diff options
Diffstat (limited to 'drivers')
353 files changed, 13524 insertions, 3523 deletions
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index b75b734ee73a..19182d091587 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3160,6 +3160,8 @@ static struct acpi_driver acpi_nfit_driver = { static __init int nfit_init(void) { + int ret; + BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40); BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56); BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48); @@ -3187,8 +3189,14 @@ static __init int nfit_init(void) return -ENOMEM; nfit_mce_register(); + ret = acpi_bus_register_driver(&acpi_nfit_driver); + if (ret) { + nfit_mce_unregister(); + destroy_workqueue(nfit_wq); + } + + return ret; - return acpi_bus_register_driver(&acpi_nfit_driver); } static __exit void nfit_exit(void) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index aae4d8d4be36..f7665c31feca 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2200,8 +2200,12 @@ static void binder_transaction(struct binder_proc *proc, list_add_tail(&t->work.entry, target_list); tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; list_add_tail(&tcomplete->entry, &thread->todo); - if (target_wait) - wake_up_interruptible(target_wait); + if (target_wait) { + if (reply || !(t->flags & TF_ONE_WAY)) + wake_up_interruptible_sync(target_wait); + else + wake_up_interruptible(target_wait); + } return; err_translate_failed: @@ -3247,10 +3251,6 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) /*pr_info("binder_ioctl: %d:%d %x %lx\n", proc->pid, current->pid, cmd, arg);*/ - if (unlikely(current->mm != proc->vma_vm_mm)) { - pr_err("current mm mismatch proc mm\n"); - return -EINVAL; - } trace_binder_ioctl(cmd, arg); ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); @@ -3464,9 +3464,8 @@ static int binder_open(struct inode *nodp, struct file *filp) proc = kzalloc(sizeof(*proc), GFP_KERNEL); if (proc == NULL) return -ENOMEM; - get_task_struct(current); - proc->tsk = current; - proc->vma_vm_mm = current->mm; + get_task_struct(current->group_leader); + proc->tsk = current->group_leader; INIT_LIST_HEAD(&proc->todo); init_waitqueue_head(&proc->wait); proc->default_priority = task_nice(current); diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 292dec18ffb8..07bdd51b3b9a 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1613,7 +1613,7 @@ static int zatm_init_one(struct pci_dev *pci_dev, ret = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); if (ret < 0) - goto out_disable; + goto out_release; zatm_dev->pci_dev = pci_dev; dev->dev_data = zatm_dev; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 3b8210ebb50e..60303aa28587 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1222,8 +1222,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, spin_unlock_irq(&dev->power.lock); - dev_pm_domain_set(dev, &genpd->domain); - return gpd_data; err_free: @@ -1237,8 +1235,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, static void genpd_free_dev_data(struct device *dev, struct generic_pm_domain_data *gpd_data) { - dev_pm_domain_set(dev, NULL); - spin_lock_irq(&dev->power.lock); dev->power.subsys_data->domain_data = NULL; @@ -1275,6 +1271,8 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (ret) goto out; + dev_pm_domain_set(dev, &genpd->domain); + genpd->device_count++; genpd->max_off_time_changed = true; @@ -1336,6 +1334,8 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, if (genpd->detach_dev) genpd->detach_dev(genpd, dev); + dev_pm_domain_set(dev, NULL); + list_del_init(&pdd->list_node); genpd_unlock(genpd); diff --git a/drivers/base/regmap/regmap-w1.c b/drivers/base/regmap/regmap-w1.c index 5f04e7bf063e..e6c64b0be5b2 100644 --- a/drivers/base/regmap/regmap-w1.c +++ b/drivers/base/regmap/regmap-w1.c @@ -1,7 +1,7 @@ /* * Register map access API - W1 (1-Wire) support * - * Copyright (C) 2017 OAO Radioavionica + * Copyright (c) 2017 Radioavionica Corporation * Author: Alex A. Mihaylov <minimumlaw@rambler.ru> * * This program is free software; you can redistribute it and/or modify @@ -11,7 +11,7 @@ #include <linux/regmap.h> #include <linux/module.h> -#include "../../w1/w1.h" +#include <linux/w1.h> #include "internal.h" diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index dea7d85134ee..87a0a29f6e7e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -626,7 +626,6 @@ static void recv_work(struct work_struct *work) struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; struct nbd_cmd *cmd; - int ret = 0; while (1) { cmd = nbd_read_stat(nbd, args->index); @@ -636,7 +635,6 @@ static void recv_work(struct work_struct *work) mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); - ret = PTR_ERR(cmd); break; } diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index f6e7491c873c..d509b500a7b5 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -41,8 +41,16 @@ static __init int timer_irq_init(struct device_node *np, struct timer_of *to = container_of(of_irq, struct timer_of, of_irq); struct clock_event_device *clkevt = &to->clkevt; - of_irq->irq = of_irq->name ? of_irq_get_byname(np, of_irq->name): - irq_of_parse_and_map(np, of_irq->index); + if (of_irq->name) { + of_irq->irq = ret = of_irq_get_byname(np, of_irq->name); + if (ret < 0) { + pr_err("Failed to get interrupt %s for %s\n", + of_irq->name, np->full_name); + return ret; + } + } else { + of_irq->irq = irq_of_parse_and_map(np, of_irq->index); + } if (!of_irq->irq) { pr_err("Failed to map interrupt for %s\n", np->full_name); return -EINVAL; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b7fb8b7c980d..6cd503525638 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -225,6 +225,9 @@ struct global_params { * @vid: Stores VID limits for this CPU * @pid: Stores PID parameters for this CPU * @last_sample_time: Last Sample time + * @aperf_mperf_shift: Number of clock cycles after aperf, merf is incremented + * This shift is a multiplier to mperf delta to + * calculate CPU busy. * @prev_aperf: Last APERF value read from APERF MSR * @prev_mperf: Last MPERF value read from MPERF MSR * @prev_tsc: Last timestamp counter (TSC) value @@ -259,6 +262,7 @@ struct cpudata { u64 last_update; u64 last_sample_time; + u64 aperf_mperf_shift; u64 prev_aperf; u64 prev_mperf; u64 prev_tsc; @@ -321,6 +325,7 @@ struct pstate_funcs { int (*get_min)(void); int (*get_turbo)(void); int (*get_scaling)(void); + int (*get_aperf_mperf_shift)(void); u64 (*get_val)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); void (*update_util)(struct update_util_data *data, u64 time, @@ -1486,6 +1491,11 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) return val; } +static int knl_get_aperf_mperf_shift(void) +{ + return 10; +} + static int knl_get_turbo_pstate(void) { u64 value; @@ -1543,6 +1553,9 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + if (pstate_funcs.get_aperf_mperf_shift) + cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); + if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -1616,7 +1629,8 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) int32_t busy_frac, boost; int target, avg_pstate; - busy_frac = div_fp(sample->mperf, sample->tsc); + busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift, + sample->tsc); boost = cpu->iowait_boost; cpu->iowait_boost >>= 1; @@ -1675,7 +1689,8 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns); perf_scaled = mul_fp(perf_scaled, sample_ratio); } else { - sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc); + sample_ratio = div_fp(100 * (cpu->sample.mperf << cpu->aperf_mperf_shift), + cpu->sample.tsc); if (sample_ratio < int_tofp(1)) perf_scaled = 0; } @@ -1807,6 +1822,7 @@ static const struct pstate_funcs knl_funcs = { .get_max_physical = core_get_max_pstate_physical, .get_min = core_get_min_pstate, .get_turbo = knl_get_turbo_pstate, + .get_aperf_mperf_shift = knl_get_aperf_mperf_shift, .get_scaling = core_get_scaling, .get_val = core_get_val, .update_util = intel_pstate_update_util_pid, @@ -2403,6 +2419,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_val = funcs->get_val; pstate_funcs.get_vid = funcs->get_vid; pstate_funcs.update_util = funcs->update_util; + pstate_funcs.get_aperf_mperf_shift = funcs->get_aperf_mperf_shift; intel_pstate_use_acpi_profile(); } diff --git a/drivers/dax/device-dax.h b/drivers/dax/device-dax.h index fdcd9769ffde..688b051750bd 100644 --- a/drivers/dax/device-dax.h +++ b/drivers/dax/device-dax.h @@ -21,5 +21,5 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct resource *res, unsigned int align, void *addr, unsigned long flags); struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, - struct resource *res, int count); + int id, struct resource *res, int count); #endif /* __DEVICE_DAX_H__ */ diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 12943d19bfc4..e9f3b3e4bbf4 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -529,7 +529,8 @@ static void dev_dax_release(struct device *dev) struct dax_region *dax_region = dev_dax->region; struct dax_device *dax_dev = dev_dax->dax_dev; - ida_simple_remove(&dax_region->ida, dev_dax->id); + if (dev_dax->id >= 0) + ida_simple_remove(&dax_region->ida, dev_dax->id); dax_region_put(dax_region); put_dax(dax_dev); kfree(dev_dax); @@ -559,7 +560,7 @@ static void unregister_dev_dax(void *dev) } struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, - struct resource *res, int count) + int id, struct resource *res, int count) { struct device *parent = dax_region->dev; struct dax_device *dax_dev; @@ -567,7 +568,10 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, struct inode *inode; struct device *dev; struct cdev *cdev; - int rc = 0, i; + int rc, i; + + if (!count) + return ERR_PTR(-EINVAL); dev_dax = kzalloc(sizeof(*dev_dax) + sizeof(*res) * count, GFP_KERNEL); if (!dev_dax) @@ -587,10 +591,16 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, if (i < count) goto err_id; - dev_dax->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); - if (dev_dax->id < 0) { - rc = dev_dax->id; - goto err_id; + if (id < 0) { + id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); + dev_dax->id = id; + if (id < 0) { + rc = id; + goto err_id; + } + } else { + /* region provider owns @id lifetime */ + dev_dax->id = -1; } /* @@ -598,8 +608,10 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, * device outside of mmap of the resulting character device. */ dax_dev = alloc_dax(dev_dax, NULL, NULL); - if (!dax_dev) + if (!dax_dev) { + rc = -ENOMEM; goto err_dax; + } /* from here on we're committed to teardown via dax_dev_release() */ dev = &dev_dax->dev; @@ -620,7 +632,7 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, dev->parent = parent; dev->groups = dax_attribute_groups; dev->release = dev_dax_release; - dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id); + dev_set_name(dev, "dax%d.%d", dax_region->id, id); rc = cdev_device_add(cdev, dev); if (rc) { @@ -636,7 +648,8 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, return dev_dax; err_dax: - ida_simple_remove(&dax_region->ida, dev_dax->id); + if (dev_dax->id >= 0) + ida_simple_remove(&dax_region->ida, dev_dax->id); err_id: kfree(dev_dax); diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index 9f2a0b4fd801..8d8c852ba8f2 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -58,13 +58,12 @@ static void dax_pmem_percpu_kill(void *data) static int dax_pmem_probe(struct device *dev) { - int rc; void *addr; struct resource res; + int rc, id, region_id; struct nd_pfn_sb *pfn_sb; struct dev_dax *dev_dax; struct dax_pmem *dax_pmem; - struct nd_region *nd_region; struct nd_namespace_io *nsio; struct dax_region *dax_region; struct nd_namespace_common *ndns; @@ -123,14 +122,17 @@ static int dax_pmem_probe(struct device *dev) /* adjust the dax_region resource to the start of data */ res.start += le64_to_cpu(pfn_sb->dataoff); - nd_region = to_nd_region(dev->parent); - dax_region = alloc_dax_region(dev, nd_region->id, &res, + rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id); + if (rc != 2) + return -EINVAL; + + dax_region = alloc_dax_region(dev, region_id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); if (!dax_region) return -ENOMEM; /* TODO: support for subdividing a dax region... */ - dev_dax = devm_create_dev_dax(dax_region, &res, 1); + dev_dax = devm_create_dev_dax(dax_region, id, &res, 1); /* child dev_dax instances now own the lifetime of the dax_region */ dax_region_put(dax_region); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 57da14c15987..56e0a0e1b600 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -75,11 +75,6 @@ int dma_fence_signal_locked(struct dma_fence *fence) if (WARN_ON(!fence)) return -EINVAL; - if (!ktime_to_ns(fence->timestamp)) { - fence->timestamp = ktime_get(); - smp_mb__before_atomic(); - } - if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { ret = -EINVAL; @@ -87,8 +82,11 @@ int dma_fence_signal_locked(struct dma_fence *fence) * we might have raced with the unlocked dma_fence_signal, * still run through all callbacks */ - } else + } else { + fence->timestamp = ktime_get(); + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); trace_dma_fence_signaled(fence); + } list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { list_del_init(&cur->node); @@ -115,14 +113,11 @@ int dma_fence_signal(struct dma_fence *fence) if (!fence) return -EINVAL; - if (!ktime_to_ns(fence->timestamp)) { - fence->timestamp = ktime_get(); - smp_mb__before_atomic(); - } - if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) return -EINVAL; + fence->timestamp = ktime_get(); + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); trace_dma_fence_signaled(fence); if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) { diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c index 82a6e7f6d37f..59a3b2f8ee91 100644 --- a/drivers/dma-buf/sync_debug.c +++ b/drivers/dma-buf/sync_debug.c @@ -84,7 +84,7 @@ static void sync_print_fence(struct seq_file *s, show ? "_" : "", sync_status_str(status)); - if (status) { + if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) { struct timespec64 ts64 = ktime_to_timespec64(fence->timestamp); diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 545e2c5c4815..d7e219d2669d 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -391,7 +391,13 @@ static void sync_fill_fence_info(struct dma_fence *fence, sizeof(info->driver_name)); info->status = dma_fence_get_status(fence); - info->timestamp_ns = ktime_to_ns(fence->timestamp); + while (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && + !test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) + cpu_relax(); + info->timestamp_ns = + test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ? + ktime_to_ns(fence->timestamp) : + ktime_set(0, 0); } static long sync_file_ioctl_fence_info(struct sync_file *sync_file, diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c index a485864cb512..06432d84cbf8 100644 --- a/drivers/fsi/fsi-core.c +++ b/drivers/fsi/fsi-core.c @@ -532,7 +532,7 @@ static inline uint32_t fsi_smode_sid(int x) return (x & FSI_SMODE_SID_MASK) << FSI_SMODE_SID_SHIFT; } -static const uint32_t fsi_slave_smode(int id) +static uint32_t fsi_slave_smode(int id) { return FSI_SMODE_WSC | FSI_SMODE_ECRC | fsi_smode_sid(id) @@ -883,17 +883,16 @@ struct bus_type fsi_bus_type = { }; EXPORT_SYMBOL_GPL(fsi_bus_type); -static int fsi_init(void) +static int __init fsi_init(void) { return bus_register(&fsi_bus_type); } +postcore_initcall(fsi_init); static void fsi_exit(void) { bus_unregister(&fsi_bus_type); } - -module_init(fsi_init); module_exit(fsi_exit); module_param(discard_errors, int, 0664); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 5f8ada1d872b..37971d9402e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -101,7 +101,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) if (adev->kfd) { struct kgd2kfd_shared_resources gpu_resources = { .compute_vmid_bitmap = 0xFF00, - .num_mec = adev->gfx.mec.num_mec, .num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec, .num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe }; @@ -122,7 +121,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) /* According to linux/bitmap.h we shouldn't use bitmap_clear if * nbits is not compile time constant */ - last_valid_bit = adev->gfx.mec.num_mec + last_valid_bit = 1 /* only first MEC can have compute queues */ * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 88187bfc5ea3..3f95f7cb4019 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -226,10 +226,6 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd->shared_resources = *gpu_resources; - /* We only use the first MEC */ - if (kfd->shared_resources.num_mec > 1) - kfd->shared_resources.num_mec = 1; - /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * kfd->device_info->mqd_size_aligned; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 955aa304ff48..602769ced3bd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -77,13 +77,6 @@ static bool is_pipe_enabled(struct device_queue_manager *dqm, int mec, int pipe) return false; } -unsigned int get_mec_num(struct device_queue_manager *dqm) -{ - BUG_ON(!dqm || !dqm->dev); - - return dqm->dev->shared_resources.num_mec; -} - unsigned int get_queues_num(struct device_queue_manager *dqm) { BUG_ON(!dqm || !dqm->dev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 66b9615bc3c1..faf820a06400 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -180,7 +180,6 @@ void device_queue_manager_init_cik(struct device_queue_manager_asic_ops *ops); void device_queue_manager_init_vi(struct device_queue_manager_asic_ops *ops); void program_sh_mem_settings(struct device_queue_manager *dqm, struct qcm_process_device *qpd); -unsigned int get_mec_num(struct device_queue_manager *dqm); unsigned int get_queues_num(struct device_queue_manager *dqm); unsigned int get_queues_per_pipe(struct device_queue_manager *dqm); unsigned int get_pipes_per_mec(struct device_queue_manager *dqm); diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index 91ef1484b3bb..36f376677a53 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -63,9 +63,6 @@ struct kgd2kfd_shared_resources { /* Bit n == 1 means VMID n is available for KFD. */ unsigned int compute_vmid_bitmap; - /* number of mec available from the hardware */ - uint32_t num_mec; - /* number of pipes per mec */ uint32_t num_pipe_per_mec; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index bfd237c15e76..ae5f06895562 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -330,6 +330,13 @@ static bool drm_dp_sideband_msg_build(struct drm_dp_sideband_msg_rx *msg, return false; } + /* + * ignore out-of-order messages or messages that are part of a + * failed transaction + */ + if (!recv_hdr.somt && !msg->have_somt) + return false; + /* get length contained in this portion */ msg->curchunk_len = recv_hdr.msg_len; msg->curchunk_hdrlen = hdrlen; @@ -2164,7 +2171,7 @@ out_unlock: } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_resume); -static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) +static bool drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) { int len; u8 replyblock[32]; @@ -2179,12 +2186,12 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) replyblock, len); if (ret != len) { DRM_DEBUG_KMS("failed to read DPCD down rep %d %d\n", len, ret); - return; + return false; } ret = drm_dp_sideband_msg_build(msg, replyblock, len, true); if (!ret) { DRM_DEBUG_KMS("sideband msg build failed %d\n", replyblock[0]); - return; + return false; } replylen = msg->curchunk_len + msg->curchunk_hdrlen; @@ -2196,21 +2203,32 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) ret = drm_dp_dpcd_read(mgr->aux, basereg + curreply, replyblock, len); if (ret != len) { - DRM_DEBUG_KMS("failed to read a chunk\n"); + DRM_DEBUG_KMS("failed to read a chunk (len %d, ret %d)\n", + len, ret); + return false; } + ret = drm_dp_sideband_msg_build(msg, replyblock, len, false); - if (ret == false) + if (!ret) { DRM_DEBUG_KMS("failed to build sideband msg\n"); + return false; + } + curreply += len; replylen -= len; } + return true; } static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) { int ret = 0; - drm_dp_get_one_sb_msg(mgr, false); + if (!drm_dp_get_one_sb_msg(mgr, false)) { + memset(&mgr->down_rep_recv, 0, + sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } if (mgr->down_rep_recv.have_eomt) { struct drm_dp_sideband_msg_tx *txmsg; @@ -2266,7 +2284,12 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) { int ret = 0; - drm_dp_get_one_sb_msg(mgr, true); + + if (!drm_dp_get_one_sb_msg(mgr, true)) { + memset(&mgr->up_req_recv, 0, + sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } if (mgr->up_req_recv.have_eomt) { struct drm_dp_sideband_msg_req_body msg; @@ -2318,7 +2341,9 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn); } - drm_dp_put_mst_branch_device(mstb); + if (mstb) + drm_dp_put_mst_branch_device(mstb); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); } return ret; diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 49546222c6d3..6276bb834b4f 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -54,7 +54,7 @@ static const uint32_t ipu_plane_formats[] = { DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBX8888, DRM_FORMAT_BGRA8888, - DRM_FORMAT_BGRA8888, + DRM_FORMAT_BGRX8888, DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_YUYV, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 636031a30e17..8aca20209cb8 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -237,7 +237,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) /* port@1 is the output port */ ret = drm_of_find_panel_or_bridge(np, 1, 0, &imxpd->panel, &imxpd->bridge); - if (ret) + if (ret && ret != -ENODEV) return ret; imxpd->dev = dev; diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c index 699fe7f9b8bf..a2ab6dcdf4a2 100644 --- a/drivers/gpu/drm/radeon/radeon_kfd.c +++ b/drivers/gpu/drm/radeon/radeon_kfd.c @@ -184,7 +184,6 @@ void radeon_kfd_device_init(struct radeon_device *rdev) if (rdev->kfd) { struct kgd2kfd_shared_resources gpu_resources = { .compute_vmid_bitmap = 0xFF00, - .num_mec = 1, .num_pipe_per_mec = 4, .num_queue_per_pipe = 8 }; diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 403bbd5f99a9..a12cc7ea99b6 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -520,6 +520,34 @@ static void vc4_crtc_disable(struct drm_crtc *crtc) SCALER_DISPSTATX_EMPTY); } +static void vc4_crtc_update_dlist(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); + struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); + + if (crtc->state->event) { + unsigned long flags; + + crtc->state->event->pipe = drm_crtc_index(crtc); + + WARN_ON(drm_crtc_vblank_get(crtc) != 0); + + spin_lock_irqsave(&dev->event_lock, flags); + vc4_crtc->event = crtc->state->event; + crtc->state->event = NULL; + + HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), + vc4_state->mm.start); + + spin_unlock_irqrestore(&dev->event_lock, flags); + } else { + HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), + vc4_state->mm.start); + } +} + static void vc4_crtc_enable(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -530,6 +558,12 @@ static void vc4_crtc_enable(struct drm_crtc *crtc) require_hvs_enabled(dev); + /* Enable vblank irq handling before crtc is started otherwise + * drm_crtc_get_vblank() fails in vc4_crtc_update_dlist(). + */ + drm_crtc_vblank_on(crtc); + vc4_crtc_update_dlist(crtc); + /* Turn on the scaler, which will wait for vstart to start * compositing. */ @@ -541,9 +575,6 @@ static void vc4_crtc_enable(struct drm_crtc *crtc) /* Turn on the pixel valve, which will emit the vstart signal. */ CRTC_WRITE(PV_V_CONTROL, CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN); - - /* Enable vblank irq handling after crtc is started. */ - drm_crtc_vblank_on(crtc); } static bool vc4_crtc_mode_fixup(struct drm_crtc *crtc, @@ -598,7 +629,6 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, { struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); struct drm_plane *plane; bool debug_dump_regs = false; @@ -620,25 +650,15 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, WARN_ON_ONCE(dlist_next - dlist_start != vc4_state->mm.size); - if (crtc->state->event) { - unsigned long flags; - - crtc->state->event->pipe = drm_crtc_index(crtc); - - WARN_ON(drm_crtc_vblank_get(crtc) != 0); - - spin_lock_irqsave(&dev->event_lock, flags); - vc4_crtc->event = crtc->state->event; - crtc->state->event = NULL; - - HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), - vc4_state->mm.start); - - spin_unlock_irqrestore(&dev->event_lock, flags); - } else { - HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), - vc4_state->mm.start); - } + /* Only update DISPLIST if the CRTC was already running and is not + * being disabled. + * vc4_crtc_enable() takes care of updating the dlist just after + * re-enabling VBLANK interrupts and before enabling the engine. + * If the CRTC is being disabled, there's no point in updating this + * information. + */ + if (crtc->state->active && old_state->active) + vc4_crtc_update_dlist(crtc); if (debug_dump_regs) { DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc)); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 41b39464ded8..501e16a9227d 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -2732,6 +2732,9 @@ static int hidpp_initialize_battery(struct hidpp_device *hidpp) hidpp_battery_props, sizeof(hidpp_battery_props), GFP_KERNEL); + if (!battery_props) + return -ENOMEM; + num_battery_props = ARRAY_SIZE(hidpp_battery_props) - 2; if (hidpp->capabilities & HIDPP_CAPABILITY_BATTERY_MILEAGE) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index f3e35e7a189d..aff20f4b6d97 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -620,16 +620,6 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 0; } -static int mt_touch_input_mapped(struct hid_device *hdev, struct hid_input *hi, - struct hid_field *field, struct hid_usage *usage, - unsigned long **bit, int *max) -{ - if (usage->type == EV_KEY || usage->type == EV_ABS) - set_bit(usage->type, hi->input->evbit); - - return -1; -} - static int mt_compute_slot(struct mt_device *td, struct input_dev *input) { __s32 quirks = td->mtclass.quirks; @@ -969,8 +959,10 @@ static int mt_input_mapped(struct hid_device *hdev, struct hid_input *hi, return 0; if (field->application == HID_DG_TOUCHSCREEN || - field->application == HID_DG_TOUCHPAD) - return mt_touch_input_mapped(hdev, hi, field, usage, bit, max); + field->application == HID_DG_TOUCHPAD) { + /* We own these mappings, tell hid-input to ignore them */ + return -1; + } /* let hid-core decide for the others */ return 0; diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index e9bf0bb87ac4..e57cc40cb768 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -606,6 +606,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel) get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); out: + /* re-enable tasklet for use on re-open */ + tasklet_enable(&channel->callback_event); return ret; } diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 0af7fd311979..76c34f4fde13 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -566,6 +566,8 @@ static int applesmc_init_smcreg_try(void) if (ret) return ret; s->fan_count = tmp[0]; + if (s->fan_count > 10) + s->fan_count = 10; ret = applesmc_get_lower_bound(&s->temp_begin, "T"); if (ret) @@ -811,7 +813,8 @@ static ssize_t applesmc_show_fan_speed(struct device *dev, char newkey[5]; u8 buffer[2]; - sprintf(newkey, fan_speed_fmt[to_option(attr)], to_index(attr)); + scnprintf(newkey, sizeof(newkey), fan_speed_fmt[to_option(attr)], + to_index(attr)); ret = applesmc_read_key(newkey, buffer, 2); speed = ((buffer[0] << 8 | buffer[1]) >> 2); @@ -834,7 +837,8 @@ static ssize_t applesmc_store_fan_speed(struct device *dev, if (kstrtoul(sysfsbuf, 10, &speed) < 0 || speed >= 0x4000) return -EINVAL; /* Bigger than a 14-bit value */ - sprintf(newkey, fan_speed_fmt[to_option(attr)], to_index(attr)); + scnprintf(newkey, sizeof(newkey), fan_speed_fmt[to_option(attr)], + to_index(attr)); buffer[0] = (speed >> 6) & 0xff; buffer[1] = (speed << 2) & 0xff; @@ -903,7 +907,7 @@ static ssize_t applesmc_show_fan_position(struct device *dev, char newkey[5]; u8 buffer[17]; - sprintf(newkey, FAN_ID_FMT, to_index(attr)); + scnprintf(newkey, sizeof(newkey), FAN_ID_FMT, to_index(attr)); ret = applesmc_read_key(newkey, buffer, 16); buffer[16] = 0; @@ -1116,7 +1120,8 @@ static int applesmc_create_nodes(struct applesmc_node_group *groups, int num) } for (i = 0; i < num; i++) { node = &grp->nodes[i]; - sprintf(node->name, grp->format, i + 1); + scnprintf(node->name, sizeof(node->name), grp->format, + i + 1); node->sda.index = (grp->option << 16) | (i & 0xffff); node->sda.dev_attr.show = grp->show; node->sda.dev_attr.store = grp->store; diff --git a/drivers/ide/ide-timings.c b/drivers/ide/ide-timings.c index 0e05f75934c9..1858e3ce3993 100644 --- a/drivers/ide/ide-timings.c +++ b/drivers/ide/ide-timings.c @@ -104,19 +104,19 @@ u16 ide_pio_cycle_time(ide_drive_t *drive, u8 pio) EXPORT_SYMBOL_GPL(ide_pio_cycle_time); #define ENOUGH(v, unit) (((v) - 1) / (unit) + 1) -#define EZ(v, unit) ((v) ? ENOUGH(v, unit) : 0) +#define EZ(v, unit) ((v) ? ENOUGH((v) * 1000, unit) : 0) static void ide_timing_quantize(struct ide_timing *t, struct ide_timing *q, int T, int UT) { - q->setup = EZ(t->setup * 1000, T); - q->act8b = EZ(t->act8b * 1000, T); - q->rec8b = EZ(t->rec8b * 1000, T); - q->cyc8b = EZ(t->cyc8b * 1000, T); - q->active = EZ(t->active * 1000, T); - q->recover = EZ(t->recover * 1000, T); - q->cycle = EZ(t->cycle * 1000, T); - q->udma = EZ(t->udma * 1000, UT); + q->setup = EZ(t->setup, T); + q->act8b = EZ(t->act8b, T); + q->rec8b = EZ(t->rec8b, T); + q->cyc8b = EZ(t->cyc8b, T); + q->active = EZ(t->active, T); + q->recover = EZ(t->recover, T); + q->cycle = EZ(t->cycle, T); + q->udma = EZ(t->udma, UT); } void ide_timing_merge(struct ide_timing *a, struct ide_timing *b, diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile index e3cdafff8ece..920609a0872e 100644 --- a/drivers/infiniband/core/Makefile +++ b/drivers/infiniband/core/Makefile @@ -11,7 +11,8 @@ ib_core-y := packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \ device.o fmr_pool.o cache.o netlink.o \ roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \ multicast.o mad.o smi.o agent.o mad_rmpp.o \ - security.o + security.o nldev.o + ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 437522ca97b4..12523f630b61 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -130,13 +130,11 @@ static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh) } int ib_nl_handle_ip_res_resp(struct sk_buff *skb, - struct netlink_callback *cb) + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { - const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh; - if ((nlh->nlmsg_flags & NLM_F_REQUEST) || - !(NETLINK_CB(skb).sk) || - !netlink_capable(skb, CAP_NET_ADMIN)) + !(NETLINK_CB(skb).sk)) return -EPERM; if (ib_nl_is_good_ip_resp(nlh)) @@ -186,7 +184,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr, /* Repair the nlmsg header length */ nlmsg_end(skb, nlh); - ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL); + rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL); /* Make the request retry, so when we get the response from userspace * we will have something. @@ -326,7 +324,7 @@ static void queue_req(struct addr_req *req) static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr, const void *daddr, u32 seq, u16 family) { - if (ibnl_chk_listeners(RDMA_NL_GROUP_LS)) + if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) return -EADDRNOTAVAIL; /* We fill in what we can, the response will fill the rest */ diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 2b4d613a3474..7a389697e2ec 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1175,6 +1175,11 @@ static void cm_format_req(struct cm_req_msg *req_msg, { struct sa_path_rec *pri_path = param->primary_path; struct sa_path_rec *alt_path = param->alternate_path; + bool pri_ext = false; + + if (pri_path->rec_type == SA_PATH_REC_TYPE_OPA) + pri_ext = opa_is_extended_lid(pri_path->opa.dlid, + pri_path->opa.slid); cm_format_mad_hdr(&req_msg->hdr, CM_REQ_ATTR_ID, cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_REQ)); @@ -1202,18 +1207,24 @@ static void cm_format_req(struct cm_req_msg *req_msg, cm_req_set_srq(req_msg, param->srq); } + req_msg->primary_local_gid = pri_path->sgid; + req_msg->primary_remote_gid = pri_path->dgid; + if (pri_ext) { + req_msg->primary_local_gid.global.interface_id + = OPA_MAKE_ID(be32_to_cpu(pri_path->opa.slid)); + req_msg->primary_remote_gid.global.interface_id + = OPA_MAKE_ID(be32_to_cpu(pri_path->opa.dlid)); + } if (pri_path->hop_limit <= 1) { - req_msg->primary_local_lid = + req_msg->primary_local_lid = pri_ext ? 0 : htons(ntohl(sa_path_get_slid(pri_path))); - req_msg->primary_remote_lid = + req_msg->primary_remote_lid = pri_ext ? 0 : htons(ntohl(sa_path_get_dlid(pri_path))); } else { /* Work-around until there's a way to obtain remote LID info */ req_msg->primary_local_lid = IB_LID_PERMISSIVE; req_msg->primary_remote_lid = IB_LID_PERMISSIVE; } - req_msg->primary_local_gid = pri_path->sgid; - req_msg->primary_remote_gid = pri_path->dgid; cm_req_set_primary_flow_label(req_msg, pri_path->flow_label); cm_req_set_primary_packet_rate(req_msg, pri_path->rate); req_msg->primary_traffic_class = pri_path->traffic_class; @@ -1225,17 +1236,29 @@ static void cm_format_req(struct cm_req_msg *req_msg, pri_path->packet_life_time)); if (alt_path) { + bool alt_ext = false; + + if (alt_path->rec_type == SA_PATH_REC_TYPE_OPA) + alt_ext = opa_is_extended_lid(alt_path->opa.dlid, + alt_path->opa.slid); + + req_msg->alt_local_gid = alt_path->sgid; + req_msg->alt_remote_gid = alt_path->dgid; + if (alt_ext) { + req_msg->alt_local_gid.global.interface_id + = OPA_MAKE_ID(be32_to_cpu(alt_path->opa.slid)); + req_msg->alt_remote_gid.global.interface_id + = OPA_MAKE_ID(be32_to_cpu(alt_path->opa.dlid)); + } if (alt_path->hop_limit <= 1) { - req_msg->alt_local_lid = + req_msg->alt_local_lid = alt_ext ? 0 : htons(ntohl(sa_path_get_slid(alt_path))); - req_msg->alt_remote_lid = + req_msg->alt_remote_lid = alt_ext ? 0 : htons(ntohl(sa_path_get_dlid(alt_path))); } else { req_msg->alt_local_lid = IB_LID_PERMISSIVE; req_msg->alt_remote_lid = IB_LID_PERMISSIVE; } - req_msg->alt_local_gid = alt_path->sgid; - req_msg->alt_remote_gid = alt_path->dgid; cm_req_set_alt_flow_label(req_msg, alt_path->flow_label); cm_req_set_alt_packet_rate(req_msg, alt_path->rate); @@ -1405,16 +1428,63 @@ static inline int cm_is_active_peer(__be64 local_ca_guid, __be64 remote_ca_guid, (be32_to_cpu(local_qpn) > be32_to_cpu(remote_qpn)))); } +static bool cm_req_has_alt_path(struct cm_req_msg *req_msg) +{ + return ((req_msg->alt_local_lid) || + (ib_is_opa_gid(&req_msg->alt_local_gid))); +} + +static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num, + struct sa_path_rec *path, union ib_gid *gid) +{ + if (ib_is_opa_gid(gid) && rdma_cap_opa_ah(ib_device, port_num)) + path->rec_type = SA_PATH_REC_TYPE_OPA; + else + path->rec_type = SA_PATH_REC_TYPE_IB; +} + +static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg, + struct sa_path_rec *primary_path, + struct sa_path_rec *alt_path) +{ + u32 lid; + + if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) { + sa_path_set_dlid(primary_path, + htonl(ntohs(req_msg->primary_local_lid))); + sa_path_set_slid(primary_path, + htonl(ntohs(req_msg->primary_remote_lid))); + } else { + lid = opa_get_lid_from_gid(&req_msg->primary_local_gid); + sa_path_set_dlid(primary_path, cpu_to_be32(lid)); + + lid = opa_get_lid_from_gid(&req_msg->primary_remote_gid); + sa_path_set_slid(primary_path, cpu_to_be32(lid)); + } + + if (!cm_req_has_alt_path(req_msg)) + return; + + if (alt_path->rec_type != SA_PATH_REC_TYPE_OPA) { + sa_path_set_dlid(alt_path, + htonl(ntohs(req_msg->alt_local_lid))); + sa_path_set_slid(alt_path, + htonl(ntohs(req_msg->alt_remote_lid))); + } else { + lid = opa_get_lid_from_gid(&req_msg->alt_local_gid); + sa_path_set_dlid(alt_path, cpu_to_be32(lid)); + + lid = opa_get_lid_from_gid(&req_msg->alt_remote_gid); + sa_path_set_slid(alt_path, cpu_to_be32(lid)); + } +} + static void cm_format_paths_from_req(struct cm_req_msg *req_msg, struct sa_path_rec *primary_path, struct sa_path_rec *alt_path) { primary_path->dgid = req_msg->primary_local_gid; primary_path->sgid = req_msg->primary_remote_gid; - sa_path_set_dlid(primary_path, - htonl(ntohs(req_msg->primary_local_lid))); - sa_path_set_slid(primary_path, - htonl(ntohs(req_msg->primary_remote_lid))); primary_path->flow_label = cm_req_get_primary_flow_label(req_msg); primary_path->hop_limit = req_msg->primary_hop_limit; primary_path->traffic_class = req_msg->primary_traffic_class; @@ -1431,13 +1501,9 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg, primary_path->packet_life_time -= (primary_path->packet_life_time > 0); primary_path->service_id = req_msg->service_id; - if (req_msg->alt_local_lid) { + if (cm_req_has_alt_path(req_msg)) { alt_path->dgid = req_msg->alt_local_gid; alt_path->sgid = req_msg->alt_remote_gid; - sa_path_set_dlid(alt_path, - htonl(ntohs(req_msg->alt_local_lid))); - sa_path_set_slid(alt_path, - htonl(ntohs(req_msg->alt_remote_lid))); alt_path->flow_label = cm_req_get_alt_flow_label(req_msg); alt_path->hop_limit = req_msg->alt_hop_limit; alt_path->traffic_class = req_msg->alt_traffic_class; @@ -1454,6 +1520,7 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg, alt_path->packet_life_time -= (alt_path->packet_life_time > 0); alt_path->service_id = req_msg->service_id; } + cm_format_path_lid_from_req(req_msg, primary_path, alt_path); } static u16 cm_get_bth_pkey(struct cm_work *work) @@ -1703,7 +1770,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc) { if (!cm_req_get_primary_subnet_local(req_msg)) { if (req_msg->primary_local_lid == IB_LID_PERMISSIVE) { - req_msg->primary_local_lid = cpu_to_be16(wc->slid); + req_msg->primary_local_lid = ib_slid_be16(wc->slid); cm_req_set_primary_sl(req_msg, wc->sl); } @@ -1713,7 +1780,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc) if (!cm_req_get_alt_subnet_local(req_msg)) { if (req_msg->alt_local_lid == IB_LID_PERMISSIVE) { - req_msg->alt_local_lid = cpu_to_be16(wc->slid); + req_msg->alt_local_lid = ib_slid_be16(wc->slid); cm_req_set_alt_sl(req_msg, wc->sl); } @@ -1784,9 +1851,12 @@ static int cm_req_handler(struct cm_work *work) dev_net(gid_attr.ndev)); dev_put(gid_attr.ndev); } else { - work->path[0].rec_type = SA_PATH_REC_TYPE_IB; + cm_path_set_rec_type(work->port->cm_dev->ib_device, + work->port->port_num, + &work->path[0], + &req_msg->primary_local_gid); } - if (req_msg->alt_local_lid) + if (cm_req_has_alt_path(req_msg)) work->path[1].rec_type = work->path[0].rec_type; cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]); @@ -1811,16 +1881,19 @@ static int cm_req_handler(struct cm_work *work) dev_net(gid_attr.ndev)); dev_put(gid_attr.ndev); } else { - work->path[0].rec_type = SA_PATH_REC_TYPE_IB; + cm_path_set_rec_type(work->port->cm_dev->ib_device, + work->port->port_num, + &work->path[0], + &req_msg->primary_local_gid); } - if (req_msg->alt_local_lid) + if (cm_req_has_alt_path(req_msg)) work->path[1].rec_type = work->path[0].rec_type; ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID, &work->path[0].sgid, sizeof work->path[0].sgid, NULL, 0); goto rejected; } - if (req_msg->alt_local_lid) { + if (cm_req_has_alt_path(req_msg)) { ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av, cm_id_priv); if (ret) { @@ -2843,6 +2916,11 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg, const void *private_data, u8 private_data_len) { + bool alt_ext = false; + + if (alternate_path->rec_type == SA_PATH_REC_TYPE_OPA) + alt_ext = opa_is_extended_lid(alternate_path->opa.dlid, + alternate_path->opa.slid); cm_format_mad_hdr(&lap_msg->hdr, CM_LAP_ATTR_ID, cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_LAP)); lap_msg->local_comm_id = cm_id_priv->id.local_id; @@ -2856,6 +2934,12 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg, htons(ntohl(sa_path_get_dlid(alternate_path))); lap_msg->alt_local_gid = alternate_path->sgid; lap_msg->alt_remote_gid = alternate_path->dgid; + if (alt_ext) { + lap_msg->alt_local_gid.global.interface_id + = OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.slid)); + lap_msg->alt_remote_gid.global.interface_id + = OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.dlid)); + } cm_lap_set_flow_label(lap_msg, alternate_path->flow_label); cm_lap_set_traffic_class(lap_msg, alternate_path->traffic_class); lap_msg->alt_hop_limit = alternate_path->hop_limit; @@ -2924,16 +3008,29 @@ out: spin_unlock_irqrestore(&cm_id_priv->lock, flags); } EXPORT_SYMBOL(ib_send_cm_lap); +static void cm_format_path_lid_from_lap(struct cm_lap_msg *lap_msg, + struct sa_path_rec *path) +{ + u32 lid; + + if (path->rec_type != SA_PATH_REC_TYPE_OPA) { + sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid))); + sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid))); + } else { + lid = opa_get_lid_from_gid(&lap_msg->alt_local_gid); + sa_path_set_dlid(path, cpu_to_be32(lid)); + + lid = opa_get_lid_from_gid(&lap_msg->alt_remote_gid); + sa_path_set_slid(path, cpu_to_be32(lid)); + } +} + static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv, struct sa_path_rec *path, struct cm_lap_msg *lap_msg) { - memset(path, 0, sizeof *path); - path->rec_type = SA_PATH_REC_TYPE_IB; path->dgid = lap_msg->alt_local_gid; path->sgid = lap_msg->alt_remote_gid; - sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid))); - sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid))); path->flow_label = cm_lap_get_flow_label(lap_msg); path->hop_limit = lap_msg->alt_hop_limit; path->traffic_class = cm_lap_get_traffic_class(lap_msg); @@ -2947,6 +3044,7 @@ static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv, path->packet_life_time_selector = IB_SA_EQ; path->packet_life_time = cm_lap_get_local_ack_timeout(lap_msg); path->packet_life_time -= (path->packet_life_time > 0); + cm_format_path_lid_from_lap(lap_msg, path); } static int cm_lap_handler(struct cm_work *work) @@ -2965,6 +3063,11 @@ static int cm_lap_handler(struct cm_work *work) return -EINVAL; param = &work->cm_event.param.lap_rcvd; + memset(&work->path[0], 0, sizeof(work->path[1])); + cm_path_set_rec_type(work->port->cm_dev->ib_device, + work->port->port_num, + &work->path[0], + &lap_msg->alt_local_gid); param->alternate_path = &work->path[0]; cm_format_path_from_lap(cm_id_priv, param->alternate_path, lap_msg); work->cm_event.private_data = &lap_msg->private_data; @@ -4201,7 +4304,7 @@ static int __init ib_cm_init(void) goto error1; } - cm.wq = create_workqueue("ib_cm"); + cm.wq = alloc_workqueue("ib_cm", 0, 1); if (!cm.wq) { ret = -ENOMEM; goto error2; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 0eb393237ba2..d8edd8b11561 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -72,6 +72,7 @@ MODULE_LICENSE("Dual BSD/GPL"); #define CMA_MAX_CM_RETRIES 15 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24) #define CMA_IBOE_PACKET_LIFETIME 18 +#define CMA_PREFERRED_ROCE_GID_TYPE (1 << IB_GID_TYPE_ROCE_UDP_ENCAP) static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", @@ -3998,7 +3999,8 @@ static void iboe_mcast_work_handler(struct work_struct *work) kfree(mw); } -static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid) +static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, + enum ib_gid_type gid_type) { struct sockaddr_in *sin = (struct sockaddr_in *)addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; @@ -4008,8 +4010,8 @@ static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid) } else if (addr->sa_family == AF_INET6) { memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else { - mgid->raw[0] = 0xff; - mgid->raw[1] = 0x0e; + mgid->raw[0] = (gid_type == IB_GID_TYPE_IB) ? 0xff : 0; + mgid->raw[1] = (gid_type == IB_GID_TYPE_IB) ? 0x0e : 0; mgid->raw[2] = 0; mgid->raw[3] = 0; mgid->raw[4] = 0; @@ -4050,7 +4052,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, goto out1; } - cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid); + gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - + rdma_start_port(id_priv->cma_dev->device)]; + cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid, gid_type); mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff); if (id_priv->id.ps == RDMA_PS_UDP) @@ -4066,8 +4070,6 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, mc->multicast.ib->rec.hop_limit = 1; mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu); - gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - - rdma_start_port(id_priv->cma_dev->device)]; if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; @@ -4280,8 +4282,12 @@ static void cma_add_one(struct ib_device *device) for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) { supported_gids = roce_gid_type_mask_support(device, i); WARN_ON(!supported_gids); - cma_dev->default_gid_type[i - rdma_start_port(device)] = - find_first_bit(&supported_gids, BITS_PER_LONG); + if (supported_gids & CMA_PREFERRED_ROCE_GID_TYPE) + cma_dev->default_gid_type[i - rdma_start_port(device)] = + CMA_PREFERRED_ROCE_GID_TYPE; + else + cma_dev->default_gid_type[i - rdma_start_port(device)] = + find_first_bit(&supported_gids, BITS_PER_LONG); cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0; } @@ -4452,9 +4458,8 @@ out: return skb->len; } -static const struct ibnl_client_cbs cma_cb_table[] = { - [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats, - .module = THIS_MODULE }, +static const struct rdma_nl_cbs cma_cb_table[] = { + [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats}, }; static int cma_init_net(struct net *net) @@ -4506,9 +4511,7 @@ static int __init cma_init(void) if (ret) goto err; - if (ibnl_add_client(RDMA_NL_RDMA_CM, ARRAY_SIZE(cma_cb_table), - cma_cb_table)) - pr_warn("RDMA CMA: failed to add netlink callback\n"); + rdma_nl_register(RDMA_NL_RDMA_CM, cma_cb_table); cma_configfs_init(); return 0; @@ -4525,7 +4528,7 @@ err_wq: static void __exit cma_cleanup(void) { cma_configfs_exit(); - ibnl_remove_client(RDMA_NL_RDMA_CM); + rdma_nl_unregister(RDMA_NL_RDMA_CM); ib_unregister_client(&cma_client); unregister_netdevice_notifier(&cma_nb); rdma_addr_unregister_client(&addr_client); diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 11ae67514e13..a1d687a664f8 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -38,6 +38,7 @@ #include <linux/cgroup_rdma.h> #include <rdma/ib_verbs.h> +#include <rdma/opa_addr.h> #include <rdma/ib_mad.h> #include "mad_priv.h" @@ -102,6 +103,14 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, roce_netdev_callback cb, void *cookie); +typedef int (*nldev_callback)(struct ib_device *device, + struct sk_buff *skb, + struct netlink_callback *cb, + unsigned int idx); + +int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, + struct netlink_callback *cb); + enum ib_cache_gid_default_mode { IB_CACHE_GID_DEFAULT_MODE_SET, IB_CACHE_GID_DEFAULT_MODE_DELETE @@ -179,8 +188,8 @@ void ib_mad_cleanup(void); int ib_sa_init(void); void ib_sa_cleanup(void); -int ibnl_init(void); -void ibnl_cleanup(void); +int rdma_nl_init(void); +void rdma_nl_exit(void); /** * Check if there are any listeners to the netlink group @@ -190,11 +199,14 @@ void ibnl_cleanup(void); int ibnl_chk_listeners(unsigned int group); int ib_nl_handle_resolve_resp(struct sk_buff *skb, - struct netlink_callback *cb); + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack); int ib_nl_handle_set_timeout(struct sk_buff *skb, - struct netlink_callback *cb); + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack); int ib_nl_handle_ip_res_resp(struct sk_buff *skb, - struct netlink_callback *cb); + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack); int ib_get_cached_subnet_prefix(struct ib_device *device, u8 port_num, @@ -301,4 +313,9 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map, return 0; } #endif + +struct ib_device *__ib_device_get_by_index(u32 ifindex); +/* RDMA device netlink */ +void nldev_init(void); +void nldev_exit(void); #endif /* _CORE_PRIV_H */ diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 221468f77128..91d7cea1a0b9 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -134,6 +134,17 @@ static int ib_device_check_mandatory(struct ib_device *device) return 0; } +struct ib_device *__ib_device_get_by_index(u32 index) +{ + struct ib_device *device; + + list_for_each_entry(device, &device_list, core_list) + if (device->index == index) + return device; + + return NULL; +} + static struct ib_device *__ib_device_get_by_name(const char *name) { struct ib_device *device; @@ -145,7 +156,6 @@ static struct ib_device *__ib_device_get_by_name(const char *name) return NULL; } - static int alloc_name(char *name) { unsigned long *inuse; @@ -326,10 +336,10 @@ static int read_port_immutable(struct ib_device *device) return 0; } -void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len) +void ib_get_device_fw_str(struct ib_device *dev, char *str) { if (dev->get_dev_fw_str) - dev->get_dev_fw_str(dev, str, str_len); + dev->get_dev_fw_str(dev, str); else str[0] = '\0'; } @@ -395,6 +405,30 @@ static int ib_security_change(struct notifier_block *nb, unsigned long event, } /** + * __dev_new_index - allocate an device index + * + * Returns a suitable unique value for a new device interface + * number. It assumes that there are less than 2^32-1 ib devices + * will be present in the system. + */ +static u32 __dev_new_index(void) +{ + /* + * The device index to allow stable naming. + * Similar to struct net -> ifindex. + */ + static u32 index; + + for (;;) { + if (!(++index)) + index = 1; + + if (!__ib_device_get_by_index(index)) + return index; + } +} + +/** * ib_register_device - Register an IB device with IB core * @device:Device to register * @@ -489,9 +523,10 @@ int ib_register_device(struct ib_device *device, device->reg_state = IB_DEV_REGISTERED; list_for_each_entry(client, &client_list, list) - if (client->add && !add_client_context(device, client)) + if (!add_client_context(device, client) && client->add) client->add(device); + device->index = __dev_new_index(); down_write(&lists_rwsem); list_add_tail(&device->core_list, &device_list); up_write(&lists_rwsem); @@ -578,7 +613,7 @@ int ib_register_client(struct ib_client *client) mutex_lock(&device_mutex); list_for_each_entry(device, &device_list, core_list) - if (client->add && !add_client_context(device, client)) + if (!add_client_context(device, client) && client->add) client->add(device); down_write(&lists_rwsem); @@ -894,6 +929,31 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, } /** + * ib_enum_all_devs - enumerate all ib_devices + * @cb: Callback to call for each found ib_device + * + * Enumerates all ib_devices and calls callback() on each device. + */ +int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct ib_device *dev; + unsigned int idx = 0; + int ret = 0; + + down_read(&lists_rwsem); + list_for_each_entry(dev, &device_list, core_list) { + ret = nldev_cb(dev, skb, cb, idx); + if (ret) + break; + idx++; + } + + up_read(&lists_rwsem); + return ret; +} + +/** * ib_query_pkey - Get P_Key table entry * @device:Device to query * @port_num:Port number to query @@ -1087,29 +1147,21 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, } EXPORT_SYMBOL(ib_get_net_dev_by_params); -static struct ibnl_client_cbs ibnl_ls_cb_table[] = { +static const struct rdma_nl_cbs ibnl_ls_cb_table[] = { [RDMA_NL_LS_OP_RESOLVE] = { - .dump = ib_nl_handle_resolve_resp, - .module = THIS_MODULE }, + .doit = ib_nl_handle_resolve_resp, + .flags = RDMA_NL_ADMIN_PERM, + }, [RDMA_NL_LS_OP_SET_TIMEOUT] = { - .dump = ib_nl_handle_set_timeout, - .module = THIS_MODULE }, + .doit = ib_nl_handle_set_timeout, + .flags = RDMA_NL_ADMIN_PERM, + }, [RDMA_NL_LS_OP_IP_RESOLVE] = { - .dump = ib_nl_handle_ip_res_resp, - .module = THIS_MODULE }, + .doit = ib_nl_handle_ip_res_resp, + .flags = RDMA_NL_ADMIN_PERM, + }, }; -static int ib_add_ibnl_clients(void) -{ - return ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ibnl_ls_cb_table), - ibnl_ls_cb_table); -} - -static void ib_remove_ibnl_clients(void) -{ - ibnl_remove_client(RDMA_NL_LS); -} - static int __init ib_core_init(void) { int ret; @@ -1131,9 +1183,9 @@ static int __init ib_core_init(void) goto err_comp; } - ret = ibnl_init(); + ret = rdma_nl_init(); if (ret) { - pr_warn("Couldn't init IB netlink interface\n"); + pr_warn("Couldn't init IB netlink interface: err %d\n", ret); goto err_sysfs; } @@ -1155,24 +1207,18 @@ static int __init ib_core_init(void) goto err_mad; } - ret = ib_add_ibnl_clients(); - if (ret) { - pr_warn("Couldn't register ibnl clients\n"); - goto err_sa; - } - ret = register_lsm_notifier(&ibdev_lsm_nb); if (ret) { pr_warn("Couldn't register LSM notifier. ret %d\n", ret); - goto err_ibnl_clients; + goto err_sa; } + nldev_init(); + rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); ib_cache_setup(); return 0; -err_ibnl_clients: - ib_remove_ibnl_clients(); err_sa: ib_sa_cleanup(); err_mad: @@ -1180,7 +1226,7 @@ err_mad: err_addr: addr_cleanup(); err_ibnl: - ibnl_cleanup(); + rdma_nl_exit(); err_sysfs: class_unregister(&ib_class); err_comp: @@ -1192,13 +1238,14 @@ err: static void __exit ib_core_cleanup(void) { - unregister_lsm_notifier(&ibdev_lsm_nb); ib_cache_cleanup(); - ib_remove_ibnl_clients(); + nldev_exit(); + rdma_nl_unregister(RDMA_NL_LS); + unregister_lsm_notifier(&ibdev_lsm_nb); ib_sa_cleanup(); ib_mad_cleanup(); addr_cleanup(); - ibnl_cleanup(); + rdma_nl_exit(); class_unregister(&ib_class); destroy_workqueue(ib_comp_wq); /* Make sure that any pending umem accounting work is done. */ diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 31661b5c1743..e33528e102f8 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason) } EXPORT_SYMBOL(iwcm_reject_msg); -static struct ibnl_client_cbs iwcm_nl_cb_table[] = { +static struct rdma_nl_cbs iwcm_nl_cb_table[] = { [RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb}, [RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb}, [RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb}, @@ -1175,13 +1175,9 @@ static int __init iw_cm_init(void) ret = iwpm_init(RDMA_NL_IWCM); if (ret) pr_err("iw_cm: couldn't init iwpm\n"); - - ret = ibnl_add_client(RDMA_NL_IWCM, ARRAY_SIZE(iwcm_nl_cb_table), - iwcm_nl_cb_table); - if (ret) - pr_err("iw_cm: couldn't register netlink callbacks\n"); - - iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", WQ_MEM_RECLAIM); + else + rdma_nl_register(RDMA_NL_IWCM, iwcm_nl_cb_table); + iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", 0); if (!iwcm_wq) return -ENOMEM; @@ -1200,7 +1196,7 @@ static void __exit iw_cm_cleanup(void) { unregister_net_sysctl_table(iwcm_ctl_table_hdr); destroy_workqueue(iwcm_wq); - ibnl_remove_client(RDMA_NL_IWCM); + rdma_nl_unregister(RDMA_NL_IWCM); iwpm_exit(RDMA_NL_IWCM); } diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index a0e7c16d8bd8..30825bb9b8e9 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -42,7 +42,6 @@ int iwpm_valid_pid(void) { return iwpm_user_pid > 0; } -EXPORT_SYMBOL(iwpm_valid_pid); /* * iwpm_register_pid - Send a netlink query to user space @@ -104,7 +103,7 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n", __func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name); - ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL); + ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNAVAILABLE; @@ -122,7 +121,6 @@ pid_query_error: iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } -EXPORT_SYMBOL(iwpm_register_pid); /* * iwpm_add_mapping - Send a netlink add mapping message @@ -174,7 +172,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) goto add_mapping_error; nlmsg_request->req_buffer = pm_msg; - ret = ibnl_unicast(skb, nlh, iwpm_user_pid); + ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNDEFINED; @@ -191,7 +189,6 @@ add_mapping_error: iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } -EXPORT_SYMBOL(iwpm_add_mapping); /* * iwpm_add_and_query_mapping - Send a netlink add and query @@ -251,7 +248,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) goto query_mapping_error; nlmsg_request->req_buffer = pm_msg; - ret = ibnl_unicast(skb, nlh, iwpm_user_pid); + ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ err_str = "Unable to send a nlmsg"; @@ -267,7 +264,6 @@ query_mapping_error: iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } -EXPORT_SYMBOL(iwpm_add_and_query_mapping); /* * iwpm_remove_mapping - Send a netlink remove mapping message @@ -312,7 +308,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) if (ret) goto remove_mapping_error; - ret = ibnl_unicast(skb, nlh, iwpm_user_pid); + ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNDEFINED; @@ -328,7 +324,6 @@ remove_mapping_error: dev_kfree_skb_any(skb); return ret; } -EXPORT_SYMBOL(iwpm_remove_mapping); /* netlink attribute policy for the received response to register pid request */ static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = { @@ -397,7 +392,6 @@ register_pid_response_exit: up(&nlmsg_request->sem); return 0; } -EXPORT_SYMBOL(iwpm_register_pid_cb); /* netlink attribute policy for the received response to add mapping request */ static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = { @@ -466,7 +460,6 @@ add_mapping_response_exit: up(&nlmsg_request->sem); return 0; } -EXPORT_SYMBOL(iwpm_add_mapping_cb); /* netlink attribute policy for the response to add and query mapping request * and response with remote address info */ @@ -558,7 +551,6 @@ query_mapping_response_exit: up(&nlmsg_request->sem); return 0; } -EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb); /* * iwpm_remote_info_cb - Process a port mapper message, containing @@ -627,7 +619,6 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb) "remote_info: Mapped remote sockaddr:"); return ret; } -EXPORT_SYMBOL(iwpm_remote_info_cb); /* netlink attribute policy for the received request for mapping info */ static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = { @@ -677,7 +668,6 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid); return ret; } -EXPORT_SYMBOL(iwpm_mapping_info_cb); /* netlink attribute policy for the received mapping info ack */ static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = { @@ -707,7 +697,6 @@ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); return 0; } -EXPORT_SYMBOL(iwpm_ack_mapping_info_cb); /* netlink attribute policy for the received port mapper error message */ static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = { @@ -751,4 +740,3 @@ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb) up(&nlmsg_request->sem); return 0; } -EXPORT_SYMBOL(iwpm_mapping_error_cb); diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c index f13870e69ccd..c81c55942626 100644 --- a/drivers/infiniband/core/iwpm_util.c +++ b/drivers/infiniband/core/iwpm_util.c @@ -54,8 +54,6 @@ static struct iwpm_admin_data iwpm_admin; int iwpm_init(u8 nl_client) { int ret = 0; - if (iwpm_valid_client(nl_client)) - return -EINVAL; mutex_lock(&iwpm_admin_lock); if (atomic_read(&iwpm_admin.refcount) == 0) { iwpm_hash_bucket = kzalloc(IWPM_MAPINFO_HASH_SIZE * @@ -83,7 +81,6 @@ init_exit: } return ret; } -EXPORT_SYMBOL(iwpm_init); static void free_hash_bucket(void); static void free_reminfo_bucket(void); @@ -109,7 +106,6 @@ int iwpm_exit(u8 nl_client) iwpm_set_registration(nl_client, IWPM_REG_UNDEF); return 0; } -EXPORT_SYMBOL(iwpm_exit); static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *, struct sockaddr_storage *); @@ -148,7 +144,6 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr, spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags); return ret; } -EXPORT_SYMBOL(iwpm_create_mapinfo); int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr, struct sockaddr_storage *mapped_local_addr) @@ -184,7 +179,6 @@ remove_mapinfo_exit: spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags); return ret; } -EXPORT_SYMBOL(iwpm_remove_mapinfo); static void free_hash_bucket(void) { @@ -297,7 +291,6 @@ get_remote_info_exit: spin_unlock_irqrestore(&iwpm_reminfo_lock, flags); return ret; } -EXPORT_SYMBOL(iwpm_get_remote_info); struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq, u8 nl_client, gfp_t gfp) @@ -383,15 +376,11 @@ int iwpm_get_nlmsg_seq(void) int iwpm_valid_client(u8 nl_client) { - if (nl_client >= RDMA_NL_NUM_CLIENTS) - return 0; return iwpm_admin.client_list[nl_client]; } void iwpm_set_valid(u8 nl_client, int valid) { - if (nl_client >= RDMA_NL_NUM_CLIENTS) - return; iwpm_admin.client_list[nl_client] = valid; } @@ -608,7 +597,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid) &mapping_num, IWPM_NLA_MAPINFO_SEND_NUM); if (ret) goto mapinfo_num_error; - ret = ibnl_unicast(skb, nlh, iwpm_pid); + ret = rdma_nl_unicast(skb, iwpm_pid); if (ret) { skb = NULL; err_str = "Unable to send a nlmsg"; @@ -637,7 +626,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid) return -ENOMEM; } nlh->nlmsg_type = NLMSG_DONE; - ret = ibnl_unicast(skb, (struct nlmsghdr *)skb->data, iwpm_pid); + ret = rdma_nl_unicast(skb, iwpm_pid); if (ret) pr_warn("%s Unable to send a nlmsg\n", __func__); return ret; diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c index 0d3cca0a8890..e5cf09c66fe6 100644 --- a/drivers/infiniband/core/mad_rmpp.c +++ b/drivers/infiniband/core/mad_rmpp.c @@ -64,7 +64,7 @@ struct mad_rmpp_recv { __be64 tid; u32 src_qp; - u16 slid; + u32 slid; u8 mgmt_class; u8 class_version; u8 method; diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 94931c474d41..27352a352770 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2017 Mellanox Technologies Inc. All rights reserved. * Copyright (c) 2010 Voltaire Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -39,237 +40,253 @@ #include <rdma/rdma_netlink.h> #include "core_priv.h" -struct ibnl_client { - struct list_head list; - int index; - int nops; - const struct ibnl_client_cbs *cb_table; -}; +#include "core_priv.h" -static DEFINE_MUTEX(ibnl_mutex); +static DEFINE_MUTEX(rdma_nl_mutex); static struct sock *nls; -static LIST_HEAD(client_list); +static struct { + const struct rdma_nl_cbs *cb_table; +} rdma_nl_types[RDMA_NL_NUM_CLIENTS]; -int ibnl_chk_listeners(unsigned int group) +int rdma_nl_chk_listeners(unsigned int group) { - if (netlink_has_listeners(nls, group) == 0) - return -1; - return 0; + return (netlink_has_listeners(nls, group)) ? 