kernel_siginfo_t *info, enum pid_type *type); +extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { @@ -287,7 +286,7 @@ static inline int kernel_dequeue_signal(void) int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info, &__type); + ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index aea25eef9a1a..4ab65874a850 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include #include @@ -590,6 +592,95 @@ struct uart_port { void *private_data; /* generic platform data pointer */ }; +/* + * Only for console->device_lock()/_unlock() callbacks and internal + * port lock wrapper synchronization. + */ +static inline void __uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) +{ + spin_lock_irqsave(&up->lock, *flags); +} + +/* + * Only for console->device_lock()/_unlock() callbacks and internal + * port lock wrapper synchronization. + */ +static inline void __uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) +{ + spin_unlock_irqrestore(&up->lock, flags); +} + +/** + * uart_port_set_cons - Safely set the @cons field for a uart + * @up: The uart port to set + * @con: The new console to set to + * + * This function must be used to set @up->cons. It uses the port lock to + * synchronize with the port lock wrappers in order to ensure that the console + * cannot change or disappear while another context is holding the port lock. + */ +static inline void uart_port_set_cons(struct uart_port *up, struct console *con) +{ + unsigned long flags; + + __uart_port_lock_irqsave(up, &flags); + up->cons = con; + __uart_port_unlock_irqrestore(up, flags); +} + +/* Only for internal port lock wrapper usage. */ +static inline bool __uart_port_using_nbcon(struct uart_port *up) +{ + lockdep_assert_held_once(&up->lock); + + if (likely(!uart_console(up))) + return false; + + /* + * @up->cons is only modified under the port lock. Therefore it is + * certain that it cannot disappear here. + * + * @up->cons->node is added/removed from the console list under the + * port lock. Therefore it is certain that the registration status + * cannot change here, thus @up->cons->flags can be read directly. + */ + if (hlist_unhashed_lockless(&up->cons->node) || + !(up->cons->flags & CON_NBCON) || + !up->cons->write_atomic) { + return false; + } + + return true; +} + +/* Only for internal port lock wrapper usage. */ +static inline bool __uart_port_nbcon_try_acquire(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return true; + + return nbcon_device_try_acquire(up->cons); +} + +/* Only for internal port lock wrapper usage. */ +static inline void __uart_port_nbcon_acquire(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return; + + while (!nbcon_device_try_acquire(up->cons)) + cpu_relax(); +} + +/* Only for internal port lock wrapper usage. */ +static inline void __uart_port_nbcon_release(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return; + + nbcon_device_release(up->cons); +} + /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure @@ -597,6 +688,7 @@ struct uart_port { static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); + __uart_port_nbcon_acquire(up); } /** @@ -606,6 +698,7 @@ static inline void uart_port_lock(struct uart_port *up) static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); + __uart_port_nbcon_acquire(up); } /** @@ -616,6 +709,7 @@ static inline void uart_port_lock_irq(struct uart_port *up) static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); + __uart_port_nbcon_acquire(up); } /** @@ -626,7 +720,15 @@ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *f */ static inline bool uart_port_trylock(struct uart_port *up) { - return spin_trylock(&up->lock); + if (!spin_trylock(&up->lock)) + return false; + + if (!__uart_port_nbcon_try_acquire(up)) { + spin_unlock(&up->lock); + return false; + } + + return true; } /** @@ -638,7 +740,15 @@ static inline bool uart_port_trylock(struct uart_port *up) */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { - return spin_trylock_irqsave(&up->lock, *flags); + if (!spin_trylock_irqsave(&up->lock, *flags)) + return false; + + if (!__uart_port_nbcon_try_acquire(up)) { + spin_unlock_irqrestore(&up->lock, *flags); + return false; + } + + return true; } /** @@ -647,6 +757,7 @@ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long */ static inline void uart_port_unlock(struct uart_port *up) { + __uart_port_nbcon_release(up); spin_unlock(&up->lock); } @@ -656,6 +767,7 @@ static inline void uart_port_unlock(struct uart_port *up) */ static inline void uart_port_unlock_irq(struct uart_port *up) { + __uart_port_nbcon_release(up); spin_unlock_irq(&up->lock); } @@ -666,6 +778,7 @@ static inline void uart_port_unlock_irq(struct uart_port *up) */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { + __uart_port_nbcon_release(up); spin_unlock_irqrestore(&up->lock, flags); } diff --git a/include/linux/smp.h b/include/linux/smp.h index fcd61dfe2af3..6a0813c905d0 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -109,7 +109,7 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, * Architecture specific boot CPU setup. Defined as empty weak function in * init/main.c. Architectures can override it. */ -void smp_prepare_boot_cpu(void); +void __init smp_prepare_boot_cpu(void); #ifdef CONFIG_SMP diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 84ff2844df2a..902c20ef495a 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -73,7 +73,7 @@ struct tk_read_base { * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) * * Note: For timespec(64) based interfaces wall_to_monotonic is what - * we need to add to xtime (or xtime corrected for sub jiffie times) + * we need to add to xtime (or xtime corrected for sub jiffy times) * to get to monotonic time. Monotonic is pegged at zero at system * boot time, so wall_to_monotonic will be negative, however, we will * ALWAYS keep the tv_nsec part positive so we can use the usual diff --git a/init/init_task.c b/init/init_task.c index 33bc679c7821..a229ece703f0 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -29,7 +29,7 @@ static struct signal_struct init_signals = { .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), .exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock), #ifdef CONFIG_POSIX_TIMERS - .posix_timers = LIST_HEAD_INIT(init_signals.posix_timers), + .posix_timers = HLIST_HEAD_INIT, .cputimer = { .cputime_atomic = INIT_CPUTIME_ATOMIC, }, diff --git a/kernel/cpu.c b/kernel/cpu.c index b1fd2a3db91a..d293d52a3e00 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -330,7 +330,7 @@ static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state st /* Poll for one millisecond */ arch_cpuhp_sync_state_poll(); } else { - usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE); + usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); } sync = atomic_read(st); } @@ -1808,6 +1808,7 @@ static int __init parallel_bringup_parse_param(char *arg) } early_param("cpuhp.parallel", parallel_bringup_parse_param); +#ifdef CONFIG_HOTPLUG_SMT static inline bool cpuhp_smt_aware(void) { return cpu_smt_max_threads > 1; @@ -1817,6 +1818,21 @@ static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_primary_thread_mask; } +#else +static inline bool cpuhp_smt_aware(void) +{ + return false; +} +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_none_mask; +} +#endif + +bool __weak arch_cpuhp_init_parallel_bringup(void) +{ + return true; +} /* * On architectures which have enabled parallel bringup this invokes all BP @@ -2689,9 +2705,7 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) return ret; } -/** - * Check if the core a CPU belongs to is online - */ +/* Check if the core a CPU belongs to is online */ #if !defined(topology_is_core_online) static inline bool topology_is_core_online(unsigned int cpu) { diff --git a/kernel/fork.c b/kernel/fork.c index fcb95dc05ec8..fb6bf78f8787 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1892,7 +1892,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS - INIT_LIST_HEAD(&sig->posix_timers); + INIT_HLIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6df0f0c83957..6f563c00a6d7 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -199,7 +199,7 @@ __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff, irqd_clr_managed_shutdown(d); - if (cpumask_any_and(aff, cpu_online_mask) >= nr_cpu_ids) { + if (!cpumask_intersects(aff, cpu_online_mask)) { /* * Catch code which fiddles with enable_irq() on a managed * and potentially shutdown IRQ. Chained interrupt diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index eb8628390156..15a7654eff68 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -37,7 +37,7 @@ static inline bool irq_needs_fixup(struct irq_data *d) * has been removed from the online mask already. */ if (cpumask_any_but(m, cpu) < nr_cpu_ids && - cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) { + !cpumask_intersects(m, cpu_online_mask)) { /* * If this happens then there was a missed IRQ fixup at some * point. Warn about it and enforce fixup. @@ -110,7 +110,7 @@ static bool migrate_one_irq(struct irq_desc *desc) if (maskchip && chip->irq_mask) chip->irq_mask(d); - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + if (!cpumask_intersects(affinity, cpu_online_mask)) { /* * If the interrupt is managed, then shut it down and leave * the affinity untouched. diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c index 3d4036db15ac..1a3d483548e2 100644 --- a/kernel/irq/irq_sim.c +++ b/kernel/irq/irq_sim.c @@ -13,7 +13,6 @@ struct irq_sim_work_ctx { struct irq_work work; - int irq_base; unsigned int irq_count; unsigned long *pending; struct irq_domain *domain; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cea8f6874b1f..e0bff21f30e0 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -128,72 +128,98 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) } EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); -static int irq_domain_set_name(struct irq_domain *domain, - const struct fwnode_handle *fwnode, - enum irq_domain_bus_token bus_token) +static int alloc_name(struct irq_domain *domain, char *base, enum irq_domain_bus_token bus_token) +{ + if (bus_token == DOMAIN_BUS_ANY) + domain->name = kasprintf(GFP_KERNEL, "%s", base); + else + domain->name = kasprintf(GFP_KERNEL, "%s-%d", base, bus_token); + if (!domain->name) + return -ENOMEM; + + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + return 0; +} + +static int alloc_fwnode_name(struct irq_domain *domain, const struct fwnode_handle *fwnode, + enum irq_domain_bus_token bus_token, const char *suffix) +{ + const char *sep = suffix ? "-" : ""; + const char *suf = suffix ? : ""; + char *name; + + if (bus_token == DOMAIN_BUS_ANY) + name = kasprintf(GFP_KERNEL, "%pfw%s%s", fwnode, sep, suf); + else + name = kasprintf(GFP_KERNEL, "%pfw%s%s-%d", fwnode, sep, suf, bus_token); + if (!name) + return -ENOMEM; + + /* + * fwnode paths contain '/', which debugfs is legitimately unhappy + * about. Replace them with ':', which does the trick and is not as + * offensive as '\'... + */ + domain->name = strreplace(name, '/', ':'); + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + return 0; +} + +static int alloc_unknown_name(struct irq_domain *domain, enum irq_domain_bus_token bus_token) { static atomic_t unknown_domains; - struct irqchip_fwid *fwid; + int id = atomic_inc_return(&unknown_domains); + + if (bus_token == DOMAIN_BUS_ANY) + domain->name = kasprintf(GFP_KERNEL, "unknown-%d", id); + else + domain->name = kasprintf(GFP_KERNEL, "unknown-%d-%d", id, bus_token); + if (!domain->name) + return -ENOMEM; + + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + return 0; +} + +static int irq_domain_set_name(struct irq_domain *domain, const struct irq_domain_info *info) +{ + enum irq_domain_bus_token bus_token = info->bus_token; + const struct fwnode_handle *fwnode = info->fwnode; if (is_fwnode_irqchip(fwnode)) { - fwid = container_of(fwnode, struct irqchip_fwid, fwnode); + struct irqchip_fwid *fwid = container_of(fwnode, struct irqchip_fwid, fwnode); + + /* + * The name_suffix is only intended to be used to avoid a name + * collision when multiple domains are created for a single + * device and the name is picked using a real device node. + * (Typical use-case is regmap-IRQ controllers for devices + * providing more than one physical IRQ.) There should be no + * need to use name_suffix with irqchip-fwnode. + */ + if (info->name_suffix) + return -EINVAL; switch (fwid->type) { case IRQCHIP_FWNODE_NAMED: case IRQCHIP_FWNODE_NAMED_ID: - domain->name = bus_token ? - kasprintf(GFP_KERNEL, "%s-%d", - fwid->name, bus_token) : - kstrdup(fwid->name, GFP_KERNEL); - if (!domain->name) - return -ENOMEM; - domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; - break; + return alloc_name(domain, fwid->name, bus_token); default: domain->name = fwid->name; - if (bus_token) { - domain->name = kasprintf(GFP_KERNEL, "%s-%d", - fwid->name, bus_token); - if (!domain->name) - return -ENOMEM; - domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; - } - break; + if (bus_token != DOMAIN_BUS_ANY) + return alloc_name(domain, fwid->name, bus_token); } - } else if (is_of_node(fwnode) || is_acpi_device_node(fwnode) || - is_software_node(fwnode)) { - char *name; - /* - * fwnode paths contain '/', which debugfs is legitimately - * unhappy about. Replace them with ':', which does - * the trick and is not as offensive as '\'... - */ - name = bus_token ? - kasprintf(GFP_KERNEL, "%pfw-%d", fwnode, bus_token) : - kasprintf(GFP_KERNEL, "%pfw", fwnode); - if (!name) - return -ENOMEM; - - domain->name = strreplace(name, '/', ':'); - domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + } else if (is_of_node(fwnode) || is_acpi_device_node(fwnode) || is_software_node(fwnode)) { + return alloc_fwnode_name(domain, fwnode, bus_token, info->name_suffix); } - if (!domain->name) { - if (fwnode) - pr_err("Invalid fwnode type for irqdomain\n"); - domain->name = bus_token ? - kasprintf(GFP_KERNEL, "unknown-%d-%d", - atomic_inc_return(&unknown_domains), - bus_token) : - kasprintf(GFP_KERNEL, "unknown-%d", - atomic_inc_return(&unknown_domains)); - if (!domain->name) - return -ENOMEM; - domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; - } + if (domain->name) + return 0; - return 0; + if (fwnode) + pr_err("Invalid fwnode type for irqdomain\n"); + return alloc_unknown_name(domain, bus_token); } static struct irq_domain *__irq_domain_create(const struct irq_domain_info *info) @@ -211,7 +237,7 @@ static struct irq_domain *__irq_domain_create(const struct irq_domain_info *info if (!domain) return ERR_PTR(-ENOMEM); - err = irq_domain_set_name(domain, info->fwnode, info->bus_token); + err = irq_domain_set_name(domain, info); if (err) { kfree(domain); return ERR_PTR(err); @@ -267,13 +293,20 @@ static void irq_domain_free(struct irq_domain *domain) kfree(domain); } -/** - * irq_domain_instantiate() - Instantiate a new irq domain data structure - * @info: Domain information pointer pointing to the information for this domain - * - * Return: A pointer to the instantiated irq domain or an ERR_PTR value. - */ -struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) +static void irq_domain_instantiate_descs(const struct irq_domain_info *info) +{ + if (!IS_ENABLED(CONFIG_SPARSE_IRQ)) + return; + + if (irq_alloc_descs(info->virq_base, info->virq_base, info->size, + of_node_to_nid(to_of_node(info->fwnode))) < 0) { + pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", + info->virq_base); + } +} + +static struct irq_domain *__irq_domain_instantiate(const struct irq_domain_info *info, + bool cond_alloc_descs, bool force_associate) { struct irq_domain *domain; int err; @@ -306,6 +339,19 @@ struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) __irq_domain_publish(domain); + if (cond_alloc_descs && info->virq_base > 0) + irq_domain_instantiate_descs(info); + + /* + * Legacy interrupt domains have a fixed Linux interrupt number + * associated. Other interrupt domains can request association by + * providing a Linux interrupt number > 0. + */ + if (force_associate || info->virq_base > 0) { + irq_domain_associate_many(domain, info->virq_base, info->hwirq_base, + info->size - info->hwirq_base); + } + return domain; err_domain_gc_remove: @@ -315,6 +361,17 @@ err_domain_free: irq_domain_free(domain); return ERR_PTR(err); } + +/** + * irq_domain_instantiate() - Instantiate a new irq domain data structure + * @info: Domain information pointer pointing to the information for this domain + * + * Return: A pointer to the instantiated irq domain or an ERR_PTR value. + */ +struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) +{ + return __irq_domain_instantiate(info, false, false); +} EXPORT_SYMBOL_GPL(irq_domain_instantiate); /** @@ -413,28 +470,13 @@ struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, .fwnode = fwnode, .size = size, .hwirq_max = size, + .virq_base = first_irq, .ops = ops, .host_data = host_data, }; - struct irq_domain *domain; + struct irq_domain *domain = __irq_domain_instantiate(&info, true, false); - domain = irq_domain_instantiate(&info); - if (IS_ERR(domain)) - return NULL; - - if (first_irq > 0) { - if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { - /* attempt to allocated irq_descs */ - int rc = irq_alloc_descs(first_irq, first_irq, size, - of_node_to_nid(to_of_node(fwnode))); - if (rc < 0) - pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", - first_irq); - } - irq_domain_associate_many(domain, first_irq, 0, size); - } - - return domain; + return IS_ERR(domain) ? NULL : domain; } EXPORT_SYMBOL_GPL(irq_domain_create_simple); @@ -476,18 +518,14 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, .fwnode = fwnode, .size = first_hwirq + size, .hwirq_max = first_hwirq + size, + .hwirq_base = first_hwirq, + .virq_base = first_irq, .ops = ops, .host_data = host_data, }; - struct irq_domain *domain; + struct irq_domain *domain = __irq_domain_instantiate(&info, false, true); - domain = irq_domain_instantiate(&info); - if (IS_ERR(domain)) - return NULL; - - irq_domain_associate_many(domain, first_irq, first_hwirq, size); - - return domain; + return IS_ERR(domain) ? NULL : domain; } EXPORT_SYMBOL_GPL(irq_domain_create_legacy); @@ -1365,7 +1403,7 @@ static int irq_domain_trim_hierarchy(unsigned int virq) tail = NULL; /* The first entry must have a valid irqchip */ - if (!irq_data->chip || IS_ERR(irq_data->chip)) + if (IS_ERR_OR_NULL(irq_data->chip)) return -EINVAL; /* diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index dd53298ef1a5..f0803d6bd296 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -218,21 +218,20 @@ static void irq_validate_effective_affinity(struct irq_data *data) static inline void irq_validate_effective_affinity(struct irq_data *data) { } #endif +static DEFINE_PER_CPU(struct cpumask, __tmp_mask); + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { + struct cpumask *tmp_mask = this_cpu_ptr(&__tmp_mask); struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); const struct cpumask *prog_mask; int ret; - static DEFINE_RAW_SPINLOCK(tmp_mask_lock); - static struct cpumask tmp_mask; - if (!chip || !chip->irq_set_affinity) return -EINVAL; - raw_spin_lock(&tmp_mask_lock); /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with @@ -258,11 +257,11 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); - cpumask_and(&tmp_mask, mask, hk_mask); - if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) + cpumask_and(tmp_mask, mask, hk_mask); + if (!cpumask_intersects(tmp_mask, cpu_online_mask)) prog_mask = mask; else - prog_mask = &tmp_mask; + prog_mask = tmp_mask; } else { prog_mask = mask; } @@ -272,16 +271,14 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, * unless we are being asked to force the affinity (in which * case we do as we are told). */ - cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); - if (!force && !cpumask_empty(&tmp_mask)) - ret = chip->irq_set_affinity(data, &tmp_mask, force); + cpumask_and(tmp_mask, prog_mask, cpu_online_mask); + if (!force && !cpumask_empty(tmp_mask)) + ret = chip->irq_set_affinity(data, tmp_mask, force); else if (force) ret = chip->irq_set_affinity(data, mask, force); else ret = -EINVAL; - raw_spin_unlock(&tmp_mask_lock); - switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 61ca924ef4b4..eb150afd671f 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -26,7 +26,7 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear) * The outgoing CPU might be the last online target in a pending * interrupt move. If that's the case clear the pending move bit. */ - if (cpumask_any_and(desc->pending_mask, cpu_online_mask) >= nr_cpu_ids) { + if (!cpumask_intersects(desc->pending_mask, cpu_online_mask)) { irqd_clr_move_pending(data); return false; } @@ -74,7 +74,7 @@ void irq_move_masked_irq(struct irq_data *idata) * For correct operation this depends on the caller * masking the irqs. */ - if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) { + if (cpumask_intersects(desc->pending_mask, cpu_online_mask)) { int ret; ret = irq_do_set_affinity(data, desc->pending_mask, false); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 5fa0547ece0c..1c7e5159064c 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -82,7 +82,7 @@ static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec, desc->dev = dev; desc->nvec_used = nvec; if (affinity) { - desc->affinity = kmemdup(affinity, nvec * sizeof(*desc->affinity), GFP_KERNEL); + desc->affinity = kmemdup_array(affinity, nvec, sizeof(*desc->affinity), GFP_KERNEL); if (!desc->affinity) { kfree(desc); return NULL; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 8cccdf40725a..9081ada81c3d 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -52,10 +52,8 @@ static int show_irq_affinity(int type, struct seq_file *m) case AFFINITY: case AFFINITY_LIST: mask = desc->irq_common_data.affinity; -#ifdef CONFIG_GENERIC_PENDING_IRQ - if (irqd_is_setaffinity_pending(&desc->irq_data)) - mask = desc->pending_mask; -#endif + if (irq_move_pending(&desc->irq_data)) + mask = irq_desc_get_pending_mask(desc); break; case EFFECTIVE: case EFFECTIVE_LIST: @@ -142,7 +140,7 @@ static ssize_t write_irq_affinity(int type, struct file *file, int err; if (!irq_can_set_affinity_usr(irq) || no_irq_affinity) - return -EIO; + return -EPERM; if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) return -ENOMEM; @@ -362,8 +360,13 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) goto out_unlock; #ifdef CONFIG_SMP + umode_t umode = S_IRUGO; + + if (irq_can_set_affinity_usr(desc->irq_data.irq)) + umode |= S_IWUSR; + /* create /proc/irq//smp_affinity */ - proc_create_data("smp_affinity", 0644, desc->dir, + proc_create_data("smp_affinity", umode, desc->dir, &irq_affinity_proc_ops, irqp); /* create /proc/irq//affinity_hint */ @@ -371,7 +374,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) irq_affinity_hint_proc_show, irqp); /* create /proc/irq//smp_affinity_list */ - proc_create_data("smp_affinity_list", 0644, desc->dir, + proc_create_data("smp_affinity_list", umode, desc->dir, &irq_affinity_list_proc_ops, irqp); proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show, diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 0349f957e672..7963deac33c3 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -56,6 +56,7 @@ #include #include #include +#include #include @@ -573,8 +574,10 @@ static struct lock_trace *save_trace(void) if (!debug_locks_off_graph_unlock()) return NULL; + nbcon_cpu_emergency_enter(); print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!"); dump_stack(); + nbcon_cpu_emergency_exit(); return NULL; } @@ -887,11 +890,13 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { instrumentation_begin(); debug_locks_off(); + nbcon_cpu_emergency_enter(); printk(KERN_ERR "BUG: looking up invalid subclass: %u\n", subclass); printk(KERN_ERR "turning off the locking correctness validator.