diff options
| -rw-r--r-- | drivers/resctrl/mpam_devices.c | 280 | ||||
| -rw-r--r-- | drivers/resctrl/mpam_internal.h | 13 |
2 files changed, 293 insertions, 0 deletions
diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c index 7943d174b3f4..21fccc3ff002 100644 --- a/drivers/resctrl/mpam_devices.c +++ b/drivers/resctrl/mpam_devices.c @@ -14,6 +14,9 @@ #include <linux/device.h> #include <linux/errno.h> #include <linux/gfp.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdesc.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/mutex.h> @@ -200,6 +203,35 @@ static u64 mpam_msc_read_idr(struct mpam_msc *msc) return (idr_high << 32) | idr_low; } +static void mpam_msc_clear_esr(struct mpam_msc *msc) +{ + u64 esr_low = __mpam_read_reg(msc, MPAMF_ESR); + + if (!esr_low) + return; + + /* + * Clearing the high/low bits of MPAMF_ESR can not be atomic. + * Clear the top half first, so that the pending error bits in the + * lower half prevent hardware from updating either half of the + * register. + */ + if (msc->has_extd_esr) + __mpam_write_reg(msc, MPAMF_ESR + 4, 0); + __mpam_write_reg(msc, MPAMF_ESR, 0); +} + +static u64 mpam_msc_read_esr(struct mpam_msc *msc) +{ + u64 esr_high = 0, esr_low; + + esr_low = __mpam_read_reg(msc, MPAMF_ESR); + if (msc->has_extd_esr) + esr_high = __mpam_read_reg(msc, MPAMF_ESR + 4); + + return (esr_high << 32) | esr_low; +} + static void __mpam_part_sel_raw(u32 partsel, struct mpam_msc *msc) { lockdep_assert_held(&msc->part_sel_lock); @@ -729,6 +761,7 @@ static int mpam_msc_hw_probe(struct mpam_msc *msc) pmg_max = FIELD_GET(MPAMF_IDR_PMG_MAX, idr); msc->partid_max = min(msc->partid_max, partid_max); msc->pmg_max = min(msc->pmg_max, pmg_max); + msc->has_extd_esr = FIELD_GET(MPAMF_IDR_HAS_EXTD_ESR, idr); mutex_lock(&mpam_list_lock); ris = mpam_get_or_create_ris(msc, ris_idx); @@ -743,6 +776,9 @@ static int mpam_msc_hw_probe(struct mpam_msc *msc) mutex_unlock(&msc->part_sel_lock); } + /* Clear any stale errors */ + mpam_msc_clear_esr(msc); + spin_lock(&partid_max_lock); mpam_partid_max = min(mpam_partid_max, msc->partid_max); mpam_pmg_max = min(mpam_pmg_max, msc->pmg_max); @@ -866,6 +902,13 @@ static void mpam_reset_msc(struct mpam_msc *msc, bool online) } } +static void _enable_percpu_irq(void *_irq) +{ + int *irq = _irq; + + enable_percpu_irq(*irq, IRQ_TYPE_NONE); +} + static int mpam_cpu_online(unsigned int cpu) { struct mpam_msc *msc; @@ -876,6 +919,9 @@ static int mpam_cpu_online(unsigned int cpu) if (!cpumask_test_cpu(cpu, &msc->accessibility)) continue; + if (msc->reenable_error_ppi) + _enable_percpu_irq(&msc->reenable_error_ppi); + if (atomic_fetch_inc(&msc->online_refs) == 0) mpam_reset_msc(msc, true); } @@ -926,6 +972,9 @@ static int mpam_cpu_offline(unsigned int cpu) if (!cpumask_test_cpu(cpu, &msc->accessibility)) continue; + if (msc->reenable_error_ppi) + disable_percpu_irq(msc->reenable_error_ppi); + if (atomic_dec_and_test(&msc->online_refs)) mpam_reset_msc(msc, false); } @@ -952,6 +1001,42 @@ static void mpam_register_cpuhp_callbacks(int (*online)(unsigned int online), mutex_unlock(&mpam_cpuhp_state_lock); } +static int __setup_ppi(struct mpam_msc *msc) +{ + int cpu; + + msc->error_dev_id = alloc_percpu(struct mpam_msc *); + if (!msc->error_dev_id) + return -ENOMEM; + + for_each_cpu(cpu, &msc->accessibility) + *per_cpu_ptr(msc->error_dev_id, cpu) = msc; + + return 0; +} + +static int mpam_msc_setup_error_irq(struct mpam_msc *msc) +{ + int irq; + + irq = platform_get_irq_byname_optional(msc->pdev, "error"); + if (irq <= 0) + return 0; + + /* Allocate and initialise the percpu device pointer for PPI */ + if (irq_is_percpu(irq)) + return __setup_ppi(msc); + + /* sanity check: shared interrupts can be routed anywhere? */ + if (!cpumask_equal(&msc->accessibility, cpu_possible_mask)) { + pr_err_once("msc:%u is a private resource with a shared error interrupt", + msc->id); + return -EINVAL; + } + + return 0; +} + /* * An MSC can control traffic from a set of CPUs, but may only be accessible * from a (hopefully wider) set of CPUs. The common reason for this is power @@ -1028,6 +1113,9 @@ static struct mpam_msc *do_mpam_msc_drv_probe(struct platform_device *pdev) if (err) return ERR_PTR(err); + err = devm_mutex_init(dev, &msc->error_irq_lock); + if (err) + return ERR_PTR(err); mpam_mon_sel_lock_init(msc); msc->id = pdev->id; msc->pdev = pdev; @@ -1040,6 +1128,10 @@ static struct mpam_msc *do_mpam_msc_drv_probe(struct platform_device *pdev) return ERR_PTR(-EINVAL); } + err = mpam_msc_setup_error_irq(msc); + if (err) + return ERR_PTR(err); + if (device_property_read_u32(&pdev->dev, "pcc-channel", &tmp)) msc->iface = MPAM_IFACE_MMIO; else @@ -1313,8 +1405,177 @@ static void mpam_enable_merge_features(struct list_head *all_classes_list) } } +static char *mpam_errcode_names[16] = { + [MPAM_ERRCODE_NONE] = "No error", + [MPAM_ERRCODE_PARTID_SEL_RANGE] = "PARTID_SEL_Range", + [MPAM_ERRCODE_REQ_PARTID_RANGE] = "Req_PARTID_Range", + [MPAM_ERRCODE_MSMONCFG_ID_RANGE] = "MSMONCFG_ID_RANGE", + [MPAM_ERRCODE_REQ_PMG_RANGE] = "Req_PMG_Range", + [MPAM_ERRCODE_MONITOR_RANGE] = "Monitor_Range", + [MPAM_ERRCODE_INTPARTID_RANGE] = "intPARTID_Range", + [MPAM_ERRCODE_UNEXPECTED_INTERNAL] = "Unexpected_INTERNAL", + [MPAM_ERRCODE_UNDEFINED_RIS_PART_SEL] = "Undefined_RIS_PART_SEL", + [MPAM_ERRCODE_RIS_NO_CONTROL] = "RIS_No_Control", + [MPAM_ERRCODE_UNDEFINED_RIS_MON_SEL] = "Undefined_RIS_MON_SEL", + [MPAM_ERRCODE_RIS_NO_MONITOR] = "RIS_No_Monitor", + [12 ... 15] = "Reserved" +}; + +static int mpam_enable_msc_ecr(void *_msc) +{ + struct mpam_msc *msc = _msc; + + __mpam_write_reg(msc, MPAMF_ECR, MPAMF_ECR_INTEN); + + return 0; +} + +/* This can run in mpam_disable(), and the interrupt handler on the same CPU */ +static int mpam_disable_msc_ecr(void *_msc) +{ + struct mpam_msc *msc = _msc; + + __mpam_write_reg(msc, MPAMF_ECR, 0); + + return 0; +} + +static irqreturn_t __mpam_irq_handler(int irq, struct mpam_msc *msc) +{ + u64 reg; + u16 partid; + u8 errcode, pmg, ris; + + if (WARN_ON_ONCE(!msc) || + WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), + &msc->accessibility))) + return IRQ_NONE; + + reg = mpam_msc_read_esr(msc); + + errcode = FIELD_GET(MPAMF_ESR_ERRCODE, reg); + if (!errcode) + return IRQ_NONE; + + /* Clear level triggered irq */ + mpam_msc_clear_esr(msc); + + partid = FIELD_GET(MPAMF_ESR_PARTID_MON, reg); + pmg = FIELD_GET(MPAMF_ESR_PMG, reg); + ris = FIELD_GET(MPAMF_ESR_RIS, reg); + + pr_err_ratelimited("error irq from msc:%u '%s', partid:%u, pmg: %u, ris: %u\n", + msc->id, mpam_errcode_names[errcode], partid, pmg, + ris); + + /* Disable this interrupt. */ + mpam_disable_msc_ecr(msc); + + /* + * Schedule the teardown work. Don't use a threaded IRQ as we can't + * unregister the interrupt from the threaded part of the handler. + */ + mpam_disable_reason = "hardware error interrupt"; + schedule_work(&mpam_broken_work); + + return IRQ_HANDLED; +} + +static irqreturn_t mpam_ppi_handler(int irq, void *dev_id) +{ + struct mpam_msc *msc = *(struct mpam_msc **)dev_id; + + return __mpam_irq_handler(irq, msc); +} + +static irqreturn_t mpam_spi_handler(int irq, void *dev_id) +{ + struct mpam_msc *msc = dev_id; + + return __mpam_irq_handler(irq, msc); +} + +static int mpam_register_irqs(void) +{ + int err, irq; + struct mpam_msc *msc; + + lockdep_assert_cpus_held(); + + guard(srcu)(&mpam_srcu); + list_for_each_entry_srcu(msc, &mpam_all_msc, all_msc_list, + srcu_read_lock_held(&mpam_srcu)) { + irq = platform_get_irq_byname_optional(msc->pdev, "error"); + if (irq <= 0) + continue; + + /* The MPAM spec says the interrupt can be SPI, PPI or LPI */ + /* We anticipate sharing the interrupt with other MSCs */ + if (irq_is_percpu(irq)) { + err = request_percpu_irq(irq, &mpam_ppi_handler, + "mpam:msc:error", + msc->error_dev_id); + if (err) + return err; + + msc->reenable_error_ppi = irq; + smp_call_function_many(&msc->accessibility, + &_enable_percpu_irq, &irq, + true); + } else { + err = devm_request_irq(&msc->pdev->dev, irq, + &mpam_spi_handler, IRQF_SHARED, + "mpam:msc:error", msc); + if (err) + return err; + } + + mutex_lock(&msc->error_irq_lock); + msc->error_irq_req = true; + mpam_touch_msc(msc, mpam_enable_msc_ecr, msc); + msc->error_irq_hw_enabled = true; + mutex_unlock(&msc->error_irq_lock); + } + + return 0; +} + +static void mpam_unregister_irqs(void) +{ + int irq; + struct mpam_msc *msc; + + guard(cpus_read_lock)(); + guard(srcu)(&mpam_srcu); + list_for_each_entry_srcu(msc, &mpam_all_msc, all_msc_list, + srcu_read_lock_held(&mpam_srcu)) { + irq = platform_get_irq_byname_optional(msc->pdev, "error"); + if (irq <= 0) + continue; + + mutex_lock(&msc->error_irq_lock); + if (msc->error_irq_hw_enabled) { + mpam_touch_msc(msc, mpam_disable_msc_ecr, msc); + msc->error_irq_hw_enabled = false; + } + + if (msc->error_irq_req) { + if (irq_is_percpu(irq)) { + msc->reenable_error_ppi = 0; + free_percpu_irq(irq, msc->error_dev_id); + } else { + devm_free_irq(&msc->pdev->dev, irq, msc); + } + msc->error_irq_req = false; + } + mutex_unlock(&msc->error_irq_lock); + } +} + static void mpam_enable_once(void) { + int err; + /* * Once the cpuhp callbacks have been changed, mpam_partid_max can no * longer change. @@ -1323,9 +1584,26 @@ static void mpam_enable_once(void) partid_max_published = true; spin_unlock(&partid_max_lock); + /* + * If all the MSC have been probed, enabling the IRQs happens next. + * That involves cross-calling to a CPU that can reach the MSC, and + * the locks must be taken in this order: + */ + cpus_read_lock(); mutex_lock(&mpam_list_lock); mpam_enable_merge_features(&mpam_classes); + + err = mpam_register_irqs(); + mutex_unlock(&mpam_list_lock); + cpus_read_unlock(); + + if (err) { + pr_warn("Failed to register irqs: %d\n", err); + mpam_disable_reason = "Failed to enable."; + schedule_work(&mpam_broken_work); + return; + } mpam_register_cpuhp_callbacks(mpam_cpu_online, mpam_cpu_offline, "mpam:online"); @@ -1393,6 +1671,8 @@ void mpam_disable(struct work_struct *ignored) } mutex_unlock(&mpam_cpuhp_state_lock); + mpam_unregister_irqs(); + idx = srcu_read_lock(&mpam_srcu); list_for_each_entry_srcu(class, &mpam_classes, classes_list, srcu_read_lock_held(&mpam_srcu)) diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h index dec485cd8a91..fa9d9a176a54 100644 --- a/drivers/resctrl/mpam_internal.h +++ b/drivers/resctrl/mpam_internal.h @@ -46,6 +46,11 @@ struct mpam_msc { enum mpam_msc_iface iface; u32 nrdy_usec; cpumask_t accessibility; + bool has_extd_esr; + + int reenable_error_ppi; + struct mpam_msc * __percpu *error_dev_id; + atomic_t online_refs; /* @@ -59,6 +64,14 @@ struct mpam_msc { unsigned long ris_idxs; u32 ris_max; + /* + * error_irq_lock is taken when registering/unregistering the error + * interrupt and maniupulating the below flags. + */ + struct mutex error_irq_lock; + bool error_irq_req; + bool error_irq_hw_enabled; + /* mpam_msc_ris of this component */ struct list_head ris; |