0 : -1; } +EXPORT_SYMBOL(rdma_nl_chk_listeners); -int ibnl_add_client(int index, int nops, - const struct ibnl_client_cbs cb_table[]) +static bool is_nl_msg_valid(unsigned int type, unsigned int op) { - struct ibnl_client *cur; - struct ibnl_client *nl_client; - - nl_client = kmalloc(sizeof *nl_client, GFP_KERNEL); - if (!nl_client) - return -ENOMEM; + static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS - 1] = { + RDMA_NL_RDMA_CM_NUM_OPS, + RDMA_NL_IWPM_NUM_OPS, + 0, + RDMA_NL_LS_NUM_OPS, + RDMA_NLDEV_NUM_OPS }; - nl_client->index = index; - nl_client->nops = nops; - nl_client->cb_table = cb_table; + /* + * This BUILD_BUG_ON is intended to catch addition of new + * RDMA netlink protocol without updating the array above. + */ + BUILD_BUG_ON(RDMA_NL_NUM_CLIENTS != 6); - mutex_lock(&ibnl_mutex); + if (type > RDMA_NL_NUM_CLIENTS - 1) + return false; - list_for_each_entry(cur, &client_list, list) { - if (cur->index == index) { - pr_warn("Client for %d already exists\n", index); - mutex_unlock(&ibnl_mutex); - kfree(nl_client); - return -EINVAL; - } - } + return (op < max_num_ops[type - 1]) ? true : false; +} - list_add_tail(&nl_client->list, &client_list); +static bool is_nl_valid(unsigned int type, unsigned int op) +{ + const struct rdma_nl_cbs *cb_table; - mutex_unlock(&ibnl_mutex); + if (!is_nl_msg_valid(type, op)) + return false; - return 0; + cb_table = rdma_nl_types[type].cb_table; + if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit)) + return false; + return true; } -EXPORT_SYMBOL(ibnl_add_client); -int ibnl_remove_client(int index) +void rdma_nl_register(unsigned int index, + const struct rdma_nl_cbs cb_table[]) { - struct ibnl_client *cur, *next; - - mutex_lock(&ibnl_mutex); - list_for_each_entry_safe(cur, next, &client_list, list) { - if (cur->index == index) { - list_del(&(cur->list)); - mutex_unlock(&ibnl_mutex); - kfree(cur); - return 0; - } + mutex_lock(&rdma_nl_mutex); + if (!is_nl_msg_valid(index, 0)) { + /* + * All clients are not interesting in success/failure of + * this call. They want to see the print to error log and + * continue their initialization. Print warning for them, + * because it is programmer's error to be here. + */ + mutex_unlock(&rdma_nl_mutex); + WARN(true, + "The not-valid %u index was supplied to RDMA netlink\n", + index); + return; } - pr_warn("Can't remove callback for client idx %d. Not found\n", index); - mutex_unlock(&ibnl_mutex); - return -EINVAL; + if (rdma_nl_types[index].cb_table) { + mutex_unlock(&rdma_nl_mutex); + WARN(true, + "The %u index is already registered in RDMA netlink\n", + index); + return; + } + + rdma_nl_types[index].cb_table = cb_table; + mutex_unlock(&rdma_nl_mutex); +} +EXPORT_SYMBOL(rdma_nl_register); + +void rdma_nl_unregister(unsigned int index) +{ + mutex_lock(&rdma_nl_mutex); + rdma_nl_types[index].cb_table = NULL; + mutex_unlock(&rdma_nl_mutex); } -EXPORT_SYMBOL(ibnl_remove_client); +EXPORT_SYMBOL(rdma_nl_unregister); void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq, int len, int client, int op, int flags) { - unsigned char *prev_tail; - - prev_tail = skb_tail_pointer(skb); - *nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), - len, flags); + *nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags); if (!*nlh) - goto out_nlmsg_trim; - (*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail; + return NULL; return nlmsg_data(*nlh); - -out_nlmsg_trim: - nlmsg_trim(skb, prev_tail); - return NULL; } EXPORT_SYMBOL(ibnl_put_msg); int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh, int len, void *data, int type) { - unsigned char *prev_tail; - - prev_tail = skb_tail_pointer(skb); - if (nla_put(skb, type, len, data)) - goto nla_put_failure; - nlh->nlmsg_len += skb_tail_pointer(skb) - prev_tail; + if (nla_put(skb, type, len, data)) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } return 0; - -nla_put_failure: - nlmsg_trim(skb, prev_tail - nlh->nlmsg_len); - return -EMSGSIZE; } EXPORT_SYMBOL(ibnl_put_attr); -static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) +static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { - struct ibnl_client *client; int type = nlh->nlmsg_type; - int index = RDMA_NL_GET_CLIENT(type); + unsigned int index = RDMA_NL_GET_CLIENT(type); unsigned int op = RDMA_NL_GET_OP(type); + const struct rdma_nl_cbs *cb_table; + + if (!is_nl_valid(index, op)) + return -EINVAL; + + cb_table = rdma_nl_types[index].cb_table; - list_for_each_entry(client, &client_list, list) { - if (client->index == index) { - if (op >= client->nops || !client->cb_table[op].dump) - return -EINVAL; - - /* - * For response or local service set_timeout request, - * there is no need to use netlink_dump_start. - */ - if (!(nlh->nlmsg_flags & NLM_F_REQUEST) || - (index == RDMA_NL_LS && - op == RDMA_NL_LS_OP_SET_TIMEOUT)) { - struct netlink_callback cb = { - .skb = skb, - .nlh = nlh, - .dump = client->cb_table[op].dump, - .module = client->cb_table[op].module, - }; - - return cb.dump(skb, &cb); - } - - { - struct netlink_dump_control c = { - .dump = client->cb_table[op].dump, - .module = client->cb_table[op].module, - }; - return netlink_dump_start(nls, skb, nlh, &c); - } - } + if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) && + !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + /* FIXME: Convert IWCM to properly handle doit callbacks */ + if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM || + index == RDMA_NL_IWCM) { + struct netlink_dump_control c = { + .dump = cb_table[op].dump, + }; + return netlink_dump_start(nls, skb, nlh, &c); } - pr_info("Index %d wasn't found in client list\n", index); - return -EINVAL; + if (cb_table[op].doit) + return cb_table[op].doit(skb, nlh, extack); + + return 0; } -static void ibnl_rcv_reply_skb(struct sk_buff *skb) +/* + * This function is similar to netlink_rcv_skb with one exception: + * It calls to the callback for the netlink messages without NLM_F_REQUEST + * flag. These messages are intended for RDMA_NL_LS consumer, so it is allowed + * for that consumer only. + */ +static int rdma_nl_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, + struct nlmsghdr *, + struct netlink_ext_ack *)) { + struct netlink_ext_ack extack = {}; struct nlmsghdr *nlh; - int msglen; + int err; - /* - * Process responses until there is no more message or the first - * request. Generally speaking, it is not recommended to mix responses - * with requests. - */ while (skb->len >= nlmsg_total_size(0)) { + int msglen; + nlh = nlmsg_hdr(skb); + err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) - return; - - /* Handle response only */ - if (nlh->nlmsg_flags & NLM_F_REQUEST) - return; - - ibnl_rcv_msg(skb, nlh, NULL); + return 0; + /* + * Generally speaking, the only requests are handled + * by the kernel, but RDMA_NL_LS is different, because it + * runs backward netlink scheme. Kernel initiates messages + * and waits for reply with data to keep pathrecord cache + * in sync. + */ + if (!(nlh->nlmsg_flags & NLM_F_REQUEST) && + (RDMA_NL_GET_CLIENT(nlh->nlmsg_type) != RDMA_NL_LS)) + goto ack; + + /* Skip control messages */ + if (nlh->nlmsg_type < NLMSG_MIN_TYPE) + goto ack; + + err = cb(skb, nlh, &extack); + if (err == -EINTR) + goto skip; + +ack: + if (nlh->nlmsg_flags & NLM_F_ACK || err) + netlink_ack(skb, nlh, err, &extack); + +skip: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } + + return 0; } -static void ibnl_rcv(struct sk_buff *skb) +static void rdma_nl_rcv(struct sk_buff *skb) { - mutex_lock(&ibnl_mutex); - ibnl_rcv_reply_skb(skb); - netlink_rcv_skb(skb, &ibnl_rcv_msg); - mutex_unlock(&ibnl_mutex); + mutex_lock(&rdma_nl_mutex); + rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg); + mutex_unlock(&rdma_nl_mutex); } -int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh, - __u32 pid) +int rdma_nl_unicast(struct sk_buff *skb, u32 pid) +{ + int err; + + err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT); + return (err < 0) ? err : 0; +} +EXPORT_SYMBOL(rdma_nl_unicast); + +int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid) { int err; err = netlink_unicast(nls, skb, pid, 0); return (err < 0) ? err : 0; } -EXPORT_SYMBOL(ibnl_unicast); +EXPORT_SYMBOL(rdma_nl_unicast_wait); -int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh, - unsigned int group, gfp_t flags) +int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags) { return nlmsg_multicast(nls, skb, 0, group, flags); } -EXPORT_SYMBOL(ibnl_multicast); +EXPORT_SYMBOL(rdma_nl_multicast); -int __init ibnl_init(void) +int __init rdma_nl_init(void) { struct netlink_kernel_cfg cfg = { - .input = ibnl_rcv, + .input = rdma_nl_rcv, }; nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg); - if (!nls) { - pr_warn("Failed to create netlink socket\n"); + if (!nls) return -ENOMEM; - } nls->sk_sndtimeo = 10 * HZ; return 0; } -void ibnl_cleanup(void) +void rdma_nl_exit(void) { - struct ibnl_client *cur, *next; + int idx; - mutex_lock(&ibnl_mutex); - list_for_each_entry_safe(cur, next, &client_list, list) { - list_del(&(cur->list)); - kfree(cur); - } - mutex_unlock(&ibnl_mutex); + for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++) + rdma_nl_unregister(idx); netlink_kernel_release(nls); } diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c new file mode 100644 index 000000000000..474022274e09 --- /dev/null +++ b/drivers/infiniband/core/nldev.c @@ -0,0 +1,322 @@ +/* + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <net/netlink.h> +#include <rdma/rdma_netlink.h> + +#include "core_priv.h" + +static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = { + [RDMA_NLDEV_ATTR_DEV_INDEX] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = IB_DEVICE_NAME_MAX - 1}, + [RDMA_NLDEV_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_FW_VERSION] = { .type = NLA_NUL_STRING, + .len = IB_FW_VERSION_NAME_MAX - 1}, + [RDMA_NLDEV_ATTR_NODE_GUID] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_SUBNET_PREFIX] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_LID] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_SM_LID] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_LMC] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_PORT_STATE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 }, +}; + +static int fill_dev_info(struct sk_buff *msg, struct ib_device *device) +{ + char fw[IB_FW_VERSION_NAME_MAX]; + + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index)) + return -EMSGSIZE; + if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name)) + return -EMSGSIZE; + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device))) + return -EMSGSIZE; + + BUILD_BUG_ON(sizeof(device->attrs.device_cap_flags) != sizeof(u64)); + if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS, + device->attrs.device_cap_flags, 0)) + return -EMSGSIZE; + + ib_get_device_fw_str(device, fw); + /* Device without FW has strlen(fw) */ + if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw)) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_NODE_GUID, + be64_to_cpu(device->node_guid), 0)) + return -EMSGSIZE; + if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SYS_IMAGE_GUID, + be64_to_cpu(device->attrs.sys_image_guid), 0)) + return -EMSGSIZE; + if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type)) + return -EMSGSIZE; + return 0; +} + +static int fill_port_info(struct sk_buff *msg, + struct ib_device *device, u32 port) +{ + struct ib_port_attr attr; + int ret; + + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index)) + return -EMSGSIZE; + if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name)) + return -EMSGSIZE; + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) + return -EMSGSIZE; + + ret = ib_query_port(device, port, &attr); + if (ret) + return ret; + + BUILD_BUG_ON(sizeof(attr.port_cap_flags) > sizeof(u64)); + if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS, + (u64)attr.port_cap_flags, 0)) + return -EMSGSIZE; + if (rdma_protocol_ib(device, port) && + nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX, + attr.subnet_prefix, 0)) + return -EMSGSIZE; + if (rdma_protocol_ib(device, port)) { + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_LID, attr.lid)) + return -EMSGSIZE; + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_SM_LID, attr.sm_lid)) + return -EMSGSIZE; + if (nla_put_u8(msg, RDMA_NLDEV_ATTR_LMC, attr.lmc)) + return -EMSGSIZE; + } + if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_STATE, attr.state)) + return -EMSGSIZE; + if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_PHYS_STATE, attr.phys_state)) + return -EMSGSIZE; + return 0; +} + +static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + struct ib_device *device; + struct sk_buff *msg; + u32 index; + int err; + + err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, extack); + if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) + return -EINVAL; + + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + + device = __ib_device_get_by_index(index); + if (!device) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), + 0, 0); + + err = fill_dev_info(msg, device); + if (err) { + nlmsg_free(msg); + return err; + } + + nlmsg_end(msg, nlh); + + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); +} + +static int _nldev_get_dumpit(struct ib_device *device, + struct sk_buff *skb, + struct netlink_callback *cb, + unsigned int idx) +{ + int start = cb->args[0]; + struct nlmsghdr *nlh; + + if (idx < start) + return 0; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), + 0, NLM_F_MULTI); + + if (fill_dev_info(skb, device)) { + nlmsg_cancel(skb, nlh); + goto out; + } + + nlmsg_end(skb, nlh); + + idx++; + +out: cb->args[0] = idx; + return skb->len; +} + +static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + /* + * There is no need to take lock, because + * we are relying on ib_core's lists_rwsem + */ + return ib_enum_all_devs(_nldev_get_dumpit, skb, cb); +} + +static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + struct ib_device *device; + struct sk_buff *msg; + u32 index; + u32 port; + int err; + + err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, extack); + if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) + return -EINVAL; + + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = __ib_device_get_by_index(index); + if (!device) + return -EINVAL; + + port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(device, port)) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), + 0, 0); + + err = fill_port_info(msg, device, port); + if (err) { + nlmsg_free(msg); + return err; + } + + nlmsg_end(msg, nlh); + + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); +} + +static int nldev_port_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + struct ib_device *device; + int start = cb->args[0]; + struct nlmsghdr *nlh; + u32 idx = 0; + u32 ifindex; + int err; + u32 p; + + err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, NULL); + if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) + return -EINVAL; + + ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = __ib_device_get_by_index(ifindex); + if (!device) + return -EINVAL; + + for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) { + /* + * The dumpit function returns all information from specific + * index. This specific index is taken from the netlink + * messages request sent by user and it is available + * in cb->args[0]. + * + * Usually, the user doesn't fill this field and it causes + * to return everything. + * + */ + if (idx < start) { + idx++; + continue; + } + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, + RDMA_NLDEV_CMD_PORT_GET), + 0, NLM_F_MULTI); + + if (fill_port_info(skb, device, p)) { + nlmsg_cancel(skb, nlh); + goto out; + } + idx++; + nlmsg_end(skb, nlh); + } + +out: cb->args[0] = idx; + return skb->len; +} + +static const struct rdma_nl_cbs nldev_cb_table[] = { + [RDMA_NLDEV_CMD_GET] = { + .doit = nldev_get_doit, + .dump = nldev_get_dumpit, + }, + [RDMA_NLDEV_CMD_PORT_GET] = { + .doit = nldev_port_get_doit, + .dump = nldev_port_get_dumpit, + }, +}; + +void __init nldev_init(void) +{ + rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table); +} + +void __exit nldev_exit(void) +{ + rdma_nl_unregister(RDMA_NL_NLDEV); +} diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index 94a9eefb3cfc..90e3889b7fbe 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -44,6 +44,8 @@ static struct workqueue_struct *gid_cache_wq; +static struct workqueue_struct *gid_cache_wq; + enum gid_op_type { GID_DEL = 0, GID_ADD diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 70fa4cabe48e..da29e2863c84 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -861,7 +861,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask) /* Repair the nlmsg header length */ nlmsg_end(skb, nlh); - ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask); + ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask); if (!ret) ret = len; else @@ -1021,9 +1021,9 @@ static void ib_nl_request_timeout(struct work_struct *work) } int ib_nl_handle_set_timeout(struct sk_buff *skb, - struct netlink_callback *cb) + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { - const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh; int timeout, delta, abs_delta; const struct nlattr *attr; unsigned long flags; @@ -1033,8 +1033,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb, int ret; if (!(nlh->nlmsg_flags & NLM_F_REQUEST) || - !(NETLINK_CB(skb).sk) || - !netlink_capable(skb, CAP_NET_ADMIN)) + !(NETLINK_CB(skb).sk)) return -EPERM; ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh), @@ -1098,9 +1097,9 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh) } int ib_nl_handle_resolve_resp(struct sk_buff *skb, - struct netlink_callback *cb) + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { - const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh; unsigned long flags; struct ib_sa_query *query; struct ib_mad_send_buf *send_buf; @@ -1109,8 +1108,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb, int ret; if ((nlh->nlmsg_flags & NLM_F_REQUEST) || - !(NETLINK_CB(skb).sk) || - !netlink_capable(skb, CAP_NET_ADMIN)) + !(NETLINK_CB(skb).sk)) return -EPERM; spin_lock_irqsave(&ib_nl_request_lock, flags); @@ -1420,7 +1418,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask) if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) && (!(query->flags & IB_SA_QUERY_OPA))) { - if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) { + if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) { if (!ib_nl_make_request(query, gfp_mask)) return id; } diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 7ebe1ef23652..abc5ab581f82 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -1210,8 +1210,8 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr, { struct ib_device *dev = container_of(device, struct ib_device, dev); - ib_get_device_fw_str(dev, buf, PAGE_SIZE); - strlcat(buf, "\n", PAGE_SIZE); + ib_get_device_fw_str(dev, buf); + strlcat(buf, "\n", IB_FW_VERSION_NAME_MAX); return strlen(buf); } diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 112099c86a19..f2a7f62c2834 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -618,7 +618,7 @@ static ssize_t ib_ucm_init_qp_attr(struct ib_ucm_file *file, if (result) goto out; - ib_copy_qp_attr_to_user(&resp, &qp_attr); + ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr); if (copy_to_user((void __user *)(unsigned long)cmd.response, &resp, sizeof(resp))) diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 276f0ef835bd..eb85b546e223 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -248,14 +248,15 @@ static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst, dst->qp_num = src->qp_num; } -static void ucma_copy_ud_event(struct rdma_ucm_ud_param *dst, +static void ucma_copy_ud_event(struct ib_device *device, + struct rdma_ucm_ud_param *dst, struct rdma_ud_param *src) { if (src->private_data_len) memcpy(dst->private_data, src->private_data, src->private_data_len); dst->private_data_len = src->private_data_len; - ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr); + ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr); dst->qp_num = src->qp_num; dst->qkey = src->qkey; } @@ -335,7 +336,8 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id, uevent->resp.event = event->event; uevent->resp.status = event->status; if (cm_id->qp_type == IB_QPT_UD) - ucma_copy_ud_event(&uevent->resp.param.ud, &event->param.ud); + ucma_copy_ud_event(cm_id->device, &uevent->resp.param.ud, + &event->param.ud); else ucma_copy_conn_event(&uevent->resp.param.conn, &event->param.conn); @@ -1157,7 +1159,7 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file, if (ret) goto out; - ib_copy_qp_attr_to_user(&resp, &qp_attr); + ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr); if (copy_to_user((void __user *)(unsigned long)cmd.response, &resp, sizeof(resp))) ret = -EFAULT; diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 36a6f5c8914c..ff3c67a7aaad 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -229,7 +229,7 @@ static void recv_handler(struct ib_mad_agent *agent, packet->mad.hdr.status = 0; packet->mad.hdr.length = hdr_size(file) + mad_recv_wc->mad_len; packet->mad.hdr.qpn = cpu_to_be32(mad_recv_wc->wc->src_qp); - packet->mad.hdr.lid = cpu_to_be16(mad_recv_wc->wc->slid); + packet->mad.hdr.lid = ib_slid_be16(mad_recv_wc->wc->slid); packet->mad.hdr.sl = mad_recv_wc->wc->sl; packet->mad.hdr.path_bits = mad_recv_wc->wc->dlid_path_bits; packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index c551d2b275fd..39a0f1dc84e4 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -275,8 +275,13 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file, resp.bad_pkey_cntr = attr.bad_pkey_cntr; resp.qkey_viol_cntr = attr.qkey_viol_cntr; resp.pkey_tbl_len = attr.pkey_tbl_len; - resp.lid = attr.lid; - resp.sm_lid = attr.sm_lid; + if (rdma_cap_opa_ah(ib_dev, cmd.port_num)) { + resp.lid = OPA_TO_IB_UCAST_LID(attr.lid); + resp.sm_lid = OPA_TO_IB_UCAST_LID(attr.sm_lid); + } else { + resp.lid = (u16)attr.lid; + resp.sm_lid = (u16)attr.sm_lid; + } resp.lmc = attr.lmc; resp.max_vl_num = attr.max_vl_num; resp.sm_sl = attr.sm_sl; @@ -1015,7 +1020,7 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file, cq->uobject = &obj->uobject; cq->comp_handler = ib_uverbs_comp_handler; cq->event_handler = ib_uverbs_cq_event_handler; - cq->cq_context = &ev_file->ev_queue; + cq->cq_context = ev_file ? &ev_file->ev_queue : NULL; atomic_set(&cq->usecnt, 0); obj->uobject.object = cq; @@ -1185,7 +1190,8 @@ out: return ret ? ret : in_len; } -static int copy_wc_to_user(void __user *dest, struct ib_wc *wc) +static int copy_wc_to_user(struct ib_device *ib_dev, void __user *dest, + struct ib_wc *wc) { struct ib_uverbs_wc tmp; @@ -1199,7 +1205,10 @@ static int copy_wc_to_user(void __user *dest, struct ib_wc *wc) tmp.src_qp = wc->src_qp; tmp.wc_flags = wc->wc_flags; tmp.pkey_index = wc->pkey_index; - tmp.slid = wc->slid; + if (rdma_cap_opa_ah(ib_dev, wc->port_num)) + tmp.slid = OPA_TO_IB_UCAST_LID(wc->slid); + else + tmp.slid = ib_slid_cpu16(wc->slid); tmp.sl = wc->sl; tmp.dlid_path_bits = wc->dlid_path_bits; tmp.port_num = wc->port_num; @@ -1243,7 +1252,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file, if (!ret) break; - ret = copy_wc_to_user(data_ptr, &wc); + ret = copy_wc_to_user(ib_dev, data_ptr, &wc); if (ret) goto out_put; @@ -1383,8 +1392,9 @@ static int create_qp(struct ib_uverbs_file *file, attr.rwq_ind_tbl = ind_tbl; } - if ((cmd_sz >= offsetof(typeof(*cmd), reserved1) + - sizeof(cmd->reserved1)) && cmd->reserved1) { + if (cmd_sz > sizeof(*cmd) && + !ib_is_udata_cleared(ucore, sizeof(*cmd), + cmd_sz - sizeof(*cmd))) { ret = -EOPNOTSUPP; goto err_put; } @@ -1482,11 +1492,21 @@ static int create_qp(struct ib_uverbs_file *file, IB_QP_CREATE_MANAGED_SEND | IB_QP_CREATE_MANAGED_RECV | IB_QP_CREATE_SCATTER_FCS | - IB_QP_CREATE_CVLAN_STRIPPING)) { + IB_QP_CREATE_CVLAN_STRIPPING | + IB_QP_CREATE_SOURCE_QPN)) { ret = -EINVAL; goto err_put; } + if (attr.create_flags & IB_QP_CREATE_SOURCE_QPN) { + if (!capable(CAP_NET_RAW)) { + ret = -EPERM; + goto err_put; + } + + attr.source_qpn = cmd->source_qpn; + } + buf = (void *)cmd + sizeof(*cmd); if (cmd_sz > sizeof(*cmd)) if (!(buf[0] == 0 && !memcmp(buf, buf + 1, diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index 94fd989c9060..bd0acf376af0 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -33,10 +33,47 @@ #include <linux/export.h> #include <rdma/ib_marshall.h> -void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, - struct rdma_ah_attr *src) +#define OPA_DEFAULT_GID_PREFIX cpu_to_be64(0xfe80000000000000ULL) +static int rdma_ah_conv_opa_to_ib(struct ib_device *dev, + struct rdma_ah_attr *ib, + struct rdma_ah_attr *opa) { + struct ib_port_attr port_attr; + int ret = 0; + + /* Do structure copy and the over-write fields */ + *ib = *opa; + + ib->type = RDMA_AH_ATTR_TYPE_IB; + rdma_ah_set_grh(ib, NULL, 0, 0, 1, 0); + + if (ib_query_port(dev, opa->port_num, &port_attr)) { + /* Set to default subnet to indicate error */ + rdma_ah_set_subnet_prefix(ib, OPA_DEFAULT_GID_PREFIX); + ret = -EINVAL; + } else { + rdma_ah_set_subnet_prefix(ib, + cpu_to_be64(port_attr.subnet_prefix)); + } + rdma_ah_set_interface_id(ib, OPA_MAKE_ID(rdma_ah_get_dlid(opa))); + return ret; +} + +void ib_copy_ah_attr_to_user(struct ib_device *device, + struct ib_uverbs_ah_attr *dst, + struct rdma_ah_attr *ah_attr) +{ + struct rdma_ah_attr *src = ah_attr; + struct rdma_ah_attr conv_ah; + memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved)); + + if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) && + (rdma_ah_get_dlid(ah_attr) >= + be16_to_cpu(IB_MULTICAST_LID_BASE)) && + (!rdma_ah_conv_opa_to_ib(device, &conv_ah, ah_attr))) + src = &conv_ah; + dst->dlid = rdma_ah_get_dlid(src); dst->sl = rdma_ah_get_sl(src); dst->src_path_bits = rdma_ah_get_path_bits(src); @@ -57,7 +94,8 @@ void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, } EXPORT_SYMBOL(ib_copy_ah_attr_to_user); -void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst, +void ib_copy_qp_attr_to_user(struct ib_device *device, + struct ib_uverbs_qp_attr *dst, struct ib_qp_attr *src) { dst->qp_state = src->qp_state; @@ -76,8 +114,8 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst, dst->max_recv_sge = src->cap.max_recv_sge; dst->max_inline_data = src->cap.max_inline_data; - ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr); - ib_copy_ah_attr_to_user(&dst->alt_ah_attr, &src->alt_ah_attr); + ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr); + ib_copy_ah_attr_to_user(device, &dst->alt_ah_attr, &src->alt_ah_attr); dst->pkey_index = src->pkey_index; dst->alt_pkey_index = src->alt_pkey_index; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 7f8fe443df46..aa4a84ecf11a 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1243,6 +1243,18 @@ int ib_resolve_eth_dmac(struct ib_device *device, if (rdma_link_local_addr((struct in6_addr *)grh->dgid.raw)) { rdma_get_ll_mac((struct in6_addr *)grh->dgid.raw, ah_attr->roce.dmac); + return 0; + } + if (rdma_is_multicast_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) { + if (ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw)) { + __be32 addr = 0; + + memcpy(&addr, ah_attr->grh.dgid.raw + 12, 4); + ip_eth_mc_map(addr, (char *)ah_attr->roce.dmac); + } else { + ipv6_eth_mc_map((struct in6_addr *)ah_attr->grh.dgid.raw, + (char *)ah_attr->roce.dmac); + } } else { union ib_gid sgid; struct ib_gid_attr sgid_attr; @@ -1301,6 +1313,61 @@ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, } EXPORT_SYMBOL(ib_modify_qp_with_udata); +int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width) +{ + int rc; + u32 netdev_speed; + struct net_device *netdev; + struct ethtool_link_ksettings lksettings; + + if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET) + return -EINVAL; + + if (!dev->get_netdev) + return -EOPNOTSUPP; + + netdev = dev->get_netdev(dev, port_num); + if (!netdev) + return -ENODEV; + + rtnl_lock(); + rc = __ethtool_get_link_ksettings(netdev, &lksettings); + rtnl_unlock(); + + dev_put(netdev); + + if (!rc) { + netdev_speed = lksettings.base.speed; + } else { + netdev_speed = SPEED_1000; + pr_warn("%s speed is unknown, defaulting to %d\n", netdev->name, + netdev_speed); + } + + if (netdev_speed <= SPEED_1000) { + *width = IB_WIDTH_1X; + *speed = IB_SPEED_SDR; + } else if (netdev_speed <= SPEED_10000) { + *width = IB_WIDTH_1X; + *speed = IB_SPEED_FDR10; + } else if (netdev_speed <= SPEED_20000) { + *width = IB_WIDTH_4X; + *speed = IB_SPEED_DDR; + } else if (netdev_speed <= SPEED_25000) { + *width = IB_WIDTH_1X; + *speed = IB_SPEED_EDR; + } else if (netdev_speed <= SPEED_40000) { + *width = IB_WIDTH_4X; + *speed = IB_SPEED_FDR10; + } else { + *width = IB_WIDTH_4X; + *speed = IB_SPEED_EDR; + } + + return 0; +} +EXPORT_SYMBOL(ib_get_eth_speed); + int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask) @@ -1568,15 +1635,53 @@ EXPORT_SYMBOL(ib_dealloc_fmr); /* Multicast groups */ +static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid) +{ + struct ib_qp_init_attr init_attr = {}; + struct ib_qp_attr attr = {}; + int num_eth_ports = 0; + int port; + + /* If QP state >= init, it is assigned to a port and we can check this + * port only. + */ + if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) { + if (attr.qp_state >= IB_QPS_INIT) { + if (qp->device->get_link_layer(qp->device, attr.port_num) != + IB_LINK_LAYER_INFINIBAND) + return true; + goto lid_check; + } + } + + /* Can't get a quick answer, iterate over all ports */ + for (port = 0; port < qp->device->phys_port_cnt; port++) + if (qp->device->get_link_layer(qp->device, port) != + IB_LINK_LAYER_INFINIBAND) + num_eth_ports++; + + /* If we have at lease one Ethernet port, RoCE annex declares that + * multicast LID should be ignored. We can't tell at this step if the + * QP belongs to an IB or Ethernet port. + */ + if (num_eth_ports) + return true; + + /* If all the ports are IB, we can check according to IB spec. */ +lid_check: + return !(lid < be16_to_cpu(IB_MULTICAST_LID_BASE) || + lid == be16_to_cpu(IB_LID_PERMISSIVE)); +} + int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid) { int ret; if (!qp->device->attach_mcast) return -ENOSYS; - if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD || - lid < be16_to_cpu(IB_MULTICAST_LID_BASE) || - lid == be16_to_cpu(IB_LID_PERMISSIVE)) + + if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) || + qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid)) return -EINVAL; ret = qp->device->attach_mcast(qp, gid, lid); @@ -1592,9 +1697,9 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid) if (!qp->device->detach_mcast) return -ENOSYS; - if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD || - lid < be16_to_cpu(IB_MULTICAST_LID_BASE) || - lid == be16_to_cpu(IB_LID_PERMISSIVE)) + + if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) || + qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid)) return -EINVAL; ret = qp->device->detach_mcast(qp, gid, lid); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index f0e01b3ac711..58461ee3773d 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -223,50 +223,6 @@ int bnxt_re_modify_device(struct ib_device *ibdev, return 0; } -static void __to_ib_speed_width(struct net_device *netdev, u8 *speed, u8 *width) -{ - struct ethtool_link_ksettings lksettings; - u32 espeed; - - if (netdev->ethtool_ops && netdev->ethtool_ops->get_link_ksettings) { - memset(&lksettings, 0, sizeof(lksettings)); - rtnl_lock(); - netdev->ethtool_ops->get_link_ksettings(netdev, &lksettings); - rtnl_unlock(); - espeed = lksettings.base.speed; - } else { - espeed = SPEED_UNKNOWN; - } - switch (espeed) { - case SPEED_1000: - *speed = IB_SPEED_SDR; - *width = IB_WIDTH_1X; - break; - case SPEED_10000: - *speed = IB_SPEED_QDR; - *width = IB_WIDTH_1X; - break; - case SPEED_20000: - *speed = IB_SPEED_DDR; - *width = IB_WIDTH_4X; - break; - case SPEED_25000: - *speed = IB_SPEED_EDR; - *width = IB_WIDTH_1X; - break; - case SPEED_40000: - *speed = IB_SPEED_QDR; - *width = IB_WIDTH_4X; - break; - case SPEED_50000: - break; - default: - *speed = IB_SPEED_SDR; - *width = IB_WIDTH_1X; - break; - } -} - /* Port */ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num, struct ib_port_attr *port_attr) @@ -308,25 +264,9 @@ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num, * IB stack to avoid race in the NETDEV_UNREG path */ if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags)) - __to_ib_speed_width(rdev->netdev, &port_attr->active_speed, - &port_attr->active_width); - return 0; -} - -int bnxt_re_modify_port(struct ib_device *ibdev, u8 port_num, - int port_modify_mask, - struct ib_port_modify *port_modify) -{ - switch (port_modify_mask) { - case IB_PORT_SHUTDOWN: - break; - case IB_PORT_INIT_TYPE: - break; - case IB_PORT_RESET_QKEY_CNTR: - break; - default: - break; - } + if (!ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed, + &port_attr->active_width)) + return -EINVAL; return 0; } @@ -846,6 +786,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) struct bnxt_re_dev *rdev = qp->rdev; int rc; + bnxt_qplib_del_flush_qp(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to destroy HW QP"); @@ -860,6 +801,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) return rc; } + bnxt_qplib_del_flush_qp(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &rdev->qp1_sqp->qplib_qp); if (rc) { @@ -1404,6 +1346,21 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, } qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_STATE; qp->qplib_qp.state = __from_ib_qp_state(qp_attr->qp_state); + + if (!qp->sumem && + qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + dev_dbg(rdev_to_dev(rdev), + "Move QP = %p to flush list\n", + qp); + bnxt_qplib_add_flush_qp(&qp->qplib_qp); + } + if (!qp->sumem && + qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_RESET) { + dev_dbg(rdev_to_dev(rdev), + "Move QP = %p out of flush list\n", + qp); + bnxt_qplib_del_flush_qp(&qp->qplib_qp); + } } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { qp->qplib_qp.modify_flags |= @@ -2414,6 +2371,7 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev, } cq->qplib_cq.max_wqe = entries; cq->qplib_cq.cnq_hw_ring_id = rdev->nq.ring_id; + cq->qplib_cq.nq = &rdev->nq; rc = bnxt_qplib_create_cq(&rdev->qplib_res, &cq->qplib_cq); if (rc) { @@ -2921,6 +2879,10 @@ int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc) sq->send_phantom = false; } } + if (ncqe < budget) + ncqe += bnxt_qplib_process_flush_list(&cq->qplib_cq, + cqe + ncqe, + budget - ncqe); if (!ncqe) break; @@ -3410,7 +3372,7 @@ int bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx) &rdev->qplib_res.dpi_tbl, &uctx->dpi); if (rc) - dev_err(rdev_to_dev(rdev), "Deallocte HW DPI failed!"); + dev_err(rdev_to_dev(rdev), "Deallocate HW DPI failed!"); /* Don't fail, continue*/ uctx->dpi.dbr = NULL; } diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index a0bb7e33d7ca..1df11ed272ea 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -141,9 +141,6 @@ int bnxt_re_modify_device(struct ib_device *ibdev, struct ib_device_modify *device_modify); int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num, struct ib_port_attr *port_attr); -int bnxt_re_modify_port(struct ib_device *ibdev, u8 port_num, - int port_modify_mask, - struct ib_port_modify *port_modify); int bnxt_re_get_port_immutable(struct ib_device *ibdev, u8 port_num, struct ib_port_immutable *immutable); int bnxt_re_query_pkey(struct ib_device *ibdev, u8 port_num, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index ceae2d92fb08..2f71123e0a9f 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -70,7 +70,6 @@ static char version[] = MODULE_AUTHOR("Eddie Wai <eddie.wai@broadcom.com>"); MODULE_DESCRIPTION(BNXT_RE_DESC " Driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(ROCE_DRV_MODULE_VERSION); /* globals */ static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list); @@ -474,7 +473,6 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev) ibdev->modify_device = bnxt_re_modify_device; ibdev->query_port = bnxt_re_query_port; - ibdev->modify_port = bnxt_re_modify_port; ibdev->get_port_immutable = bnxt_re_get_port_immutable; ibdev->query_pkey = bnxt_re_query_pkey; ibdev->query_gid = bnxt_re_query_gid; @@ -835,6 +833,42 @@ static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) mutex_unlock(&rdev->qp_lock); } +static int bnxt_re_update_gid(struct bnxt_re_dev *rdev) +{ + struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl; + struct bnxt_qplib_gid gid; + u16 gid_idx, index; + int rc = 0; + + if (!test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags)) + return 0; + + if (!sgid_tbl) { + dev_err(rdev_to_dev(rdev), "QPLIB: SGID table not allocated"); + return -EINVAL; + } + + for (index = 0; index < sgid_tbl->active; index++) { + gid_idx = sgid_tbl->hw_id[index]; + + if (!memcmp(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero, + sizeof(bnxt_qplib_gid_zero))) + continue; + /* need to modify the VLAN enable setting of non VLAN GID only + * as setting is done for VLAN GID while adding GID + */ + if (sgid_tbl->vlan[index]) + continue; + + memcpy(&gid, &sgid_tbl->tbl[index], sizeof(gid)); + + rc = bnxt_qplib_update_sgid(sgid_tbl, &gid, gid_idx, + rdev->qplib_res.netdev->dev_addr); + } + + return rc; +} + static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev) { u32 prio_map = 0, tmp_map = 0; @@ -854,8 +888,6 @@ static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev) tmp_map = dcb_ieee_getapp_mask(netdev, &app); prio_map |= tmp_map; - if (!prio_map) - prio_map = -EFAULT; return prio_map; } @@ -881,10 +913,7 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) int rc; /* Get priority for roce */ - rc = bnxt_re_get_priority_mask(rdev); - if (rc < 0) - return rc; - prio_map = (u8)rc; + prio_map = bnxt_re_get_priority_mask(rdev); if (prio_map == rdev->cur_prio_map) return 0; @@ -906,6 +935,16 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) return rc; } + /* Actual priorities are not programmed as they are already + * done by L2 driver; just enable or disable priority vlan tagging + */ + if ((prio_map == 0 && rdev->qplib_res.prio) || + (prio_map != 0 && !rdev->qplib_res.prio)) { + rdev->qplib_res.prio = prio_map ? true : false; + + bnxt_re_update_gid(rdev); + } + return 0; } @@ -998,7 +1037,8 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) /* Establish RCFW Communication Channel to initialize the context * memory for the function and all child VFs */ - rc = bnxt_qplib_alloc_rcfw_channel(rdev->en_dev->pdev, &rdev->rcfw); + rc = bnxt_qplib_alloc_rcfw_channel(rdev->en_dev->pdev, &rdev->rcfw, + BNXT_RE_MAX_QPC_COUNT); if (rc) goto fail; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 9af1514e5944..31e15f31bba5 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -51,6 +51,168 @@ #include "qplib_fp.h" static void bnxt_qplib_arm_cq_enable(struct bnxt_qplib_cq *cq); +static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp); + +static void bnxt_qplib_cancel_phantom_processing(struct bnxt_qplib_qp *qp) +{ + qp->sq.condition = false; + qp->sq.send_phantom = false; + qp->sq.single = false; +} + +/* Flush list */ +static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) +{ + struct bnxt_qplib_cq *scq, *rcq; + + scq = qp->scq; + rcq = qp->rcq; + + if (!qp->sq.flushed) { + dev_dbg(&scq->hwq.pdev->dev, + "QPLIB: FP: Adding to SQ Flush list = %p", + qp); + bnxt_qplib_cancel_phantom_processing(qp); + list_add_tail(&qp->sq_flush, &scq->sqf_head); + qp->sq.flushed = true; + } + if (!qp->srq) { + if (!qp->rq.flushed) { + dev_dbg(&rcq->hwq.pdev->dev, + "QPLIB: FP: Adding to RQ Flush list = %p", + qp); + list_add_tail(&qp->rq_flush, &rcq->rqf_head); + qp->rq.flushed = true; + } + } +} + +void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __acquires(&qp->scq->hwq.lock) __acquires(&qp->rcq->hwq.lock) +{ + spin_lock_irqsave(&qp->scq->hwq.lock, *flags); + if (qp->scq == qp->rcq) + __acquire(&qp->rcq->hwq.lock); + else + spin_lock(&qp->rcq->hwq.lock); +} + +void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __releases(&qp->scq->hwq.lock) __releases(&qp->rcq->hwq.lock) +{ + if (qp->scq == qp->rcq) + __release(&qp->rcq->hwq.lock); + else + spin_unlock(&qp->rcq->hwq.lock); + spin_unlock_irqrestore(&qp->scq->hwq.lock, *flags); +} + +static struct bnxt_qplib_cq *bnxt_qplib_find_buddy_cq(struct bnxt_qplib_qp *qp, + struct bnxt_qplib_cq *cq) +{ + struct bnxt_qplib_cq *buddy_cq = NULL; + + if (qp->scq == qp->rcq) + buddy_cq = NULL; + else if (qp->scq == cq) + buddy_cq = qp->rcq; + else + buddy_cq = qp->scq; + return buddy_cq; +} + +static void bnxt_qplib_lock_buddy_cq(struct bnxt_qplib_qp *qp, + struct bnxt_qplib_cq *cq) + __acquires(&buddy_cq->hwq.lock) +{ + struct bnxt_qplib_cq *buddy_cq = NULL; + + buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); + if (!buddy_cq) + __acquire(&cq->hwq.lock); + else + spin_lock(&buddy_cq->hwq.lock); +} + +static void bnxt_qplib_unlock_buddy_cq(struct bnxt_qplib_qp *qp, + struct bnxt_qplib_cq *cq) + __releases(&buddy_cq->hwq.lock) +{ + struct bnxt_qplib_cq *buddy_cq = NULL; + + buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); + if (!buddy_cq) + __release(&cq->hwq.lock); + else + spin_unlock(&buddy_cq->hwq.lock); +} + +void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) +{ + unsigned long flags; + + bnxt_qplib_acquire_cq_locks(qp, &flags); + __bnxt_qplib_add_flush_qp(qp); + bnxt_qplib_release_cq_locks(qp, &flags); +} + +static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) +{ + struct bnxt_qplib_cq *scq, *rcq; + + scq = qp->scq; + rcq = qp->rcq; + + if (qp->sq.flushed) { + qp->sq.flushed = false; + list_del(&qp->sq_flush); + } + if (!qp->srq) { + if (qp->rq.flushed) { + qp->rq.flushed = false; + list_del(&qp->rq_flush); + } + } +} + +void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) +{ + unsigned long flags; + + bnxt_qplib_acquire_cq_locks(qp, &flags); + __clean_cq(qp->scq, (u64)(unsigned long)qp); + qp->sq.hwq.prod = 0; + qp->sq.hwq.cons = 0; + __clean_cq(qp->rcq, (u64)(unsigned long)qp); + qp->rq.hwq.prod = 0; + qp->rq.hwq.cons = 0; + + __bnxt_qplib_del_flush_qp(qp); + bnxt_qplib_release_cq_locks(qp, &flags); +} + +static void bnxt_qpn_cqn_sched_task(struct work_struct *work) +{ + struct bnxt_qplib_nq_work *nq_work = + container_of(work, struct bnxt_qplib_nq_work, work); + + struct bnxt_qplib_cq *cq = nq_work->cq; + struct bnxt_qplib_nq *nq = nq_work->nq; + + if (cq && nq) { + spin_lock_bh(&cq->compl_lock); + if (atomic_read(&cq->arm_state) && nq->cqn_handler) { + dev_dbg(&nq->pdev->dev, + "%s:Trigger cq = %p event nq = %p\n", + __func__, cq, nq); + nq->cqn_handler(nq, cq); + } + spin_unlock_bh(&cq->compl_lock); + } + kfree(nq_work); +} static void bnxt_qplib_free_qp_hdr_buf(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) @@ -119,6 +281,7 @@ static void bnxt_qplib_service_nq(unsigned long data) struct bnxt_qplib_nq *nq = (struct bnxt_qplib_nq *)data; struct bnxt_qplib_hwq *hwq = &nq->hwq; struct nq_base *nqe, **nq_ptr; + struct bnxt_qplib_cq *cq; int num_cqne_processed = 0; u32 sw_cons, raw_cons; u16 type; @@ -143,15 +306,17 @@ static void bnxt_qplib_service_nq(unsigned long data) q_handle = le32_to_cpu(nqcne->cq_handle_low); q_handle |= (u64)le32_to_cpu(nqcne->cq_handle_high) << 32; - bnxt_qplib_arm_cq_enable((struct bnxt_qplib_cq *) - ((unsigned long)q_handle)); - if (!nq->cqn_handler(nq, (struct bnxt_qplib_cq *) - ((unsigned long)q_handle))) + cq = (struct bnxt_qplib_cq *)(unsigned long)q_handle; + bnxt_qplib_arm_cq_enable(cq); + spin_lock_bh(&cq->compl_lock); + atomic_set(&cq->arm_state, 0); + if (!nq->cqn_handler(nq, (cq))) num_cqne_processed++; else dev_warn(&nq->pdev->dev, "QPLIB: cqn - type 0x%x not handled", type); + spin_unlock_bh(&cq->compl_lock); break; } case NQ_BASE_TYPE_DBQ_EVENT: @@ -190,6 +355,10 @@ static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance) void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq) { + if (nq->cqn_wq) { + destroy_workqueue(nq->cqn_wq); + nq->cqn_wq = NULL; + } /* Make sure the HW is stopped! */ synchronize_irq(nq->vector); tasklet_disable(&nq->worker); @@ -216,7 +385,7 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq, void *, u8 event)) { resource_size_t nq_base; - int rc; + int rc = -1; nq->pdev = pdev; nq->vector = msix_vector; @@ -227,6 +396,11 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq, tasklet_init(&nq->worker, bnxt_qplib_service_nq, (unsigned long)nq); + /* Have a task to schedule CQ notifiers in post send case */ + nq->cqn_wq = create_singlethread_workqueue("bnxt_qplib_nq"); + if (!nq->cqn_wq) + goto fail; + nq->requested = false; rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, "bnxt_qplib_nq", nq); if (rc) { @@ -401,8 +575,8 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) qp->id = le32_to_cpu(resp.xid); qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET; - sq->flush_in_progress = false; - rq->flush_in_progress = false; + rcfw->qp_tbl[qp->id].qp_id = qp->id; + rcfw->qp_tbl[qp->id].qp_handle = (void *)qp; return 0; @@ -615,8 +789,10 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) qp->id = le32_to_cpu(resp.xid); qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET; - sq->flush_in_progress = false; - rq->flush_in_progress = false; + INIT_LIST_HEAD(&qp->sq_flush); + INIT_LIST_HEAD(&qp->rq_flush); + rcfw->qp_tbl[qp->id].qp_id = qp->id; + rcfw->qp_tbl[qp->id].qp_handle = (void *)qp; return 0; @@ -963,13 +1139,19 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, u16 cmd_flags = 0; int rc; + rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID; + rcfw->qp_tbl[qp->id].qp_handle = NULL; + RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags); req.qp_cid = cpu_to_le32(qp->id); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, 0); - if (rc) + if (rc) { + rcfw->qp_tbl[qp->id].qp_id = qp->id; + rcfw->qp_tbl[qp->id].qp_handle = qp; return rc; + } /* Must walk the associated CQs to nullified the QP ptr */ spin_lock_irqsave(&qp->scq->hwq.lock, flags); @@ -1074,14 +1256,21 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp, struct bnxt_qplib_swq *swq; struct sq_send *hw_sq_send_hdr, **hw_sq_send_ptr; struct sq_sge *hw_sge; + struct bnxt_qplib_nq_work *nq_work = NULL; + bool sch_handler = false; u32 sw_prod; u8 wqe_size16; int i, rc = 0, data_len = 0, pkt_num = 0; __le32 temp32; if (qp->state != CMDQ_MODIFY_QP_NEW_STATE_RTS) { - rc = -EINVAL; - goto done; + if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + sch_handler = true; + dev_dbg(&sq->hwq.pdev->dev, + "%s Error QP. Scheduling for poll_cq\n", + __func__); + goto queue_err; + } } if (bnxt_qplib_queue_full(sq)) { @@ -1301,12 +1490,35 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp, ((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) & SQ_PSN_SEARCH_NEXT_PSN_MASK)); } - +queue_err: + if (sch_handler) { + /* Store the ULP info in the software structures */ + sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq); + swq = &sq->swq[sw_prod]; + swq->wr_id = wqe->wr_id; + swq->type = wqe->type; + swq->flags = wqe->flags; + if (qp->sig_type) + swq->flags |= SQ_SEND_FLAGS_SIGNAL_COMP; + swq->start_psn = sq->psn & BTH_PSN_MASK; + } sq->hwq.prod++; - qp->wqe_cnt++; done: + if (sch_handler) { + nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC); + if (nq_work) { + nq_work->cq = qp->scq; + nq_work->nq = qp->scq->nq; + INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task); + queue_work(qp->scq->nq->cqn_wq, &nq_work->work); + } else { + dev_err(&sq->hwq.pdev->dev, + "QPLIB: FP: Failed to allocate SQ nq_work!"); + rc = -ENOMEM; + } + } return rc; } @@ -1334,15 +1546,17 @@ int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp, struct bnxt_qplib_q *rq = &qp->rq; struct rq_wqe *rqe, **rqe_ptr; struct sq_sge *hw_sge; + struct bnxt_qplib_nq_work *nq_work = NULL; + bool sch_handler = false; u32 sw_prod; int i, rc = 0; if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { - dev_err(&rq->hwq.pdev->dev, - "QPLIB: FP: QP (0x%x) is in the 0x%x state", - qp->id, qp->state); - rc = -EINVAL; - goto done; + sch_handler = true; + dev_dbg(&rq->hwq.pdev->dev, + "%s Error QP. Scheduling for poll_cq\n", + __func__); + goto queue_err; } if (bnxt_qplib_queue_full(rq)) { dev_err(&rq->hwq.pdev->dev, @@ -1378,7 +1592,27 @@ int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp, /* Supply the rqe->wr_id index to the wr_id_tbl for now */ rqe->wr_id[0] = cpu_to_le32(sw_prod); +queue_err: + if (sch_handler) { + /* Store the ULP info in the software structures */ + sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq); + rq->swq[sw_prod].wr_id = wqe->wr_id; + } + rq->hwq.prod++; + if (sch_handler) { + nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC); + if (nq_work) { + nq_work->cq = qp->rcq; + nq_work->nq = qp->rcq->nq; + INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task); + queue_work(qp->rcq->nq->cqn_wq, &nq_work->work); + } else { + dev_err(&rq->hwq.pdev->dev, + "QPLIB: FP: Failed to allocate RQ nq_work!"); + rc = -ENOMEM; + } + } done: return rc; } @@ -1471,6 +1705,9 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) cq->dbr_base = res->dpi_tbl.dbr_bar_reg_iomem; cq->period = BNXT_QPLIB_QUEUE_START_PERIOD; init_waitqueue_head(&cq->waitq); + INIT_LIST_HEAD(&cq->sqf_head); + INIT_LIST_HEAD(&cq->rqf_head); + spin_lock_init(&cq->compl_lock); bnxt_qplib_arm_cq_enable(cq); return 0; @@ -1513,9 +1750,13 @@ static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp, while (*budget) { sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq); if (sw_cons == sw_prod) { - sq->flush_in_progress = false; break; } + /* Skip the FENCE WQE completions */ + if (sq->swq[sw_cons].wr_id == BNXT_QPLIB_FENCE_WRID) { + bnxt_qplib_cancel_phantom_processing(qp); + goto skip_compl; + } memset(cqe, 0, sizeof(*cqe)); cqe->status = CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR; cqe->opcode = CQ_BASE_CQE_TYPE_REQ; @@ -1525,6 +1766,7 @@ static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp, cqe->type = sq->swq[sw_cons].type; cqe++; (*budget)--; +skip_compl: sq->hwq.cons++; } *pcqe = cqe; @@ -1536,11 +1778,24 @@ static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp, } static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp, - int opcode, struct bnxt_qplib_cqe **pcqe, int *budget) + struct bnxt_qplib_cqe **pcqe, int *budget) { struct bnxt_qplib_cqe *cqe; u32 sw_prod, sw_cons; int rc = 0; + int opcode = 0; + + switch (qp->type) { + case CMDQ_CREATE_QP1_TYPE_GSI: + opcode = CQ_BASE_CQE_TYPE_RES_RAWETH_QP1; + break; + case CMDQ_CREATE_QP_TYPE_RC: + opcode = CQ_BASE_CQE_TYPE_RES_RC; + break; + case CMDQ_CREATE_QP_TYPE_UD: + opcode = CQ_BASE_CQE_TYPE_RES_UD; + break; + } /* Flush the rest of the RQ */ sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq); @@ -1567,6 +1822,21 @@ static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp, return rc; } +void bnxt_qplib_mark_qp_error(void *qp_handle) +{ + struct bnxt_qplib_qp *qp = qp_handle; + + if (!qp) + return; + + /* Must block new posting of SQ and RQ */ + qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; + bnxt_qplib_cancel_phantom_processing(qp); + + /* Add qp to flush list of the CQ */ + __bnxt_qplib_add_flush_qp(qp); +} + /* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive) * CQE is track from sw_cq_cons to max_element but valid only if VALID=1 */ @@ -1694,10 +1964,12 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, cqe_sq_cons, sq->hwq.max_elements); return -EINVAL; } - /* If we were in the middle of flushing the SQ, continue */ - if (sq->flush_in_progress) - goto flush; + if (qp->sq.flushed) { + dev_dbg(&cq->hwq.pdev->dev, + "%s: QPLIB: QP in Flush QP = %p\n", __func__, qp); + goto done; + } /* Require to walk the sq's swq to fabricate CQEs for all previously * signaled SWQEs due to CQE aggregation from the current sq cons * to the cqe_sq_cons @@ -1733,11 +2005,9 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, sw_sq_cons, cqe->wr_id, cqe->status); cqe++; (*budget)--; - sq->flush_in_progress = true; - /* Must block new posting of SQ and RQ */ - qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; - sq->condition = false; - sq->single = false; + bnxt_qplib_lock_buddy_cq(qp, cq); + bnxt_qplib_mark_qp_error(qp); + bnxt_qplib_unlock_buddy_cq(qp, cq); } else { if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { /* Before we complete, do WA 9060 */ @@ -1768,15 +2038,6 @@ out: * the WC for this CQE */ sq->single = false; - if (!sq->flush_in_progress) - goto done; -flush: - /* Require to walk the sq's swq to fabricate CQEs for all - * previously posted SWQEs due to the error CQE received - */ - rc = __flush_sq(sq, qp, pcqe, budget); - if (!rc) - sq->flush_in_progress = false; done: return rc; } @@ -1798,6 +2059,12 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq, dev_err(&cq->hwq.pdev->dev, "QPLIB: process_cq RC qp is NULL"); return -EINVAL; } + if (qp->rq.flushed) { + dev_dbg(&cq->hwq.pdev->dev, + "%s: QPLIB: QP in Flush QP = %p\n", __func__, qp); + goto done; + } + cqe = *pcqe; cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK; cqe->length = le32_to_cpu(hwcqe->length); @@ -1817,8 +2084,6 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq, wr_id_idx, rq->hwq.max_elements); return -EINVAL; } - if (rq->flush_in_progress) - goto flush_rq; cqe->wr_id = rq->swq[wr_id_idx].wr_id; cqe++; @@ -1827,12 +2092,13 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq, *pcqe = cqe; if (hwcqe->status != CQ_RES_RC_STATUS_OK) { - rq->flush_in_progress = true; -flush_rq: - rc = __flush_rq(rq, qp, CQ_BASE_CQE_TYPE_RES_RC, pcqe, budget); - if (!rc) - rq->flush_in_progress = false; + /* Add qp to flush list of the CQ */ + bnxt_qplib_lock_buddy_cq(qp, cq); + __bnxt_qplib_add_flush_qp(qp); + bnxt_qplib_unlock_buddy_cq(qp, cq); } + +done: return rc; } @@ -1853,6 +2119,11 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq, dev_err(&cq->hwq.pdev->dev, "QPLIB: process_cq UD qp is NULL"); return -EINVAL; } + if (qp->rq.flushed) { + dev_dbg(&cq->hwq.pdev->dev, + "%s: QPLIB: QP in Flush QP = %p\n", __func__, qp); + goto done; + } cqe = *pcqe; cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK; cqe->length = le32_to_cpu(hwcqe->length); @@ -1876,8 +2147,6 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq, wr_id_idx, rq->hwq.max_elements); return -EINVAL; } - if (rq->flush_in_progress) - goto flush_rq; cqe->wr_id = rq->swq[wr_id_idx].wr_id; cqe++; @@ -1886,12 +2155,12 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq, *pcqe = cqe; if (hwcqe->status != CQ_RES_RC_STATUS_OK) { - rq->flush_in_progress = true; -flush_rq: - rc = __flush_rq(rq, qp, CQ_BASE_CQE_TYPE_RES_UD, pcqe, budget); - if (!rc) - rq->flush_in_progress = false; + /* Add qp to flush list of the CQ */ + bnxt_qplib_lock_buddy_cq(qp, cq); + __bnxt_qplib_add_flush_qp(qp); + bnxt_qplib_unlock_buddy_cq(qp, cq); } +done: return rc; } @@ -1932,6 +2201,11 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq, "QPLIB: process_cq Raw/QP1 qp is NULL"); return -EINVAL; } + if (qp->rq.flushed) { + dev_dbg(&cq->hwq.pdev->dev, + "%s: QPLIB: QP in Flush QP = %p\n", __func__, qp); + goto done; + } cqe = *pcqe; cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK; cqe->flags = le16_to_cpu(hwcqe->flags); @@ -1960,8 +2234,6 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq, wr_id_idx, rq->hwq.max_elements); return -EINVAL; } - if (rq->flush_in_progress) - goto flush_rq; cqe->wr_id = rq->swq[wr_id_idx].wr_id; cqe++; @@ -1970,13 +2242,13 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq, *pcqe = cqe; if (hwcqe->status != CQ_RES_RC_STATUS_OK) { - rq->flush_in_progress = true; -flush_rq: - rc = __flush_rq(rq, qp, CQ_BASE_CQE_TYPE_RES_RAWETH_QP1, pcqe, - budget); - if (!rc) - rq->flush_in_progress = false; + /* Add qp to flush list of the CQ */ + bnxt_qplib_lock_buddy_cq(qp, cq); + __bnxt_qplib_add_flush_qp(qp); + bnxt_qplib_unlock_buddy_cq(qp, cq); } + +done: return rc; } @@ -1990,7 +2262,6 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe; u32 sw_cons = 0, cqe_cons; int rc = 0; - u8 opcode = 0; /* Check the Status */ if (hwcqe->status != CQ_TERMINAL_STATUS_OK) @@ -2005,6 +2276,7 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq, "QPLIB: FP: CQ Process terminal qp is NULL"); return -EINVAL; } + /* Must block new posting of SQ and RQ */ qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; @@ -2023,9 +2295,12 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq, cqe_cons, sq->hwq.max_elements); goto do_rq; } - /* If we were in the middle of flushing, continue */ - if (sq->flush_in_progress) - goto flush_sq; + + if (qp->sq.flushed) { + dev_dbg(&cq->hwq.pdev->dev, + "%s: QPLIB: QP in Flush QP = %p\n", __func__, qp); + goto sq_done; + } /* Terminal CQE can also include aggregated successful CQEs prior. * So we must complete all CQEs from the current sq's cons to the @@ -2055,11 +2330,6 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq, rc = -EAGAIN; goto sq_done; } - sq->flush_in_progress = true; -flush_sq: - rc = __flush_sq(sq, qp, pcqe, budget); - if (!rc) - sq->flush_in_progress = false; sq_done: if (rc) return rc; @@ -2075,26 +2345,23 @@ do_rq: cqe_cons, rq->hwq.max_elements); goto done; } + + if (qp->rq.flushed) { + dev_dbg(&cq->hwq.pdev->dev, + "%s: QPLIB: QP in Flush QP = %p\n", __func__, qp); + rc = 0; + goto done; + } + /* Terminal CQE requires all posted RQEs to complete with FLUSHED_ERR * from the current rq->cons to the rq->prod regardless what the * rq->cons the terminal CQE indicates */ - rq->flush_in_progress = true; - switch (qp->type) { - case CMDQ_CREATE_QP1_TYPE_GSI: - opcode = CQ_BASE_CQE_TYPE_RES_RAWETH_QP1; - break; - case CMDQ_CREATE_QP_TYPE_RC: - opcode = CQ_BASE_CQE_TYPE_RES_RC; - break; - case CMDQ_CREATE_QP_TYPE_UD: - opcode = CQ_BASE_CQE_TYPE_RES_UD; - break; - } - rc = __flush_rq(rq, qp, opcode, pcqe, budget); - if (!rc) - rq->flush_in_progress = false; + /* Add qp to flush list of the CQ */ + bnxt_qplib_lock_buddy_cq(qp, cq); + __bnxt_qplib_add_flush_qp(qp); + bnxt_qplib_unlock_buddy_cq(qp, cq); done: return rc; } @@ -2115,6 +2382,33 @@ static int bnxt_qplib_cq_process_cutoff(struct bnxt_qplib_cq *cq, return 0; } +int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, + struct bnxt_qplib_cqe *cqe, + int num_cqes) +{ + struct bnxt_qplib_qp *qp = NULL; + u32 budget = num_cqes; + unsigned long flags; + + spin_lock_irqsave(&cq->hwq.lock, flags); + list_for_each_entry(qp, &cq->sqf_head, sq_flush) { + dev_dbg(&cq->hwq.pdev->dev, + "QPLIB: FP: Flushing SQ QP= %p", + qp); + __flush_sq(&qp->sq, qp, &cqe, &budget); + } + + list_for_each_entry(qp, &cq->rqf_head, rq_flush) { + dev_dbg(&cq->hwq.pdev->dev, + "QPLIB: FP: Flushing RQ QP= %p", + qp); + __flush_rq(&qp->rq, qp, &cqe, &budget); + } + spin_unlock_irqrestore(&cq->hwq.lock, flags); + + return num_cqes - budget; +} + int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, int num_cqes, struct bnxt_qplib_qp **lib_qp) { @@ -2205,6 +2499,7 @@ void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type) spin_lock_irqsave(&cq->hwq.lock, flags); if (arm_type) bnxt_qplib_arm_cq(cq, arm_type); - + /* Using cq->arm_state variable to track whether to issue cq handler */ + atomic_set(&cq->arm_state, 1); spin_unlock_irqrestore(&cq->hwq.lock, flags); } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index 19176e06c98a..23a26d5cbe18 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -220,19 +220,20 @@ struct bnxt_qplib_q { u16 q_full_delta; u16 max_sge; u32 psn; - bool flush_in_progress; bool condition; bool single; bool send_phantom; u32 phantom_wqe_cnt; u32 phantom_cqe_cnt; u32 next_cq_cons; + bool flushed; }; struct bnxt_qplib_qp { struct bnxt_qplib_pd *pd; struct bnxt_qplib_dpi *dpi; u64 qp_handle; +#define BNXT_QPLIB_QP_ID_INVALID 0xFFFFFFFF u32 id; u8 type; u8 sig_type; @@ -296,6 +297,8 @@ struct bnxt_qplib_qp { dma_addr_t sq_hdr_buf_map; void *rq_hdr_buf; dma_addr_t rq_hdr_buf_map; + struct list_head sq_flush; + struct list_head rq_flush; }; #define BNXT_QPLIB_MAX_CQE_ENTRY_SIZE sizeof(struct cq_base) @@ -351,6 +354,7 @@ struct bnxt_qplib_cq { u16 period; struct bnxt_qplib_hwq hwq; u32 cnq_hw_ring_id; + struct bnxt_qplib_nq *nq; bool resize_in_progress; struct scatterlist *sghead; u32 nmap; @@ -360,6 +364,9 @@ struct bnxt_qplib_cq { unsigned long flags; #define CQ_FLAGS_RESIZE_IN_PROG 1 wait_queue_head_t waitq; + struct list_head sqf_head, rqf_head; + atomic_t arm_state; + spinlock_t compl_lock; /* synch CQ handlers */ }; #define BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE sizeof(struct xrrq_irrq) @@ -417,6 +424,13 @@ struct bnxt_qplib_nq { (struct bnxt_qplib_nq *nq, void *srq, u8 event); + struct workqueue_struct *cqn_wq; +}; + +struct bnxt_qplib_nq_work { + struct work_struct work; + struct bnxt_qplib_nq *nq; + struct bnxt_qplib_cq *cq; }; void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq); @@ -453,4 +467,13 @@ bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq); void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type); void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq); int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq); +void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp); +void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp); +void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags); +void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags); +int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, + struct bnxt_qplib_cqe *cqe, + int num_cqes); #endif /* __BNXT_QPLIB_FP_H__ */ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 16e42754dbec..391bb7006e8f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -44,6 +44,9 @@ #include "roce_hsi.h" #include "qplib_res.h" #include "qplib_rcfw.h" +#include "qplib_sp.h" +#include "qplib_fp.h" + static void bnxt_qplib_service_creq(unsigned long data); /* Hardware communication channel */ @@ -279,16 +282,29 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, struct creq_qp_event *qp_event) { struct bnxt_qplib_hwq *cmdq = &rcfw->cmdq; + struct creq_qp_error_notification *err_event; struct bnxt_qplib_crsq *crsqe; unsigned long flags; + struct bnxt_qplib_qp *qp; u16 cbit, blocked = 0; u16 cookie; __le16 mcookie; + u32 qp_id; switch (qp_event->event) { case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION: + err_event = (struct creq_qp_error_notification *)qp_event; + qp_id = le32_to_cpu(err_event->xid); + qp = rcfw->qp_tbl[qp_id].qp_handle; dev_dbg(&rcfw->pdev->dev, "QPLIB: Received QP error notification"); + dev_dbg(&rcfw->pdev->dev, + "QPLIB: qpid 0x%x, req_err=0x%x, resp_err=0x%x\n", + qp_id, err_event->req_err_state_reason, + err_event->res_err_state_reason); + bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_mark_qp_error(qp); + bnxt_qplib_release_cq_locks(qp, &flags); break; default: /* Command Response */ @@ -507,6 +523,7 @@ skip_ctx_setup: void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw) { + kfree(rcfw->qp_tbl); kfree(rcfw->crsqe_tbl); bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->cmdq); bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->creq); @@ -514,7 +531,8 @@ void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw) } int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev, - struct bnxt_qplib_rcfw *rcfw) + struct bnxt_qplib_rcfw *rcfw, + int qp_tbl_sz) { rcfw->pdev = pdev; rcfw->creq.max_elements = BNXT_QPLIB_CREQE_MAX_CNT; @@ -541,6 +559,12 @@ int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev, if (!rcfw->crsqe_tbl) goto fail; + rcfw->qp_tbl_size = qp_tbl_sz; + rcfw->qp_tbl = kcalloc(qp_tbl_sz, sizeof(struct bnxt_qplib_qp_node), + GFP_KERNEL); + if (!rcfw->qp_tbl) + goto fail; + return 0; fail: diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 09ce121770cd..0ed312f17c8d 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -148,6 +148,11 @@ struct bnxt_qplib_rcfw_sbuf { u32 size; }; +struct bnxt_qplib_qp_node { + u32 qp_id; /* QP id */ + void *qp_handle; /* ptr to qplib_qp */ +}; + /* RCFW Communication Channels */ struct bnxt_qplib_rcfw { struct pci_dev *pdev; @@ -181,11 +186,13 @@ struct bnxt_qplib_rcfw { /* Actual Cmd and Resp Queues */ struct bnxt_qplib_hwq cmdq; struct bnxt_qplib_crsq *crsqe_tbl; + int qp_tbl_size; + struct bnxt_qplib_qp_node *qp_tbl; }; void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev, - struct bnxt_qplib_rcfw *rcfw); + struct bnxt_qplib_rcfw *rcfw, int qp_tbl_sz); void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev, struct bnxt_qplib_rcfw *rcfw, @@ -207,4 +214,5 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_ctx *ctx, int is_virtfn); +void bnxt_qplib_mark_qp_error(void *qp_handle); #endif /* __BNXT_QPLIB_RCFW_H__ */ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 62447b3badec..4e101704e801 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -468,9 +468,11 @@ static void bnxt_qplib_free_sgid_tbl(struct bnxt_qplib_res *res, kfree(sgid_tbl->tbl); kfree(sgid_tbl->hw_id); kfree(sgid_tbl->ctx); + kfree(sgid_tbl->vlan); sgid_tbl->tbl = NULL; sgid_tbl->hw_id = NULL; sgid_tbl->ctx = NULL; + sgid_tbl->vlan = NULL; sgid_tbl->max = 0; sgid_tbl->active = 0; } @@ -491,8 +493,15 @@ static int bnxt_qplib_alloc_sgid_tbl(struct bnxt_qplib_res *res, if (!sgid_tbl->ctx) goto out_free2; + sgid_tbl->vlan = kcalloc(max, sizeof(u8), GFP_KERNEL); + if (!sgid_tbl->vlan) + goto out_free3; + sgid_tbl->max = max; return 0; +out_free3: + kfree(sgid_tbl->ctx); + sgid_tbl->ctx = NULL; out_free2: kfree(sgid_tbl->hw_id); sgid_tbl->hw_id = NULL; @@ -514,6 +523,7 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res, } memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max); memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max); + memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max); sgid_tbl->active = 0; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 2e4855509719..e87207526d2c 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -116,6 +116,7 @@ struct bnxt_qplib_sgid_tbl { u16 max; u16 active; void *ctx; + u8 *vlan; }; struct bnxt_qplib_pkey_tbl { @@ -188,6 +189,7 @@ struct bnxt_qplib_res { struct bnxt_qplib_sgid_tbl sgid_tbl; struct bnxt_qplib_pkey_tbl pkey_tbl; struct bnxt_qplib_dpi_tbl dpi_tbl; + bool prio; }; #define to_bnxt_qplib(ptr, type, member) \ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index ef91ab786dd4..e277e54a05eb 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -213,6 +213,7 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, } memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero, sizeof(bnxt_qplib_gid_zero)); + sgid_tbl->vlan[index] = 0; sgid_tbl->active--; dev_dbg(&res->pdev->dev, "QPLIB: SGID deleted hw_id[0x%x] = 0x%x active = 0x%x", @@ -265,28 +266,32 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct cmdq_add_gid req; struct creq_add_gid_resp resp; u16 cmd_flags = 0; - u32 temp32[4]; - u16 temp16[3]; int rc; RCFW_CMD_PREP(req, ADD_GID, cmd_flags); - memcpy(temp32, gid->data, sizeof(struct bnxt_qplib_gid)); - req.gid[0] = cpu_to_be32(temp32[3]); - req.gid[1] = cpu_to_be32(temp32[2]); - req.gid[2] = cpu_to_be32(temp32[1]); - req.gid[3] = cpu_to_be32(temp32[0]); - if (vlan_id != 0xFFFF) - req.vlan = cpu_to_le16((vlan_id & - CMDQ_ADD_GID_VLAN_VLAN_ID_MASK) | - CMDQ_ADD_GID_VLAN_TPID_TPID_8100 | - CMDQ_ADD_GID_VLAN_VLAN_EN); + req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]); + req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]); + req.gid[2] = cpu_to_be32(((u32 *)gid->data)[1]); + req.gid[3] = cpu_to_be32(((u32 *)gid->data)[0]); + /* + * driver should ensure that all RoCE traffic is always VLAN + * tagged if RoCE traffic is running on non-zero VLAN ID or + * RoCE traffic is running on non-zero Priority. + */ + if ((vlan_id != 0xFFFF) || res->prio) { + if (vlan_id != 0xFFFF) + req.vlan = cpu_to_le16 + (vlan_id & CMDQ_ADD_GID_VLAN_VLAN_ID_MASK); + req.vlan |= cpu_to_le16 + (CMDQ_ADD_GID_VLAN_TPID_TPID_8100 | + CMDQ_ADD_GID_VLAN_VLAN_EN); + } /* MAC in network format */ - memcpy(temp16, smac, 6); - req.src_mac[0] = cpu_to_be16(temp16[0]); - req.src_mac[1] = cpu_to_be16(temp16[1]); - req.src_mac[2] = cpu_to_be16(temp16[2]); + req.src_mac[0] = cpu_to_be16(((u16 *)smac)[0]); + req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]); + req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, 0); @@ -297,6 +302,9 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, /* Add GID to the sgid_tbl */ memcpy(&sgid_tbl->tbl[free_idx], gid, sizeof(*gid)); sgid_tbl->active++; + if (vlan_id != 0xFFFF) + sgid_tbl->vlan[free_idx] = 1; + dev_dbg(&res->pdev->dev, "QPLIB: SGID added hw_id[0x%x] = 0x%x active = 0x%x", free_idx, sgid_tbl->hw_id[free_idx], sgid_tbl->active); @@ -306,6 +314,43 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, return 0; } +int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, + struct bnxt_qplib_gid *gid, u16 gid_idx, + u8 *smac) +{ + struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl, + struct bnxt_qplib_res, + sgid_tbl); + struct bnxt_qplib_rcfw *rcfw = res->rcfw; + struct creq_modify_gid_resp resp; + struct cmdq_modify_gid req; + int rc; + u16 cmd_flags = 0; + + RCFW_CMD_PREP(req, MODIFY_GID, cmd_flags); + + req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]); + req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]); + req.gid[2] = cpu_to_be32(((u32 *)gid->data)[1]); + req.gid[3] = cpu_to_be32(((u32 *)gid->data)[0]); + if (res->prio) { + req.vlan |= cpu_to_le16 + (CMDQ_ADD_GID_VLAN_TPID_TPID_8100 | + CMDQ_ADD_GID_VLAN_VLAN_EN); + } + + /* MAC in network format */ + req.src_mac[0] = cpu_to_be16(((u16 *)smac)[0]); + req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]); + req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]); + + req.gid_index = cpu_to_le16(gid_idx); + + rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, + (void *)&resp, NULL, 0); + return rc; +} + /* pkeys */ int bnxt_qplib_get_pkey(struct bnxt_qplib_res *res, struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 index, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 2ce7e2a32cf0..11322582f5e4 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -135,6 +135,8 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct bnxt_qplib_gid *gid, u8 *mac, u16 vlan_id, bool update, u32 *index); +int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, + struct bnxt_qplib_gid *gid, u16 gid_idx, u8 *smac); int bnxt_qplib_get_pkey(struct bnxt_qplib_res *res, struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 index, u16 *pkey); diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index fc23477ac52f..eeb55b2db57e 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -1473,8 +1473,8 @@ struct cmdq_modify_gid { u8 resp_size; u8 reserved8; __le64 resp_addr; - __le32 gid[4]; - __le16 src_mac[3]; + __be32 gid[4]; + __be16 src_mac[3]; __le16 vlan; #define CMDQ_MODIFY_GID_VLAN_VLAN_ID_MASK 0xfffUL #define CMDQ_MODIFY_GID_VLAN_VLAN_ID_SFT 0 diff --git a/drivers/infiniband/hw/cxgb3/iwch.c b/drivers/infiniband/hw/cxgb3/iwch.c index 47b2ce2ef203..591de319c178 100644 --- a/drivers/infiniband/hw/cxgb3/iwch.c +++ b/drivers/infiniband/hw/cxgb3/iwch.c @@ -45,7 +45,6 @@ MODULE_AUTHOR("Boyd Faulkner, Steve Wise"); MODULE_DESCRIPTION("Chelsio T3 RDMA Driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); static void open_rnic_dev(struct t3cdev *); static void close_rnic_dev(struct t3cdev *); diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 0cd0c1fa27d4..099e76f3758a 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1336,8 +1336,7 @@ static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str, - size_t str_len) +static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str) { struct iwch_dev *iwch_dev = to_iwch_dev(ibdev); struct ethtool_drvinfo info; @@ -1345,7 +1344,7 @@ static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str, pr_debug("%s dev 0x%p\n", __func__, iwch_dev); lldev->ethtool_ops->get_drvinfo(lldev, &info); - snprintf(str, str_len, "%s", info.fw_version); + snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version); } int iwch_register_device(struct iwch_dev *dev) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index e49b34c3b136..ceaa2fa54d32 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -2871,7 +2871,6 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb) return 0; pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid); - BUG_ON(!ep); /* The cm_id may be null if we failed to connect */ mutex_lock(&ep->com.mutex); diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index ae0b79aeea2e..fc886f81b885 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -44,7 +44,6 @@ MODULE_AUTHOR("Steve Wise"); MODULE_DESCRIPTION("Chelsio T4/T5 RDMA Driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); static int allow_db_fc_on_t5; module_param(allow_db_fc_on_t5, int, 0644); diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 0771e9a4d061..346e8334279a 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -517,14 +517,13 @@ static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_dev_fw_str(struct ib_device *dev, char *str, - size_t str_len) +static void get_dev_fw_str(struct ib_device *dev, char *str) { struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, ibdev); pr_debug("%s dev 0x%p\n", __func__, dev); - snprintf(str, str_len, "%u.