\n"); dump_stack(); + nbcon_cpu_emergency_exit(); instrumentation_end(); return NULL; } @@ -968,11 +973,13 @@ static bool assign_lock_key(struct lockdep_map *lock) else { /* Debug-check: all keys must be persistent! */ debug_locks_off(); + nbcon_cpu_emergency_enter(); pr_err("INFO: trying to register non-static key.\n"); pr_err("The code is fine but needs lockdep annotation, or maybe\n"); pr_err("you didn't initialize this object before use?\n"); pr_err("turning off the locking correctness validator.\n"); dump_stack(); + nbcon_cpu_emergency_exit(); return false; } @@ -1316,8 +1323,10 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) return NULL; } + nbcon_cpu_emergency_enter(); print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!"); dump_stack(); + nbcon_cpu_emergency_exit(); return NULL; } nr_lock_classes++; @@ -1349,11 +1358,13 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) if (verbose(class)) { graph_unlock(); + nbcon_cpu_emergency_enter(); printk("\nnew class %px: %s", class->key, class->name); if (class->name_version > 1) printk(KERN_CONT "#%d", class->name_version); printk(KERN_CONT "\n"); dump_stack(); + nbcon_cpu_emergency_exit(); if (!graph_lock()) { return NULL; @@ -1392,8 +1403,10 @@ static struct lock_list *alloc_list_entry(void) if (!debug_locks_off_graph_unlock()) return NULL; + nbcon_cpu_emergency_enter(); print_lockdep_off("BUG: MAX_LOCKDEP_ENTRIES too low!"); dump_stack(); + nbcon_cpu_emergency_exit(); return NULL; } nr_list_entries++; @@ -2039,6 +2052,8 @@ static noinline void print_circular_bug(struct lock_list *this, depth = get_lock_depth(target); + nbcon_cpu_emergency_enter(); + print_circular_bug_header(target, depth, check_src, check_tgt); parent = get_lock_parent(target); @@ -2057,6 +2072,8 @@ static noinline void print_circular_bug(struct lock_list *this, printk("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } static noinline void print_bfs_bug(int ret) @@ -2569,6 +2586,8 @@ print_bad_irq_dependency(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("=====================================================\n"); pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n", @@ -2618,11 +2637,13 @@ print_bad_irq_dependency(struct task_struct *curr, pr_warn(" and %s-irq-unsafe lock:\n", irqclass); next_root->trace = save_trace(); if (!next_root->trace) - return; + goto out; print_shortest_lock_dependencies(forwards_entry, next_root); pr_warn("\nstack backtrace:\n"); dump_stack(); +out: + nbcon_cpu_emergency_exit(); } static const char *state_names[] = { @@ -2987,6 +3008,8 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("============================================\n"); pr_warn("WARNING: possible recursive locking detected\n"); @@ -3009,6 +3032,8 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } /* @@ -3606,6 +3631,8 @@ static void print_collision(struct task_struct *curr, struct held_lock *hlock_next, struct lock_chain *chain) { + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("============================\n"); pr_warn("WARNING: chain_key collision\n"); @@ -3622,6 +3649,8 @@ static void print_collision(struct task_struct *curr, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } #endif @@ -3712,8 +3741,10 @@ static inline int add_chain_cache(struct task_struct *curr, if (!debug_locks_off_graph_unlock()) return 0; + nbcon_cpu_emergency_enter(); print_lockdep_off("BUG: MAX_LOCKDEP_CHAINS too low!"); dump_stack(); + nbcon_cpu_emergency_exit(); return 0; } chain->chain_key = chain_key; @@ -3730,8 +3761,10 @@ static inline int add_chain_cache(struct task_struct *curr, if (!debug_locks_off_graph_unlock()) return 0; + nbcon_cpu_emergency_enter(); print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); dump_stack(); + nbcon_cpu_emergency_exit(); return 0; } @@ -3970,6 +4003,8 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, if (!debug_locks_off() || debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("================================\n"); pr_warn("WARNING: inconsistent lock state\n"); @@ -3998,6 +4033,8 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } /* @@ -4032,6 +4069,8 @@ print_irq_inversion_bug(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("========================================================\n"); pr_warn("WARNING: possible irq lock inversion dependency detected\n"); @@ -4072,11 +4111,13 @@ print_irq_inversion_bug(struct task_struct *curr, pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); root->trace = save_trace(); if (!root->trace) - return; + goto out; print_shortest_lock_dependencies(other, root); pr_warn("\nstack backtrace:\n"); dump_stack(); +out: + nbcon_cpu_emergency_exit(); } /* @@ -4153,6 +4194,8 @@ void print_irqtrace_events(struct task_struct *curr) { const struct irqtrace_events *trace = &curr->irqtrace; + nbcon_cpu_emergency_enter(); + printk("irq event stamp: %u\n", trace->irq_events); printk("hardirqs last enabled at (%u): [<%px>] %pS\n", trace->hardirq_enable_event, (void *)trace->hardirq_enable_ip, @@ -4166,6 +4209,8 @@ void print_irqtrace_events(struct task_struct *curr) printk("softirqs last disabled at (%u): [<%px>] %pS\n", trace->softirq_disable_event, (void *)trace->softirq_disable_ip, (void *)trace->softirq_disable_ip); + + nbcon_cpu_emergency_exit(); } static int HARDIRQ_verbose(struct lock_class *class) @@ -4686,10 +4731,12 @@ unlock: * We must printk outside of the graph_lock: */ if (ret == 2) { + nbcon_cpu_emergency_enter(); printk("\nmarked lock as {%s}:\n", usage_str[new_bit]); print_lock(this); print_irqtrace_events(curr); dump_stack(); + nbcon_cpu_emergency_exit(); } return ret; @@ -4730,6 +4777,8 @@ print_lock_invalid_wait_context(struct task_struct *curr, if (debug_locks_silent) return 0; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("=============================\n"); pr_warn("[ BUG: Invalid wait context ]\n"); @@ -4749,6 +4798,8 @@ print_lock_invalid_wait_context(struct task_struct *curr, pr_warn("stack backtrace:\n"); dump_stack(); + nbcon_cpu_emergency_exit(); + return 0; } @@ -4956,6 +5007,8 @@ print_lock_nested_lock_not_held(struct task_struct *curr, if (debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("==================================\n"); pr_warn("WARNING: Nested lock was not taken\n"); @@ -4976,6 +5029,8 @@ print_lock_nested_lock_not_held(struct task_struct *curr, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } static int __lock_is_held(const struct lockdep_map *lock, int read); @@ -5024,11 +5079,13 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, debug_class_ops_inc(class); if (very_verbose(class)) { + nbcon_cpu_emergency_enter(); printk("\nacquire class [%px] %s", class->key, class->name); if (class->name_version > 1) printk(KERN_CONT "#%d", class->name_version); printk(KERN_CONT "\n"); dump_stack(); + nbcon_cpu_emergency_exit(); } /* @@ -5155,6 +5212,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, #endif if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) { debug_locks_off(); + nbcon_cpu_emergency_enter(); print_lockdep_off("BUG: MAX_LOCK_DEPTH too low!"); printk(KERN_DEBUG "depth: %i max: %lu!\n", curr->lockdep_depth, MAX_LOCK_DEPTH); @@ -5162,6 +5220,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, lockdep_print_held_locks(current); debug_show_all_locks(); dump_stack(); + nbcon_cpu_emergency_exit(); return 0; } @@ -5181,6 +5240,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr, if (debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("=====================================\n"); pr_warn("WARNING: bad unlock balance detected!\n"); @@ -5197,6 +5258,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } static noinstr int match_held_lock(const struct held_lock *hlock, @@ -5901,6 +5964,8 @@ static void print_lock_contention_bug(struct task_struct *curr, if (debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("=================================\n"); pr_warn("WARNING: bad contention detected!\n"); @@ -5917,6 +5982,8 @@ static void print_lock_contention_bug(struct task_struct *curr, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } static void @@ -6536,6 +6603,8 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, if (debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("=========================\n"); pr_warn("WARNING: held lock freed!\n"); @@ -6548,6 +6617,8 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } static inline int not_in_range(const void* mem_from, unsigned long mem_len, @@ -6594,6 +6665,8 @@ static void print_held_locks_bug(void) if (debug_locks_silent) return; + nbcon_cpu_emergency_enter(); + pr_warn("\n"); pr_warn("====================================\n"); pr_warn("WARNING: %s/%d still has locks held!\n", @@ -6603,6 +6676,8 @@ static void print_held_locks_bug(void) lockdep_print_held_locks(current); pr_warn("\nstack backtrace:\n"); dump_stack(); + + nbcon_cpu_emergency_exit(); } void debug_check_no_locks_held(void) @@ -6660,6 +6735,7 @@ asmlinkage __visible void lockdep_sys_exit(void) if (unlikely(curr->lockdep_depth)) { if (!debug_locks_off()) return; + nbcon_cpu_emergency_enter(); pr_warn("\n"); pr_warn("================================================\n"); pr_warn("WARNING: lock held when returning to user space!\n"); @@ -6668,6 +6744,7 @@ asmlinkage __visible void lockdep_sys_exit(void) pr_warn("%s/%d is leaving the kernel with locks still held!\n", curr->comm, curr->pid); lockdep_print_held_locks(curr); + nbcon_cpu_emergency_exit(); } /* @@ -6684,6 +6761,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) bool rcu = warn_rcu_enter(); /* Note: the following can be executed concurrently, so be careful. */ + nbcon_cpu_emergency_enter(); pr_warn("\n"); pr_warn("=============================\n"); pr_warn("WARNING: suspicious RCU usage\n"); @@ -6722,6 +6800,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) lockdep_print_held_locks(curr); pr_warn("\nstack backtrace:\n"); dump_stack(); + nbcon_cpu_emergency_exit(); warn_rcu_exit(rcu); } EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); diff --git a/kernel/panic.c b/kernel/panic.c index 2a0449144f82..753d12f4dc8f 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -374,6 +374,8 @@ void panic(const char *fmt, ...) panic_other_cpus_shutdown(_crash_kexec_post_notifiers); + printk_legacy_allow_panic_sync(); + /* * Run any panic handlers, including those that might need to * add information to the kmsg dump output. @@ -463,6 +465,7 @@ void panic(const char *fmt, ...) * Explicitly flush the kernel log buffer one last time. */ console_flush_on_panic(CONSOLE_FLUSH_PENDING); + nbcon_atomic_flush_unsafe(); local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { @@ -682,6 +685,7 @@ bool oops_may_print(void) */ void oops_enter(void) { + nbcon_cpu_emergency_enter(); tracing_off(); /* can't trust the integrity of the kernel anymore: */ debug_locks_off(); @@ -704,6 +708,7 @@ void oops_exit(void) { do_oops_enter_exit(); print_oops_end_marker(); + nbcon_cpu_emergency_exit(); kmsg_dump(KMSG_DUMP_OOPS); } @@ -715,6 +720,8 @@ struct warn_args { void __warn(const char *file, int line, void *caller, unsigned taint, struct pt_regs *regs, struct warn_args *args) { + nbcon_cpu_emergency_enter(); + disable_trace_on_warning(); if (file) @@ -750,6 +757,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); + + nbcon_cpu_emergency_exit(); } #ifdef CONFIG_BUG diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 19dcc5832651..3fcb48502adb 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -2,11 +2,12 @@ /* * internal.h - printk internal definitions */ -#include #include -#include "printk_ringbuffer.h" +#include +#include #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) +struct ctl_table; void __init printk_sysctl_init(void); int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); @@ -20,6 +21,19 @@ int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, (con->flags & CON_BOOT) ? "boot" : "", \ con->name, con->index, ##__VA_ARGS__) +/* + * Identify if legacy printing is forced in a dedicated kthread. If + * true, all printing via console lock occurs within a dedicated + * legacy printer thread. The only exception is on panic, after the + * nbcon consoles have had their chance to print the panic messages + * first. + */ +#ifdef CONFIG_PREEMPT_RT +# define force_legacy_kthread() (true) +#else +# define force_legacy_kthread() (false) +#endif + #ifdef CONFIG_PRINTK #ifdef CONFIG_PRINTK_CALLER @@ -43,7 +57,11 @@ enum printk_info_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; +struct printk_ringbuffer; +struct dev_printk_info; + extern struct printk_ringbuffer *prb; +extern bool printk_kthreads_running; __printf(4, 0) int vprintk_store(int facility, int level, @@ -53,6 +71,9 @@ int vprintk_store(int facility, int level, __printf(1, 0) int vprintk_default(const char *fmt, va_list args); __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); +void __printk_safe_enter(void); +void __printk_safe_exit(void); + bool printk_percpu_data_ready(void); #define printk_safe_enter_irqsave(flags) \ @@ -68,15 +89,85 @@ bool printk_percpu_data_ready(void); } while (0) void defer_console_output(void); +bool is_printk_legacy_deferred(void); u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags); +void console_lock_spinning_enable(void); +int console_lock_spinning_disable_and_check(int cookie); u64 nbcon_seq_read(struct console *con); void nbcon_seq_force(struct console *con, u64 seq); bool nbcon_alloc(struct console *con); -void nbcon_init(struct console *con); void nbcon_free(struct console *con); +enum nbcon_prio nbcon_get_default_prio(void); +void nbcon_atomic_flush_pending(void); +bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, + int cookie, bool use_atomic); +bool nbcon_kthread_create(struct console *con); +void nbcon_kthread_stop(struct console *con); +void nbcon_kthreads_wake(void); + +/* + * Check if the given console is currently capable and allowed to print + * records. Note that this function does not consider the current context, + * which can also play a role in deciding if @con can be used to print + * records. + */ +static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) +{ + if (!(flags & CON_ENABLED)) + return false; + + if ((flags & CON_SUSPENDED)) + return false; + + if (flags & CON_NBCON) { + /* The write_atomic() callback is optional. */ + if (use_atomic && !con->write_atomic) + return false; + + /* + * For the !use_atomic case, @printk_kthreads_running is not + * checked because the write_thread() callback is also used + * via the legacy loop when the printer threads are not + * available. + */ + } else { + if (!con->write) + return false; + } + + /* + * Console drivers may assume that per-cpu resources have been + * allocated. So unless they're explicitly marked as being able to + * cope (CON_ANYTIME) don't call them until this CPU is officially up. + */ + if (!cpu_online(raw_smp_processor_id()) && !