%u.%u.%u", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u.%u", FW_HDR_FW_VER_MAJOR_G(c4iw_dev->rdev.lldi.fw_vers), FW_HDR_FW_VER_MINOR_G(c4iw_dev->rdev.lldi.fw_vers), FW_HDR_FW_VER_MICRO_G(c4iw_dev->rdev.lldi.fw_vers), diff --git a/drivers/infiniband/hw/hfi1/Makefile b/drivers/infiniband/hw/hfi1/Makefile index 88085f65432e..66d538c033b0 100644 --- a/drivers/infiniband/hw/hfi1/Makefile +++ b/drivers/infiniband/hw/hfi1/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_INFINIBAND_HFI1) += hfi1.o hfi1-y := affinity.o chip.o device.o driver.o efivar.o \ - eprom.o file_ops.o firmware.o \ + eprom.o exp_rcv.o file_ops.o firmware.o \ init.o intr.o mad.o mmu_rb.o pcie.o pio.o pio_copy.o platform.o \ qp.o qsfp.o rc.o ruc.o sdma.o sysfs.o trace.o \ uc.o ud.o user_exp_rcv.o user_pages.o user_sdma.o verbs.o \ diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index e2cd2cd3b28a..a97055dd4fbd 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -335,10 +335,10 @@ static void hfi1_update_sdma_affinity(struct hfi1_msix_entry *msix, int cpu) sde->cpu = cpu; cpumask_clear(&msix->mask); cpumask_set_cpu(cpu, &msix->mask); - dd_dev_dbg(dd, "IRQ vector: %u, type %s engine %u -> cpu: %d\n", - msix->msix.vector, irq_type_names[msix->type], + dd_dev_dbg(dd, "IRQ: %u, type %s engine %u -> cpu: %d\n", + msix->irq, irq_type_names[msix->type], sde->this_idx, cpu); - irq_set_affinity_hint(msix->msix.vector, &msix->mask); + irq_set_affinity_hint(msix->irq, &msix->mask); /* * Set the new cpu in the hfi1_affinity_node and clean @@ -387,7 +387,7 @@ static void hfi1_setup_sdma_notifier(struct hfi1_msix_entry *msix) { struct irq_affinity_notify *notify = &msix->notify; - notify->irq = msix->msix.vector; + notify->irq = msix->irq; notify->notify = hfi1_irq_notifier_notify; notify->release = hfi1_irq_notifier_release; @@ -472,10 +472,10 @@ static int get_irq_affinity(struct hfi1_devdata *dd, } cpumask_set_cpu(cpu, &msix->mask); - dd_dev_info(dd, "IRQ vector: %u, type %s %s -> cpu: %d\n", - msix->msix.vector, irq_type_names[msix->type], + dd_dev_info(dd, "IRQ: %u, type %s %s -> cpu: %d\n", + msix->irq, irq_type_names[msix->type], extra, cpu); - irq_set_affinity_hint(msix->msix.vector, &msix->mask); + irq_set_affinity_hint(msix->irq, &msix->mask); if (msix->type == IRQ_SDMA) { sde->cpu = cpu; @@ -533,7 +533,7 @@ void hfi1_put_irq_affinity(struct hfi1_devdata *dd, } } - irq_set_affinity_hint(msix->msix.vector, NULL); + irq_set_affinity_hint(msix->irq, NULL); cpumask_clear(&msix->mask); mutex_unlock(&node_affinity.lock); } diff --git a/drivers/infiniband/hw/hfi1/affinity.h b/drivers/infiniband/hw/hfi1/affinity.h index e78c7aa094e0..2a1e374169c0 100644 --- a/drivers/infiniband/hw/hfi1/affinity.h +++ b/drivers/infiniband/hw/hfi1/affinity.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -75,24 +75,26 @@ struct hfi1_msix_entry; /* Initialize non-HT cpu cores mask */ void init_real_cpu_mask(void); /* Initialize driver affinity data */ -int hfi1_dev_affinity_init(struct hfi1_devdata *); +int hfi1_dev_affinity_init(struct hfi1_devdata *dd); /* * Set IRQ affinity to a CPU. The function will determine the * CPU and set the affinity to it. */ -int hfi1_get_irq_affinity(struct hfi1_devdata *, struct hfi1_msix_entry *); +int hfi1_get_irq_affinity(struct hfi1_devdata *dd, + struct hfi1_msix_entry *msix); /* * Remove the IRQ's CPU affinity. This function also updates * any internal CPU tracking data */ -void hfi1_put_irq_affinity(struct hfi1_devdata *, struct hfi1_msix_entry *); +void hfi1_put_irq_affinity(struct hfi1_devdata *dd, + struct hfi1_msix_entry *msix); /* * Determine a CPU affinity for a user process, if the process does not * have an affinity set yet. */ -int hfi1_get_proc_affinity(int); +int hfi1_get_proc_affinity(int node); /* Release a CPU used by a user process. */ -void hfi1_put_proc_affinity(int); +void hfi1_put_proc_affinity(int cpu); struct hfi1_affinity_node { int node; diff --git a/drivers/infiniband/hw/hfi1/aspm.h b/drivers/infiniband/hw/hfi1/aspm.h index 794e6814a531..3f9a071ccac3 100644 --- a/drivers/infiniband/hw/hfi1/aspm.h +++ b/drivers/infiniband/hw/hfi1/aspm.h @@ -237,7 +237,7 @@ static inline void aspm_disable_all(struct hfi1_devdata *dd) { struct hfi1_ctxtdata *rcd; unsigned long flags; - unsigned i; + u16 i; for (i = 0; i < dd->first_dyn_alloc_ctxt; i++) { rcd = dd->rcd[i]; @@ -256,7 +256,7 @@ static inline void aspm_enable_all(struct hfi1_devdata *dd) { struct hfi1_ctxtdata *rcd; unsigned long flags; - unsigned i; + u16 i; aspm_enable(dd); @@ -284,7 +284,7 @@ static inline void aspm_ctx_init(struct hfi1_ctxtdata *rcd) static inline void aspm_init(struct hfi1_devdata *dd) { - unsigned i; + u16 i; spin_lock_init(&dd->aspm_lock); dd->aspm_supported = aspm_hw_l1_supported(dd); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 94b54850ec75..fdeec8abb6f1 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1012,14 +1012,15 @@ static struct flag_table dc8051_info_err_flags[] = { */ static struct flag_table dc8051_info_host_msg_flags[] = { FLAG_ENTRY0("Host request done", 0x0001), - FLAG_ENTRY0("BC SMA message", 0x0002), - FLAG_ENTRY0("BC PWR_MGM message", 0x0004), + FLAG_ENTRY0("BC PWR_MGM message", 0x0002), + FLAG_ENTRY0("BC SMA message", 0x0004), FLAG_ENTRY0("BC Unknown message (BCC)", 0x0008), FLAG_ENTRY0("BC Unknown message (LCB)", 0x0010), FLAG_ENTRY0("External device config request", 0x0020), FLAG_ENTRY0("VerifyCap all frames received", 0x0040), FLAG_ENTRY0("LinkUp achieved", 0x0080), FLAG_ENTRY0("Link going down", 0x0100), + FLAG_ENTRY0("Link width downgraded", 0x0200), }; static u32 encoded_size(u32 size); @@ -1066,6 +1067,8 @@ static int thermal_init(struct hfi1_devdata *dd); static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, int msecs); +static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state, + int msecs); static void read_planned_down_reason_code(struct hfi1_devdata *dd, u8 *pdrrc); static void read_link_down_reason(struct hfi1_devdata *dd, u8 *ldr); static void handle_temp_err(struct hfi1_devdata *dd); @@ -1294,25 +1297,71 @@ CNTR_ELEM(#name, \ CNTR_SYNTH, \ access_ibp_##cntr) +/** + * hfi_addr_from_offset - return addr for readq/writeq + * @dd - the dd device + * @offset - the offset of the CSR within bar0 + * + * This routine selects the appropriate base address + * based on the indicated offset. + */ +static inline void __iomem *hfi1_addr_from_offset( + const struct hfi1_devdata *dd, + u32 offset) +{ + if (offset >= dd->base2_start) + return dd->kregbase2 + (offset - dd->base2_start); + return dd->kregbase1 + offset; +} + +/** + * read_csr - read CSR at the indicated offset + * @dd - the dd device + * @offset - the offset of the CSR within bar0 + * + * Return: the value read or all FF's if there + * is no mapping + */ u64 read_csr(const struct hfi1_devdata *dd, u32 offset) { - if (dd->flags & HFI1_PRESENT) { - return readq((void __iomem *)dd->kregbase + offset); - } + if (dd->flags & HFI1_PRESENT) + return readq(hfi1_addr_from_offset(dd, offset)); return -1; } +/** + * write_csr - write CSR at the indicated offset + * @dd - the dd device + * @offset - the offset of the CSR within bar0 + * @value - value to write + */ void write_csr(const struct hfi1_devdata *dd, u32 offset, u64 value) { - if (dd->flags & HFI1_PRESENT) - writeq(value, (void __iomem *)dd->kregbase + offset); + if (dd->flags & HFI1_PRESENT) { + void __iomem *base = hfi1_addr_from_offset(dd, offset); + + /* avoid write to RcvArray */ + if (WARN_ON(offset >= RCV_ARRAY && offset < dd->base2_start)) + return; + writeq(value, base); + } } +/** + * get_csr_addr - return te iomem address for offset + * @dd - the dd device + * @offset - the offset of the CSR within bar0 + * + * Return: The iomem address to use in subsequent + * writeq/readq operations. + */ void __iomem *get_csr_addr( - struct hfi1_devdata *dd, + const struct hfi1_devdata *dd, u32 offset) { - return (void __iomem *)dd->kregbase + offset; + if (dd->flags & HFI1_PRESENT) + return hfi1_addr_from_offset(dd, offset); + return NULL; } static inline u64 read_write_csr(const struct hfi1_devdata *dd, u32 csr, @@ -5496,7 +5545,7 @@ static void update_rcverr_timer(unsigned long opaque) set_link_down_reason( ppd, OPA_LINKDOWN_REASON_EXCESSIVE_BUFFER_OVERRUN, 0, OPA_LINKDOWN_REASON_EXCESSIVE_BUFFER_OVERRUN); - queue_work(ppd->hfi1_wq, &ppd->link_bounce_work); + queue_work(ppd->link_wq, &ppd->link_bounce_work); } dd->rcv_ovfl_cnt = (u32)cur_ovfl_cnt; @@ -6051,7 +6100,7 @@ static void handle_qsfp_int(struct hfi1_devdata *dd, u32 src_ctx, u64 reg) * will not happen. We have to do it here * before turning the DC off. */ - queue_work(ppd->hfi1_wq, &ppd->link_down_work); + queue_work(ppd->link_wq, &ppd->link_down_work); } } else { dd_dev_info(dd, "%s: QSFP module inserted\n", @@ -6086,7 +6135,7 @@ static void handle_qsfp_int(struct hfi1_devdata *dd, u32 src_ctx, u64 reg) /* Schedule the QSFP work only if there is a cable attached. */ if (qsfp_mod_present(ppd)) - queue_work(ppd->hfi1_wq, &ppd->qsfp_info.qsfp_work); + queue_work(ppd->link_wq, &ppd->qsfp_info.qsfp_work); } static int request_host_lcb_access(struct hfi1_devdata *dd) @@ -6741,7 +6790,7 @@ static void rxe_freeze(struct hfi1_devdata *dd) /* disable all receive contexts */ for (i = 0; i < dd->num_rcv_contexts; i++) - hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_DIS, i); + hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_DIS, dd->rcd[i]); } /* @@ -6753,7 +6802,7 @@ static void rxe_freeze(struct hfi1_devdata *dd) static void rxe_kernel_unfreeze(struct hfi1_devdata *dd) { u32 rcvmask; - int i; + u16 i; /* enable all kernel contexts */ for (i = 0; i < dd->num_rcv_contexts; i++) { @@ -6765,9 +6814,9 @@ static void rxe_kernel_unfreeze(struct hfi1_devdata *dd) rcvmask = HFI1_RCVCTRL_CTXT_ENB; /* HFI1_RCVCTRL_TAILUPD_[ENB|DIS] needs to be set explicitly */ - rcvmask |= HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, DMA_RTAIL) ? + rcvmask |= HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ? HFI1_RCVCTRL_TAILUPD_ENB : HFI1_RCVCTRL_TAILUPD_DIS; - hfi1_rcvctrl(dd, rcvmask, i); + hfi1_rcvctrl(dd, rcvmask, rcd); } /* enable port */ @@ -6906,7 +6955,7 @@ static void reset_neighbor_info(struct hfi1_pportdata *ppd) static const char * const link_down_reason_strs[] = { [OPA_LINKDOWN_REASON_NONE] = "None", - [OPA_LINKDOWN_REASON_RCV_ERROR_0] = "Recive error 0", + [OPA_LINKDOWN_REASON_RCV_ERROR_0] = "Receive error 0", [OPA_LINKDOWN_REASON_BAD_PKT_LEN] = "Bad packet length", [OPA_LINKDOWN_REASON_PKT_TOO_LONG] = "Packet too long", [OPA_LINKDOWN_REASON_PKT_TOO_SHORT] = "Packet too short", @@ -6996,6 +7045,7 @@ void handle_link_down(struct work_struct *work) /* Go offline first, then deal with reading/writing through 8051 */ was_up = !!(ppd->host_link_state & HLS_UP); set_link_state(ppd, HLS_DN_OFFLINE); + xchg(&ppd->is_link_down_queued, 0); if (was_up) { lcl_reason = 0; @@ -7330,7 +7380,7 @@ void handle_verify_cap(struct work_struct *work) struct hfi1_devdata *dd = ppd->dd; u64 reg; u8 power_management; - u8 continious; + u8 continuous; u8 vcu; u8 vau; u8 z; @@ -7349,7 +7399,7 @@ void handle_verify_cap(struct work_struct *work) lcb_shutdown(dd, 0); adjust_lcb_for_fpga_serdes(dd); - read_vc_remote_phy(dd, &power_management, &continious); + read_vc_remote_phy(dd, &power_management, &continuous); read_vc_remote_fabric(dd, &vau, &z, &vcu, &vl15buf, &partner_supported_crc); read_vc_remote_link_width(dd, &remote_tx_rate, &link_widths); @@ -7363,7 +7413,7 @@ void handle_verify_cap(struct work_struct *work) get_link_widths(dd, &active_tx, &active_rx); dd_dev_info(dd, "Peer PHY: power management 0x%x, continuous updates 0x%x\n", - (int)power_management, (int)continious); + (int)power_management, (int)continuous); dd_dev_info(dd, "Peer Fabric: vAU %d, Z %d, vCU %d, vl15 credits 0x%x, CRC sizes 0x%x\n", (int)vau, (int)z, (int)vcu, (int)vl15buf, @@ -7689,12 +7739,12 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg) host_msg &= ~(u64)HOST_REQ_DONE; } if (host_msg & BC_SMA_MSG) { - queue_work(ppd->hfi1_wq, &ppd->sma_message_work); + queue_work(ppd->link_wq, &ppd->sma_message_work); host_msg &= ~(u64)BC_SMA_MSG; } if (host_msg & LINKUP_ACHIEVED) { dd_dev_info(dd, "8051: Link up\n"); - queue_work(ppd->hfi1_wq, &ppd->link_up_work); + queue_work(ppd->link_wq, &ppd->link_up_work); host_msg &= ~(u64)LINKUP_ACHIEVED; } if (host_msg & EXT_DEVICE_CFG_REQ) { @@ -7702,7 +7752,7 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg) host_msg &= ~(u64)EXT_DEVICE_CFG_REQ; } if (host_msg & VERIFY_CAP_FRAME) { - queue_work(ppd->hfi1_wq, &ppd->link_vc_work); + queue_work(ppd->link_wq, &ppd->link_vc_work); host_msg &= ~(u64)VERIFY_CAP_FRAME; } if (host_msg & LINK_GOING_DOWN) { @@ -7717,7 +7767,7 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg) host_msg &= ~(u64)LINK_GOING_DOWN; } if (host_msg & LINK_WIDTH_DOWNGRADED) { - queue_work(ppd->hfi1_wq, &ppd->link_downgrade_work); + queue_work(ppd->link_wq, &ppd->link_downgrade_work); host_msg &= ~(u64)LINK_WIDTH_DOWNGRADED; } if (host_msg) { @@ -7756,11 +7806,12 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg) */ if ((ppd->host_link_state & (HLS_GOING_OFFLINE | HLS_LINK_COOLDOWN)) || - ppd->link_enabled == 0) { + ppd->link_enabled == 0 || ppd->is_link_down_queued) { dd_dev_info(dd, "%s: not queuing link down\n", __func__); } else { - queue_work(ppd->hfi1_wq, &ppd->link_down_work); + xchg(&ppd->is_link_down_queued, 1); + queue_work(ppd->link_wq, &ppd->link_down_work); } } } @@ -7968,7 +8019,7 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg) dd_dev_info_ratelimited(dd, "%s: PortErrorAction bounce\n", __func__); set_link_down_reason(ppd, lcl_reason, 0, lcl_reason); - queue_work(ppd->hfi1_wq, &ppd->link_bounce_work); + queue_work(ppd->link_wq, &ppd->link_bounce_work); } } @@ -8781,6 +8832,20 @@ static void read_remote_device_id(struct hfi1_devdata *dd, u16 *device_id, & REMOTE_DEVICE_REV_MASK; } +int write_host_interface_version(struct hfi1_devdata *dd, u8 version) +{ + u32 frame; + u32 mask; + + mask = (HOST_INTERFACE_VERSION_MASK << HOST_INTERFACE_VERSION_SHIFT); + read_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, &frame); + /* Clear, then set field */ + frame &= ~mask; + frame |= ((u32)version << HOST_INTERFACE_VERSION_SHIFT); + return load_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, + frame); +} + void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor, u8 *ver_patch) { @@ -9257,12 +9322,6 @@ int start_link(struct hfi1_pportdata *ppd) */ tune_serdes(ppd); - if (!ppd->link_enabled) { - dd_dev_info(ppd->dd, - "%s: stopping link start because link is disabled\n", - __func__); - return 0; - } if (!ppd->driver_link_ready) { dd_dev_info(ppd->dd, "%s: stopping link start because driver is not ready\n", @@ -9373,13 +9432,13 @@ static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd, if ((qsfp_interrupt_status[0] & QSFP_HIGH_TEMP_ALARM) || (qsfp_interrupt_status[0] & QSFP_HIGH_TEMP_WARNING)) - dd_dev_info(dd, "%s: QSFP cable temperature too high\n", - __func__); + dd_dev_err(dd, "%s: QSFP cable temperature too high\n", + __func__); if ((qsfp_interrupt_status[0] & QSFP_LOW_TEMP_ALARM) || (qsfp_interrupt_status[0] & QSFP_LOW_TEMP_WARNING)) - dd_dev_info(dd, "%s: QSFP cable temperature too low\n", - __func__); + dd_dev_err(dd, "%s: QSFP cable temperature too low\n", + __func__); /* * The remaining alarms/warnings don't matter if the link is down. @@ -9389,75 +9448,75 @@ static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd, if ((qsfp_interrupt_status[1] & QSFP_HIGH_VCC_ALARM) || (qsfp_interrupt_status[1] & QSFP_HIGH_VCC_WARNING)) - dd_dev_info(dd, "%s: QSFP supply voltage too high\n", - __func__); + dd_dev_err(dd, "%s: QSFP supply voltage too high\n", + __func__); if ((qsfp_interrupt_status[1] & QSFP_LOW_VCC_ALARM) || (qsfp_interrupt_status[1] & QSFP_LOW_VCC_WARNING)) - dd_dev_info(dd, "%s: QSFP supply voltage too low\n", - __func__); + dd_dev_err(dd, "%s: QSFP supply voltage too low\n", + __func__); /* Byte 2 is vendor specific */ if ((qsfp_interrupt_status[3] & QSFP_HIGH_POWER_ALARM) || (qsfp_interrupt_status[3] & QSFP_HIGH_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable RX channel 1/2 power too high\n", - __func__); + dd_dev_err(dd, "%s: Cable RX channel 1/2 power too high\n", + __func__); if ((qsfp_interrupt_status[3] & QSFP_LOW_POWER_ALARM) || (qsfp_interrupt_status[3] & QSFP_LOW_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable RX channel 1/2 power too low\n", - __func__); + dd_dev_err(dd, "%s: Cable RX channel 1/2 power too low\n", + __func__); if ((qsfp_interrupt_status[4] & QSFP_HIGH_POWER_ALARM) || (qsfp_interrupt_status[4] & QSFP_HIGH_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable RX channel 3/4 power too high\n", - __func__); + dd_dev_err(dd, "%s: Cable RX channel 3/4 power too high\n", + __func__); if ((qsfp_interrupt_status[4] & QSFP_LOW_POWER_ALARM) || (qsfp_interrupt_status[4] & QSFP_LOW_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable RX channel 3/4 power too low\n", - __func__); + dd_dev_err(dd, "%s: Cable RX channel 3/4 power too low\n", + __func__); if ((qsfp_interrupt_status[5] & QSFP_HIGH_BIAS_ALARM) || (qsfp_interrupt_status[5] & QSFP_HIGH_BIAS_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 1/2 bias too high\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 1/2 bias too high\n", + __func__); if ((qsfp_interrupt_status[5] & QSFP_LOW_BIAS_ALARM) || (qsfp_interrupt_status[5] & QSFP_LOW_BIAS_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 1/2 bias too low\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 1/2 bias too low\n", + __func__); if ((qsfp_interrupt_status[6] & QSFP_HIGH_BIAS_ALARM) || (qsfp_interrupt_status[6] & QSFP_HIGH_BIAS_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 3/4 bias too high\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 3/4 bias too high\n", + __func__); if ((qsfp_interrupt_status[6] & QSFP_LOW_BIAS_ALARM) || (qsfp_interrupt_status[6] & QSFP_LOW_BIAS_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 3/4 bias too low\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 3/4 bias too low\n", + __func__); if ((qsfp_interrupt_status[7] & QSFP_HIGH_POWER_ALARM) || (qsfp_interrupt_status[7] & QSFP_HIGH_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 1/2 power too high\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 1/2 power too high\n", + __func__); if ((qsfp_interrupt_status[7] & QSFP_LOW_POWER_ALARM) || (qsfp_interrupt_status[7] & QSFP_LOW_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 1/2 power too low\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 1/2 power too low\n", + __func__); if ((qsfp_interrupt_status[8] & QSFP_HIGH_POWER_ALARM) || (qsfp_interrupt_status[8] & QSFP_HIGH_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 3/4 power too high\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 3/4 power too high\n", + __func__); if ((qsfp_interrupt_status[8] & QSFP_LOW_POWER_ALARM) || (qsfp_interrupt_status[8] & QSFP_LOW_POWER_WARNING)) - dd_dev_info(dd, "%s: Cable TX channel 3/4 power too low\n", - __func__); + dd_dev_err(dd, "%s: Cable TX channel 3/4 power too low\n", + __func__); /* Bytes 9-10 and 11-12 are reserved */ /* Bytes 13-15 are vendor specific */ @@ -9480,6 +9539,13 @@ void qsfp_event(struct work_struct *work) if (!qsfp_mod_present(ppd)) return; + if (ppd->host_link_state == HLS_DN_DISABLE) { + dd_dev_info(ppd->dd, + "%s: stopping link start because link is disabled\n", + __func__); + return; + } + /* * Turn DC back on after cable has been re-inserted. Up until * now, the DC has been in reset to save power. @@ -9635,7 +9701,7 @@ static void try_start_link(struct hfi1_pportdata *ppd) "QSFP not responding, waiting and retrying %d\n", (int)ppd->qsfp_retry_count); ppd->qsfp_retry_count++; - queue_delayed_work(ppd->hfi1_wq, &ppd->start_link_work, + queue_delayed_work(ppd->link_wq, &ppd->start_link_work, msecs_to_jiffies(QSFP_RETRY_WAIT)); return; } @@ -9742,17 +9808,6 @@ static inline int init_cpu_counters(struct hfi1_devdata *dd) return 0; } -static const char * const pt_names[] = { - "expected", - "eager", - "invalid" -}; - -static const char *pt_name(u32 type) -{ - return type >= ARRAY_SIZE(pt_names) ? "unknown" : pt_names[type]; -} - /* * index is the index into the receive array */ @@ -9760,35 +9815,34 @@ void hfi1_put_tid(struct hfi1_devdata *dd, u32 index, u32 type, unsigned long pa, u16 order) { u64 reg; - void __iomem *base = (dd->rcvarray_wc ? dd->rcvarray_wc : - (dd->kregbase + RCV_ARRAY)); if (!(dd->flags & HFI1_PRESENT)) goto done; - if (type == PT_INVALID) { + if (type == PT_INVALID || type == PT_INVALID_FLUSH) { pa = 0; + order = 0; } else if (type > PT_INVALID) { dd_dev_err(dd, "unexpected receive array type %u for index %u, not handled\n", type, index); goto done; } - - hfi1_cdbg(TID, "type %s, index 0x%x, pa 0x%lx, bsize 0x%lx", - pt_name(type), index, pa, (unsigned long)order); + trace_hfi1_put_tid(dd, index, type, pa, order); #define RT_ADDR_SHIFT 12 /* 4KB kernel address boundary */ reg = RCV_ARRAY_RT_WRITE_ENABLE_SMASK | (u64)order << RCV_ARRAY_RT_BUF_SIZE_SHIFT | ((pa >> RT_ADDR_SHIFT) & RCV_ARRAY_RT_ADDR_MASK) << RCV_ARRAY_RT_ADDR_SHIFT; - writeq(reg, base + (index * 8)); + trace_hfi1_write_rcvarray(dd->rcvarray_wc + (index * 8), reg); + writeq(reg, dd->rcvarray_wc + (index * 8)); - if (type == PT_EAGER) + if (type == PT_EAGER || type == PT_INVALID_FLUSH || (index & 3) == 3) /* - * Eager entries are written one-by-one so we have to push them - * after we write the entry. + * Eager entries are written and flushed + * + * Expected entries are flushed every 4 writes */ flush_wc(); done: @@ -9810,15 +9864,6 @@ void hfi1_clear_tids(struct hfi1_ctxtdata *rcd) hfi1_put_tid(dd, i, PT_INVALID, 0, 0); } -struct ib_header *hfi1_get_msgheader( - struct hfi1_devdata *dd, __le32 *rhf_addr) -{ - u32 offset = rhf_hdrq_offset(rhf_to_cpu(rhf_addr)); - - return (struct ib_header *) - (rhf_addr - dd->rhf_offset + offset); -} - static const char * const ib_cfg_name_strings[] = { "HFI1_IB_CFG_LIDLMC", "HFI1_IB_CFG_LWID_DG_ENB", @@ -10037,28 +10082,6 @@ static void set_lidlmc(struct hfi1_pportdata *ppd) sdma_update_lmc(dd, mask, ppd->lid); } -static int wait_phy_linkstate(struct hfi1_devdata *dd, u32 state, u32 msecs) -{ - unsigned long timeout; - u32 curr_state; - - timeout = jiffies + msecs_to_jiffies(msecs); - while (1) { - curr_state = read_physical_state(dd); - if (curr_state == state) - break; - if (time_after(jiffies, timeout)) { - dd_dev_err(dd, - "timeout waiting for phy link state 0x%x, current state is 0x%x\n", - state, curr_state); - return -ETIMEDOUT; - } - usleep_range(1950, 2050); /* sleep 2ms-ish */ - } - - return 0; -} - static const char *state_completed_string(u32 completed) { static const char * const state_completed[] = { @@ -10253,49 +10276,35 @@ static void force_logical_link_state_down(struct hfi1_pportdata *ppd) static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) { struct hfi1_devdata *dd = ppd->dd; - u32 pstate, previous_state; + u32 previous_state; int ret; - int do_transition; - int do_wait; update_lcb_cache(dd); previous_state = ppd->host_link_state; ppd->host_link_state = HLS_GOING_OFFLINE; - pstate = read_physical_state(dd); - if (pstate == PLS_OFFLINE) { - do_transition = 0; /* in right state */ - do_wait = 0; /* ...no need to wait */ - } else if ((pstate & 0xf0) == PLS_OFFLINE) { - do_transition = 0; /* in an offline transient state */ - do_wait = 1; /* ...wait for it to settle */ - } else { - do_transition = 1; /* need to move to offline */ - do_wait = 1; /* ...will need to wait */ - } - if (do_transition) { - ret = set_physical_link_state(dd, - (rem_reason << 8) | PLS_OFFLINE); + /* start offline transition */ + ret = set_physical_link_state(dd, (rem_reason << 8) | PLS_OFFLINE); - if (ret != HCMD_SUCCESS) { - dd_dev_err(dd, - "Failed to transition to Offline link state, return %d\n", - ret); - return -EINVAL; - } - if (ppd->offline_disabled_reason == - HFI1_ODR_MASK(OPA_LINKDOWN_REASON_NONE)) - ppd->offline_disabled_reason = - HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT); + if (ret != HCMD_SUCCESS) { + dd_dev_err(dd, + "Failed to transition to Offline link state, return %d\n", + ret); + return -EINVAL; } + if (ppd->offline_disabled_reason == + HFI1_ODR_MASK(OPA_LINKDOWN_REASON_NONE)) + ppd->offline_disabled_reason = + HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT); - if (do_wait) { - /* it can take a while for the link to go down */ - ret = wait_phy_linkstate(dd, PLS_OFFLINE, 10000); - if (ret < 0) - return ret; - } + /* + * Wait for offline transition. It can take a while for + * the link to go down. + */ + ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000); + if (ret < 0) + return ret; /* * Now in charge of LCB - must be after the physical state is @@ -10484,6 +10493,14 @@ void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason, } /* + * Verify if BCT for data VLs is non-zero. + */ +static inline bool data_vls_operational(struct hfi1_pportdata *ppd) +{ + return !!ppd->actual_vls_operational; +} + +/* * Change the physical and/or logical link state. * * Do not call this routine while inside an interrupt. It contains @@ -10545,38 +10562,58 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) goto unexpected; } + /* + * Wait for Link_Up physical state. + * Physical and Logical states should already be + * be transitioned to LinkUp and LinkInit respectively. + */ + ret = wait_physical_linkstate(ppd, PLS_LINKUP, 1000); + if (ret) { + dd_dev_err(dd, + "%s: physical state did not change to LINK-UP\n", + __func__); + break; + } + ret = wait_logical_linkstate(ppd, IB_PORT_INIT, 1000); if (ret) { dd_dev_err(dd, "%s: logical state did not change to INIT\n", __func__); - } else { - /* clear old transient LINKINIT_REASON code */ - if (ppd->linkinit_reason >= OPA_LINKINIT_REASON_CLEAR) - ppd->linkinit_reason = - OPA_LINKINIT_REASON_LINKUP; + break; + } - /* enable the port */ - add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK); + /* clear old transient LINKINIT_REASON code */ + if (ppd->linkinit_reason >= OPA_LINKINIT_REASON_CLEAR) + ppd->linkinit_reason = + OPA_LINKINIT_REASON_LINKUP; - handle_linkup_change(dd, 1); - ppd->host_link_state = HLS_UP_INIT; - } + /* enable the port */ + add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK); + + handle_linkup_change(dd, 1); + ppd->host_link_state = HLS_UP_INIT; break; case HLS_UP_ARMED: if (ppd->host_link_state != HLS_UP_INIT) goto unexpected; - ppd->host_link_state = HLS_UP_ARMED; + if (!data_vls_operational(ppd)) { + dd_dev_err(dd, + "%s: data VLs not operational\n", __func__); + ret = -EINVAL; + break; + } + set_logical_state(dd, LSTATE_ARMED); ret = wait_logical_linkstate(ppd, IB_PORT_ARMED, 1000); if (ret) { - /* logical state didn't change, stay at init */ - ppd->host_link_state = HLS_UP_INIT; dd_dev_err(dd, "%s: logical state did not change to ARMED\n", __func__); + break; } + ppd->host_link_state = HLS_UP_ARMED; /* * The simulator does not currently implement SMA messages, * so neighbor_normal is not set. Set it here when we first @@ -10589,18 +10626,16 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) if (ppd->host_link_state != HLS_UP_ARMED) goto unexpected; - ppd->host_link_state = HLS_UP_ACTIVE; set_logical_state(dd, LSTATE_ACTIVE); ret = wait_logical_linkstate(ppd, IB_PORT_ACTIVE, 1000); if (ret) { - /* logical state didn't change, stay at armed */ - ppd->host_link_state = HLS_UP_ARMED; dd_dev_err(dd, "%s: logical state did not change to ACTIVE\n", __func__); } else { /* tell all engines to go running */ sdma_all_running(dd); + ppd->host_link_state = HLS_UP_ACTIVE; /* Signal the IB layer that the port has went active */ event.device = &dd->verbs_dev.rdi.ibdev; @@ -10658,6 +10693,8 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) */ if (ret) goto_offline(ppd, 0); + else + cache_physical_state(ppd); break; case HLS_DN_DISABLE: /* link is disabled */ @@ -10682,6 +10719,13 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) ret = -EINVAL; break; } + ret = wait_physical_linkstate(ppd, PLS_DISABLED, 10000); + if (ret) { + dd_dev_err(dd, + "%s: physical state did not change to DISABLED\n", + __func__); + break; + } dc_shutdown(dd); } ppd->host_link_state = HLS_DN_DISABLE; @@ -10699,6 +10743,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) if (ppd->host_link_state != HLS_DN_POLL) goto unexpected; ppd->host_link_state = HLS_VERIFY_CAP; + cache_physical_state(ppd); break; case HLS_GOING_UP: if (ppd->host_link_state != HLS_VERIFY_CAP) @@ -11693,16 +11738,18 @@ static u32 encoded_size(u32 size) return 0x1; /* if invalid, go with the minimum size */ } -void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, int ctxt) +void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, + struct hfi1_ctxtdata *rcd) { - struct hfi1_ctxtdata *rcd; u64 rcvctrl, reg; int did_enable = 0; + u16 ctxt; - rcd = dd->rcd[ctxt]; if (!rcd) return; + ctxt = rcd->ctxt; + hfi1_cdbg(RCVCTRL, "ctxt %d op 0x%x", ctxt, op); rcvctrl = read_kctxt_csr(dd, ctxt, RCV_CTXT_CTRL); @@ -12672,21 +12719,56 @@ static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, return -ETIMEDOUT; } -u8 hfi1_ibphys_portstate(struct hfi1_pportdata *ppd) +/* + * Read the physical hardware link state and set the driver's cached value + * of it. + */ +void cache_physical_state(struct hfi1_pportdata *ppd) { - u32 pstate; + u32 read_pstate; u32 ib_pstate; - pstate = read_physical_state(ppd->dd); - ib_pstate = chip_to_opa_pstate(ppd->dd, pstate); - if (ppd->last_pstate != ib_pstate) { + read_pstate = read_physical_state(ppd->dd); + ib_pstate = chip_to_opa_pstate(ppd->dd, read_pstate); + /* check if OPA pstate changed */ + if (chip_to_opa_pstate(ppd->dd, ppd->pstate) != ib_pstate) { dd_dev_info(ppd->dd, "%s: physical state changed to %s (0x%x), phy 0x%x\n", __func__, opa_pstate_name(ib_pstate), ib_pstate, - pstate); - ppd->last_pstate = ib_pstate; + read_pstate); } - return ib_pstate; + ppd->pstate = read_pstate; +} + +/* + * wait_physical_linkstate - wait for an physical link state change to occur + * @ppd: port device + * @state: the state to wait for + * @msecs: the number of milliseconds to wait + * + * Wait up to msecs milliseconds for physical link state change to occur. + * Returns 0 if state reached, otherwise -ETIMEDOUT. + */ +static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state, + int msecs) +{ + unsigned long timeout; + + timeout = jiffies + msecs_to_jiffies(msecs); + while (1) { + cache_physical_state(ppd); + if (ppd->pstate == state) + break; + if (time_after(jiffies, timeout)) { + dd_dev_err(ppd->dd, + "timeout waiting for phy link state 0x%x, current state is 0x%x\n", + state, ppd->pstate); + return -ETIMEDOUT; + } + usleep_range(1950, 2050); /* sleep 2ms-ish */ + } + + return 0; } #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \ @@ -12809,30 +12891,24 @@ static void clean_up_interrupts(struct hfi1_devdata *dd) for (i = 0; i < dd->num_msix_entries; i++, me++) { if (!me->arg) /* => no irq, no affinity */ continue; - hfi1_put_irq_affinity(dd, &dd->msix_entries[i]); - free_irq(me->msix.vector, me->arg); + hfi1_put_irq_affinity(dd, me); + free_irq(me->irq, me->arg); } + + /* clean structures */ + kfree(dd->msix_entries); + dd->msix_entries = NULL; + dd->num_msix_entries = 0; } else { /* INTx */ if (dd->requested_intx_irq) { free_irq(dd->pcidev->irq, dd); dd->requested_intx_irq = 0; } - } - - /* turn off interrupts */ - if (dd->num_msix_entries) { - /* MSI-X */ - pci_disable_msix(dd->pcidev); - } else { - /* INTx */ disable_intx(dd->pcidev); } - /* clean structures */ - kfree(dd->msix_entries); - dd->msix_entries = NULL; - dd->num_msix_entries = 0; + pci_free_irq_vectors(dd->pcidev); } /* @@ -12986,13 +13062,21 @@ static int request_msix_irqs(struct hfi1_devdata *dd) continue; /* make sure the name is terminated */ me->name[sizeof(me->name) - 1] = 0; + me->irq = pci_irq_vector(dd->pcidev, i); + /* + * On err return me->irq. Don't need to clear this + * because 'arg' has not been set, and cleanup will + * do the right thing. + */ + if (me->irq < 0) + return me->irq; - ret = request_threaded_irq(me->msix.vector, handler, thread, 0, + ret = request_threaded_irq(me->irq, handler, thread, 0, me->name, arg); if (ret) { dd_dev_err(dd, - "unable to allocate %s interrupt, vector %d, index %d, err %d\n", - err_info, me->msix.vector, idx, ret); + "unable to allocate %s interrupt, irq %d, index %d, err %d\n", + err_info, me->irq, idx, ret); return ret; } /* @@ -13003,8 +13087,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd) ret = hfi1_get_irq_affinity(dd, me); if (ret) - dd_dev_err(dd, - "unable to pin IRQ %d\n", ret); + dd_dev_err(dd, "unable to pin IRQ %d\n", ret); } return ret; @@ -13023,7 +13106,7 @@ void hfi1_vnic_synchronize_irq(struct hfi1_devdata *dd) struct hfi1_ctxtdata *rcd = dd->vnic.ctxt[i]; struct hfi1_msix_entry *me = &dd->msix_entries[rcd->msix_intr]; - synchronize_irq(me->msix.vector); + synchronize_irq(me->irq); } } @@ -13036,7 +13119,7 @@ void hfi1_reset_vnic_msix_info(struct hfi1_ctxtdata *rcd) return; hfi1_put_irq_affinity(dd, me); - free_irq(me->msix.vector, me->arg); + free_irq(me->irq, me->arg); me->arg = NULL; } @@ -13064,14 +13147,19 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd) DRIVER_NAME "_%d kctxt%d", dd->unit, idx); me->name[sizeof(me->name) - 1] = 0; me->type = IRQ_RCVCTXT; - + me->irq = pci_irq_vector(dd->pcidev, rcd->msix_intr); + if (me->irq < 0) { + dd_dev_err(dd, "vnic irq vector request (idx %d) fail %d\n", + idx, me->irq); + return; + } remap_intr(dd, IS_RCVAVAIL_START + idx, rcd->msix_intr); - ret = request_threaded_irq(me->msix.vector, receive_context_interrupt, + ret = request_threaded_irq(me->irq, receive_context_interrupt, receive_context_thread, 0, me->name, arg); if (ret) { - dd_dev_err(dd, "vnic irq request (vector %d, idx %d) fail %d\n", - me->msix.vector, idx, ret); + dd_dev_err(dd, "vnic irq request (irq %d, idx %d) fail %d\n", + me->irq, idx, ret); return; } /* @@ -13084,7 +13172,7 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd) if (ret) { dd_dev_err(dd, "unable to pin IRQ %d\n", ret); - free_irq(me->msix.vector, me->arg); + free_irq(me->irq, me->arg); } } @@ -13107,9 +13195,8 @@ static void reset_interrupts(struct hfi1_devdata *dd) static int set_up_interrupts(struct hfi1_devdata *dd) { - struct hfi1_msix_entry *entries; - u32 total, request; - int i, ret; + u32 total; + int ret, request; int single_interrupt = 0; /* we expect to have all the interrupts */ /* @@ -13121,39 +13208,31 @@ static int set_up_interrupts(struct hfi1_devdata *dd) */ total = 1 + dd->num_sdma + dd->n_krcv_queues + HFI1_NUM_VNIC_CTXT; - entries = kcalloc(total, sizeof(*entries), GFP_KERNEL); - if (!entries) { - ret = -ENOMEM; - goto fail; - } - /* 1-1 MSI-X entry assignment */ - for (i = 0; i < total; i++) - entries[i].msix.entry = i; - /* ask for MSI-X interrupts */ - request = total; - request_msix(dd, &request, entries); - - if (request == 0) { + request = request_msix(dd, total); + if (request < 0) { + ret = request; + goto fail; + } else if (request == 0) { /* using INTx */ /* dd->num_msix_entries already zero */ - kfree(entries); single_interrupt = 1; dd_dev_err(dd, "MSI-X failed, using INTx interrupts\n"); + } else if (request < total) { + /* using MSI-X, with reduced interrupts */ + dd_dev_err(dd, "reduced interrupt found, wanted %u, got %u\n", + total, request); + ret = -EINVAL; + goto fail; } else { - /* using MSI-X */ - dd->num_msix_entries = request; - dd->msix_entries = entries; - - if (request != total) { - /* using MSI-X, with reduced interrupts */ - dd_dev_err( - dd, - "cannot handle reduced interrupt case, want %u, got %u\n", - total, request); - ret = -EINVAL; + dd->msix_entries = kcalloc(total, sizeof(*dd->msix_entries), + GFP_KERNEL); + if (!dd->msix_entries) { + ret = -ENOMEM; goto fail; } + /* using MSI-X */ + dd->num_msix_entries = total; dd_dev_info(dd, "%u MSI-X interrupts allocated\n", total); } @@ -13396,8 +13475,7 @@ static void write_uninitialized_csrs_and_memories(struct hfi1_devdata *dd) /* RcvArray */ for (i = 0; i < dd->chip_rcv_array_count; i++) - write_csr(dd, RCV_ARRAY + (8 * i), - RCV_ARRAY_RT_WRITE_ENABLE_SMASK); + hfi1_put_tid(dd, i, PT_INVALID_FLUSH, 0, 0); /* RcvQPMapTable */ for (i = 0; i < 32; i++) @@ -13831,9 +13909,10 @@ static void init_sc2vl_tables(struct hfi1_devdata *dd) * a reset following the (possible) FLR in this routine. * */ -static void init_chip(struct hfi1_devdata *dd) +static int init_chip(struct hfi1_devdata *dd) { int i; + int ret = 0; /* * Put the HFI CSRs in a known state. @@ -13881,12 +13960,22 @@ static void init_chip(struct hfi1_devdata *dd) pcie_flr(dd->pcidev); /* restore command and BARs */ - restore_pci_variables(dd); + ret = restore_pci_variables(dd); + if (ret) { + dd_dev_err(dd, "%s: Could not restore PCI variables\n", + __func__); + return ret; + } if (is_ax(dd)) { dd_dev_info(dd, "Resetting CSRs with FLR\n"); pcie_flr(dd->pcidev); - restore_pci_variables(dd); + ret = restore_pci_variables(dd); + if (ret) { + dd_dev_err(dd, "%s: Could not restore PCI variables\n", + __func__); + return ret; + } } } else { dd_dev_info(dd, "Resetting CSRs with writes\n"); @@ -13914,6 +14003,7 @@ static void init_chip(struct hfi1_devdata *dd) write_csr(dd, ASIC_QSFP1_OUT, 0x1f); write_csr(dd, ASIC_QSFP2_OUT, 0x1f); init_chip_resources(dd); + return ret; } static void init_early_variables(struct hfi1_devdata *dd) @@ -14470,99 +14560,86 @@ static void init_txe(struct hfi1_devdata *dd) write_csr(dd, SEND_CM_TIMER_CTRL, HFI1_CREDIT_RETURN_RATE); } -int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt, u16 jkey) +int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd, + u16 jkey) { - struct hfi1_ctxtdata *rcd = dd->rcd[ctxt]; - unsigned sctxt; - int ret = 0; + u8 hw_ctxt; u64 reg; - if (!rcd || !rcd->sc) { - ret = -EINVAL; - goto done; - } - sctxt = rcd->sc->hw_context; + if (!rcd || !rcd->sc) + return -EINVAL; + + hw_ctxt = rcd->sc->hw_context; reg = SEND_CTXT_CHECK_JOB_KEY_MASK_SMASK | /* mask is always 1's */ ((jkey & SEND_CTXT_CHECK_JOB_KEY_VALUE_MASK) << SEND_CTXT_CHECK_JOB_KEY_VALUE_SHIFT); /* JOB_KEY_ALLOW_PERMISSIVE is not allowed by default */ if (HFI1_CAP_KGET_MASK(rcd->flags, ALLOW_PERM_JKEY)) reg |= SEND_CTXT_CHECK_JOB_KEY_ALLOW_PERMISSIVE_SMASK; - write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_JOB_KEY, reg); + write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_JOB_KEY, reg); /* * Enable send-side J_KEY integrity check, unless this is A0 h/w */ if (!is_ax(dd)) { - reg = read_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE); + reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE); reg |= SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK; - write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE, reg); + write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE, reg); } /* Enable J_KEY check on receive context. */ reg = RCV_KEY_CTRL_JOB_KEY_ENABLE_SMASK | ((jkey & RCV_KEY_CTRL_JOB_KEY_VALUE_MASK) << RCV_KEY_CTRL_JOB_KEY_VALUE_SHIFT); - write_kctxt_csr(dd, ctxt, RCV_KEY_CTRL, reg); -done: - return ret; + write_kctxt_csr(dd, rcd->ctxt, RCV_KEY_CTRL, reg); + + return 0; } -int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt) +int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd) { - struct hfi1_ctxtdata *rcd = dd->rcd[ctxt]; - unsigned sctxt; - int ret = 0; + u8 hw_ctxt; u64 reg; - if (!rcd || !rcd->sc) { - ret = -EINVAL; - goto done; - } - sctxt = rcd->sc->hw_context; - write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_JOB_KEY, 0); + if (!rcd || !rcd->sc) + return -EINVAL; + + hw_ctxt = rcd->sc->hw_context; + write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_JOB_KEY, 0); /* * Disable send-side J_KEY integrity check, unless this is A0 h/w. * This check would not have been enabled for A0 h/w, see * set_ctxt_jkey(). */ if (!is_ax(dd)) { - reg = read_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE); + reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE); reg &= ~SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK; - write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE, reg); + write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE, reg); } /* Turn off the J_KEY on the receive side */ - write_kctxt_csr(dd, ctxt, RCV_KEY_CTRL, 0); -done: - return ret; + write_kctxt_csr(dd, rcd->ctxt, RCV_KEY_CTRL, 0); + + return 0; } -int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, unsigned ctxt, u16 pkey) +int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd, + u16 pkey) { - struct hfi1_ctxtdata *rcd; - unsigned sctxt; - int ret = 0; + u8 hw_ctxt; u64 reg; - if (ctxt < dd->num_rcv_contexts) { - rcd = dd->rcd[ctxt]; - } else { - ret = -EINVAL; - goto done; - } - if (!rcd || !rcd->sc) { - ret = -EINVAL; - goto done; - } - sctxt = rcd->sc->hw_context; + if (!rcd || !rcd->sc) + return -EINVAL; + + hw_ctxt = rcd->sc->hw_context; reg = ((u64)pkey & SEND_CTXT_CHECK_PARTITION_KEY_VALUE_MASK) << SEND_CTXT_CHECK_PARTITION_KEY_VALUE_SHIFT; - write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_PARTITION_KEY, reg); - reg = read_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE); + write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_PARTITION_KEY, reg); + reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE); reg |= SEND_CTXT_CHECK_ENABLE_CHECK_PARTITION_KEY_SMASK; reg &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_KDETH_PACKETS_SMASK; - write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE, reg); -done: - return ret; + write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE, reg); + + return 0; } int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt) @@ -14573,9 +14650,6 @@ int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt) if (!ctxt || !ctxt->sc) return -EINVAL; - if (ctxt->ctxt >= dd->num_rcv_contexts) - return -EINVAL; - hw_ctxt = ctxt->sc->hw_context; reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE); reg &= ~SEND_CTXT_CHECK_ENABLE_CHECK_PARTITION_KEY_SMASK; @@ -14773,7 +14847,6 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, } ppd->vls_supported = num_vls; ppd->vls_operational = ppd->vls_supported; - ppd->actual_vls_operational = ppd->vls_supported; /* Set the default MTU. */ for (vl = 0; vl < num_vls; vl++) dd->vld[vl].mtu = hfi1_max_mtu; @@ -14793,7 +14866,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, /* start in offline */ ppd->host_link_state = HLS_DN_OFFLINE; init_vl_arb_caches(ppd); - ppd->last_pstate = 0xff; /* invalid value */ + ppd->pstate = PLS_OFFLINE; } dd->link_default = HLS_DN_POLL; @@ -14807,6 +14880,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, if (ret < 0) goto bail_free; + /* Save PCI space registers to rewrite after device reset */ + ret = save_pci_variables(dd); + if (ret < 0) + goto bail_cleanup; + /* verify that reads actually work, save revision for reset check */ dd->revision = read_csr(dd, CCE_REVISION); if (dd->revision == ~(u64)0) { @@ -14899,7 +14977,9 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, goto bail_cleanup; /* obtain chip sizes, reset chip CSRs */ - init_chip(dd); + ret = init_chip(dd); + if (ret) + goto bail_cleanup; /* read in the PCIe link speed information */ ret = pcie_speeds(dd); diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index cbe455d9ab8b..6a0c691f1385 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -384,6 +384,7 @@ #define VERIFY_CAP_LOCAL_FABRIC 0x08 #define VERIFY_CAP_LOCAL_LINK_WIDTH 0x09 #define LOCAL_DEVICE_ID 0x0a +#define RESERVED_REGISTERS 0x0b #define LOCAL_LNI_INFO 0x0c #define REMOTE_LNI_INFO 0x0d #define MISC_STATUS 0x0e @@ -506,6 +507,9 @@ #define DOWN_REMOTE_REASON_SHIFT 16 #define DOWN_REMOTE_REASON_MASK 0xff +#define HOST_INTERFACE_VERSION_SHIFT 16 +#define HOST_INTERFACE_VERSION_MASK 0xff + /* verify capability PHY power management bits */ #define PWRM_BER_CONTROL 0x1 #define PWRM_BANDWIDTH_CONTROL 0x2 @@ -605,11 +609,11 @@ int read_lcb_csr(struct hfi1_devdata *dd, u32 offset, u64 *data); int write_lcb_csr(struct hfi1_devdata *dd, u32 offset, u64 data); void __iomem *get_csr_addr( - struct hfi1_devdata *dd, + const struct hfi1_devdata *dd, u32 offset); static inline void __iomem *get_kctxt_csr_addr( - struct hfi1_devdata *dd, + const struct hfi1_devdata *dd, int ctxt, u32 offset0) { @@ -704,6 +708,7 @@ int read_8051_data(struct hfi1_devdata *dd, u32 addr, u32 len, u64 *result); /* chip.c */ void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor, u8 *ver_patch); +int write_host_interface_version(struct hfi1_devdata *dd, u8 version); void read_guid(struct hfi1_devdata *dd); int wait_fm_ready(struct hfi1_devdata *dd, u32 mstimeout); void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason, @@ -744,6 +749,7 @@ int is_bx(struct hfi1_devdata *dd); u32 read_physical_state(struct hfi1_devdata *dd); u32 chip_to_opa_pstate(struct hfi1_devdata *dd, u32 chip_pstate); u32 get_logical_state(struct hfi1_pportdata *ppd); +void cache_physical_state(struct hfi1_pportdata *ppd); const char *opa_lstate_name(u32 lstate); const char *opa_pstate_name(u32 pstate); u32 driver_physical_state(struct hfi1_pportdata *ppd); @@ -1347,21 +1353,21 @@ enum { u64 get_all_cpu_total(u64 __percpu *cntr); void hfi1_start_cleanup(struct hfi1_devdata *dd); void hfi1_clear_tids(struct hfi1_ctxtdata *rcd); -struct ib_header *hfi1_get_msgheader( - struct hfi1_devdata *dd, __le32 *rhf_addr); void hfi1_init_ctxt(struct send_context *sc); void hfi1_put_tid(struct hfi1_devdata *dd, u32 index, u32 type, unsigned long pa, u16 order); void hfi1_quiet_serdes(struct hfi1_pportdata *ppd); -void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, int ctxt); +void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, + struct hfi1_ctxtdata *rcd); u32 hfi1_read_cntrs(struct hfi1_devdata *dd, char **namep, u64 **cntrp); u32 hfi1_read_portcntrs(struct hfi1_pportdata *ppd, char **namep, u64 **cntrp); -u8 hfi1_ibphys_portstate(struct hfi1_pportdata *ppd); int hfi1_get_ib_cfg(struct hfi1_pportdata *ppd, int which); int hfi1_set_ib_cfg(struct hfi1_pportdata *ppd, int which, u32 val); -int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt, u16 jkey); -int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt); -int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, unsigned ctxt, u16 pkey); +int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd, + u16 jkey); +int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt); +int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt, + u16 pkey); int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt); void hfi1_read_link_quality(struct hfi1_devdata *dd, u8 *link_quality); void hfi1_init_vnic_rsm(struct hfi1_devdata *dd); diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h index 995d62c7f9a7..ba9ab971ced9 100644 --- a/drivers/infiniband/hw/hfi1/common.h +++ b/drivers/infiniband/hw/hfi1/common.h @@ -325,6 +325,7 @@ struct diag_pkt { #define HFI1_LRH_BTH 0x0002 /* 1. word of IB LRH - next header: BTH */ /* misc. */ +#define SC15_PACKET 0xF #define SIZE_OF_CRC 1 #define LIM_MGMT_P_KEY 0x7FFF diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index a50870e455a3..0b7ca0e05320 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -96,7 +96,6 @@ MODULE_PARM_DESC(cap_mask, "Bit mask of enabled/disabled HW features"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("Intel Omni-Path Architecture driver"); -MODULE_VERSION(HFI1_DRIVER_VERSION); /* * MAX_PKT_RCV is the max # if packets processed per receive interrupt. @@ -196,7 +195,7 @@ int hfi1_count_active_units(void) spin_lock_irqsave(&hfi1_devs_lock, flags); list_for_each_entry(dd, &hfi1_dev_list, list) { - if (!(dd->flags & HFI1_PRESENT) || !dd->kregbase) + if (!(dd->flags & HFI1_PRESENT) || !dd->kregbase1) continue; for (pidx = 0; pidx < dd->num_pports; ++pidx) { ppd = dd->pport + pidx; @@ -224,6 +223,20 @@ static inline void *get_egrbuf(const struct hfi1_ctxtdata *rcd, u64 rhf, (offset * RCV_BUF_BLOCK_SIZE)); } +static inline void *hfi1_get_header(struct hfi1_devdata *dd, + __le32 *rhf_addr) +{ + u32 offset = rhf_hdrq_offset(rhf_to_cpu(rhf_addr)); + + return (void *)(rhf_addr - dd->rhf_offset + offset); +} + +static inline struct ib_header *hfi1_get_msgheader(struct hfi1_devdata *dd, + __le32 *rhf_addr) +{ + return (struct ib_header *)hfi1_get_header(dd, rhf_addr); +} + /* * Validate and encode the a given RcvArray Buffer size. * The function will check whether the given size falls within @@ -249,7 +262,8 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd, { struct ib_header *rhdr = packet->hdr; u32 rte = rhf_rcv_type_err(packet->rhf); - int lnh = ib_get_lnh(rhdr); + u8 lnh = ib_get_lnh(rhdr); + bool has_grh = false; struct hfi1_ibport *ibp = rcd_to_iport(rcd); struct hfi1_devdata *dd = ppd->dd; struct rvt_dev_info *rdi = &dd->verbs_dev.rdi; @@ -257,37 +271,42 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd, if (packet->rhf & (RHF_VCRC_ERR | RHF_ICRC_ERR)) return; + if (lnh == HFI1_LRH_BTH) { + packet->ohdr = &rhdr->u.oth; + } else if (lnh == HFI1_LRH_GRH) { + has_grh = true; + packet->ohdr = &rhdr->u.l.oth; + packet->grh = &rhdr->u.l.grh; + } else { + goto drop; + } + if (packet->rhf & RHF_TID_ERR) { /* For TIDERR and RC QPs preemptively schedule a NAK */ - struct ib_other_headers *ohdr = NULL; u32 tlen = rhf_pkt_len(packet->rhf); /* in bytes */ - u16 lid = ib_get_dlid(rhdr); + u32 dlid = ib_get_dlid(rhdr); u32 qp_num; - u32 rcv_flags = 0; + u32 mlid_base = be16_to_cpu(IB_MULTICAST_LID_BASE); /* Sanity check packet */ if (tlen < 24) goto drop; /* Check for GRH */ - if (lnh == HFI1_LRH_BTH) { - ohdr = &rhdr->u.oth; - } else if (lnh == HFI1_LRH_GRH) { + if (has_grh) { u32 vtf; + struct ib_grh *grh = packet->grh; - ohdr = &rhdr->u.l.oth; - if (rhdr->u.l.grh.next_hdr != IB_GRH_NEXT_HDR) + if (grh->next_hdr != IB_GRH_NEXT_HDR) goto drop; - vtf = be32_to_cpu(rhdr->u.l.grh.version_tclass_flow); + vtf = be32_to_cpu(grh->version_tclass_flow); if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION) goto drop; - rcv_flags |= HFI1_HAS_GRH; - } else { - goto drop; } + /* Get the destination QP number. */ - qp_num = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK; - if (lid < be16_to_cpu(IB_MULTICAST_LID_BASE)) { + qp_num = ib_bth_get_qpn(packet->ohdr); + if (dlid < mlid_base) { struct rvt_qp *qp; unsigned long flags; @@ -312,11 +331,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd, switch (qp->ibqp.qp_type) { case IB_QPT_RC: - hfi1_rc_hdrerr( - rcd, - rhdr, - rcv_flags, - qp); + hfi1_rc_hdrerr(rcd, packet, qp); break; default: /* For now don't handle any other QP types */ @@ -332,9 +347,8 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd, switch (rte) { case RHF_RTE_ERROR_OP_CODE_ERR: { - u32 opcode; void *ebuf = NULL; - __be32 *bth = NULL; + u8 opcode; if (rhf_use_egr_bfr(packet->rhf)) ebuf = packet->ebuf; @@ -342,16 +356,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd, if (!ebuf) goto drop; /* this should never happen */ - if (lnh == HFI1_LRH_BTH) - bth = (__be32 *)ebuf; - else if (lnh == HFI1_LRH_GRH) - bth = (__be32 *)((char *)ebuf + sizeof(struct ib_grh)); - else - goto drop; - - opcode = be32_to_cpu(bth[0]) >> 24; - opcode &= 0xff; - + opcode = ib_bth_get_opcode(packet->ohdr); if (opcode == IB_OPCODE_CNP) { /* * Only in pre-B0 h/w is the CNP_OPCODE handled @@ -365,7 +370,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd, sc5 = hfi1_9B_get_sc5(rhdr, packet->rhf); sl = ibp->sc_to_sl[sc5]; - lqpn = be32_to_cpu(bth[1]) & RVT_QPN_MASK; + lqpn = ib_bth_get_qpn(packet->ohdr); rcu_read_lock(); qp = rvt_lookup_qpn(rdi, &ibp->rvp, lqpn); if (!qp) { @@ -415,7 +420,6 @@ static inline void init_packet(struct hfi1_ctxtdata *rcd, packet->rhf = rhf_to_cpu(packet->rhf_addr); packet->rhqoff = rcd->head; packet->numpkt = 0; - packet->rcv_flags = 0; } void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt, @@ -424,21 +428,18 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt, struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num); struct ib_header *hdr = pkt->hdr; struct ib_other_headers *ohdr = pkt->ohdr; - struct ib_grh *grh = NULL; + struct ib_grh *grh = pkt->grh; u32 rqpn = 0, bth1; u16 rlid, dlid = ib_get_dlid(hdr); u8 sc, svc_type; bool is_mcast = false; - if (pkt->rcv_flags & HFI1_HAS_GRH) - grh = &hdr->u.l.grh; - switch (qp->ibqp.qp_type) { case IB_QPT_SMI: case IB_QPT_GSI: case IB_QPT_UD: rlid = ib_get_slid(hdr); - rqpn = be32_to_cpu(ohdr->u.ud.deth[1]) & RVT_QPN_MASK; + rqpn = ib_get_sqpn(ohdr); svc_type = IB_CC_SVCTYPE_UD; is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) && (dlid != be16_to_cpu(IB_LID_PERMISSIVE)); @@ -461,7 +462,7 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt, bth1 = be32_to_cpu(ohdr->bth[1]); if (do_cnp && (bth1 & IB_FECN_SMASK)) { - u16 pkey = (u16)be32_to_cpu(ohdr->bth[0]); + u16 pkey = ib_bth_get_pkey(ohdr); return_cnp(ibp, qp, rqpn, pkey, dlid, rlid, sc, grh); } @@ -591,9 +592,10 @@ static void __prescan_rxq(struct hfi1_packet *packet) if (lnh == HFI1_LRH_BTH) { packet->ohdr = &hdr->u.oth; + packet->grh = NULL; } else if (lnh == HFI1_LRH_GRH) { packet->ohdr = &hdr->u.l.oth; - packet->rcv_flags |= HFI1_HAS_GRH; + packet->grh = &hdr->u.l.grh; } else { goto next; /* just in case */ } @@ -698,10 +700,8 @@ static inline int process_rcv_packet(struct hfi1_packet *packet, int thread) { int ret; - packet->hdr = hfi1_get_msgheader(packet->rcd->dd, - packet->rhf_addr); - packet->hlen = (u8 *)packet->rhf_addr - (u8 *)packet->hdr; packet->etype = rhf_rcv_type(packet->rhf); + /* total length */ packet->tlen = rhf_pkt_len(packet->rhf); /* in bytes */ /* retrieve eager buffer details */ @@ -759,7 +759,7 @@ static inline void process_rcv_update(int last, struct hfi1_packet *packet) packet->etail, 0, 0); packet->updegr = 0; } - packet->rcv_flags = 0; + packet->grh = NULL; } static inline void finish_packet(struct hfi1_packet *packet) @@ -837,9 +837,9 @@ bail: return last; } -static inline void set_nodma_rtail(struct hfi1_devdata *dd, u8 ctxt) +static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt) { - int i; + u16 i; /* * For dynamically allocated kernel contexts (like vnic) switch @@ -857,9 +857,9 @@ static inline void set_nodma_rtail(struct hfi1_devdata *dd, u8 ctxt) &handle_receive_interrupt_nodma_rtail; } -static inline void set_dma_rtail(struct hfi1_devdata *dd, u8 ctxt) +static inline void set_dma_rtail(struct hfi1_devdata *dd, u16 ctxt) { - int i; + u16 i; /* * For dynamically allocated kernel contexts (like vnic) switch @@ -879,7 +879,7 @@ static inline void set_dma_rtail(struct hfi1_devdata *dd, u8 ctxt) void set_all_slowpath(struct hfi1_devdata *dd) { - int i; + u16 i; /* HFI1_CTRL_CTXT must always use the slow path interrupt handler */ for (i = HFI1_CTRL_CTXT + 1; i < dd->num_rcv_contexts; i++) { @@ -896,20 +896,25 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd, struct hfi1_devdata *dd) { struct work_struct *lsaw = &rcd->ppd->linkstate_active_work; - struct ib_header *hdr = hfi1_get_msgheader(packet->rcd->dd, - packet->rhf_addr); u8 etype = rhf_rcv_type(packet->rhf); + u8 sc = SC15_PACKET; - if (etype == RHF_RCV_TYPE_IB && - hfi1_9B_get_sc5(hdr, packet->rhf) != 0xf) { - int hwstate = read_logical_state(dd); + if (etype == RHF_RCV_TYPE_IB) { + struct ib_header *hdr = hfi1_get_msgheader(packet->rcd->dd, + packet->rhf_addr); + sc = hfi1_9B_get_sc5(hdr, packet->rhf); + } + if (sc != SC15_PACKET) { + int hwstate = driver_lstate(rcd->ppd); - if (hwstate != LSTATE_ACTIVE) { - dd_dev_info(dd, "Unexpected link state %d\n", hwstate); + if (hwstate != IB_PORT_ACTIVE) { + dd_dev_info(dd, + "Unexpected link state %s\n", + opa_lstate_name(hwstate)); return 0; } - queue_work(rcd->ppd->hfi1_wq, lsaw); + queue_work(rcd->ppd->link_wq, lsaw); return 1; } return 0; @@ -1063,7 +1068,7 @@ void receive_interrupt_work(struct work_struct *work) struct hfi1_pportdata *ppd = container_of(work, struct hfi1_pportdata, linkstate_active_work); struct hfi1_devdata *dd = ppd->dd; - int i; + u16 i; /* Received non-SC15 packet implies neighbor_normal */ ppd->neighbor_normal = 1; @@ -1264,7 +1269,8 @@ void hfi1_start_led_override(struct hfi1_pportdata *ppd, unsigned int timeon, */ int hfi1_reset_device(int unit) { - int ret, i; + int ret; + u16 i; struct hfi1_devdata *dd = hfi1_lookup(unit); struct hfi1_pportdata *ppd; unsigned long flags; @@ -1277,7 +1283,7 @@ int hfi1_reset_device(int unit) dd_dev_info(dd, "Reset on unit %u requested\n", unit); - if (!dd->kregbase || !(dd->flags & HFI1_PRESENT)) { + if (!dd->kregbase1 || !(dd->flags & HFI1_PRESENT)) { dd_dev_info(dd, "Invalid unit number %u or not initialized or not present\n", unit); @@ -1321,6 +1327,58 @@ bail: return ret; } +static inline void hfi1_setup_ib_header(struct hfi1_packet *packet) +{ + packet->hdr = (struct hfi1_ib_message_header *) + hfi1_get_msgheader(packet->rcd->dd, + packet->rhf_addr); + packet->hlen = (u8 *)packet->rhf_addr - (u8 *)packet->hdr; +} + +static int hfi1_setup_9B_packet(struct hfi1_packet *packet) +{ + struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd); + struct ib_header *hdr; + u8 lnh; + + hfi1_setup_ib_header(packet); + hdr = packet->hdr; + + lnh = ib_get_lnh(hdr); + if (lnh == HFI1_LRH_BTH) { + packet->ohdr = &hdr->u.oth; + packet->grh = NULL; + } else if (lnh == HFI1_LRH_GRH) { + u32 vtf; + + packet->ohdr = &hdr->u.l.oth; + packet->grh = &hdr->u.l.grh; + if (packet->grh->next_hdr != IB_GRH_NEXT_HDR) + goto drop; + vtf = be32_to_cpu(packet->grh->version_tclass_flow); + if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION) + goto drop; + } else { + goto drop; + } + + /* Query commonly used fields from packet header */ + packet->opcode = ib_bth_get_opcode(packet->ohdr); + packet->slid = ib_get_slid(hdr); + packet->dlid = ib_get_dlid(hdr); + packet->sl = ib_get_sl(hdr); + packet->sc = hfi1_9B_get_sc5(hdr, packet->rhf); + packet->pad = ib_bth_get_pad(packet->ohdr); + packet->extra_byte = 0; + packet->fecn = ib_bth_get_fecn(packet->ohdr); + packet->becn = ib_bth_get_becn(packet->ohdr); + + return 0; +drop: + ibp->rvp.n_pkt_drops++; + return -EINVAL; +} + void handle_eflags(struct hfi1_packet *packet) { struct hfi1_ctxtdata *rcd = packet->rcd; @@ -1351,6 +1409,9 @@ int process_receive_ib(struct hfi1_packet *packet) if (unlikely(hfi1_dbg_fault_packet(packet))) return RHF_RCV_CONTINUE; + if (hfi1_setup_9B_packet(packet)) + return RHF_RCV_CONTINUE; + trace_hfi1_rcvhdr(packet->rcd->ppd->dd, packet->rcd->ctxt, rhf_err_flags(packet->rhf), @@ -1422,6 +1483,7 @@ int process_receive_error(struct hfi1_packet *packet) rhf_rcv_type_err(packet->rhf) == 3)) return RHF_RCV_CONTINUE; + hfi1_setup_ib_header(packet); handle_eflags(packet); if (unlikely(rhf_err_flags(packet->rhf))) @@ -1435,6 +1497,8 @@ int kdeth_process_expected(struct hfi1_packet *packet) { if (unlikely(hfi1_dbg_fault_packet(packet))) return RHF_RCV_CONTINUE; + + hfi1_setup_ib_header(packet); if (unlikely(rhf_err_flags(packet->rhf))) handle_eflags(packet); @@ -1445,6 +1509,7 @@ int kdeth_process_expected(struct hfi1_packet *packet) int kdeth_process_eager(struct hfi1_packet *packet) { + hfi1_setup_ib_header(packet); if (unlikely(rhf_err_flags(packet->rhf))) handle_eflags(packet); if (unlikely(hfi1_dbg_fault_packet(packet))) diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c index 26da124c88e2..d46b17107901 100644 --- a/drivers/infiniband/hw/hfi1/eprom.c +++ b/drivers/infiniband/hw/hfi1/eprom.c @@ -250,7 +250,6 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, { void *buffer; void *p; - u32 length; int ret; buffer = kmalloc(P1_SIZE, GFP_KERNEL); @@ -265,13 +264,13 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, /* scan for image magic that may trail the actual data */ p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); - if (p) - length = p - buffer; - else - length = P1_SIZE; + if (!p) { + kfree(buffer); + return -ENOENT; + } *data = buffer; - *size = length; + *size = p - buffer; return 0; } diff --git a/drivers/infiniband/hw/hfi1/exp_rcv.c b/drivers/infiniband/hw/hfi1/exp_rcv.c new file mode 100644 index 000000000000..0af91675acc6 --- /dev/null +++ b/drivers/infiniband/hw/hfi1/exp_rcv.c @@ -0,0 +1,114 @@ +/* + * Copyright(c) 2017 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#include "exp_rcv.h" +#include "trace.h" + +/** + * exp_tid_group_init - initialize exp_tid_set + * @set - the set + */ +void hfi1_exp_tid_group_init(struct exp_tid_set *set) +{ + INIT_LIST_HEAD(&set->list); + set->count = 0; +} + +/** + * alloc_ctxt_rcv_groups - initialize expected receive groups + * @rcd - the context to add the groupings to + */ +int hfi1_alloc_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd) +{ + struct hfi1_devdata *dd = rcd->dd; + u32 tidbase; + struct tid_group *grp; + int i; + + tidbase = rcd->expected_base; + for (i = 0; i < rcd->expected_count / + dd->rcv_entries.group_size; i++) { + grp = kzalloc(sizeof(*grp), GFP_KERNEL); + if (!grp) + goto bail; + grp->size = dd->rcv_entries.group_size; + grp->base = tidbase; + tid_group_add_tail(grp, &rcd->tid_group_list); + tidbase += dd->rcv_entries.group_size; + } + + return 0; +bail: + hfi1_free_ctxt_rcv_groups(rcd); + return -ENOMEM; +} + +/** + * free_ctxt_rcv_groups - free expected receive groups + * @rcd - the context to free + * + * The routine dismantles the expect receive linked + * list and clears any tids associated with the receive + * context. + * + * This should only be called for kernel contexts and the + * a base user context. + */ +void hfi1_free_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd) +{ + struct tid_group *grp, *gptr; + + WARN_ON(!EXP_TID_SET_EMPTY(rcd->tid_full_list)); + WARN_ON(!EXP_TID_SET_EMPTY(rcd->tid_used_list)); + + list_for_each_entry_safe(grp, gptr, &rcd->tid_group_list.list, list) { + tid_group_remove(grp, &rcd->tid_group_list); + kfree(grp); + } + + hfi1_clear_tids(rcd); +} diff --git a/drivers/infiniband/hw/hfi1/exp_rcv.h b/drivers/infiniband/hw/hfi1/exp_rcv.h new file mode 100644 index 000000000000..08719047628a --- /dev/null +++ b/drivers/infiniband/hw/hfi1/exp_rcv.h @@ -0,0 +1,190 @@ +#ifndef _HFI1_EXP_RCV_H +#define _HFI1_EXP_RCV_H +/* + * Copyright(c) 2017 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#include "hfi.h" + +#define EXP_TID_SET_EMPTY(set) (set.count == 0 && list_empty(&set.list)) + +#define EXP_TID_TIDLEN_MASK 0x7FFULL +#define EXP_TID_TIDLEN_SHIFT 0 +#define EXP_TID_TIDCTRL_MASK 0x3ULL +#define EXP_TID_TIDCTRL_SHIFT 20 +#define EXP_TID_TIDIDX_MASK 0x3FFULL +#define EXP_TID_TIDIDX_SHIFT 22 +#define EXP_TID_GET(tid, field) \ + (((tid) >> EXP_TID_TID##field##_SHIFT) & EXP_TID_TID##field##_MASK) + +#define EXP_TID_SET(field, value) \ + (((value) & EXP_TID_TID##field##_MASK) << \ + EXP_TID_TID##field##_SHIFT) +#define EXP_TID_CLEAR(tid, field) ({ \ + (tid) &= ~(EXP_TID_TID##field##_MASK << \ + EXP_TID_TID##field##_SHIFT); \ + }) +#define EXP_TID_RESET(tid, field, value) do { \ + EXP_TID_CLEAR(tid, field); \ + (tid) |= EXP_TID_SET(field, (value)); \ + } while (0) + +/* + * Define fields in the KDETH header so we can update the header + * template. + */ +#define KDETH_OFFSET_SHIFT 0 +#define KDETH_OFFSET_MASK 0x7fff +#define KDETH_OM_SHIFT 15 +#define KDETH_OM_MASK 0x1 +#define KDETH_TID_SHIFT 16 +#define KDETH_TID_MASK 0x3ff +#define KDETH_TIDCTRL_SHIFT 26 +#define KDETH_TIDCTRL_MASK 0x3 +#define KDETH_INTR_SHIFT 28 +#define KDETH_INTR_MASK 0x1 +#define KDETH_SH_SHIFT 29 +#define KDETH_SH_MASK 0x1 +#define KDETH_KVER_SHIFT 30 +#define KDETH_KVER_MASK 0x3 +#define KDETH_JKEY_SHIFT 0x0 +#define KDETH_JKEY_MASK 0xff +#define KDETH_HCRC_UPPER_SHIFT 16 +#define KDETH_HCRC_UPPER_MASK 0xff +#define KDETH_HCRC_LOWER_SHIFT 24 +#define KDETH_HCRC_LOWER_MASK 0xff + +#define KDETH_GET(val, field) \ + (((le32_to_cpu((val))) >> KDETH_##field##_SHIFT) & KDETH_##field##_MASK) +#define KDETH_SET(dw, field, val) do { \ + u32 dwval = le32_to_cpu(dw); \ + dwval &= ~(KDETH_##field##_MASK << KDETH_##field##_SHIFT); \ + dwval |= (((val) & KDETH_##field##_MASK) << \ + KDETH_##field##_SHIFT); \ + dw = cpu_to_le32(dwval); \ + } while (0) + +#define KDETH_RESET(dw, field, val) ({ dw = 0; KDETH_SET(dw, field, val); }) + +/* KDETH OM multipliers and switch over point */ +#define KDETH_OM_SMALL 4 +#define KDETH_OM_SMALL_SHIFT 2 +#define KDETH_OM_LARGE 64 +#define KDETH_OM_LARGE_SHIFT 6 +#define KDETH_OM_MAX_SIZE (1 << ((KDETH_OM_LARGE / KDETH_OM_SMALL) + 1)) + +struct tid_group { + struct list_head list; + u32 base; + u8 size; + u8 used; + u8 map; +}; + +/* + * Write an "empty" RcvArray entry. + * This function exists so the TID registaration code can use it + * to write to unused/unneeded entries and still take advantage + * of the WC performance improvements. The HFI will ignore this + * write to the RcvArray entry. + */ +static inline void rcv_array_wc_fill(struct hfi1_devdata *dd, u32 index) +{ + /* + * Doing the WC fill writes only makes sense if the device is + * present and the RcvArray has been mapped as WC memory. + */ + if ((dd->flags & HFI1_PRESENT) && dd->rcvarray_wc) { + writeq(0, dd->rcvarray_wc + (index * 8)); + if ((index & 3) == 3) + flush_wc(); + } +} + +static inline void tid_group_add_tail(struct tid_group *grp, + struct exp_tid_set *set) +{ + list_add_tail(&grp->list, &set->list); + set->count++; +} + +static inline void tid_group_remove(struct tid_group *grp, + struct exp_tid_set *set) +{ + list_del_init(&grp->list); + set->count--; +} + +static inline void tid_group_move(struct tid_group *group, + struct exp_tid_set *s1, + struct exp_tid_set *s2) +{ + tid_group_remove(group, s1); + tid_group_add_tail(group, s2); +} + +static inline struct tid_group *tid_group_pop(struct exp_tid_set *set) +{ + struct tid_group *grp = + list_first_entry(&set->list, struct tid_group, list); + list_del_init(&grp->list); + set->count--; + return grp; +} + +static inline u32 rcventry2tidinfo(u32 rcventry) +{ + u32 pair = rcventry & ~0x1; + + return EXP_TID_SET(IDX, pair >> 1) | + EXP_TID_SET(CTRL, 1 << (rcventry - pair)); +} + +int hfi1_alloc_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd); +void hfi1_free_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd); +void hfi1_exp_tid_group_init(struct exp_tid_set *set); + +#endif /* _HFI1_EXP_RCV_H */ diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 3158128d57e8..a0c13fa5babb 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -81,19 +81,23 @@ static u64 kvirt_to_phys(void *addr); static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo); static int init_subctxts(struct hfi1_ctxtdata *uctxt, const struct hfi1_user_info *uinfo); -static int init_user_ctxt(struct hfi1_filedata *fd); +static int init_user_ctxt(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt); static void user_init(struct hfi1_ctxtdata *uctxt); static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase, __u32 len); static int get_base_info(struct hfi1_filedata *fd, void __user *ubase, __u32 len); -static int setup_base_ctxt(struct hfi1_filedata *fd); +static int setup_base_ctxt(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt); static int setup_subctxt(struct hfi1_ctxtdata *uctxt); static int find_sub_ctxt(struct hfi1_filedata *fd, const struct hfi1_user_info *uinfo); static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd, - struct hfi1_user_info *uinfo); + struct hfi1_user_info *uinfo, + struct hfi1_ctxtdata **cd); +static void deallocate_ctxt(struct hfi1_ctxtdata *uctxt); static unsigned int poll_urgent(struct file *fp, struct poll_table_struct *pt); static unsigned int poll_next(struct file *fp, struct poll_table_struct *pt); static int user_event_ack(struct hfi1_ctxtdata *uctxt, u16 subctxt, @@ -181,7 +185,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) struct hfi1_devdata, user_cdev); - if (!((dd->flags & HFI1_PRESENT) && dd->kregbase)) + if (!((dd->flags & HFI1_PRESENT) && dd->kregbase1)) return -EINVAL; if (!atomic_inc_not_zero(&dd->user_refcount)) @@ -267,12 +271,14 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, /* * Copy the number of tidlist entries we used * and the length of the buffer we registered. - * These fields are adjacent in the structure so - * we can copy them at the same time. */ addr = arg + offsetof(struct hfi1_tid_info, tidcnt); if (copy_to_user((void __user *)addr, &tinfo.tidcnt, - sizeof(tinfo.tidcnt) + + sizeof(tinfo.tidcnt))) + return -EFAULT; + + addr = arg + offsetof(struct hfi1_tid_info, length); + if (copy_to_user((void __user *)addr, &tinfo.length, sizeof(tinfo.length))) ret = -EFAULT; } @@ -388,8 +394,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, sc_disable(sc); ret = sc_enable(sc); - hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB, - uctxt->ctxt); + hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB, uctxt); } else { ret = sc_restart(sc); } @@ -757,7 +762,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) flush_wc(); /* drain user sdma queue */ - hfi1_user_sdma_free_queues(fdata); + hfi1_user_sdma_free_queues(fdata, uctxt); /* release the cpu */ hfi1_put_proc_affinity(fdata->rec_cpu_num); @@ -774,6 +779,8 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) *ev = 0; __clear_bit(fdata->subctxt, uctxt->in_use_ctxts); + fdata->uctxt = NULL; + hfi1_rcd_put(uctxt); /* fdata reference */ if (!bitmap_empty(uctxt->in_use_ctxts, HFI1_MAX_SHARED_CTXTS)) { mutex_unlock(&hfi1_mutex); goto done; @@ -790,34 +797,26 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) HFI1_RCVCTRL_TAILUPD_DIS | HFI1_RCVCTRL_ONE_PKT_EGR_DIS | HFI1_RCVCTRL_NO_RHQ_DROP_DIS | - HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt->ctxt); + HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt); /* Clear the context's J_KEY */ - hfi1_clear_ctxt_jkey(dd, uctxt->ctxt); + hfi1_clear_ctxt_jkey(dd, uctxt); /* - * Reset context integrity checks to default. - * (writes to CSRs probably belong in chip.c) + * If a send context is allocated, reset context integrity + * checks to default and disable the send context. */ - write_kctxt_csr(dd, uctxt->sc->hw_context, SEND_CTXT_CHECK_ENABLE, - hfi1_pkt_default_send_ctxt_mask(dd, uctxt->sc->type)); - sc_disable(uctxt->sc); + if (uctxt->sc) { + set_pio_integrity(uctxt->sc); + sc_disable(uctxt->sc); + } spin_unlock_irqrestore(&dd->uctxt_lock, flags); - dd->rcd[uctxt->ctxt] = NULL; - - hfi1_user_exp_rcv_grp_free(uctxt); + hfi1_free_ctxt_rcv_groups(uctxt); hfi1_clear_ctxt_pkey(dd, uctxt); - uctxt->rcvwait_to = 0; - uctxt->piowait_to = 0; - uctxt->rcvnowait = 0; - uctxt->pionowait = 0; uctxt->event_flags = 0; - - hfi1_stats.sps_ctxts--; - if (++dd->freectxts == dd->num_user_contexts) - aspm_enable_all(dd); mutex_unlock(&hfi1_mutex); - hfi1_free_ctxtdata(dd, uctxt); + + deallocate_ctxt(uctxt); done: mmdrop(fdata->mm); kobject_put(&dd->kobj); @@ -849,6 +848,7 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) { int ret; unsigned int swmajor, swminor; + struct hfi1_ctxtdata *uctxt = NULL; swmajor = uinfo->userversion >> 16; if (swmajor != HFI1_USER_SWMAJOR) @@ -874,7 +874,7 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) * couldn't find a sub context. */ if (!ret) - ret = allocate_ctxt(fd, fd->dd, uinfo); + ret = allocate_ctxt(fd, fd->dd, uinfo, &uctxt); mutex_unlock(&hfi1_mutex); @@ -887,31 +887,38 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) ret = wait_event_interruptible(fd->uctxt->wait, !test_bit( HFI1_CTXT_BASE_UNINIT, &fd->uctxt->event_flags)); - if (test_bit(HFI1_CTXT_BASE_FAILED, &fd->uctxt->event_flags)) { - clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts); - return -ENOMEM; - } + if (test_bit(HFI1_CTXT_BASE_FAILED, &fd->uctxt->event_flags)) + ret = -ENOMEM; + /* The only thing a sub context needs is the user_xxx stuff */ if (!ret) - ret = init_user_ctxt(fd); + ret = init_user_ctxt(fd, fd->uctxt); if (ret) clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts); + } else if (!ret) { - ret = setup_base_ctxt(fd); - if (fd->uctxt->subctxt_cnt) { + ret = setup_base_ctxt(fd, uctxt); + if (uctxt->subctxt_cnt) { /* If there is an error, set the failed bit. */ if (ret) set_bit(HFI1_CTXT_BASE_FAILED, - &fd->uctxt->event_flags); + &uctxt->event_flags); /* * Base context is done, notify anybody using a * sub-context that is waiting for this completion */ - clear_bit(HFI1_CTXT_BASE_UNINIT, - &fd->uctxt->event_flags); - wake_up(&fd->uctxt->wait); + clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); + wake_up(&uctxt->wait); } + if (ret) + deallocate_ctxt(uctxt); + } + + /* If an error occurred, clear the reference */ + if (ret && fd->uctxt) { + hfi1_rcd_put(fd->uctxt); + fd->uctxt = NULL; } return ret; @@ -924,7 +931,7 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) static int find_sub_ctxt(struct hfi1_filedata *fd, const struct hfi1_user_info *uinfo) { - int i; + u16 i; struct hfi1_devdata *dd = fd->dd; u16 subctxt; @@ -961,6 +968,8 @@ static int find_sub_ctxt(struct hfi1_filedata *fd, fd->uctxt = uctxt; fd->subctxt = subctxt; + + hfi1_rcd_get(uctxt); __set_bit(fd->subctxt, uctxt->in_use_ctxts); return 1; @@ -970,10 +979,11 @@ static int find_sub_ctxt(struct hfi1_filedata *fd, } static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd, - struct hfi1_user_info *uinfo) + struct hfi1_user_info *uinfo, + struct hfi1_ctxtdata **cd) { struct hfi1_ctxtdata *uctxt; - unsigned int ctxt; + u16 ctxt; int ret, numa; if (dd->flags & HFI1_FROZEN) { @@ -1058,8 +1068,6 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd, strlcpy(uctxt->comm, current->comm, sizeof(uctxt->comm)); memcpy(uctxt->uuid, uinfo->uuid, sizeof(uctxt->uuid)); uctxt->jkey = generate_jkey(current_uid()); - INIT_LIST_HEAD(&uctxt->sdma_queues); - spin_lock_init(&uctxt->sdma_qlock); hfi1_stats.sps_ctxts++; /* * Disable ASPM when there are open user/PSM contexts to avoid @@ -1067,16 +1075,31 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd, */ if (dd->freectxts-- == dd->num_user_contexts) aspm_disable_all(dd); - fd->uctxt = uctxt; + + *cd = uctxt; return 0; ctxdata_free: + *cd = NULL; dd->rcd[ctxt] = NULL; - hfi1_free_ctxtdata(dd, uctxt); + hfi1_rcd_put(uctxt); return ret; } +static void deallocate_ctxt(struct hfi1_ctxtdata *uctxt) +{ + mutex_lock(&hfi1_mutex); + hfi1_stats.sps_ctxts--; + if (++uctxt->dd->freectxts == uctxt->dd->num_user_contexts) + aspm_enable_all(uctxt->dd); + + /* _rcd_put() should be done after releasing mutex */ + uctxt->dd->rcd[uctxt->ctxt] = NULL; + mutex_unlock(&hfi1_mutex); + hfi1_rcd_put(uctxt); /* dd reference */ +} + static int init_subctxts(struct hfi1_ctxtdata *uctxt, const struct hfi1_user_info *uinfo) { @@ -1153,7 +1176,7 @@ static void user_init(struct hfi1_ctxtdata *uctxt) clear_rcvhdrtail(uctxt); /* Setup J_KEY before enabling the context */ - hfi1_set_ctxt_jkey(uctxt->dd, uctxt->ctxt, uctxt->jkey); + hfi1_set_ctxt_jkey(uctxt->dd, uctxt, uctxt->jkey); rcvctrl_ops = HFI1_RCVCTRL_CTXT_ENB; if (HFI1_CAP_UGET_MASK(uctxt->flags, HDRSUPP)) @@ -1179,7 +1202,7 @@ static void user_init(struct hfi1_ctxtdata *uctxt) rcvctrl_ops |= HFI1_RCVCTRL_TAILUPD_ENB; else rcvctrl_ops |= HFI1_RCVCTRL_TAILUPD_DIS; - hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt->ctxt); + hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt); } static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase, @@ -1223,23 +1246,25 @@ static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase, return ret; } -static int init_user_ctxt(struct hfi1_filedata *fd) +static int init_user_ctxt(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt) { - struct hfi1_ctxtdata *uctxt = fd->uctxt; int ret; ret = hfi1_user_sdma_alloc_queues(uctxt, fd); if (ret) return ret; - ret = hfi1_user_exp_rcv_init(fd); + ret = hfi1_user_exp_rcv_init(fd, uctxt); + if (ret) + hfi1_user_sdma_free_queues(fd, uctxt); return ret; } -static int setup_base_ctxt(struct hfi1_filedata *fd) +static int setup_base_ctxt(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt) { - struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; int ret = 0; @@ -1260,19 +1285,24 @@ static int setup_base_ctxt(struct hfi1_filedata *fd) if (ret) goto setup_failed; - ret = hfi1_user_exp_rcv_grp_init(fd); + ret = hfi1_alloc_ctxt_rcv_groups(uctxt); if (ret) goto setup_failed; - ret = init_user_ctxt(fd); + ret = init_user_ctxt(fd, uctxt); if (ret) goto setup_failed; user_init(uctxt); + /* Now that the context is set up, the fd can get a reference. */ + fd->uctxt = uctxt; + hfi1_rcd_get(uctxt); + return 0; setup_failed: + /* Call _free_ctxtdata, not _rcd_put(). We still need the context. */ hfi1_free_ctxtdata(dd, uctxt); return ret; } @@ -1390,7 +1420,7 @@ static unsigned int poll_next(struct file *fp, spin_lock_irq(&dd->uctxt_lock); if (hdrqempty(uctxt)) { set_bit(HFI1_CTXT_WAITING_RCV, &uctxt->event_flags); - hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_ENB, uctxt->ctxt); + hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_ENB, uctxt); pollflag = 0; } else { pollflag = POLLIN | POLLRDNORM; @@ -1409,7 +1439,7 @@ int hfi1_set_uevent_bits(struct hfi1_pportdata *ppd, const int evtbit) { struct hfi1_ctxtdata *uctxt; struct hfi1_devdata *dd = ppd->dd; - unsigned ctxt; + u16 ctxt; int ret = 0; unsigned long flags; @@ -1475,7 +1505,7 @@ static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt, } else { rcvctrl_op = HFI1_RCVCTRL_CTXT_DIS; } - hfi1_rcvctrl(dd, rcvctrl_op, uctxt->ctxt); + hfi1_rcvctrl(dd, rcvctrl_op, uctxt); /* always; new head should be equal to new tail; see above */ bail: return 0; @@ -1525,7 +1555,7 @@ static int set_ctxt_pkey(struct hfi1_ctxtdata *uctxt, u16 subctxt, u16 pkey) } if (intable) - ret = hfi1_set_ctxt_pkey(dd, uctxt->ctxt, pkey); + ret = hfi1_set_ctxt_pkey(dd, uctxt, pkey); done: return ret; } diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c index 4042c11b2742..885714b93557 100644 --- a/drivers/infiniband/hw/hfi1/firmware.c +++ b/drivers/infiniband/hw/hfi1/firmware.c @@ -69,6 +69,7 @@ #define ALT_FW_FABRIC_NAME "hfi1_fabric_d.fw" #define ALT_FW_SBUS_NAME "hfi1_sbus_d.fw" #define ALT_FW_PCIE_NAME "hfi1_pcie_d.fw" +#define HOST_INTERFACE_VERSION 1 static uint fw_8051_load = 1; static uint fw_fabric_serdes_load = 1; @@ -615,6 +616,14 @@ retry: fw_fabric_serdes_name = ALT_FW_FABRIC_NAME; fw_sbus_name = ALT_FW_SBUS_NAME; fw_pcie_serdes_name = ALT_FW_PCIE_NAME; + + /* + * Add a delay before obtaining and loading debug firmware. + * Authorization will fail if the delay between firmware + * authorization events is shorter than 50us. Add 100us to + * make a delay time safe. + */ + usleep_range(100, 120); } if (fw_sbus_load) { @@ -1079,6 +1088,13 @@ static int load_8051_firmware(struct hfi1_devdata *dd, dd_dev_info(dd, "8051 firmware version %d.%d.%d\n", (int)ver_major, (int)ver_minor, (int)ver_patch); dd->dc8051_ver = dc8051_ver(ver_major, ver_minor, ver_patch); + ret = write_host_interface_version(dd, HOST_INTERFACE_VERSION); + if (ret != HCMD_SUCCESS) { + dd_dev_err(dd, + "Failed to set host interface version, return 0x%x\n", + ret); + return -EIO; + } return 0; } diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 414a04a481c2..fb5f8394fbed 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -213,13 +213,11 @@ struct hfi1_ctxtdata { /* dynamic receive available interrupt timeout */ u32 rcvavail_timeout; - /* - * number of opens (including slave sub-contexts) on this instance - * (ignoring forks, dup, etc. for now) - */ - int cnt; + /* Reference count the base context usage */ + struct kref kref; + /* Device context index */ - unsigned ctxt; + u16 ctxt; /* * non-zero if ctxt can be shared, and defines the maximum number of * sub-contexts for this device context. @@ -245,24 +243,10 @@ struct hfi1_ctxtdata { /* lock protecting all Expected TID data */ struct mutex exp_lock; - /* number of pio bufs for this ctxt (all procs, if shared) */ - u32 piocnt; - /* first pio buffer for this ctxt */ - u32 pio_base; - /* chip offset of PIO buffers for this ctxt */ - u32 piobufs; /* per-context configuration flags */ unsigned long flags; /* per-context event flags for fileops/intr communication */ unsigned long event_flags; - /* WAIT_RCV that timed out, no interrupt */ - u32 rcvwait_to; - /* WAIT_PIO that timed out, no interrupt */ - u32 piowait_to; - /* WAIT_RCV already happened, no wait */ - u32 rcvnowait; - /* WAIT_PIO already happened, no wait */ - u32 pionowait; /* total number of polled urgent packets */ u32 urgent; /* saved total number of polled urgent packets for poll edge trigger */ @@ -292,7 +276,6 @@ struct hfi1_ctxtdata { u8 redirect_seq_cnt; /* ctxt rcvhdrq head offset */ u32 head; - u32 pkt_count; /* QPs waiting for context processing */ struct list_head qp_wait_list; /* interrupt handling */ @@ -301,15 +284,6 @@ struct hfi1_ctxtdata { unsigned numa_id; /* numa node of this context */ /* verbs stats per CTX */ struct hfi1_opcode_stats_perctx *opstats; - /* - * This is the kernel thread that will keep making - * progress on the user sdma requests behind the scenes. - * There is one per context (shared contexts use the master's). - */ - struct task_struct *progress; - struct list_head sdma_queues; - /* protect sdma queues */ - spinlock_t sdma_qlock; /* Is ASPM interrupt supported for this context */ bool aspm_intr_supported; @@ -356,17 +330,26 @@ struct hfi1_packet { __le32 *rhf_addr; struct rvt_qp *qp; struct ib_other_headers *ohdr; + struct ib_grh *grh; u64 rhf; u32 maxcnt; u32 rhqoff; + u32 dlid; + u32 slid; u16 tlen; s16 etail; u8 hlen; u8 numpkt; u8 rsize; u8 updegr; - u8 rcv_flags; u8 etype; + u8 extra_byte; + u8 pad; + u8 sc; + u8 sl; + u8 opcode; + bool becn; + bool fecn; }; struct rvt_sge_state; @@ -512,7 +495,7 @@ static inline void incr_cntr32(u32 *cntr) #define MAX_NAME_SIZE 64 struct hfi1_msix_entry { enum irq_type type; - struct msix_entry msix; + int irq; void *arg; char name[MAX_NAME_SIZE]; cpumask_t mask; @@ -593,6 +576,7 @@ struct hfi1_pportdata { /* SendDMA related entries */ struct workqueue_struct *hfi1_wq; + struct workqueue_struct *link_wq; /* move out of interrupt context */ struct work_struct link_vc_work; @@ -654,12 +638,13 @@ struct hfi1_pportdata { u8 link_enabled; /* link enabled? */ u8 linkinit_reason; u8 local_tx_rate; /* rate given to 8051 firmware */ - u8 last_pstate; /* info only */ + u8 pstate; /* info only */ u8 qsfp_retry_count; /* placeholders for IB MAD packet settings */ u8 overrun_threshold; u8 phy_error_threshold; + unsigned int is_link_down_queued; /* Used to override LED behavior for things like maintenance beaconing*/ /* @@ -860,12 +845,15 @@ struct hfi1_devdata { struct device *diag_device; struct device *ui_device; - /* mem-mapped pointer to base of chip regs */ - u8 __iomem *kregbase; - /* end of mem-mapped chip space excluding sendbuf and user regs */ - u8 __iomem *kregend; - /* physical address of chip for io_remap, etc. */ + /* first mapping up to RcvArray */ + u8 __iomem *kregbase1; resource_size_t physaddr; + + /* second uncached mapping from RcvArray to pio send buffers */ + u8 __iomem *kregbase2; + /* for detecting offset above kregbase2 address */ + u32 base2_start; + /* Per VL data. Enough for all VLs but not all elements are set/used. */ struct per_vl_data vld[PER_VL_SEND_CONTEXTS]; /* send context data */ @@ -1229,9 +1217,10 @@ static inline bool hfi1_vnic_is_rsm_full(struct hfi1_devdata *dd, int spare) #define dc8051_ver_patch(a) ((a) & 0x0000ff) /* f_put_tid types */ -#define PT_EXPECTED 0 -#define PT_EAGER 1 -#define PT_INVALID 2 +#define PT_EXPECTED 0 +#define PT_EAGER 1 +#define PT_INVALID_FLUSH 2 +#define PT_INVALID 3 struct tid_rb_node; struct mmu_rb_node; @@ -1277,12 +1266,13 @@ void handle_user_interrupt(struct hfi1_ctxtdata *rcd); int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd); int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd); int hfi1_create_ctxts(struct hfi1_devdata *dd); -struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt, +struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u16 ctxt, int numa); void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd, struct hfi1_devdata *dd, u8 hw_pidx, u8 port); void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd); - +int hfi1_rcd_put(struct hfi1_ctxtdata *rcd); +void hfi1_rcd_get(struct hfi1_ctxtdata *rcd); int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread); int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread); int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread); @@ -1321,6 +1311,22 @@ static inline u32 driver_lstate(struct hfi1_pportdata *ppd) return ppd->lstate; } +/* return the driver's idea of the physical OPA port state */ +static inline u32 driver_pstate(struct hfi1_pportdata *ppd) +{ + /* + * The driver does some processing from the time the physical + * link state is at LINKUP to the time the SM can be notified + * as such. Return IB_PORTPHYSSTATE_TRAINING until the software + * state is ready. + */ + if (ppd->pstate == PLS_LINKUP && + !(ppd->host_link_state & HLS_UP)) + return IB_PORTPHYSSTATE_TRAINING; + else + return chip_to_opa_pstate(ppd->dd, ppd->pstate); +} + void receive_interrupt_work(struct work_struct *work); /* extract service channel from header and rhf */ @@ -1829,10 +1835,9 @@ void hfi1_pcie_cleanup(struct pci_dev *pdev); int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev); void hfi1_pcie_ddcleanup(struct hfi1_devdata *); int pcie_speeds(struct hfi1_devdata *dd); -void request_msix(struct hfi1_devdata *dd, u32 *nent, - struct hfi1_msix_entry *entry); -void hfi1_enable_intx(struct pci_dev *pdev); -void restore_pci_variables(struct hfi1_devdata *dd); +int request_msix(struct hfi1_devdata *dd, u32 msireq); +int restore_pci_variables(struct hfi1_devdata *dd); +int save_pci_variables(struct hfi1_devdata *dd); int do_pcie_gen3_transition(struct hfi1_devdata *dd); int parse_platform_config(struct hfi1_devdata *dd); int get_platform_config_field(struct hfi1_devdata *dd, @@ -2087,52 +2092,13 @@ int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp); #define DD_DEV_ENTRY(dd) __string(dev, dev_name(&(dd)->pcidev->dev)) #define DD_DEV_ASSIGN(dd) __assign_str(dev, dev_name(&(dd)->pcidev->dev)) -#define packettype_name(etype) { RHF_RCV_TYPE_##etype, #etype } -#define show_packettype(etype) \ -__print_symbolic(etype, \ - packettype_name(EXPECTED), \ - packettype_name(EAGER), \ - packettype_name(IB), \ - packettype_name(ERROR), \ - packettype_name(BYPASS)) - -#define ib_opcode_name(opcode) { IB_OPCODE_##opcode, #opcode } -#define show_ib_opcode(opcode) \ -__print_symbolic(opcode, \ - ib_opcode_name(RC_SEND_FIRST), \ - ib_opcode_name(RC_SEND_MIDDLE), \ - ib_opcode_name(RC_SEND_LAST), \ - ib_opcode_name(RC_SEND_LAST_WITH_IMMEDIATE), \ - ib_opcode_name(RC_SEND_ONLY), \ - ib_opcode_name(RC_SEND_ONLY_WITH_IMMEDIATE), \ - ib_opcode_name(RC_RDMA_WRITE_FIRST), \ - ib_opcode_name(RC_RDMA_WRITE_MIDDLE), \ - ib_opcode_name(RC_RDMA_WRITE_LAST), \ - ib_opcode_name(RC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \ - ib_opcode_name(RC_RDMA_WRITE_ONLY), \ - ib_opcode_name(RC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \ - ib_opcode_name(RC_RDMA_READ_REQUEST), \ - ib_opcode_name(RC_RDMA_READ_RESPONSE_FIRST), \ - ib_opcode_name(RC_RDMA_READ_RESPONSE_MIDDLE), \ - ib_opcode_name(RC_RDMA_READ_RESPONSE_LAST), \ - ib_opcode_name(RC_RDMA_READ_RESPONSE_ONLY), \ - ib_opcode_name(RC_ACKNOWLEDGE), \ - ib_opcode_name(RC_ATOMIC_ACKNOWLEDGE), \ - ib_opcode_name(RC_COMPARE_SWAP), \ - ib_opcode_name(RC_FETCH_ADD), \ - ib_opcode_name(UC_SEND_FIRST), \ - ib_opcode_name(UC_SEND_MIDDLE), \ - ib_opcode_name(UC_SEND_LAST), \ - ib_opcode_name(UC_SEND_LAST_WITH_IMMEDIATE), \ - ib_opcode_name(UC_SEND_ONLY), \ - ib_opcode_name(UC_SEND_ONLY_WITH_IMMEDIATE), \ - ib_opcode_name(UC_RDMA_WRITE_FIRST), \ - ib_opcode_name(UC_RDMA_WRITE_MIDDLE), \ - ib_opcode_name(UC_RDMA_WRITE_LAST), \ - ib_opcode_name(UC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \ - ib_opcode_name(UC_RDMA_WRITE_ONLY), \ - ib_opcode_name(UC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \ - ib_opcode_name(UD_SEND_ONLY), \ - ib_opcode_name(UD_SEND_ONLY_WITH_IMMEDIATE), \ - ib_opcode_name(CNP)) +/* + * hfi1_check_mcast- Check if the given lid is + * in the IB multicast range. + */ +static inline bool hfi1_check_mcast(u16 lid) +{ + return ((lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) && + (lid != be16_to_cpu(IB_LID_PERMISSIVE))); +} #endif /* _HFI1_KERNEL_H */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 4a11d4da4c92..be027c9c880e 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -67,6 +67,7 @@ #include "aspm.h" #include "affinity.h" #include "vnic.h" +#include "exp_rcv.h" #undef pr_fmt #define pr_fmt(fmt) DRIVER_NAME ": " fmt @@ -130,7 +131,7 @@ unsigned long *hfi1_cpulist; */ int hfi1_create_ctxts(struct hfi1_devdata *dd) { - unsigned i; + u16 i; int ret; /* Control context has to be always 0 */ @@ -190,19 +191,49 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd) nomem: ret = -ENOMEM; - if (dd->rcd) { - for (i = 0; i < dd->num_rcv_contexts; ++i) - hfi1_free_ctxtdata(dd, dd->rcd[i]); - } + for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i) + hfi1_rcd_put(dd->rcd[i]); + + /* All the contexts should be freed, free the array */ kfree(dd->rcd); dd->rcd = NULL; return ret; } /* + * Helper routines for the receive context reference count (rcd and uctxt) + */ +static void hfi1_rcd_init(struct hfi1_ctxtdata *rcd) +{ + kref_init(&rcd->kref); +} + +static void hfi1_rcd_free(struct kref *kref) +{ + struct hfi1_ctxtdata *rcd = + container_of(kref, struct hfi1_ctxtdata, kref); + + hfi1_free_ctxtdata(rcd->dd, rcd); + kfree(rcd); +} + +int hfi1_rcd_put(struct hfi1_ctxtdata *rcd) +{ + if (rcd) + return kref_put(&rcd->kref, hfi1_rcd_free); + + return 0; +} + +void hfi1_rcd_get(struct hfi1_ctxtdata *rcd) +{ + kref_get(&rcd->kref); +} + +/* * Common code for user and kernel context setup. */ -struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt, +struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u16 ctxt, int numa) { struct hfi1_devdata *dd = ppd->dd; @@ -221,6 +252,9 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt, hfi1_cdbg(PROC, "setting up context %u\n", ctxt); INIT_LIST_HEAD(&rcd->qp_wait_list); + hfi1_exp_tid_group_init(&rcd->tid_group_list); + hfi1_exp_tid_group_init(&rcd->tid_used_list); + hfi1_exp_tid_group_init(&rcd->tid_full_list); rcd->ppd = ppd; rcd->dd = dd; __set_bit(0, rcd->in_use_ctxts); @@ -328,6 +362,8 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt, if (!rcd->opstats) goto bail; } + + hfi1_rcd_init(rcd); } return rcd; bail: @@ -567,8 +603,8 @@ static int init_after_reset(struct hfi1_devdata *dd) */ for (i = 0; i < dd->num_rcv_contexts; i++) hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_DIS | - HFI1_RCVCTRL_INTRAVAIL_DIS | - HFI1_RCVCTRL_TAILUPD_DIS, i); + HFI1_RCVCTRL_INTRAVAIL_DIS | + HFI1_RCVCTRL_TAILUPD_DIS, dd->rcd[i]); pio_send_control(dd, PSC_GLOBAL_DISABLE); for (i = 0; i < dd->num_send_contexts; i++) sc_disable(dd->send_contexts[i].sc); @@ -579,7 +615,7 @@ static int init_after_reset(struct hfi1_devdata *dd) static void enable_chip(struct hfi1_devdata *dd) { u32 rcvmask; - u32 i; + u16 i; /* enable PIO send */ pio_send_control(dd, PSC_GLOBAL_ENABLE); @@ -598,7 +634,7 @@ static void enable_chip(struct hfi1_devdata *dd) rcvmask |= HFI1_RCVCTRL_NO_RHQ_DROP_ENB; if (HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, NODROP_EGR_FULL)) rcvmask |= HFI1_RCVCTRL_NO_EGR_DROP_ENB; - hfi1_rcvctrl(dd, rcvmask, i); + hfi1_rcvctrl(dd, rcvmask, dd->rcd[i]); sc_enable(dd->rcd[i]->sc); } } @@ -624,6 +660,20 @@ static int create_workqueues(struct hfi1_devdata *dd) if (!ppd->hfi1_wq) goto wq_error; } + if (!ppd->link_wq) { + /* + * Make the link workqueue single-threaded to enforce + * serialization. + */ + ppd->link_wq = + alloc_workqueue( + "hfi_link_%d_%d", + WQ_SYSFS | WQ_MEM_RECLAIM | WQ_UNBOUND, + 1, /* max_active */ + dd->unit, pidx); + if (!ppd->link_wq) + goto wq_error; + } } return 0; wq_error: @@ -634,6 +684,10 @@ wq_error: destroy_workqueue(ppd->hfi1_wq); ppd->hfi1_wq = NULL; } + if (ppd->link_wq) { + destroy_workqueue(ppd->link_wq); + ppd->link_wq = NULL; + } } return -ENOMEM; } @@ -656,7 +710,8 @@ wq_error: int hfi1_init(struct hfi1_devdata *dd, int reinit) { int ret = 0, pidx, lastfail = 0; - unsigned i, len; + unsigned long len; + u16 i; struct hfi1_ctxtdata *rcd; struct hfi1_pportdata *ppd; @@ -878,10 +933,10 @@ static void shutdown_device(struct hfi1_devdata *dd) ppd = dd->pport + pidx; for (i = 0; i < dd->num_rcv_contexts; i++) hfi1_rcvctrl(dd, HFI1_RCVCTRL_TAILUPD_DIS | - HFI1_RCVCTRL_CTXT_DIS | - HFI1_RCVCTRL_INTRAVAIL_DIS | - HFI1_RCVCTRL_PKEY_DIS | - HFI1_RCVCTRL_ONE_PKT_EGR_DIS, i); + HFI1_RCVCTRL_CTXT_DIS | + HFI1_RCVCTRL_INTRAVAIL_DIS | + HFI1_RCVCTRL_PKEY_DIS | + HFI1_RCVCTRL_ONE_PKT_EGR_DIS, dd->rcd[i]); /* * Gracefully stop all sends allowing any in progress to * trickle out first. @@ -917,6 +972,10 @@ static void shutdown_device(struct hfi1_devdata *dd) destroy_workqueue(ppd->hfi1_wq); ppd->hfi1_wq = NULL; } + if (ppd->link_wq) { + destroy_workqueue(ppd->link_wq); + ppd->link_wq = NULL; + } } sdma_exit(dd); } @@ -927,14 +986,11 @@ static void shutdown_device(struct hfi1_devdata *dd) * @rcd: the ctxtdata structure * * free up any allocated data for a context - * This should not touch anything that would affect a simultaneous - * re-allocation of context data, because it is called after hfi1_mutex - * is released (and can be called from reinit as well). * It should never change any chip state, or global driver state. */ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd) { - unsigned e; + u32 e; if (!rcd) return; @@ -953,6 +1009,7 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd) /* all the RcvArray entries should have been cleared by now */ kfree(rcd->egrbufs.rcvtids); + rcd->egrbufs.rcvtids = NULL; for (e = 0; e < rcd->egrbufs.alloced; e++) { if (rcd->egrbufs.buffers[e].dma) @@ -962,13 +1019,21 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd) rcd->egrbufs.buffers[e].dma); } kfree(rcd->egrbufs.buffers); + rcd->egrbufs.alloced = 0; + rcd->egrbufs.buffers = NULL; sc_free(rcd->sc); + rcd->sc = NULL; + vfree(rcd->subctxt_uregbase); vfree(rcd->subctxt_rcvegrbuf); vfree(rcd->subctxt_rcvhdr_base); kfree(rcd->opstats); - kfree(rcd); + + rcd->subctxt_uregbase = NULL; + rcd->subctxt_rcvegrbuf = NULL; + rcd->subctxt_rcvhdr_base = NULL; + rcd->opstats = NULL; } /* @@ -1362,7 +1427,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) tmp[ctxt] = NULL; /* debugging paranoia */ if (rcd) { hfi1_clear_tids(rcd); - hfi1_free_ctxtdata(dd, rcd); + hfi1_rcd_put(rcd); } } kfree(tmp); @@ -1532,6 +1597,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) destroy_workqueue(ppd->hfi1_wq); ppd->hfi1_wq = NULL; } + if (ppd->link_wq) { + destroy_workqueue(ppd->link_wq); + ppd->link_wq = NULL; + } } if (!j) hfi1_device_remove(dd); diff --git a/drivers/infiniband/hw/hfi1/intr.c b/drivers/infiniband/hw/hfi1/intr.c index 04a5082d5ac5..96845dfed5c5 100644 --- a/drivers/infiniband/hw/hfi1/intr.c +++ b/drivers/infiniband/hw/hfi1/intr.c @@ -164,6 +164,7 @@ void handle_linkup_change(struct hfi1_devdata *dd, u32 linkup) ppd->linkup = 0; /* clear HW details of the previous connection */ + ppd->actual_vls_operational = 0; reset_link_credits(dd); /* freeze after a link down to guarantee a clean egress */ @@ -196,7 +197,7 @@ void handle_user_interrupt(struct hfi1_ctxtdata *rcd) if (test_and_clear_bit(HFI1_CTXT_WAITING_RCV, &rcd->event_flags)) { wake_up_interruptible(&rcd->wait); - hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_DIS, rcd->ctxt); + hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_DIS, rcd); } else if (test_and_clear_bit(HFI1_CTXT_WAITING_URG, &rcd->event_flags)) { rcd->urgent++; diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h index d9740ddea6f1..591697d85eed 100644 --- a/drivers/infiniband/hw/hfi1/iowait.h +++ b/drivers/infiniband/hw/hfi1/iowait.h @@ -106,7 +106,9 @@ struct iowait { struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *tx, - unsigned seq); + uint seq, + bool pkts_sent + ); void (*wakeup)(struct iowait *wait, int reason); void (*sdma_drained)(struct iowait *wait); seqlock_t *lock; @@ -118,6 +120,7 @@ struct iowait { u32 count; u32 tx_limit; u32 tx_count; + u8 starved_cnt; }; #define SDMA_AVAIL_REASON 0 @@ -143,7 +146,8 @@ static inline void iowait_init( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *tx, - unsigned seq), + uint seq, + bool pkts_sent), void (*wakeup)(struct iowait *wait, int reason), void (*sdma_drained)(struct iowait *wait)) { @@ -305,4 +309,66 @@ static inline struct sdma_txreq *iowait_get_txhead(struct iowait *wait) return tx; } +/** + * iowait_queue - Put the iowait on a wait queue + * @pkts_sent: have some packets been sent before queuing? + * @w: the iowait struct + * @wait_head: the wait queue + * + * This function is called to insert an iowait struct into a + * wait queue after a resource (eg, sdma decriptor or pio + * buffer) is run out. + */ +static inline void iowait_queue(bool pkts_sent, struct iowait *w, + struct list_head *wait_head) +{ + /* + * To play fair, insert the iowait at the tail of the wait queue if it + * has already sent some packets; Otherwise, put it at the head. + */ + if (pkts_sent) { + list_add_tail(&w->list, wait_head); + w->starved_cnt = 0; + } else { + list_add(&w->list, wait_head); + w->starved_cnt++; + } +} + +/** + * iowait_starve_clear - clear the wait queue's starve count + * @pkts_sent: have some packets been sent? + * @w: the iowait struct + * + * This function is called to clear the starve count. If no + * packets have been sent, the starve count will not be cleared. + */ +static inline void iowait_starve_clear(bool pkts_sent, struct iowait *w) +{ + if (pkts_sent) + w->starved_cnt = 0; +} + +/** + * iowait_starve_find_max - Find the maximum of the starve count + * @w: the iowait struct + * @max: a variable containing the max starve count + * @idx: the index of the current iowait in an array + * @max_idx: a variable containing the array index for the + * iowait entry that has the max starve count + * + * This function is called to compare the starve count of a + * given iowait with the given max starve count. The max starve + * count and the index will be updated if the iowait's start + * count is larger. + */ +static inline void iowait_starve_find_max(struct iowait *w, u8 *max, + uint idx, uint *max_idx) +{ + if (w->starved_cnt > *max) { + *max = w->starved_cnt; + *max_idx = idx; + } +} + #endif diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 5977673a52d4..8daa3a5f7e95 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -59,6 +59,24 @@ #define OPA_LINK_WIDTH_RESET_OLD 0x0fff #define OPA_LINK_WIDTH_RESET 0xffff +struct trap_node { + struct list_head list; + struct opa_mad_notice_attr data; + __be64 tid; + int len; + u32 retry; + u8 in_use; + u8 repress; +}; + +static int smp_length_check(u32 data_size, u32 request_len) +{ + if (unlikely(request_len < data_size)) + return -EINVAL; + + return 0; +} + static int reply(struct ib_mad_hdr *smp) { /* @@ -89,28 +107,156 @@ void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port) ib_dispatch_event(&event); } -static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len) +/* + * If the port is down, clean up all pending traps. We need to be careful + * with the given trap, because it may be queued. + */ +static void cleanup_traps(struct hfi1_ibport *ibp, struct trap_node *trap) +{ + struct trap_node *node, *q; + unsigned long flags; + struct list_head trap_list; + int i; + + for (i = 0; i < RVT_MAX_TRAP_LISTS; i++) { + spin_lock_irqsave(&ibp->rvp.lock, flags); + list_replace_init(&ibp->rvp.trap_lists[i].list, &trap_list); + ibp->rvp.trap_lists[i].list_len = 0; + spin_unlock_irqrestore(&ibp->rvp.lock, flags); + + /* + * Remove all items from the list, freeing all the non-given + * traps. + */ + list_for_each_entry_safe(node, q, &trap_list, list) { + list_del(&node->list); + if (node != trap) + kfree(node); + } + } + + /* + * If this wasn't on one of the lists it would not be freed. If it + * was on the list, it is now safe to free. + */ + kfree(trap); +} + +static struct trap_node *check_and_add_trap(struct hfi1_ibport *ibp, + struct trap_node *trap) +{ + struct trap_node *node; + struct trap_list *trap_list; + unsigned long flags; + unsigned long timeout; + int found = 0; + + /* + * Since the retry (handle timeout) does not remove a trap request + * from the list, all we have to do is compare the node. + */ + spin_lock_irqsave(&ibp->rvp.lock, flags); + trap_list = &ibp->rvp.trap_lists[trap->data.generic_type & 0x0F]; + + list_for_each_entry(node, &trap_list->list, list) { + if (node == trap) { + node->retry++; + found = 1; + break; + } + } + + /* If it is not on the list, add it, limited to RVT-MAX_TRAP_LEN. */ + if (!found) { + if (trap_list->list_len < RVT_MAX_TRAP_LEN) { + trap_list->list_len++; + list_add_tail(&trap->list, &trap_list->list); + } else { + pr_warn_ratelimited("hfi1: Maximim trap limit reached for 0x%0x traps\n", + trap->data.generic_type); + kfree(trap); + } + } + + /* + * Next check to see if there is a timer pending. If not, set it up + * and get the first trap from the list. + */ + node = NULL; + if (!timer_pending(&ibp->rvp.trap_timer)) { + /* + * o14-2 + * If the time out is set we have to wait until it expires + * before the trap can be sent. + * This should be > RVT_TRAP_TIMEOUT + */ + timeout = (RVT_TRAP_TIMEOUT * + (1UL << ibp->rvp.subnet_timeout)) / 1000; + mod_timer(&ibp->rvp.trap_timer, + jiffies + usecs_to_jiffies(timeout)); + node = list_first_entry(&trap_list->list, struct trap_node, + list); + node->in_use = 1; + } + spin_unlock_irqrestore(&ibp->rvp.lock, flags); + + return node; +} + +static void subn_handle_opa_trap_repress(struct hfi1_ibport *ibp, + struct opa_smp *smp) +{ + struct trap_list *trap_list; + struct trap_node *trap; + unsigned long flags; + int i; + + if (smp->attr_id != IB_SMP_ATTR_NOTICE) + return; + + spin_lock_irqsave(&ibp->rvp.lock, flags); + for (i = 0; i < RVT_MAX_TRAP_LISTS; i++) { + trap_list = &ibp->rvp.trap_lists[i]; + trap = list_first_entry_or_null(&trap_list->list, + struct trap_node, list); + if (trap && trap->tid == smp->tid) { + if (trap->in_use) { + trap->repress = 1; + } else { + trap_list->list_len--; + list_del(&trap->list); + kfree(trap); + } + break; + } + } + spin_unlock_irqrestore(&ibp->rvp.lock, flags); +} + +static void send_trap(struct hfi1_ibport *ibp, struct trap_node *trap) { struct ib_mad_send_buf *send_buf; struct ib_mad_agent *agent; struct opa_smp *smp; - int ret; unsigned long flags; - unsigned long timeout; int pkey_idx; u32 qpn = ppd_from_ibp(ibp)->sm_trap_qp; agent = ibp->rvp.send_agent; - if (!agent) + if (!agent) { + cleanup_traps(ibp, trap); return; + } /* o14-3.2.1 */ - if (ppd_from_ibp(ibp)->lstate != IB_PORT_ACTIVE) + if (driver_lstate(ppd_from_ibp(ibp)) != IB_PORT_ACTIVE) { + cleanup_traps(ibp, trap); return; + } - /* o14-2 */ - if (ibp->rvp.trap_timeout && time_before(jiffies, - ibp->rvp.trap_timeout)) + /* Add the trap to the list if necessary and see if we can send it */ + trap = check_and_add_trap(ibp, trap); + if (!trap) return; pkey_idx = hfi1_lookup_pkey_idx(ibp, LIM_MGMT_P_KEY); @@ -131,11 +277,21 @@ static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len) smp->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; smp->class_version = OPA_SM_CLASS_VERSION; smp->method = IB_MGMT_METHOD_TRAP; - ibp->rvp.tid++; - smp->tid = cpu_to_be64(ibp->rvp.tid); + + /* Only update the transaction ID for new traps (o13-5). */ + if (trap->tid == 0) { + ibp->rvp.tid++; + /* make sure that tid != 0 */ + if (ibp->rvp.tid == 0) + ibp->rvp.tid++; + trap->tid = cpu_to_be64(ibp->rvp.tid); + } + smp->tid = trap->tid; + smp->attr_id = IB_SMP_ATTR_NOTICE; /* o14-1: smp->mkey = 0; */ - memcpy(smp->route.lid.data, data, len); + + memcpy(smp->route.lid.data, &trap->data, trap->len); spin_lock_irqsave(&ibp->rvp.lock, flags); if (!ibp->rvp.sm_ah) { @@ -144,65 +300,103 @@ static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len) ah = hfi1_create_qp0_ah(ibp, ibp->rvp.sm_lid); if (IS_ERR(ah)) { - ret = PTR_ERR(ah); - } else { - send_buf->ah = ah; - ibp->rvp.sm_ah = ibah_to_rvtah(ah); - ret = 0; + spin_unlock_irqrestore(&ibp->rvp.lock, flags); + return; } + send_buf->ah = ah; + ibp->rvp.sm_ah = ibah_to_rvtah(ah); } else { - ret = -EINVAL; + spin_unlock_irqrestore(&ibp->rvp.lock, flags); + return; } } else { send_buf->ah = &ibp->rvp.sm_ah->ibah; - ret = 0; } + + /* + * If the trap was repressed while things were getting set up, don't + * bother sending it. This could happen for a retry. + */ + if (trap->repress) { + list_del(&trap->list); + spin_unlock_irqrestore(&ibp->rvp.lock, flags); + kfree(trap); + ib_free_send_mad(send_buf); + return; + } + + trap->in_use = 0; spin_unlock_irqrestore(&ibp->rvp.lock, flags); - if (!ret) - ret = ib_post_send_mad(send_buf, NULL); - if (!ret) { - /* 4.096 usec. */ - timeout = (4096 * (1UL << ibp->rvp.subnet_timeout)) / 1000; - ibp->rvp.trap_timeout = jiffies + usecs_to_jiffies(timeout); - } else { + if (ib_post_send_mad(send_buf, NULL)) ib_free_send_mad(send_buf); - ibp->rvp.trap_timeout = 0; +} + +void hfi1_handle_trap_timer(unsigned long data) +{ + struct hfi1_ibport *ibp = (struct hfi1_ibport *)data; + struct trap_node *trap = NULL; + unsigned long flags; + int i; + + /* Find the trap with the highest priority */ + spin_lock_irqsave(&ibp->rvp.lock, flags); + for (i = 0; !trap && i < RVT_MAX_TRAP_LISTS; i++) { + trap = list_first_entry_or_null(&ibp->rvp.trap_lists[i].list, + struct trap_node, list); } + spin_unlock_irqrestore(&ibp->rvp.lock, flags); + + if (trap) + send_trap(ibp, trap); +} + +static struct trap_node *create_trap_node(u8 type, __be16 trap_num, u32 lid) +{ + struct trap_node *trap; + + trap = kzalloc(sizeof(*trap), GFP_ATOMIC); + if (!trap) + return NULL; + + INIT_LIST_HEAD(&trap->list); + trap->data.generic_type = type; + trap->data.prod_type_lsb = IB_NOTICE_PROD_CA; + trap->data.trap_num = trap_num; + trap->data.issuer_lid = cpu_to_be32(lid); + + return trap; } /* - * Send a bad [PQ]_Key trap (ch. 14.3.8). + * Send a bad P_Key trap (ch. 14.3.8). */ -void hfi1_bad_pqkey(struct hfi1_ibport *ibp, __be16 trap_num, u32 key, u32 sl, - u32 qp1, u32 qp2, u16 lid1, u16 lid2) +void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl, + u32 qp1, u32 qp2, u16 lid1, u16 lid2) { - struct opa_mad_notice_attr data; + struct trap_node *trap; u32 lid = ppd_from_ibp(ibp)->lid; u32 _lid1 = lid1; u32 _lid2 = lid2; - memset(&data, 0, sizeof(data)); - - if (trap_num == OPA_TRAP_BAD_P_KEY) - ibp->rvp.pkey_violations++; - else - ibp->rvp.qkey_violations++; ibp->rvp.n_pkt_drops++; + ibp->rvp.pkey_violations++; + + trap = create_trap_node(IB_NOTICE_TYPE_SECURITY, OPA_TRAP_BAD_P_KEY, + lid); + if (!trap) + return; /* Send violation trap */ - data.generic_type = IB_NOTICE_TYPE_SECURITY; - data.prod_type_lsb = IB_NOTICE_PROD_CA; - data.trap_num = trap_num; - data.issuer_lid = cpu_to_be32(lid); - data.ntc_257_258.lid1 = cpu_to_be32(_lid1); - data.ntc_257_258.lid2 = cpu_to_be32(_lid2); - data.ntc_257_258.key = cpu_to_be32(key); - data.ntc_257_258.sl = sl << 3; - data.ntc_257_258.qp1 = cpu_to_be32(qp1); - data.ntc_257_258.qp2 = cpu_to_be32(qp2); - - send_trap(ibp, &data, sizeof(data)); + trap->data.ntc_257_258.lid1 = cpu_to_be32(_lid1); + trap->data.ntc_257_258.lid2 = cpu_to_be32(_lid2); + trap->data.ntc_257_258.key = cpu_to_be32(key); + trap->data.ntc_257_258.sl = sl << 3; + trap->data.ntc_257_258.qp1 = cpu_to_be32(qp1); + trap->data.ntc_257_258.qp2 = cpu_to_be32(qp2); + + trap->len = sizeof(trap->data); + send_trap(ibp, trap); } /* @@ -211,34 +405,36 @@ void hfi1_bad_pqkey(struct hfi1_ibport *ibp, __be16 trap_num, u32 key, u32 sl, static void bad_mkey(struct hfi1_ibport *ibp, struct ib_mad_hdr *mad, __be64 mkey, __be32 dr_slid, u8 return_path[], u8 hop_cnt) { - struct opa_mad_notice_attr data; + struct trap_node *trap; u32 lid = ppd_from_ibp(ibp)->lid; - memset(&data, 0, sizeof(data)); + trap = create_trap_node(IB_NOTICE_TYPE_SECURITY, OPA_TRAP_BAD_M_KEY, + lid); + if (!trap) + return; + /* Send violation trap */ - data.generic_type = IB_NOTICE_TYPE_SECURITY; - data.prod_type_lsb = IB_NOTICE_PROD_CA; - data.trap_num = OPA_TRAP_BAD_M_KEY; - data.issuer_lid = cpu_to_be32(lid); - data.ntc_256.lid = data.issuer_lid; - data.ntc_256.method = mad->method; - data.ntc_256.attr_id = mad->attr_id; - data.ntc_256.attr_mod = mad->attr_mod; - data.ntc_256.mkey = mkey; + trap->data.ntc_256.lid = trap->data.issuer_lid; + trap->data.ntc_256.method = mad->method; + trap->data.ntc_256.attr_id = mad->attr_id; + trap->data.ntc_256.attr_mod = mad->attr_mod; + trap->data.ntc_256.mkey = mkey; if (mad->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) { - data.ntc_256.dr_slid = dr_slid; - data.ntc_256.dr_trunc_hop = IB_NOTICE_TRAP_DR_NOTICE; - if (hop_cnt > ARRAY_SIZE(data.ntc_256.dr_rtn_path)) { - data.ntc_256.dr_trunc_hop |= + trap->data.ntc_256.dr_slid = dr_slid; + trap->data.ntc_256.dr_trunc_hop = IB_NOTICE_TRAP_DR_NOTICE; + if (hop_cnt > ARRAY_SIZE(trap->data.ntc_256.dr_rtn_path)) { + trap->data.ntc_256.dr_trunc_hop |= IB_NOTICE_TRAP_DR_TRUNC; - hop_cnt = ARRAY_SIZE(data.ntc_256.dr_rtn_path); + hop_cnt = ARRAY_SIZE(trap->data.ntc_256.dr_rtn_path); } - data.ntc_256.dr_trunc_hop |= hop_cnt; - memcpy(data.ntc_256.dr_rtn_path, return_path, + trap->data.ntc_256.dr_trunc_hop |= hop_cnt; + memcpy(trap->data.ntc_256.dr_rtn_path, return_path, hop_cnt); } - send_trap(ibp, &data, sizeof(data)); + trap->len = sizeof(trap->data); + + send_trap(ibp, trap); } /* @@ -246,22 +442,24 @@ static void bad_mkey(struct hfi1_ibport *ibp, struct ib_mad_hdr *mad, */ void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num) { - struct opa_mad_notice_attr data; + struct trap_node *trap; struct hfi1_ibdev *verbs_dev = dev_from_rdi(rdi); struct hfi1_devdata *dd = dd_from_dev(verbs_dev); struct hfi1_ibport *ibp = &dd->pport[port_num - 1].ibport_data; u32 lid = ppd_from_ibp(ibp)->lid; - memset(&data, 0, sizeof(data)); + trap = create_trap_node(IB_NOTICE_TYPE_INFO, + OPA_TRAP_CHANGE_CAPABILITY, + lid); + if (!trap) + return; - data.generic_type = IB_NOTICE_TYPE_INFO; - data.prod_type_lsb = IB_NOTICE_PROD_CA; - data.trap_num = OPA_TRAP_CHANGE_CAPABILITY; - data.issuer_lid = cpu_to_be32(lid); - data.ntc_144.lid = data.issuer_lid; - data.ntc_144.new_cap_mask = cpu_to_be32(ibp->rvp.port_cap_flags); + trap->data.ntc_144.lid = trap->data.issuer_lid; + trap->data.ntc_144.new_cap_mask = cpu_to_be32(ibp->rvp.port_cap_flags); + trap->data.ntc_144.cap_mask3 = cpu_to_be16(ibp->rvp.port_cap3_flags); - send_trap(ibp, &data, sizeof(data)); + trap->len = sizeof(trap->data); + send_trap(ibp, trap); } /* @@ -269,19 +467,19 @@ void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num) */ void hfi1_sys_guid_chg(struct hfi1_ibport *ibp) { - struct opa_mad_notice_attr data; + struct trap_node *trap; u32 lid = ppd_from_ibp(ibp)->lid; - memset(&data, 0, sizeof(data)); + trap = create_trap_node(IB_NOTICE_TYPE_INFO, OPA_TRAP_CHANGE_SYSGUID, + lid); + if (!trap) + return; - data.generic_type = IB_NOTICE_TYPE_INFO; - data.prod_type_lsb = IB_NOTICE_PROD_CA; - data.trap_num = OPA_TRAP_CHANGE_SYSGUID; - data.issuer_lid = cpu_to_be32(lid); - data.ntc_145.new_sys_guid = ib_hfi1_sys_image_guid; - data.ntc_145.lid = data.issuer_lid; + trap->data.ntc_145.new_sys_guid = ib_hfi1_sys_image_guid; + trap->data.ntc_145.lid = trap->data.issuer_lid; - send_trap(ibp, &data, sizeof(data)); + trap->len = sizeof(trap->data); + send_trap(ibp, trap); } /* @@ -289,29 +487,30 @@ void hfi1_sys_guid_chg(struct hfi1_ibport *ibp) */ void hfi1_node_desc_chg(struct hfi1_ibport *ibp) { - struct opa_mad_notice_attr data; + struct trap_node *trap; u32 lid = ppd_from_ibp(ibp)->lid; - memset(&data, 0, sizeof(data)); + trap = create_trap_node(IB_NOTICE_TYPE_INFO, + OPA_TRAP_CHANGE_CAPABILITY, + lid); + if (!trap) + return; - data.generic_type = IB_NOTICE_TYPE_INFO; - data.prod_type_lsb = IB_NOTICE_PROD_CA; - data.trap_num = OPA_TRAP_CHANGE_CAPABILITY; - data.issuer_lid = cpu_to_be32(lid); - data.ntc_144.lid = data.issuer_lid; - data.ntc_144.change_flags = + trap->data.ntc_144.lid = trap->data.issuer_lid; + trap->data.ntc_144.change_flags = cpu_to_be16(OPA_NOTICE_TRAP_NODE_DESC_CHG); - send_trap(ibp, &data, sizeof(data)); + trap->len = sizeof(trap->data); + send_trap(ibp, trap); } static int __subn_get_opa_nodedesc(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, - u8 port, u32 *resp_len) + u8 port, u32 *resp_len, u32 max_len) { struct opa_node_description *nd; - if (am) { + if (am || smp_length_check(sizeof(*nd), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -328,7 +527,7 @@ static int __subn_get_opa_nodedesc(struct opa_smp *smp, u32 am, static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct opa_node_info *ni; struct hfi1_devdata *dd = dd_from_ibdev(ibdev); @@ -338,6 +537,7 @@ static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data, /* GUID 0 is illegal */ if (am || pidx >= dd->num_pports || ibdev->node_guid == 0 || + smp_length_check(sizeof(*ni), max_len) || get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); @@ -519,7 +719,7 @@ void read_ltp_rtt(struct hfi1_devdata *dd) static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { int i; struct hfi1_devdata *dd; @@ -535,7 +735,7 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, u32 buffer_units; u64 tmp = 0; - if (num_ports != 1) { + if (num_ports != 1 || smp_length_check(sizeof(*pi), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -605,7 +805,7 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, ppd->offline_disabled_reason; pi->port_states.portphysstate_portstate = - (hfi1_ibphys_portstate(ppd) << 4) | state; + (driver_pstate(ppd) << 4) | state; pi->mkeyprotect_lmc = (ibp->rvp.mkeyprot << 6) | ppd->lmc; @@ -704,11 +904,7 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, buffer_units |= (dd->vl15_init << 11) & OPA_PI_MASK_BUF_UNIT_VL15_INIT; pi->buffer_units = cpu_to_be32(buffer_units); - pi->opa_cap_mask = cpu_to_be16(OPA_CAP_MASK3_IsSharedSpaceSupported | - OPA_CAP_MASK3_IsEthOnFabricSupported); - /* Driver does not support mcast/collective configuration */ - pi->opa_cap_mask &= - cpu_to_be16(~OPA_CAP_MASK3_IsAddrRangeConfigSupported); + pi->opa_cap_mask = cpu_to_be16(ibp->rvp.port_cap3_flags); pi->collectivemask_multicastmask = ((HFI1_COLLECTIVE_NR & 0x7) << 3 | (HFI1_MCAST_NR & 0x7)); @@ -748,7 +944,7 @@ static int get_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys) static int __subn_get_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_devdata *dd = dd_from_ibdev(ibdev); u32 n_blocks_req = OPA_AM_NBLK(am); @@ -771,6 +967,11 @@ static int __subn_get_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data, size = (n_blocks_req * OPA_PARTITION_TABLE_BLK_SIZE) * sizeof(u16); + if (smp_length_check(size, max_len)) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + if (start_block + n_blocks_req > n_blocks_avail || n_blocks_req > OPA_NUM_PKEY_BLOCKS_PER_SMP) { pr_warn("OPA Get PKey AM Invalid : s 0x%x; req 0x%x; " @@ -1074,7 +1275,7 @@ static int set_port_states(struct hfi1_pportdata *ppd, struct opa_smp *smp, */ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct opa_port_info *pi = (struct opa_port_info *)data; struct ib_event event; @@ -1095,7 +1296,8 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, int ret, i, invalid = 0, call_set_mtu = 0; int call_link_downgrade_policy = 0; - if (num_ports != 1) { + if (num_ports != 1 || + smp_length_check(sizeof(*pi), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1346,7 +1548,8 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, if (ret) return ret; - ret = __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len); + ret = __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len, + max_len); /* restore re-reg bit per o14-12.2.1 */ pi->clientrereg_subnettimeout |= clientrereg; @@ -1363,7 +1566,8 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data, return ret; get_only: - return __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len, + max_len); } /** @@ -1424,7 +1628,7 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys) static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_devdata *dd = dd_from_ibdev(ibdev); u32 n_blocks_sent = OPA_AM_NBLK(am); @@ -1434,6 +1638,7 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data, int i; u16 n_blocks_avail; unsigned npkeys = hfi1_get_npkeys(dd); + u32 size = 0; if (n_blocks_sent == 0) { pr_warn("OPA Get PKey AM Invalid : P = %d; B = 0x%x; N = 0x%x\n", @@ -1444,6 +1649,13 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data, n_blocks_avail = (u16)(npkeys / OPA_PARTITION_TABLE_BLK_SIZE) + 1; + size = sizeof(u16) * (n_blocks_sent * OPA_PARTITION_TABLE_BLK_SIZE); + + if (smp_length_check(size, max_len)) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + if (start_block + n_blocks_sent > n_blocks_avail || n_blocks_sent > OPA_NUM_PKEY_BLOCKS_PER_SMP) { pr_warn("OPA Set PKey AM Invalid : s 0x%x; req 0x%x; avail 0x%x; blk/smp 0x%lx\n", @@ -1461,7 +1673,8 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data, return reply((struct ib_mad_hdr *)smp); } - return __subn_get_opa_pkeytable(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_pkeytable(smp, am, data, ibdev, port, resp_len, + max_len); } #define ILLEGAL_VL 12 @@ -1522,14 +1735,14 @@ static int get_sc2vlt_tables(struct hfi1_devdata *dd, void *data) static int __subn_get_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_ibport *ibp = to_iport(ibdev, port); u8 *p = data; size_t size = ARRAY_SIZE(ibp->sl_to_sc); /* == 32 */ unsigned i; - if (am) { + if (am || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1545,14 +1758,15 @@ static int __subn_get_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_ibport *ibp = to_iport(ibdev, port); u8 *p = data; + size_t size = ARRAY_SIZE(ibp->sl_to_sc); int i; u8 sc; - if (am) { + if (am || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1567,19 +1781,20 @@ static int __subn_set_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data, } } - return __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port, resp_len, + max_len); } static int __subn_get_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_ibport *ibp = to_iport(ibdev, port); u8 *p = data; size_t size = ARRAY_SIZE(ibp->sc_to_sl); /* == 32 */ unsigned i; - if (am) { + if (am || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1595,13 +1810,14 @@ static int __subn_get_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_ibport *ibp = to_iport(ibdev, port); + size_t size = ARRAY_SIZE(ibp->sc_to_sl); u8 *p = data; int i; - if (am) { + if (am || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1609,19 +1825,20 @@ static int __subn_set_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data, for (i = 0; i < ARRAY_SIZE(ibp->sc_to_sl); i++) ibp->sc_to_sl[i] = *p++; - return __subn_get_opa_sc_to_sl(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_sc_to_sl(smp, am, data, ibdev, port, resp_len, + max_len); } static int __subn_get_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { u32 n_blocks = OPA_AM_NBLK(am); struct hfi1_devdata *dd = dd_from_ibdev(ibdev); void *vp = (void *)data; size_t size = 4 * sizeof(u64); - if (n_blocks != 1) { + if (n_blocks != 1 || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1636,7 +1853,7 @@ static int __subn_get_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { u32 n_blocks = OPA_AM_NBLK(am); int async_update = OPA_AM_ASYNC(am); @@ -1644,8 +1861,15 @@ static int __subn_set_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data, void *vp = (void *)data; struct hfi1_pportdata *ppd; int lstate; + /* + * set_sc2vlt_tables writes the information contained in *data + * to four 64-bit registers SendSC2VLt[0-3]. We need to make + * sure *max_len is not greater than the total size of the four + * SendSC2VLt[0-3] registers. + */ + size_t size = 4 * sizeof(u64); - if (n_blocks != 1 || async_update) { + if (n_blocks != 1 || async_update || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1665,27 +1889,28 @@ static int __subn_set_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data, set_sc2vlt_tables(dd, vp); - return __subn_get_opa_sc_to_vlt(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_sc_to_vlt(smp, am, data, ibdev, port, resp_len, + max_len); } static int __subn_get_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { u32 n_blocks = OPA_AM_NPORT(am); struct hfi1_devdata *dd = dd_from_ibdev(ibdev); struct hfi1_pportdata *ppd; void *vp = (void *)data; - int size; + int size = sizeof(struct sc2vlnt); - if (n_blocks != 1) { + if (n_blocks != 1 || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } ppd = dd->pport + (port - 1); - size = fm_get_table(ppd, FM_TBL_SC2VLNT, vp); + fm_get_table(ppd, FM_TBL_SC2VLNT, vp); if (resp_len) *resp_len += size; @@ -1695,15 +1920,16 @@ static int __subn_get_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { u32 n_blocks = OPA_AM_NPORT(am); struct hfi1_devdata *dd = dd_from_ibdev(ibdev); struct hfi1_pportdata *ppd; void *vp = (void *)data; int lstate; + int size = sizeof(struct sc2vlnt); - if (n_blocks != 1) { + if (n_blocks != 1 || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1721,12 +1947,12 @@ static int __subn_set_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data, fm_set_table(ppd, FM_TBL_SC2VLNT, vp); return __subn_get_opa_sc_to_vlnt(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); } static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { u32 nports = OPA_AM_NPORT(am); u32 start_of_sm_config = OPA_AM_START_SM_CFG(am); @@ -1735,7 +1961,7 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data, struct hfi1_pportdata *ppd; struct opa_port_state_info *psi = (struct opa_port_state_info *)data; - if (nports != 1) { + if (nports != 1 || smp_length_check(sizeof(*psi), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1755,7 +1981,7 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data, ppd->offline_disabled_reason; psi->port_states.portphysstate_portstate = - (hfi1_ibphys_portstate(ppd) << 4) | (lstate & 0xf); + (driver_pstate(ppd) << 4) | (lstate & 0xf); psi->link_width_downgrade_tx_active = cpu_to_be16(ppd->link_width_downgrade_tx_active); psi->link_width_downgrade_rx_active = @@ -1768,7 +1994,7 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_psi(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { u32 nports = OPA_AM_NPORT(am); u32 start_of_sm_config = OPA_AM_START_SM_CFG(am); @@ -1779,7 +2005,7 @@ static int __subn_set_opa_psi(struct opa_smp *smp, u32 am, u8 *data, struct opa_port_state_info *psi = (struct opa_port_state_info *)data; int ret, invalid = 0; - if (nports != 1) { + if (nports != 1 || smp_length_check(sizeof(*psi), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1809,19 +2035,21 @@ static int __subn_set_opa_psi(struct opa_smp *smp, u32 am, u8 *data, if (invalid) smp->status |= IB_SMP_INVALID_FIELD; - return __subn_get_opa_psi(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_psi(smp, am, data, ibdev, port, resp_len, + max_len); } static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_devdata *dd = dd_from_ibdev(ibdev); u32 addr = OPA_AM_CI_ADDR(am); u32 len = OPA_AM_CI_LEN(am) + 1; int ret; - if (dd->pport->port_type != PORT_TYPE_QSFP) { + if (dd->pport->port_type != PORT_TYPE_QSFP || + smp_length_check(len, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1864,21 +2092,22 @@ static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data, } static int __subn_get_opa_bct(struct opa_smp *smp, u32 am, u8 *data, - struct ib_device *ibdev, u8 port, u32 *resp_len) + struct ib_device *ibdev, u8 port, u32 *resp_len, + u32 max_len) { u32 num_ports = OPA_AM_NPORT(am); struct hfi1_devdata *dd = dd_from_ibdev(ibdev); struct hfi1_pportdata *ppd; struct buffer_control *p = (struct buffer_control *)data; - int size; + int size = sizeof(struct buffer_control); - if (num_ports != 1) { + if (num_ports != 1 || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } ppd = dd->pport + (port - 1); - size = fm_get_table(ppd, FM_TBL_BUFFER_CONTROL, p); + fm_get_table(ppd, FM_TBL_BUFFER_CONTROL, p); trace_bct_get(dd, p); if (resp_len) *resp_len += size; @@ -1887,14 +2116,15 @@ static int __subn_get_opa_bct(struct opa_smp *smp, u32 am, u8 *data, } static int __subn_set_opa_bct(struct opa_smp *smp, u32 am, u8 *data, - struct ib_device *ibdev, u8 port, u32 *resp_len) + struct ib_device *ibdev, u8 port, u32 *resp_len, + u32 max_len) { u32 num_ports = OPA_AM_NPORT(am); struct hfi1_devdata *dd = dd_from_ibdev(ibdev); struct hfi1_pportdata *ppd; struct buffer_control *p = (struct buffer_control *)data; - if (num_ports != 1) { + if (num_ports != 1 || smp_length_check(sizeof(*p), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1905,41 +2135,43 @@ static int __subn_set_opa_bct(struct opa_smp *smp, u32 am, u8 *data, return reply((struct ib_mad_hdr *)smp); } - return __subn_get_opa_bct(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_bct(smp, am, data, ibdev, port, resp_len, + max_len); } static int __subn_get_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_pportdata *ppd = ppd_from_ibp(to_iport(ibdev, port)); u32 num_ports = OPA_AM_NPORT(am); u8 section = (am & 0x00ff0000) >> 16; u8 *p = data; - int size = 0; + int size = 256; - if (num_ports != 1) { + if (num_ports != 1 || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } switch (section) { case OPA_VLARB_LOW_ELEMENTS: - size = fm_get_table(ppd, FM_TBL_VL_LOW_ARB, p); + fm_get_table(ppd, FM_TBL_VL_LOW_ARB, p); break; case OPA_VLARB_HIGH_ELEMENTS: - size = fm_get_table(ppd, FM_TBL_VL_HIGH_ARB, p); + fm_get_table(ppd, FM_TBL_VL_HIGH_ARB, p); break; case OPA_VLARB_PREEMPT_ELEMENTS: - size = fm_get_table(ppd, FM_TBL_VL_PREEMPT_ELEMS, p); + fm_get_table(ppd, FM_TBL_VL_PREEMPT_ELEMS, p); break; case OPA_VLARB_PREEMPT_MATRIX: - size = fm_get_table(ppd, FM_TBL_VL_PREEMPT_MATRIX, p); + fm_get_table(ppd, FM_TBL_VL_PREEMPT_MATRIX, p); break; default: pr_warn("OPA SubnGet(VL Arb) AM Invalid : 0x%x\n", be32_to_cpu(smp->attr_mod)); smp->status |= IB_SMP_INVALID_FIELD; + size = 0; break; } @@ -1951,14 +2183,15 @@ static int __subn_get_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_pportdata *ppd = ppd_from_ibp(to_iport(ibdev, port)); u32 num_ports = OPA_AM_NPORT(am); u8 section = (am & 0x00ff0000) >> 16; u8 *p = data; + int size = 256; - if (num_ports != 1) { + if (num_ports != 1 || smp_length_check(size, max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -1986,7 +2219,8 @@ static int __subn_set_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data, break; } - return __subn_get_opa_vl_arb(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_vl_arb(smp, am, data, ibdev, port, resp_len, + max_len); } struct opa_pma_mad { @@ -3282,13 +3516,18 @@ struct opa_congestion_info_attr { static int __subn_get_opa_cong_info(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct opa_congestion_info_attr *p = (struct opa_congestion_info_attr *)data; struct hfi1_ibport *ibp = to_iport(ibdev, port); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); + if (smp_length_check(sizeof(*p), max_len)) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + p->congestion_info = 0; p->control_table_cap = ppd->cc_max_table_entries; p->congestion_log_length = OPA_CONG_LOG_ELEMS; @@ -3301,7 +3540,7 @@ static int __subn_get_opa_cong_info(struct opa_smp *smp, u32 am, u8 *data, static int __subn_get_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, - u8 port, u32 *resp_len) + u8 port, u32 *resp_len, u32 max_len) { int i; struct opa_congestion_setting_attr *p = @@ -3311,6 +3550,11 @@ static int __subn_get_opa_cong_setting(struct opa_smp *smp, u32 am, struct opa_congestion_setting_entry_shadow *entries; struct cc_state *cc_state; + if (smp_length_check(sizeof(*p), max_len)) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + rcu_read_lock(); cc_state = get_cc_state(ppd); @@ -3385,7 +3629,7 @@ static void apply_cc_state(struct hfi1_pportdata *ppd) static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct opa_congestion_setting_attr *p = (struct opa_congestion_setting_attr *)data; @@ -3394,6 +3638,11 @@ static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, struct opa_congestion_setting_entry_shadow *entries; int i; + if (smp_length_check(sizeof(*p), max_len)) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + /* * Save details from packet into the ppd. Hold the cc_state_lock so * our information is consistent with anyone trying to apply the state. @@ -3415,12 +3664,12 @@ static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, apply_cc_state(ppd); return __subn_get_opa_cong_setting(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); } static int __subn_get_opa_hfi1_cong_log(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, - u8 port, u32 *resp_len) + u8 port, u32 *resp_len, u32 max_len) { struct hfi1_ibport *ibp = to_iport(ibdev, port); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); @@ -3428,7 +3677,7 @@ static int __subn_get_opa_hfi1_cong_log(struct opa_smp *smp, u32 am, s64 ts; int i; - if (am != 0) { + if (am || smp_length_check(sizeof(*cong_log), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -3486,7 +3735,7 @@ static int __subn_get_opa_hfi1_cong_log(struct opa_smp *smp, u32 am, static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct ib_cc_table_attr *cc_table_attr = (struct ib_cc_table_attr *)data; @@ -3498,9 +3747,10 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, int i, j; u32 sentry, eentry; struct cc_state *cc_state; + u32 size = sizeof(u16) * (IB_CCT_ENTRIES * n_blocks + 1); /* sanity check n_blocks, start_block */ - if (n_blocks == 0 || + if (n_blocks == 0 || smp_length_check(size, max_len) || start_block + n_blocks > ppd->cc_max_table_entries) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); @@ -3530,14 +3780,14 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, rcu_read_unlock(); if (resp_len) - *resp_len += sizeof(u16) * (IB_CCT_ENTRIES * n_blocks + 1); + *resp_len += size; return reply((struct ib_mad_hdr *)smp); } static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct ib_cc_table_attr *p = (struct ib_cc_table_attr *)data; struct hfi1_ibport *ibp = to_iport(ibdev, port); @@ -3548,9 +3798,10 @@ static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, int i, j; u32 sentry, eentry; u16 ccti_limit; + u32 size = sizeof(u16) * (IB_CCT_ENTRIES * n_blocks + 1); /* sanity check n_blocks, start_block */ - if (n_blocks == 0 || + if (n_blocks == 0 || smp_length_check(size, max_len) || start_block + n_blocks > ppd->cc_max_table_entries) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); @@ -3581,7 +3832,8 @@ static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, /* now apply the information */ apply_cc_state(ppd); - return __subn_get_opa_cc_table(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_cc_table(smp, am, data, ibdev, port, resp_len, + max_len); } struct opa_led_info { @@ -3594,7 +3846,7 @@ struct opa_led_info { static int __subn_get_opa_led_info(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_devdata *dd = dd_from_ibdev(ibdev); struct hfi1_pportdata *ppd = dd->pport; @@ -3602,7 +3854,7 @@ static int __subn_get_opa_led_info(struct opa_smp *smp, u32 am, u8 *data, u32 nport = OPA_AM_NPORT(am); u32 is_beaconing_active; - if (nport != 1) { + if (nport != 1 || smp_length_check(sizeof(*p), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -3624,14 +3876,14 @@ static int __subn_get_opa_led_info(struct opa_smp *smp, u32 am, u8 *data, static int __subn_set_opa_led_info(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { struct hfi1_devdata *dd = dd_from_ibdev(ibdev); struct opa_led_info *p = (struct opa_led_info *)data; u32 nport = OPA_AM_NPORT(am); int on = !!(be32_to_cpu(p->rsvd_led_mask) & OPA_LED_MASK); - if (nport != 1) { + if (nport != 1 || smp_length_check(sizeof(*p), max_len)) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } @@ -3641,12 +3893,13 @@ static int __subn_set_opa_led_info(struct opa_smp *smp, u32 am, u8 *data, else shutdown_led_override(dd->pport); - return __subn_get_opa_led_info(smp, am, data, ibdev, port, resp_len); + return __subn_get_opa_led_info(smp, am, data, ibdev, port, resp_len, + max_len); } static int subn_get_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { int ret; struct hfi1_ibport *ibp = to_iport(ibdev, port); @@ -3654,71 +3907,71 @@ static int subn_get_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am, switch (attr_id) { case IB_SMP_ATTR_NODE_DESC: ret = __subn_get_opa_nodedesc(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_NODE_INFO: ret = __subn_get_opa_nodeinfo(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_PORT_INFO: ret = __subn_get_opa_portinfo(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_PKEY_TABLE: ret = __subn_get_opa_pkeytable(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SL_TO_SC_MAP: ret = __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SC_TO_SL_MAP: ret = __subn_get_opa_sc_to_sl(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SC_TO_VLT_MAP: ret = __subn_get_opa_sc_to_vlt(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SC_TO_VLNT_MAP: ret = __subn_get_opa_sc_to_vlnt(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_PORT_STATE_INFO: ret = __subn_get_opa_psi(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_BUFFER_CONTROL_TABLE: ret = __subn_get_opa_bct(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_CABLE_INFO: ret = __subn_get_opa_cable_info(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_VL_ARB_TABLE: ret = __subn_get_opa_vl_arb(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_CONGESTION_INFO: ret = __subn_get_opa_cong_info(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_HFI_CONGESTION_SETTING: ret = __subn_get_opa_cong_setting(smp, am, data, ibdev, - port, resp_len); + port, resp_len, max_len); break; case OPA_ATTRIB_ID_HFI_CONGESTION_LOG: ret = __subn_get_opa_hfi1_cong_log(smp, am, data, ibdev, - port, resp_len); + port, resp_len, max_len); break; case OPA_ATTRIB_ID_CONGESTION_CONTROL_TABLE: ret = __subn_get_opa_cc_table(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_LED_INFO: ret = __subn_get_opa_led_info(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_SM_INFO: if (ibp->rvp.port_cap_flags & IB_PORT_SM_DISABLED) @@ -3736,7 +3989,7 @@ static int subn_get_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am, static int subn_set_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, - u32 *resp_len) + u32 *resp_len, u32 max_len) { int ret; struct hfi1_ibport *ibp = to_iport(ibdev, port); @@ -3744,51 +3997,51 @@ static int subn_set_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am, switch (attr_id) { case IB_SMP_ATTR_PORT_INFO: ret = __subn_set_opa_portinfo(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_PKEY_TABLE: ret = __subn_set_opa_pkeytable(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SL_TO_SC_MAP: ret = __subn_set_opa_sl_to_sc(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SC_TO_SL_MAP: ret = __subn_set_opa_sc_to_sl(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SC_TO_VLT_MAP: ret = __subn_set_opa_sc_to_vlt(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_SC_TO_VLNT_MAP: ret = __subn_set_opa_sc_to_vlnt(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_PORT_STATE_INFO: ret = __subn_set_opa_psi(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_BUFFER_CONTROL_TABLE: ret = __subn_set_opa_bct(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_VL_ARB_TABLE: ret = __subn_set_opa_vl_arb(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case OPA_ATTRIB_ID_HFI_CONGESTION_SETTING: ret = __subn_set_opa_cong_setting(smp, am, data, ibdev, - port, resp_len); + port, resp_len, max_len); break; case OPA_ATTRIB_ID_CONGESTION_CONTROL_TABLE: ret = __subn_set_opa_cc_table(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_LED_INFO: ret = __subn_set_opa_led_info(smp, am, data, ibdev, port, - resp_len); + resp_len, max_len); break; case IB_SMP_ATTR_SM_INFO: if (ibp->rvp.port_cap_flags & IB_PORT_SM_DISABLED) @@ -3844,7 +4097,10 @@ static int subn_get_opa_aggregate(struct opa_smp *smp, memset(next_smp + sizeof(*agg), 0, agg_data_len); (void)subn_get_opa_sma(agg->attr_id, smp, am, agg->data, - ibdev, port, NULL); + ibdev, port, NULL, (u32)agg_data_len); + + if (smp->status & IB_SMP_INVALID_FIELD) + break; if (smp->status & ~IB_SMP_DIRECTION) { set_aggr_error(agg); return reply((struct ib_mad_hdr *)smp); @@ -3887,7 +4143,9 @@ static int subn_set_opa_aggregate(struct opa_smp *smp, } (void)subn_set_opa_sma(agg->attr_id, smp, am, agg->data, - ibdev, port, NULL); + ibdev, port, NULL, (u32)agg_data_len); + if (smp->status & IB_SMP_INVALID_FIELD) + break; if (smp->status & ~IB_SMP_DIRECTION) { set_aggr_error(agg); return reply((struct ib_mad_hdr *)smp); @@ -3958,7 +4216,7 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp, const struct ib_wc *in_wc) { struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - u16 slid = in_wc->slid; + u16 slid = ib_slid_cpu16(in_wc->slid); u16 pkey; if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys)) @@ -3997,12 +4255,13 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags, struct opa_smp *smp = (struct opa_smp *)out_mad; struct hfi1_ibport *ibp = to_iport(ibdev, port); u8 *data; - u32 am; + u32 am, data_size; __be16 attr_id; int ret; *out_mad = *in_mad; data = opa_get_smp_data(smp); + data_size = (u32)opa_get_smp_data_size(smp); am = be32_to_cpu(smp->attr_mod); attr_id = smp->attr_id; @@ -4046,7 +4305,8 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags, default: clear_opa_smp_data(smp); ret = subn_get_opa_sma(attr_id, smp, am, data, - ibdev, port, resp_len); + ibdev, port, resp_len, + data_size); break; case OPA_ATTRIB_ID_AGGREGATE: ret = subn_get_opa_aggregate(smp, ibdev, port, @@ -4058,7 +4318,8 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags, switch (attr_id) { default: ret = subn_set_opa_sma(attr_id, smp, am, data, - ibdev, port, resp_len); + ibdev, port, resp_len, + data_size); break; case OPA_ATTRIB_ID_AGGREGATE: ret = subn_set_opa_aggregate(smp, ibdev, port, @@ -4077,6 +4338,11 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags, */ ret = IB_MAD_RESULT_SUCCESS; break; + case IB_MGMT_METHOD_TRAP_REPRESS: + subn_handle_opa_trap_repress(ibp, smp); + /* Always successful */ + ret = IB_MAD_RESULT_SUCCESS; + break; default: smp->status |= IB_SMP_UNSUP_METHOD; ret = reply((struct ib_mad_hdr *)smp); diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h index 5aa3fd1be653..4c1245072093 100644 --- a/drivers/infiniband/hw/hfi1/mad.h +++ b/drivers/infiniband/hw/hfi1/mad.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -115,7 +115,7 @@ struct opa_mad_notice_attr { __be32 lid; /* LID where change occurred */ __be32 new_cap_mask; /* new capability mask */ __be16 reserved2; - __be16 cap_mask; + __be16 cap_mask3; __be16 change_flags; /* low 4 bits only */ } __packed ntc_144; @@ -428,5 +428,6 @@ struct sc2vlnt { COUNTER_MASK(1, 4)) void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port); +void hfi1_handle_trap_timer(unsigned long data); #endif /* _HFI1_MAD_H */ diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index ccbf52c8ff6f..d41fd87a39f2 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -217,21 +217,27 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, return node; } -struct mmu_rb_node *hfi1_mmu_rb_extract(struct mmu_rb_handler *handler, - unsigned long addr, unsigned long len) +bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, + unsigned long addr, unsigned long len, + struct mmu_rb_node **rb_node) { struct mmu_rb_node *node; unsigned long flags; + bool ret = false; spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, addr, len); if (node) { + if (node->addr == addr && node->len == len) + goto unlock; __mmu_int_rb_remove(node, &handler->root); list_del(&node->list); /* remove from LRU list */ + ret = true; } +unlock: spin_unlock_irqrestore(&handler->lock, flags); - - return node; + *rb_node = node; + return ret; } void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index 754f6ebf13fb..f04cec1e99d1 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -81,7 +81,8 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg); void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, struct mmu_rb_node *mnode); -struct mmu_rb_node *hfi1_mmu_rb_extract(struct mmu_rb_handler *handler, - unsigned long addr, unsigned long len); +bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, + unsigned long addr, unsigned long len, + struct mmu_rb_node **rb_node); #endif /* _HFI1_MMU_RB_H */ diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 6a9f6f9819e1..82447b7cdda1 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -68,7 +68,7 @@ /* * Code to adjust PCIe capabilities. */ -static void tune_pcie_caps(struct hfi1_devdata *); +static int tune_pcie_caps(struct hfi1_devdata *); /* * Do all the common PCIe setup and initialization. @@ -161,6 +161,7 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev) { unsigned long len; resource_size_t addr; + int ret = 0; dd->pcidev = pdev; pci_set_drvdata(pdev, dd); @@ -179,47 +180,54 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev) return -EINVAL; } - dd->kregbase = ioremap_nocache(addr, TXE_PIO_SEND); - if (!dd->kregbase) + dd->kregbase1 = ioremap_nocache(addr, RCV_ARRAY); + if (!dd->kregbase1) { + dd_dev_err(dd, "UC mapping of kregbase1 failed\n"); return -ENOMEM; + } + dd_dev_info(dd, "UC base1: %p for %x\n", dd->kregbase1, RCV_ARRAY); + dd->chip_rcv_array_count = readq(dd->kregbase1 + RCV_ARRAY_CNT); + dd_dev_info(dd, "RcvArray count: %u\n", dd->chip_rcv_array_count); + dd->base2_start = RCV_ARRAY + dd->chip_rcv_array_count * 8; + + dd->kregbase2 = ioremap_nocache( + addr + dd->base2_start, + TXE_PIO_SEND - dd->base2_start); + if (!dd->kregbase2) { + dd_dev_err(dd, "UC mapping of kregbase2 failed\n"); + goto nomem; + } + dd_dev_info(dd, "UC base2: %p for %x\n", dd->kregbase2, + TXE_PIO_SEND - dd->base2_start); dd->piobase = ioremap_wc(addr + TXE_PIO_SEND, TXE_PIO_SIZE); if (!dd->piobase) { - iounmap(dd->kregbase); - return -ENOMEM; + dd_dev_err(dd, "WC mapping of send buffers failed\n"); + goto nomem; } + dd_dev_info(dd, "WC piobase: %p\n for %x", dd->piobase, TXE_PIO_SIZE); - dd->flags |= HFI1_PRESENT; /* now register routines work */ - - dd->kregend = dd->kregbase + TXE_PIO_SEND; dd->physaddr = addr; /* used for io_remap, etc. */ /* - * Re-map the chip's RcvArray as write-combining to allow us + * Map the chip's RcvArray as write-combining to allow us * to write an entire cacheline worth of entries in one shot. - * If this re-map fails, just continue - the RcvArray programming - * function will handle both cases. */ - dd->chip_rcv_array_count = read_csr(dd, RCV_ARRAY_CNT); dd->rcvarray_wc = ioremap_wc(addr + RCV_ARRAY, dd->chip_rcv_array_count * 8); - dd_dev_info(dd, "WC Remapped RcvArray: %p\n", dd->rcvarray_wc); - /* - * Save BARs and command to rewrite after device reset. - */ - pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, &dd->pcibar0); - pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, &dd->pcibar1); - pci_read_config_dword(dd->pcidev, PCI_ROM_ADDRESS, &dd->pci_rom); - pci_read_config_word(dd->pcidev, PCI_COMMAND, &dd->pci_command); - pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &dd->pcie_devctl); - pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL, &dd->pcie_lnkctl); - pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL2, - &dd->pcie_devctl2); - pci_read_config_dword(dd->pcidev, PCI_CFG_MSIX0, &dd->pci_msix0); - pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, &dd->pci_lnkctl3); - pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2); + if (!dd->rcvarray_wc) { + dd_dev_err(dd, "WC mapping of receive array failed\n"); + goto nomem; + } + dd_dev_info(dd, "WC RcvArray: %p for %x\n", + dd->rcvarray_wc, dd->chip_rcv_array_count * 8); + dd->flags |= HFI1_PRESENT; /* chip.c CSR routines now work */ return 0; +nomem: + ret = -ENOMEM; + hfi1_pcie_ddcleanup(dd); + return ret; } /* @@ -229,59 +237,19 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev) */ void hfi1_pcie_ddcleanup(struct hfi1_devdata *dd) { - u64 __iomem *base = (void __iomem *)dd->kregbase; - dd->flags &= ~HFI1_PRESENT; - dd->kregbase = NULL; - iounmap(base); + if (dd->kregbase1) + iounmap(dd->kregbase1); + dd->kregbase1 = NULL; + if (dd->kregbase2) + iounmap(dd->kregbase2); + dd->kregbase2 = NULL; if (dd->rcvarray_wc) iounmap(dd->rcvarray_wc); + dd->rcvarray_wc = NULL; if (dd->piobase) iounmap(dd->piobase); -} - -static void msix_setup(struct hfi1_devdata *dd, int pos, u32 *msixcnt, - struct hfi1_msix_entry *hfi1_msix_entry) -{ - int ret; - int nvec = *msixcnt; - struct msix_entry *msix_entry; - int i; - - /* - * We can't pass hfi1_msix_entry array to msix_setup - * so use a dummy msix_entry array and copy the allocated - * irq back to the hfi1_msix_entry array. - */ - msix_entry = kmalloc_array(nvec, sizeof(*msix_entry), GFP_KERNEL); - if (!msix_entry) { - ret = -ENOMEM; - goto do_intx; - } - - for (i = 0; i < nvec; i++) - msix_entry[i] = hfi1_msix_entry[i].msix; - - ret = pci_enable_msix_range(dd->pcidev, msix_entry, 1, nvec); - if (ret < 0) - goto free_msix_entry; - nvec = ret; - - for (i = 0; i < nvec; i++) - hfi1_msix_entry[i].msix = msix_entry[i]; - - kfree(msix_entry); - *msixcnt = nvec; - return; - -free_msix_entry: - kfree(msix_entry); - -do_intx: - dd_dev_err(dd, "pci_enable_msix_range %d vectors failed: %d, falling back to INTx\n", - nvec, ret); - *msixcnt = 0; - hfi1_enable_intx(dd->pcidev); + dd->piobase = NULL; } /* return the PCIe link speed from the given link status */ @@ -314,8 +282,14 @@ static u32 extract_width(u16 linkstat) static void update_lbus_info(struct hfi1_devdata *dd) { u16 linkstat; + int ret; + + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + return; + } - pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat); dd->lbus_width = extract_width(linkstat); dd->lbus_speed = extract_speed(linkstat); snprintf(dd->lbus_info, sizeof(dd->lbus_info), @@ -330,6 +304,7 @@ int pcie_speeds(struct hfi1_devdata *dd) { u32 linkcap; struct pci_dev *parent = dd->pcidev->bus->self; + int ret; if (!pci_is_pcie(dd->pcidev)) { dd_dev_err(dd, "Can't find PCI Express capability!\n"); @@ -339,7 +314,12 @@ int pcie_speeds(struct hfi1_devdata *dd) /* find if our max speed is Gen3 and parent supports Gen3 speeds */ dd->link_gen3_capable = 1; - pcie_capability_read_dword(dd->pcidev, PCI_EXP_LNKCAP, &linkcap); + ret = pcie_capability_read_dword(dd->pcidev, PCI_EXP_LNKCAP, &linkcap); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + return ret; + } + if ((linkcap & PCI_EXP_LNKCAP_SLS) != GEN3_SPEED_VECTOR) { dd_dev_info(dd, "This HFI is not Gen3 capable, max speed 0x%x, need 0x3\n", @@ -364,49 +344,150 @@ int pcie_speeds(struct hfi1_devdata *dd) } /* - * Returns in *nent: - * - actual number of interrupts allocated + * Returns: + * - actual number of interrupts allocated or * - 0 if fell back to INTx. + * - error */ -void request_msix(struct hfi1_devdata *dd, u32 *nent, - struct hfi1_msix_entry *entry) +int request_msix(struct hfi1_devdata *dd, u32 msireq) { - int pos; + int nvec, ret; - pos = dd->pcidev->msix_cap; - if (*nent && pos) { - msix_setup(dd, pos, nent, entry); - /* did it, either MSI-X or INTx */ - } else { - *nent = 0; - hfi1_enable_intx(dd->pcidev); + nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq, + PCI_IRQ_MSIX | PCI_IRQ_LEGACY); + if (nvec < 0) { + dd_dev_err(dd, "pci_alloc_irq_vectors() failed: %d\n", nvec); + return nvec; } - tune_pcie_caps(dd); + ret = tune_pcie_caps(dd); + if (ret) { + dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret); + pci_free_irq_vectors(dd->pcidev); + return ret; + } + + /* check for legacy IRQ */ + if (nvec == 1 && !dd->pcidev->msix_enabled) + return 0; + + return nvec; } -void hfi1_enable_intx(struct pci_dev *pdev) +/* restore command and BARs after a reset has wiped them out */ +int restore_pci_variables(struct hfi1_devdata *dd) { - /* first, turn on INTx */ - pci_intx(pdev, 1); - /* then turn off MSI-X */ - pci_disable_msix(pdev); + int ret = 0; + + ret = pci_write_config_word(dd->pcidev, PCI_COMMAND, dd->pci_command); + if (ret) + goto error; + + ret = pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, + dd->pcibar0); + if (ret) + goto error; + + ret = pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, + dd->pcibar1); + if (ret) + goto error; + + ret = pci_write_config_dword(dd->pcidev, PCI_ROM_ADDRESS, dd->pci_rom); + if (ret) + goto error; + + ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, + dd->pcie_devctl); + if (ret) + goto error; + + ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL, + dd->pcie_lnkctl); + if (ret) + goto error; + + ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL2, + dd->pcie_devctl2); + if (ret) + goto error; + + ret = pci_write_config_dword(dd->pcidev, PCI_CFG_MSIX0, dd->pci_msix0); + if (ret) + goto error; + + ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, + dd->pci_lnkctl3); + if (ret) + goto error; + + ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2); + if (ret) + goto error; + + return 0; + +error: + dd_dev_err(dd, "Unable to write to PCI config\n"); + return ret; } -/* restore command and BARs after a reset has wiped them out */ -void restore_pci_variables(struct hfi1_devdata *dd) +/* Save BARs and command to rewrite after device reset */ +int save_pci_variables(struct hfi1_devdata *dd) { - pci_write_config_word(dd->pcidev, PCI_COMMAND, dd->pci_command); - pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, dd->pcibar0); - pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, dd->pcibar1); - pci_write_config_dword(dd->pcidev, PCI_ROM_ADDRESS, dd->pci_rom); - pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, dd->pcie_devctl); - pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL, dd->pcie_lnkctl); - pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL2, - dd->pcie_devctl2); - pci_write_config_dword(dd->pcidev, PCI_CFG_MSIX0, dd->pci_msix0); - pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, dd->pci_lnkctl3); - pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2); + int ret = 0; + + ret = pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, + &dd->pcibar0); + if (ret) + goto error; + + ret = pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, + &dd->pcibar1); + if (ret) + goto error; + + ret = pci_read_config_dword(dd->pcidev, PCI_ROM_ADDRESS, &dd->pci_rom); + if (ret) + goto error; + + ret = pci_read_config_word(dd->pcidev, PCI_COMMAND, &dd->pci_command); + if (ret) + goto error; + + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, + &dd->pcie_devctl); + if (ret) + goto error; + + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL, + &dd->pcie_lnkctl); + if (ret) + goto error; + + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL2, + &dd->pcie_devctl2); + if (ret) + goto error; + + ret = pci_read_config_dword(dd->pcidev, PCI_CFG_MSIX0, &dd->pci_msix0); + if (ret) + goto error; + + ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, + &dd->pci_lnkctl3); + if (ret) + goto error; + + ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2); + if (ret) + goto error; + + return 0; + +error: + dd_dev_err(dd, "Unable to read from PCI config\n"); + return ret; } /* @@ -421,21 +502,33 @@ uint aspm_mode = ASPM_MODE_DISABLED; module_param_named(aspm, aspm_mode, uint, S_IRUGO); MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic"); -static void tune_pcie_caps(struct hfi1_devdata *dd) +static int tune_pcie_caps(struct hfi1_devdata *dd) { struct pci_dev *parent; u16 rc_mpss, rc_mps, ep_mpss, ep_mps; u16 rc_mrrs, ep_mrrs, max_mrrs, ectl; + int ret; /* * Turn on extended tags in DevCtl in case the BIOS has turned it off * to improve WFR SDMA bandwidth */ - pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl); + ret = pcie_capability_read_word(dd->pcidev, + PCI_EXP_DEVCTL, &ectl); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + return ret; + } + if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { dd_dev_info(dd, "Enabling PCIe extended tags\n"); ectl |= PCI_EXP_DEVCTL_EXT_TAG; - pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl); + ret = pcie_capability_write_word(dd->pcidev, + PCI_EXP_DEVCTL, ectl); + if (ret) { + dd_dev_err(dd, "Unable to write to PCI config\n"); + return ret; + } } /* Find out supported and configured values for parent (root) */ parent = dd->pcidev->bus->self; @@ -444,14 +537,14 @@ static void tune_pcie_caps(struct hfi1_devdata *dd) * access to the upstream component. */ if (!parent) - return; + return -EINVAL; if (!pci_is_root_bus(parent->bus)) { dd_dev_info(dd, "Parent not root\n"); - return; + return -EINVAL; } if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev)) - return; + return -EINVAL; rc_mpss = parent->pcie_mpss; rc_mps = ffs(pcie_get_mps(parent)) - 8; /* Find out supported and configured values for endpoint (us) */ @@ -497,6 +590,8 @@ static void tune_pcie_caps(struct hfi1_devdata *dd) ep_mrrs = max_mrrs; pcie_set_readrq(dd->pcidev, ep_mrrs); } + + return 0; } /* End of PCIe capability tuning */ @@ -728,6 +823,7 @@ static int load_eq_table(struct hfi1_devdata *dd, const u8 eq[11][3], u8 fs, u32 violation; u32 i; u8 c_minus1, c0, c_plus1; + int ret; for (i = 0; i < 11; i++) { /* set index */ @@ -739,8 +835,14 @@ static int load_eq_table(struct hfi1_devdata *dd, const u8 eq[11][3], u8 fs, pci_write_config_dword(pdev, PCIE_CFG_REG_PL102, eq_value(c_minus1, c0, c_plus1)); /* check if these coefficients violate EQ rules */ - pci_read_config_dword(dd->pcidev, PCIE_CFG_REG_PL105, - &violation); + ret = pci_read_config_dword(dd->pcidev, + PCIE_CFG_REG_PL105, &violation); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + hit_error = 1; + break; + } + if (violation & PCIE_CFG_REG_PL105_GEN3_EQ_VIOLATE_COEF_RULES_SMASK){ if (hit_error == 0) { @@ -1194,7 +1296,13 @@ retry: * that it is Gen3 capable earlier. */ dd_dev_info(dd, "%s: setting parent target link speed\n", __func__); - pcie_capability_read_word(parent, PCI_EXP_LNKCTL2, &lnkctl2); + ret = pcie_capability_read_word(parent, PCI_EXP_LNKCTL2, &lnkctl2); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + return_error = 1; + goto done; + } + dd_dev_info(dd, "%s: ..old link control2: 0x%x\n", __func__, (u32)lnkctl2); /* only write to parent if target is not as high as ours */ @@ -1203,20 +1311,37 @@ retry: lnkctl2 |= target_vector; dd_dev_info(dd, "%s: ..new link control2: 0x%x\n", __func__, (u32)lnkctl2); - pcie_capability_write_word(parent, PCI_EXP_LNKCTL2, lnkctl2); + ret = pcie_capability_write_word(parent, + PCI_EXP_LNKCTL2, lnkctl2); + if (ret) { + dd_dev_err(dd, "Unable to write to PCI config\n"); + return_error = 1; + goto done; + } } else { dd_dev_info(dd, "%s: ..target speed is OK\n", __func__); } dd_dev_info(dd, "%s: setting target link speed\n", __func__); - pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL2, &lnkctl2); + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL2, &lnkctl2); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + return_error = 1; + goto done; + } + dd_dev_info(dd, "%s: ..old link control2: 0x%x\n", __func__, (u32)lnkctl2); lnkctl2 &= ~LNKCTL2_TARGET_LINK_SPEED_MASK; lnkctl2 |= target_vector; dd_dev_info(dd, "%s: ..new link control2: 0x%x\n", __func__, (u32)lnkctl2); - pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL2, lnkctl2); + ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL2, lnkctl2); + if (ret) { + dd_dev_err(dd, "Unable to write to PCI config\n"); + return_error = 1; + goto done; + } /* step 5h: arm gasket logic */ /* hold DC in reset across the SBR */ @@ -1266,7 +1391,14 @@ retry: /* restore PCI space registers we know were reset */ dd_dev_info(dd, "%s: calling restore_pci_variables\n", __func__); - restore_pci_variables(dd); + ret = restore_pci_variables(dd); + if (ret) { + dd_dev_err(dd, "%s: Could not restore PCI variables\n", + __func__); + return_error = 1; + goto done; + } + /* restore firmware control */ write_csr(dd, MISC_CFG_FW_CTRL, fw_ctrl); @@ -1296,7 +1428,13 @@ retry: setextled(dd, 0); /* check for any per-lane errors */ - pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE2, ®32); + ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE2, ®32); + if (ret) { + dd_dev_err(dd, "Unable to read from PCI config\n"); + return_error = 1; + goto done; + } + dd_dev_info(dd, "%s: per-lane errors: 0x%x\n", __func__, reg32); /* extract status, look for our HFI */ diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index ed72b5aca139..7108a4b5e94c 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -1012,7 +1012,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause) "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n", __func__, sc->sw_index, sc->hw_context, (u32)reg); - queue_work(dd->pport->hfi1_wq, + queue_work(dd->pport->link_wq, &dd->pport->link_bounce_work); break; } @@ -1568,7 +1568,8 @@ static void sc_piobufavail(struct send_context *sc) struct rvt_qp *qp; struct hfi1_qp_priv *priv; unsigned long flags; - unsigned i, n = 0; + uint i, n = 0, max_idx = 0; + u8 max_starved_cnt = 0; if (dd->send_contexts[sc->sw_index].type != SC_KERNEL && dd->send_contexts[sc->sw_index].type != SC_VL15) @@ -1591,6 +1592,7 @@ static void sc_piobufavail(struct send_context *sc) priv = qp->priv; list_del_init(&priv->s_iowait.list); priv->s_iowait.lock = NULL; + iowait_starve_find_max(wait, &max_starved_cnt, n, &max_idx); /* refcount held until actual wake up */ qps[n++] = qp; } @@ -1605,9 +1607,14 @@ static void sc_piobufavail(struct send_context *sc) } write_sequnlock_irqrestore(&dev->iowait_lock, flags); - for (i = 0; i < n; i++) - hfi1_qp_wakeup(qps[i], + /* Wake up the most starved one first */ + if (n) + hfi1_qp_wakeup(qps[max_idx], RVT_S_WAIT_PIO | RVT_S_WAIT_PIO_DRAIN); + for (i = 0; i < n; i++) + if (i != max_idx) + hfi1_qp_wakeup(qps[i], + RVT_S_WAIT_PIO | RVT_S_WAIT_PIO_DRAIN); } /* translate a send credit update to a bit code of reasons */ diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c index 838fe84e285a..5c38a24484ab 100644 --- a/drivers/infiniband/hw/hfi1/platform.c +++ b/drivers/infiniband/hw/hfi1/platform.c @@ -58,8 +58,13 @@ static int validate_scratch_checksum(struct hfi1_devdata *dd) version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT; /* Prevent power on default of all zeroes from passing checksum */ - if (!version) + if (!version) { + dd_dev_err(dd, "%s: Config bitmap uninitialized\n", __func__); + dd_dev_err(dd, + "%s: Please update your BIOS to support active channels\n", + __func__); return 0; + } /* * ASIC scratch 0 only contains the checksum and bitmap version as @@ -84,6 +89,8 @@ static int validate_scratch_checksum(struct hfi1_devdata *dd) if (checksum + temp_scratch == 0xFFFF) return 1; + + dd_dev_err(dd, "%s: Configuration bitmap corrupted\n", __func__); return 0; } @@ -136,7 +143,6 @@ static void save_platform_config_fields(struct hfi1_devdata *dd) void get_platform_config(struct hfi1_devdata *dd) { int ret = 0; - unsigned long size = 0; u8 *temp_platform_config = NULL; u32 esize; @@ -145,11 +151,6 @@ void get_platform_config(struct hfi1_devdata *dd) save_platform_config_fields(dd); return; } - dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n", - __func__); - dd_dev_err(dd, - "%s: Please update your BIOS to support active channels\n", - __func__); } else { ret = eprom_read_platform_config(dd, (void **)&temp_platform_config, @@ -160,15 +161,6 @@ void get_platform_config(struct hfi1_devdata *dd) dd->platform_config.size = esize; return; } - /* fail, try EFI variable */ - - ret = read_hfi1_efi_var(dd, "configuration", &size, - (void **)&temp_platform_config); - if (!ret) { - dd->platform_config.data = temp_platform_config; - dd->platform_config.size = size; - return; - } } dd_dev_err(dd, "%s: Failed to get platform config, falling back to sub-optimal default file\n", @@ -242,7 +234,7 @@ static int qual_power(struct hfi1_pportdata *ppd) if (ppd->offline_disabled_reason == HFI1_ODR_MASK(OPA_LINKDOWN_REASON_POWER_POLICY)) { - dd_dev_info( + dd_dev_err( ppd->dd, "%s: Port disabled due to system power restrictions\n", __func__); @@ -268,7 +260,7 @@ static int qual_bitrate(struct hfi1_pportdata *ppd) if (ppd->offline_disabled_reason == HFI1_ODR_MASK(OPA_LINKDOWN_REASON_LINKSPEED_POLICY)) { - dd_dev_info( + dd_dev_err( ppd->dd, "%s: Cable failed bitrate check, disabling port\n", __func__); @@ -709,15 +701,15 @@ static void apply_tunings( ret = load_8051_config(ppd->dd, DC_HOST_COMM_SETTINGS, GENERAL_CONFIG, config_data); if (ret != HCMD_SUCCESS) - dd_dev_info(ppd->dd, - "%s: Failed set ext device config params\n", - __func__); + dd_dev_err(ppd->dd, + "%s: Failed set ext device config params\n", + __func__); } if (tx_preset_index == OPA_INVALID_INDEX) { if (ppd->port_type == PORT_TYPE_QSFP && limiting_active) - dd_dev_info(ppd->dd, "%s: Invalid Tx preset index\n", - __func__); + dd_dev_err(ppd->dd, "%s: Invalid Tx preset index\n", + __func__); return; } @@ -900,7 +892,7 @@ static int tune_qsfp(struct hfi1_pportdata *ppd, case 0xD: /* fallthrough */ case 0xF: default: - dd_dev_info(ppd->dd, "%s: Unknown/unsupported cable\n", + dd_dev_warn(ppd->dd, "%s: Unknown/unsupported cable\n", __func__); break; } @@ -942,7 +934,7 @@ void tune_serdes(struct hfi1_pportdata *ppd) case PORT_TYPE_DISCONNECTED: ppd->offline_disabled_reason = HFI1_ODR_MASK(OPA_LINKDOWN_REASON_DISCONNECTED); - dd_dev_info(dd, "%s: Port disconnected, disabling port\n", + dd_dev_warn(dd, "%s: Port disconnected, disabling port\n", __func__); goto bail; case PORT_TYPE_FIXED: @@ -1027,7 +1019,7 @@ void tune_serdes(struct hfi1_pportdata *ppd) } break; default: - dd_dev_info(ppd->dd, "%s: Unknown port type\n", __func__); + dd_dev_warn(ppd->dd, "%s: Unknown port type\n", __func__); ppd->port_type = PORT_TYPE_UNKNOWN; tuning_method = OPA_UNKNOWN_TUNING; total_atten = 0; diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 1a7af9f60c13..b801d8469956 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -68,17 +68,12 @@ static int iowait_sleep( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *stx, - unsigned seq); + unsigned int seq, + bool pkts_sent); static void iowait_wakeup(struct iowait *wait, int reason); static void iowait_sdma_drained(struct iowait *wait); static void qp_pio_drain(struct rvt_qp *qp); -static inline unsigned mk_qpn(struct rvt_qpn_table *qpt, - struct rvt_qpn_map *map, unsigned off) -{ - return (map - qpt->map) * RVT_BITS_PER_PAGE + off; -} - const struct rvt_operation_params hfi1_post_parms[RVT_OPERATION_MAX] = { [IB_WR_RDMA_WRITE] = { .length = sizeof(struct ib_rdma_wr), @@ -377,7 +372,8 @@ static int iowait_sleep( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *stx, - unsigned seq) + uint seq, + bool pkts_sent) { struct verbs_txreq *tx = container_of(stx, struct verbs_txreq, txreq); struct rvt_qp *qp; @@ -408,7 +404,8 @@ static int iowait_sleep( ibp->rvp.n_dmawait++; qp->s_flags |= RVT_S_WAIT_DMA_DESC; - list_add_tail(&priv->s_iowait.list, &sde->dmawait); + iowait_queue(pkts_sent, &priv->s_iowait, + &sde->dmawait); priv->s_iowait.lock = &dev->iowait_lock; trace_hfi1_qpsleep(qp, RVT_S_WAIT_DMA_DESC); rvt_get_qp(qp); @@ -607,7 +604,7 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter) wqe = rvt_get_swqe_ptr(qp, qp->s_last); send_context = qp_to_send_context(qp, priv->s_sc); seq_printf(s, - "N %d %s QP %x R %u %s %u %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x (%u %u %u %u %u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d\n", + "N %d %s QP %x R %u %s %u %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x S(%u %u %u %u %u %u %u) R(%u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d\n", iter->n, qp_idle(qp) ? "I" : "B", qp->ibqp.qp_num, @@ -630,6 +627,10 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter) qp->s_last, qp->s_acked, qp->s_cur, qp->s_tail, qp->s_head, qp->s_size, qp->s_avail, + /* ack_queue ring pointers, size */ + qp->s_tail_ack_queue, qp->r_head_ack_queue, + HFI1_MAX_RDMA_ATOMIC, + /* remote QP info */ qp->remote_qpn, rdma_ah_get_dlid(&qp->remote_ah_attr), rdma_ah_get_sl(&qp->remote_ah_attr), diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 1080778a1f7c..baa67bf0772b 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -765,7 +765,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp, ohdr->u.aeth = rvt_compute_aeth(qp); sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&qp->remote_ah_attr)]; /* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */ - pbc_flags |= ((!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT); + pbc_flags |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT); lrh0 |= (sc5 & 0xf) << 12 | (rdma_ah_get_sl(&qp->remote_ah_attr) & 0xf) << 4; hdr.lrh[0] = cpu_to_be16(lrh0); @@ -798,7 +798,8 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp, goto queue_ack; } - trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device), &hdr); + trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device), + &hdr, ib_is_sc5(sc5)); /* write the pbc and data */ ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc, &hdr, hwords); @@ -1009,7 +1010,7 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr) return; } - psn = be32_to_cpu(ohdr->bth[2]); + psn = ib_bth_get_psn(ohdr); reset_sending_psn(qp, psn); /* @@ -1915,17 +1916,16 @@ void process_becn(struct hfi1_pportdata *ppd, u8 sl, u16 rlid, u32 lqpn, void hfi1_rc_rcv(struct hfi1_packet *packet) { struct hfi1_ctxtdata *rcd = packet->rcd; - struct ib_header *hdr = packet->hdr; - u32 rcv_flags = packet->rcv_flags; void *data = packet->ebuf; u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; struct hfi1_ibport *ibp = rcd_to_iport(rcd); struct ib_other_headers *ohdr = packet->ohdr; - u32 bth0, opcode; + u32 bth0; + u32 opcode = packet->opcode; u32 hdrsize = packet->hlen; u32 psn; - u32 pad; + u32 pad = packet->pad; struct ib_wc wc; u32 pmtu = qp->pmtu; int diff; @@ -1937,14 +1937,13 @@ void hfi1_rc_rcv(struct hfi1_packet *packet) u32 rkey; lockdep_assert_held(&qp->r_lock); + bth0 = be32_to_cpu(ohdr->bth[0]); - if (hfi1_ruc_check_hdr(ibp, hdr, rcv_flags & HFI1_HAS_GRH, qp, bth0)) + if (hfi1_ruc_check_hdr(ibp, packet)) return; is_fecn = process_ecn(qp, packet, false); - - psn = be32_to_cpu(ohdr->bth[2]); - opcode = ib_bth_get_opcode(ohdr); + psn = ib_bth_get_psn(ohdr); /* * Process responses (ACKs) before anything else. Note that the @@ -2074,8 +2073,6 @@ no_immediate_data: wc.wc_flags = 0; wc.ex.imm_data = 0; send_last: - /* Get the number of bytes the message was padded by. */ - pad = ib_bth_get_pad(ohdr); /* Check for invalid length. */ /* LAST len should be >= 1 */ if (unlikely(tlen < (hdrsize + pad + 4))) @@ -2368,28 +2365,19 @@ send_ack: void hfi1_rc_hdrerr( struct hfi1_ctxtdata *rcd, - struct ib_header *hdr, - u32 rcv_flags, + struct hfi1_packet *packet, struct rvt_qp *qp) { - int has_grh = rcv_flags & HFI1_HAS_GRH; - struct ib_other_headers *ohdr; struct hfi1_ibport *ibp = rcd_to_iport(rcd); int diff; u32 opcode; - u32 psn, bth0; - - /* Check for GRH */ - ohdr = &hdr->u.oth; - if (has_grh) - ohdr = &hdr->u.l.oth; + u32 psn; - bth0 = be32_to_cpu(ohdr->bth[0]); - if (hfi1_ruc_check_hdr(ibp, hdr, has_grh, qp, bth0)) + if (hfi1_ruc_check_hdr(ibp, packet)) return; - psn = be32_to_cpu(ohdr->bth[2]); - opcode = ib_bth_get_opcode(ohdr); + psn = ib_bth_get_psn(packet->ohdr); + opcode = ib_bth_get_opcode(packet->ohdr); /* Only deal with RDMA Writes for now */ if (opcode < IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST) { diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c index 3a17daba28a9..4afa00f921f2 100644 --- a/drivers/infiniband/hw/hfi1/ruc.c +++ b/drivers/infiniband/hw/hfi1/ruc.c @@ -74,8 +74,10 @@ static int init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe) if (wqe->sg_list[i].length == 0) continue; /* Check LKEY */ - if (!rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge, - &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE)) + ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge, + NULL, &wqe->sg_list[i], + IB_ACCESS_LOCAL_WRITE); + if (unlikely(ret <= 0)) goto bad_lkey; qp->r_len += wqe->sg_list[i].length; j++; @@ -214,100 +216,95 @@ static int gid_ok(union ib_gid *gid, __be64 gid_prefix, __be64 id) * * The s_lock will be acquired around the hfi1_migrate_qp() call. */ -int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct ib_header *hdr, - int has_grh, struct rvt_qp *qp, u32 bth0) +int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet) { __be64 guid; unsigned long flags; + struct rvt_qp *qp = packet->qp; u8 sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&qp->remote_ah_attr)]; - - if (qp->s_mig_state == IB_MIG_ARMED && (bth0 & IB_BTH_MIG_REQ)) { - if (!has_grh) { + u32 dlid = packet->dlid; + u32 slid = packet->slid; + u32 sl = packet->sl; + int migrated; + u32 bth0, bth1; + + bth0 = be32_to_cpu(packet->ohdr->bth[0]); + bth1 = be32_to_cpu(packet->ohdr->bth[1]); + migrated = bth0 & IB_BTH_MIG_REQ; + + if (qp->s_mig_state == IB_MIG_ARMED && migrated) { + if (!packet->grh) { if (rdma_ah_get_ah_flags(&qp->alt_ah_attr) & IB_AH_GRH) - goto err; + return 1; } else { const struct ib_global_route *grh; if (!(rdma_ah_get_ah_flags(&qp->alt_ah_attr) & IB_AH_GRH)) - goto err; + return 1; grh = rdma_ah_read_grh(&qp->alt_ah_attr); guid = get_sguid(ibp, grh->sgid_index); - if (!gid_ok(&hdr->u.l.grh.dgid, ibp->rvp.gid_prefix, + if (!gid_ok(&packet->grh->dgid, ibp->rvp.gid_prefix, guid)) - goto err; + return 1; if (!gid_ok( - &hdr->u.l.grh.sgid, + &packet->grh->sgid, grh->dgid.global.subnet_prefix, grh->dgid.global.interface_id)) - goto err; + return 1; } - if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, sc5, - ib_get_slid(hdr)))) { - hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY, - (u16)bth0, - ib_get_sl(hdr), - 0, qp->ibqp.qp_num, - ib_get_slid(hdr), - ib_get_dlid(hdr)); - goto err; + if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, + sc5, slid))) { + hfi1_bad_pkey(ibp, (u16)bth0, sl, + 0, qp->ibqp.qp_num, slid, dlid); + return 1; } /* Validate the SLID. See Ch. 9.6.1.5 and 17.2.8 */ - if (ib_get_slid(hdr) != - rdma_ah_get_dlid(&qp->alt_ah_attr) || + if (slid != rdma_ah_get_dlid(&qp->alt_ah_attr) || ppd_from_ibp(ibp)->port != rdma_ah_get_port_num(&qp->alt_ah_attr)) - goto err; + return 1; spin_lock_irqsave(&qp->s_lock, flags); hfi1_migrate_qp(qp); spin_unlock_irqrestore(&qp->s_lock, flags); } else { - if (!has_grh) { + if (!packet->grh) { if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) - goto err; + return 1; } else { const struct ib_global_route *grh; if (!(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) - goto err; + return 1; grh = rdma_ah_read_grh(&qp->remote_ah_attr); guid = get_sguid(ibp, grh->sgid_index); - if (!gid_ok(&hdr->u.l.grh.dgid, ibp->rvp.gid_prefix, + if (!gid_ok(&packet->grh->dgid, ibp->rvp.gid_prefix, guid)) - goto err; + return 1; if (!gid_ok( - &hdr->u.l.grh.sgid, + &packet->grh->sgid, grh->dgid.global.subnet_prefix, grh->dgid.global.interface_id)) - goto err; + return 1; } - if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, sc5, - ib_get_slid(hdr)))) { - hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY, - (u16)bth0, - ib_get_sl(hdr), - 0, qp->ibqp.qp_num, - ib_get_slid(hdr), - ib_get_dlid(hdr)); - goto err; + if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, + sc5, slid))) { + hfi1_bad_pkey(ibp, (u16)bth0, sl, + 0, qp->ibqp.qp_num, slid, dlid); + return 1; } /* Validate the SLID. See Ch. 9.6.1.5 */ - if (ib_get_slid(hdr) != - rdma_ah_get_dlid(&qp->remote_ah_attr) || + if ((slid != rdma_ah_get_dlid(&qp->remote_ah_attr)) || ppd_from_ibp(ibp)->port != qp->port_num) - goto err; - if (qp->s_mig_state == IB_MIG_REARM && - !(bth0 & IB_BTH_MIG_REQ)) + return 1; + if (qp->s_mig_state == IB_MIG_REARM && !migrated) qp->s_mig_state = IB_MIG_ARMED; } return 0; - -err: - return 1; } /** @@ -816,6 +813,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr, static bool schedule_send_yield(struct rvt_qp *qp, struct hfi1_pkt_state *ps) { + ps->pkts_sent = true; + if (unlikely(time_after(jiffies, ps->timeout))) { if (!ps->in_thread || workqueue_congested(ps->cpu, ps->ppd->hfi1_wq)) { @@ -912,6 +911,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread) ps.timeout = jiffies + ps.timeout_int; ps.cpu = priv->s_sde ? priv->s_sde->cpu : cpumask_first(cpumask_of_node(ps.ppd->dd->node)); + ps.pkts_sent = false; /* insure a pre-built packet is handled */ ps.s_txreq = get_waiting_verbs_txreq(qp); @@ -934,7 +934,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread) spin_lock_irqsave(&qp->s_lock, ps.flags); } } while (make_req(qp, &ps)); - + iowait_starve_clear(ps.pkts_sent, &priv->s_iowait); spin_unlock_irqrestore(&qp->s_lock, ps.flags); } diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index bfd0d5187e9b..6781bcdb10b3 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -246,7 +246,7 @@ static void __sdma_process_event( enum sdma_events event); static void dump_sdma_state(struct sdma_engine *sde); static void sdma_make_progress(struct sdma_engine *sde, u64 status); -static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail); +static void sdma_desc_avail(struct sdma_engine *sde, uint avail); static void sdma_flush_descq(struct sdma_engine *sde); /** @@ -325,7 +325,7 @@ static void sdma_wait_for_packet_egress(struct sdma_engine *sde, /* timed out - bounce the link */ dd_dev_err(dd, "%s: engine %u timeout waiting for packets to egress, remaining count %u, bouncing link\n", __func__, sde->this_idx, (u32)reg); - queue_work(dd->pport->hfi1_wq, + queue_work(dd->pport->link_wq, &dd->pport->link_bounce_work); break; } @@ -1340,10 +1340,8 @@ static void sdma_clean(struct hfi1_devdata *dd, size_t num_engines) * @dd: hfi1_devdata * @port: port number (currently only zero) * - * sdma_init initializes the specified number of engines. - * - * The code initializes each sde, its csrs. Interrupts - * are not required to be enabled. + * Initializes each sde and its csrs. + * Interrupts are not required to be enabled. * * Returns: * 0 - success, -errno on failure @@ -1764,13 +1762,14 @@ retry: * * This is called with head_lock held. */ -static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail) +static void sdma_desc_avail(struct sdma_engine *sde, uint avail) { struct iowait *wait, *nw; struct iowait *waits[SDMA_WAIT_BATCH_SIZE]; - unsigned i, n = 0, seq; + uint i, n = 0, seq, max_idx = 0; struct sdma_txreq *stx; struct hfi1_ibdev *dev = &sde->dd->verbs_dev; + u8 max_starved_cnt = 0; #ifdef CONFIG_SDMA_VERBOSITY dd_dev_err(sde->dd, "CONFIG SDMA(%u) %s:%d %s()\n", sde->this_idx, @@ -1805,6 +1804,9 @@ static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail) if (num_desc > avail) break; avail -= num_desc; + /* Find the most starved wait memeber */ + iowait_starve_find_max(wait, &max_starved_cnt, + n, &max_idx); list_del_init(&wait->list); waits[n++] = wait; } @@ -1813,8 +1815,13 @@ static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail) } } while (read_seqretry(&dev->iowait_lock, seq)); + /* Schedule the most starved one first */ + if (n) + waits[max_idx]->wakeup(waits[max_idx], SDMA_AVAIL_REASON); + for (i = 0; i < n; i++) - waits[i]->wakeup(waits[i], SDMA_AVAIL_REASON); + if (i != max_idx) + waits[i]->wakeup(waits[i], SDMA_AVAIL_REASON); } /* head_lock must be held */ @@ -2351,7 +2358,8 @@ static inline u16 submit_tx(struct sdma_engine *sde, struct sdma_txreq *tx) static int sdma_check_progress( struct sdma_engine *sde, struct iowait *wait, - struct sdma_txreq *tx) + struct sdma_txreq *tx, + bool pkts_sent) { int ret; @@ -2364,7 +2372,7 @@ static int sdma_check_progress( seq = raw_seqcount_begin( (const seqcount_t *)&sde->head_lock.seqcount); - ret = wait->sleep(sde, wait, tx, seq); + ret = wait->sleep(sde, wait, tx, seq, pkts_sent); if (ret == -EAGAIN) sde->desc_avail = sdma_descq_freecnt(sde); } else { @@ -2378,6 +2386,7 @@ static int sdma_check_progress( * @sde: sdma engine to use * @wait: wait structure to use when full (may be NULL) * @tx: sdma_txreq to submit + * @pkts_sent: has any packet been sent yet? * * The call submits the tx into the ring. If a iowait structure is non-NULL * the packet will be queued to the list in wait. @@ -2389,7 +2398,8 @@ static int sdma_check_progress( */ int sdma_send_txreq(struct sdma_engine *sde, struct iowait *wait, - struct sdma_txreq *tx) + struct sdma_txreq *tx, + bool pkts_sent) { int ret = 0; u16 tail; @@ -2431,7 +2441,7 @@ unlock_noconn: ret = -ECOMM; goto unlock; nodesc: - ret = sdma_check_progress(sde, wait, tx); + ret = sdma_check_progress(sde, wait, tx, pkts_sent); if (ret == -EAGAIN) { ret = 0; goto retry; @@ -2500,8 +2510,10 @@ retry: } update_tail: total_count = submit_count + flush_count; - if (wait) + if (wait) { iowait_sdma_add(wait, total_count); + iowait_starve_clear(submit_count > 0, wait); + } if (tail != INVALID_TAIL) sdma_update_tail(sde, tail); spin_unlock_irqrestore(&sde->tail_lock, flags); @@ -2529,7 +2541,7 @@ unlock_noconn: ret = -ECOMM; goto update_tail; nodesc: - ret = sdma_check_progress(sde, wait, tx); + ret = sdma_check_progress(sde, wait, tx, submit_count > 0); if (ret == -EAGAIN) { ret = 0; goto retry; diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 64f10b8b5db8..107011d8613b 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -852,7 +852,8 @@ struct iowait; int sdma_send_txreq(struct sdma_engine *sde, struct iowait *wait, - struct sdma_txreq *tx); + struct sdma_txreq *tx, + bool pkts_sent); int sdma_send_txlist(struct sdma_engine *sde, struct iowait *wait, struct list_head *tx_list, diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c index 2f3bbcac1e34..6d2702ef34ac 100644 --- a/drivers/infiniband/hw/hfi1/sysfs.c +++ b/drivers/infiniband/hw/hfi1/sysfs.c @@ -95,7 +95,7 @@ static void port_release(struct kobject *kobj) /* nothing to do since memory is freed by hfi1_free_devdata() */ } -static struct bin_attribute cc_table_bin_attr = { +static const struct bin_attribute cc_table_bin_attr = { .attr = {.name = "cc_table_bin", .mode = 0444}, .read = read_cc_table_bin, .size = PAGE_SIZE, @@ -137,7 +137,7 @@ static ssize_t read_cc_setting_bin(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute cc_setting_bin_attr = { +static const struct bin_attribute cc_setting_bin_attr = { .attr = {.name = "cc_settings_bin", .mode = 0444}, .read = read_cc_setting_bin, .size = PAGE_SIZE, diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c index eafae487face..b80b74d0c252 100644 --- a/drivers/infiniband/hw/hfi1/trace.c +++ b/drivers/infiniband/hw/hfi1/trace.c @@ -47,7 +47,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -u8 ibhdr_exhdr_len(struct ib_header *hdr) +u8 hfi1_trace_ib_hdr_len(struct ib_header *hdr) { struct ib_other_headers *ohdr; u8 opcode; @@ -61,13 +61,18 @@ u8 ibhdr_exhdr_len(struct ib_header *hdr) 0 : hdr_len_by_opcode[opcode] - (12 + 8); } -#define IMM_PRN "imm %d" -#define RETH_PRN "reth vaddr 0x%.16llx rkey 0x%.8x dlen 0x%.8x" -#define AETH_PRN "aeth syn 0x%.2x %s msn 0x%.8x" -#define DETH_PRN "deth qkey 0x%.8x sqpn 0x%.6x" -#define IETH_PRN "ieth rkey 0x%.8x" -#define ATOMICACKETH_PRN "origdata %llx" -#define ATOMICETH_PRN "vaddr 0x%llx rkey 0x%.8x sdata %llx cdata %llx" +const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet) +{ + return "IB"; +} + +#define IMM_PRN "imm:%d" +#define RETH_PRN "reth vaddr:0x%.16llx rkey:0x%.8x dlen:0x%.8x" +#define AETH_PRN "aeth syn:0x%.2x %s msn:0x%.8x" +#define DETH_PRN "deth qkey:0x%.8x sqpn:0x%.6x" +#define IETH_PRN "ieth rkey:0x%.8x" +#define ATOMICACKETH_PRN "origdata:%llx" +#define ATOMICETH_PRN "vaddr:0x%llx rkey:0x%.8x sdata:%llx cdata:%llx" #define OP(transport, op) IB_OPCODE_## transport ## _ ## op @@ -84,6 +89,43 @@ static const char *parse_syndrome(u8 syndrome) return ""; } +void hfi1_trace_parse_bth(struct ib_other_headers *ohdr, + u8 *ack, u8 *becn, u8 *fecn, u8 *mig, + u8 *se, u8 *pad, u8 *opcode, u8 *tver, + u16 *pkey, u32 *psn, u32 *qpn) +{ + *ack = ib_bth_get_ackreq(ohdr); + *becn = ib_bth_get_becn(ohdr); + *fecn = ib_bth_get_fecn(ohdr); + *mig = ib_bth_get_migreq(ohdr); + *se = ib_bth_get_se(ohdr); + *pad = ib_bth_get_pad(ohdr); + *opcode = ib_bth_get_opcode(ohdr); + *tver = ib_bth_get_tver(ohdr); + *pkey = ib_bth_get_pkey(ohdr); + *psn = ib_bth_get_psn(ohdr); + *qpn = ib_bth_get_qpn(ohdr); +} + +void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5, + struct ib_other_headers **ohdr, + u8 *lnh, u8 *lver, u8 *sl, u8 *sc, + u16 *len, u32 *dlid, u32 *slid) +{ + *lnh = ib_get_lnh(hdr); + *lver = ib_get_lver(hdr); + *sl = ib_get_sl(hdr); + *sc = ib_get_sc(hdr) | (sc5 << 4); + *len = ib_get_len(hdr); + *dlid = ib_get_dlid(hdr); + *slid = ib_get_slid(hdr); + + if (*lnh == HFI1_LRH_BTH) + *ohdr = &hdr->u.oth; + else + *ohdr = &hdr->u.l.oth; +} + const char *parse_everbs_hdrs( struct trace_seq *p, u8 opcode, diff --git a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h index 090f6b506953..0f2d2da057ec 100644 --- a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h +++ b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h @@ -55,8 +55,57 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM hfi1_ibhdrs -u8 ibhdr_exhdr_len(struct ib_header *hdr); +#define ib_opcode_name(opcode) { IB_OPCODE_##opcode, #opcode } +#define show_ib_opcode(opcode) \ +__print_symbolic(opcode, \ + ib_opcode_name(RC_SEND_FIRST), \ + ib_opcode_name(RC_SEND_MIDDLE), \ + ib_opcode_name(RC_SEND_LAST), \ + ib_opcode_name(RC_SEND_LAST_WITH_IMMEDIATE), \ + ib_opcode_name(RC_SEND_ONLY), \ + ib_opcode_name(RC_SEND_ONLY_WITH_IMMEDIATE), \ + ib_opcode_name(RC_RDMA_WRITE_FIRST), \ + ib_opcode_name(RC_RDMA_WRITE_MIDDLE), \ + ib_opcode_name(RC_RDMA_WRITE_LAST), \ + ib_opcode_name(RC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \ + ib_opcode_name(RC_RDMA_WRITE_ONLY), \ + ib_opcode_name(RC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \ + ib_opcode_name(RC_RDMA_READ_REQUEST), \ + ib_opcode_name(RC_RDMA_READ_RESPONSE_FIRST), \ + ib_opcode_name(RC_RDMA_READ_RESPONSE_MIDDLE), \ + ib_opcode_name(RC_RDMA_READ_RESPONSE_LAST), \ + ib_opcode_name(RC_RDMA_READ_RESPONSE_ONLY), \ + ib_opcode_name(RC_ACKNOWLEDGE), \ + ib_opcode_name(RC_ATOMIC_ACKNOWLEDGE), \ + ib_opcode_name(RC_COMPARE_SWAP), \ + ib_opcode_name(RC_FETCH_ADD), \ + ib_opcode_name(UC_SEND_FIRST), \ + ib_opcode_name(UC_SEND_MIDDLE), \ + ib_opcode_name(UC_SEND_LAST), \ + ib_opcode_name(UC_SEND_LAST_WITH_IMMEDIATE), \ + ib_opcode_name(UC_SEND_ONLY), \ + ib_opcode_name(UC_SEND_ONLY_WITH_IMMEDIATE), \ + ib_opcode_name(UC_RDMA_WRITE_FIRST), \ + ib_opcode_name(UC_RDMA_WRITE_MIDDLE), \ + ib_opcode_name(UC_RDMA_WRITE_LAST), \ + ib_opcode_name(UC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \ + ib_opcode_name(UC_RDMA_WRITE_ONLY), \ + ib_opcode_name(UC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \ + ib_opcode_name(UD_SEND_ONLY), \ + ib_opcode_name(UD_SEND_ONLY_WITH_IMMEDIATE), \ + ib_opcode_name(CNP)) + const char *parse_everbs_hdrs(struct trace_seq *p, u8 opcode, void *ehdrs); +u8 hfi1_trace_ib_hdr_len(struct ib_header *hdr); +const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet); +void hfi1_trace_parse_bth(struct ib_other_headers *ohdr, + u8 *ack, u8 *becn, u8 *fecn, u8 *mig, + u8 *se, u8 *pad, u8 *opcode, u8 *tver, + u16 *pkey, u32 *psn, u32 *qpn); +void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5, + struct ib_other_headers **ohdr, + u8 *lnh, u8 *lver, u8 *sl, u8 *sc, + u16 *len, u32 *dlid, u32 *slid); #define __parse_ib_ehdrs(op, ehdrs) parse_everbs_hdrs(p, op, ehdrs) @@ -66,139 +115,198 @@ __print_symbolic(lrh, \ lrh_name(LRH_BTH), \ lrh_name(LRH_GRH)) -#define LRH_PRN "vl %d lver %d sl %d lnh %d,%s dlid %.4x len %d slid %.4x" +#define LRH_PRN "len:%d sc:%d dlid:0x%.4x slid:0x%.4x" +#define LRH_9B_PRN "lnh:%d,%s lver:%d sl:%d " #define BTH_PRN \ - "op 0x%.2x,%s se %d m %d pad %d tver %d pkey 0x%.4x " \ - "f %d b %d qpn 0x%.6x a %d psn 0x%.8x" -#define EHDR_PRN "%s" + "op:0x%.2x,%s se:%d m:%d pad:%d tver:%d pkey:0x%.4x " \ + "f:%d b:%d qpn:0x%.6x a:%d psn:0x%.8x" +#define EHDR_PRN "hlen:%d %s" -DECLARE_EVENT_CLASS(hfi1_ibhdr_template, +DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template, TP_PROTO(struct hfi1_devdata *dd, - struct ib_header *hdr), - TP_ARGS(dd, hdr), + struct hfi1_packet *packet, + bool sc5), + TP_ARGS(dd, packet, sc5), TP_STRUCT__entry( DD_DEV_ENTRY(dd) - /* LRH */ - __field(u8, vl) + __field(u8, lnh) __field(u8, lver) __field(u8, sl) + __field(u16, len) + __field(u32, dlid) + __field(u8, sc) + __field(u32, slid) + __field(u8, opcode) + __field(u8, se) + __field(u8, mig) + __field(u8, pad) + __field(u8, tver) + __field(u16, pkey) + __field(u8, fecn) + __field(u8, becn) + __field(u32, qpn) + __field(u8, ack) + __field(u32, psn) + /* extended headers */ + __dynamic_array(u8, ehdrs, + hfi1_trace_ib_hdr_len(packet->hdr)) + ), + TP_fast_assign( + struct ib_other_headers *ohdr; + + DD_DEV_ASSIGN(dd); + + hfi1_trace_parse_9b_hdr(packet->hdr, sc5, + &ohdr, + &__entry->lnh, + &__entry->lver, + &__entry->sl, + &__entry->sc, + &__entry->len, + &__entry->dlid, + &__entry->slid); + + hfi1_trace_parse_bth(ohdr, &__entry->ack, + &__entry->becn, &__entry->fecn, + &__entry->mig, &__entry->se, + &__entry->pad, &__entry->opcode, + &__entry->tver, &__entry->pkey, + &__entry->psn, &__entry->qpn); + /* extended headers */ + memcpy(__get_dynamic_array(ehdrs), &ohdr->u, + __get_dynamic_array_len(ehdrs)); + ), + TP_printk("[%s] (IB) " LRH_PRN " " LRH_9B_PRN " " + BTH_PRN " " EHDR_PRN, + __get_str(dev), + __entry->len, + __entry->sc, + __entry->dlid, + __entry->slid, + __entry->lnh, show_lnh(__entry->lnh), + __entry->lver, + __entry->sl, + /* BTH */ + __entry->opcode, show_ib_opcode(__entry->opcode), + __entry->se, + __entry->mig, + __entry->pad, + __entry->tver, + __entry->pkey, + __entry->fecn, + __entry->becn, + __entry->qpn, + __entry->ack, + __entry->psn, + /* extended headers */ + __get_dynamic_array_len(ehdrs), + __parse_ib_ehdrs( + __entry->opcode, + (void *)__get_dynamic_array(ehdrs)) + ) +); + +DEFINE_EVENT(hfi1_input_ibhdr_template, input_ibhdr, + TP_PROTO(struct hfi1_devdata *dd, + struct hfi1_packet *packet, bool sc5), + TP_ARGS(dd, packet, sc5)); + +DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template, + TP_PROTO(struct hfi1_devdata *dd, + struct ib_header *hdr, + bool sc5), + TP_ARGS(dd, hdr, sc5), + TP_STRUCT__entry( + DD_DEV_ENTRY(dd) __field(u8, lnh) - __field(u16, dlid) + __field(u8, lver) + __field(u8, sl) __field(u16, len) - __field(u16, slid) - /* BTH */ + __field(u32, dlid) + __field(u8, sc) + __field(u32, slid) __field(u8, opcode) __field(u8, se) - __field(u8, m) + __field(u8, mig) __field(u8, pad) __field(u8, tver) __field(u16, pkey) - __field(u8, f) - __field(u8, b) + __field(u8, fecn) + __field(u8, becn) __field(u32, qpn) - __field(u8, a) + __field(u8, ack) __field(u32, psn) /* extended headers */ - __dynamic_array(u8, ehdrs, ibhdr_exhdr_len(hdr)) + __dynamic_array(u8, ehdrs, + hfi1_trace_ib_hdr_len(hdr)) ), - TP_fast_assign( + TP_fast_assign( struct ib_other_headers *ohdr; DD_DEV_ASSIGN(dd); - /* LRH */ - __entry->vl = - (u8)(be16_to_cpu(hdr->lrh[0]) >> 12); - __entry->lver = - (u8)(be16_to_cpu(hdr->lrh[0]) >> 8) & 0xf; - __entry->sl = - (u8)(be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf; - __entry->lnh = - (u8)(be16_to_cpu(hdr->lrh[0]) & 3); - __entry->dlid = - be16_to_cpu(hdr->lrh[1]); - /* allow for larger len */ - __entry->len = - be16_to_cpu(hdr->lrh[2]); - __entry->slid = - be16_to_cpu(hdr->lrh[3]); - /* BTH */ - if (__entry->lnh == HFI1_LRH_BTH) - ohdr = &hdr->u.oth; - else - ohdr = &hdr->u.l.oth; - __entry->opcode = - (be32_to_cpu(ohdr->bth[0]) >> 24) & 0xff; - __entry->se = - (be32_to_cpu(ohdr->bth[0]) >> 23) & 1; - __entry->m = - (be32_to_cpu(ohdr->bth[0]) >> 22) & 1; - __entry->pad = - (be32_to_cpu(ohdr->bth[0]) >> 20) & 3; - __entry->tver = - (be32_to_cpu(ohdr->bth[0]) >> 16) & 0xf; - __entry->pkey = - be32_to_cpu(ohdr->bth[0]) & 0xffff; - __entry->f = - (be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) & - IB_FECN_MASK; - __entry->b = - (be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) & - IB_BECN_MASK; - __entry->qpn = - be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK; - __entry->a = - (be32_to_cpu(ohdr->bth[2]) >> 31) & 1; - /* allow for larger PSN */ - __entry->psn = - be32_to_cpu(ohdr->bth[2]) & 0x7fffffff; + + hfi1_trace_parse_9b_hdr(hdr, sc5, + &ohdr, &__entry->lnh, + &__entry->lver, &__entry->sl, + &__entry->sc, &__entry->len, + &__entry->dlid, &__entry->slid); + + hfi1_trace_parse_bth(ohdr, &__entry->ack, + &__entry->becn, &__entry->fecn, + &__entry->mig, &__entry->se, + &__entry->pad, &__entry->opcode, + &__entry->tver, &__entry->pkey, + &__entry->psn, &__entry->qpn); + /* extended headers */ - memcpy(__get_dynamic_array(ehdrs), &ohdr->u, - ibhdr_exhdr_len(hdr)); - ), - TP_printk("[%s] " LRH_PRN " " BTH_PRN " " EHDR_PRN, - __get_str(dev), - /* LRH */ - __entry->vl, - __entry->lver, - __entry->sl, - __entry->lnh, show_lnh(__entry->lnh), - __entry->dlid, - __entry->len, - __entry->slid, - /* BTH */ - __entry->opcode, show_ib_opcode(__entry->opcode), - __entry->se, - __entry->m, - __entry->pad, - __entry->tver, - __entry->pkey, - __entry->f, - __entry->b, - __entry->qpn, - __entry->a, - __entry->psn, - /* extended headers */ - __parse_ib_ehdrs( - __entry->opcode, - (void *)__get_dynamic_array(ehdrs)) - ) + memcpy(__get_dynamic_array(ehdrs), + &ohdr->u, __get_dynamic_array_len(ehdrs)); + ), + TP_printk("[%s] (IB) " LRH_PRN " " LRH_9B_PRN " " + BTH_PRN " " EHDR_PRN, + __get_str(dev), + __entry->len, + __entry->sc, + __entry->dlid, + __entry->slid, + __entry->lnh, show_lnh(__entry->lnh), + __entry->lver, + __entry->sl, + /* BTH */ + __entry->opcode, show_ib_opcode(__entry->opcode), + __entry->se, + __entry->mig, + __entry->pad, + __entry->tver, + __entry->pkey, + __entry->fecn, + __entry->becn, + __entry->qpn, + __entry->ack, + __entry->psn, + /* extended headers */ + __get_dynamic_array_len(ehdrs), + __parse_ib_ehdrs( + __entry->opcode, + (void *)__get_dynamic_array(ehdrs)) + ) ); -DEFINE_EVENT(hfi1_ibhdr_template, input_ibhdr, - TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr), - TP_ARGS(dd, hdr)); +DEFINE_EVENT(hfi1_output_ibhdr_template, pio_output_ibhdr, + TP_PROTO(struct hfi1_devdata *dd, + struct ib_header *hdr, bool sc5), + TP_ARGS(dd, hdr, sc5)); -DEFINE_EVENT(hfi1_ibhdr_template, pio_output_ibhdr, - TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr), - TP_ARGS(dd, hdr)); +DEFINE_EVENT(hfi1_output_ibhdr_template, ack_output_ibhdr, + TP_PROTO(struct hfi1_devdata *dd, + struct ib_header *hdr, bool sc5), + TP_ARGS(dd, hdr, sc5)); -DEFINE_EVENT(hfi1_ibhdr_template, ack_output_ibhdr, - TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr), - TP_ARGS(dd, hdr)); +DEFINE_EVENT(hfi1_output_ibhdr_template, sdma_output_ibhdr, + TP_PROTO(struct hfi1_devdata *dd, + struct ib_header *hdr, bool sc5), + TP_ARGS(dd, hdr, sc5)); -DEFINE_EVENT(hfi1_ibhdr_template, sdma_output_ibhdr, - TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr), - TP_ARGS(dd, hdr)); #endif /* __HFI1_TRACE_IBHDRS_H */ diff --git a/drivers/infiniband/hw/hfi1/trace_misc.h b/drivers/infiniband/hw/hfi1/trace_misc.h index deac77ddaeab..8db2253523ff 100644 --- a/drivers/infiniband/hw/hfi1/trace_misc.h +++ b/drivers/infiniband/hw/hfi1/trace_misc.h @@ -72,6 +72,26 @@ TRACE_EVENT(hfi1_interrupt, __entry->src) ); +DECLARE_EVENT_CLASS( + hfi1_csr_template, + TP_PROTO(void __iomem *addr, u64 value), + TP_ARGS(addr, value), + TP_STRUCT__entry( + __field(void __iomem *, addr) + __field(u64, value) + ), + TP_fast_assign( + __entry->addr = addr; + __entry->value = value; + ), + TP_printk("addr %p value %llx", __entry->addr, __entry->value) +); + +DEFINE_EVENT( + hfi1_csr_template, hfi1_write_rcvarray, + TP_PROTO(void __iomem *addr, u64 value), + TP_ARGS(addr, value)); + #ifdef CONFIG_FAULT_INJECTION TRACE_EVENT(hfi1_fault_opcode, TP_PROTO(struct rvt_qp *qp, u8 opcode), diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h index f77e59fb43fe..bebf0a8f214d 100644 --- a/drivers/infiniband/hw/hfi1/trace_rx.h +++ b/drivers/infiniband/hw/hfi1/trace_rx.h @@ -52,9 +52,25 @@ #include "hfi.h" +#define tidtype_name(type) { PT_##type, #type } +#define show_tidtype(type) \ +__print_symbolic(type, \ + tidtype_name(EXPECTED), \ + tidtype_name(EAGER), \ + tidtype_name(INVALID)) \ + #undef TRACE_SYSTEM #define TRACE_SYSTEM hfi1_rx +#define packettype_name(etype) { RHF_RCV_TYPE_##etype, #etype } +#define show_packettype(etype) \ +__print_symbolic(etype, \ + packettype_name(EXPECTED), \ + packettype_name(EAGER), \ + packettype_name(IB), \ + packettype_name(ERROR), \ + packettype_name(BYPASS)) + TRACE_EVENT(hfi1_rcvhdr, TP_PROTO(struct hfi1_devdata *dd, u32 ctxt, @@ -98,7 +114,7 @@ TRACE_EVENT(hfi1_rcvhdr, ); TRACE_EVENT(hfi1_receive_interrupt, - TP_PROTO(struct hfi1_devdata *dd, u32 ctxt), + TP_PROTO(struct hfi1_devdata *dd, u16 ctxt), TP_ARGS(dd, ctxt), TP_STRUCT__entry(DD_DEV_ENTRY(dd) __field(u32, ctxt) @@ -129,7 +145,8 @@ TRACE_EVENT(hfi1_receive_interrupt, ) ); -TRACE_EVENT(hfi1_exp_tid_reg, +DECLARE_EVENT_CLASS( + hfi1_exp_tid_reg_unreg, TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages, unsigned long va, unsigned long pa, dma_addr_t dma), @@ -163,38 +180,45 @@ TRACE_EVENT(hfi1_exp_tid_reg, ) ); -TRACE_EVENT(hfi1_exp_tid_unreg, - TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages, - unsigned long va, unsigned long pa, dma_addr_t dma), - TP_ARGS(ctxt, subctxt, rarr, npages, va, pa, dma), - TP_STRUCT__entry( - __field(unsigned int, ctxt) - __field(u16, subctxt) - __field(u32, rarr) - __field(u32, npages) - __field(unsigned long, va) - __field(unsigned long, pa) - __field(dma_addr_t, dma) - ), - TP_fast_assign( - __entry->ctxt = ctxt; - __entry->subctxt = subctxt; - __entry->rarr = rarr; - __entry->npages = npages; - __entry->va = va; - __entry->pa = pa; - __entry->dma = dma; - ), - TP_printk("[%u:%u] entry:%u, %u pages @ 0x%lx, va:0x%lx dma:0x%llx", - __entry->ctxt, - __entry->subctxt, - __entry->rarr, - __entry->npages, - __entry->pa, - __entry->va, - __entry->dma - ) - ); +DEFINE_EVENT( + hfi1_exp_tid_reg_unreg, hfi1_exp_tid_unreg, + TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages, + unsigned long va, unsigned long pa, dma_addr_t dma), + TP_ARGS(ctxt, subctxt, rarr, npages, va, pa, dma)); + +DEFINE_EVENT( + hfi1_exp_tid_reg_unreg, hfi1_exp_tid_reg, + TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages, + unsigned long va, unsigned long pa, dma_addr_t dma), + TP_ARGS(ctxt, subctxt, rarr, npages, va, pa, dma)); + +TRACE_EVENT( + hfi1_put_tid, + TP_PROTO(struct hfi1_devdata *dd, + u32 index, u32 type, unsigned long pa, u16 order), + TP_ARGS(dd, index, type, pa, order), + TP_STRUCT__entry( + DD_DEV_ENTRY(dd) + __field(unsigned long, pa); + __field(u32, index); + __field(u32, type); + __field(u16, order); + ), + TP_fast_assign( + DD_DEV_ASSIGN(dd); + __entry->pa = pa; + __entry->index = index; + __entry->type = type; + __entry->order = order; + ), + TP_printk("[%s] type %s pa %lx index %u order %u", + __get_str(dev), + show_tidtype(__entry->type), + __entry->pa, + __entry->index, + __entry->order + ) +); TRACE_EVENT(hfi1_exp_tid_inval, TP_PROTO(unsigned int ctxt, u16 subctxt, unsigned long va, u32 rarr, diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c index 5da1e4546543..76c2451a53d7 100644 --- a/drivers/infiniband/hw/hfi1/uc.c +++ b/drivers/infiniband/hw/hfi1/uc.c @@ -297,31 +297,25 @@ bail_no_tx: void hfi1_uc_rcv(struct hfi1_packet *packet) { struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd); - struct ib_header *hdr = packet->hdr; - u32 rcv_flags = packet->rcv_flags; void *data = packet->ebuf; u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; struct ib_other_headers *ohdr = packet->ohdr; - u32 bth0, opcode; + u32 opcode = packet->opcode; u32 hdrsize = packet->hlen; u32 psn; - u32 pad; + u32 pad = packet->pad; struct ib_wc wc; u32 pmtu = qp->pmtu; struct ib_reth *reth; - int has_grh = rcv_flags & HFI1_HAS_GRH; int ret; - bth0 = be32_to_cpu(ohdr->bth[0]); - if (hfi1_ruc_check_hdr(ibp, hdr, has_grh, qp, bth0)) + if (hfi1_ruc_check_hdr(ibp, packet)) return; process_ecn(qp, packet, true); - psn = be32_to_cpu(ohdr->bth[2]); - opcode = ib_bth_get_opcode(ohdr); - + psn = ib_bth_get_psn(ohdr); /* Compare the PSN verses the expected PSN. */ if (unlikely(cmp_psn(psn, qp->r_psn) != 0)) { /* @@ -432,8 +426,6 @@ no_immediate_data: wc.ex.imm_data = 0; wc.wc_flags = 0; send_last: - /* Get the number of bytes the message was padded by. */ - pad = ib_bth_get_pad(ohdr); /* Check for invalid length. */ /* LAST len should be >= 1 */ if (unlikely(tlen < (hdrsize + pad + 4))) @@ -527,8 +519,6 @@ rdma_first: rdma_last_imm: wc.wc_flags = IB_WC_WITH_IMM; - /* Get the number of bytes the message was padded by. */ - pad = ib_bth_get_pad(ohdr); /* Check for invalid length. */ /* LAST len should be >= 1 */ if (unlikely(tlen < (hdrsize + pad + 4))) diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 6a4e95cefae5..6bf7a1b08491 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -110,10 +110,10 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe) ((1 << ppd->lmc) - 1)); if (unlikely(ingress_pkey_check(ppd, pkey, sc5, qp->s_pkey_index, slid))) { - hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY, pkey, - rdma_ah_get_sl(ah_attr), - sqp->ibqp.qp_num, qp->ibqp.qp_num, - slid, rdma_ah_get_dlid(ah_attr)); + hfi1_bad_pkey(ibp, pkey, + rdma_ah_get_sl(ah_attr), + sqp->ibqp.qp_num, qp->ibqp.qp_num, + slid, rdma_ah_get_dlid(ah_attr)); goto drop; } } @@ -128,18 +128,8 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe) qkey = (int)swqe->ud_wr.remote_qkey < 0 ? sqp->qkey : swqe->ud_wr.remote_qkey; - if (unlikely(qkey != qp->qkey)) { - u16 lid; - - lid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) & - ((1 << ppd->lmc) - 1)); - hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_Q_KEY, qkey, - rdma_ah_get_sl(ah_attr), - sqp->ibqp.qp_num, qp->ibqp.qp_num, - lid, - rdma_ah_get_dlid(ah_attr)); - goto drop; - } + if (unlikely(qkey != qp->qkey)) + goto drop; /* silently drop per IBTA spec */ } /* @@ -549,7 +539,7 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn, hdr.lrh[3] = cpu_to_be16(slid); plen = 2 /* PBC */ + hwords; - pbc_flags |= (!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT; + pbc_flags |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT); vl = sc_to_vlt(ppd->dd, sc5); pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen); if (ctxt) { @@ -668,36 +658,31 @@ static int opa_smp_check(struct hfi1_ibport *ibp, u16 pkey, u8 sc5, void hfi1_ud_rcv(struct hfi1_packet *packet) { struct ib_other_headers *ohdr = packet->ohdr; - int opcode; u32 hdrsize = packet->hlen; struct ib_wc wc; u32 qkey; u32 src_qp; - u16 dlid, pkey; + u16 pkey; int mgmt_pkey_idx = -1; struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); struct ib_header *hdr = packet->hdr; - u32 rcv_flags = packet->rcv_flags; void *data = packet->ebuf; u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; - bool has_grh = rcv_flags & HFI1_HAS_GRH; u8 sc5 = hfi1_9B_get_sc5(hdr, packet->rhf); u32 bth1; - u8 sl_from_sc, sl; - u16 slid; - u8 extra_bytes; + u8 sl_from_sc; + u8 extra_bytes = packet->pad; + u8 opcode = packet->opcode; + u8 sl = packet->sl; + u32 dlid = packet->dlid; + u32 slid = packet->slid; - qkey = be32_to_cpu(ohdr->u.ud.deth[0]); - src_qp = be32_to_cpu(ohdr->u.ud.deth[1]) & RVT_QPN_MASK; - dlid = ib_get_dlid(hdr); bth1 = be32_to_cpu(ohdr->bth[1]); - slid = ib_get_slid(hdr); + qkey = ib_get_qkey(ohdr); + src_qp = ib_get_sqpn(ohdr); pkey = ib_bth_get_pkey(ohdr); - opcode = ib_bth_get_opcode(ohdr); - sl = ib_get_sl(hdr); - extra_bytes = ib_bth_get_pad(ohdr); extra_bytes += (SIZE_OF_CRC << 2); sl_from_sc = ibp->sc_to_sl[sc5]; @@ -727,10 +712,10 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) * for invalid pkeys is optional according to * IB spec (release 1.3, section 10.9.4) */ - hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY, - pkey, sl, - src_qp, qp->ibqp.qp_num, - slid, dlid); + hfi1_bad_pkey(ibp, + pkey, sl, + src_qp, qp->ibqp.qp_num, + slid, dlid); return; } } else { @@ -739,12 +724,9 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (mgmt_pkey_idx < 0) goto drop; } - if (unlikely(qkey != qp->qkey)) { - hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_Q_KEY, qkey, sl, - src_qp, qp->ibqp.qp_num, - slid, dlid); + if (unlikely(qkey != qp->qkey)) /* Silent drop */ return; - } + /* Drop invalid MAD packets (see 13.5.3.1). */ if (unlikely(qp->ibqp.qp_num == 1 && (tlen > 2048 || (sc5 == 0xF)))) @@ -811,7 +793,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) qp->r_flags |= RVT_R_REUSE_SGE; goto drop; } - if (has_grh) { + if (packet->grh) { hfi1_copy_sge(&qp->r_sge, &hdr->u.l.grh, sizeof(struct ib_grh), true, false); wc.wc_flags |= IB_WC_GRH; diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index a8f0aa4722f6..d9036ba3f4eb 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -51,14 +51,6 @@ #include "trace.h" #include "mmu_rb.h" -struct tid_group { - struct list_head list; - u32 base; - u8 size; - u8 used; - u8 map; -}; - struct tid_rb_node { struct mmu_rb_node mmu; unsigned long phys; @@ -75,8 +67,6 @@ struct tid_pageset { u16 count; }; -#define EXP_TID_SET_EMPTY(set) (set.count == 0 && list_empty(&set.list)) - #define num_user_pages(vaddr, len) \ (1 + (((((unsigned long)(vaddr) + \ (unsigned long)(len) - 1) & PAGE_MASK) - \ @@ -109,96 +99,14 @@ static struct mmu_rb_ops tid_rb_ops = { .invalidate = tid_rb_invalidate }; -static inline u32 rcventry2tidinfo(u32 rcventry) -{ - u32 pair = rcventry & ~0x1; - - return EXP_TID_SET(IDX, pair >> 1) | - EXP_TID_SET(CTRL, 1 << (rcventry - pair)); -} - -static inline void exp_tid_group_init(struct exp_tid_set *set) -{ - INIT_LIST_HEAD(&set->list); - set->count = 0; -} - -static inline void tid_group_remove(struct tid_group *grp, - struct exp_tid_set *set) -{ - list_del_init(&grp->list); - set->count--; -} - -static inline void tid_group_add_tail(struct tid_group *grp, - struct exp_tid_set *set) -{ - list_add_tail(&grp->list, &set->list); - set->count++; -} - -static inline struct tid_group *tid_group_pop(struct exp_tid_set *set) -{ - struct tid_group *grp = - list_first_entry(&set->list, struct tid_group, list); - list_del_init(&grp->list); - set->count--; - return grp; -} - -static inline void tid_group_move(struct tid_group *group, - struct exp_tid_set *s1, - struct exp_tid_set *s2) -{ - tid_group_remove(group, s1); - tid_group_add_tail(group, s2); -} - -int hfi1_user_exp_rcv_grp_init(struct hfi1_filedata *fd) -{ - struct hfi1_ctxtdata *uctxt = fd->uctxt; - struct hfi1_devdata *dd = fd->dd; - u32 tidbase; - u32 i; - struct tid_group *grp, *gptr; - - exp_tid_group_init(&uctxt->tid_group_list); - exp_tid_group_init(&uctxt->tid_used_list); - exp_tid_group_init(&uctxt->tid_full_list); - - tidbase = uctxt->expected_base; - for (i = 0; i < uctxt->expected_count / - dd->rcv_entries.group_size; i++) { - grp = kzalloc(sizeof(*grp), GFP_KERNEL); - if (!grp) - goto grp_failed; - - grp->size = dd->rcv_entries.group_size; - grp->base = tidbase; - tid_group_add_tail(grp, &uctxt->tid_group_list); - tidbase += dd->rcv_entries.group_size; - } - - return 0; - -grp_failed: - list_for_each_entry_safe(grp, gptr, &uctxt->tid_group_list.list, - list) { - list_del_init(&grp->list); - kfree(grp); - } - - return -ENOMEM; -} - /* * Initialize context and file private data needed for Expected * receive caching. This needs to be done after the context has * been configured with the eager/expected RcvEntry counts. */ -int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd) +int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt) { - struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; int ret = 0; @@ -266,18 +174,6 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd) return ret; } -void hfi1_user_exp_rcv_grp_free(struct hfi1_ctxtdata *uctxt) -{ - struct tid_group *grp, *gptr; - - list_for_each_entry_safe(grp, gptr, &uctxt->tid_group_list.list, - list) { - list_del_init(&grp->list); - kfree(grp); - } - hfi1_clear_tids(uctxt); -} - void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd) { struct hfi1_ctxtdata *uctxt = fd->uctxt; @@ -303,23 +199,6 @@ void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd) } /* - * Write an "empty" RcvArray entry. - * This function exists so the TID registaration code can use it - * to write to unused/unneeded entries and still take advantage - * of the WC performance improvements. The HFI will ignore this - * write to the RcvArray entry. - */ -static inline void rcv_array_wc_fill(struct hfi1_devdata *dd, u32 index) -{ - /* - * Doing the WC fill writes only makes sense if the device is - * present and the RcvArray has been mapped as WC memory. - */ - if ((dd->flags & HFI1_PRESENT) && dd->rcvarray_wc) - writeq(0, dd->rcvarray_wc + (index * 8)); -} - -/* * RcvArray entry allocation for Expected Receives is done by the * following algorithm: * @@ -935,12 +814,11 @@ static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) node->npages, node->mmu.addr, node->phys, node->dma_addr); - hfi1_put_tid(dd, node->rcventry, PT_INVALID, 0, 0); /* * Make sure device has seen the write before we unpin the * pages. */ - flush_wc(); + hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0); pci_unmap_single(dd->pcidev, node->dma_addr, node->mmu.len, PCI_DMA_FROMDEVICE); diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index 5250c897298d..6cbaa4cf4970 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -49,30 +49,10 @@ #include "hfi.h" -#define EXP_TID_TIDLEN_MASK 0x7FFULL -#define EXP_TID_TIDLEN_SHIFT 0 -#define EXP_TID_TIDCTRL_MASK 0x3ULL -#define EXP_TID_TIDCTRL_SHIFT 20 -#define EXP_TID_TIDIDX_MASK 0x3FFULL -#define EXP_TID_TIDIDX_SHIFT 22 -#define EXP_TID_GET(tid, field) \ - (((tid) >> EXP_TID_TID##field##_SHIFT) & EXP_TID_TID##field##_MASK) +#include "exp_rcv.h" -#define EXP_TID_SET(field, value) \ - (((value) & EXP_TID_TID##field##_MASK) << \ - EXP_TID_TID##field##_SHIFT) -#define EXP_TID_CLEAR(tid, field) ({ \ - (tid) &= ~(EXP_TID_TID##field##_MASK << \ - EXP_TID_TID##field##_SHIFT); \ - }) -#define EXP_TID_RESET(tid, field, value) do { \ - EXP_TID_CLEAR(tid, field); \ - (tid) |= EXP_TID_SET(field, (value)); \ - } while (0) - -void hfi1_user_exp_rcv_grp_free(struct hfi1_ctxtdata *uctxt); -int hfi1_user_exp_rcv_grp_init(struct hfi1_filedata *fd); -int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd); +int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt); void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd); int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, struct hfi1_tid_info *tinfo); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index d55339f5d73b..8f02707e9c95 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -94,43 +94,13 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12 /* Number of BTH.PSN bits used for sequence number in expected rcvs */ #define BTH_SEQ_MASK 0x7ffull -/* - * Define fields in the KDETH header so we can update the header - * template. - */ -#define KDETH_OFFSET_SHIFT 0 -#define KDETH_OFFSET_MASK 0x7fff -#define KDETH_OM_SHIFT 15 -#define KDETH_OM_MASK 0x1 -#define KDETH_TID_SHIFT 16 -#define KDETH_TID_MASK 0x3ff -#define KDETH_TIDCTRL_SHIFT 26 -#define KDETH_TIDCTRL_MASK 0x3 -#define KDETH_INTR_SHIFT 28 -#define KDETH_INTR_MASK 0x1 -#define KDETH_SH_SHIFT 29 -#define KDETH_SH_MASK 0x1 -#define KDETH_HCRC_UPPER_SHIFT 16 -#define KDETH_HCRC_UPPER_MASK 0xff -#define KDETH_HCRC_LOWER_SHIFT 24 -#define KDETH_HCRC_LOWER_MASK 0xff - #define AHG_KDETH_INTR_SHIFT 12 #define AHG_KDETH_SH_SHIFT 13 +#define AHG_KDETH_ARRAY_SIZE 9 #define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4) #define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff) -#define KDETH_GET(val, field) \ - (((le32_to_cpu((val))) >> KDETH_##field##_SHIFT) & KDETH_##field##_MASK) -#define KDETH_SET(dw, field, val) do { \ - u32 dwval = le32_to_cpu(dw); \ - dwval &= ~(KDETH_##field##_MASK << KDETH_##field##_SHIFT); \ - dwval |= (((val) & KDETH_##field##_MASK) << \ - KDETH_##field##_SHIFT); \ - dw = cpu_to_le32(dwval); \ - } while (0) - #define AHG_HEADER_SET(arr, idx, dw, bit, width, value) \ do { \ if ((idx) < ARRAY_SIZE((arr))) \ @@ -141,23 +111,10 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12 return -ERANGE; \ } while (0) -/* KDETH OM multipliers and switch over point */ -#define KDETH_OM_SMALL 4 -#define KDETH_OM_SMALL_SHIFT 2 -#define KDETH_OM_LARGE 64 -#define KDETH_OM_LARGE_SHIFT 6 -#define KDETH_OM_MAX_SIZE (1 << ((KDETH_OM_LARGE / KDETH_OM_SMALL) + 1)) - /* Tx request flag bits */ #define TXREQ_FLAGS_REQ_ACK BIT(0) /* Set the ACK bit in the header */ #define TXREQ_FLAGS_REQ_DISABLE_SH BIT(1) /* Disable header suppression */ -/* SDMA request flag bits */ -#define SDMA_REQ_FOR_THREAD 1 -#define SDMA_REQ_SEND_DONE 2 -#define SDMA_REQ_HAS_ERROR 3 -#define SDMA_REQ_DONE_ERROR 4 - #define SDMA_PKT_Q_INACTIVE BIT(0) #define SDMA_PKT_Q_ACTIVE BIT(1) #define SDMA_PKT_Q_DEFERRED BIT(2) @@ -204,25 +161,41 @@ struct evict_data { }; struct user_sdma_request { - struct sdma_req_info info; - struct hfi1_user_sdma_pkt_q *pq; - struct hfi1_user_sdma_comp_q *cq; /* This is the original header from user space */ struct hfi1_pkt_header hdr; + + /* Read mostly fields */ + struct hfi1_user_sdma_pkt_q *pq ____cacheline_aligned_in_smp; + struct hfi1_user_sdma_comp_q *cq; /* * Pointer to the SDMA engine for this request. * Since different request could be on different VLs, * each request will need it's own engine pointer. */ struct sdma_engine *sde; - s8 ahg_idx; - u32 ahg[9]; + struct sdma_req_info info; + /* TID array values copied from the tid_iov vector */ + u32 *tids; + /* total length of the data in the request */ + u32 data_len; + /* number of elements copied to the tids array */ + u16 n_tids; /* - * KDETH.Offset (Eager) field - * We need to remember the initial value so the headers - * can be updated properly. + * We copy the iovs for this request (based on + * info.iovcnt). These are only the data vectors */ - u32 koffset; + u8 data_iovs; + s8 ahg_idx; + + /* Writeable fields shared with interrupt */ + u64 seqcomp ____cacheline_aligned_in_smp; + u64 seqsubmitted; + /* status of the last txreq completed */ + int status; + + /* Send side fields */ + struct list_head txps ____cacheline_aligned_in_smp; + u64 seqnum; /* * KDETH.OFFSET (TID) field * The offset can cover multiple packets, depending on the @@ -230,29 +203,21 @@ struct user_sdma_request { */ u32 tidoffset; /* - * We copy the iovs for this request (based on - * info.iovcnt). These are only the data vectors + * KDETH.Offset (Eager) field + * We need to remember the initial value so the headers + * can be updated properly. */ - unsigned data_iovs; - /* total length of the data in the request */ - u32 data_len; + u32 koffset; + u32 sent; + /* TID index copied from the tid_iov vector */ + u16 tididx; /* progress index moving along the iovs array */ - unsigned iov_idx; + u8 iov_idx; + u8 done; + u8 has_error; + struct user_sdma_iovec iovs[MAX_VECTORS_PER_REQ]; - /* number of elements copied to the tids array */ - u16 n_tids; - /* TID array values copied from the tid_iov vector */ - u32 *tids; - u16 tididx; - u32 sent; - u64 seqnum; - u64 seqcomp; - u64 seqsubmitted; - struct list_head txps; - unsigned long flags; - /* status of the last txreq completed */ - int status; -}; +} ____cacheline_aligned_in_smp; /* * A single txreq could span up to 3 physical pages when the MTU @@ -307,7 +272,8 @@ static int defer_packet_queue( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *txreq, - unsigned int seq); + uint seq, + bool pkts_sent); static void activate_packet_queue(struct iowait *wait, int reason); static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr, unsigned long len); @@ -329,7 +295,8 @@ static int defer_packet_queue( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *txreq, - unsigned seq) + uint seq, + bool pkts_sent) { struct hfi1_user_sdma_pkt_q *pq = container_of(wait, struct hfi1_user_sdma_pkt_q, busy); @@ -349,7 +316,7 @@ static int defer_packet_queue( xchg(&pq->state, SDMA_PKT_Q_DEFERRED); write_seqlock(&dev->iowait_lock); if (list_empty(&pq->busy.list)) - list_add_tail(&pq->busy.list, &sde->dmawait); + iowait_queue(pkts_sent, &pq->busy, &sde->dmawait); write_sequnlock(&dev->iowait_lock); return -EBUSY; eagain: @@ -379,7 +346,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, struct hfi1_devdata *dd; struct hfi1_user_sdma_comp_q *cq; struct hfi1_user_sdma_pkt_q *pq; - unsigned long flags; if (!uctxt || !fd) return -EBADF; @@ -393,7 +359,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, if (!pq) return -ENOMEM; - INIT_LIST_HEAD(&pq->list); pq->dd = dd; pq->ctxt = uctxt->ctxt; pq->subctxt = fd->subctxt; @@ -454,10 +419,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, fd->pq = pq; fd->cq = cq; - spin_lock_irqsave(&uctxt->sdma_qlock, flags); - list_add(&pq->list, &uctxt->sdma_queues); - spin_unlock_irqrestore(&uctxt->sdma_qlock, flags); - return 0; pq_mmu_fail: @@ -476,11 +437,10 @@ pq_reqs_nomem: return ret; } -int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd) +int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt) { - struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_user_sdma_pkt_q *pq; - unsigned long flags; hfi1_cdbg(SDMA, "[%u:%u:%u] Freeing user SDMA queues", uctxt->dd->unit, uctxt->ctxt, fd->subctxt); @@ -488,10 +448,6 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd) if (pq) { if (pq->handler) hfi1_mmu_rb_unregister(pq->handler); - spin_lock_irqsave(&uctxt->sdma_qlock, flags); - if (!list_empty(&pq->list)) - list_del_init(&pq->list); - spin_unlock_irqrestore(&uctxt->sdma_qlock, flags); iowait_sdma_drain(&pq->busy); /* Wait until all requests have been freed. */ wait_event_interruptible( @@ -607,12 +563,20 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, hfi1_cdbg(SDMA, "[%u:%u:%u] Using req/comp entry %u\n", dd->unit, uctxt->ctxt, fd->subctxt, info.comp_idx); req = pq->reqs + info.comp_idx; - memset(req, 0, sizeof(*req)); req->data_iovs = req_iovcnt(info.ctrl) - 1; /* subtract header vector */ + req->data_len = 0; req->pq = pq; req->cq = cq; req->status = -1; req->ahg_idx = -1; + req->iov_idx = 0; + req->sent = 0; + req->seqnum = 0; + req->seqcomp = 0; + req->seqsubmitted = 0; + req->tids = NULL; + req->done = 0; + req->has_error = 0; INIT_LIST_HEAD(&req->txps); memcpy(&req->info, &info, sizeof(info)); @@ -701,12 +665,14 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, /* Save all the IO vector structures */ for (i = 0; i < req->data_iovs; i++) { + req->iovs[i].offset = 0; INIT_LIST_HEAD(&req->iovs[i].list); memcpy(&req->iovs[i].iov, iovec + idx++, sizeof(req->iovs[i].iov)); ret = pin_vector_pages(req, &req->iovs[i]); if (ret) { + req->data_iovs = i; req->status = ret; goto free_req; } @@ -749,6 +715,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, } req->tids = tmp; req->n_tids = ntids; + req->tididx = 0; idx++; } @@ -791,12 +758,12 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, * request have been submitted to the SDMA engine. However, it * will not wait for send completions. */ - while (!test_bit(SDMA_REQ_SEND_DONE, &req->flags)) { + while (req->seqsubmitted != req->info.npkts) { ret = user_sdma_send_pkts(req, pcount); if (ret < 0) { if (ret != -EBUSY) { req->status = ret; - set_bit(SDMA_REQ_DONE_ERROR, &req->flags); + WRITE_ONCE(req->has_error, 1); if (ACCESS_ONCE(req->seqcomp) == req->seqsubmitted - 1) goto free_req; @@ -898,10 +865,8 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) pq = req->pq; /* If tx completion has reported an error, we are done. */ - if (test_bit(SDMA_REQ_HAS_ERROR, &req->flags)) { - set_bit(SDMA_REQ_DONE_ERROR, &req->flags); + if (READ_ONCE(req->has_error)) return -EFAULT; - } /* * Check if we might have sent the entire request already @@ -924,10 +889,8 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) * with errors. If so, we are not going to process any * more packets from this request. */ - if (test_bit(SDMA_REQ_HAS_ERROR, &req->flags)) { - set_bit(SDMA_REQ_DONE_ERROR, &req->flags); + if (READ_ONCE(req->has_error)) return -EFAULT; - } tx = kmem_cache_alloc(pq->txreq_cache, GFP_KERNEL); if (!tx) @@ -1024,11 +987,6 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) datalen); if (changes < 0) goto free_tx; - sdma_txinit_ahg(&tx->txreq, - SDMA_TXREQ_F_USE_AHG, - datalen, req->ahg_idx, changes, - req->ahg, sizeof(req->hdr), - user_sdma_txreq_cb); } } else { ret = sdma_txinit(&tx->txreq, 0, sizeof(req->hdr) + @@ -1105,7 +1063,7 @@ dosend: ret = sdma_send_txlist(req->sde, &pq->busy, &req->txps, &count); req->seqsubmitted += count; if (req->seqsubmitted == req->info.npkts) { - set_bit(SDMA_REQ_SEND_DONE, &req->flags); + WRITE_ONCE(req->done, 1); /* * The txreq has already been submitted to the HW queue * so we can free the AHG entry now. Corruption will not @@ -1155,14 +1113,23 @@ static int pin_vector_pages(struct user_sdma_request *req, struct hfi1_user_sdma_pkt_q *pq = req->pq; struct sdma_mmu_node *node = NULL; struct mmu_rb_node *rb_node; - - rb_node = hfi1_mmu_rb_extract(pq->handler, - (unsigned long)iovec->iov.iov_base, - iovec->iov.iov_len); - if (rb_node) + bool extracted; + + extracted = + hfi1_mmu_rb_remove_unless_exact(pq->handler, + (unsigned long) + iovec->iov.iov_base, + iovec->iov.iov_len, &rb_node); + if (rb_node) { node = container_of(rb_node, struct sdma_mmu_node, rb); - else - rb_node = NULL; + if (!extracted) { + atomic_inc(&node->refcount); + iovec->pages = node->pages; + iovec->npages = node->npages; + iovec->node = node; + return 0; + } + } if (!node) { node = kzalloc(sizeof(*node), GFP_KERNEL); @@ -1423,21 +1390,22 @@ done: } static int set_txreq_header_ahg(struct user_sdma_request *req, - struct user_sdma_txreq *tx, u32 len) + struct user_sdma_txreq *tx, u32 datalen) { + u32 ahg[AHG_KDETH_ARRAY_SIZE]; int diff = 0; u8 omfactor; /* KDETH.OM */ struct hfi1_user_sdma_pkt_q *pq = req->pq; struct hfi1_pkt_header *hdr = &req->hdr; u16 pbclen = le16_to_cpu(hdr->pbc[0]); - u32 val32, tidval = 0, lrhlen = get_lrh_len(*hdr, pad_len(len)); + u32 val32, tidval = 0, lrhlen = get_lrh_len(*hdr, pad_len(datalen)); if (PBC2LRH(pbclen) != lrhlen) { /* PBC.PbcLengthDWs */ - AHG_HEADER_SET(req->ahg, diff, 0, 0, 12, + AHG_HEADER_SET(ahg, diff, 0, 0, 12, cpu_to_le16(LRH2PBC(lrhlen))); /* LRH.PktLen (we need the full 16 bits due to byte swap) */ - AHG_HEADER_SET(req->ahg, diff, 3, 0, 16, + AHG_HEADER_SET(ahg, diff, 3, 0, 16, cpu_to_be16(lrhlen >> 2)); } @@ -1449,13 +1417,12 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, (HFI1_CAP_IS_KSET(EXTENDED_PSN) ? 0x7fffffff : 0xffffff); if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK)) val32 |= 1UL << 31; - AHG_HEADER_SET(req->ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16)); - AHG_HEADER_SET(req->ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff)); + AHG_HEADER_SET(ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16)); + AHG_HEADER_SET(ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff)); /* KDETH.Offset */ - AHG_HEADER_SET(req->ahg, diff, 15, 0, 16, + AHG_HEADER_SET(ahg, diff, 15, 0, 16, cpu_to_le16(req->koffset & 0xffff)); - AHG_HEADER_SET(req->ahg, diff, 15, 16, 16, - cpu_to_le16(req->koffset >> 16)); + AHG_HEADER_SET(ahg, diff, 15, 16, 16, cpu_to_le16(req->koffset >> 16)); if (req_opcode(req->info.ctrl) == EXPECTED) { __le16 val; @@ -1473,9 +1440,8 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, * we have to check again. */ if (++req->tididx > req->n_tids - 1 || - !req->tids[req->tididx]) { + !req->tids[req->tididx]) return -EINVAL; - } tidval = req->tids[req->tididx]; } omfactor = ((EXP_TID_GET(tidval, LEN) * @@ -1483,7 +1449,7 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, KDETH_OM_MAX_SIZE) ? KDETH_OM_LARGE_SHIFT : KDETH_OM_SMALL_SHIFT; /* KDETH.OM and KDETH.OFFSET (TID) */ - AHG_HEADER_SET(req->ahg, diff, 7, 0, 16, + AHG_HEADER_SET(ahg, diff, 7, 0, 16, ((!!(omfactor - KDETH_OM_SMALL_SHIFT)) << 15 | ((req->tidoffset >> omfactor) & 0x7fff))); @@ -1503,12 +1469,20 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, AHG_KDETH_INTR_SHIFT)); } - AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val); + AHG_HEADER_SET(ahg, diff, 7, 16, 14, val); } + if (diff < 0) + return diff; trace_hfi1_sdma_user_header_ahg(pq->dd, pq->ctxt, pq->subctxt, req->info.comp_idx, req->sde->this_idx, - req->ahg_idx, req->ahg, diff, tidval); + req->ahg_idx, ahg, diff, tidval); + sdma_txinit_ahg(&tx->txreq, + SDMA_TXREQ_F_USE_AHG, + datalen, req->ahg_idx, diff, + ahg, sizeof(req->hdr), + user_sdma_txreq_cb); + return diff; } @@ -1537,7 +1511,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status) if (status != SDMA_TXREQ_S_OK) { SDMA_DBG(req, "SDMA completion with error %d", status); - set_bit(SDMA_REQ_HAS_ERROR, &req->flags); + WRITE_ONCE(req->has_error, 1); } req->seqcomp = tx->seqnum; @@ -1556,8 +1530,8 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status) if (status != SDMA_TXREQ_S_OK) req->status = status; if (req->seqcomp == (ACCESS_ONCE(req->seqsubmitted) - 1) && - (test_bit(SDMA_REQ_SEND_DONE, &req->flags) || - test_bit(SDMA_REQ_DONE_ERROR, &req->flags))) { + (READ_ONCE(req->done) || + READ_ONCE(req->has_error))) { user_sdma_free_request(req, false); pq_update(pq); set_comp_state(pq, cq, idx, ERROR, req->status); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index e5b10aefe212..84c199d3e003 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -56,8 +56,7 @@ extern uint extended_psn; struct hfi1_user_sdma_pkt_q { - struct list_head list; - unsigned ctxt; + u16 ctxt; u16 subctxt; u16 n_max_reqs; atomic_t n_reqs; @@ -82,7 +81,8 @@ struct hfi1_user_sdma_comp_q { int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, struct hfi1_filedata *fd); -int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd); +int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, + struct hfi1_ctxtdata *uctxt); int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, struct iovec *iovec, unsigned long dim, unsigned long *count); diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 2d19f9bb434d..c88c03c11555 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -508,13 +508,14 @@ again: /* * Make sure the QP is ready and able to accept the given opcode. */ -static inline opcode_handler qp_ok(int opcode, struct hfi1_packet *packet) +static inline opcode_handler qp_ok(struct hfi1_packet *packet) { if (!(ib_rvt_state_ops[packet->qp->state] & RVT_PROCESS_RECV_OK)) return NULL; - if (((opcode & RVT_OPCODE_QP_MASK) == packet->qp->allowed_ops) || - (opcode == IB_OPCODE_CNP)) - return opcode_handler_tbl[opcode]; + if (((packet->opcode & RVT_OPCODE_QP_MASK) == + packet->qp->allowed_ops) || + (packet->opcode == IB_OPCODE_CNP)) + return opcode_handler_tbl[packet->opcode]; return NULL; } @@ -548,69 +549,34 @@ static u64 hfi1_fault_tx(struct rvt_qp *qp, u8 opcode, u64 pbc) return pbc; } -/** - * hfi1_ib_rcv - process an incoming packet - * @packet: data packet information - * - * This is called to process an incoming packet at interrupt level. - * - * Tlen is the length of the header + data + CRC in bytes. - */ -void hfi1_ib_rcv(struct hfi1_packet *packet) +static inline void hfi1_handle_packet(struct hfi1_packet *packet, + bool is_mcast) { + u32 qp_num; struct hfi1_ctxtdata *rcd = packet->rcd; - struct ib_header *hdr = packet->hdr; - u32 tlen = packet->tlen; struct hfi1_pportdata *ppd = rcd->ppd; struct hfi1_ibport *ibp = rcd_to_iport(rcd); struct rvt_dev_info *rdi = &ppd->dd->verbs_dev.rdi; opcode_handler packet_handler; unsigned long flags; - u32 qp_num; - int lnh; - u8 opcode; - u16 lid; - - /* Check for GRH */ - lnh = ib_get_lnh(hdr); - if (lnh == HFI1_LRH_BTH) { - packet->ohdr = &hdr->u.oth; - } else if (lnh == HFI1_LRH_GRH) { - u32 vtf; - - packet->ohdr = &hdr->u.l.oth; - if (hdr->u.l.grh.next_hdr != IB_GRH_NEXT_HDR) - goto drop; - vtf = be32_to_cpu(hdr->u.l.grh.version_tclass_flow); - if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION) - goto drop; - packet->rcv_flags |= HFI1_HAS_GRH; - } else { - goto drop; - } - trace_input_ibhdr(rcd->dd, hdr); + inc_opstats(packet->tlen, &rcd->opstats->stats[packet->opcode]); - opcode = ib_bth_get_opcode(packet->ohdr); - inc_opstats(tlen, &rcd->opstats->stats[opcode]); - - /* Get the destination QP number. */ - qp_num = be32_to_cpu(packet->ohdr->bth[1]) & RVT_QPN_MASK; - lid = ib_get_dlid(hdr); - if (unlikely((lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) && - (lid != be16_to_cpu(IB_LID_PERMISSIVE)))) { + if (unlikely(is_mcast)) { struct rvt_mcast *mcast; struct rvt_mcast_qp *p; - if (lnh != HFI1_LRH_GRH) + if (!packet->grh) goto drop; - mcast = rvt_mcast_find(&ibp->rvp, &hdr->u.l.grh.dgid, lid); + mcast = rvt_mcast_find(&ibp->rvp, + &packet->grh->dgid, + packet->dlid); if (!mcast) goto drop; list_for_each_entry_rcu(p, &mcast->qp_list, list) { packet->qp = p->qp; spin_lock_irqsave(&packet->qp->r_lock, flags); - packet_handler = qp_ok(opcode, packet); + packet_handler = qp_ok(packet); if (likely(packet_handler)) packet_handler(packet); else @@ -624,19 +590,21 @@ void hfi1_ib_rcv(struct hfi1_packet *packet) if (atomic_dec_return(&mcast->refcount) <= 1) wake_up(&mcast->wait); } else { + /* Get the destination QP number. */ + qp_num = ib_bth_get_qpn(packet->ohdr); rcu_read_lock(); packet->qp = rvt_lookup_qpn(rdi, &ibp->rvp, qp_num); if (!packet->qp) { rcu_read_unlock(); goto drop; } - if (unlikely(hfi1_dbg_fault_opcode(packet->qp, opcode, + if (unlikely(hfi1_dbg_fault_opcode(packet->qp, packet->opcode, true))) { rcu_read_unlock(); goto drop; } spin_lock_irqsave(&packet->qp->r_lock, flags); - packet_handler = qp_ok(opcode, packet); + packet_handler = qp_ok(packet); if (likely(packet_handler)) packet_handler(packet); else @@ -645,11 +613,29 @@ void hfi1_ib_rcv(struct hfi1_packet *packet) rcu_read_unlock(); } return; - drop: ibp->rvp.n_pkt_drops++; } +/** + * hfi1_ib_rcv - process an incoming packet + * @packet: data packet information + * + * This is called to process an incoming packet at interrupt level. + */ +void hfi1_ib_rcv(struct hfi1_packet *packet) +{ + struct hfi1_ctxtdata *rcd = packet->rcd; + bool is_mcast = false; + + if (unlikely(hfi1_check_mcast(packet->dlid))) + is_mcast = true; + + trace_input_ibhdr(rcd->dd, packet, + !!(packet->rhf & RHF_DC_INFO_SMASK)); + hfi1_handle_packet(packet, is_mcast); +} + /* * This is called from a timer to check for QPs * which need kernel memory in order to send a packet. @@ -863,7 +849,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps, /* No vl15 here */ /* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */ - pbc |= (!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT; + pbc |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT); if (unlikely(hfi1_dbg_fault_opcode(qp, opcode, false))) pbc = hfi1_fault_tx(qp, opcode, pbc); @@ -878,14 +864,15 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps, if (unlikely(ret)) goto bail_build; } - ret = sdma_send_txreq(tx->sde, &priv->s_iowait, &tx->txreq); + ret = sdma_send_txreq(tx->sde, &priv->s_iowait, &tx->txreq, + ps->pkts_sent); if (unlikely(ret < 0)) { if (ret == -ECOMM) goto bail_ecomm; return ret; } trace_sdma_output_ibhdr(dd_from_ibdev(qp->ibqp.device), - &ps->s_txreq->phdr.hdr); + &ps->s_txreq->phdr.hdr, ib_is_sc5(sc5)); return ret; bail_ecomm: @@ -935,7 +922,8 @@ static int pio_wait(struct rvt_qp *qp, dev->n_piodrain += !!(flag & RVT_S_WAIT_PIO_DRAIN); qp->s_flags |= flag; was_empty = list_empty(&sc->piowait); - list_add_tail(&priv->s_iowait.list, &sc->piowait); + iowait_queue(ps->pkts_sent, &priv->s_iowait, + &sc->piowait); priv->s_iowait.lock = &dev->iowait_lock; trace_hfi1_qpsleep(qp, RVT_S_WAIT_PIO); rvt_get_qp(qp); @@ -999,7 +987,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, u8 opcode = get_opcode(&tx->phdr.hdr); /* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */ - pbc |= (!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT; + pbc |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT); if (unlikely(hfi1_dbg_fault_opcode(qp, opcode, false))) pbc = hfi1_fault_tx(qp, opcode, pbc); pbc = create_pbc(ppd, pbc, qp->srate_mbps, vl, plen); @@ -1058,7 +1046,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, } trace_pio_output_ibhdr(dd_from_ibdev(qp->ibqp.device), - &ps->s_txreq->phdr.hdr); + &ps->s_txreq->phdr.hdr, ib_is_sc5(sc5)); pio_bail: if (qp->s_wqe) { @@ -1368,7 +1356,7 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num, props->lmc = ppd->lmc; /* OPA logical states match IB logical states */ props->state = driver_lstate(ppd); - props->phys_state = hfi1_ibphys_portstate(ppd); + props->phys_state = driver_pstate(ppd); props->gid_tbl_len = HFI1_GUIDS_PER_PORT; props->active_width = (u8)opa_width_to_ib(ppd->link_width_active); /* see rate_show() in ib core/sysfs.c */ @@ -1547,13 +1535,22 @@ static void init_ibport(struct hfi1_pportdata *ppd) ibp->sc_to_sl[i] = i; } + for (i = 0; i < RVT_MAX_TRAP_LISTS ; i++) + INIT_LIST_HEAD(&ibp->rvp.trap_lists[i].list); + setup_timer(&ibp->rvp.trap_timer, hfi1_handle_trap_timer, + (unsigned long)ibp); + spin_lock_init(&ibp->rvp.lock); /* Set the prefix to the default value (see ch. 4.1.1) */ ibp->rvp.gid_prefix = IB_DEFAULT_GID_PREFIX; ibp->rvp.sm_lid = 0; - /* Below should only set bits defined in OPA PortInfo.CapabilityMask */ + /* + * Below should only set bits defined in OPA PortInfo.CapabilityMask + * and PortInfo.CapabilityMask3 + */ ibp->rvp.port_cap_flags = IB_PORT_AUTO_MIGR_SUP | IB_PORT_CAP_MASK_NOTICE_SUP; + ibp->rvp.port_cap3_flags = OPA_CAP_MASK3_IsSharedSpaceSupported; ibp->rvp.pma_counter_select[0] = IB_PMA_PORT_XMIT_DATA; ibp->rvp.pma_counter_select[1] = IB_PMA_PORT_RCV_DATA; ibp->rvp.pma_counter_select[2] = IB_PMA_PORT_XMIT_PKTS; @@ -1564,14 +1561,13 @@ static void init_ibport(struct hfi1_pportdata *ppd) RCU_INIT_POINTER(ibp->rvp.qp[1], NULL); } -static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str, - size_t str_len) +static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str) { struct rvt_dev_info *rdi = ib_to_rvt(ibdev); struct hfi1_ibdev *dev = dev_from_rdi(rdi); u32 ver = dd_from_dev(dev)->dc8051_ver; - snprintf(str, str_len, "%u.%u.%u", dc8051_ver_maj(ver), + snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u", dc8051_ver_maj(ver), dc8051_ver_min(ver), dc8051_ver_patch(ver)); } diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index cd635d0c1d3b..34267c7ef85a 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -143,6 +143,7 @@ struct hfi1_pkt_state { unsigned long timeout_int; int cpu; bool in_thread; + bool pkts_sent; }; #define HFI1_PSN_CREDIT 16 @@ -236,8 +237,8 @@ static inline int hfi1_send_ok(struct rvt_qp *qp) /* * This must be called with s_lock held. */ -void hfi1_bad_pqkey(struct hfi1_ibport *ibp, __be16 trap_num, u32 key, u32 sl, - u32 qp1, u32 qp2, u16 lid1, u16 lid2); +void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl, + u32 qp1, u32 qp2, u16 lid1, u16 lid2); void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num); void hfi1_sys_guid_chg(struct hfi1_ibport *ibp); void hfi1_node_desc_chg(struct hfi1_ibport *ibp); @@ -307,8 +308,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet); void hfi1_rc_hdrerr( struct hfi1_ctxtdata *rcd, - struct ib_header *hdr, - u32 rcv_flags, + struct hfi1_packet *packet, struct rvt_qp *qp); u8 ah_to_sc(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr); @@ -346,8 +346,7 @@ static inline u8 get_opcode(struct ib_header *h) return be32_to_cpu(h->u.l.oth.bth[0]) >> 24; } -int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct ib_header *hdr, - int has_grh, struct rvt_qp *qp, u32 bth0); +int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet); u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr, const struct ib_global_route *grh, u32 hwords, u32 nwords); diff --git a/drivers/infiniband/hw/hfi1/vnic.h b/drivers/infiniband/hw/hfi1/vnic.h index 4a621cde4abb..eec7c1424991 100644 --- a/drivers/infiniband/hw/hfi1/vnic.h +++ b/drivers/infiniband/hw/hfi1/vnic.h @@ -103,6 +103,7 @@ struct hfi1_vnic_sdma { struct sdma_txreq stx; unsigned int state; u8 q_idx; + bool pkts_sent; }; /** diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c index 339f0cdd56d6..89b056489769 100644 --- a/drivers/infiniband/hw/hfi1/vnic_main.c +++ b/drivers/infiniband/hw/hfi1/vnic_main.c @@ -95,7 +95,7 @@ static int setup_vnic_ctxt(struct hfi1_devdata *dd, struct hfi1_ctxtdata *uctxt) if (HFI1_CAP_KGET_MASK(uctxt->flags, DMA_RTAIL)) rcvctrl_ops |= HFI1_RCVCTRL_TAILUPD_ENB; - hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt->ctxt); + hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt); uctxt->is_vnic = true; done: @@ -106,7 +106,7 @@ static int allocate_vnic_ctxt(struct hfi1_devdata *dd, struct hfi1_ctxtdata **vnic_ctxt) { struct hfi1_ctxtdata *uctxt; - unsigned int ctxt; + u16 ctxt; int ret; if (dd->flags & HFI1_FROZEN) @@ -156,11 +156,11 @@ static int allocate_vnic_ctxt(struct hfi1_devdata *dd, return ret; bail: /* - * hfi1_free_ctxtdata() also releases send_context - * structure if uctxt->sc is not null + * hfi1_rcd_put() will call hfi1_free_ctxtdata(), which will + * release send_context structure if uctxt->sc is not null */ dd->rcd[uctxt->ctxt] = NULL; - hfi1_free_ctxtdata(dd, uctxt); + hfi1_rcd_put(uctxt); dd_dev_dbg(dd, "vnic allocation failed. rc %d\n", ret); return ret; } @@ -186,7 +186,7 @@ static void deallocate_vnic_ctxt(struct hfi1_devdata *dd, HFI1_RCVCTRL_INTRAVAIL_DIS | HFI1_RCVCTRL_ONE_PKT_EGR_DIS | HFI1_RCVCTRL_NO_RHQ_DROP_DIS | - HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt->ctxt); + HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt); /* * VNIC contexts are allocated from user context pool. * Release them back to user context pool. @@ -208,7 +208,7 @@ static void deallocate_vnic_ctxt(struct hfi1_devdata *dd, hfi1_clear_ctxt_pkey(dd, uctxt); hfi1_stats.sps_ctxts--; - hfi1_free_ctxtdata(dd, uctxt); + hfi1_rcd_put(uctxt); } void hfi1_vnic_setup(struct hfi1_devdata *dd) @@ -751,6 +751,7 @@ static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo) rc = hfi1_vnic_allot_ctxt(dd, &dd->vnic.ctxt[i]); if (rc) break; + hfi1_rcd_get(dd->vnic.ctxt[i]); dd->vnic.ctxt[i]->vnic_q_idx = i; } @@ -762,6 +763,7 @@ static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo) */ while (i-- > dd->vnic.num_ctxt) { deallocate_vnic_ctxt(dd, dd->vnic.ctxt[i]); + hfi1_rcd_put(dd->vnic.ctxt[i]); dd->vnic.ctxt[i] = NULL; } goto alloc_fail; @@ -791,6 +793,7 @@ static void hfi1_vnic_deinit(struct hfi1_vnic_vport_info *vinfo) if (--dd->vnic.num_vports == 0) { for (i = 0; i < dd->vnic.num_ctxt; i++) { deallocate_vnic_ctxt(dd, dd->vnic.ctxt[i]); + hfi1_rcd_put(dd->vnic.ctxt[i]); dd->vnic.ctxt[i] = NULL; } hfi1_deinit_vnic_rsm(dd); diff --git a/drivers/infiniband/hw/hfi1/vnic_sdma.c b/drivers/infiniband/hw/hfi1/vnic_sdma.c index 51a817d3aa14..7815d7405462 100644 --- a/drivers/infiniband/hw/hfi1/vnic_sdma.c +++ b/drivers/infiniband/hw/hfi1/vnic_sdma.c @@ -198,11 +198,16 @@ int hfi1_vnic_send_dma(struct hfi1_devdata *dd, u8 q_idx, goto free_desc; tx->retry_count = 0; - ret = sdma_send_txreq(sde, &vnic_sdma->wait, &tx->txreq); + ret = sdma_send_txreq(sde, &vnic_sdma->wait, &tx->txreq, + vnic_sdma->pkts_sent); /* When -ECOMM, sdma callback will be called with ABORT status */ if (unlikely(ret && unlikely(ret != -ECOMM))) goto free_desc; + if (!ret) { + vnic_sdma->pkts_sent = true; + iowait_starve_clear(vnic_sdma->pkts_sent, &vnic_sdma->wait); + } return ret; free_desc: @@ -211,6 +216,8 @@ free_desc: tx_err: if (ret != -EBUSY) dev_kfree_skb_any(skb); + else + vnic_sdma->pkts_sent = false; return ret; } @@ -225,7 +232,8 @@ tx_err: static int hfi1_vnic_sdma_sleep(struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *txreq, - unsigned int seq) + uint seq, + bool pkts_sent) { struct hfi1_vnic_sdma *vnic_sdma = container_of(wait, struct hfi1_vnic_sdma, wait); @@ -239,7 +247,7 @@ static int hfi1_vnic_sdma_sleep(struct sdma_engine *sde, vnic_sdma->state = HFI1_VNIC_SDMA_Q_DEFERRED; write_seqlock(&dev->iowait_lock); if (list_empty(&vnic_sdma->wait.list)) - list_add_tail(&vnic_sdma->wait.list, &sde->dmawait); + iowait_queue(pkts_sent, wait, &sde->dmawait); write_sequnlock(&dev->iowait_lock); return -EBUSY; } diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig index e1a6e055cd60..61c93bbd230d 100644 --- a/drivers/infiniband/hw/hns/Kconfig +++ b/drivers/infiniband/hw/hns/Kconfig @@ -1,7 +1,7 @@ config INFINIBAND_HNS tristate "HNS RoCE Driver" depends on NET_VENDOR_HISILICON - depends on ARM64 && HNS && HNS_DSAF && HNS_ENET + depends on (ARM64 || (COMPILE_TEST && 64BIT)) && HNS && HNS_DSAF && HNS_ENET ---help--- This is a RoCE/RDMA driver for the Hisilicon RoCE engine. The engine is used in Hisilicon Hi1610 and more further ICT SoC. diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c index 605962f2828c..e1b433cdd5e2 100644 --- a/drivers/infiniband/hw/hns/hns_roce_alloc.c +++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c @@ -32,6 +32,7 @@ */ #include <linux/platform_device.h> +#include <linux/vmalloc.h> #include "hns_roce_device.h" int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj) diff --git a/drivers/infiniband/hw/hns/hns_roce_eq.c b/drivers/infiniband/hw/hns/hns_roce_eq.c index 50f864935a0e..b0f43735de1a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_eq.c +++ b/drivers/infiniband/hw/hns/hns_roce_eq.c @@ -31,6 +31,7 @@ */ #include <linux/platform_device.h> +#include <linux/interrupt.h> #include "hns_roce_common.h" #include "hns_roce_device.h" #include "hns_roce_eq.h" @@ -292,7 +293,7 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq) dev_warn(dev, "Unhandled event %d on EQ %d at index %u\n", event_type, eq->eqn, eq->cons_index); break; - }; + } eq->cons_index++; aeqes_found = 1; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 2540b65e242c..747efd1ae5a6 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -2023,7 +2023,6 @@ int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) struct hns_roce_cq *hr_cq = to_hr_cq(ibcq); u32 notification_flag; u32 doorbell[2]; - int ret = 0; notification_flag = (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ? CQ_DB_REQ_NOT : CQ_DB_REQ_NOT_SOL; @@ -2043,7 +2042,7 @@ int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) hns_roce_write64_k(doorbell, hr_cq->cq_db_l); - return ret; + return 0; } static int hns_roce_v1_poll_one(struct hns_roce_cq *hr_cq, diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 80fc01ffd8bd..e387360e3780 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -32,6 +32,7 @@ */ #include <linux/platform_device.h> +#include <linux/vmalloc.h> #include <rdma/ib_umem.h> #include "hns_roce_device.h" #include "hns_roce_cmd.h" diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 054c52699090..f5dd21c2d275 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -799,7 +799,7 @@ bool hns_roce_wq_overflow(struct hns_roce_wq *hr_wq, int nreq, cur = hr_wq->head - hr_wq->tail; if (likely(cur + nreq < hr_wq->max_post)) - return 0; + return false; hr_cq = to_hr_cq(ib_cq); spin_lock(&hr_cq->lock); diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 5a2fa743676c..a2b135039e5a 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -3687,8 +3687,6 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) cm_node->accelerated = 1; if (cm_node->accept_pend) { - if (!cm_node->listener) - i40iw_pr_err("cm_node->listener NULL for passive node\n"); atomic_dec(&cm_node->listener->pend_accepts_cnt); cm_node->accept_pend = 0; } @@ -4056,12 +4054,7 @@ static void i40iw_cm_event_connected(struct i40iw_cm_event *event) i40iw_modify_qp(&iwqp->ibqp, &attr, IB_QP_STATE, NULL); cm_node->accelerated = 1; - if (cm_node->accept_pend) { - if (!cm_node->listener) - i40iw_pr_err("listener is null for passive node\n"); - atomic_dec(&cm_node->listener->pend_accepts_cnt); - cm_node->accept_pend = 0; - } + return; error: diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index ae8463ff59a7..cc742c3132c6 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -77,7 +77,6 @@ MODULE_PARM_DESC(mpa_version, "MPA version to be used in MPA Req/Resp 1 or 2"); MODULE_AUTHOR("Intel Corporation, <e1000-rdma@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection X722 iWARP RDMA Driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); static struct i40e_client i40iw_client; static char i40iw_client_name[I40E_CLIENT_STR_LENGTH] = "i40iw"; diff --git a/drivers/infiniband/hw/i40iw/i40iw_pble.c b/drivers/infiniband/hw/i40iw/i40iw_pble.c index c87ba1617087..540aab5e502d 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_pble.c +++ b/drivers/infiniband/hw/i40iw/i40iw_pble.c @@ -269,10 +269,8 @@ static enum i40iw_status_code add_bp_pages(struct i40iw_sc_dev *dev, status = i40iw_add_sd_table_entry(dev->hw, hmc_info, info->idx.sd_idx, I40IW_SD_TYPE_PAGED, I40IW_HMC_DIRECT_BP_SIZE); - if (status) { - i40iw_free_vmalloc_mem(dev->hw, chunk); - return status; - } + if (status) + goto error; if (!dev->is_pf) { status = i40iw_vchnl_vf_add_hmc_objs(dev, I40IW_HMC_IW_PBLE, fpm_to_idx(pble_rsrc, @@ -280,8 +278,7 @@ static enum i40iw_status_code add_bp_pages(struct i40iw_sc_dev *dev, (info->pages << PBLE_512_SHIFT)); if (status) { i40iw_pr_err("allocate PBLEs in the PF. Error %i\n", status); - i40iw_free_vmalloc_mem(dev->hw, chunk); - return status; + goto error; } } addr = chunk->vaddr; diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index 7f5583d83622..c2cab20c4bc5 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -949,14 +949,16 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_vsi *vsi, ret = i40iw_puda_qp_create(rsrc); } if (ret) { - i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error qp_create\n", __func__); + i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error qp_create\n", + __func__); goto error; } rsrc->completion = PUDA_QP_CREATED; ret = i40iw_puda_allocbufs(rsrc, info->tx_buf_cnt + info->rq_size); if (ret) { - i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error allloc_buf\n", __func__); + i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error alloc_buf\n", + __func__); goto error; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 02d871db7ca5..1aa411034a27 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -2584,13 +2584,12 @@ static const char * const i40iw_hw_stat_names[] = { "iwRdmaInv" }; -static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str, - size_t str_len) +static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str) { u32 firmware_version = I40IW_FW_VERSION; - snprintf(str, str_len, "%u.%u", firmware_version, - (firmware_version & 0x000000ff)); + snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u", firmware_version, + (firmware_version & 0x000000ff)); } /** diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c index ea24230ea0d4..5a897b0106a9 100644 --- a/drivers/infiniband/hw/mlx4/alias_GUID.c +++ b/drivers/infiniband/hw/mlx4/alias_GUID.c @@ -528,7 +528,7 @@ static int set_guid_rec(struct ib_device *ibdev, memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec)); - guid_info_rec.lid = cpu_to_be16(attr.lid); + guid_info_rec.lid = cpu_to_be16((u16)attr.lid); guid_info_rec.block_num = index; memcpy(guid_info_rec.guid_info_list, rec_det->all_recs, diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index ff931c580557..95382faa7ad1 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -218,6 +218,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, goto err_mtt; uar = &to_mucontext(context)->uar; + cq->mcq.usage = MLX4_RES_USAGE_USER_VERBS; } else { err = mlx4_db_alloc(dev->dev, &cq->db, 1); if (err) @@ -233,6 +234,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, goto err_db; uar = &dev->priv_uar; + cq->mcq.usage = MLX4_RES_USAGE_DRIVER; } if (dev->eq_table) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 21d31cb1325f..04fb44e7699e 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -169,7 +169,7 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, op_modifier |= 0x4; - in_modifier |= in_wc->slid << 16; + in_modifier |= ib_slid_cpu16(in_wc->slid) << 16; } err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier, @@ -625,7 +625,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2); } else { tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12); - tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid); + tun_mad->hdr.slid_mac_47_32 = ib_slid_be16(wc->slid); } ib_dma_sync_single_for_device(&dev->ib_dev, @@ -826,7 +826,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, } } - slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE); + slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE); if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) { forward_trap(to_mdev(ibdev), port_num, in_mad); @@ -860,7 +860,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, in_mad->mad_hdr.method == IB_MGMT_METHOD_SET && in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO && !ib_query_port(ibdev, port_num, &pattr)) - prev_lid = pattr.lid; + prev_lid = (u16)pattr.lid; err = mlx4_MAD_IFC(to_mdev(ibdev), (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) | diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index d1b43cbbfea7..c636842c5be0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -70,7 +70,6 @@ MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); int mlx4_ib_sm_guid_assign = 0; module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444); @@ -81,6 +80,8 @@ static const char mlx4_ib_version[] = DRV_VERSION "\n"; static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init); +static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device, + u8 port_num); static struct workqueue_struct *wq; @@ -552,6 +553,16 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->timestamp_mask = 0xFFFFFFFFFFFFULL; props->max_ah = INT_MAX; + if ((dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) && + (mlx4_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET || + mlx4_ib_port_link_layer(ibdev, 2) == IB_LINK_LAYER_ETHERNET)) { + props->rss_caps.max_rwq_indirection_tables = props->max_qp; + props->rss_caps.max_rwq_indirection_table_size = + dev->dev->caps.max_rss_tbl_sz; + props->rss_caps.supported_qpts = 1 << IB_QPT_RAW_PACKET; + props->max_wq_type_rq = props->max_qp; + } + if (!mlx4_is_slave(dev->dev)) err = mlx4_get_internal_clock_params(dev->dev, &clock_params); @@ -563,6 +574,13 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, } } + if (uhw->outlen >= resp.response_length + + sizeof(resp.max_inl_recv_sz)) { + resp.response_length += sizeof(resp.max_inl_recv_sz); + resp.max_inl_recv_sz = dev->dev->caps.max_rq_sg * + sizeof(struct mlx4_wqe_data_seg); + } + if (uhw->outlen) { err = ib_copy_to_udata(uhw, &resp, resp.response_length); if (err) @@ -1069,6 +1087,9 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev, INIT_LIST_HEAD(&context->db_page_list); mutex_init(&context->db_page_mutex); + INIT_LIST_HEAD(&context->wqn_ranges_list); + mutex_init(&context->wqn_ranges_mutex); + if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3)); else @@ -2566,12 +2587,11 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_fw_ver_str(struct ib_device *device, char *str, - size_t str_len) +static void get_fw_ver_str(struct ib_device *device, char *str) { struct mlx4_ib_dev *dev = container_of(device, struct mlx4_ib_dev, ib_dev); - snprintf(str, str_len, "%d.