(flags & CON_ANYTIME)) + return false; + + return true; +} + +/** + * nbcon_kthread_wake - Wake up a console printing thread + * @con: Console to operate on + */ +static inline void nbcon_kthread_wake(struct console *con) +{ + /* + * Guarantee any new records can be seen by tasks preparing to wait + * before this context checks if the rcuwait is empty. + * + * The full memory barrier in rcuwait_wake_up() pairs with the full + * memory barrier within set_current_state() of + * ___rcuwait_wait_event(), which is called after prepare_to_rcuwait() + * adds the waiter but before it has checked the wait condition. + * + * This pairs with nbcon_kthread_func:A. + */ + rcuwait_wake_up(&con->rcuwait); /* LMM(nbcon_kthread_wake:A) */ +} #else @@ -84,6 +175,8 @@ void nbcon_free(struct console *con); #define PRINTK_MESSAGE_MAX 0 #define PRINTKRB_RECORD_MAX 0 +#define printk_kthreads_running (false) + /* * In !PRINTK builds we still export console_sem * semaphore and some of console functions (console_unlock()/etc.), so @@ -93,14 +186,119 @@ void nbcon_free(struct console *con); #define printk_safe_exit_irqrestore(flags) local_irq_restore(flags) static inline bool printk_percpu_data_ready(void) { return false; } +static inline void defer_console_output(void) { } +static inline bool is_printk_legacy_deferred(void) { return false; } static inline u64 nbcon_seq_read(struct console *con) { return 0; } static inline void nbcon_seq_force(struct console *con, u64 seq) { } static inline bool nbcon_alloc(struct console *con) { return false; } -static inline void nbcon_init(struct console *con) { } static inline void nbcon_free(struct console *con) { } +static inline enum nbcon_prio nbcon_get_default_prio(void) { return NBCON_PRIO_NONE; } +static inline void nbcon_atomic_flush_pending(void) { } +static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, + int cookie, bool use_atomic) { return false; } +static inline void nbcon_kthread_wake(struct console *con) { } +static inline void nbcon_kthreads_wake(void) { } + +static inline bool console_is_usable(struct console *con, short flags, + bool use_atomic) { return false; } #endif /* CONFIG_PRINTK */ +extern bool have_boot_console; +extern bool have_nbcon_console; +extern bool have_legacy_console; +extern bool legacy_allow_panic_sync; + +/** + * struct console_flush_type - Define available console flush methods + * @nbcon_atomic: Flush directly using nbcon_atomic() callback + * @nbcon_offload: Offload flush to printer thread + * @legacy_direct: Call the legacy loop in this context + * @legacy_offload: Offload the legacy loop into IRQ or legacy thread + * + * Note that the legacy loop also flushes the nbcon consoles. + */ +struct console_flush_type { + bool nbcon_atomic; + bool nbcon_offload; + bool legacy_direct; + bool legacy_offload; +}; + +/* + * Identify which console flushing methods should be used in the context of + * the caller. + */ +static inline void printk_get_console_flush_type(struct console_flush_type *ft) +{ + memset(ft, 0, sizeof(*ft)); + + switch (nbcon_get_default_prio()) { + case NBCON_PRIO_NORMAL: + if (have_nbcon_console && !have_boot_console) { + if (printk_kthreads_running) + ft->nbcon_offload = true; + else + ft->nbcon_atomic = true; + } + + /* Legacy consoles are flushed directly when possible. */ + if (have_legacy_console || have_boot_console) { + if (!is_printk_legacy_deferred()) + ft->legacy_direct = true; + else + ft->legacy_offload = true; + } + break; + + case NBCON_PRIO_EMERGENCY: + if (have_nbcon_console && !have_boot_console) + ft->nbcon_atomic = true; + + /* Legacy consoles are flushed directly when possible. */ + if (have_legacy_console || have_boot_console) { + if (!is_printk_legacy_deferred()) + ft->legacy_direct = true; + else + ft->legacy_offload = true; + } + break; + + case NBCON_PRIO_PANIC: + /* + * In panic, the nbcon consoles will directly print. But + * only allowed if there are no boot consoles. + */ + if (have_nbcon_console && !have_boot_console) + ft->nbcon_atomic = true; + + if (have_legacy_console || have_boot_console) { + /* + * This is the same decision as NBCON_PRIO_NORMAL + * except that offloading never occurs in panic. + * + * Note that console_flush_on_panic() will flush + * legacy consoles anyway, even if unsafe. + */ + if (!is_printk_legacy_deferred()) + ft->legacy_direct = true; + + /* + * In panic, if nbcon atomic printing occurs, + * the legacy consoles must remain silent until + * explicitly allowed. + */ + if (ft->nbcon_atomic && !legacy_allow_panic_sync) + ft->legacy_direct = false; + } + break; + + default: + WARN_ON_ONCE(1); + break; + } +} + extern struct printk_buffers printk_shared_pbufs; /** @@ -135,4 +333,5 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, #ifdef CONFIG_PRINTK void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped); +void console_prepend_replay(struct printk_message *pmsg); #endif diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index c8093bcc01fe..fd12efcc4aed 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -2,11 +2,25 @@ // Copyright (C) 2022 Linutronix GmbH, John Ogness // Copyright (C) 2022 Intel, Thomas Gleixner -#include +#include +#include #include #include +#include +#include +#include +#include +#include +#include +#include +#include #include +#include +#include +#include +#include #include "internal.h" +#include "printk_ringbuffer.h" /* * Printk console printing implementation for consoles which does not depend * on the legacy style console_lock mechanism. @@ -172,9 +186,6 @@ void nbcon_seq_force(struct console *con, u64 seq) u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); - - /* Clear con->seq since nbcon consoles use con->nbcon_seq instead. */ - con->seq = 0; } /** @@ -231,6 +242,13 @@ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt, struct nbcon_state new; do { + /* + * Panic does not imply that the console is owned. However, it + * is critical that non-panic CPUs during panic are unable to + * acquire ownership in order to satisfy the assumptions of + * nbcon_waiter_matches(). In particular, the assumption that + * lower priorities are ignored during panic. + */ if (other_cpu_in_panic()) return -EPERM; @@ -262,18 +280,29 @@ static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio) /* * The request context is well defined by the @req_prio because: * - * - Only a context with a higher priority can take over the request. + * - Only a context with a priority higher than the owner can become + * a waiter. + * - Only a context with a priority higher than the waiter can + * directly take over the request. * - There are only three priorities. * - Only one CPU is allowed to request PANIC priority. * - Lower priorities are ignored during panic() until reboot. * * As a result, the following scenario is *not* possible: * - * 1. Another context with a higher priority directly takes ownership. - * 2. The higher priority context releases the ownership. - * 3. A lower priority context takes the ownership. - * 4. Another context with the same priority as this context + * 1. This context is currently a waiter. + * 2. Another context with a higher priority than this context + * directly takes ownership. + * 3. The higher priority context releases the ownership. + * 4. Another lower priority context takes the ownership. + * 5. Another context with the same priority as this context * creates a request and starts waiting. + * + * Event #1 implies this context is EMERGENCY. + * Event #2 implies the new context is PANIC. + * Event #3 occurs when panic() has flushed the console. + * Events #4 and #5 are not possible due to the other_cpu_in_panic() + * check in nbcon_context_try_acquire_direct(). */ return (cur->req_prio == expected_prio); @@ -531,6 +560,7 @@ static struct printk_buffers panic_nbcon_pbufs; * nbcon_context_try_acquire - Try to acquire nbcon console * @ctxt: The context of the caller * + * Context: Under @ctxt->con->device_lock() or local_irq_save(). * Return: True if the console was acquired. False otherwise. * * If the caller allowed an unsafe hostile takeover, on success the @@ -538,7 +568,6 @@ static struct printk_buffers panic_nbcon_pbufs; * in an unsafe state. Otherwise, on success the caller may assume * the console is not in an unsafe state. */ -__maybe_unused static bool nbcon_context_try_acquire(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); @@ -581,11 +610,29 @@ static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu, int expected_prio) { /* - * Since consoles can only be acquired by higher priorities, - * owning contexts are uniquely identified by @prio. However, - * since contexts can unexpectedly lose ownership, it is - * possible that later another owner appears with the same - * priority. For this reason @cpu is also needed. + * A similar function, nbcon_waiter_matches(), only deals with + * EMERGENCY and PANIC priorities. However, this function must also + * deal with the NORMAL priority, which requires additional checks + * and constraints. + * + * For the case where preemption and interrupts are disabled, it is + * enough to also verify that the owning CPU has not changed. + * + * For the case where preemption or interrupts are enabled, an + * external synchronization method *must* be used. In particular, + * the driver-specific locking mechanism used in device_lock() + * (including disabling migration) should be used. It prevents + * scenarios such as: + * + * 1. [Task A] owns a context with NBCON_PRIO_NORMAL on [CPU X] and + * is scheduled out. + * 2. Another context takes over the lock with NBCON_PRIO_EMERGENCY + * and releases it. + * 3. [Task B] acquires a context with NBCON_PRIO_NORMAL on [CPU X] + * and is scheduled out. + * 4. [Task A] gets running on [CPU X] and sees that the console is + * still owned by a task on [CPU X] with NBON_PRIO_NORMAL. Thus + * [Task A] thinks it is the owner when it is not. */ if (cur->prio != expected_prio) @@ -784,6 +831,19 @@ out: return nbcon_context_can_proceed(ctxt, &cur); } +static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, + char *buf, unsigned int len) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + struct console *con = ctxt->console; + struct nbcon_state cur; + + wctxt->outbuf = buf; + wctxt->len = len; + nbcon_state_read(con, &cur); + wctxt->unsafe_takeover = cur.unsafe_takeover; +} + /** * nbcon_enter_unsafe - Enter an unsafe region in the driver * @wctxt: The write context that was handed to the write function @@ -799,8 +859,12 @@ out: bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + bool is_owner; - return nbcon_context_enter_unsafe(ctxt); + is_owner = nbcon_context_enter_unsafe(ctxt); + if (!is_owner) + nbcon_write_context_set_buf(wctxt, NULL, 0); + return is_owner; } EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); @@ -819,14 +883,47 @@ EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + bool ret; - return nbcon_context_exit_unsafe(ctxt); + ret = nbcon_context_exit_unsafe(ctxt); + if (!ret) + nbcon_write_context_set_buf(wctxt, NULL, 0); + return ret; } EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); +/** + * nbcon_reacquire_nobuf - Reacquire a console after losing ownership + * while printing + * @wctxt: The write context that was handed to the write callback + * + * Since ownership can be lost at any time due to handover or takeover, a + * printing context _must_ be prepared to back out immediately and + * carefully. However, there are scenarios where the printing context must + * reacquire ownership in order to finalize or revert hardware changes. + * + * This function allows a printing context to reacquire ownership using the + * same priority as its previous ownership. + * + * Note that after a successful reacquire the printing context will have no + * output buffer because that has been lost. This function cannot be used to + * resume printing. + */ +void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + + while (!nbcon_context_try_acquire(ctxt)) + cpu_relax(); + + nbcon_write_context_set_buf(wctxt, NULL, 0); +} +EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf); + /** * nbcon_emit_next_record - Emit a record in the acquired context * @wctxt: The write context that will be handed to the write function + * @use_atomic: True if the write_atomic() callback is to be used * * Return: True if this context still owns the console. False if * ownership was handed over or taken. @@ -840,8 +937,7 @@ EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); * When true is returned, @wctxt->ctxt.backlog indicates whether there are * still records pending in the ringbuffer, */ -__maybe_unused -static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) +static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; @@ -852,7 +948,22 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) unsigned long con_dropped; struct nbcon_state cur; unsigned long dropped; - bool done; + unsigned long ulseq; + + /* + * This function should never be called for consoles that have not + * implemented the necessary callback for writing: i.e. legacy + * consoles and, when atomic, nbcon consoles with no write_atomic(). + * Handle it as if ownership was lost and try to continue. + * + * Note that for nbcon consoles the write_thread() callback is + * mandatory and was already checked in nbcon_alloc(). + */ + if (WARN_ON_ONCE((use_atomic && !con->write_atomic) || + !(console_srcu_read_flags(con) & CON_NBCON))) { + nbcon_context_release(ctxt); + return false; + } /* * The printk buffers are filled within an unsafe section. This @@ -878,6 +989,29 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) if (dropped && !is_extended) console_prepend_dropped(&pmsg, dropped); + /* + * If the previous owner was assigned the same record, this context + * has taken over ownership and is replaying the record. Prepend a + * message to let the user know the record is replayed. + */ + ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq)); + if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) { + console_prepend_replay(&pmsg); + } else { + /* + * Ensure this context is still the owner before trying to + * update @nbcon_prev_seq. Otherwise the value in @ulseq may + * not be from the previous owner and instead be some later + * value from the context that took over ownership. + */ + nbcon_state_read(con, &cur); + if (!nbcon_context_can_proceed(ctxt, &cur)) + return false; + + atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq, + __u64seq_to_ulseq(pmsg.seq)); + } + if (!nbcon_context_exit_unsafe(ctxt)) return false; @@ -886,22 +1020,27 @@ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt) goto update_con; /* Initialize the write context for driver callbacks. */ - wctxt->outbuf = &pmsg.pbufs->outbuf[0]; - wctxt->len = pmsg.outbuf_len; - nbcon_state_read(con, &cur); - wctxt->unsafe_takeover = cur.unsafe_takeover; + nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len); - if (con->write_atomic) { - done = con->write_atomic(con, wctxt); - } else { + if (use_atomic) + con->write_atomic(con, wctxt); + else + con->write_thread(con, wctxt); + + if (!wctxt->outbuf) { + /* + * Ownership was lost and reacquired by the driver. Handle it + * as if ownership was lost. + */ nbcon_context_release(ctxt); - WARN_ON_ONCE(1); - done = false; + return false; } - /* If not done, the emit was aborted. */ - if (!done) - return false; + /* + * Ownership may have been lost but _not_ reacquired by the driver. + * This case is detected and handled when entering unsafe to update + * dropped/seq values. + */ /* * Since any dropped message was successfully output, reset the @@ -928,18 +1067,626 @@ update_con: return nbcon_context_exit_unsafe(ctxt); } +/* + * nbcon_emit_one - Print one record for an nbcon console using the + * specified callback + * @wctxt: An initialized write context struct to use for this context + * @use_atomic: True if the write_atomic() callback is to be used + * + * Return: True, when a record has been printed and there are still + * pending records. The caller might want to continue flushing. + * + * False, when there is no pending record, or when the console + * context cannot be acquired, or the ownership has been lost. + * The caller should give up. Either the job is done, cannot be + * done, or will be handled by the owning context. + * + * This is an internal helper to handle the locking of the console before + * calling nbcon_emit_next_record(). + */ +static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); + struct console *con = ctxt->console; + unsigned long flags; + bool ret = false; + + if (!use_atomic) { + con->device_lock(con, &flags); + + /* + * Ensure this stays on the CPU to make handover and + * takeover possible. + */ + cant_migrate(); + } + + if (!nbcon_context_try_acquire(ctxt)) + goto out; + + /* + * nbcon_emit_next_record() returns false when the console was + * handed over or taken over. In both cases the context is no + * longer valid. + * + * The higher priority printing context takes over responsibility + * to print the pending records. + */ + if (!nbcon_emit_next_record(wctxt, use_atomic)) + goto out; + + nbcon_context_release(ctxt); + + ret = ctxt->backlog; +out: + if (!use_atomic) + con->device_unlock(con, flags); + return ret; +} + /** - * nbcon_alloc - Allocate buffers needed by the nbcon console - * @con: Console to allocate buffers for + * nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup + * @con: Console to operate on + * @ctxt: The nbcon context from nbcon_context_try_acquire() * - * Return: True on success. False otherwise and the console cannot - * be used. + * Return: True if the thread should shutdown or if the console is + * allowed to print and a record is available. False otherwise. * - * This is not part of nbcon_init() because buffer allocation must - * be performed earlier in the console registration process. + * After the thread wakes up, it must first check if it should shutdown before + * attempting any printing. + */ +static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt) +{ + bool ret = false; + short flags; + int cookie; + + if (kthread_should_stop()) + return true; + + cookie = console_srcu_read_lock(); + + flags = console_srcu_read_flags(con); + if (console_is_usable(con, flags, false)) { + /* Bring the sequence in @ctxt up to date */ + ctxt->seq = nbcon_seq_read(con); + + ret = prb_read_valid(prb, ctxt->seq, NULL); + } + + console_srcu_read_unlock(cookie); + return ret; +} + +/** + * nbcon_kthread_func - The printer thread function + * @__console: Console to operate on + * + * Return: 0 + */ +static int nbcon_kthread_func(void *__console) +{ + struct console *con = __console; + struct nbcon_write_context wctxt = { + .ctxt.console = con, + .ctxt.prio = NBCON_PRIO_NORMAL, + }; + struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); + short con_flags; + bool backlog; + int cookie; + +wait_for_event: + /* + * Guarantee this task is visible on the rcuwait before + * checking the wake condition. + * + * The full memory barrier within set_current_state() of + * ___rcuwait_wait_event() pairs with the full memory + * barrier within rcuwait_has_sleeper(). + * + * This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A. + */ + rcuwait_wait_event(&con->rcuwait, + nbcon_kthread_should_wakeup(con, ctxt), + TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */ + + do { + if (kthread_should_stop()) + return 0; + + backlog = false; + + /* + * Keep the srcu read lock around the entire operation so that + * synchronize_srcu() can guarantee that the kthread stopped + * or suspended printing. + */ + cookie = console_srcu_read_lock(); + + con_flags = console_srcu_read_flags(con); + + if (console_is_usable(con, con_flags, false)) + backlog = nbcon_emit_one(&wctxt, false); + + console_srcu_read_unlock(cookie); + + cond_resched(); + + } while (backlog); + + goto wait_for_event; +} + +/** + * nbcon_irq_work - irq work to wake console printer thread + * @irq_work: The irq work to operate on + */ +static void nbcon_irq_work(struct irq_work *irq_work) +{ + struct console *con = container_of(irq_work, struct console, irq_work); + + nbcon_kthread_wake(con); +} + +static inline bool rcuwait_has_sleeper(struct rcuwait *w) +{ + /* + * Guarantee any new records can be seen by tasks preparing to wait + * before this context checks if the rcuwait is empty. + * + * This full memory barrier pairs with the full memory barrier within + * set_current_state() of ___rcuwait_wait_event(), which is called + * after prepare_to_rcuwait() adds the waiter but before it has + * checked the wait condition. + * + * This pairs with nbcon_kthread_func:A. + */ + smp_mb(); /* LMM(rcuwait_has_sleeper:A) */ + return rcuwait_active(w); +} + +/** + * nbcon_kthreads_wake - Wake up printing threads using irq_work + */ +void nbcon_kthreads_wake(void) +{ + struct console *con; + int cookie; + + if (!printk_kthreads_running) + return; + + cookie = console_srcu_read_lock(); + for_each_console_srcu(con) { + if (!