%d.%d", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d", (int) (dev->dev->caps.fw_ver >> 32), (int) (dev->dev->caps.fw_ver >> 16) & 0xffff, (int) dev->dev->caps.fw_ver & 0xffff); @@ -2713,6 +2733,26 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.get_dev_fw_str = get_fw_ver_str; ibdev->ib_dev.disassociate_ucontext = mlx4_ib_disassociate_ucontext; + if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) && + ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) == + IB_LINK_LAYER_ETHERNET) || + (mlx4_ib_port_link_layer(&ibdev->ib_dev, 2) == + IB_LINK_LAYER_ETHERNET))) { + ibdev->ib_dev.create_wq = mlx4_ib_create_wq; + ibdev->ib_dev.modify_wq = mlx4_ib_modify_wq; + ibdev->ib_dev.destroy_wq = mlx4_ib_destroy_wq; + ibdev->ib_dev.create_rwq_ind_table = + mlx4_ib_create_rwq_ind_table; + ibdev->ib_dev.destroy_rwq_ind_table = + mlx4_ib_destroy_rwq_ind_table; + ibdev->ib_dev.uverbs_ex_cmd_mask |= + (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | + (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | + (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | + (1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | + (1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL); + } + if (!mlx4_is_slave(ibdev->dev)) { ibdev->ib_dev.alloc_fmr = mlx4_ib_fmr_alloc; ibdev->ib_dev.map_phys_fmr = mlx4_ib_map_phys_fmr; @@ -2772,7 +2812,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) allocated = 0; if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) == IB_LINK_LAYER_ETHERNET) { - err = mlx4_counter_alloc(ibdev->dev, &counter_index); + err = mlx4_counter_alloc(ibdev->dev, &counter_index, + MLX4_RES_USAGE_DRIVER); /* if failed to allocate a new counter, use default */ if (err) counter_index = @@ -2827,7 +2868,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS; err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count, MLX4_IB_UC_STEER_QPN_ALIGN, - &ibdev->steer_qpn_base, 0); + &ibdev->steer_qpn_base, 0, + MLX4_RES_USAGE_DRIVER); if (err) goto err_counter; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 9db82e67e959..1fa19820355a 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -46,6 +46,7 @@ #include <linux/mlx4/device.h> #include <linux/mlx4/doorbell.h> +#include <linux/mlx4/qp.h> #define MLX4_IB_DRV_NAME "mlx4_ib" @@ -88,6 +89,8 @@ struct mlx4_ib_ucontext { struct list_head db_page_list; struct mutex db_page_mutex; struct mlx4_ib_vma_private_data hw_bar_info[HW_BAR_COUNT]; + struct list_head wqn_ranges_list; + struct mutex wqn_ranges_mutex; /* protect wqn_ranges_list */ }; struct mlx4_ib_pd { @@ -289,8 +292,25 @@ struct mlx4_roce_smac_vlan_info { int update_vid; }; +struct mlx4_wqn_range { + int base_wqn; + int size; + int refcount; + bool dirty; + struct list_head list; +}; + +struct mlx4_ib_rss { + unsigned int base_qpn_tbl_sz; + u8 flags; + u8 rss_key[MLX4_EN_RSS_KEY_SIZE]; +}; + struct mlx4_ib_qp { - struct ib_qp ibqp; + union { + struct ib_qp ibqp; + struct ib_wq ibwq; + }; struct mlx4_qp mqp; struct mlx4_buf buf; @@ -318,6 +338,7 @@ struct mlx4_ib_qp { u8 sq_no_prefetch; u8 state; int mlx_type; + u32 inl_recv_sz; struct list_head gid_list; struct list_head steering_rules; struct mlx4_ib_buf *sqp_proxy_rcv; @@ -328,6 +349,10 @@ struct mlx4_ib_qp { struct list_head cq_recv_list; struct list_head cq_send_list; struct counter_index *counter_index; + struct mlx4_wqn_range *wqn_range; + /* Number of RSS QP parents that uses this WQ */ + u32 rss_usecnt; + struct mlx4_ib_rss *rss_ctx; }; struct mlx4_ib_srq { @@ -623,6 +648,8 @@ struct mlx4_uverbs_ex_query_device_resp { __u32 comp_mask; __u32 response_length; __u64 hca_core_clock_offset; + __u32 max_inl_recv_sz; + __u32 reserved; }; static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev) @@ -890,4 +917,17 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev, void mlx4_ib_sl2vl_update(struct mlx4_ib_dev *mdev, int port); +struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd, + struct ib_wq_init_attr *init_attr, + struct ib_udata *udata); +int mlx4_ib_destroy_wq(struct ib_wq *wq); +int mlx4_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr, + u32 wq_attr_mask, struct ib_udata *udata); + +struct ib_rwq_ind_table +*mlx4_ib_create_rwq_ind_table(struct ib_device *device, + struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); +int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); + #endif /* MLX4_IB_H */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 75c0e6c5dd56..e42acfb20588 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -53,6 +53,7 @@ static void mlx4_ib_lock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *recv_cq); static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *recv_cq); +static int _mlx4_ib_modify_wq(struct ib_wq *ibwq, enum ib_wq_state new_state); enum { MLX4_IB_ACK_REQ_FREQ = 8, @@ -116,6 +117,11 @@ static const __be32 mlx4_ib_opcode[] = { [IB_WR_MASKED_ATOMIC_FETCH_AND_ADD] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA), }; +enum mlx4_ib_source_type { + MLX4_IB_QP_SRC = 0, + MLX4_IB_RWQ_SRC = 1, +}; + static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp) { return container_of(mqp, struct mlx4_ib_sqp, qp); @@ -330,6 +336,12 @@ static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type) } } +static void mlx4_ib_wq_event(struct mlx4_qp *qp, enum mlx4_event type) +{ + pr_warn_ratelimited("Unexpected event type %d on WQ 0x%06x. Events are not supported for WQs\n", + type, qp->qpn); +} + static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags) { /* @@ -377,7 +389,8 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags) } static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap, - int is_user, int has_rq, struct mlx4_ib_qp *qp) + int is_user, int has_rq, struct mlx4_ib_qp *qp, + u32 inl_recv_sz) { /* Sanity check RQ size before proceeding */ if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE || @@ -385,18 +398,24 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap, return -EINVAL; if (!has_rq) { - if (cap->max_recv_wr) + if (cap->max_recv_wr || inl_recv_sz) return -EINVAL; qp->rq.wqe_cnt = qp->rq.max_gs = 0; } else { + u32 max_inl_recv_sz = dev->dev->caps.max_rq_sg * + sizeof(struct mlx4_wqe_data_seg); + u32 wqe_size; + /* HW requires >= 1 RQ entry with >= 1 gather entry */ - if (is_user && (!cap->max_recv_wr || !cap->max_recv_sge)) + if (is_user && (!cap->max_recv_wr || !cap->max_recv_sge || + inl_recv_sz > max_inl_recv_sz)) return -EINVAL; qp->rq.wqe_cnt = roundup_pow_of_two(max(1U, cap->max_recv_wr)); qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge)); - qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg)); + wqe_size = qp->rq.max_gs * sizeof(struct mlx4_wqe_data_seg); + qp->rq.wqe_shift = ilog2(max_t(u32, wqe_size, inl_recv_sz)); } /* leave userspace return values as they were, so as not to break ABI */ @@ -632,7 +651,297 @@ static void mlx4_ib_free_qp_counter(struct mlx4_ib_dev *dev, qp->counter_index = NULL; } +static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx, + struct ib_qp_init_attr *init_attr, + struct mlx4_ib_create_qp_rss *ucmd) +{ + rss_ctx->base_qpn_tbl_sz = init_attr->rwq_ind_tbl->ind_tbl[0]->wq_num | + (init_attr->rwq_ind_tbl->log_ind_tbl_size << 24); + + if ((ucmd->rx_hash_function == MLX4_IB_RX_HASH_FUNC_TOEPLITZ) && + (dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) { + memcpy(rss_ctx->rss_key, ucmd->rx_hash_key, + MLX4_EN_RSS_KEY_SIZE); + } else { + pr_debug("RX Hash function is not supported\n"); + return (-EOPNOTSUPP); + } + + if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) && + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) { + rss_ctx->flags = MLX4_RSS_IPV4; + } else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) || + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) { + pr_debug("RX Hash fields_mask is not supported - both IPv4 SRC and DST must be set\n"); + return (-EOPNOTSUPP); + } + + if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV6) && + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV6)) { + rss_ctx->flags |= MLX4_RSS_IPV6; + } else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV6) || + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV6)) { + pr_debug("RX Hash fields_mask is not supported - both IPv6 SRC and DST must be set\n"); + return (-EOPNOTSUPP); + } + + if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_UDP) && + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_UDP)) { + if (!(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UDP_RSS)) { + pr_debug("RX Hash fields_mask for UDP is not supported\n"); + return (-EOPNOTSUPP); + } + + if (rss_ctx->flags & MLX4_RSS_IPV4) { + rss_ctx->flags |= MLX4_RSS_UDP_IPV4; + } else if (rss_ctx->flags & MLX4_RSS_IPV6) { + rss_ctx->flags |= MLX4_RSS_UDP_IPV6; + } else { + pr_debug("RX Hash fields_mask is not supported - UDP must be set with IPv4 or IPv6\n"); + return (-EOPNOTSUPP); + } + } else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_UDP) || + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_UDP)) { + pr_debug("RX Hash fields_mask is not supported - both UDP SRC and DST must be set\n"); + return (-EOPNOTSUPP); + } + + if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) && + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) { + if (rss_ctx->flags & MLX4_RSS_IPV4) { + rss_ctx->flags |= MLX4_RSS_TCP_IPV4; + } else if (rss_ctx->flags & MLX4_RSS_IPV6) { + rss_ctx->flags |= MLX4_RSS_TCP_IPV6; + } else { + pr_debug("RX Hash fields_mask is not supported - TCP must be set with IPv4 or IPv6\n"); + return (-EOPNOTSUPP); + } + + } else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) || + (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) { + pr_debug("RX Hash fields_mask is not supported - both TCP SRC and DST must be set\n"); + return (-EOPNOTSUPP); + } + + return 0; +} + +static int create_qp_rss(struct mlx4_ib_dev *dev, struct ib_pd *ibpd, + struct ib_qp_init_attr *init_attr, + struct mlx4_ib_create_qp_rss *ucmd, + struct mlx4_ib_qp *qp) +{ + int qpn; + int err; + + qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS; + + err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn, 0, qp->mqp.usage); + if (err) + return err; + + err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp); + if (err) + goto err_qpn; + + mutex_init(&qp->mutex); + + INIT_LIST_HEAD(&qp->gid_list); + INIT_LIST_HEAD(&qp->steering_rules); + + qp->mlx4_ib_qp_type = MLX4_IB_QPT_RAW_ETHERTYPE; + qp->state = IB_QPS_RESET; + + /* Set dummy send resources to be compatible with HV and PRM */ + qp->sq_no_prefetch = 1; + qp->sq.wqe_cnt = 1; + qp->sq.wqe_shift = MLX4_IB_MIN_SQ_STRIDE; + qp->buf_size = qp->sq.wqe_cnt << MLX4_IB_MIN_SQ_STRIDE; + qp->mtt = (to_mqp( + (struct ib_qp *)init_attr->rwq_ind_tbl->ind_tbl[0]))->mtt; + + qp->rss_ctx = kzalloc(sizeof(*qp->rss_ctx), GFP_KERNEL); + if (!qp->rss_ctx) { + err = -ENOMEM; + goto err_qp_alloc; + } + + err = set_qp_rss(dev, qp->rss_ctx, init_attr, ucmd); + if (err) + goto err; + + return 0; + +err: + kfree(qp->rss_ctx); + +err_qp_alloc: + mlx4_qp_remove(dev->dev, &qp->mqp); + mlx4_qp_free(dev->dev, &qp->mqp); + +err_qpn: + mlx4_qp_release_range(dev->dev, qpn, 1); + return err; +} + +static struct ib_qp *_mlx4_ib_create_qp_rss(struct ib_pd *pd, + struct ib_qp_init_attr *init_attr, + struct ib_udata *udata) +{ + struct mlx4_ib_qp *qp; + struct mlx4_ib_create_qp_rss ucmd = {}; + size_t required_cmd_sz; + int err; + + if (!udata) { + pr_debug("RSS QP with NULL udata\n"); + return ERR_PTR(-EINVAL); + } + + if (udata->outlen) + return ERR_PTR(-EOPNOTSUPP); + + required_cmd_sz = offsetof(typeof(ucmd), reserved1) + + sizeof(ucmd.reserved1); + if (udata->inlen < required_cmd_sz) { + pr_debug("invalid inlen\n"); + return ERR_PTR(-EINVAL); + } + + if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen))) { + pr_debug("copy failed\n"); + return ERR_PTR(-EFAULT); + } + + if (ucmd.comp_mask || ucmd.reserved1) + return ERR_PTR(-EOPNOTSUPP); + + if (udata->inlen > sizeof(ucmd) && + !ib_is_udata_cleared(udata, sizeof(ucmd), + udata->inlen - sizeof(ucmd))) { + pr_debug("inlen is not supported\n"); + return ERR_PTR(-EOPNOTSUPP); + } + + if (init_attr->qp_type != IB_QPT_RAW_PACKET) { + pr_debug("RSS QP with unsupported QP type %d\n", + init_attr->qp_type); + return ERR_PTR(-EOPNOTSUPP); + } + + if (init_attr->create_flags) { + pr_debug("RSS QP doesn't support create flags\n"); + return ERR_PTR(-EOPNOTSUPP); + } + + if (init_attr->send_cq || init_attr->cap.max_send_wr) { + pr_debug("RSS QP with unsupported send attributes\n"); + return ERR_PTR(-EOPNOTSUPP); + } + + qp = kzalloc(sizeof(*qp), GFP_KERNEL); + if (!qp) + return ERR_PTR(-ENOMEM); + + qp->pri.vid = 0xFFFF; + qp->alt.vid = 0xFFFF; + + err = create_qp_rss(to_mdev(pd->device), pd, init_attr, &ucmd, qp); + if (err) { + kfree(qp); + return ERR_PTR(err); + } + + qp->ibqp.qp_num = qp->mqp.qpn; + + return &qp->ibqp; +} + +/* + * This function allocates a WQN from a range which is consecutive and aligned + * to its size. In case the range is full, then it creates a new range and + * allocates WQN from it. The new range will be used for following allocations. + */ +static int mlx4_ib_alloc_wqn(struct mlx4_ib_ucontext *context, + struct mlx4_ib_qp *qp, int range_size, int *wqn) +{ + struct mlx4_ib_dev *dev = to_mdev(context->ibucontext.device); + struct mlx4_wqn_range *range; + int err = 0; + + mutex_lock(&context->wqn_ranges_mutex); + + range = list_first_entry_or_null(&context->wqn_ranges_list, + struct mlx4_wqn_range, list); + + if (!range || (range->refcount == range->size) || range->dirty) { + range = kzalloc(sizeof(*range), GFP_KERNEL); + if (!range) { + err = -ENOMEM; + goto out; + } + + err = mlx4_qp_reserve_range(dev->dev, range_size, + range_size, &range->base_wqn, 0, + qp->mqp.usage); + if (err) { + kfree(range); + goto out; + } + + range->size = range_size; + list_add(&range->list, &context->wqn_ranges_list); + } else if (range_size != 1) { + /* + * Requesting a new range (>1) when last range is still open, is + * not valid. + */ + err = -EINVAL; + goto out; + } + + qp->wqn_range = range; + + *wqn = range->base_wqn + range->refcount; + + range->refcount++; + +out: + mutex_unlock(&context->wqn_ranges_mutex); + + return err; +} + +static void mlx4_ib_release_wqn(struct mlx4_ib_ucontext *context, + struct mlx4_ib_qp *qp, bool dirty_release) +{ + struct mlx4_ib_dev *dev = to_mdev(context->ibucontext.device); + struct mlx4_wqn_range *range; + + mutex_lock(&context->wqn_ranges_mutex); + + range = qp->wqn_range; + + range->refcount--; + if (!range->refcount) { + mlx4_qp_release_range(dev->dev, range->base_wqn, + range->size); + list_del(&range->list); + kfree(range); + } else if (dirty_release) { + /* + * A range which one of its WQNs is destroyed, won't be able to be + * reused for further WQN allocations. + * The next created WQ will allocate a new range. + */ + range->dirty = 1; + } + + mutex_unlock(&context->wqn_ranges_mutex); +} + static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, + enum mlx4_ib_source_type src, struct ib_qp_init_attr *init_attr, struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp) @@ -645,6 +954,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, enum mlx4_ib_qp_type qp_type = (enum mlx4_ib_qp_type) init_attr->qp_type; struct mlx4_ib_cq *mcq; unsigned long flags; + int range_size = 0; /* When tunneling special qps, we use a plain UD qp */ if (sqpn) { @@ -719,26 +1029,71 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) qp->sq_signal_bits = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE); - err = set_rq_size(dev, &init_attr->cap, !!pd->uobject, qp_has_rq(init_attr), qp); - if (err) - goto err; if (pd->uobject) { - struct mlx4_ib_create_qp ucmd; + union { + struct mlx4_ib_create_qp qp; + struct mlx4_ib_create_wq wq; + } ucmd; + size_t copy_len; - if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) { + copy_len = (src == MLX4_IB_QP_SRC) ? + sizeof(struct mlx4_ib_create_qp) : + min(sizeof(struct mlx4_ib_create_wq), udata->inlen); + + if (ib_copy_from_udata(&ucmd, udata, copy_len)) { err = -EFAULT; goto err; } - qp->sq_no_prefetch = ucmd.sq_no_prefetch; + if (src == MLX4_IB_RWQ_SRC) { + if (ucmd.wq.comp_mask || ucmd.wq.reserved1 || + ucmd.wq.reserved[0] || ucmd.wq.reserved[1] || + ucmd.wq.reserved[2]) { + pr_debug("user command isn't supported\n"); + err = -EOPNOTSUPP; + goto err; + } + + if (ucmd.wq.log_range_size > + ilog2(dev->dev->caps.max_rss_tbl_sz)) { + pr_debug("WQN range size must be equal or smaller than %d\n", + dev->dev->caps.max_rss_tbl_sz); + err = -EOPNOTSUPP; + goto err; + } + range_size = 1 << ucmd.wq.log_range_size; + } else { + qp->inl_recv_sz = ucmd.qp.inl_recv_sz; + } - err = set_user_sq_size(dev, qp, &ucmd); + err = set_rq_size(dev, &init_attr->cap, !!pd->uobject, + qp_has_rq(init_attr), qp, qp->inl_recv_sz); if (err) goto err; - qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, - qp->buf_size, 0, 0); + if (src == MLX4_IB_QP_SRC) { + qp->sq_no_prefetch = ucmd.qp.sq_no_prefetch; + + err = set_user_sq_size(dev, qp, + (struct mlx4_ib_create_qp *) + &ucmd); + if (err) + goto err; + } else { + qp->sq_no_prefetch = 1; + qp->sq.wqe_cnt = 1; + qp->sq.wqe_shift = MLX4_IB_MIN_SQ_STRIDE; + /* Allocated buffer expects to have at least that SQ + * size. + */ + qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) + + (qp->sq.wqe_cnt << qp->sq.wqe_shift); + } + + qp->umem = ib_umem_get(pd->uobject->context, + (src == MLX4_IB_QP_SRC) ? ucmd.qp.buf_addr : + ucmd.wq.buf_addr, qp->buf_size, 0, 0); if (IS_ERR(qp->umem)) { err = PTR_ERR(qp->umem); goto err; @@ -755,11 +1110,18 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (qp_has_rq(init_attr)) { err = mlx4_ib_db_map_user(to_mucontext(pd->uobject->context), - ucmd.db_addr, &qp->db); + (src == MLX4_IB_QP_SRC) ? ucmd.qp.db_addr : + ucmd.wq.db_addr, &qp->db); if (err) goto err_mtt; } + qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS; } else { + err = set_rq_size(dev, &init_attr->cap, !!pd->uobject, + qp_has_rq(init_attr), qp, 0); + if (err) + goto err; + qp->sq_no_prefetch = 0; if (init_attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO) @@ -826,6 +1188,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, err = -ENOMEM; goto err_wrid; } + qp->mqp.usage = MLX4_RES_USAGE_DRIVER; } if (sqpn) { @@ -836,6 +1199,11 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, goto err_wrid; } } + } else if (src == MLX4_IB_RWQ_SRC) { + err = mlx4_ib_alloc_wqn(to_mucontext(pd->uobject->context), qp, + range_size, &qpn); + if (err) + goto err_wrid; } else { /* Raw packet QPNs may not have bits 6,7 set in their qp_num; * otherwise, the WQE BlueFlame setup flow wrongly causes @@ -845,13 +1213,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, (init_attr->cap.max_send_wr ? MLX4_RESERVE_ETH_BF_QP : 0) | (init_attr->cap.max_recv_wr ? - MLX4_RESERVE_A0_QP : 0)); + MLX4_RESERVE_A0_QP : 0), + qp->mqp.usage); else if (qp->flags & MLX4_IB_QP_NETIF) err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn); else err = mlx4_qp_reserve_range(dev->dev, 1, 1, - &qpn, 0); + &qpn, 0, qp->mqp.usage); if (err) goto err_proxy; } @@ -873,7 +1242,9 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, */ qp->doorbell_qpn = swab32(qp->mqp.qpn << 8); - qp->mqp.event = mlx4_ib_qp_event; + qp->mqp.event = (src == MLX4_IB_QP_SRC) ? mlx4_ib_qp_event : + mlx4_ib_wq_event; + if (!*caller_qp) *caller_qp = qp; @@ -900,6 +1271,9 @@ err_qpn: if (!sqpn) { if (qp->flags & MLX4_IB_QP_NETIF) mlx4_ib_steer_qp_free(dev, qpn, 1); + else if (src == MLX4_IB_RWQ_SRC) + mlx4_ib_release_wqn(to_mucontext(pd->uobject->context), + qp, 0); else mlx4_qp_release_range(dev->dev, qpn, 1); } @@ -998,7 +1372,7 @@ static struct mlx4_ib_pd *get_pd(struct mlx4_ib_qp *qp) return to_mpd(qp->ibqp.pd); } -static void get_cqs(struct mlx4_ib_qp *qp, +static void get_cqs(struct mlx4_ib_qp *qp, enum mlx4_ib_source_type src, struct mlx4_ib_cq **send_cq, struct mlx4_ib_cq **recv_cq) { switch (qp->ibqp.qp_type) { @@ -1011,14 +1385,46 @@ static void get_cqs(struct mlx4_ib_qp *qp, *recv_cq = *send_cq; break; default: - *send_cq = to_mcq(qp->ibqp.send_cq); - *recv_cq = to_mcq(qp->ibqp.recv_cq); + *recv_cq = (src == MLX4_IB_QP_SRC) ? to_mcq(qp->ibqp.recv_cq) : + to_mcq(qp->ibwq.cq); + *send_cq = (src == MLX4_IB_QP_SRC) ? to_mcq(qp->ibqp.send_cq) : + *recv_cq; break; } } +static void destroy_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) +{ + if (qp->state != IB_QPS_RESET) { + int i; + + for (i = 0; i < (1 << qp->ibqp.rwq_ind_tbl->log_ind_tbl_size); + i++) { + struct ib_wq *ibwq = qp->ibqp.rwq_ind_tbl->ind_tbl[i]; + struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq); + + mutex_lock(&wq->mutex); + + wq->rss_usecnt--; + + mutex_unlock(&wq->mutex); + } + + if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state), + MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp)) + pr_warn("modify QP %06x to RESET failed.\n", + qp->mqp.qpn); + } + + mlx4_qp_remove(dev->dev, &qp->mqp); + mlx4_qp_free(dev->dev, &qp->mqp); + mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1); + del_gid_entries(qp); + kfree(qp->rss_ctx); +} + static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, - int is_user) + enum mlx4_ib_source_type src, int is_user) { struct mlx4_ib_cq *send_cq, *recv_cq; unsigned long flags; @@ -1051,7 +1457,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, } } - get_cqs(qp, &send_cq, &recv_cq); + get_cqs(qp, src, &send_cq, &recv_cq); spin_lock_irqsave(&dev->reset_flow_resource_lock, flags); mlx4_ib_lock_cqs(send_cq, recv_cq); @@ -1077,6 +1483,9 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) { if (qp->flags & MLX4_IB_QP_NETIF) mlx4_ib_steer_qp_free(dev, qp->mqp.qpn, 1); + else if (src == MLX4_IB_RWQ_SRC) + mlx4_ib_release_wqn(to_mucontext( + qp->ibwq.uobject->context), qp, 1); else mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1); } @@ -1084,9 +1493,12 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, mlx4_mtt_cleanup(dev->dev, &qp->mtt); if (is_user) { - if (qp->rq.wqe_cnt) - mlx4_ib_db_unmap_user(to_mucontext(qp->ibqp.uobject->context), - &qp->db); + if (qp->rq.wqe_cnt) { + struct mlx4_ib_ucontext *mcontext = !src ? + to_mucontext(qp->ibqp.uobject->context) : + to_mucontext(qp->ibwq.uobject->context); + mlx4_ib_db_unmap_user(mcontext, &qp->db); + } ib_umem_release(qp->umem); } else { kvfree(qp->sq.wrid); @@ -1128,6 +1540,9 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, int sup_u_create_flags = MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK; u16 xrcdn = 0; + if (init_attr->rwq_ind_tbl) + return _mlx4_ib_create_qp_rss(pd, init_attr, udata); + /* * We only support LSO, vendor flag1, and multicast loopback blocking, * and only for kernel UD QPs. @@ -1182,8 +1597,8 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, /* fall through */ case IB_QPT_UD: { - err = create_qp_common(to_mdev(pd->device), pd, init_attr, - udata, 0, &qp); + err = create_qp_common(to_mdev(pd->device), pd, MLX4_IB_QP_SRC, + init_attr, udata, 0, &qp); if (err) { kfree(qp); return ERR_PTR(err); @@ -1203,7 +1618,9 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, if (udata) return ERR_PTR(-EINVAL); if (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI) { - int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev, 1, 1, &sqpn, 0); + int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev, + 1, 1, &sqpn, 0, + MLX4_RES_USAGE_DRIVER); if (res) return ERR_PTR(res); @@ -1211,8 +1628,8 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, sqpn = get_sqp_num(to_mdev(pd->device), init_attr); } - err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata, - sqpn, &qp); + err = create_qp_common(to_mdev(pd->device), pd, MLX4_IB_QP_SRC, + init_attr, udata, sqpn, &qp); if (err) return ERR_PTR(err); @@ -1267,7 +1684,6 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp) { struct mlx4_ib_dev *dev = to_mdev(qp->device); struct mlx4_ib_qp *mqp = to_mqp(qp); - struct mlx4_ib_pd *pd; if (is_qp0(dev, mqp)) mlx4_CLOSE_PORT(dev->dev, mqp->port); @@ -1282,8 +1698,14 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp) if (mqp->counter_index) mlx4_ib_free_qp_counter(dev, mqp); - pd = get_pd(mqp); - destroy_qp_common(dev, mqp, !!pd->ibpd.uobject); + if (qp->rwq_ind_tbl) { + destroy_qp_rss(dev, mqp); + } else { + struct mlx4_ib_pd *pd; + + pd = get_pd(mqp); + destroy_qp_common(dev, mqp, MLX4_IB_QP_SRC, !!pd->ibpd.uobject); + } if (is_sqp(dev, mqp)) kfree(to_msqp(mqp)); @@ -1566,7 +1988,7 @@ static int create_qp_lb_counter(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) !(dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_LB_SRC_CHK)) return 0; - err = mlx4_counter_alloc(dev->dev, &tmp_idx); + err = mlx4_counter_alloc(dev->dev, &tmp_idx, MLX4_RES_USAGE_DRIVER); if (err) return err; @@ -1606,12 +2028,119 @@ static u8 gid_type_to_qpc(enum ib_gid_type gid_type) } } -static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, +/* + * Go over all RSS QP's childes (WQs) and apply their HW state according to + * their logic state if the RSS QP is the first RSS QP associated for the WQ. + */ +static int bringup_rss_rwqs(struct ib_rwq_ind_table *ind_tbl, u8 port_num) +{ + int i; + int err; + + for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) { + struct ib_wq *ibwq = ind_tbl->ind_tbl[i]; + struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq); + + mutex_lock(&wq->mutex); + + /* Mlx4_ib restrictions: + * WQ's is associated to a port according to the RSS QP it is + * associates to. + * In case the WQ is associated to a different port by another + * RSS QP, return a failure. + */ + if ((wq->rss_usecnt > 0) && (wq->port != port_num)) { + err = -EINVAL; + mutex_unlock(&wq->mutex); + break; + } + wq->port = port_num; + if ((wq->rss_usecnt == 0) && (ibwq->state == IB_WQS_RDY)) { + err = _mlx4_ib_modify_wq(ibwq, IB_WQS_RDY); + if (err) { + mutex_unlock(&wq->mutex); + break; + } + } + wq->rss_usecnt++; + + mutex_unlock(&wq->mutex); + } + + if (i && err) { + int j; + + for (j = (i - 1); j >= 0; j--) { + struct ib_wq *ibwq = ind_tbl->ind_tbl[j]; + struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq); + + mutex_lock(&wq->mutex); + + if ((wq->rss_usecnt == 1) && + (ibwq->state == IB_WQS_RDY)) + if (_mlx4_ib_modify_wq(ibwq, IB_WQS_RESET)) + pr_warn("failed to reverse WQN=0x%06x\n", + ibwq->wq_num); + wq->rss_usecnt--; + + mutex_unlock(&wq->mutex); + } + } + + return err; +} + +static void bring_down_rss_rwqs(struct ib_rwq_ind_table *ind_tbl) +{ + int i; + + for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) { + struct ib_wq *ibwq = ind_tbl->ind_tbl[i]; + struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq); + + mutex_lock(&wq->mutex); + + if ((wq->rss_usecnt == 1) && (ibwq->state == IB_WQS_RDY)) + if (_mlx4_ib_modify_wq(ibwq, IB_WQS_RESET)) + pr_warn("failed to reverse WQN=%x\n", + ibwq->wq_num); + wq->rss_usecnt--; + + mutex_unlock(&wq->mutex); + } +} + +static void fill_qp_rss_context(struct mlx4_qp_context *context, + struct mlx4_ib_qp *qp) +{ + struct mlx4_rss_context *rss_context; + + rss_context = (void *)context + offsetof(struct mlx4_qp_context, + pri_path) + MLX4_RSS_OFFSET_IN_QPC_PRI_PATH; + + rss_context->base_qpn = cpu_to_be32(qp->rss_ctx->base_qpn_tbl_sz); + rss_context->default_qpn = + cpu_to_be32(qp->rss_ctx->base_qpn_tbl_sz & 0xffffff); + if (qp->rss_ctx->flags & (MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6)) + rss_context->base_qpn_udp = rss_context->default_qpn; + rss_context->flags = qp->rss_ctx->flags; + /* Currently support just toeplitz */ + rss_context->hash_fn = MLX4_RSS_HASH_TOP; + + memcpy(rss_context->rss_key, qp->rss_ctx->rss_key, + MLX4_EN_RSS_KEY_SIZE); +} + +static int __mlx4_ib_modify_qp(void *src, enum mlx4_ib_source_type src_type, const struct ib_qp_attr *attr, int attr_mask, enum ib_qp_state cur_state, enum ib_qp_state new_state) { - struct mlx4_ib_dev *dev = to_mdev(ibqp->device); - struct mlx4_ib_qp *qp = to_mqp(ibqp); + struct ib_uobject *ibuobject; + struct ib_srq *ibsrq; + struct ib_rwq_ind_table *rwq_ind_tbl; + enum ib_qp_type qp_type; + struct mlx4_ib_dev *dev; + struct mlx4_ib_qp *qp; struct mlx4_ib_pd *pd; struct mlx4_ib_cq *send_cq, *recv_cq; struct mlx4_qp_context *context; @@ -1621,6 +2150,30 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, int err = -EINVAL; int counter_index; + if (src_type == MLX4_IB_RWQ_SRC) { + struct ib_wq *ibwq; + + ibwq = (struct ib_wq *)src; + ibuobject = ibwq->uobject; + ibsrq = NULL; + rwq_ind_tbl = NULL; + qp_type = IB_QPT_RAW_PACKET; + qp = to_mqp((struct ib_qp *)ibwq); + dev = to_mdev(ibwq->device); + pd = to_mpd(ibwq->pd); + } else { + struct ib_qp *ibqp; + + ibqp = (struct ib_qp *)src; + ibuobject = ibqp->uobject; + ibsrq = ibqp->srq; + rwq_ind_tbl = ibqp->rwq_ind_tbl; + qp_type = ibqp->qp_type; + qp = to_mqp(ibqp); + dev = to_mdev(ibqp->device); + pd = get_pd(qp); + } + /* APM is not supported under RoCE */ if (attr_mask & IB_QP_ALT_PATH && rdma_port_get_link_layer(&dev->ib_dev, qp->port) == @@ -1634,6 +2187,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, context->flags = cpu_to_be32((to_mlx4_state(new_state) << 28) | (to_mlx4_st(dev, qp->mlx4_ib_qp_type) << 16)); + if (rwq_ind_tbl) { + fill_qp_rss_context(context, qp); + context->flags |= cpu_to_be32(1 << MLX4_RSS_QPC_FLAG_OFFSET); + } + if (!(attr_mask & IB_QP_PATH_MIG_STATE)) context->flags |= cpu_to_be32(MLX4_QP_PM_MIGRATED << 11); else { @@ -1651,11 +2209,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } } - if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_SMI) + if (qp->inl_recv_sz) + context->param3 |= cpu_to_be32(1 << 25); + + if (qp_type == IB_QPT_GSI || qp_type == IB_QPT_SMI) context->mtu_msgmax = (IB_MTU_4096 << 5) | 11; - else if (ibqp->qp_type == IB_QPT_RAW_PACKET) + else if (qp_type == IB_QPT_RAW_PACKET) context->mtu_msgmax = (MLX4_RAW_QP_MTU << 5) | MLX4_RAW_QP_MSGMAX; - else if (ibqp->qp_type == IB_QPT_UD) { + else if (qp_type == IB_QPT_UD) { if (qp->flags & MLX4_IB_QP_LSO) context->mtu_msgmax = (IB_MTU_4096 << 5) | ilog2(dev->dev->caps.max_gso_sz); @@ -1671,9 +2232,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, ilog2(dev->dev->caps.max_msg_sz); } - if (qp->rq.wqe_cnt) - context->rq_size_stride = ilog2(qp->rq.wqe_cnt) << 3; - context->rq_size_stride |= qp->rq.wqe_shift - 4; + if (!rwq_ind_tbl) { /* PRM RSS receive side should be left zeros */ + if (qp->rq.wqe_cnt) + context->rq_size_stride = ilog2(qp->rq.wqe_cnt) << 3; + context->rq_size_stride |= qp->rq.wqe_shift - 4; + } if (qp->sq.wqe_cnt) context->sq_size_stride = ilog2(qp->sq.wqe_cnt) << 3; @@ -1685,14 +2248,15 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) { context->sq_size_stride |= !!qp->sq_no_prefetch << 7; context->xrcd = cpu_to_be32((u32) qp->xrcdn); - if (ibqp->qp_type == IB_QPT_RAW_PACKET) + if (qp_type == IB_QPT_RAW_PACKET) context->param3 |= cpu_to_be32(1 << 30); } - if (qp->ibqp.uobject) + if (ibuobject) context->usr_page = cpu_to_be32( mlx4_to_hw_uar_index(dev->dev, - to_mucontext(ibqp->uobject->context)->uar.index)); + to_mucontext(ibuobject->context) + ->uar.index)); else context->usr_page = cpu_to_be32( mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index)); @@ -1736,7 +2300,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, steer_qp = 1; } - if (ibqp->qp_type == IB_QPT_GSI) { + if (qp_type == IB_QPT_GSI) { enum ib_gid_type gid_type = qp->flags & MLX4_IB_ROCE_V2_GSI_QP ? IB_GID_TYPE_ROCE_UDP_ENCAP : IB_GID_TYPE_ROCE; u8 qpc_roce_mode = gid_type_to_qpc(gid_type); @@ -1753,7 +2317,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } if (attr_mask & IB_QP_AV) { - u8 port_num = mlx4_is_bonded(to_mdev(ibqp->device)->dev) ? 1 : + u8 port_num = mlx4_is_bonded(dev->dev) ? 1 : attr_mask & IB_QP_PORT ? attr->port_num : qp->port; union ib_gid gid; struct ib_gid_attr gid_attr = {.gid_type = IB_GID_TYPE_IB}; @@ -1768,7 +2332,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, int index = rdma_ah_read_grh(&attr->ah_attr)->sgid_index; - status = ib_get_cached_gid(ibqp->device, port_num, + status = ib_get_cached_gid(&dev->ib_dev, port_num, index, &gid, &gid_attr); if (!status && !memcmp(&gid, &zgid, sizeof(gid))) status = -ENOENT; @@ -1825,15 +2389,20 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, optpar |= MLX4_QP_OPTPAR_ALT_ADDR_PATH; } - pd = get_pd(qp); - get_cqs(qp, &send_cq, &recv_cq); - context->pd = cpu_to_be32(pd->pdn); + context->pd = cpu_to_be32(pd->pdn); + + if (!rwq_ind_tbl) { + get_cqs(qp, src_type, &send_cq, &recv_cq); + } else { /* Set dummy CQs to be compatible with HV and PRM */ + send_cq = to_mcq(rwq_ind_tbl->ind_tbl[0]->cq); + recv_cq = send_cq; + } context->cqn_send = cpu_to_be32(send_cq->mcq.cqn); context->cqn_recv = cpu_to_be32(recv_cq->mcq.cqn); context->params1 = cpu_to_be32(MLX4_IB_ACK_REQ_FREQ << 28); /* Set "fast registration enabled" for all kernel QPs */ - if (!qp->ibqp.uobject) + if (!ibuobject) context->params1 |= cpu_to_be32(1 << 11); if (attr_mask & IB_QP_RNR_RETRY) { @@ -1868,7 +2437,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, optpar |= MLX4_QP_OPTPAR_RWE | MLX4_QP_OPTPAR_RRE | MLX4_QP_OPTPAR_RAE; } - if (ibqp->srq) + if (ibsrq) context->params2 |= cpu_to_be32(MLX4_QP_BIT_RIC); if (attr_mask & IB_QP_MIN_RNR_TIMER) { @@ -1899,17 +2468,19 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, optpar |= MLX4_QP_OPTPAR_Q_KEY; } - if (ibqp->srq) - context->srqn = cpu_to_be32(1 << 24 | to_msrq(ibqp->srq)->msrq.srqn); + if (ibsrq) + context->srqn = cpu_to_be32(1 << 24 | + to_msrq(ibsrq)->msrq.srqn); - if (qp->rq.wqe_cnt && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) + if (qp->rq.wqe_cnt && + cur_state == IB_QPS_RESET && + new_state == IB_QPS_INIT) context->db_rec_addr = cpu_to_be64(qp->db.dma); if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR && - (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_SMI || - ibqp->qp_type == IB_QPT_UD || - ibqp->qp_type == IB_QPT_RAW_PACKET)) { + (qp_type == IB_QPT_GSI || qp_type == IB_QPT_SMI || + qp_type == IB_QPT_UD || qp_type == IB_QPT_RAW_PACKET)) { context->pri_path.sched_queue = (qp->port - 1) << 6; if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_SMI || qp->mlx4_ib_qp_type & @@ -1942,7 +2513,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } } - if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) { + if (qp_type == IB_QPT_RAW_PACKET) { context->pri_path.ackto = (context->pri_path.ackto & 0xf8) | MLX4_IB_LINK_TYPE_ETH; if (dev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { @@ -1952,7 +2523,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } } - if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) { + if (qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) { int is_eth = rdma_port_get_link_layer( &dev->ib_dev, qp->port) == IB_LINK_LAYER_ETHERNET; @@ -1962,14 +2533,15 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } } - if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD && attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify) sqd_event = 1; else sqd_event = 0; - if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) + if (!ibuobject && + cur_state == IB_QPS_RESET && + new_state == IB_QPS_INIT) context->rlkey_roce_mode |= (1 << 4); /* @@ -1978,7 +2550,9 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, * headroom is stamped so that the hardware doesn't start * processing stale work requests. */ - if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) { + if (!ibuobject && + cur_state == IB_QPS_RESET && + new_state == IB_QPS_INIT) { struct mlx4_wqe_ctrl_seg *ctrl; int i; @@ -2035,9 +2609,9 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, * entries and reinitialize the QP. */ if (new_state == IB_QPS_RESET) { - if (!ibqp->uobject) { + if (!ibuobject) { mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn, - ibqp->srq ? to_msrq(ibqp->srq) : NULL); + ibsrq ? to_msrq(ibsrq) : NULL); if (send_cq != recv_cq) mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL); @@ -2148,6 +2722,11 @@ out: return err; } +enum { + MLX4_IB_MODIFY_QP_RSS_SUP_ATTR_MSK = (IB_QP_STATE | + IB_QP_PORT), +}; + static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { @@ -2178,6 +2757,27 @@ static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, goto out; } + if (ibqp->rwq_ind_tbl) { + if (!(((cur_state == IB_QPS_RESET) && + (new_state == IB_QPS_INIT)) || + ((cur_state == IB_QPS_INIT) && + (new_state == IB_QPS_RTR)))) { + pr_debug("qpn 0x%x: RSS QP unsupported transition %d to %d\n", + ibqp->qp_num, cur_state, new_state); + + err = -EOPNOTSUPP; + goto out; + } + + if (attr_mask & ~MLX4_IB_MODIFY_QP_RSS_SUP_ATTR_MSK) { + pr_debug("qpn 0x%x: RSS QP unsupported attribute mask 0x%x for transition %d to %d\n", + ibqp->qp_num, attr_mask, cur_state, new_state); + + err = -EOPNOTSUPP; + goto out; + } + } + if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT)) { if ((cur_state == IB_QPS_RESET) && (new_state == IB_QPS_INIT)) { if ((ibqp->qp_type == IB_QPT_RC) || @@ -2242,7 +2842,17 @@ static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, goto out; } - err = __mlx4_ib_modify_qp(ibqp, attr, attr_mask, cur_state, new_state); + if (ibqp->rwq_ind_tbl && (new_state == IB_QPS_INIT)) { + err = bringup_rss_rwqs(ibqp->rwq_ind_tbl, attr->port_num); + if (err) + goto out; + } + + err = __mlx4_ib_modify_qp(ibqp, MLX4_IB_QP_SRC, attr, attr_mask, + cur_state, new_state); + + if (ibqp->rwq_ind_tbl && err) + bring_down_rss_rwqs(ibqp->rwq_ind_tbl); if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT)) attr->port_num = 1; @@ -3432,6 +4042,9 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr int mlx4_state; int err = 0; + if (ibqp->rwq_ind_tbl) + return -EOPNOTSUPP; + mutex_lock(&qp->mutex); if (qp->state == IB_QPS_RESET) { @@ -3527,3 +4140,285 @@ out: return err; } +struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd, + struct ib_wq_init_attr *init_attr, + struct ib_udata *udata) +{ + struct mlx4_ib_dev *dev; + struct ib_qp_init_attr ib_qp_init_attr; + struct mlx4_ib_qp *qp; + struct mlx4_ib_create_wq ucmd; + int err, required_cmd_sz; + + if (!(udata && pd->uobject)) + return ERR_PTR(-EINVAL); + + required_cmd_sz = offsetof(typeof(ucmd), reserved) + + sizeof(ucmd.reserved); + if (udata->inlen < required_cmd_sz) { + pr_debug("invalid inlen\n"); + return ERR_PTR(-EINVAL); + } + + if (udata->inlen > sizeof(ucmd) && + !ib_is_udata_cleared(udata, sizeof(ucmd), + udata->inlen - sizeof(ucmd))) { + pr_debug("inlen is not supported\n"); + return ERR_PTR(-EOPNOTSUPP); + } + + if (udata->outlen) + return ERR_PTR(-EOPNOTSUPP); + + dev = to_mdev(pd->device); + + if (init_attr->wq_type != IB_WQT_RQ) { + pr_debug("unsupported wq type %d\n", init_attr->wq_type); + return ERR_PTR(-EOPNOTSUPP); + } + + if (init_attr->create_flags) { + pr_debug("unsupported create_flags %u\n", + init_attr->create_flags); + return ERR_PTR(-EOPNOTSUPP); + } + + qp = kzalloc(sizeof(*qp), GFP_KERNEL); + if (!qp) + return ERR_PTR(-ENOMEM); + + qp->pri.vid = 0xFFFF; + qp->alt.vid = 0xFFFF; + + memset(&ib_qp_init_attr, 0, sizeof(ib_qp_init_attr)); + ib_qp_init_attr.qp_context = init_attr->wq_context; + ib_qp_init_attr.qp_type = IB_QPT_RAW_PACKET; + ib_qp_init_attr.cap.max_recv_wr = init_attr->max_wr; + ib_qp_init_attr.cap.max_recv_sge = init_attr->max_sge; + ib_qp_init_attr.recv_cq = init_attr->cq; + ib_qp_init_attr.send_cq = ib_qp_init_attr.recv_cq; /* Dummy CQ */ + + err = create_qp_common(dev, pd, MLX4_IB_RWQ_SRC, &ib_qp_init_attr, + udata, 0, &qp); + if (err) { + kfree(qp); + return ERR_PTR(err); + } + + qp->ibwq.event_handler = init_attr->event_handler; + qp->ibwq.wq_num = qp->mqp.qpn; + qp->ibwq.state = IB_WQS_RESET; + + return &qp->ibwq; +} + +static int ib_wq2qp_state(enum ib_wq_state state) +{ + switch (state) { + case IB_WQS_RESET: + return IB_QPS_RESET; + case IB_WQS_RDY: + return IB_QPS_RTR; + default: + return IB_QPS_ERR; + } +} + +static int _mlx4_ib_modify_wq(struct ib_wq *ibwq, enum ib_wq_state new_state) +{ + struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq); + enum ib_qp_state qp_cur_state; + enum ib_qp_state qp_new_state; + int attr_mask; + int err; + + /* ib_qp.state represents the WQ HW state while ib_wq.state represents + * the WQ logic state. + */ + qp_cur_state = qp->state; + qp_new_state = ib_wq2qp_state(new_state); + + if (ib_wq2qp_state(new_state) == qp_cur_state) + return 0; + + if (new_state == IB_WQS_RDY) { + struct ib_qp_attr attr = {}; + + attr.port_num = qp->port; + attr_mask = IB_QP_PORT; + + err = __mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, &attr, + attr_mask, IB_QPS_RESET, IB_QPS_INIT); + if (err) { + pr_debug("WQN=0x%06x failed to apply RST->INIT on the HW QP\n", + ibwq->wq_num); + return err; + } + + qp_cur_state = IB_QPS_INIT; + } + + attr_mask = 0; + err = __mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, NULL, attr_mask, + qp_cur_state, qp_new_state); + + if (err && (qp_cur_state == IB_QPS_INIT)) { + qp_new_state = IB_QPS_RESET; + if (__mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, NULL, + attr_mask, IB_QPS_INIT, IB_QPS_RESET)) { + pr_warn("WQN=0x%06x failed with reverting HW's resources failure\n", + ibwq->wq_num); + qp_new_state = IB_QPS_INIT; + } + } + + qp->state = qp_new_state; + + return err; +} + +int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr, + u32 wq_attr_mask, struct ib_udata *udata) +{ + struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq); + struct mlx4_ib_modify_wq ucmd = {}; + size_t required_cmd_sz; + enum ib_wq_state cur_state, new_state; + int err = 0; + + required_cmd_sz = offsetof(typeof(ucmd), reserved) + + sizeof(ucmd.reserved); + if (udata->inlen < required_cmd_sz) + return -EINVAL; + + if (udata->inlen > sizeof(ucmd) && + !ib_is_udata_cleared(udata, sizeof(ucmd), + udata->inlen - sizeof(ucmd))) + return -EOPNOTSUPP; + + if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen))) + return -EFAULT; + + if (ucmd.comp_mask || ucmd.reserved) + return -EOPNOTSUPP; + + if (wq_attr_mask & IB_WQ_FLAGS) + return -EOPNOTSUPP; + + cur_state = wq_attr_mask & IB_WQ_CUR_STATE ? wq_attr->curr_wq_state : + ibwq->state; + new_state = wq_attr_mask & IB_WQ_STATE ? wq_attr->wq_state : cur_state; + + if (cur_state < IB_WQS_RESET || cur_state > IB_WQS_ERR || + new_state < IB_WQS_RESET || new_state > IB_WQS_ERR) + return -EINVAL; + + if ((new_state == IB_WQS_RDY) && (cur_state == IB_WQS_ERR)) + return -EINVAL; + + if ((new_state == IB_WQS_ERR) && (cur_state == IB_WQS_RESET)) + return -EINVAL; + + /* Need to protect against the parent RSS which also may modify WQ + * state. + */ + mutex_lock(&qp->mutex); + + /* Can update HW state only if a RSS QP has already associated to this + * WQ, so we can apply its port on the WQ. + */ + if (qp->rss_usecnt) + err = _mlx4_ib_modify_wq(ibwq, new_state); + + if (!err) + ibwq->state = new_state; + + mutex_unlock(&qp->mutex); + + return err; +} + +int mlx4_ib_destroy_wq(struct ib_wq *ibwq) +{ + struct mlx4_ib_dev *dev = to_mdev(ibwq->device); + struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq); + + if (qp->counter_index) + mlx4_ib_free_qp_counter(dev, qp); + + destroy_qp_common(dev, qp, MLX4_IB_RWQ_SRC, 1); + + kfree(qp); + + return 0; +} + +struct ib_rwq_ind_table +*mlx4_ib_create_rwq_ind_table(struct ib_device *device, + struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata) +{ + struct ib_rwq_ind_table *rwq_ind_table; + struct mlx4_ib_create_rwq_ind_tbl_resp resp = {}; + unsigned int ind_tbl_size = 1 << init_attr->log_ind_tbl_size; + unsigned int base_wqn; + size_t min_resp_len; + int i; + int err; + + if (udata->inlen > 0 && + !ib_is_udata_cleared(udata, 0, + udata->inlen)) + return ERR_PTR(-EOPNOTSUPP); + + min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved); + if (udata->outlen && udata->outlen < min_resp_len) + return ERR_PTR(-EINVAL); + + if (ind_tbl_size > + device->attrs.rss_caps.max_rwq_indirection_table_size) { + pr_debug("log_ind_tbl_size = %d is bigger than supported = %d\n", + ind_tbl_size, + device->attrs.rss_caps.max_rwq_indirection_table_size); + return ERR_PTR(-EINVAL); + } + + base_wqn = init_attr->ind_tbl[0]->wq_num; + + if (base_wqn % ind_tbl_size) { + pr_debug("WQN=0x%x isn't aligned with indirection table size\n", + base_wqn); + return ERR_PTR(-EINVAL); + } + + for (i = 1; i < ind_tbl_size; i++) { + if (++base_wqn != init_attr->ind_tbl[i]->wq_num) { + pr_debug("indirection table's WQNs aren't consecutive\n"); + return ERR_PTR(-EINVAL); + } + } + + rwq_ind_table = kzalloc(sizeof(*rwq_ind_table), GFP_KERNEL); + if (!rwq_ind_table) + return ERR_PTR(-ENOMEM); + + if (udata->outlen) { + resp.response_length = offsetof(typeof(resp), response_length) + + sizeof(resp.response_length); + err = ib_copy_to_udata(udata, &resp, resp.response_length); + if (err) + goto err; + } + + return rwq_ind_table; + +err: + kfree(rwq_ind_table); + return ERR_PTR(err); +} + +int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl) +{ + kfree(ib_rwq_ind_tbl); + return 0; +} diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile index 90ad2adc752f..bc6299697dda 100644 --- a/drivers/infiniband/hw/mlx5/Makefile +++ b/drivers/infiniband/hw/mlx5/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5_ib.o -mlx5_ib-y := main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o +mlx5_ib-y := main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o cong.o mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 18d5e1db93ed..470995fa38d2 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -57,3 +57,23 @@ int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev, MLX5_SET(query_cong_statistics_in, in, clear, reset); return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size); } + +int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point, + void *out, int out_size) +{ + u32 in[MLX5_ST_SZ_DW(query_cong_params_in)] = { }; + + MLX5_SET(query_cong_params_in, in, opcode, + MLX5_CMD_OP_QUERY_CONG_PARAMS); + MLX5_SET(query_cong_params_in, in, cong_protocol, cong_point); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size); +} + +int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *dev, + void *in, int in_size) +{ + u32 out[MLX5_ST_SZ_DW(modify_cong_params_out)] = { }; + + return mlx5_cmd_exec(dev, in, in_size, out, sizeof(out)); +} diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index fa09228193a6..af4c24596274 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -39,4 +39,8 @@ int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey); int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev, bool reset, void *out, int out_size); +int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point, + void *out, int out_size); +int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev, + void *in, int in_size); #endif /* MLX5_IB_CMD_H */ diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c new file mode 100644 index 000000000000..2d32b519bb61 --- /dev/null +++ b/drivers/infiniband/hw/mlx5/cong.c @@ -0,0 +1,421 @@ +/* + * Copyright (c) 2013-2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/debugfs.h> + +#include "mlx5_ib.h" +#include "cmd.h" + +enum mlx5_ib_cong_node_type { + MLX5_IB_RROCE_ECN_RP = 1, + MLX5_IB_RROCE_ECN_NP = 2, +}; + +static const char * const mlx5_ib_dbg_cc_name[] = { + "rp_clamp_tgt_rate", + "rp_clamp_tgt_rate_ati", + "rp_time_reset", + "rp_byte_reset", + "rp_threshold", + "rp_ai_rate", + "rp_hai_rate", + "rp_min_dec_fac", + "rp_min_rate", + "rp_rate_to_set_on_first_cnp", + "rp_dce_tcp_g", + "rp_dce_tcp_rtt", + "rp_rate_reduce_monitor_period", + "rp_initial_alpha_value", + "rp_gd", + "np_cnp_dscp", + "np_cnp_prio_mode", + "np_cnp_prio", +}; + +#define MLX5_IB_RP_CLAMP_TGT_RATE_ATTR BIT(1) +#define MLX5_IB_RP_CLAMP_TGT_RATE_ATI_ATTR BIT(2) +#define MLX5_IB_RP_TIME_RESET_ATTR BIT(3) +#define MLX5_IB_RP_BYTE_RESET_ATTR BIT(4) +#define MLX5_IB_RP_THRESHOLD_ATTR BIT(5) +#define MLX5_IB_RP_AI_RATE_ATTR BIT(7) +#define MLX5_IB_RP_HAI_RATE_ATTR BIT(8) +#define MLX5_IB_RP_MIN_DEC_FAC_ATTR BIT(9) +#define MLX5_IB_RP_MIN_RATE_ATTR BIT(10) +#define MLX5_IB_RP_RATE_TO_SET_ON_FIRST_CNP_ATTR BIT(11) +#define MLX5_IB_RP_DCE_TCP_G_ATTR BIT(12) +#define MLX5_IB_RP_DCE_TCP_RTT_ATTR BIT(13) +#define MLX5_IB_RP_RATE_REDUCE_MONITOR_PERIOD_ATTR BIT(14) +#define MLX5_IB_RP_INITIAL_ALPHA_VALUE_ATTR BIT(15) +#define MLX5_IB_RP_GD_ATTR BIT(16) + +#define MLX5_IB_NP_CNP_DSCP_ATTR BIT(3) +#define MLX5_IB_NP_CNP_PRIO_MODE_ATTR BIT(4) + +static enum mlx5_ib_cong_node_type +mlx5_ib_param_to_node(enum mlx5_ib_dbg_cc_types param_offset) +{ + if (param_offset >= MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE && + param_offset <= MLX5_IB_DBG_CC_RP_GD) + return MLX5_IB_RROCE_ECN_RP; + else + return MLX5_IB_RROCE_ECN_NP; +} + +static u32 mlx5_get_cc_param_val(void *field, int offset) +{ + switch (offset) { + case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + clamp_tgt_rate); + case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + clamp_tgt_rate_after_time_inc); + case MLX5_IB_DBG_CC_RP_TIME_RESET: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_time_reset); + case MLX5_IB_DBG_CC_RP_BYTE_RESET: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_byte_reset); + case MLX5_IB_DBG_CC_RP_THRESHOLD: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_threshold); + case MLX5_IB_DBG_CC_RP_AI_RATE: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_ai_rate); + case MLX5_IB_DBG_CC_RP_HAI_RATE: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_hai_rate); + case MLX5_IB_DBG_CC_RP_MIN_DEC_FAC: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_min_dec_fac); + case MLX5_IB_DBG_CC_RP_MIN_RATE: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_min_rate); + case MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rate_to_set_on_first_cnp); + case MLX5_IB_DBG_CC_RP_DCE_TCP_G: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + dce_tcp_g); + case MLX5_IB_DBG_CC_RP_DCE_TCP_RTT: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + dce_tcp_rtt); + case MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rate_reduce_monitor_period); + case MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + initial_alpha_value); + case MLX5_IB_DBG_CC_RP_GD: + return MLX5_GET(cong_control_r_roce_ecn_rp, field, + rpg_gd); + case MLX5_IB_DBG_CC_NP_CNP_DSCP: + return MLX5_GET(cong_control_r_roce_ecn_np, field, + cnp_dscp); + case MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE: + return MLX5_GET(cong_control_r_roce_ecn_np, field, + cnp_prio_mode); + case MLX5_IB_DBG_CC_NP_CNP_PRIO: + return MLX5_GET(cong_control_r_roce_ecn_np, field, + cnp_802p_prio); + default: + return 0; + } +} + +static void mlx5_ib_set_cc_param_mask_val(void *field, int offset, + u32 var, u32 *attr_mask) +{ + switch (offset) { + case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE: + *attr_mask |= MLX5_IB_RP_CLAMP_TGT_RATE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + clamp_tgt_rate, var); + break; + case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI: + *attr_mask |= MLX5_IB_RP_CLAMP_TGT_RATE_ATI_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + clamp_tgt_rate_after_time_inc, var); + break; + case MLX5_IB_DBG_CC_RP_TIME_RESET: + *attr_mask |= MLX5_IB_RP_TIME_RESET_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_time_reset, var); + break; + case MLX5_IB_DBG_CC_RP_BYTE_RESET: + *attr_mask |= MLX5_IB_RP_BYTE_RESET_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_byte_reset, var); + break; + case MLX5_IB_DBG_CC_RP_THRESHOLD: + *attr_mask |= MLX5_IB_RP_THRESHOLD_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_threshold, var); + break; + case MLX5_IB_DBG_CC_RP_AI_RATE: + *attr_mask |= MLX5_IB_RP_AI_RATE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_ai_rate, var); + break; + case MLX5_IB_DBG_CC_RP_HAI_RATE: + *attr_mask |= MLX5_IB_RP_HAI_RATE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_hai_rate, var); + break; + case MLX5_IB_DBG_CC_RP_MIN_DEC_FAC: + *attr_mask |= MLX5_IB_RP_MIN_DEC_FAC_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_min_dec_fac, var); + break; + case MLX5_IB_DBG_CC_RP_MIN_RATE: + *attr_mask |= MLX5_IB_RP_MIN_RATE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_min_rate, var); + break; + case MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP: + *attr_mask |= MLX5_IB_RP_RATE_TO_SET_ON_FIRST_CNP_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rate_to_set_on_first_cnp, var); + break; + case MLX5_IB_DBG_CC_RP_DCE_TCP_G: + *attr_mask |= MLX5_IB_RP_DCE_TCP_G_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + dce_tcp_g, var); + break; + case MLX5_IB_DBG_CC_RP_DCE_TCP_RTT: + *attr_mask |= MLX5_IB_RP_DCE_TCP_RTT_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + dce_tcp_rtt, var); + break; + case MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD: + *attr_mask |= MLX5_IB_RP_RATE_REDUCE_MONITOR_PERIOD_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rate_reduce_monitor_period, var); + break; + case MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE: + *attr_mask |= MLX5_IB_RP_INITIAL_ALPHA_VALUE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + initial_alpha_value, var); + break; + case MLX5_IB_DBG_CC_RP_GD: + *attr_mask |= MLX5_IB_RP_GD_ATTR; + MLX5_SET(cong_control_r_roce_ecn_rp, field, + rpg_gd, var); + break; + case MLX5_IB_DBG_CC_NP_CNP_DSCP: + *attr_mask |= MLX5_IB_NP_CNP_DSCP_ATTR; + MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_dscp, var); + break; + case MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE: + *attr_mask |= MLX5_IB_NP_CNP_PRIO_MODE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, var); + break; + case MLX5_IB_DBG_CC_NP_CNP_PRIO: + *attr_mask |= MLX5_IB_NP_CNP_PRIO_MODE_ATTR; + MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, 0); + MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_802p_prio, var); + break; + } +} + +static int mlx5_ib_get_cc_params(struct mlx5_ib_dev *dev, int offset, u32 *var) +{ + int outlen = MLX5_ST_SZ_BYTES(query_cong_params_out); + void *out; + void *field; + int err; + enum mlx5_ib_cong_node_type node; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + node = mlx5_ib_param_to_node(offset); + + err = mlx5_cmd_query_cong_params(dev->mdev, node, out, outlen); + if (err) + goto free; + + field = MLX5_ADDR_OF(query_cong_params_out, out, congestion_parameters); + *var = mlx5_get_cc_param_val(field, offset); + +free: + kvfree(out); + return err; +} + +static int mlx5_ib_set_cc_params(struct mlx5_ib_dev *dev, int offset, u32 var) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_cong_params_in); + void *in; + void *field; + enum mlx5_ib_cong_node_type node; + u32 attr_mask = 0; + int err; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_cong_params_in, in, opcode, + MLX5_CMD_OP_MODIFY_CONG_PARAMS); + + node = mlx5_ib_param_to_node(offset); + MLX5_SET(modify_cong_params_in, in, cong_protocol, node); + + field = MLX5_ADDR_OF(modify_cong_params_in, in, congestion_parameters); + mlx5_ib_set_cc_param_mask_val(field, offset, var, &attr_mask); + + field = MLX5_ADDR_OF(modify_cong_params_in, in, field_select); + MLX5_SET(field_select_r_roce_rp, field, field_select_r_roce_rp, + attr_mask); + + err = mlx5_cmd_modify_cong_params(dev->mdev, in, inlen); + kvfree(in); + return err; +} + +static ssize_t set_param(struct file *filp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct mlx5_ib_dbg_param *param = filp->private_data; + int offset = param->offset; + char lbuf[11] = { }; + u32 var; + int ret; + + if (count > sizeof(lbuf)) + return -EINVAL; + + if (copy_from_user(lbuf, buf, count)) + return -EFAULT; + + lbuf[sizeof(lbuf) - 1] = '\0'; + + if (kstrtou32(lbuf, 0, &var)) + return -EINVAL; + + ret = mlx5_ib_set_cc_params(param->dev, offset, var); + return ret ? ret : count; +} + +static ssize_t get_param(struct file *filp, char __user *buf, size_t count, + loff_t *pos) +{ + struct mlx5_ib_dbg_param *param = filp->private_data; + int offset = param->offset; + u32 var = 0; + int ret; + char lbuf[11]; + + if (*pos) + return 0; + + ret = mlx5_ib_get_cc_params(param->dev, offset, &var); + if (ret) + return ret; + + ret = snprintf(lbuf, sizeof(lbuf), "%d\n", var); + if (ret < 0) + return ret; + + if (copy_to_user(buf, lbuf, ret)) + return -EFAULT; + + *pos += ret; + return ret; +} + +static const struct file_operations dbg_cc_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = set_param, + .read = get_param, +}; + +void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev) +{ + if (!mlx5_debugfs_root || + !dev->dbg_cc_params || + !dev->dbg_cc_params->root) + return; + + debugfs_remove_recursive(dev->dbg_cc_params->root); + kfree(dev->dbg_cc_params); + dev->dbg_cc_params = NULL; +} + +int mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev) +{ + struct mlx5_ib_dbg_cc_params *dbg_cc_params; + int i; + + if (!mlx5_debugfs_root) + goto out; + + if (!MLX5_CAP_GEN(dev->mdev, cc_query_allowed) || + !MLX5_CAP_GEN(dev->mdev, cc_modify_allowed)) + goto out; + + dbg_cc_params = kzalloc(sizeof(*dbg_cc_params), GFP_KERNEL); + if (!dbg_cc_params) + goto out; + + dev->dbg_cc_params = dbg_cc_params; + + dbg_cc_params->root = debugfs_create_dir("cc_params", + dev->mdev->priv.dbg_root); + if (!dbg_cc_params->root) + goto err; + + for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) { + dbg_cc_params->params[i].offset = i; + dbg_cc_params->params[i].dev = dev; + dbg_cc_params->params[i].dentry = + debugfs_create_file(mlx5_ib_dbg_cc_name[i], + 0600, dbg_cc_params->root, + &dbg_cc_params->params[i], + &dbg_cc_fops); + if (!dbg_cc_params->params[i].dentry) + goto err; + } +out: return 0; + +err: + mlx5_ib_warn(dev, "cong debugfs failure\n"); + mlx5_ib_cleanup_cong_debugfs(dev); + /* + * We don't want to fail driver if debugfs failed to initialize, + * so we are not forwarding error to the user. + */ + return 0; +} diff --git a/drivers/infiniband/hw/mlx5/ib_virt.c b/drivers/infiniband/hw/mlx5/ib_virt.c index c1b9de800fe5..649a3364f838 100644 --- a/drivers/infiniband/hw/mlx5/ib_virt.c +++ b/drivers/infiniband/hw/mlx5/ib_virt.c @@ -96,6 +96,7 @@ int mlx5_ib_set_vf_link_state(struct ib_device *device, int vf, struct mlx5_ib_dev *dev = to_mdev(device); struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_hca_vport_context *in; + struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx; int err; in = kzalloc(sizeof(*in), GFP_KERNEL); @@ -109,6 +110,8 @@ int mlx5_ib_set_vf_link_state(struct ib_device *device, int vf, } in->field_select = MLX5_HCA_VPORT_SEL_STATE_POLICY; err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in); + if (!err) + vfs_ctx[vf].policy = in->policy; out: kfree(in); @@ -151,6 +154,7 @@ static int set_vf_node_guid(struct ib_device *device, int vf, u8 port, u64 guid) struct mlx5_ib_dev *dev = to_mdev(device); struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_hca_vport_context *in; + struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx; int err; in = kzalloc(sizeof(*in), GFP_KERNEL); @@ -160,6 +164,8 @@ static int set_vf_node_guid(struct ib_device *device, int vf, u8 port, u64 guid) in->field_select = MLX5_HCA_VPORT_SEL_NODE_GUID; in->node_guid = guid; err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in); + if (!err) + vfs_ctx[vf].node_guid = guid; kfree(in); return err; } @@ -169,6 +175,7 @@ static int set_vf_port_guid(struct ib_device *device, int vf, u8 port, u64 guid) struct mlx5_ib_dev *dev = to_mdev(device); struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_hca_vport_context *in; + struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx; int err; in = kzalloc(sizeof(*in), GFP_KERNEL); @@ -178,6 +185,8 @@ static int set_vf_port_guid(struct ib_device *device, int vf, u8 port, u64 guid) in->field_select = MLX5_HCA_VPORT_SEL_PORT_GUID; in->port_guid = guid; err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in); + if (!err) + vfs_ctx[vf].port_guid = guid; kfree(in); return err; } diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 95db929bdc34..cd2264ac88ae 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -78,7 +78,7 @@ static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, u16 slid; int err; - slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE); + slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE); if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a7f2e60085c4..cde7d1ce4a3c 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include <linux/debugfs.h> #include <linux/highmem.h> #include <linux/module.h> #include <linux/init.h> @@ -58,6 +59,7 @@ #include <linux/mlx5/vport.h> #include "mlx5_ib.h" #include "cmd.h" +#include <linux/mlx5/vport.h> #define DRIVER_NAME "mlx5_ib" #define DRIVER_VERSION "5.0-0" @@ -65,7 +67,6 @@ MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRIVER_VERSION); static char mlx5_version[] = DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v" @@ -97,6 +98,20 @@ mlx5_ib_port_link_layer(struct ib_device *device, u8 port_num) return mlx5_port_type_cap_to_rdma_ll(port_type_cap); } +static int get_port_state(struct ib_device *ibdev, + u8 port_num, + enum ib_port_state *state) +{ + struct ib_port_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); + ret = mlx5_ib_query_port(ibdev, port_num, &attr); + if (!ret) + *state = attr.state; + return ret; +} + static int mlx5_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -114,6 +129,7 @@ static int mlx5_netdev_event(struct notifier_block *this, write_unlock(&ibdev->roce.netdev_lock); break; + case NETDEV_CHANGE: case NETDEV_UP: case NETDEV_DOWN: { struct net_device *lag_ndev = mlx5_lag_get_roce_netdev(ibdev->mdev); @@ -127,10 +143,23 @@ static int mlx5_netdev_event(struct notifier_block *this, if ((upper == ndev || (!upper && ndev == ibdev->roce.netdev)) && ibdev->ib_active) { struct ib_event ibev = { }; + enum ib_port_state port_state; + + if (get_port_state(&ibdev->ib_dev, 1, &port_state)) + return NOTIFY_DONE; + + if (ibdev->roce.last_port_state == port_state) + return NOTIFY_DONE; + ibdev->roce.last_port_state = port_state; ibev.device = &ibdev->ib_dev; - ibev.event = (event == NETDEV_UP) ? - IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR; + if (port_state == IB_PORT_DOWN) + ibev.event = IB_EVENT_PORT_ERR; + else if (port_state == IB_PORT_ACTIVE) + ibev.event = IB_EVENT_PORT_ACTIVE; + else + return NOTIFY_DONE; + ibev.element.port_num = 1; ib_dispatch_event(&ibev); } @@ -668,6 +697,14 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_UD_TSO; } + if (MLX5_CAP_GEN(dev->mdev, rq_delay_drop) && + MLX5_CAP_GEN(dev->mdev, general_notification_event)) + props->raw_packet_caps |= IB_RAW_PACKET_CAP_DELAY_DROP; + + if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads) && + MLX5_CAP_IPOIB_ENHANCED(mdev, csum_cap)) + props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM; + if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) && MLX5_CAP_ETH(dev->mdev, scatter_fcs)) { /* Legacy bit to support old userspace libraries */ @@ -1138,7 +1175,7 @@ static int calc_total_bfregs(struct mlx5_ib_dev *dev, bool lib_uar_4k, if (req->num_low_latency_bfregs > req->total_num_bfregs - 1) return -EINVAL; - mlx5_ib_dbg(dev, "uar_4k: fw support %s, lib support %s, user requested %d bfregs, alloated %d, using %d sys pages\n", + mlx5_ib_dbg(dev, "uar_4k: fw support %s, lib support %s, user requested %d bfregs, allocated %d, using %d sys pages\n", MLX5_CAP_GEN(dev->mdev, uar_4k) ? "yes" : "no", lib_uar_4k ? "yes" : "no", ref_bfregs, req->total_num_bfregs, *num_sys_pages); @@ -1187,6 +1224,45 @@ static int deallocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *con return 0; } +static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn) +{ + int err; + + err = mlx5_core_alloc_transport_domain(dev->mdev, tdn); + if (err) + return err; + + if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) || + !MLX5_CAP_GEN(dev->mdev, disable_local_lb)) + return err; + + mutex_lock(&dev->lb_mutex); + dev->user_td++; + + if (dev->user_td == 2) + err = mlx5_nic_vport_update_local_lb(dev->mdev, true); + + mutex_unlock(&dev->lb_mutex); + return err; +} + +static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn) +{ + mlx5_core_dealloc_transport_domain(dev->mdev, tdn); + + if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) || + !MLX5_CAP_GEN(dev->mdev, disable_local_lb)) + return; + + mutex_lock(&dev->lb_mutex); + dev->user_td--; + + if (dev->user_td < 2) + mlx5_nic_vport_update_local_lb(dev->mdev, false); + + mutex_unlock(&dev->lb_mutex); +} + static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, struct ib_udata *udata) { @@ -1295,8 +1371,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, mutex_init(&context->upd_xlt_page_mutex); if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) { - err = mlx5_core_alloc_transport_domain(dev->mdev, - &context->tdn); + err = mlx5_ib_alloc_transport_domain(dev, &context->tdn); if (err) goto out_page; } @@ -1362,7 +1437,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, out_td: if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) - mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn); + mlx5_ib_dealloc_transport_domain(dev, context->tdn); out_page: free_page(context->upd_xlt_page); @@ -1390,7 +1465,7 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext) bfregi = &context->bfregi; if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) - mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn); + mlx5_ib_dealloc_transport_domain(dev, context->tdn); free_page(context->upd_xlt_page); deallocate_uars(dev, context); @@ -2030,21 +2105,32 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c, */ static bool flow_is_multicast_only(struct ib_flow_attr *ib_attr) { - struct ib_flow_spec_eth *eth_spec; + union ib_flow_spec *flow_spec; if (ib_attr->type != IB_FLOW_ATTR_NORMAL || - ib_attr->size < sizeof(struct ib_flow_attr) + - sizeof(struct ib_flow_spec_eth) || ib_attr->num_of_specs < 1) return false; - eth_spec = (struct ib_flow_spec_eth *)(ib_attr + 1); - if (eth_spec->type != IB_FLOW_SPEC_ETH || - eth_spec->size != sizeof(*eth_spec)) + flow_spec = (union ib_flow_spec *)(ib_attr + 1); + if (flow_spec->type == IB_FLOW_SPEC_IPV4) { + struct ib_flow_spec_ipv4 *ipv4_spec; + + ipv4_spec = (struct ib_flow_spec_ipv4 *)flow_spec; + if (ipv4_is_multicast(ipv4_spec->val.dst_ip)) + return true; + return false; + } + + if (flow_spec->type == IB_FLOW_SPEC_ETH) { + struct ib_flow_spec_eth *eth_spec; + + eth_spec = (struct ib_flow_spec_eth *)flow_spec; + return is_multicast_ether_addr(eth_spec->mask.dst_mac) && + is_multicast_ether_addr(eth_spec->val.dst_mac); + } - return is_multicast_ether_addr(eth_spec->mask.dst_mac) && - is_multicast_ether_addr(eth_spec->val.dst_mac); + return false; } static bool is_valid_ethertype(struct mlx5_core_dev *mdev, @@ -2522,8 +2608,14 @@ unlock: static int mlx5_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { struct mlx5_ib_dev *dev = to_mdev(ibqp->device); + struct mlx5_ib_qp *mqp = to_mqp(ibqp); int err; + if (mqp->flags & MLX5_IB_QP_UNDERLAY) { + mlx5_ib_dbg(dev, "Attaching a multi cast group to underlay QP is not supported\n"); + return -EOPNOTSUPP; + } + err = mlx5_core_attach_mcg(dev->mdev, gid, ibqp->qp_num); if (err) mlx5_ib_warn(dev, "failed attaching QPN 0x%x, MGID %pI6\n", @@ -2685,6 +2777,26 @@ static void mlx5_ib_handle_internal_error(struct mlx5_ib_dev *ibdev) spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags); } +static void delay_drop_handler(struct work_struct *work) +{ + int err; + struct mlx5_ib_delay_drop *delay_drop = + container_of(work, struct mlx5_ib_delay_drop, + delay_drop_work); + + atomic_inc(&delay_drop->events_cnt); + + mutex_lock(&delay_drop->lock); + err = mlx5_core_set_delay_drop(delay_drop->dev->mdev, + delay_drop->timeout); + if (err) { + mlx5_ib_warn(delay_drop->dev, "Failed to set delay drop, timeout=%u\n", + delay_drop->timeout); + delay_drop->activate = false; + } + mutex_unlock(&delay_drop->lock); +} + static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, enum mlx5_dev_event event, unsigned long param) { @@ -2737,8 +2849,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, ibev.event = IB_EVENT_CLIENT_REREGISTER; port = (u8)param; break; + case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT: + schedule_work(&ibdev->delay_drop.delay_drop_work); + goto out; default: - return; + goto out; } ibev.device = &ibdev->ib_dev; @@ -2746,7 +2861,7 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, if (port < 1 || port > ibdev->num_ports) { mlx5_ib_warn(ibdev, "warning: event on port %d\n", port); - return; + goto out; } if (ibdev->ib_active) @@ -2754,6 +2869,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, if (fatal) ibdev->ib_active = false; + +out: + return; } static int set_has_smi_cap(struct mlx5_ib_dev *dev) @@ -3167,13 +3285,13 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_dev_fw_str(struct ib_device *ibdev, char *str, - size_t str_len) +static void get_dev_fw_str(struct ib_device *ibdev, char *str) { struct mlx5_ib_dev *dev = container_of(ibdev, struct mlx5_ib_dev, ib_dev); - snprintf(str, str_len, "%d.