(console_srcu_read_flags(con) & CON_NBCON)) + continue; + + /* + * Only schedule irq_work if the printing thread is + * actively waiting. If not waiting, the thread will + * notice by itself that it has work to do. + */ + if (rcuwait_has_sleeper(&con->rcuwait)) + irq_work_queue(&con->irq_work); + } + console_srcu_read_unlock(cookie); +} + +/* + * nbcon_kthread_stop - Stop a console printer thread + * @con: Console to operate on + */ +void nbcon_kthread_stop(struct console *con) +{ + lockdep_assert_console_list_lock_held(); + + if (!con->kthread) + return; + + kthread_stop(con->kthread); + con->kthread = NULL; +} + +/** + * nbcon_kthread_create - Create a console printer thread + * @con: Console to operate on + * + * Return: True if the kthread was started or already exists. + * Otherwise false and @con must not be registered. + * + * This function is called when it will be expected that nbcon consoles are + * flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL + * will be no longer flushed by the legacy loop. This is why failure must + * be fatal for console registration. + * + * If @con was already registered and this function fails, @con must be + * unregistered before the global state variable @printk_kthreads_running + * can be set. + */ +bool nbcon_kthread_create(struct console *con) +{ + struct task_struct *kt; + + lockdep_assert_console_list_lock_held(); + + if (con->kthread) + return true; + + kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); + if (WARN_ON(IS_ERR(kt))) { + con_printk(KERN_ERR, con, "failed to start printing thread\n"); + return false; + } + + con->kthread = kt; + + /* + * It is important that console printing threads are scheduled + * shortly after a printk call and with generous runtime budgets. + */ + sched_set_normal(con->kthread, -20); + + return true; +} + +/* Track the nbcon emergency nesting per CPU. */ +static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); +static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; + +/** + * nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer + * + * Context: For reading, any context. For writing, any context which could + * not be migrated to another CPU. + * Return: Either a pointer to the per CPU emergency nesting counter of + * the current CPU or to the init data during early boot. + * + * The function is safe for reading per-CPU variables in any context because + * preemption is disabled if the current CPU is in the emergency state. See + * also nbcon_cpu_emergency_enter(). + */ +static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void) +{ + /* + * The value of __printk_percpu_data_ready gets set in normal + * context and before SMP initialization. As a result it could + * never change while inside an nbcon emergency section. + */ + if (!printk_percpu_data_ready()) + return &early_nbcon_pcpu_emergency_nesting; + + return raw_cpu_ptr(&nbcon_pcpu_emergency_nesting); +} + +/** + * nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon + * printing on the current CPU + * + * Context: Any context. + * Return: The nbcon_prio to use for acquiring an nbcon console in this + * context for printing. + * + * The function is safe for reading per-CPU data in any context because + * preemption is disabled if the current CPU is in the emergency or panic + * state. + */ +enum nbcon_prio nbcon_get_default_prio(void) +{ + unsigned int *cpu_emergency_nesting; + + if (this_cpu_in_panic()) + return NBCON_PRIO_PANIC; + + cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); + if (*cpu_emergency_nesting) + return NBCON_PRIO_EMERGENCY; + + return NBCON_PRIO_NORMAL; +} + +/** + * nbcon_legacy_emit_next_record - Print one record for an nbcon console + * in legacy contexts + * @con: The console to print on + * @handover: Will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding + * both the console_lock and the SRCU read lock. Otherwise it + * is set to false. + * @cookie: The cookie from the SRCU read lock. + * @use_atomic: Set true when called in an atomic or unknown context. + * It affects which nbcon callback will be used: write_atomic() + * or write_thread(). + * + * When false, the write_thread() callback is used and would be + * called in a preemtible context unless disabled by the + * device_lock. The legacy handover is not allowed in this mode. + * + * Context: Any context except NMI. + * Return: True, when a record has been printed and there are still + * pending records. The caller might want to continue flushing. + * + * False, when there is no pending record, or when the console + * context cannot be acquired, or the ownership has been lost. + * The caller should give up. Either the job is done, cannot be + * done, or will be handled by the owning context. + * + * This function is meant to be called by console_flush_all() to print records + * on nbcon consoles from legacy context (printing via console unlocking). + * Essentially it is the nbcon version of console_emit_next_record(). + */ +bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, + int cookie, bool use_atomic) +{ + struct nbcon_write_context wctxt = { }; + struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); + unsigned long flags; + bool progress; + + ctxt->console = con; + ctxt->prio = nbcon_get_default_prio(); + + if (use_atomic) { + /* + * In an atomic or unknown context, use the same procedure as + * in console_emit_next_record(). It allows to handover. + */ + printk_safe_enter_irqsave(flags); + console_lock_spinning_enable(); + stop_critical_timings(); + } + + progress = nbcon_emit_one(&wctxt, use_atomic); + + if (use_atomic) { + start_critical_timings(); + *handover = console_lock_spinning_disable_and_check(cookie); + printk_safe_exit_irqrestore(flags); + } else { + /* Non-atomic does not perform legacy spinning handovers. */ + *handover = false; + } + + return progress; +} + +/** + * __nbcon_atomic_flush_pending_con - Flush specified nbcon console using its + * write_atomic() callback + * @con: The nbcon console to flush + * @stop_seq: Flush up until this record + * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers + * + * Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on + * failure. + * + * Errors: + * + * -EPERM: Unable to acquire console ownership. + * + * -EAGAIN: Another context took over ownership while printing. + * + * -ENOENT: A record before @stop_seq is not available. + * + * If flushing up to @stop_seq was not successful, it only makes sense for the + * caller to try again when -EAGAIN was returned. When -EPERM is returned, + * this context is not allowed to acquire the console. When -ENOENT is + * returned, it cannot be expected that the unfinalized record will become + * available. + */ +static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, + bool allow_unsafe_takeover) +{ + struct nbcon_write_context wctxt = { }; + struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); + int err = 0; + + ctxt->console = con; + ctxt->spinwait_max_us = 2000; + ctxt->prio = nbcon_get_default_prio(); + ctxt->allow_unsafe_takeover = allow_unsafe_takeover; + + if (!nbcon_context_try_acquire(ctxt)) + return -EPERM; + + while (nbcon_seq_read(con) < stop_seq) { + /* + * nbcon_emit_next_record() returns false when the console was + * handed over or taken over. In both cases the context is no + * longer valid. + */ + if (!nbcon_emit_next_record(&wctxt, true)) + return -EAGAIN; + + if (!ctxt->backlog) { + /* Are there reserved but not yet finalized records? */ + if (nbcon_seq_read(con) < stop_seq) + err = -ENOENT; + break; + } + } + + nbcon_context_release(ctxt); + return err; +} + +/** + * nbcon_atomic_flush_pending_con - Flush specified nbcon console using its + * write_atomic() callback + * @con: The nbcon console to flush + * @stop_seq: Flush up until this record + * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers + * + * This will stop flushing before @stop_seq if another context has ownership. + * That context is then responsible for the flushing. Likewise, if new records + * are added while this context was flushing and there is no other context + * to handle the printing, this context must also flush those records. + */ +static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, + bool allow_unsafe_takeover) +{ + struct console_flush_type ft; + unsigned long flags; + int err; + +again: + /* + * Atomic flushing does not use console driver synchronization (i.e. + * it does not hold the port lock for uart consoles). Therefore IRQs + * must be disabled to avoid being interrupted and then calling into + * a driver that will deadlock trying to acquire console ownership. + */ + local_irq_save(flags); + + err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); + + local_irq_restore(flags); + + /* + * If there was a new owner (-EPERM, -EAGAIN), that context is + * responsible for completing. + * + * Do not wait for records not yet finalized (-ENOENT) to avoid a + * possible deadlock. They will either get flushed by the writer or + * eventually skipped on panic CPU. + */ + if (err) + return; + + /* + * If flushing was successful but more records are available, this + * context must flush those remaining records if the printer thread + * is not available do it. + */ + printk_get_console_flush_type(&ft); + if (!ft.nbcon_offload && + prb_read_valid(prb, nbcon_seq_read(con), NULL)) { + stop_seq = prb_next_reserve_seq(prb); + goto again; + } +} + +/** + * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their + * write_atomic() callback + * @stop_seq: Flush up until this record + * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers + */ +static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover) +{ + struct console *con; + int cookie; + + cookie = console_srcu_read_lock(); + for_each_console_srcu(con) { + short flags = console_srcu_read_flags(con); + + if (!(flags & CON_NBCON)) + continue; + + if (!console_is_usable(con, flags, true)) + continue; + + if (nbcon_seq_read(con) >= stop_seq) + continue; + + nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); + } + console_srcu_read_unlock(cookie); +} + +/** + * nbcon_atomic_flush_pending - Flush all nbcon consoles using their + * write_atomic() callback + * + * Flush the backlog up through the currently newest record. Any new + * records added while flushing will not be flushed if there is another + * context available to handle the flushing. This is to avoid one CPU + * printing unbounded because other CPUs continue to add records. + */ +void nbcon_atomic_flush_pending(void) +{ + __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false); +} + +/** + * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their + * write_atomic() callback and allowing unsafe hostile takeovers + * + * Flush the backlog up through the currently newest record. Unsafe hostile + * takeovers will be performed, if necessary. + */ +void nbcon_atomic_flush_unsafe(void) +{ + __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true); +} + +/** + * nbcon_cpu_emergency_enter - Enter an emergency section where printk() + * messages for that CPU are flushed directly + * + * Context: Any context. Disables preemption. + * + * When within an emergency section, printk() calls will attempt to flush any + * pending messages in the ringbuffer. + */ +void nbcon_cpu_emergency_enter(void) +{ + unsigned int *cpu_emergency_nesting; + + preempt_disable(); + + cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); + (*cpu_emergency_nesting)++; +} + +/** + * nbcon_cpu_emergency_exit - Exit an emergency section + * + * Context: Within an emergency section. Enables preemption. + */ +void nbcon_cpu_emergency_exit(void) +{ + unsigned int *cpu_emergency_nesting; + + cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); + + if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0)) + (*cpu_emergency_nesting)--; + + preempt_enable(); +} + +/** + * nbcon_alloc - Allocate and init the nbcon console specific data + * @con: Console to initialize + * + * Return: True if the console was fully allocated and initialized. + * Otherwise @con must not be registered. + * + * When allocation and init was successful, the console must be properly + * freed using nbcon_free() once it is no longer needed. */ bool nbcon_alloc(struct console *con) { + struct nbcon_state state = { }; + + /* The write_thread() callback is mandatory. */ + if (WARN_ON(!con->write_thread)) + return false; + + rcuwait_init(&con->rcuwait); + init_irq_work(&con->irq_work, nbcon_irq_work); + atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); + nbcon_state_set(con, &state); + + /* + * Initialize @nbcon_seq to the highest possible sequence number so + * that practically speaking it will have nothing to print until a + * desired initial sequence number has been set via nbcon_seq_force(). + */ + atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), ULSEQ_MAX(prb)); + if (con->flags & CON_BOOT) { /* * Boot console printing is synchronized with legacy console @@ -953,31 +1700,19 @@ bool nbcon_alloc(struct console *con) con_printk(KERN_ERR, con, "failed to allocate printing buffer\n"); return false; } + + if (printk_kthreads_running) { + if (!nbcon_kthread_create(con)) { + kfree(con->pbufs); + con->pbufs = NULL; + return false; + } + } } return true; } -/** - * nbcon_init - Initialize the nbcon console specific data - * @con: Console to initialize - * - * nbcon_alloc() *must* be called and succeed before this function - * is called. - * - * This function expects that the legacy @con->seq has been set. - */ -void nbcon_init(struct console *con) -{ - struct nbcon_state state = { }; - - /* nbcon_alloc() must have been called and successful! */ - BUG_ON(!con->pbufs); - - nbcon_seq_force(con, con->seq); - nbcon_state_set(con, &state); -} - /** * nbcon_free - Free and cleanup the nbcon console specific data * @con: Console to free/cleanup nbcon data @@ -986,6 +1721,9 @@ void nbcon_free(struct console *con) { struct nbcon_state state = { }; + if (printk_kthreads_running) + nbcon_kthread_stop(con); + nbcon_state_set(con, &state); /* Boot consoles share global printk buffers. */ @@ -994,3 +1732,85 @@ void nbcon_free(struct console *con) con->pbufs = NULL; } + +/** + * nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe + * section + * @con: The nbcon console to acquire + * + * Context: Under the locking mechanism implemented in + * @con->device_lock() including disabling migration. + * Return: True if the console was acquired. False otherwise. + * + * Console drivers will usually use their own internal synchronization + * mechasism to synchronize between console printing and non-printing + * activities (such as setting baud rates). However, nbcon console drivers + * supporting atomic consoles may also want to mark unsafe sections when + * performing non-printing activities in order to synchronize against their + * atomic_write() callback. + * + * This function acquires the nbcon console using priority NBCON_PRIO_NORMAL + * and marks it unsafe for handover/takeover. + */ +bool nbcon_device_try_acquire(struct console *con) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); + + cant_migrate(); + + memset(ctxt, 0, sizeof(*ctxt)); + ctxt->console = con; + ctxt->prio = NBCON_PRIO_NORMAL; + + if (!nbcon_context_try_acquire(ctxt)) + return false; + + if (!nbcon_context_enter_unsafe(ctxt)) + return false; + + return true; +} +EXPORT_SYMBOL_GPL(nbcon_device_try_acquire); + +/** + * nbcon_device_release - Exit unsafe section and release the nbcon console + * @con: The nbcon console acquired in nbcon_device_try_acquire() + */ +void nbcon_device_release(struct console *con) +{ + struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); + struct console_flush_type ft; + int cookie; + + if (!nbcon_context_exit_unsafe(ctxt)) + return; + + nbcon_context_release(ctxt); + + /* + * This context must flush any new records added while the console + * was locked if the printer thread is not available to do it. The + * console_srcu_read_lock must be taken to ensure the console is + * usable throughout flushing. + */ + cookie = console_srcu_read_lock(); + printk_get_console_flush_type(&ft); + if (console_is_usable(con, console_srcu_read_flags(con), true) && + !ft.nbcon_offload && + prb_read_valid(prb, nbcon_seq_read(con), NULL)) { + /* + * If nbcon_atomic flushing is not available, fallback to + * using the legacy loop. + */ + if (ft.nbcon_atomic) { + __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false); + } else if (ft.legacy_direct) { + if (console_trylock()) + console_unlock(); + } else if (ft.legacy_offload) { + printk_trigger_flush(); + } + } + console_srcu_read_unlock(cookie); +} +EXPORT_SYMBOL_GPL(nbcon_device_release); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index dc759b180fe2..b6f6d6ac51e1 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -284,6 +285,7 @@ EXPORT_SYMBOL(console_list_unlock); * Return: A cookie to pass to console_srcu_read_unlock(). */ int console_srcu_read_lock(void) + __acquires(&console_srcu) { return srcu_read_lock_nmisafe(&console_srcu); } @@ -297,6 +299,7 @@ EXPORT_SYMBOL(console_srcu_read_lock); * Counterpart to console_srcu_read_lock() */ void console_srcu_read_unlock(int cookie) + __releases(&console_srcu) { srcu_read_unlock_nmisafe(&console_srcu, cookie); } @@ -463,14 +466,43 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); +/* + * Specifies if a legacy console is registered. If legacy consoles are + * present, it is necessary to perform the console lock/unlock dance + * whenever console flushing should occur. + */ +bool have_legacy_console; + +/* + * Specifies if an nbcon console is registered. If nbcon consoles are present, + * synchronous printing of legacy consoles will not occur during panic until + * the backtrace has been stored to the ringbuffer. + */ +bool have_nbcon_console; + +/* + * Specifies if a boot console is registered. If boot consoles are present, + * nbcon consoles cannot print simultaneously and must be synchronized by + * the console lock. This is because boot consoles and nbcon consoles may + * have mapped the same hardware. + */ +bool have_boot_console; + +/* See printk_legacy_allow_panic_sync() for details. */ +bool legacy_allow_panic_sync; + #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); +static DECLARE_WAIT_QUEUE_HEAD(legacy_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; +/* True when _all_ printer threads are available for printing. */ +bool printk_kthreads_running; + struct latched_seq { seqcount_latch_t latch; u64 val[2]; @@ -1859,7 +1891,7 @@ static bool console_waiter; * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ -static void console_lock_spinning_enable(void) +void console_lock_spinning_enable(void) { /* * Do not use spinning in panic(). The panic CPU wants to keep the lock. @@ -1898,7 +1930,7 @@ lockdep: * * Return: 1 if the lock rights were passed, 0 otherwise. */ -static int console_lock_spinning_disable_and_check(int cookie) +int console_lock_spinning_disable_and_check(int cookie) { int waiter; @@ -2315,12 +2347,30 @@ out: return ret; } +/* + * This acts as a one-way switch to allow legacy consoles to print from + * the printk() caller context on a panic CPU. It also attempts to flush + * the legacy consoles in this context. + */ +void printk_legacy_allow_panic_sync(void) +{ + struct console_flush_type ft; + + legacy_allow_panic_sync = true; + + printk_get_console_flush_type(&ft); + if (ft.legacy_direct) { + if (console_trylock()) + console_unlock(); + } +} + asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { + struct console_flush_type ft; int printed_len; - bool in_sched = false; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) @@ -2334,17 +2384,26 @@ asmlinkage int vprintk_emit(int facility, int level, if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0; + printk_get_console_flush_type(&ft); + + /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; - in_sched = true; + ft.legacy_offload |= ft.legacy_direct; + ft.legacy_direct = false; } printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); - /* If called from the scheduler, we can not call up(). */ - if (!in_sched) { + if (ft.nbcon_atomic) + nbcon_atomic_flush_pending(); + + if (ft.nbcon_offload) + nbcon_kthreads_wake(); + + if (ft.legacy_direct) { /* * The caller may be holding system-critical or * timing-sensitive locks. Disable preemption during @@ -2364,7 +2423,7 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } - if (in_sched) + if (ft.legacy_offload) defer_console_output(); else wake_up_klogd(); @@ -2693,6 +2752,7 @@ void suspend_console(void) void resume_console(void) { + struct console_flush_type ft; struct console *con; if (!console_suspend_enabled) @@ -2710,6 +2770,12 @@ void resume_console(void) */ synchronize_srcu(&console_srcu); + printk_get_console_flush_type(&ft); + if (ft.nbcon_offload) + nbcon_kthreads_wake(); + if (ft.legacy_offload) + defer_console_output(); + pr_flush(1000, true); } @@ -2730,10 +2796,16 @@ static int console_cpu_notify(unsigned int cpu) if (flag) return 0; + struct console_flush_type ft; + if (!cpuhp_tasks_frozen) { - /* If trylock fails, someone else is doing the printing */ - if (console_trylock()) - console_unlock(); + printk_get_console_flush_type(&ft); + if (ft.nbcon_atomic) + nbcon_atomic_flush_pending(); + if (ft.legacy_direct) { + if (console_trylock()) + console_unlock(); + } } return 0; } @@ -2787,36 +2859,6 @@ int is_console_locked(void) } EXPORT_SYMBOL(is_console_locked); -/* - * Check if the given console is currently capable and allowed to print - * records. - * - * Requires the console_srcu_read_lock. - */ -static inline bool console_is_usable(struct console *con) -{ - short flags = console_srcu_read_flags(con); - - if (!(flags & CON_ENABLED)) - return false; - - if ((flags & CON_SUSPENDED)) - return false; - - if (!con->write) - return false; - - /* - * Console drivers may assume that per-cpu resources have been - * allocated. So unless they're explicitly marked as being able to - * cope (CON_ANYTIME) don't call them until this CPU is officially up. - */ - if (!cpu_online(raw_smp_processor_id()) && !(flags & CON_ANYTIME)) - return false; - - return true; -} - static void __console_unlock(void) { console_locked = 0; @@ -2826,30 +2868,31 @@ static void __console_unlock(void) #ifdef CONFIG_PRINTK /* - * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". This - * is achieved by shifting the existing message over and inserting the dropped - * message. + * Prepend the message in @pmsg->pbufs->outbuf. This is achieved by shifting + * the existing message over and inserting the scratchbuf message. * - * @pmsg is the printk message to prepend. + * @pmsg is the original printk message. + * @fmt is the printf format of the message which will prepend the existing one. * - * @dropped is the dropped count to report in the dropped message. - * - * If the message text in @pmsg->pbufs->outbuf does not have enough space for - * the dropped message, the message text will be sufficiently truncated. + * If there is not enough space in @pmsg->pbufs->outbuf, the existing + * message text will be sufficiently truncated. * * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated. */ -void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) +__printf(2, 3) +static void console_prepend_message(struct printk_message *pmsg, const char *fmt, ...) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; + va_list args; size_t len; - len = scnprintf(scratchbuf, scratchbuf_sz, - "** %lu printk messages dropped **\n", dropped); + va_start(args, fmt); + len = vscnprintf(scratchbuf, scratchbuf_sz, fmt, args); + va_end(args); /* * Make sure outbuf is sufficiently large before prepending. @@ -2871,6 +2914,30 @@ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) pmsg->outbuf_len += len; } +/* + * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". + * @pmsg->outbuf_len is updated appropriately. + * + * @pmsg is the printk message to prepend. + * + * @dropped is the dropped count to report in the dropped message. + */ +void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) +{ + console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped); +} + +/* + * Prepend the message in @pmsg->pbufs->outbuf with a "replay message". + * @pmsg->outbuf_len is updated appropriately. + * + * @pmsg is the printk message to prepend. + */ +void console_prepend_replay(struct printk_message *pmsg) +{ + console_prepend_message(pmsg, "** replaying previous printk message **\n"); +} + /* * Read and format the specified record (or a later record if the specified * record is not available). @@ -2936,6 +3003,34 @@ out: return true; } +/* + * Legacy console printing from printk() caller context does not respect + * raw_spinlock/spinlock nesting. For !PREEMPT_RT the lockdep warning is a + * false positive. For PREEMPT_RT the false positive condition does not + * occur. + * + * This map is used to temporarily establish LD_WAIT_SLEEP context for the + * console write() callback when legacy printing to avoid false positive + * lockdep complaints, thus allowing lockdep to continue to function for + * real issues. + */ +#ifdef CONFIG_PREEMPT_RT +static inline void printk_legacy_allow_spinlock_enter(void) { } +static inline void printk_legacy_allow_spinlock_exit(void) { } +#else +static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_SLEEP); + +static inline void printk_legacy_allow_spinlock_enter(void) +{ + lock_map_acquire_try(&printk_legacy_map); +} + +static inline void printk_legacy_allow_spinlock_exit(void) +{ + lock_map_release(&printk_legacy_map); +} +#endif /* CONFIG_PREEMPT_RT */ + /* * Used as the printk buffers for non-panic, serialized console printing. * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles. @@ -2985,31 +3080,46 @@ static bool console_emit_next_record(struct console *con, bool *handover, int co con->dropped = 0; } - /* - * While actively printing out messages, if another printk() - * were to occur on another CPU, it may wait for this one to - * finish. This task can not be preempted if there is a - * waiter waiting to take over. - * - * Interrupts are disabled because the hand over to a waiter - * must not be interrupted until the hand over is completed - * (@console_waiter is cleared). - */ - printk_safe_enter_irqsave(flags); - console_lock_spinning_enable(); - - /* Do not trace print latency. */ - stop_critical_timings(); - /* Write everything out to the hardware. */ - con->write(con, outbuf, pmsg.outbuf_len); - start_critical_timings(); + if (force_legacy_kthread() && !panic_in_progress()) { + /* + * With forced threading this function is in a task context + * (either legacy kthread or get_init_console_seq()). There + * is no need for concern about printk reentrance, handovers, + * or lockdep complaints. + */ - con->seq = pmsg.seq + 1; + con->write(con, outbuf, pmsg.outbuf_len); + con->seq = pmsg.seq + 1; + } else { + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to + * finish. This task can not be preempted if there is a + * waiter waiting to take over. + * + * Interrupts are disabled because the hand over to a waiter + * must not be interrupted until the hand over is completed + * (@console_waiter is cleared). + */ + printk_safe_enter_irqsave(flags); + console_lock_spinning_enable(); - *handover = console_lock_spinning_disable_and_check(cookie); - printk_safe_exit_irqrestore(flags); + /* Do not trace print latency. */ + stop_critical_timings(); + + printk_legacy_allow_spinlock_enter(); + con->write(con, outbuf, pmsg.outbuf_len); + printk_legacy_allow_spinlock_exit(); + + start_critical_timings(); + + con->seq = pmsg.seq + 1; + + *handover = console_lock_spinning_disable_and_check(cookie); + printk_safe_exit_irqrestore(flags); + } skip: return true; } @@ -3022,6 +3132,8 @@ static bool console_emit_next_record(struct console *con, bool *handover, int co return false; } +static inline void printk_kthreads_check_locked(void) { } + #endif /* CONFIG_PRINTK */ /* @@ -3049,6 +3161,7 @@ static bool console_emit_next_record(struct console *con, bool *handover, int co */ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) { + struct console_flush_type ft; bool any_usable = false; struct console *con; bool any_progress; @@ -3060,15 +3173,34 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove do { any_progress = false; + printk_get_console_flush_type(&ft); + cookie = console_srcu_read_lock(); for_each_console_srcu(con) { + short flags = console_srcu_read_flags(con); + u64 printk_seq; bool progress; - if (!console_is_usable(con)) + /* + * console_flush_all() is only responsible for nbcon + * consoles when the nbcon consoles cannot print via + * their atomic or threaded flushing. + */ + if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) + continue; + + if (!console_is_usable(con, flags, !do_cond_resched)) continue; any_usable = true; - progress = console_emit_next_record(con, handover, cookie); + if (flags & CON_NBCON) { + progress = nbcon_legacy_emit_next_record(con, handover, cookie, + !do_cond_resched); + printk_seq = nbcon_seq_read(con); + } else { + progress = console_emit_next_record(con, handover, cookie); + printk_seq = con->seq; + } /* * If a handover has occurred, the SRCU read lock @@ -3078,8 +3210,8 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove return false; /* Track the next of the highest seq flushed. */ - if (con->seq > *next_seq) - *next_seq = con->seq; + if (printk_seq > *next_seq) + *next_seq = printk_seq; if (!progress) continue; @@ -3102,19 +3234,7 @@ abandon: return false; } -/** - * console_unlock - unblock the console subsystem from printing - * - * Releases the console_lock which the caller holds to block printing of - * the console subsystem. - * - * While the console_lock was held, console output may have been buffered - * by printk(). If this is the case, console_unlock(); emits - * the output prior to releasing the lock. - * - * console_unlock(); may be called from any context. - */ -void console_unlock(void) +static void __console_flush_and_unlock(void) { bool do_cond_resched; bool handover; @@ -3158,6 +3278,29 @@ void console_unlock(void) */ } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); } + +/** + * console_unlock - unblock the legacy console subsystem from printing + * + * Releases the console_lock which the caller holds to block printing of + * the legacy console subsystem. + * + * While the console_lock was held, console output may have been buffered + * by printk(). If this is the case, console_unlock() emits the output on + * legacy consoles prior to releasing the lock. + * + * console_unlock(); may be called from any context. + */ +void console_unlock(void) +{ + struct console_flush_type ft; + + printk_get_console_flush_type(&ft); + if (ft.legacy_direct) + __console_flush_and_unlock(); + else + __console_unlock(); +} EXPORT_SYMBOL(console_unlock); /** @@ -3280,6 +3423,7 @@ static void __console_rewind_all(void) */ void console_flush_on_panic(enum con_flush_mode mode) { + struct console_flush_type ft; bool handover; u64 next_seq; @@ -3303,7 +3447,13 @@ void console_flush_on_panic(enum con_flush_mode mode) if (mode == CONSOLE_REPLAY_ALL) __console_rewind_all(); - console_flush_all(false, &next_seq, &handover); + printk_get_console_flush_type(&ft); + if (ft.nbcon_atomic) + nbcon_atomic_flush_pending(); + + /* Flush legacy consoles once allowed, even when dangerous. */ + if (legacy_allow_panic_sync) + console_flush_all(false, &next_seq, &handover); } /* @@ -3360,13 +3510,236 @@ EXPORT_SYMBOL(console_stop); void console_start(struct console *console) { + struct console_flush_type ft; + bool is_nbcon; + console_list_lock(); console_srcu_write_flags(console, console->flags | CON_ENABLED); + is_nbcon = console->flags & CON_NBCON; console_list_unlock(); + + /* + * Ensure that all SRCU list walks have completed. The related + * printing context must be able to see it is enabled so that + * it is guaranteed to wake up and resume printing. + */ + synchronize_srcu(&console_srcu); + + printk_get_console_flush_type(&ft); + if (is_nbcon && ft.nbcon_offload) + nbcon_kthread_wake(console); + else if (ft.legacy_offload) + defer_console_output(); + __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); +#ifdef CONFIG_PRINTK +static int unregister_console_locked(struct console *console); + +/* True when system boot is far enough to create printer threads. */ +static bool printk_kthreads_ready __ro_after_init; + +static struct task_struct *printk_legacy_kthread; + +static bool legacy_kthread_should_wakeup(void) +{ + struct console_flush_type ft; + struct console *con; + bool ret = false; + int cookie; + + if (kthread_should_stop()) + return true; + + printk_get_console_flush_type(&ft); + + cookie = console_srcu_read_lock(); + for_each_console_srcu(con) { + short flags = console_srcu_read_flags(con); + u64 printk_seq; + + /* + * The legacy printer thread is only responsible for nbcon + * consoles when the nbcon consoles cannot print via their + * atomic or threaded flushing. + */ + if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) + continue; + + if (!console_is_usable(con, flags, false)) + continue; + + if (flags & CON_NBCON) { + printk_seq = nbcon_seq_read(con); + } else { + /* + * It is safe to read @seq because only this + * thread context updates @seq. + */ + printk_seq = con->seq; + } + + if (prb_read_valid(prb, printk_seq, NULL)) { + ret = true; + break; + } + } + console_srcu_read_unlock(cookie); + + return ret; +} + +static int legacy_kthread_func(void *unused) +{ + for (;;) { + wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup()); + + if (kthread_should_stop()) + break; + + console_lock(); + __console_flush_and_unlock(); + } + + return 0; +} + +static bool legacy_kthread_create(void) +{ + struct task_struct *kt; + + lockdep_assert_console_list_lock_held(); + + kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); + if (WARN_ON(IS_ERR(kt))) { + pr_err("failed to start legacy printing thread\n"); + return false; + } + + printk_legacy_kthread = kt; + + /* + * It is important that console printing threads are scheduled + * shortly after a printk call and with generous runtime budgets. + */ + sched_set_normal(printk_legacy_kthread, -20); + + return true; +} + +/** + * printk_kthreads_shutdown - shutdown all threaded printers + * + * On system shutdown all threaded printers are stopped. This allows printk + * to transition back to atomic printing, thus providing a robust mechanism + * for the final shutdown/reboot messages to be output. + */ +static void printk_kthreads_shutdown(void) +{ + struct console *con; + + console_list_lock(); + if (printk_kthreads_running) { + printk_kthreads_running = false; + + for_each_console(con) { + if (con->flags & CON_NBCON) + nbcon_kthread_stop(con); + } + + /* + * The threads may have been stopped while printing a + * backlog. Flush any records left over. + */ + nbcon_atomic_flush_pending(); + } + console_list_unlock(); +} + +static struct syscore_ops printk_syscore_ops = { + .shutdown = printk_kthreads_shutdown, +}; + +/* + * If appropriate, start nbcon kthreads and set @printk_kthreads_running. + * If any kthreads fail to start, those consoles are unregistered. + * + * Must be called under console_list_lock(). + */ +static void printk_kthreads_check_locked(void) +{ + struct hlist_node *tmp; + struct console *con; + + lockdep_assert_console_list_lock_held(); + + if (!printk_kthreads_ready) + return; + + if (have_legacy_console || have_boot_console) { + if (!printk_legacy_kthread && + force_legacy_kthread() && + !legacy_kthread_create()) { + /* + * All legacy consoles must be unregistered. If there + * are any nbcon consoles, they will set up their own + * kthread. + */ + hlist_for_each_entry_safe(con, tmp, &console_list, node) { + if (con->flags & CON_NBCON) + continue; + + unregister_console_locked(con); + } + } + } else if (printk_legacy_kthread) { + kthread_stop(printk_legacy_kthread); + printk_legacy_kthread = NULL; + } + + /* + * Printer threads cannot be started as long as any boot console is + * registered because there is no way to synchronize the hardware + * registers between boot console code and regular console code. + * It can only be known that there will be no new boot consoles when + * an nbcon console is registered. + */ + if (have_boot_console || !have_nbcon_console) { + /* Clear flag in case all nbcon consoles unregistered. */ + printk_kthreads_running = false; + return; + } + + if (printk_kthreads_running) + return; + + hlist_for_each_entry_safe(con, tmp, &console_list, node) { + if (!(con->flags & CON_NBCON)) + continue; + + if (!nbcon_kthread_create(con)) + unregister_console_locked(con); + } + + printk_kthreads_running = true; +} + +static int __init printk_set_kthreads_ready(void) +{ + register_syscore_ops(&printk_syscore_ops); + + console_list_lock(); + printk_kthreads_ready = true; + printk_kthreads_check_locked(); + console_list_unlock(); + + return 0; +} +early_initcall(printk_set_kthreads_ready); +#endif /* CONFIG_PRINTK */ + static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) @@ -3468,19 +3841,21 @@ static void try_enable_default_console(struct console *newcon) newcon->flags |= CON_CONSDEV; } -static void console_init_seq(struct console *newcon, bool bootcon_registered) +/* Return the starting sequence number for a newly registered console. */ +static u64 get_init_console_seq(struct console *newcon, bool bootcon_registered) { struct console *con; bool handover; + u64 init_seq; if (newcon->flags & (CON_PRINTBUFFER | CON_BOOT)) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); - newcon->seq = syslog_seq; + init_seq = syslog_seq; mutex_unlock(&syslog_lock); } else { /* Begin with next message added to ringbuffer. */ - newcon->seq = prb_next_seq(prb); + init_seq = prb_next_seq(prb); /* * If any enabled boot consoles are due to be unregistered @@ -3501,7 +3876,7 @@ static void console_init_seq(struct console *newcon, bool bootcon_registered) * Flush all consoles and set the console to start at * the next unprinted sequence number. */ - if (!console_flush_all(true, &newcon->seq, &handover)) { + if (!console_flush_all(true, &init_seq, &handover)) { /* * Flushing failed. Just choose the lowest * sequence of the enabled boot consoles. @@ -3514,19 +3889,30 @@ static void console_init_seq(struct console *newcon, bool bootcon_registered) if (handover) console_lock(); - newcon->seq = prb_next_seq(prb); + init_seq = prb_next_seq(prb); for_each_console(con) { - if ((con->flags & CON_BOOT) && - (con->flags & CON_ENABLED) && - con->seq < newcon->seq) { - newcon->seq = con->seq; + u64 seq; + + if (!(con->flags & CON_BOOT) || + !(con->flags & CON_ENABLED)) { + continue; } + + if (con->flags & CON_NBCON) + seq = nbcon_seq_read(con); + else + seq = con->seq; + + if (seq < init_seq) + init_seq = seq; } } console_unlock(); } } + + return init_seq; } #define console_first() \ @@ -3555,9 +3941,12 @@ static int unregister_console_locked(struct console *console); */ void register_console(struct console *newcon) { - struct console *con; + bool use_device_lock = (newcon->flags & CON_NBCON) && newcon->write_atomic; bool bootcon_registered = false; bool realcon_registered = false; + struct console *con; + unsigned long flags; + u64 init_seq; int err; console_list_lock(); @@ -3635,10 +4024,31 @@ void register_console(struct console *newcon) } newcon->dropped = 0; - console_init_seq(newcon, bootcon_registered); + init_seq = get_init_console_seq(newcon, bootcon_registered); - if (newcon->flags & CON_NBCON) - nbcon_init(newcon); + if (newcon->flags & CON_NBCON) { + have_nbcon_console = true; + nbcon_seq_force(newcon, init_seq); + } else { + have_legacy_console = true; + newcon->seq = init_seq; + } + + if (newcon->flags & CON_BOOT) + have_boot_console = true; + + /* + * If another context is actively using the hardware of this new + * console, it will not be aware of the nbcon synchronization. This + * is a risk that two contexts could access the hardware + * simultaneously if this new console is used for atomic printing + * and the other context is still using the hardware. + * + * Use the driver synchronization to ensure that the hardware is not + * in use while this new console transitions to being registered. + */ + if (use_device_lock) + newcon->device_lock(newcon, &flags); /* * Put this console in the list - keep the @@ -3664,6 +4074,10 @@ void register_console(struct console *newcon) * register_console() completes. */ + /* This new console is now registered. */ + if (use_device_lock) + newcon->device_unlock(newcon, flags); + console_sysfs_notify(); /* @@ -3684,6 +4098,9 @@ void register_console(struct console *newcon) unregister_console_locked(con); } } + + /* Changed console list, may require printer threads to start/stop. */ + printk_kthreads_check_locked(); unlock: console_list_unlock(); } @@ -3692,6 +4109,12 @@ EXPORT_SYMBOL(register_console); /* Must be called under console_list_lock(). */ static int unregister_console_locked(struct console *console) { + bool use_device_lock = (console->flags & CON_NBCON) && console->write_atomic; + bool found_legacy_con = false; + bool found_nbcon_con = false; + bool found_boot_con = false; + unsigned long flags; + struct console *c; int res; lockdep_assert_console_list_lock_held(); @@ -3704,14 +4127,29 @@ static int unregister_console_locked(struct console *console) if (res > 0) return 0; + if (!console_is_registered_locked(console)) + res = -ENODEV; + else if (console_is_usable(console, console->flags, true)) + __pr_flush(console, 1000, true); + /* Disable it unconditionally */ console_srcu_write_flags(console, console->flags & ~CON_ENABLED); - if (!console_is_registered_locked(console)) - return -ENODEV; + if (res < 0) + return res; + + /* + * Use the driver synchronization to ensure that the hardware is not + * in use while this console transitions to being unregistered. + */ + if (use_device_lock) + console->device_lock(console, &flags); hlist_del_init_rcu(&console->node); + if (use_device_lock) + console->device_unlock(console, flags); + /* * * If this isn't the last console and it has CON_CONSDEV set, we @@ -3739,6 +4177,29 @@ static int unregister_console_locked(struct console *console) if (console->exit) res = console->exit(console); + /* + * With this console gone, the global flags tracking registered + * console types may have changed. Update them. + */ + for_each_console(c) { + if (c->flags & CON_BOOT) + found_boot_con = true; + + if (c->flags & CON_NBCON) + found_nbcon_con = true; + else + found_legacy_con = true; + } + if (!found_boot_con) + have_boot_console = found_boot_con; + if (!found_legacy_con) + have_legacy_console = found_legacy_con; + if (!found_nbcon_con) + have_nbcon_console = found_nbcon_con; + + /* Changed console list, may require printer threads to start/stop. */ + printk_kthreads_check_locked(); + return res; } @@ -3885,6 +4346,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre { unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms); unsigned long remaining_jiffies = timeout_jiffies; + struct console_flush_type ft; struct console *c; u64 last_diff = 0; u64 printk_seq; @@ -3893,13 +4355,22 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre u64 diff; u64 seq; + /* Sorry, pr_flush() will not work this early. */ + if (system_state < SYSTEM_SCHEDULING) + return false; + might_sleep(); seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ - console_lock(); - console_unlock(); + printk_get_console_flush_type(&ft); + if (ft.nbcon_atomic) + nbcon_atomic_flush_pending(); + if (ft.legacy_direct) { + console_lock(); + console_unlock(); + } for (;;) { unsigned long begin_jiffies; @@ -3912,6 +4383,12 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre * console->seq. Releasing console_lock flushes more * records in case @seq is still not printed on all * usable consoles. + * + * Holding the console_lock is not necessary if there + * are no legacy or boot consoles. However, such a + * console could register at any time. Always hold the + * console_lock as a precaution rather than + * synchronizing against register_console(). */ console_lock(); @@ -3927,8 +4404,10 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre * that they make forward progress, so only increment * @diff for usable consoles. */ - if (!console_is_usable(c)) + if (!console_is_usable(c, flags, true) && + !console_is_usable(c, flags, false)) { continue; + } if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(c); @@ -3996,9 +4475,13 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) int pending = this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { - /* If trylock fails, someone else is doing the printing */ - if (console_trylock()) - console_unlock(); + if (force_legacy_kthread()) { + if (printk_legacy_kthread) + wake_up_interruptible(&legacy_wait); + } else { + if (console_trylock()) + console_unlock(); + } } if (pending & PRINTK_PENDING_WAKEUP) @@ -4405,8 +4888,17 @@ EXPORT_SYMBOL_GPL(kmsg_dump_rewind); */ void console_try_replay_all(void) { + struct console_flush_type ft; + + printk_get_console_flush_type(&ft); if (console_trylock()) { __console_rewind_all(); + if (ft.nbcon_atomic) + nbcon_atomic_flush_pending(); + if (ft.nbcon_offload) + nbcon_kthreads_wake(); + if (ft.legacy_offload) + defer_console_output(); /* Consoles are flushed as part of console_unlock(). */ console_unlock(); } diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h index 52626d0f1fa3..4ef81349d9fb 100644 --- a/kernel/printk/printk_ringbuffer.h +++ b/kernel/printk/printk_ringbuffer.h @@ -4,7 +4,10 @@ #define _KERNEL_PRINTK_RINGBUFFER_H #include +#include #include +#include +#include /* * Meta information about each stored message. @@ -120,7 +123,7 @@ enum desc_state { #define _DATA_SIZE(sz_bits) (1UL << (sz_bits)) #define _DESCS_COUNT(ct_bits) (1U << (ct_bits)) -#define DESC_SV_BITS (sizeof(unsigned long) * 8) +#define DESC_SV_BITS BITS_PER_LONG #define DESC_FLAGS_SHIFT (DESC_SV_BITS - 2) #define DESC_FLAGS_MASK (3UL << DESC_FLAGS_SHIFT) #define DESC_STATE(sv) (3UL & (sv >> DESC_FLAGS_SHIFT)) @@ -401,10 +404,12 @@ u64 prb_next_reserve_seq(struct printk_ringbuffer *rb); #define __u64seq_to_ulseq(u64seq) (u64seq) #define __ulseq_to_u64seq(rb, ulseq) (ulseq) +#define ULSEQ_MAX(rb) (-1) #else /* CONFIG_64BIT */ #define __u64seq_to_ulseq(u64seq) ((u32)u64seq) +#define ULSEQ_MAX(rb) __u64seq_to_ulseq(prb_first_seq(rb) + 0x80000000UL) static inline u64 __ulseq_to_u64seq(struct printk_ringbuffer *rb, u32 ulseq) { diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 6d10927a07d8..2b35a9d3919d 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -26,6 +26,29 @@ void __printk_safe_exit(void) this_cpu_dec(printk_context); } +void __printk_deferred_enter(void) +{ + cant_migrate(); + __printk_safe_enter(); +} + +void __printk_deferred_exit(void) +{ + cant_migrate(); + __printk_safe_exit(); +} + +bool is_printk_legacy_deferred(void) +{ + /* + * The per-CPU variable @printk_context can be read safely in any + * context. CPU migration is always disabled when set. + */ + return (force_legacy_kthread() || + this_cpu_read(printk_context) || + in_nmi()); +} + asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB @@ -38,7 +61,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ - if (this_cpu_read(printk_context) || in_nmi()) + if (is_printk_legacy_deferred()) return vprintk_deferred(fmt, args); /* No obstacles. */ diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 4402d6f5f857..b3b3ce34df63 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -105,7 +105,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head) } /* Invoke the RCU callbacks whose grace period has elapsed. */ -static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) +static __latent_entropy void rcu_process_callbacks(void) { struct rcu_head *next, *list; unsigned long flags; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e641cc681901..93bd665637c0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2855,7 +2855,7 @@ static __latent_entropy void rcu_core(void) queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work); } -static void rcu_core_si(struct softirq_action *h) +static void rcu_core_si(void) { rcu_core(); } diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 4acd29d16fdb..f6b35a0585a8 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -7,6 +7,7 @@ * Authors: Paul E. McKenney */ +#include #include static void rcu_exp_handler(void *unused); @@ -590,6 +591,9 @@ static void synchronize_rcu_expedited_wait(void) return; if (rcu_stall_is_suppressed()) continue; + + nbcon_cpu_emergency_enter(); + j = jiffies; rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_EXP, (void *)(j - jiffies_start)); trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall")); @@ -643,6 +647,9 @@ static void synchronize_rcu_expedited_wait(void) rcu_exp_print_detail_task_stall_rnp(rnp); } jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3; + + nbcon_cpu_emergency_exit(); + panic_on_rcu_stall(); } } diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 4b0e9d7c4c68..b3a6943127bc 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -7,6 +7,7 @@ * Author: Paul E. McKenney */ +#include #include #include @@ -605,6 +606,8 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) if (rcu_stall_is_suppressed()) return; + nbcon_cpu_emergency_enter(); + /* * OK, time to rat on our buddy... * See Documentation/RCU/stallwarn.rst for info on how to debug @@ -657,6 +660,8 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); + nbcon_cpu_emergency_exit(); + panic_on_rcu_stall(); rcu_force_quiescent_state(); /* Kick them all. */ @@ -677,6 +682,8 @@ static void print_cpu_stall(unsigned long gps) if (rcu_stall_is_suppressed()) return; + nbcon_cpu_emergency_enter(); + /* * OK, time to rat on ourselves... * See Documentation/RCU/stallwarn.rst for info on how to debug @@ -706,6 +713,8 @@ static void print_cpu_stall(unsigned long gps) jiffies + 3 * rcu_jiffies_till_stall_check() + 3); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + nbcon_cpu_emergency_exit(); + panic_on_rcu_stall(); /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index daf616bdd643..c2f51d94582e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -12606,7 +12606,7 @@ out: * - indirectly from a remote scheduler_tick() for NOHZ idle balancing * through the SMP cross-call nohz_csd_func() */ -static __latent_entropy void sched_balance_softirq(struct softirq_action *h) +static __latent_entropy void sched_balance_softirq(void) { struct rq *this_rq = this_rq(); enum cpu_idle_type idle = this_rq->idle_balance; diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 244790341969..cde0017b45ac 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -406,6 +406,14 @@ static void __setscheduler_params(struct task_struct *p, else if (fair_policy(policy)) p->static_prio = NICE_TO_PRIO(attr->sched_nice); + /* rt-policy tasks do not have a timerslack */ + if (task_is_realtime(p)) { + p->timer_slack_ns = 0; + } else if (p->timer_slack_ns == 0) { + /* when switching back to non-rt policy, restore timerslack */ + p->timer_slack_ns = p->default_timer_slack_ns; + } + /* * __sched_setscheduler() ensures attr->sched_priority == 0 when * !rt_policy. Always setting this ensures that things like diff --git a/kernel/signal.c b/kernel/signal.c index 60c737e423a1..6f3a5aa39b09 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -618,20 +618,18 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, } /* - * Dequeue a signal and return the element to the caller, which is - * expected to free it. - * - * All callers have to hold the siglock. + * Try to dequeue a signal. If a deliverable signal is found fill in the + * caller provided siginfo and return the signal number. Otherwise return + * 0. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, - kernel_siginfo_t *info, enum pid_type *type) +int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) { + struct task_struct *tsk = current; bool resched_timer = false; int signr; - /* We only dequeue private signals from ourselves, we don't let - * signalfd steal them - */ + lockdep_assert_held(&tsk->sighand->siglock); + *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { @@ -1940,10 +1938,11 @@ struct sigqueue *sigqueue_alloc(void) void sigqueue_free(struct sigqueue *q) { - unsigned long flags; spinlock_t *lock = ¤t->sighand->siglock; + unsigned long flags; - BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); + if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) + return; /* * We must hold ->siglock while testing q->list * to serialize with collect_signal() or with @@ -1971,7 +1970,10 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) unsigned long flags; int ret, result; - BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); + if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) + return 0; + if (WARN_ON_ONCE(q->info.si_code != SI_TIMER)) + return 0; ret = -1; rcu_read_lock(); @@ -2006,7 +2008,6 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) * If an SI_TIMER entry is already queue just increment * the overrun count. */ - BUG_ON(q->info.si_code != SI_TIMER); q->info.si_overrun++; result = TRACE_SIGNAL_ALREADY_PENDING; goto out; @@ -2793,8 +2794,7 @@ relock: type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) - signr = dequeue_signal(current, ¤t->blocked, - &ksig->info, &type); + signr = dequeue_signal(¤t->blocked, &ksig->info, &type); if (!signr) break; /* will return 0 */ @@ -3648,7 +3648,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); - sig = dequeue_signal(tsk, &mask, info, &type); + sig = dequeue_signal(&mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested @@ -3667,7 +3667,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); - sig = dequeue_signal(tsk, &mask, info, &type); + sig = dequeue_signal(&mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); diff --git a/kernel/softirq.c b/kernel/softirq.c index 4f5be1c4b0fb..8371b7c4b517 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -554,7 +554,7 @@ restart: kstat_incr_softirqs_this_cpu(vec_nr); trace_softirq_entry(vec_nr); - h->action(h); + h->action(); trace_softirq_exit(vec_nr); if (unlikely(prev_count != preempt_count())) { pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", @@ -703,7 +703,7 @@ void __raise_softirq_irqoff(unsigned int nr) or_softirq_pending(1UL << nr); } -void open_softirq(int nr, void (*action)(struct softirq_action *)) +void open_softirq(int nr, void (*action)(void)) { softirq_vec[nr].action = action; } @@ -763,8 +763,7 @@ static bool tasklet_clear_sched(struct tasklet_struct *t) return false; } -static void tasklet_action_common(struct softirq_action *a, - struct tasklet_head *tl_head, +static void tasklet_action_common(struct tasklet_head *tl_head, unsigned int softirq_nr) { struct tasklet_struct *list; @@ -808,16 +807,16 @@ static void tasklet_action_common(struct softirq_action *a, } } -static __latent_entropy void tasklet_action(struct softirq_action *a) +static __latent_entropy void tasklet_action(void) { workqueue_softirq_action(false); - tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); + tasklet_action_common(this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); } -static __latent_entropy void tasklet_hi_action(struct softirq_action *a) +static __latent_entropy void tasklet_hi_action(void) { workqueue_softirq_action(true); - tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); + tasklet_action_common(this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); } void tasklet_setup(struct tasklet_struct *t, diff --git a/kernel/sys.c b/kernel/sys.c index 3a38d61fff6e..c63046c89598 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2559,6 +2559,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: + if (task_is_realtime(current)) + break; if (arg2 <= 0) current->timer_slack_ns = current->default_timer_slack_ns; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 5abfa4390673..8bf888641694 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -493,7 +493,7 @@ static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throt * promised in the context of posix_timer_fn() never * materialized, but someone should really work on it. * - * To prevent DOS fake @now to be 1 jiffie out which keeps + * To prevent DOS fake @now to be 1 jiffy out which keeps * the overrun accounting correct but creates an * inconsistency vs. timer_gettime(2). */ @@ -574,15 +574,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, it.alarm.alarmtimer); enum alarmtimer_restart result = ALARMTIMER_NORESTART; unsigned long flags; - int si_private = 0; spin_lock_irqsave(&ptr->it_lock, flags); - ptr->it_active = 0; - if (ptr->it_interval) - si_private = ++ptr->it_requeue_pending; - - if (posix_timer_event(ptr, si_private) && ptr->it_interval) { + if (posix_timer_queue_signal(ptr) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go * away once we handle ignored signals proper. Ensure that diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 60a6484831b1..78c7bd64d0dd 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -190,7 +190,7 @@ int clockevents_tick_resume(struct clock_event_device *dev) #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST -/* Limit min_delta to a jiffie */ +/* Limit min_delta to a jiffy */ #define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) /** diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index d0538a75f4c6..23336eecb4f4 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -113,7 +113,6 @@ static u64 suspend_start; /* * Threshold: 0.0312s, when doubled: 0.0625s. - * Also a default for cs->uncertainty_margin when registering clocks. */ #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5) @@ -125,6 +124,13 @@ static u64 suspend_start; * * The default of 500 parts per million is based on NTP's limits. * If a clocksource is good enough for NTP, it is good enough for us! + * + * In other words, by default, even if a clocksource is extremely + * precise (for example, with a sub-nanosecond period), the maximum + * permissible skew between the clocksource watchdog and the clocksource + * under test is not permitted to go below the 500ppm minimum defined + * by MAX_SKEW_USEC. This 500ppm minimum may be overridden using the + * CLOCKSOURCE_WATCHDOG_MAX_SKEW_US Kconfig option. */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US #define MAX_SKEW_USEC CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US @@ -132,6 +138,13 @@ static u64 suspend_start; #define MAX_SKEW_USEC (125 * WATCHDOG_INTERVAL / HZ) #endif +/* + * Default for maximum permissible skew when cs->uncertainty_margin is + * not specified, and the lower bound even when cs->uncertainty_margin + * is specified. This is also the default that is used when registering + * clocks with unspecifed cs->uncertainty_margin, so this macro is used + * even in CONFIG_CLOCKSOURCE_WATCHDOG=n kernels. + */ #define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC) #ifdef CONFIG_CLOCKSOURCE_WATCHDOG @@ -231,6 +244,7 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { + int64_t md = 2 * watchdog->uncertainty_margin; unsigned int nretries, max_retries; int64_t wd_delay, wd_seq_delay; u64 wd_end, wd_end2; @@ -245,7 +259,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, local_irq_enable(); wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end); - if (wd_delay <= WATCHDOG_MAX_SKEW) { + if (wd_delay <= md + cs->uncertainty_margin) { if (nretries > 1 && nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); @@ -258,12 +272,12 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, * there is too much external interferences that cause * significant delay in reading both clocksource and watchdog. * - * If consecutive WD read-back delay > WATCHDOG_MAX_SKEW/2, - * report system busy, reinit the watchdog and skip the current + * If consecutive WD read-back delay > md, report + * system busy, reinit the watchdog and skip the current * watchdog test. */ wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2); - if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) + if (wd_seq_delay > md) goto skip_test; } @@ -1146,14 +1160,19 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq } /* - * If the uncertainty margin is not specified, calculate it. - * If both scale and freq are non-zero, calculate the clock - * period, but bound below at 2*WATCHDOG_MAX_SKEW. However, - * if either of scale or freq is zero, be very conservative and - * take the tens-of-milliseconds WATCHDOG_THRESHOLD value for the - * uncertainty margin. Allow stupidly small uncertainty margins - * to be specified by the caller for testing purposes, but warn - * to discourage production use of this capability. + * If the uncertainty margin is not specified, calculate it. If + * both scale and freq are non-zero, calculate the clock period, but + * bound below at 2*WATCHDOG_MAX_SKEW, that is, 500ppm by default. + * However, if either of scale or freq is zero, be very conservative + * and take the tens-of-milliseconds WATCHDOG_THRESHOLD value + * for the uncertainty margin. Allow stupidly small uncertainty + * margins to be specified by the caller for testing purposes, + * but warn to discourage production use of this capability. + * + * Bottom line: The sum of the uncertainty margins of the + * watchdog clocksource and the clocksource under test will be at + * least 500ppm by default. For more information, please see the + * comment preceding CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US above. */ if (scale && freq && !cs->uncertainty_margin) { cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index b8ee320208d4..12eb40d6290e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1177,7 +1177,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution - * (i.e. one jiffie) to prevent short timeouts. + * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) @@ -1351,11 +1351,13 @@ static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) + __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) + __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } @@ -1757,7 +1759,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, } } -static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) +static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; @@ -2072,14 +2074,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; - u64 slack; - - slack = current->timer_slack_ns; - if (rt_task(current)) - slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); - hrtimer_set_expires_range_ns(&t.timer, rqtp, slack); + hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; @@ -2249,7 +2246,7 @@ void __init hrtimers_init(void) /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks + * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * @clock_id: timer clock to be used */ @@ -2276,13 +2273,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } - /* - * Override any slack passed by the user if under - * rt contraints. - */ - if (rt_task(current)) - delta = 0; - hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); @@ -2302,7 +2292,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks + * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 8d2dd214ec68..802b336f4b8c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -660,8 +660,16 @@ rearm: sched_sync_hw_clock(offset_nsec, res != 0); } -void ntp_notify_cmos_timer(void) +void ntp_notify_cmos_timer(bool offset_set) { + /* + * If the time jumped (using ADJ_SETOFFSET) cancels sync timer, + * which may have been running if the time was synchronized + * prior to the ADJ_SETOFFSET call. + */ + if (offset_set) + hrtimer_cancel(&sync_hrtimer); + /* * When the work is currently executed but has not yet the timer * rearmed this queues the work immediately again. No big issue, diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 23d1b74c3065..5a633dce9057 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -14,9 +14,9 @@ extern int __do_adjtimex(struct __kernel_timex *txc, extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) -extern void ntp_notify_cmos_timer(void); +extern void ntp_notify_cmos_timer(bool offset_set); #else -static inline void ntp_notify_cmos_timer(void) { } +static inline void ntp_notify_cmos_timer(bool offset_set) { } #endif #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index e9c6f9d0e42c..6bcee4704059 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -453,6 +453,7 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base; + timer->it_active = 0; if (!cpu_timer_dequeue(ctmr)) return; @@ -559,6 +560,7 @@ static void arm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; u64 newexp = cpu_timer_getexpires(ctmr); + timer->it_active = 1; if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return; @@ -584,12 +586,8 @@ static void cpu_timer_fire(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; - if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { - /* - * User don't want any signal. - */ - cpu_timer_setexpires(ctmr, 0); - } else if (unlikely(timer->sigq == NULL)) { + timer->it_active = 0; + if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. @@ -600,9 +598,9 @@ static void cpu_timer_fire(struct k_itimer *timer) /* * One-shot timer. Clear it as soon as it's fired. */ - posix_timer_event(timer, 0); + posix_timer_queue_signal(timer); cpu_timer_setexpires(ctmr, 0); - } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { + } else if (posix_timer_queue_signal(timer)) { /* * The signal did not get queued because the signal * was ignored, so we won't get any callback to @@ -614,6 +612,8 @@ static void cpu_timer_fire(struct k_itimer *timer) } } +static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now); + /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. @@ -623,9 +623,10 @@ static void cpu_timer_fire(struct k_itimer *timer) static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, struct itimerspec64 *new, struct itimerspec64 *old) { + bool sigev_none = timer->it_sigev_notify == SIGEV_NONE; clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); - u64 old_expires, new_expires, old_incr, val; struct cpu_timer *ctmr = &timer->it.cpu; + u64 old_expires, new_expires, now; struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; @@ -662,10 +663,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, return -ESRCH; } - /* - * Disarm any old timer after extracting its expiry time. - */ - old_incr = timer->it_interval; + /* Retrieve the current expiry time before disarming the timer */ old_expires = cpu_timer_getexpires(ctmr); if (unlikely(timer->it.cpu.firing)) { @@ -673,157 +671,122 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); + timer->it_active = 0; } /* - * We need to sample the current value to convert the new - * value from to relative and absolute, and to convert the - * old value from absolute to relative. To set a process - * timer, we need a sample to balance the thread expiry - * times (in arm_timer). With an absolute time, we must - * check if it's already passed. In short, we need a sample. + * Sample the current clock for saving the previous setting + * and for rearming the timer. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) - val = cpu_clock_sample(clkid, p); + now = cpu_clock_sample(clkid, p); else - val = cpu_clock_sample_group(clkid, p, true); + now = cpu_clock_sample_group(clkid, p, !sigev_none); + /* Retrieve the previous expiry value if requested. */ if (old) { - if (old_expires == 0) { - old->it_value.tv_sec = 0; - old->it_value.tv_nsec = 0; - } else { - /* - * Update the timer in case it has overrun already. - * If it has, we'll report it as having overrun and - * with the next reloaded timer already ticking, - * though we are swallowing that pending - * notification here to install the new setting. - */ - u64 exp = bump_cpu_timer(timer, val); - - if (val < exp) { - old_expires = exp - val; - old->it_value = ns_to_timespec64(old_expires); - } else { - old->it_value.tv_nsec = 1; - old->it_value.tv_sec = 0; - } - } + old->it_value = (struct timespec64){ }; + if (old_expires) + __posix_cpu_timer_get(timer, old, now); } + /* Retry if the timer expiry is running concurrently */ if (unlikely(ret)) { - /* - * We are colliding with the timer actually firing. - * Punt after filling in the timer's old value, and - * disable this firing since we are already reporting - * it as an overrun (thanks to bump_cpu_timer above). - */ unlock_task_sighand(p, &flags); goto out; } - if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) { - new_expires += val; - } + /* Convert relative expiry time to absolute */ + if (new_expires && !(timer_flags & TIMER_ABSTIME)) + new_expires += now; + + /* Set the new expiry time (might be 0) */ + cpu_timer_setexpires(ctmr, new_expires); /* - * Install the new expiry time (or zero). - * For a timer with no notification action, we don't actually - * arm the timer (we'll just fake it for timer_gettime). + * Arm the timer if it is not disabled, the new expiry value has + * not yet expired and the timer requires signal delivery. + * SIGEV_NONE timers are never armed. In case the timer is not + * armed, enforce the reevaluation of the timer base so that the + * process wide cputime counter can be disabled eventually. */ - cpu_timer_setexpires(ctmr, new_expires); - if (new_expires != 0 && val < new_expires) { - arm_timer(timer, p); + if (likely(!sigev_none)) { + if (new_expires && now < new_expires) + arm_timer(timer, p); + else + trigger_base_recalc_expires(timer, p); } unlock_task_sighand(p, &flags); - /* - * Install the new reload setting, and - * set up the signal and overrun bookkeeping. - */ - timer->it_interval = timespec64_to_ktime(new->it_interval); + + posix_timer_set_common(timer, new); /* - * This acts as a modification timestamp for the timer, - * so any automatic reload attempt will punt on seeing - * that we have reset the timer manually. + * If the new expiry time was already in the past the timer was not + * queued. Fire it immediately even if the thread never runs to + * accumulate more time on this clock. */ - timer->it_requeue_pending = (timer->it_requeue_pending + 2) & - ~REQUEUE_PENDING; - timer->it_overrun_last = 0; - timer->it_overrun = -1; - - if (val >= new_expires) { - if (new_expires != 0) { - /* - * The designated time already passed, so we notify - * immediately, even if the thread never runs to - * accumulate more time on this clock. - */ - cpu_timer_fire(timer); - } - - /* - * Make sure we don't keep around the process wide cputime - * counter or the tick dependency if they are not necessary. - */ - sighand = lock_task_sighand(p, &flags); - if (!sighand) - goto out; - - if (!cpu_timer_queued(ctmr)) - trigger_base_recalc_expires(timer, p); - - unlock_task_sighand(p, &flags); - } - out: + if (!sigev_none && new_expires && now >= new_expires) + cpu_timer_fire(timer); +out: rcu_read_unlock(); - if (old) - old->it_interval = ns_to_timespec64(old_incr); - return ret; } +static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now) +{ + bool sigev_none = timer->it_sigev_notify == SIGEV_NONE; + u64 expires, iv = timer->it_interval; + + /* + * Make sure that interval timers are moved forward for the + * following cases: + * - SIGEV_NONE timers which are never armed + * - Timers which expired, but the signal has not yet been + * delivered + */ + if (iv && ((timer->it_requeue_pending & REQUEUE_PENDING) || sigev_none)) + expires = bump_cpu_timer(timer, now); + else + expires = cpu_timer_getexpires(&timer->it.cpu); + + /* + * Expired interval timers cannot have a remaining time <= 0. + * The kernel has to move them forward so that the next + * timer expiry is > @now. + */ + if (now < expires) { + itp->it_value = ns_to_timespec64(expires - now); + } else { + /* + * A single shot SIGEV_NONE timer must return 0, when it is + * expired! Timers which have a real signal delivery mode + * must return a remaining time greater than 0 because the + * signal has not yet been delivered. + */ + if (!sigev_none) + itp->it_value.tv_nsec = 1; + } +} + static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); - struct cpu_timer *ctmr = &timer->it.cpu; - u64 now, expires = cpu_timer_getexpires(ctmr); struct task_struct *p; + u64 now; rcu_read_lock(); p = cpu_timer_task_rcu(timer); - if (!p) - goto out; + if (p && cpu_timer_getexpires(&timer->it.cpu)) { + itp->it_interval = ktime_to_timespec64(timer->it_interval); - /* - * Easy part: convert the reload time. - */ - itp->it_interval = ktime_to_timespec64(timer->it_interval); + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + now = cpu_clock_sample(clkid, p); + else + now = cpu_clock_sample_group(clkid, p, false); - if (!expires) - goto out; - - /* - * Sample the clock to take the difference with the expiry time. - */ - if (CPUCLOCK_PERTHREAD(timer->it_clock)) - now = cpu_clock_sample(clkid, p); - else - now = cpu_clock_sample_group(clkid, p, false); - - if (now < expires) { - itp->it_value = ns_to_timespec64(expires - now); - } else { - /* - * The timer should have expired already, but the firing - * hasn't taken place yet. Say it's just about to expire. - */ - itp->it_value.tv_nsec = 1; - itp->it_value.tv_sec = 0; + __posix_cpu_timer_get(timer, itp, now); } -out: rcu_read_unlock(); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b924f0f096fa..4576aaed13b2 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -277,10 +277,17 @@ void posixtimer_rearm(struct kernel_siginfo *info) unlock_timer(timr, flags); } -int posix_timer_event(struct k_itimer *timr, int si_private) +int posix_timer_queue_signal(struct k_itimer *timr) { + int ret, si_private = 0; enum pid_type type; - int ret; + + lockdep_assert_held(&timr->it_lock); + + timr->it_active = 0; + if (timr->it_interval) + si_private = ++timr->it_requeue_pending; + /* * FIXME: if ->sigq is queued we can race with * dequeue_signal()->posixtimer_rearm(). @@ -309,19 +316,13 @@ int posix_timer_event(struct k_itimer *timr, int si_private) */ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { + struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer); enum hrtimer_restart ret = HRTIMER_NORESTART; - struct k_itimer *timr; unsigned long flags; - int si_private = 0; - timr = container_of(timer, struct k_itimer, it.real.timer); spin_lock_irqsave(&timr->it_lock, flags); - timr->it_active = 0; - if (timr->it_interval != 0) - si_private = ++timr->it_requeue_pending; - - if (posix_timer_event(timr, si_private)) { + if (posix_timer_queue_signal(timr)) { /* * The signal was not queued due to SIG_IGN. As a * consequence the timer is not going to be rearmed from @@ -338,14 +339,14 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) * change to the signal handling code. * * For now let timers with an interval less than a - * jiffie expire every jiffie and recheck for a + * jiffy expire every jiffy and recheck for a * valid signal handler. * * This avoids interrupt starvation in case of a * very small interval, which would expire the * timer immediately again. * - * Moving now ahead of time by one jiffie tricks + * Moving now ahead of time by one jiffy tricks * hrtimer_forward() to expire the timer later, * while it still maintains the overrun accuracy * for the price of a slight inconsistency in the @@ -515,7 +516,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, spin_lock_irq(¤t->sighand->siglock); /* This makes the timer valid in the hash table */ WRITE_ONCE(new_timer->it_signal, current->signal); - list_add(&new_timer->list, ¤t->signal->posix_timers); + hlist_add_head(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); /* * After unlocking sighand::siglock @new_timer is subject to @@ -856,6 +857,23 @@ static struct k_itimer *timer_wait_running(struct k_itimer *timer, return lock_timer(timer_id, flags); } +/* + * Set up the new interval and reset the signal delivery data + */ +void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting) +{ + if (new_setting->it_value.tv_sec || new_setting->it_value.tv_nsec) + timer->it_interval = timespec64_to_ktime(new_setting->it_interval); + else + timer->it_interval = 0; + + /* Prevent reloading in case there is a signal pending */ + timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING; + /* Reset overrun accounting */ + timer->it_overrun_last = 0; + timer->it_overrun = -1LL; +} + /* Set a POSIX.1b interval timer. */ int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, @@ -878,15 +896,12 @@ int common_timer_set(struct k_itimer *timr, int flags, return TIMER_RETRY; timr->it_active = 0; - timr->it_requeue_pending = (timr->it_requeue_pending + 2) & - ~REQUEUE_PENDING; - timr->it_overrun_last = 0; + posix_timer_set_common(timr, new_setting); - /* Switch off the timer when it_value is zero */ + /* Keep timer disarmed when it_value is zero */ if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; - timr->it_interval = timespec64_to_ktime(new_setting->it_interval); expires = timespec64_to_ktime(new_setting->it_value); if (flags & TIMER_ABSTIME) expires = timens_ktime_to_host(timr->it_clock, expires); @@ -904,7 +919,7 @@ static int do_timer_settime(timer_t timer_id, int tmr_flags, const struct k_clock *kc; struct k_itimer *timr; unsigned long flags; - int error = 0; + int error; if (!timespec64_valid(&new_spec64->it_interval) || !timespec64_valid(&new_spec64->it_value)) @@ -918,6 +933,9 @@ retry: if (!timr) return -EINVAL; + if (old_spec64) + old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); + kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -1021,7 +1039,7 @@ retry_delete: } spin_lock(¤t->sighand->siglock); - list_del(&timer->list); + hlist_del(&timer->list); spin_unlock(¤t->sighand->siglock); /* * A concurrent lookup could check timer::it_signal lockless. It @@ -1071,7 +1089,7 @@ retry_delete: goto retry_delete; } - list_del(&timer->list); + hlist_del(&timer->list); /* * Setting timer::it_signal to NULL is technically not required @@ -1092,22 +1110,19 @@ retry_delete: */ void exit_itimers(struct task_struct *tsk) { - struct list_head timers; - struct k_itimer *tmr; + struct hlist_head timers; - if (list_empty(&tsk->signal->posix_timers)) + if (hlist_empty(&tsk->signal->posix_timers)) return; /* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq(&tsk->sighand->siglock); - list_replace_init(&tsk->signal->posix_timers, &timers); + hlist_move_list(&tsk->signal->posix_timers, &timers); spin_unlock_irq(&tsk->sighand->siglock); /* The timers are not longer accessible via tsk::signal */ - while (!list_empty(&timers)) { - tmr = list_first_entry(&timers, struct k_itimer, list); - itimer_delete(tmr); - } + while (!hlist_empty(&timers)) + itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index f32a2ebba9b8..4784ea65f685 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -36,10 +36,11 @@ extern const struct k_clock clock_process; extern const struct k_clock clock_thread; extern const struct k_clock alarm_clock; -int posix_timer_event(struct k_itimer *timr, int si_private); +int posix_timer_queue_signal(struct k_itimer *timr); void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting); int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, struct itimerspec64 *old_setting); +void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting); int common_timer_del(struct k_itimer *timer); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5391e4167d60..7e6f409bf311 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2553,6 +2553,7 @@ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; + bool offset_set = false; bool clock_set = false; struct timespec64 ts; unsigned long flags; @@ -2575,6 +2576,7 @@ int do_adjtimex(struct __kernel_timex *txc) if (ret) return ret; + offset_set = delta.tv_sec != 0; audit_tk_injoffset(delta); } @@ -2608,7 +2610,7 @@ int do_adjtimex(struct __kernel_timex *txc) if (clock_set) clock_was_set(CLOCK_SET_WALL); - ntp_notify_cmos_timer(); + ntp_notify_cmos_timer(offset_set); return ret; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index fd0f24da9e78..d43e73291938 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -367,7 +367,7 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu, rem = j % HZ; /* - * If the target jiffie is just after a whole second (which can happen + * If the target jiffy is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. @@ -675,7 +675,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ - base->next_expiry = bucket_expiry; + WRITE_ONCE(base->next_expiry, bucket_expiry); base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); @@ -1564,6 +1564,8 @@ static inline void timer_base_unlock_expiry(struct timer_base *base) * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) + __releases(&base->lock) __releases(&base->expiry_lock) + __acquires(&base->expiry_lock) __acquires(&base->lock) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); @@ -1901,7 +1903,7 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset, * * Store next expiry time in base->next_expiry. */ -static void next_expiry_recalc(struct timer_base *base) +static void timer_recalc_next_expiry(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; @@ -1931,7 +1933,7 @@ static void next_expiry_recalc(struct timer_base *base) * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next - * expiring jiffie. So in case of: + * expiring jiffy. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 @@ -1967,7 +1969,7 @@ static void next_expiry_recalc(struct timer_base *base) clk += adj; } - base->next_expiry = next; + WRITE_ONCE(base->next_expiry, next); base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); } @@ -1996,7 +1998,7 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) return basem; /* - * Round up to the next jiffie. High resolution timers are + * Round up to the next jiffy. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. @@ -2010,7 +2012,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base, unsigned long basej) { if (base->next_expiry_recalc) - next_expiry_recalc(base); + timer_recalc_next_expiry(base); /* * Move next_expiry for the empty base into the future to prevent an @@ -2021,7 +2023,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base, * easy comparable to find out which base holds the first pending timer. */ if (!base->timers_pending) - base->next_expiry = basej + NEXT_TIMER_MAX_DELTA; + WRITE_ONCE(base->next_expiry, basej + NEXT_TIMER_MAX_DELTA); return base->next_expiry; } @@ -2255,7 +2257,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, base_global, &tevt); /* - * If the next event is only one jiffie ahead there is no need to call + * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. @@ -2414,7 +2416,7 @@ static inline void __run_timers(struct timer_base *base) * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; - next_expiry_recalc(base); + timer_recalc_next_expiry(base); while (levels--) expire_timers(base, heads + levels); @@ -2443,7 +2445,7 @@ static void run_timer_base(int index) /* * This function runs timers and the timer-tq in bottom half context. */ -static __latent_entropy void run_timer_softirq(struct softirq_action *h) +static __latent_entropy void run_timer_softirq(void) { run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { @@ -2465,8 +2467,40 @@ static void run_local_timers(void) hrtimer_run_queues(); for (int i = 0; i < NR_BASES; i++, base++) { - /* Raise the softirq only if required. */ - if (time_after_eq(jiffies, base->next_expiry) || + /* + * Raise the softirq only if required. + * + * timer_base::next_expiry can be written by a remote CPU while + * holding the lock. If this write happens at the same time than + * the lockless local read, sanity checker could complain about + * data corruption. + * + * There are two possible situations where + * timer_base::next_expiry is written by a remote CPU: + * + * 1. Remote CPU expires global timers of this CPU and updates + * timer_base::next_expiry of BASE_GLOBAL afterwards in + * next_timer_interrupt() or timer_recalc_next_expiry(). The + * worst outcome is a superfluous raise of the timer softirq + * when the not yet updated value is read. + * + * 2. A new first pinned timer is enqueued by a remote CPU + * and therefore timer_base::next_expiry of BASE_LOCAL is + * updated. When this update is missed, this isn't a + * problem, as an IPI is executed nevertheless when the CPU + * was idle before. When the CPU wasn't idle but the update + * is missed, then the timer would expire one jiffy late - + * bad luck. + * + * Those unlikely corner cases where the worst outcome is only a + * one jiffy delay or a superfluous raise of the softirq are + * not that expensive as doing the check always while holding + * the lock. + * + * Possible remote writers are using WRITE_ONCE(). Local reader + * uses therefore READ_ONCE(). + */ + if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { raise_softirq(TIMER_SOFTIRQ); return; @@ -2733,7 +2767,7 @@ void __init init_timers(void) */ void msleep(unsigned int msecs) { - unsigned long timeout = msecs_to_jiffies(msecs) + 1; + unsigned long timeout = msecs_to_jiffies(msecs); while (timeout) timeout = schedule_timeout_uninterruptible(timeout); @@ -2747,7 +2781,7 @@ EXPORT_SYMBOL(msleep); */ unsigned long msleep_interruptible(unsigned int msecs) { - unsigned long timeout = msecs_to_jiffies(msecs) + 1; + unsigned long timeout = msecs_to_jiffies(msecs); while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..a40aa606cd04 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -97,7 +97,7 @@ config BOOT_PRINTK_DELAY using "boot_delay=N". It is likely that you would also need to use "lpj=M" to preset - the "loops per jiffie" value. + the "loops per jiffy" value. See a previous boot log for the "lpj" value to use for your system, and then set "lpj=M" before setting "boot_delay=N". NOTE: Using this option may adversely affect SMP systems. diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 7cea91e193a8..5ce473ad499b 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -70,10 +70,10 @@ static HLIST_HEAD(obj_to_free); * made at debug_stats_show(). Both obj_pool_min_free and obj_pool_max_used * can be off. */ -static int obj_pool_min_free = ODEBUG_POOL_SIZE; -static int obj_pool_free = ODEBUG_POOL_SIZE; +static int __data_racy obj_pool_min_free = ODEBUG_POOL_SIZE; +static int __data_racy obj_pool_free = ODEBUG_POOL_SIZE; static int obj_pool_used; -static int obj_pool_max_used; +static int __data_racy obj_pool_max_used; static bool obj_freeing; /* The number of objs on the global free list */ static int obj_nr_tofree; @@ -84,9 +84,9 @@ static int __data_racy debug_objects_fixups __read_mostly; static int __data_racy debug_objects_warnings __read_mostly; static int __data_racy debug_objects_enabled __read_mostly = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; -static int __data_racy debug_objects_pool_size __read_mostly +static int debug_objects_pool_size __ro_after_init = ODEBUG_POOL_SIZE; -static int __data_racy debug_objects_pool_min_level __read_mostly +static int debug_objects_pool_min_level __ro_after_init = ODEBUG_POOL_MIN_LEVEL; static const struct debug_obj_descr *descr_test __read_mostly; @@ -95,8 +95,8 @@ static struct kmem_cache *obj_cache __ro_after_init; /* * Track numbers of kmem_cache_alloc()/free() calls done. */ -static int debug_objects_allocated; -static int debug_objects_freed; +static int __data_racy debug_objects_allocated; +static int __data_racy debug_objects_freed; static void free_obj_work(struct work_struct *work); static DECLARE_DELAYED_WORK(debug_obj_work, free_obj_work); @@ -135,20 +135,19 @@ static void fill_pool(void) return; /* - * Reuse objs from the global free list; they will be reinitialized - * when allocating. + * Reuse objs from the global obj_to_free list; they will be + * reinitialized when allocating. * - * Both obj_nr_tofree and obj_pool_free are checked locklessly; the - * READ_ONCE()s pair with the WRITE_ONCE()s in pool_lock critical - * sections. + * obj_nr_tofree is checked locklessly; the READ_ONCE() pairs with + * the WRITE_ONCE() in pool_lock critical sections. */ - while (READ_ONCE(obj_nr_tofree) && (READ_ONCE(obj_pool_free) < obj_pool_min_free)) { + if (READ_ONCE(obj_nr_tofree)) { raw_spin_lock_irqsave(&pool_lock, flags); /* * Recheck with the lock held as the worker thread might have * won the race and freed the global free list already. */ - while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) { + while (obj_nr_tofree && (obj_pool_free < debug_objects_pool_min_level)) { obj = hlist_entry(obj_to_free.first, typeof(*obj), node); hlist_del(&obj->node); WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 2d5329a42105..08b242bbdbdf 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -75,7 +75,7 @@ void irq_poll_complete(struct irq_poll *iop) } EXPORT_SYMBOL(irq_poll_complete); -static void __latent_entropy irq_poll_softirq(struct softirq_action *h) +static void __latent_entropy irq_poll_softirq(void) { struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll); int rearm = 0, budget = irq_poll_budget; diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 00840d5784fe..04f6398b3a40 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -287,7 +287,7 @@ struct batadv_frag_table_entry { /** @lock: lock to protect the list of fragments */ spinlock_t lock; - /** @timestamp: time (jiffie) of last received fragment */ + /** @timestamp: time (jiffy) of last received fragment */ unsigned long timestamp; /** @seqno: sequence number of the fragments in the list */ diff --git a/net/core/dev.c b/net/core/dev.c index bea4992de7d8..191087910536 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5256,7 +5256,7 @@ int netif_rx(struct sk_buff *skb) } EXPORT_SYMBOL(netif_rx); -static __latent_entropy void net_tx_action(struct softirq_action *h) +static __latent_entropy void net_tx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -6927,7 +6927,7 @@ static int napi_threaded_poll(void *data) return 0; } -static __latent_entropy void net_rx_action(struct softirq_action *h) +static __latent_entropy void net_rx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 07c81c0093c0..16bd49492efa 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -6,10 +6,13 @@ * * Kernel loop code stolen from Steven Rostedt */ - +#define _GNU_SOURCE #include +#include #include #include +#include +#include #include #include #include @@ -18,6 +21,21 @@ #define DELAY 2 #define USECS_PER_SEC 1000000 +#define NSECS_PER_SEC 1000000000 + +static void __fatal_error(const char *test, const char *name, const char *what) +{ + char buf[64]; + + strerror_r(errno, buf, sizeof(buf)); + + if (name && strlen(name)) + ksft_exit_fail_msg("%s %s %s %s\n", test, name, what, buf); + else + ksft_exit_fail_msg("%s %s %s\n", test, what, buf); +} + +#define fatal_error(name, what) __fatal_error(__func__, name, what) static volatile int done; @@ -74,24 +92,13 @@ static int check_diff(struct timeval start, struct timeval end) return 0; } -static int check_itimer(int which) +static void check_itimer(int which, const char *name) { - const char *name; - int err; struct timeval start, end; struct itimerval val = { .it_value.tv_sec = DELAY, }; - if (which == ITIMER_VIRTUAL) - name = "ITIMER_VIRTUAL"; - else if (which == ITIMER_PROF) - name = "ITIMER_PROF"; - else if (which == ITIMER_REAL) - name = "ITIMER_REAL"; - else - return -1; - done = 0; if (which == ITIMER_VIRTUAL) @@ -101,17 +108,11 @@ static int check_itimer(int which) else if (which == ITIMER_REAL) signal(SIGALRM, sig_handler); - err = gettimeofday(&start, NULL); - if (err < 0) { - ksft_perror("Can't call gettimeofday()"); - return -1; - } + if (gettimeofday(&start, NULL) < 0) + fatal_error(name, "gettimeofday()"); - err = setitimer(which, &val, NULL); - if (err < 0) { - ksft_perror("Can't set timer"); - return -1; - } + if (setitimer(which, &val, NULL) < 0) + fatal_error(name, "setitimer()"); if (which == ITIMER_VIRTUAL) user_loop(); @@ -120,68 +121,41 @@ static int check_itimer(int which) else if (which == ITIMER_REAL) idle_loop(); - err = gettimeofday(&end, NULL); - if (err < 0) { - ksft_perror("Can't call gettimeofday()"); - return -1; - } + if (gettimeofday(&end, NULL) < 0) + fatal_error(name, "gettimeofday()"); ksft_test_result(check_diff(start, end) == 0, "%s\n", name); - - return 0; } -static int check_timer_create(int which) +static void check_timer_create(int which, const char *name) { - const char *type; - int err; - timer_t id; struct timeval start, end; struct itimerspec val = { .it_value.tv_sec = DELAY, }; - - if (which == CLOCK_THREAD_CPUTIME_ID) { - type = "thread"; - } else if (which == CLOCK_PROCESS_CPUTIME_ID) { - type = "process"; - } else { - ksft_print_msg("Unknown timer_create() type %d\n", which); - return -1; - } + timer_t id; done = 0; - err = timer_create(which, NULL, &id); - if (err < 0) { - ksft_perror("Can't create timer"); - return -1; - } - signal(SIGALRM, sig_handler); - err = gettimeofday(&start, NULL); - if (err < 0) { - ksft_perror("Can't call gettimeofday()"); - return -1; - } + if (timer_create(which, NULL, &id) < 0) + fatal_error(name, "timer_create()"); - err = timer_settime(id, 0, &val, NULL); - if (err < 0) { - ksft_perror("Can't set timer"); - return -1; - } + if (signal(SIGALRM, sig_handler) == SIG_ERR) + fatal_error(name, "signal()"); + + if (gettimeofday(&start, NULL) < 0) + fatal_error(name, "gettimeofday()"); + + if (timer_settime(id, 0, &val, NULL) < 0) + fatal_error(name, "timer_settime()"); user_loop(); - err = gettimeofday(&end, NULL); - if (err < 0) { - ksft_perror("Can't call gettimeofday()"); - return -1; - } + if (gettimeofday(&end, NULL) < 0) + fatal_error(name, "gettimeofday()"); ksft_test_result(check_diff(start, end) == 0, - "timer_create() per %s\n", type); - - return 0; + "timer_create() per %s\n", name); } static pthread_t ctd_thread; @@ -209,15 +183,14 @@ static void *ctd_thread_func(void *arg) ctd_count = 100; if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id)) - return "Can't create timer\n"; + fatal_error(NULL, "timer_create()"); if (timer_settime(id, 0, &val, NULL)) - return "Can't set timer\n"; - + fatal_error(NULL, "timer_settime()"); while (ctd_count > 0 && !ctd_failed) ; if (timer_delete(id)) - return "Can't delete timer\n"; + fatal_error(NULL, "timer_delete()"); return NULL; } @@ -225,19 +198,16 @@ static void *ctd_thread_func(void *arg) /* * Test that only the running thread receives the timer signal. */ -static int check_timer_distribution(void) +static void check_timer_distribution(void) { - const char *errmsg; + if (signal(SIGALRM, ctd_sighandler) == SIG_ERR) + fatal_error(NULL, "signal()"); - signal(SIGALRM, ctd_sighandler); - - errmsg = "Can't create thread\n"; if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL)) - goto err; + fatal_error(NULL, "pthread_create()"); - errmsg = "Can't join thread\n"; - if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg) - goto err; + if (pthread_join(ctd_thread, NULL)) + fatal_error(NULL, "pthread_join()"); if (!ctd_failed) ksft_test_result_pass("check signal distribution\n"); @@ -245,31 +215,399 @@ static int check_timer_distribution(void) ksft_test_result_fail("check signal distribution\n"); else ksft_test_result_skip("check signal distribution (old kernel)\n"); - return 0; -err: - ksft_print_msg("%s", errmsg); - return -1; +} + +struct tmrsig { + int signals; + int overruns; +}; + +static void siginfo_handler(int sig, siginfo_t *si, void *uc) +{ + struct tmrsig *tsig = si ? si->si_ptr : NULL; + + if (tsig) { + tsig->signals++; + tsig->overruns += si->si_overrun; + } +} + +static void *ignore_thread(void *arg) +{ + unsigned int *tid = arg; + sigset_t set; + + sigemptyset(&set); + sigaddset(&set, SIGUSR1); + if (sigprocmask(SIG_BLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_BLOCK)"); + + *tid = gettid(); + sleep(100); + + if (sigprocmask(SIG_UNBLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)"); + return NULL; +} + +static void check_sig_ign(int thread) +{ + struct tmrsig tsig = { }; + struct itimerspec its; + unsigned int tid = 0; + struct sigaction sa; + struct sigevent sev; + pthread_t pthread; + timer_t timerid; + sigset_t set; + + if (thread) { + if (pthread_create(&pthread, NULL, ignore_thread, &tid)) + fatal_error(NULL, "pthread_create()"); + sleep(1); + } + + sa.sa_flags = SA_SIGINFO; + sa.sa_sigaction = siginfo_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL)) + fatal_error(NULL, "sigaction()"); + + /* Block the signal */ + sigemptyset(&set); + sigaddset(&set, SIGUSR1); + if (sigprocmask(SIG_BLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_BLOCK)"); + + memset(&sev, 0, sizeof(sev)); + sev.sigev_notify = SIGEV_SIGNAL; + sev.sigev_signo = SIGUSR1; + sev.sigev_value.sival_ptr = &tsig; + if (thread) { + sev.sigev_notify = SIGEV_THREAD_ID; + sev._sigev_un._tid = tid; + } + + if (timer_create(CLOCK_MONOTONIC, &sev, &timerid)) + fatal_error(NULL, "timer_create()"); + + /* Start the timer to expire in 100ms and 100ms intervals */ + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 100000000; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 100000000; + timer_settime(timerid, 0, &its, NULL); + + sleep(1); + + /* Set the signal to be ignored */ + if (signal(SIGUSR1, SIG_IGN) == SIG_ERR) + fatal_error(NULL, "signal(SIG_IGN)"); + + sleep(1); + + if (thread) { + /* Stop the thread first. No signal should be delivered to it */ + if (pthread_cancel(pthread)) + fatal_error(NULL, "pthread_cancel()"); + if (pthread_join(pthread, NULL)) + fatal_error(NULL, "pthread_join()"); + } + + /* Restore the handler */ + if (sigaction(SIGUSR1, &sa, NULL)) + fatal_error(NULL, "sigaction()"); + + sleep(1); + + /* Unblock it, which should deliver the signal in the !thread case*/ + if (sigprocmask(SIG_UNBLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)"); + + if (timer_delete(timerid)) + fatal_error(NULL, "timer_delete()"); + + if (!thread) { + ksft_test_result(tsig.signals == 1 && tsig.overruns == 29, + "check_sig_ign SIGEV_SIGNAL\n"); + } else { + ksft_test_result(tsig.signals == 0 && tsig.overruns == 0, + "check_sig_ign SIGEV_THREAD_ID\n"); + } +} + +static void check_rearm(void) +{ + struct tmrsig tsig = { }; + struct itimerspec its; + struct sigaction sa; + struct sigevent sev; + timer_t timerid; + sigset_t set; + + sa.sa_flags = SA_SIGINFO; + sa.sa_sigaction = siginfo_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL)) + fatal_error(NULL, "sigaction()"); + + /* Block the signal */ + sigemptyset(&set); + sigaddset(&set, SIGUSR1); + if (sigprocmask(SIG_BLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_BLOCK)"); + + memset(&sev, 0, sizeof(sev)); + sev.sigev_notify = SIGEV_SIGNAL; + sev.sigev_signo = SIGUSR1; + sev.sigev_value.sival_ptr = &tsig; + if (timer_create(CLOCK_MONOTONIC, &sev, &timerid)) + fatal_error(NULL, "timer_create()"); + + /* Start the timer to expire in 100ms and 100ms intervals */ + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 100000000; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 100000000; + if (timer_settime(timerid, 0, &its, NULL)) + fatal_error(NULL, "timer_settime()"); + + sleep(1); + + /* Reprogram the timer to single shot */ + its.it_value.tv_sec = 10; + its.it_value.tv_nsec = 0; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 0; + if (timer_settime(timerid, 0, &its, NULL)) + fatal_error(NULL, "timer_settime()"); + + /* Unblock it, which should not deliver a signal */ + if (sigprocmask(SIG_UNBLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)"); + + if (timer_delete(timerid)) + fatal_error(NULL, "timer_delete()"); + + ksft_test_result(!tsig.signals, "check_rearm\n"); +} + +static void check_delete(void) +{ + struct tmrsig tsig = { }; + struct itimerspec its; + struct sigaction sa; + struct sigevent sev; + timer_t timerid; + sigset_t set; + + sa.sa_flags = SA_SIGINFO; + sa.sa_sigaction = siginfo_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL)) + fatal_error(NULL, "sigaction()"); + + /* Block the signal */ + sigemptyset(&set); + sigaddset(&set, SIGUSR1); + if (sigprocmask(SIG_BLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_BLOCK)"); + + memset(&sev, 0, sizeof(sev)); + sev.sigev_notify = SIGEV_SIGNAL; + sev.sigev_signo = SIGUSR1; + sev.sigev_value.sival_ptr = &tsig; + if (timer_create(CLOCK_MONOTONIC, &sev, &timerid)) + fatal_error(NULL, "timer_create()"); + + /* Start the timer to expire in 100ms and 100ms intervals */ + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 100000000; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 100000000; + if (timer_settime(timerid, 0, &its, NULL)) + fatal_error(NULL, "timer_settime()"); + + sleep(1); + + if (timer_delete(timerid)) + fatal_error(NULL, "timer_delete()"); + + /* Unblock it, which should not deliver a signal */ + if (sigprocmask(SIG_UNBLOCK, &set, NULL)) + fatal_error(NULL, "sigprocmask(SIG_UNBLOCK)"); + + ksft_test_result(!tsig.signals, "check_delete\n"); +} + +static inline int64_t calcdiff_ns(struct timespec t1, struct timespec t2) +{ + int64_t diff; + + diff = NSECS_PER_SEC * (int64_t)((int) t1.tv_sec - (int) t2.tv_sec); + diff += ((int) t1.tv_nsec - (int) t2.tv_nsec); + return diff; +} + +static void check_sigev_none(int which, const char *name) +{ + struct timespec start, now; + struct itimerspec its; + struct sigevent sev; + timer_t timerid; + + memset(&sev, 0, sizeof(sev)); + sev.sigev_notify = SIGEV_NONE; + + if (timer_create(which, &sev, &timerid)) + fatal_error(name, "timer_create()"); + + /* Start the timer to expire in 100ms and 100ms intervals */ + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 100000000; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 100000000; + timer_settime(timerid, 0, &its, NULL); + + if (clock_gettime(which, &start)) + fatal_error(name, "clock_gettime()"); + + do { + if (clock_gettime(which, &now)) + fatal_error(name, "clock_gettime()"); + } while (calcdiff_ns(now, start) < NSECS_PER_SEC); + + if (timer_gettime(timerid, &its)) + fatal_error(name, "timer_gettime()"); + + if (timer_delete(timerid)) + fatal_error(name, "timer_delete()"); + + ksft_test_result(its.it_value.tv_sec || its.it_value.tv_nsec, + "check_sigev_none %s\n", name); +} + +static void check_gettime(int which, const char *name) +{ + struct itimerspec its, prev; + struct timespec start, now; + struct sigevent sev; + timer_t timerid; + int wraps = 0; + sigset_t set; + + /* Block the signal */ + sigemptyset(&set); + sigaddset(&set, SIGUSR1); + if (sigprocmask(SIG_BLOCK, &set, NULL)) + fatal_error(name, "sigprocmask(SIG_BLOCK)"); + + memset(&sev, 0, sizeof(sev)); + sev.sigev_notify = SIGEV_SIGNAL; + sev.sigev_signo = SIGUSR1; + + if (timer_create(which, &sev, &timerid)) + fatal_error(name, "timer_create()"); + + /* Start the timer to expire in 100ms and 100ms intervals */ + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 100000000; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 100000000; + if (timer_settime(timerid, 0, &its, NULL)) + fatal_error(name, "timer_settime()"); + + if (timer_gettime(timerid, &prev)) + fatal_error(name, "timer_gettime()"); + + if (clock_gettime(which, &start)) + fatal_error(name, "clock_gettime()"); + + do { + if (clock_gettime(which, &now)) + fatal_error(name, "clock_gettime()"); + if (timer_gettime(timerid, &its)) + fatal_error(name, "timer_gettime()"); + if (its.it_value.tv_nsec > prev.it_value.tv_nsec) + wraps++; + prev = its; + + } while (calcdiff_ns(now, start) < NSECS_PER_SEC); + + if (timer_delete(timerid)) + fatal_error(name, "timer_delete()"); + + ksft_test_result(wraps > 1, "check_gettime %s\n", name); +} + +static void check_overrun(int which, const char *name) +{ + struct timespec start, now; + struct tmrsig tsig = { }; + struct itimerspec its; + struct sigaction sa; + struct sigevent sev; + timer_t timerid; + sigset_t set; + + sa.sa_flags = SA_SIGINFO; + sa.sa_sigaction = siginfo_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL)) + fatal_error(name, "sigaction()"); + + /* Block the signal */ + sigemptyset(&set); + sigaddset(&set, SIGUSR1); + if (sigprocmask(SIG_BLOCK, &set, NULL)) + fatal_error(name, "sigprocmask(SIG_BLOCK)"); + + memset(&sev, 0, sizeof(sev)); + sev.sigev_notify = SIGEV_SIGNAL; + sev.sigev_signo = SIGUSR1; + sev.sigev_value.sival_ptr = &tsig; + if (timer_create(which, &sev, &timerid)) + fatal_error(name, "timer_create()"); + + /* Start the timer to expire in 100ms and 100ms intervals */ + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 100000000; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 100000000; + if (timer_settime(timerid, 0, &its, NULL)) + fatal_error(name, "timer_settime()"); + + if (clock_gettime(which, &start)) + fatal_error(name, "clock_gettime()"); + + do { + if (clock_gettime(which, &now)) + fatal_error(name, "clock_gettime()"); + } while (calcdiff_ns(now, start) < NSECS_PER_SEC); + + /* Unblock it, which should deliver a signal */ + if (sigprocmask(SIG_UNBLOCK, &set, NULL)) + fatal_error(name, "sigprocmask(SIG_UNBLOCK)"); + + if (timer_delete(timerid)) + fatal_error(name, "timer_delete()"); + + ksft_test_result(tsig.signals == 1 && tsig.overruns == 9, + "check_overrun %s\n", name); } int main(int argc, char **argv) { ksft_print_header(); - ksft_set_plan(6); + ksft_set_plan(18); ksft_print_msg("Testing posix timers. False negative may happen on CPU execution \n"); ksft_print_msg("based timers if other threads run on the CPU...\n"); - if (check_itimer(ITIMER_VIRTUAL) < 0) - ksft_exit_fail(); - - if (check_itimer(ITIMER_PROF) < 0) - ksft_exit_fail(); - - if (check_itimer(ITIMER_REAL) < 0) - ksft_exit_fail(); - - if (check_timer_create(CLOCK_THREAD_CPUTIME_ID) < 0) - ksft_exit_fail(); + check_itimer(ITIMER_VIRTUAL, "ITIMER_VIRTUAL"); + check_itimer(ITIMER_PROF, "ITIMER_PROF"); + check_itimer(ITIMER_REAL, "ITIMER_REAL"); + check_timer_create(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID"); /* * It's unfortunately hard to reliably test a timer expiration @@ -280,11 +618,21 @@ int main(int argc, char **argv) * to ensure true parallelism. So test only one thread until we * find a better solution. */ - if (check_timer_create(CLOCK_PROCESS_CPUTIME_ID) < 0) - ksft_exit_fail(); + check_timer_create(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID"); + check_timer_distribution(); - if (check_timer_distribution() < 0) - ksft_exit_fail(); + check_sig_ign(0); + check_sig_ign(1); + check_rearm(); + check_delete(); + check_sigev_none(CLOCK_MONOTONIC, "CLOCK_MONOTONIC"); + check_sigev_none(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID"); + check_gettime(CLOCK_MONOTONIC, "CLOCK_MONOTONIC"); + check_gettime(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID"); + check_gettime(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID"); + check_overrun(CLOCK_MONOTONIC, "CLOCK_MONOTONIC"); + check_overrun(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID"); + check_overrun(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID"); ksft_finished(); }