%d.%04d", fw_rev_maj(dev->mdev), - fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev)); + snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%04d", + fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev), + fw_rev_sub(dev->mdev)); } static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) @@ -3313,6 +3431,17 @@ static const struct mlx5_ib_counter cong_cnts[] = { INIT_CONG_COUNTER(np_cnp_sent), }; +static const struct mlx5_ib_counter extended_err_cnts[] = { + INIT_Q_COUNTER(resp_local_length_error), + INIT_Q_COUNTER(resp_cqe_error), + INIT_Q_COUNTER(req_cqe_error), + INIT_Q_COUNTER(req_remote_invalid_request), + INIT_Q_COUNTER(req_remote_access_errors), + INIT_Q_COUNTER(resp_remote_access_errors), + INIT_Q_COUNTER(resp_cqe_flush_error), + INIT_Q_COUNTER(req_cqe_flush_error), +}; + static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev) { unsigned int i; @@ -3337,6 +3466,10 @@ static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev, if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) num_counters += ARRAY_SIZE(retrans_q_cnts); + + if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) + num_counters += ARRAY_SIZE(extended_err_cnts); + cnts->num_q_counters = num_counters; if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { @@ -3386,6 +3519,13 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev, } } + if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) { + for (i = 0; i < ARRAY_SIZE(extended_err_cnts); i++, j++) { + names[j] = extended_err_cnts[i].name; + offsets[j] = extended_err_cnts[i].offset; + } + } + if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { for (i = 0; i < ARRAY_SIZE(cong_cnts); i++, j++) { names[j] = cong_cnts[i].name; @@ -3556,6 +3696,134 @@ mlx5_ib_alloc_rdma_netdev(struct ib_device *hca, return netdev; } +static void delay_drop_debugfs_cleanup(struct mlx5_ib_dev *dev) +{ + if (!dev->delay_drop.dbg) + return; + debugfs_remove_recursive(dev->delay_drop.dbg->dir_debugfs); + kfree(dev->delay_drop.dbg); + dev->delay_drop.dbg = NULL; +} + +static void cancel_delay_drop(struct mlx5_ib_dev *dev) +{ + if (!(dev->ib_dev.attrs.raw_packet_caps & IB_RAW_PACKET_CAP_DELAY_DROP)) + return; + + cancel_work_sync(&dev->delay_drop.delay_drop_work); + delay_drop_debugfs_cleanup(dev); +} + +static ssize_t delay_drop_timeout_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos) +{ + struct mlx5_ib_delay_drop *delay_drop = filp->private_data; + char lbuf[20]; + int len; + + len = snprintf(lbuf, sizeof(lbuf), "%u\n", delay_drop->timeout); + return simple_read_from_buffer(buf, count, pos, lbuf, len); +} + +static ssize_t delay_drop_timeout_write(struct file *filp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct mlx5_ib_delay_drop *delay_drop = filp->private_data; + u32 timeout; + u32 var; + + if (kstrtouint_from_user(buf, count, 0, &var)) + return -EFAULT; + + timeout = min_t(u32, roundup(var, 100), MLX5_MAX_DELAY_DROP_TIMEOUT_MS * + 1000); + if (timeout != var) + mlx5_ib_dbg(delay_drop->dev, "Round delay drop timeout to %u usec\n", + timeout); + + delay_drop->timeout = timeout; + + return count; +} + +static const struct file_operations fops_delay_drop_timeout = { + .owner = THIS_MODULE, + .open = simple_open, + .write = delay_drop_timeout_write, + .read = delay_drop_timeout_read, +}; + +static int delay_drop_debugfs_init(struct mlx5_ib_dev *dev) +{ + struct mlx5_ib_dbg_delay_drop *dbg; + + if (!mlx5_debugfs_root) + return 0; + + dbg = kzalloc(sizeof(*dbg), GFP_KERNEL); + if (!dbg) + return -ENOMEM; + + dbg->dir_debugfs = + debugfs_create_dir("delay_drop", + dev->mdev->priv.dbg_root); + if (!dbg->dir_debugfs) + return -ENOMEM; + + dbg->events_cnt_debugfs = + debugfs_create_atomic_t("num_timeout_events", 0400, + dbg->dir_debugfs, + &dev->delay_drop.events_cnt); + if (!dbg->events_cnt_debugfs) + goto out_debugfs; + + dbg->rqs_cnt_debugfs = + debugfs_create_atomic_t("num_rqs", 0400, + dbg->dir_debugfs, + &dev->delay_drop.rqs_cnt); + if (!dbg->rqs_cnt_debugfs) + goto out_debugfs; + + dbg->timeout_debugfs = + debugfs_create_file("timeout", 0600, + dbg->dir_debugfs, + &dev->delay_drop, + &fops_delay_drop_timeout); + if (!dbg->timeout_debugfs) + goto out_debugfs; + + return 0; + +out_debugfs: + delay_drop_debugfs_cleanup(dev); + return -ENOMEM; +} + +static void init_delay_drop(struct mlx5_ib_dev *dev) +{ + if (!(dev->ib_dev.attrs.raw_packet_caps & IB_RAW_PACKET_CAP_DELAY_DROP)) + return; + + mutex_init(&dev->delay_drop.lock); + dev->delay_drop.dev = dev; + dev->delay_drop.activate = false; + dev->delay_drop.timeout = MLX5_MAX_DELAY_DROP_TIMEOUT_MS * 1000; + INIT_WORK(&dev->delay_drop.delay_drop_work, delay_drop_handler); + atomic_set(&dev->delay_drop.rqs_cnt, 0); + atomic_set(&dev->delay_drop.events_cnt, 0); + + if (delay_drop_debugfs_init(dev)) + mlx5_ib_warn(dev, "Failed to init delay drop debugfs\n"); +} + +const struct cpumask *mlx5_ib_get_vector_affinity(struct ib_device *ibdev, + int comp_vector) +{ + struct mlx5_ib_dev *dev = to_mdev(ibdev); + + return mlx5_get_vector_affinity(dev->mdev, comp_vector); +} + static void *mlx5_ib_add(struct mlx5_core_dev *mdev) { struct mlx5_ib_dev *dev; @@ -3686,6 +3954,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status; dev->ib_dev.get_port_immutable = mlx5_port_immutable; dev->ib_dev.get_dev_fw_str = get_dev_fw_str; + dev->ib_dev.get_vector_affinity = mlx5_ib_get_vector_affinity; if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads)) dev->ib_dev.alloc_rdma_netdev = mlx5_ib_alloc_rdma_netdev; @@ -3723,18 +3992,20 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) (1ull << IB_USER_VERBS_CMD_CLOSE_XRCD); } + dev->ib_dev.create_flow = mlx5_ib_create_flow; + dev->ib_dev.destroy_flow = mlx5_ib_destroy_flow; + dev->ib_dev.uverbs_ex_cmd_mask |= + (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) | + (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW); + if (mlx5_ib_port_link_layer(&dev->ib_dev, 1) == IB_LINK_LAYER_ETHERNET) { - dev->ib_dev.create_flow = mlx5_ib_create_flow; - dev->ib_dev.destroy_flow = mlx5_ib_destroy_flow; dev->ib_dev.create_wq = mlx5_ib_create_wq; dev->ib_dev.modify_wq = mlx5_ib_modify_wq; dev->ib_dev.destroy_wq = mlx5_ib_destroy_wq; dev->ib_dev.create_rwq_ind_table = mlx5_ib_create_rwq_ind_table; dev->ib_dev.destroy_rwq_ind_table = mlx5_ib_destroy_rwq_ind_table; dev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW) | (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | @@ -3754,6 +4025,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) err = mlx5_enable_eth(dev); if (err) goto err_free_port; + dev->roce.last_port_state = IB_PORT_DOWN; } err = create_dev_resources(&dev->devr); @@ -3770,9 +4042,13 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) goto err_odp; } + err = mlx5_ib_init_cong_debugfs(dev); + if (err) + goto err_cnt; + dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev); if (!dev->mdev->priv.uar) - goto err_cnt; + goto err_cong; err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false); if (err) @@ -3790,18 +4066,25 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) if (err) goto err_dev; + init_delay_drop(dev); + for (i = 0; i < ARRAY_SIZE(mlx5_class_attributes); i++) { err = device_create_file(&dev->ib_dev.dev, mlx5_class_attributes[i]); if (err) - goto err_umrc; + goto err_delay_drop; } + if ((MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && + MLX5_CAP_GEN(mdev, disable_local_lb)) + mutex_init(&dev->lb_mutex); + dev->ib_active = true; return dev; -err_umrc: +err_delay_drop: + cancel_delay_drop(dev); destroy_umrc_res(dev); err_dev: @@ -3817,6 +4100,8 @@ err_uar_page: mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar); err_cnt: + mlx5_ib_cleanup_cong_debugfs(dev); +err_cong: if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) mlx5_ib_dealloc_counters(dev); @@ -3846,11 +4131,13 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) struct mlx5_ib_dev *dev = context; enum rdma_link_layer ll = mlx5_ib_port_link_layer(&dev->ib_dev, 1); + cancel_delay_drop(dev); mlx5_remove_netdev_notifier(dev); ib_unregister_device(&dev->ib_dev); mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg); mlx5_free_bfreg(dev->mdev, &dev->bfreg); mlx5_put_uars_page(dev->mdev, mdev->priv.uar); + mlx5_ib_cleanup_cong_debugfs(dev); if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) mlx5_ib_dealloc_counters(dev); destroy_umrc_res(dev); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index bdcf25410c99..7ac991070020 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -247,6 +247,10 @@ struct mlx5_ib_wq { void *qend; }; +enum mlx5_ib_wq_flags { + MLX5_IB_WQ_FLAGS_DELAY_DROP = 0x1, +}; + struct mlx5_ib_rwq { struct ib_wq ibwq; struct mlx5_core_qp core_qp; @@ -264,6 +268,7 @@ struct mlx5_ib_rwq { u32 wqe_count; u32 wqe_shift; int wq_sig; + u32 create_flags; /* Use enum mlx5_ib_wq_flags */ }; enum { @@ -378,6 +383,7 @@ struct mlx5_ib_qp { struct list_head cq_recv_list; struct list_head cq_send_list; u32 rate_limit; + u32 underlay_qpn; }; struct mlx5_ib_cq_buf { @@ -399,6 +405,7 @@ enum mlx5_ib_qp_flags { MLX5_IB_QP_CAP_SCATTER_FCS = 1 << 7, MLX5_IB_QP_RSS = 1 << 8, MLX5_IB_QP_CVLAN_STRIPPING = 1 << 9, + MLX5_IB_QP_UNDERLAY = 1 << 10, }; struct mlx5_umr_wr { @@ -616,6 +623,63 @@ struct mlx5_roce { struct net_device *netdev; struct notifier_block nb; atomic_t next_port; + enum ib_port_state last_port_state; +}; + +struct mlx5_ib_dbg_param { + int offset; + struct mlx5_ib_dev *dev; + struct dentry *dentry; +}; + +enum mlx5_ib_dbg_cc_types { + MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE, + MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI, + MLX5_IB_DBG_CC_RP_TIME_RESET, + MLX5_IB_DBG_CC_RP_BYTE_RESET, + MLX5_IB_DBG_CC_RP_THRESHOLD, + MLX5_IB_DBG_CC_RP_AI_RATE, + MLX5_IB_DBG_CC_RP_HAI_RATE, + MLX5_IB_DBG_CC_RP_MIN_DEC_FAC, + MLX5_IB_DBG_CC_RP_MIN_RATE, + MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP, + MLX5_IB_DBG_CC_RP_DCE_TCP_G, + MLX5_IB_DBG_CC_RP_DCE_TCP_RTT, + MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD, + MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE, + MLX5_IB_DBG_CC_RP_GD, + MLX5_IB_DBG_CC_NP_CNP_DSCP, + MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE, + MLX5_IB_DBG_CC_NP_CNP_PRIO, + MLX5_IB_DBG_CC_MAX, +}; + +struct mlx5_ib_dbg_cc_params { + struct dentry *root; + struct mlx5_ib_dbg_param params[MLX5_IB_DBG_CC_MAX]; +}; + +enum { + MLX5_MAX_DELAY_DROP_TIMEOUT_MS = 100, +}; + +struct mlx5_ib_dbg_delay_drop { + struct dentry *dir_debugfs; + struct dentry *rqs_cnt_debugfs; + struct dentry *events_cnt_debugfs; + struct dentry *timeout_debugfs; +}; + +struct mlx5_ib_delay_drop { + struct mlx5_ib_dev *dev; + struct work_struct delay_drop_work; + /* serialize setting of delay drop */ + struct mutex lock; + u32 timeout; + bool activate; + atomic_t events_cnt; + atomic_t rqs_cnt; + struct mlx5_ib_dbg_delay_drop *dbg; }; struct mlx5_ib_dev { @@ -652,9 +716,15 @@ struct mlx5_ib_dev { struct list_head qp_list; /* Array with num_ports elements */ struct mlx5_ib_port *port; - struct mlx5_sq_bfreg bfreg; - struct mlx5_sq_bfreg fp_bfreg; - u8 umr_fence; + struct mlx5_sq_bfreg bfreg; + struct mlx5_sq_bfreg fp_bfreg; + struct mlx5_ib_delay_drop delay_drop; + struct mlx5_ib_dbg_cc_params *dbg_cc_params; + + /* protect the user_td */ + struct mutex lb_mutex; + u32 user_td; + u8 umr_fence; }; static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq) @@ -904,6 +974,9 @@ __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num, int mlx5_get_roce_gid_type(struct mlx5_ib_dev *dev, u8 port_num, int index, enum ib_gid_type *gid_type); +void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev); +int mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev); + /* GSI QP helper functions */ struct ib_qp *mlx5_ib_gsi_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 2c40a2e989d2..a0eb2f96179a 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -48,6 +48,7 @@ enum { #define MLX5_UMR_ALIGN 2048 static int clean_mr(struct mlx5_ib_mr *mr); +static int max_umr_order(struct mlx5_ib_dev *dev); static int use_umr(struct mlx5_ib_dev *dev, int order); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); @@ -491,16 +492,18 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order) struct mlx5_mr_cache *cache = &dev->cache; struct mlx5_ib_mr *mr = NULL; struct mlx5_cache_ent *ent; + int last_umr_cache_entry; int c; int i; c = order2idx(dev, order); - if (c < 0 || c > MAX_UMR_CACHE_ENTRY) { + last_umr_cache_entry = order2idx(dev, max_umr_order(dev)); + if (c < 0 || c > last_umr_cache_entry) { mlx5_ib_warn(dev, "order %d, cache index %d\n", order, c); return NULL; } - for (i = c; i < MAX_UMR_CACHE_ENTRY; i++) { + for (i = c; i <= last_umr_cache_entry; i++) { ent = &cache->ent[i]; mlx5_ib_dbg(dev, "order %d, cache index %d\n", ent->order, i); @@ -816,11 +819,16 @@ static int get_octo_len(u64 addr, u64 len, int page_size) return (npages + 1) / 2; } -static int use_umr(struct mlx5_ib_dev *dev, int order) +static int max_umr_order(struct mlx5_ib_dev *dev) { if (MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) - return order <= MAX_UMR_CACHE_ENTRY + 2; - return order <= MLX5_MAX_UMR_SHIFT; + return MAX_UMR_CACHE_ENTRY + 2; + return MLX5_MAX_UMR_SHIFT; +} + +static int use_umr(struct mlx5_ib_dev *dev, int order) +{ + return order <= max_umr_order(dev); } static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length, diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 0889ff367c86..5c7ce9bd466e 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -34,6 +34,7 @@ #include <rdma/ib_umem.h> #include <rdma/ib_cache.h> #include <rdma/ib_user_verbs.h> +#include <linux/mlx5/fs.h> #include "mlx5_ib.h" /* not supported currently */ @@ -453,7 +454,8 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev, return -EINVAL; } - if (attr->qp_type == IB_QPT_RAW_PACKET) { + if (attr->qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) { base->ubuffer.buf_size = qp->rq.wqe_cnt << qp->rq.wqe_shift; qp->raw_packet_qp.sq.ubuffer.buf_size = qp->sq.wqe_cnt << 6; } else { @@ -675,10 +677,14 @@ err_umem: return err; } -static void destroy_user_rq(struct ib_pd *pd, struct mlx5_ib_rwq *rwq) +static void destroy_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd, + struct mlx5_ib_rwq *rwq) { struct mlx5_ib_ucontext *context; + if (rwq->create_flags & MLX5_IB_WQ_FLAGS_DELAY_DROP) + atomic_dec(&dev->delay_drop.rqs_cnt); + context = to_mucontext(pd->uobject->context); mlx5_ib_db_unmap_user(context, &rwq->db); if (rwq->umem) @@ -1021,12 +1027,16 @@ static int is_connected(enum ib_qp_type qp_type) } static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev, + struct mlx5_ib_qp *qp, struct mlx5_ib_sq *sq, u32 tdn) { u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0}; void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); MLX5_SET(tisc, tisc, transport_domain, tdn); + if (qp->flags & MLX5_IB_QP_UNDERLAY) + MLX5_SET(tisc, tisc, underlay_qpn, qp->underlay_qpn); + return mlx5_core_create_tis(dev->mdev, in, sizeof(in), &sq->tisn); } @@ -1229,7 +1239,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, u32 tdn = mucontext->tdn; if (qp->sq.wqe_cnt) { - err = create_raw_packet_qp_tis(dev, sq, tdn); + err = create_raw_packet_qp_tis(dev, qp, sq, tdn); if (err) return err; @@ -1502,10 +1512,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - base = init_attr->qp_type == IB_QPT_RAW_PACKET ? - &qp->raw_packet_qp.rq.base : - &qp->trans_qp.base; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -1587,10 +1593,28 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, qp->wq_sig = !!(ucmd.flags & MLX5_QP_FLAG_SIGNATURE); qp->scat_cqe = !!(ucmd.flags & MLX5_QP_FLAG_SCATTER_CQE); + + if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) { + if (init_attr->qp_type != IB_QPT_UD || + (MLX5_CAP_GEN(dev->mdev, port_type) != + MLX5_CAP_PORT_TYPE_IB) || + !mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS)) { + mlx5_ib_dbg(dev, "Source QP option isn't supported\n"); + return -EOPNOTSUPP; + } + + qp->flags |= MLX5_IB_QP_UNDERLAY; + qp->underlay_qpn = init_attr->source_qpn; + } } else { qp->wq_sig = !!wq_signature; } + base = (init_attr->qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) ? + &qp->raw_packet_qp.rq.base : + &qp->trans_qp.base; + qp->has_rq = qp_has_rq(init_attr); err = set_rq_size(dev, &init_attr->cap, qp->has_rq, qp, (pd && pd->uobject) ? &ucmd : NULL); @@ -1741,7 +1765,8 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, qp->flags |= MLX5_IB_QP_LSO; } - if (init_attr->qp_type == IB_QPT_RAW_PACKET) { + if (init_attr->qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) { qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr; raw_packet_qp_copy_info(qp, &qp->raw_packet_qp); err = create_raw_packet_qp(dev, qp, in, pd); @@ -1893,7 +1918,7 @@ static int modify_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp) { struct mlx5_ib_cq *send_cq, *recv_cq; - struct mlx5_ib_qp_base *base = &qp->trans_qp.base; + struct mlx5_ib_qp_base *base; unsigned long flags; int err; @@ -1902,12 +1927,14 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp) return; } - base = qp->ibqp.qp_type == IB_QPT_RAW_PACKET ? + base = (qp->ibqp.qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) ? &qp->raw_packet_qp.rq.base : &qp->trans_qp.base; if (qp->state != IB_QPS_RESET) { - if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET) { + if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET && + !(qp->flags & MLX5_IB_QP_UNDERLAY)) { err = mlx5_core_qp_modify(dev->mdev, MLX5_CMD_OP_2RST_QP, 0, NULL, &base->mqp); @@ -1946,7 +1973,8 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp) mlx5_ib_unlock_cqs(send_cq, recv_cq); spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags); - if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) { + if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) { destroy_raw_packet_qp(dev, qp); } else { err = mlx5_core_destroy_qp(dev->mdev, &base->mqp); @@ -2702,7 +2730,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (is_sqp(ibqp->qp_type)) { context->mtu_msgmax = (IB_MTU_256 << 5) | 8; - } else if (ibqp->qp_type == IB_QPT_UD || + } else if ((ibqp->qp_type == IB_QPT_UD && + !(qp->flags & MLX5_IB_QP_UNDERLAY)) || ibqp->qp_type == MLX5_IB_QPT_REG_UMR) { context->mtu_msgmax = (IB_MTU_4096 << 5) | 12; } else if (attr_mask & IB_QP_PATH_MTU) { @@ -2799,6 +2828,11 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) { u8 port_num = (attr_mask & IB_QP_PORT ? attr->port_num : qp->port) - 1; + + /* Underlay port should be used - index 0 function per port */ + if (qp->flags & MLX5_IB_QP_UNDERLAY) + port_num = 0; + mibport = &dev->port[port_num]; context->qp_counter_set_usr_page |= cpu_to_be32((u32)(mibport->cnts.set_id) << 24); @@ -2824,7 +2858,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, optpar = ib_mask_to_mlx5_opt(attr_mask); optpar &= opt_mask[mlx5_cur][mlx5_new][mlx5_st]; - if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) { + if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) { struct mlx5_modify_raw_qp_param raw_qp_param = {}; raw_qp_param.operation = op; @@ -2913,7 +2948,13 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, ll = dev->ib_dev.get_link_layer(&dev->ib_dev, port); } - if (qp_type != MLX5_IB_QPT_REG_UMR && + if (qp->flags & MLX5_IB_QP_UNDERLAY) { + if (attr_mask & ~(IB_QP_STATE | IB_QP_CUR_STATE)) { + mlx5_ib_dbg(dev, "invalid attr_mask 0x%x when underlay QP is used\n", + attr_mask); + goto out; + } + } else if (qp_type != MLX5_IB_QPT_REG_UMR && !ib_modify_qp_is_ok(cur_state, new_state, qp_type, attr_mask, ll)) { mlx5_ib_dbg(dev, "invalid QP state transition from %d to %d, qp_type %d, attr_mask 0x%x\n", cur_state, new_state, ibqp->qp_type, attr_mask); @@ -4477,9 +4518,14 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, return mlx5_ib_gsi_query_qp(ibqp, qp_attr, qp_attr_mask, qp_init_attr); + /* Not all of output fields are applicable, make sure to zero them */ + memset(qp_init_attr, 0, sizeof(*qp_init_attr)); + memset(qp_attr, 0, sizeof(*qp_attr)); + mutex_lock(&qp->mutex); - if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) { + if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET || + qp->flags & MLX5_IB_QP_UNDERLAY) { err = query_raw_packet_qp_state(dev, qp, &raw_packet_qp_state); if (err) goto out; @@ -4597,6 +4643,27 @@ static void mlx5_ib_wq_event(struct mlx5_core_qp *core_qp, int type) } } +static int set_delay_drop(struct mlx5_ib_dev *dev) +{ + int err = 0; + + mutex_lock(&dev->delay_drop.lock); + if (dev->delay_drop.activate) + goto out; + + err = mlx5_core_set_delay_drop(dev->mdev, dev->delay_drop.timeout); + if (err) + goto out; + + dev->delay_drop.activate = true; +out: + mutex_unlock(&dev->delay_drop.lock); + + if (!err) + atomic_inc(&dev->delay_drop.rqs_cnt); + return err; +} + static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, struct ib_wq_init_attr *init_attr) { @@ -4651,9 +4718,28 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, } MLX5_SET(rqc, rqc, scatter_fcs, 1); } + if (init_attr->create_flags & IB_WQ_FLAGS_DELAY_DROP) { + if (!(dev->ib_dev.attrs.raw_packet_caps & + IB_RAW_PACKET_CAP_DELAY_DROP)) { + mlx5_ib_dbg(dev, "Delay drop is not supported\n"); + err = -EOPNOTSUPP; + goto out; + } + MLX5_SET(rqc, rqc, delay_drop_en, 1); + } rq_pas0 = (__be64 *)MLX5_ADDR_OF(wq, wq, pas); mlx5_ib_populate_pas(dev, rwq->umem, rwq->page_shift, rq_pas0, 0); err = mlx5_core_create_rq_tracked(dev->mdev, in, inlen, &rwq->core_qp); + if (!err && init_attr->create_flags & IB_WQ_FLAGS_DELAY_DROP) { + err = set_delay_drop(dev); + if (err) { + mlx5_ib_warn(dev, "Failed to enable delay drop err=%d\n", + err); + mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp); + } else { + rwq->create_flags |= MLX5_IB_WQ_FLAGS_DELAY_DROP; + } + } out: kvfree(in); return err; @@ -4787,7 +4873,7 @@ struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd, err_copy: mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp); err_user_rq: - destroy_user_rq(pd, rwq); + destroy_user_rq(dev, pd, rwq); err: kfree(rwq); return ERR_PTR(err); @@ -4799,7 +4885,7 @@ int mlx5_ib_destroy_wq(struct ib_wq *wq) struct mlx5_ib_rwq *rwq = to_mrwq(wq); mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp); - destroy_user_rq(wq->pd, rwq); + destroy_user_rq(dev, wq->pd, rwq); kfree(rwq); return 0; diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c index 9d83a53c0c67..e19ae0b9b439 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.c +++ b/drivers/infiniband/hw/mthca/mthca_cmd.c @@ -1921,7 +1921,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey, (in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0); MTHCA_PUT(inbox, val, MAD_IFC_G_PATH_OFFSET); - MTHCA_PUT(inbox, in_wc->slid, MAD_IFC_RLID_OFFSET); + MTHCA_PUT(inbox, ib_slid_cpu16(in_wc->slid), MAD_IFC_RLID_OFFSET); MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET); if (in_grh) @@ -1929,7 +1929,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey, op_modifier |= 0x4; - in_modifier |= in_wc->slid << 16; + in_modifier |= ib_slid_cpu16(in_wc->slid) << 16; } err = mthca_cmd_box(dev, inmailbox->dma, outmailbox->dma, diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c index 7df3db71777a..a9caadab22cf 100644 --- a/drivers/infiniband/hw/mthca/mthca_mad.c +++ b/drivers/infiniband/hw/mthca/mthca_mad.c @@ -205,7 +205,7 @@ int mthca_process_mad(struct ib_device *ibdev, u16 *out_mad_pkey_index) { int err; - u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE); + u16 slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE); u16 prev_lid = 0; struct ib_port_attr pattr; const struct ib_mad *in_mad = (const struct ib_mad *)in; @@ -256,7 +256,7 @@ int mthca_process_mad(struct ib_device *ibdev, in_mad->mad_hdr.method == IB_MGMT_METHOD_SET && in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO && !ib_query_port(ibdev, port_num, &pattr)) - prev_lid = pattr.lid; + prev_lid = (u16)pattr.lid; err = mthca_MAD_IFC(to_mdev(ibdev), mad_flags & IB_MAD_IGNORE_MKEY, diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c index c309e5c96383..e36a9bc52268 100644 --- a/drivers/infiniband/hw/mthca/mthca_main.c +++ b/drivers/infiniband/hw/mthca/mthca_main.c @@ -49,7 +49,6 @@ MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("Mellanox InfiniBand HCA low-level driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); #ifdef CONFIG_INFINIBAND_MTHCA_DEBUG @@ -1162,7 +1161,7 @@ static void mthca_remove_one(struct pci_dev *pdev) mutex_unlock(&mthca_device_mutex); } -static struct pci_device_id mthca_pci_table[] = { +static const struct pci_device_id mthca_pci_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MELLANOX, PCI_DEVICE_ID_MELLANOX_TAVOR), .driver_data = TAVOR }, { PCI_DEVICE(PCI_VENDOR_ID_TOPSPIN, PCI_DEVICE_ID_MELLANOX_TAVOR), diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index c197cd9b193f..eae9bffd45d4 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -1178,12 +1178,11 @@ static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_dev_fw_str(struct ib_device *device, char *str, - size_t str_len) +static void get_dev_fw_str(struct ib_device *device, char *str) { struct mthca_dev *dev = container_of(device, struct mthca_dev, ib_dev); - snprintf(str, str_len, "%d.%d.%d", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d", (int) (dev->fw_ver >> 32), (int) (dev->fw_ver >> 16) & 0xffff, (int) dev->fw_ver & 0xffff); diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c index a30aa6527f7e..942ca84713c9 100644 --- a/drivers/infiniband/hw/nes/nes.c +++ b/drivers/infiniband/hw/nes/nes.c @@ -63,7 +63,6 @@ MODULE_AUTHOR("NetEffect"); MODULE_DESCRIPTION("NetEffect RNIC Low-level iWARP Driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); int interrupt_mod_interval = 0; @@ -102,7 +101,7 @@ static unsigned int ee_flsh_adapter; static unsigned int sysfs_nonidx_addr; static unsigned int sysfs_idx_addr; -static struct pci_device_id nes_pci_table[] = { +static const struct pci_device_id nes_pci_table[] = { { PCI_VDEVICE(NETEFFECT, PCI_DEVICE_ID_NETEFFECT_NE020), }, { PCI_VDEVICE(NETEFFECT, PCI_DEVICE_ID_NETEFFECT_NE020_KR), }, {0} @@ -808,13 +807,6 @@ static void nes_remove(struct pci_dev *pcidev) } -static struct pci_driver nes_pci_driver = { - .name = DRV_NAME, - .id_table = nes_pci_table, - .probe = nes_probe, - .remove = nes_remove, -}; - static ssize_t adapter_show(struct device_driver *ddp, char *buf) { unsigned int devfn = 0xffffffff; @@ -1156,35 +1148,29 @@ static DRIVER_ATTR_RW(idx_addr); static DRIVER_ATTR_RW(idx_data); static DRIVER_ATTR_RW(wqm_quanta); -static int nes_create_driver_sysfs(struct pci_driver *drv) -{ - int error; - error = driver_create_file(&drv->driver, &driver_attr_adapter); - error |= driver_create_file(&drv->driver, &driver_attr_eeprom_cmd); - error |= driver_create_file(&drv->driver, &driver_attr_eeprom_data); - error |= driver_create_file(&drv->driver, &driver_attr_flash_cmd); - error |= driver_create_file(&drv->driver, &driver_attr_flash_data); - error |= driver_create_file(&drv->driver, &driver_attr_nonidx_addr); - error |= driver_create_file(&drv->driver, &driver_attr_nonidx_data); - error |= driver_create_file(&drv->driver, &driver_attr_idx_addr); - error |= driver_create_file(&drv->driver, &driver_attr_idx_data); - error |= driver_create_file(&drv->driver, &driver_attr_wqm_quanta); - return error; -} +static struct attribute *nes_attrs[] = { + &driver_attr_adapter.attr, + &driver_attr_eeprom_cmd.attr, + &driver_attr_eeprom_data.attr, + &driver_attr_flash_cmd.attr, + &driver_attr_flash_data.attr, + &driver_attr_nonidx_addr.attr, + &driver_attr_nonidx_data.attr, + &driver_attr_idx_addr.attr, + &driver_attr_idx_data.attr, + &driver_attr_wqm_quanta.attr, + NULL, +}; +ATTRIBUTE_GROUPS(nes); + +static struct pci_driver nes_pci_driver = { + .name = DRV_NAME, + .id_table = nes_pci_table, + .probe = nes_probe, + .remove = nes_remove, + .groups = nes_groups, +}; -static void nes_remove_driver_sysfs(struct pci_driver *drv) -{ - driver_remove_file(&drv->driver, &driver_attr_adapter); - driver_remove_file(&drv->driver, &driver_attr_eeprom_cmd); - driver_remove_file(&drv->driver, &driver_attr_eeprom_data); - driver_remove_file(&drv->driver, &driver_attr_flash_cmd); - driver_remove_file(&drv->driver, &driver_attr_flash_data); - driver_remove_file(&drv->driver, &driver_attr_nonidx_addr); - driver_remove_file(&drv->driver, &driver_attr_nonidx_data); - driver_remove_file(&drv->driver, &driver_attr_idx_addr); - driver_remove_file(&drv->driver, &driver_attr_idx_data); - driver_remove_file(&drv->driver, &driver_attr_wqm_quanta); -} /** * nes_init_module - module initialization entry point @@ -1192,20 +1178,13 @@ static void nes_remove_driver_sysfs(struct pci_driver *drv) static int __init nes_init_module(void) { int retval; - int retval1; retval = nes_cm_start(); if (retval) { printk(KERN_ERR PFX "Unable to start NetEffect iWARP CM.\n"); return retval; } - retval = pci_register_driver(&nes_pci_driver); - if (retval >= 0) { - retval1 = nes_create_driver_sysfs(&nes_pci_driver); - if (retval1 < 0) - printk(KERN_ERR PFX "Unable to create NetEffect sys files.\n"); - } - return retval; + return pci_register_driver(&nes_pci_driver); } @@ -1215,7 +1194,6 @@ static int __init nes_init_module(void) static void __exit nes_exit_module(void) { nes_cm_stop(); - nes_remove_driver_sysfs(&nes_pci_driver); pci_unregister_driver(&nes_pci_driver); } diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 25dcd7573df9..c2943e39d2f9 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3672,15 +3672,14 @@ static int nes_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_dev_fw_str(struct ib_device *dev, char *str, - size_t str_len) +static void get_dev_fw_str(struct ib_device *dev, char *str) { struct nes_ib_device *nesibdev = container_of(dev, struct nes_ib_device, ibdev); struct nes_vnic *nesvnic = nesibdev->nesvnic; nes_debug(NES_DBG_INIT, "\n"); - snprintf(str, str_len, "%u.%u", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u", (nesvnic->nesdev->nesadapter->firmware_version >> 16), (nesvnic->nesdev->nesadapter->firmware_version & 0x000000ff)); } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 57c9a2ad0260..fbfbd9e96147 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -58,7 +58,6 @@ #include "ocrdma_stats.h" #include <rdma/ocrdma-abi.h> -MODULE_VERSION(OCRDMA_ROCE_DRV_VERSION); MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION); MODULE_AUTHOR("Emulex Corporation"); MODULE_LICENSE("Dual BSD/GPL"); @@ -108,12 +107,11 @@ static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void get_dev_fw_str(struct ib_device *device, char *str, - size_t str_len) +static void get_dev_fw_str(struct ib_device *device, char *str) { struct ocrdma_dev *dev = get_ocrdma_dev(device); - snprintf(str, str_len, "%s", &dev->attr.fw_ver[0]); + snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", &dev->attr.fw_ver[0]); } static int ocrdma_register_device(struct ocrdma_dev *dev) diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index b5851fd67d4f..97d033f51dc9 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -47,7 +47,6 @@ MODULE_DESCRIPTION("QLogic 40G/100G ROCE Driver"); MODULE_AUTHOR("QLogic Corporation"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(QEDR_MODULE_VERSION); #define QEDR_WQ_MULTIPLIER_DFT (3) @@ -69,13 +68,12 @@ static enum rdma_link_layer qedr_link_layer(struct ib_device *device, return IB_LINK_LAYER_ETHERNET; } -static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str, - size_t str_len) +static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str) { struct qedr_dev *qedr = get_qedr_dev(ibdev); u32 fw_ver = (u32)qedr->attr.fw_ver; - snprintf(str, str_len, "%d. %d. %d. %d", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d", (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF, (fw_ver >> 8) & 0xFF, fw_ver & 0xFF); } @@ -778,6 +776,7 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev, if (rc) goto init_err; + dev->user_dpm_enabled = dev_info.user_dpm_enabled; dev->num_hwfns = dev_info.common.num_hwfns; dev->rdma_ctx = dev->ops->rdma_get_rdma_ctx(cdev); diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index ab7784bfdac6..b2bb42e2805d 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -41,7 +41,6 @@ #include <linux/qed/roce_common.h> #include "qedr_hsi_rdma.h" -#define QEDR_MODULE_VERSION "8.10.10.0" #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA" #define DP_NAME(dev) ((dev)->ibdev.name) @@ -163,6 +162,8 @@ struct qedr_dev { struct qedr_qp *gsi_qp; unsigned long enet_state; + + u8 user_dpm_enabled; }; #define QEDR_MAX_SQ_PBL (0x8000) diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 2ae71b8f1ba8..9ee2dce3e5bb 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -376,6 +376,9 @@ struct ib_ucontext *qedr_alloc_ucontext(struct ib_device *ibdev, memset(&uresp, 0, sizeof(uresp)); + uresp.dpm_enabled = dev->user_dpm_enabled; + uresp.wids_enabled = 1; + uresp.wid_count = oparams.wid_count; uresp.db_pa = ctx->dpi_phys_addr; uresp.db_size = ctx->dpi_size; uresp.max_send_wr = dev->attr.max_sqe; diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h index a3e21a25cea5..f9e1c69603a5 100644 --- a/drivers/infiniband/hw/qib/qib.h +++ b/drivers/infiniband/hw/qib/qib.h @@ -1,7 +1,7 @@ #ifndef _QIB_KERNEL_H #define _QIB_KERNEL_H /* - * Copyright (c) 2012, 2013 Intel Corporation. All rights reserved. + * Copyright (c) 2012 - 2017 Intel Corporation. All rights reserved. * Copyright (c) 2006 - 2012 QLogic Corporation. All rights reserved. * Copyright (c) 2003, 2004, 2005, 2006 PathScale, Inc. All rights reserved. * @@ -443,7 +443,7 @@ struct qib_irq_notify; #endif struct qib_msix_entry { - struct msix_entry msix; + int irq; void *arg; #ifdef CONFIG_INFINIBAND_QIB_DCA int dca; @@ -1433,9 +1433,9 @@ int qib_pcie_init(struct pci_dev *, const struct pci_device_id *); int qib_pcie_ddinit(struct qib_devdata *, struct pci_dev *, const struct pci_device_id *); void qib_pcie_ddcleanup(struct qib_devdata *); -int qib_pcie_params(struct qib_devdata *, u32, u32 *, struct qib_msix_entry *); +int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent); int qib_reinit_intr(struct qib_devdata *); -void qib_enable_intx(struct pci_dev *); +void qib_enable_intx(struct qib_devdata *dd); void qib_nomsi(struct qib_devdata *); void qib_nomsix(struct qib_devdata *); void qib_pcie_getcmd(struct qib_devdata *, u16 *, u8 *, u8 *); diff --git a/drivers/infiniband/hw/qib/qib_driver.c b/drivers/infiniband/hw/qib/qib_driver.c index 2b5982f743ef..719906a9fd51 100644 --- a/drivers/infiniband/hw/qib/qib_driver.c +++ b/drivers/infiniband/hw/qib/qib_driver.c @@ -66,7 +66,6 @@ MODULE_PARM_DESC(compat_ddr_negotiate, MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Intel <ibsupport@intel.com>"); MODULE_DESCRIPTION("Intel IB driver"); -MODULE_VERSION(QIB_DRIVER_VERSION); /* * QIB_PIO_MAXIBHDR is the max IB header size allowed for in our diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c index e423b71e6ea0..46045fc28fa0 100644 --- a/drivers/infiniband/hw/qib/qib_iba6120.c +++ b/drivers/infiniband/hw/qib/qib_iba6120.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013 Intel Corporation. All rights reserved. + * Copyright (c) 2013 - 2017 Intel Corporation. All rights reserved. * Copyright (c) 2006, 2007, 2008, 2009, 2010 QLogic Corporation. * All rights reserved. * Copyright (c) 2003, 2004, 2005, 2006 PathScale, Inc. All rights reserved. @@ -1838,7 +1838,7 @@ static int qib_6120_setup_reset(struct qib_devdata *dd) bail: if (ret) { - if (qib_pcie_params(dd, dd->lbus_width, NULL, NULL)) + if (qib_pcie_params(dd, dd->lbus_width, NULL)) qib_dev_err(dd, "Reset failed to setup PCIe or interrupts; continuing anyway\n"); /* clear the reset error, init error/hwerror mask */ @@ -3562,7 +3562,7 @@ struct qib_devdata *qib_init_iba6120_funcs(struct pci_dev *pdev, if (qib_mini_init) goto bail; - if (qib_pcie_params(dd, 8, NULL, NULL)) + if (qib_pcie_params(dd, 8, NULL)) qib_dev_err(dd, "Failed to setup PCIe or interrupts; continuing anyway\n"); dd->cspec->irq = pdev->irq; /* save IRQ */ diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c index c3679c48e61c..49cd6e3beb72 100644 --- a/drivers/infiniband/hw/qib/qib_iba7220.c +++ b/drivers/infiniband/hw/qib/qib_iba7220.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2011 - 2017 Intel Corporation. All rights reserved. * Copyright (c) 2006, 2007, 2008, 2009, 2010 QLogic Corporation. * All rights reserved. * Copyright (c) 2003, 2004, 2005, 2006 PathScale, Inc. All rights reserved. @@ -2148,7 +2149,7 @@ static int qib_setup_7220_reset(struct qib_devdata *dd) bail: if (ret) { - if (qib_pcie_params(dd, dd->lbus_width, NULL, NULL)) + if (qib_pcie_params(dd, dd->lbus_width, NULL)) qib_dev_err(dd, "Reset failed to setup PCIe or interrupts; continuing anyway\n"); @@ -3309,7 +3310,7 @@ static int qib_7220_intr_fallback(struct qib_devdata *dd) qib_devinfo(dd->pcidev, "MSI interrupt not detected, trying INTx interrupts\n"); qib_7220_free_irq(dd); - qib_enable_intx(dd->pcidev); + qib_enable_intx(dd); /* * Some newer kernels require free_irq before disable_msi, * and irq can be changed during disable and INTx enable @@ -4619,7 +4620,7 @@ struct qib_devdata *qib_init_iba7220_funcs(struct pci_dev *pdev, minwidth = 8; /* x8 capable boards */ break; } - if (qib_pcie_params(dd, minwidth, NULL, NULL)) + if (qib_pcie_params(dd, minwidth, NULL)) qib_dev_err(dd, "Failed to setup PCIe or interrupts; continuing anyway\n"); diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index bb2439fff8fa..2653064ce9e9 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2012 Intel Corporation. All rights reserved. + * Copyright (c) 2012 - 2017 Intel Corporation. All rights reserved. * Copyright (c) 2008 - 2012 QLogic Corporation. All rights reserved. * * This software is available to you under a choice of one of two @@ -2841,10 +2841,10 @@ static void qib_7322_nomsix(struct qib_devdata *dd) reset_dca_notifier(dd, &dd->cspec->msix_entries[i]); #endif irq_set_affinity_hint( - dd->cspec->msix_entries[i].msix.vector, NULL); + dd->cspec->msix_entries[i].irq, NULL); free_cpumask_var(dd->cspec->msix_entries[i].mask); - free_irq(dd->cspec->msix_entries[i].msix.vector, - dd->cspec->msix_entries[i].arg); + free_irq(dd->cspec->msix_entries[i].irq, + dd->cspec->msix_entries[i].arg); } qib_nomsix(dd); } @@ -3336,9 +3336,9 @@ static void reset_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m) qib_devinfo(dd->pcidev, "Disabling notifier on HCA %d irq %d\n", dd->unit, - m->msix.vector); + m->irq); irq_set_affinity_notifier( - m->msix.vector, + m->irq, NULL); m->notifier = NULL; } @@ -3354,7 +3354,7 @@ static void setup_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m) int ret; m->notifier = n; - n->notify.irq = m->msix.vector; + n->notify.irq = m->irq; n->notify.notify = qib_irq_notifier_notify; n->notify.release = qib_irq_notifier_release; n->arg = m->arg; @@ -3500,10 +3500,21 @@ try_intx: - 1, QIB_DRV_NAME "%d (kctx)", dd->unit); } - ret = request_irq( - dd->cspec->msix_entries[msixnum].msix.vector, - handler, 0, dd->cspec->msix_entries[msixnum].name, - arg); + + dd->cspec->msix_entries[msixnum].irq = pci_irq_vector( + dd->pcidev, msixnum); + if (dd->cspec->msix_entries[msixnum].irq < 0) { + qib_dev_err(dd, + "Couldn't get MSIx irq (vec=%d): %d\n", + msixnum, + dd->cspec->msix_entries[msixnum].irq); + qib_7322_nomsix(dd); + goto try_intx; + } + ret = request_irq(dd->cspec->msix_entries[msixnum].irq, + handler, 0, + dd->cspec->msix_entries[msixnum].name, + arg); if (ret) { /* * Shouldn't happen since the enable said we could @@ -3512,7 +3523,7 @@ try_intx: qib_dev_err(dd, "Couldn't setup MSIx interrupt (vec=%d, irq=%d): %d\n", msixnum, - dd->cspec->msix_entries[msixnum].msix.vector, + dd->cspec->msix_entries[msixnum].irq, ret); qib_7322_nomsix(dd); goto try_intx; @@ -3548,7 +3559,7 @@ try_intx: dd->cspec->msix_entries[msixnum].mask); } irq_set_affinity_hint( - dd->cspec->msix_entries[msixnum].msix.vector, + dd->cspec->msix_entries[msixnum].irq, dd->cspec->msix_entries[msixnum].mask); } msixnum++; @@ -3744,7 +3755,6 @@ static int qib_do_7322_reset(struct qib_devdata *dd) if (msix_entries) { /* restore the MSIx vector address and data if saved above */ for (i = 0; i < msix_entries; i++) { - dd->cspec->msix_entries[i].msix.entry = i; if (!msix_vecsave || !msix_vecsave[2 * i]) continue; qib_write_kreg(dd, 2 * i + @@ -3762,8 +3772,7 @@ static int qib_do_7322_reset(struct qib_devdata *dd) write_7322_initregs(dd); if (qib_pcie_params(dd, dd->lbus_width, - &dd->cspec->num_msix_entries, - dd->cspec->msix_entries)) + &dd->cspec->num_msix_entries)) qib_dev_err(dd, "Reset failed to setup PCIe or interrupts; continuing anyway\n"); @@ -5195,7 +5204,7 @@ static int qib_7322_intr_fallback(struct qib_devdata *dd) qib_devinfo(dd->pcidev, "MSIx interrupt not detected, trying INTx interrupts\n"); qib_7322_nomsix(dd); - qib_enable_intx(dd->pcidev); + qib_enable_intx(dd); qib_setup_7322_interrupt(dd, 0); return 1; } @@ -7327,10 +7336,7 @@ struct qib_devdata *qib_init_iba7322_funcs(struct pci_dev *pdev, if (!dd->cspec->msix_entries) tabsize = 0; - for (i = 0; i < tabsize; i++) - dd->cspec->msix_entries[i].msix.entry = i; - - if (qib_pcie_params(dd, 8, &tabsize, dd->cspec->msix_entries)) + if (qib_pcie_params(dd, 8, &tabsize)) qib_dev_err(dd, "Failed to setup PCIe or interrupts; continuing anyway\n"); /* may be less than we wanted, if not enough available */ diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index 6c16ba1107ba..cce4ab468b29 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -399,7 +399,7 @@ static int loadtime_init(struct qib_devdata *dd) if (((dd->revision >> QLOGIC_IB_R_SOFTWARE_SHIFT) & QLOGIC_IB_R_SOFTWARE_MASK) != QIB_CHIP_SWVERSION) { qib_dev_err(dd, - "Driver only handles version %d, chip swversion is %d (%llx), failng\n", + "Driver only handles version %d, chip swversion is %d (%llx), failing\n", QIB_CHIP_SWVERSION, (int)(dd->revision >> QLOGIC_IB_R_SOFTWARE_SHIFT) & diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index da295e0392ed..6b9b43b944e3 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -134,24 +134,21 @@ static void qib_send_trap(struct qib_ibport *ibp, void *data, unsigned len) } /* - * Send a bad [PQ]_Key trap (ch. 14.3.8). + * Send a bad P_Key trap (ch. 14.3.8). */ -void qib_bad_pqkey(struct qib_ibport *ibp, __be16 trap_num, u32 key, u32 sl, - u32 qp1, u32 qp2, __be16 lid1, __be16 lid2) +void qib_bad_pkey(struct qib_ibport *ibp, u32 key, u32 sl, + u32 qp1, u32 qp2, __be16 lid1, __be16 lid2) { struct ib_mad_notice_attr data; - if (trap_num == IB_NOTICE_TRAP_BAD_PKEY) - ibp->rvp.pkey_violations++; - else - ibp->rvp.qkey_violations++; ibp->rvp.n_pkt_drops++; + ibp->rvp.pkey_violations++; /* Send violation trap */ data.generic_type = IB_NOTICE_TYPE_SECURITY; data.prod_type_msb = 0; data.prod_type_lsb = IB_NOTICE_PROD_CA; - data.trap_num = trap_num; + data.trap_num = IB_NOTICE_TRAP_BAD_PKEY; data.issuer_lid = cpu_to_be16(ppd_from_ibp(ibp)->lid); data.toggle_count = 0; memset(&data.details, 0, sizeof(data.details)); @@ -874,8 +871,6 @@ static int subn_set_portinfo(struct ib_smp *smp, struct ib_device *ibdev, ib_dispatch_event(&event); } - ret = subn_get_portinfo(smp, ibdev, port); - /* restore re-reg bit per o14-12.2.1 */ pip->clientrereg_resv_subnetto |= clientrereg; diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c index c379b8342a09..d90403e31a9d 100644 --- a/drivers/infiniband/hw/qib/qib_pcie.c +++ b/drivers/infiniband/hw/qib/qib_pcie.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2010 - 2017 Intel Corporation. All rights reserved. * Copyright (c) 2008, 2009 QLogic Corporation. All rights reserved. * * This software is available to you under a choice of one of two @@ -187,112 +188,84 @@ void qib_pcie_ddcleanup(struct qib_devdata *dd) pci_set_drvdata(dd->pcidev, NULL); } -static void qib_msix_setup(struct qib_devdata *dd, int pos, u32 *msixcnt, - struct qib_msix_entry *qib_msix_entry) -{ - int ret; - int nvec = *msixcnt; - struct msix_entry *msix_entry; - int i; - - ret = pci_msix_vec_count(dd->pcidev); - if (ret < 0) - goto do_intx; - - nvec = min(nvec, ret); - - /* We can't pass qib_msix_entry array to qib_msix_setup - * so use a dummy msix_entry array and copy the allocated - * irq back to the qib_msix_entry array. */ - msix_entry = kcalloc(nvec, sizeof(*msix_entry), GFP_KERNEL); - if (!msix_entry) - goto do_intx; - - for (i = 0; i < nvec; i++) - msix_entry[i] = qib_msix_entry[i].msix; - - ret = pci_enable_msix_range(dd->pcidev, msix_entry, 1, nvec); - if (ret < 0) - goto free_msix_entry; - else - nvec = ret; - - for (i = 0; i < nvec; i++) - qib_msix_entry[i].msix = msix_entry[i]; - - kfree(msix_entry); - *msixcnt = nvec; - return; - -free_msix_entry: - kfree(msix_entry); - -do_intx: - qib_dev_err( - dd, - "pci_enable_msix_range %d vectors failed: %d, falling back to INTx\n", - nvec, ret); - *msixcnt = 0; - qib_enable_intx(dd->pcidev); -} - /** * We save the msi lo and hi values, so we can restore them after * chip reset (the kernel PCI infrastructure doesn't yet handle that * correctly. */ -static int qib_msi_setup(struct qib_devdata *dd, int pos) +static void qib_msi_setup(struct qib_devdata *dd, int pos) { struct pci_dev *pdev = dd->pcidev; u16 control; - int ret; - ret = pci_enable_msi(pdev); - if (ret) - qib_dev_err(dd, - "pci_enable_msi failed: %d, interrupts may not work\n", - ret); - /* continue even if it fails, we may still be OK... */ - - pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_LO, - &dd->msi_lo); - pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_HI, - &dd->msi_hi); + pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_LO, &dd->msi_lo); + pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_HI, &dd->msi_hi); pci_read_config_word(pdev, pos + PCI_MSI_FLAGS, &control); + /* now save the data (vector) info */ - pci_read_config_word(pdev, pos + ((control & PCI_MSI_FLAGS_64BIT) - ? 12 : 8), + pci_read_config_word(pdev, + pos + ((control & PCI_MSI_FLAGS_64BIT) ? 12 : 8), &dd->msi_data); - return ret; } -int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent, - struct qib_msix_entry *entry) +static int qib_allocate_irqs(struct qib_devdata *dd, u32 maxvec) +{ + unsigned int flags = PCI_IRQ_LEGACY; + + /* Check our capabilities */ + if (dd->pcidev->msix_cap) { + flags |= PCI_IRQ_MSIX; + } else { + if (dd->pcidev->msi_cap) { + flags |= PCI_IRQ_MSI; + /* Get msi_lo and msi_hi */ + qib_msi_setup(dd, dd->pcidev->msi_cap); + } + } + + if (!(flags & (PCI_IRQ_MSIX | PCI_IRQ_MSI))) + qib_dev_err(dd, "No PCI MSI or MSIx capability!\n"); + + return pci_alloc_irq_vectors(dd->pcidev, 1, maxvec, flags); +} + +int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent) { u16 linkstat, speed; - int pos = 0, ret = 1; + int nvec; + int maxvec; + int ret = 0; if (!pci_is_pcie(dd->pcidev)) { qib_dev_err(dd, "Can't find PCI Express capability!\n"); /* set up something... */ dd->lbus_width = 1; dd->lbus_speed = 2500; /* Gen1, 2.5GHz */ + ret = -1; goto bail; } - pos = dd->pcidev->msix_cap; - if (nent && *nent && pos) { - qib_msix_setup(dd, pos, nent, entry); - ret = 0; /* did it, either MSIx or INTx */ - } else { - pos = dd->pcidev->msi_cap; - if (pos) - ret = qib_msi_setup(dd, pos); - else - qib_dev_err(dd, "No PCI MSI or MSIx capability!\n"); + maxvec = (nent && *nent) ? *nent : 1; + nvec = qib_allocate_irqs(dd, maxvec); + if (nvec < 0) { + ret = nvec; + goto bail; + } + + /* + * If nent exists, make sure to record how many vectors were allocated + */ + if (nent) { + *nent = nvec; + + /* + * If we requested (nent) MSIX, but msix_enabled is not set, + * pci_alloc_irq_vectors() enabled INTx. + */ + if (!dd->pcidev->msix_enabled) + qib_dev_err(dd, + "no msix vectors allocated, using INTx\n"); } - if (!pos) - qib_enable_intx(dd->pcidev); pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat); /* @@ -379,7 +352,7 @@ int qib_reinit_intr(struct qib_devdata *dd) ret = 1; bail: if (!ret && (dd->flags & QIB_HAS_INTX)) { - qib_enable_intx(dd->pcidev); + qib_enable_intx(dd); ret = 1; } @@ -397,7 +370,7 @@ bail: void qib_nomsi(struct qib_devdata *dd) { dd->msi_lo = 0; - pci_disable_msi(dd->pcidev); + pci_free_irq_vectors(dd->pcidev); } /* @@ -405,23 +378,21 @@ void qib_nomsi(struct qib_devdata *dd) */ void qib_nomsix(struct qib_devdata *dd) { - pci_disable_msix(dd->pcidev); + pci_free_irq_vectors(dd->pcidev); } /* * Similar to pci_intx(pdev, 1), except that we make sure * msi(x) is off. */ -void qib_enable_intx(struct pci_dev *pdev) +void qib_enable_intx(struct qib_devdata *dd) { u16 cw, new; int pos; + struct pci_dev *pdev = dd->pcidev; - /* first, turn on INTx */ - pci_read_config_word(pdev, PCI_COMMAND, &cw); - new = cw & ~PCI_COMMAND_INTX_DISABLE; - if (new != cw) - pci_write_config_word(pdev, PCI_COMMAND, new); + if (pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY) < 0) + qib_dev_err(dd, "Failed to enable INTx\n"); pos = pdev->msi_cap; if (pos) { diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c index bd09de7c6e56..e6a42a8972f5 100644 --- a/drivers/infiniband/hw/qib/qib_ruc.c +++ b/drivers/infiniband/hw/qib/qib_ruc.c @@ -58,8 +58,10 @@ static int qib_init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe) if (wqe->sg_list[i].length == 0) continue; /* Check LKEY */ - if (!rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge, - &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE)) + ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge, + NULL, &wqe->sg_list[i], + IB_ACCESS_LOCAL_WRITE); + if (unlikely(ret <= 0)) goto bad_lkey; qp->r_len += wqe->sg_list[i].length; j++; @@ -256,11 +258,11 @@ int qib_ruc_check_hdr(struct qib_ibport *ibp, struct ib_header *hdr, } if (!qib_pkey_ok((u16)bth0, qib_get_pkey(ibp, qp->s_alt_pkey_index))) { - qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY, - (u16)bth0, - (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF, - 0, qp->ibqp.qp_num, - hdr->lrh[3], hdr->lrh[1]); + qib_bad_pkey(ibp, + (u16)bth0, + (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF, + 0, qp->ibqp.qp_num, + hdr->lrh[3], hdr->lrh[1]); goto err; } /* Validate the SLID. See Ch. 9.6.1.5 and 17.2.8 */ @@ -295,11 +297,11 @@ int qib_ruc_check_hdr(struct qib_ibport *ibp, struct ib_header *hdr, } if (!qib_pkey_ok((u16)bth0, qib_get_pkey(ibp, qp->s_pkey_index))) { - qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY, - (u16)bth0, - (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF, - 0, qp->ibqp.qp_num, - hdr->lrh[3], hdr->lrh[1]); + qib_bad_pkey(ibp, + (u16)bth0, + (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF, + 0, qp->ibqp.qp_num, + hdr->lrh[3], hdr->lrh[1]); goto err; } /* Validate the SLID. See Ch. 9.6.1.5 */ diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index fe4cf5e4acec..ca2638d8f35e 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -247,7 +247,7 @@ static struct kobj_type qib_port_cc_ktype = { .release = qib_port_release, }; -static struct bin_attribute cc_table_bin_attr = { +static const struct bin_attribute cc_table_bin_attr = { .attr = {.name = "cc_table_bin", .mode = 0444}, .read = read_cc_table_bin, .size = PAGE_SIZE, @@ -286,7 +286,7 @@ static ssize_t read_cc_setting_bin(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute cc_setting_bin_attr = { +static const struct bin_attribute cc_setting_bin_attr = { .attr = {.name = "cc_settings_bin", .mode = 0444}, .read = read_cc_setting_bin, .size = PAGE_SIZE, diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index 341a123ee95c..be4907453ac4 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -66,8 +66,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe) qp = rvt_lookup_qpn(rdi, &ibp->rvp, swqe->ud_wr.remote_qpn); if (!qp) { ibp->rvp.n_pkt_drops++; - rcu_read_unlock(); - return; + goto drop; } sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ? @@ -94,11 +93,11 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe) if (unlikely(!qib_pkey_ok(pkey1, pkey2))) { lid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) & ((1 << ppd->lmc) - 1)); - qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY, pkey1, - rdma_ah_get_sl(ah_attr), - sqp->ibqp.qp_num, qp->ibqp.qp_num, - cpu_to_be16(lid), - cpu_to_be16(rdma_ah_get_dlid(ah_attr))); + qib_bad_pkey(ibp, pkey1, + rdma_ah_get_sl(ah_attr), + sqp->ibqp.qp_num, qp->ibqp.qp_num, + cpu_to_be16(lid), + cpu_to_be16(rdma_ah_get_dlid(ah_attr))); goto drop; } } @@ -113,18 +112,8 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe) qkey = (int)swqe->ud_wr.remote_qkey < 0 ? sqp->qkey : swqe->ud_wr.remote_qkey; - if (unlikely(qkey != qp->qkey)) { - u16 lid; - - lid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) & - ((1 << ppd->lmc) - 1)); - qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_QKEY, qkey, - rdma_ah_get_sl(ah_attr), - sqp->ibqp.qp_num, qp->ibqp.qp_num, - cpu_to_be16(lid), - cpu_to_be16(rdma_ah_get_dlid(ah_attr))); + if (unlikely(qkey != qp->qkey)) goto drop; - } } /* @@ -487,22 +476,18 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr, pkey1 = be32_to_cpu(ohdr->bth[0]); pkey2 = qib_get_pkey(ibp, qp->s_pkey_index); if (unlikely(!qib_pkey_ok(pkey1, pkey2))) { - qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY, - pkey1, - (be16_to_cpu(hdr->lrh[0]) >> 4) & + qib_bad_pkey(ibp, + pkey1, + (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF, - src_qp, qp->ibqp.qp_num, - hdr->lrh[3], hdr->lrh[1]); + src_qp, qp->ibqp.qp_num, + hdr->lrh[3], hdr->lrh[1]); return; } } - if (unlikely(qkey != qp->qkey)) { - qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_QKEY, qkey, - (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF, - src_qp, qp->ibqp.qp_num, - hdr->lrh[3], hdr->lrh[1]); + if (unlikely(qkey != qp->qkey)) return; - } + /* Drop invalid MAD packets (see 13.5.3.1). */ if (unlikely(qp->ibqp.qp_num == 1 && (tlen != 256 || diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h index a52fc67b40d7..95e370192948 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.h +++ b/drivers/infiniband/hw/qib/qib_verbs.h @@ -241,8 +241,8 @@ static inline int qib_pkey_ok(u16 pkey1, u16 pkey2) return p1 && p1 == p2 && ((__s16)pkey1 < 0 || (__s16)pkey2 < 0); } -void qib_bad_pqkey(struct qib_ibport *ibp, __be16 trap_num, u32 key, u32 sl, - u32 qp1, u32 qp2, __be16 lid1, __be16 lid2); +void qib_bad_pkey(struct qib_ibport *ibp, u32 key, u32 sl, + u32 qp1, u32 qp2, __be16 lid1, __be16 lid2); void qib_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num); void qib_sys_guid_chg(struct qib_ibport *ibp); void qib_node_desc_chg(struct qib_ibport *ibp); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c0c1e8b027b1..e86700f994cb 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -333,9 +333,7 @@ static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } -static void usnic_get_dev_fw_str(struct ib_device *device, - char *str, - size_t str_len) +static void usnic_get_dev_fw_str(struct ib_device *device, char *str) { struct usnic_ib_dev *us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev); @@ -345,7 +343,7 @@ static void usnic_get_dev_fw_str(struct ib_device *device, us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info); mutex_unlock(&us_ibdev->usdev_lock); - snprintf(str, str_len, "%s", info.fw_version); + snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version); } /* Start of PF discovery section */ @@ -409,6 +407,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev) us_ibdev->ib_dev.query_port = usnic_ib_query_port; us_ibdev->ib_dev.query_pkey = usnic_ib_query_pkey; us_ibdev->ib_dev.query_gid = usnic_ib_query_gid; + us_ibdev->ib_dev.get_netdev = usnic_get_netdev; us_ibdev->ib_dev.get_link_layer = usnic_ib_port_link_layer; us_ibdev->ib_dev.alloc_pd = usnic_ib_alloc_pd; us_ibdev->ib_dev.dealloc_pd = usnic_ib_dealloc_pd; @@ -720,7 +719,6 @@ static void __exit usnic_ib_destroy(void) MODULE_DESCRIPTION("Cisco VIC (usNIC) Verbs Driver"); MODULE_AUTHOR("Upinder Malhi <umalhi@cisco.com>"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); module_param(usnic_log_lvl, uint, S_IRUGO | S_IWUSR); module_param(usnic_ib_share_vf, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(usnic_log_lvl, " Off=0, Err=1, Info=2, Debug=3"); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 4996984885c2..e5f57dd49980 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -226,27 +226,6 @@ static void qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp) spin_unlock(&vf->lock); } -static void eth_speed_to_ib_speed(int speed, u8 *active_speed, - u8 *active_width) -{ - if (speed <= 10000) { - *active_width = IB_WIDTH_1X; - *active_speed = IB_SPEED_FDR10; - } else if (speed <= 20000) { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_DDR; - } else if (speed <= 30000) { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_QDR; - } else if (speed <= 40000) { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_FDR10; - } else { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_EDR; - } -} - static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd) { if (cmd.spec.trans_type <= USNIC_TRANSPORT_UNKNOWN || @@ -326,12 +305,16 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *props) { struct usnic_ib_dev *us_ibdev = to_usdev(ibdev); - struct ethtool_link_ksettings cmd; usnic_dbg("\n"); mutex_lock(&us_ibdev->usdev_lock); - __ethtool_get_link_ksettings(us_ibdev->netdev, &cmd); + if (!ib_get_eth_speed(ibdev, port, &props->active_speed, + &props->active_width)) { + mutex_unlock(&us_ibdev->usdev_lock); + return -EINVAL; + } + /* props being zeroed by the caller, avoid zeroing it here */ props->lid = 0; @@ -355,8 +338,6 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port, props->pkey_tbl_len = 1; props->bad_pkey_cntr = 0; props->qkey_viol_cntr = 0; - eth_speed_to_ib_speed(cmd.base.speed, &props->active_speed, - &props->active_width); props->max_mtu = IB_MTU_4096; props->active_mtu = iboe_get_mtu(us_ibdev->ufdev->mtu); /* Userspace will adjust for hdrs */ @@ -424,6 +405,16 @@ int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index, return 0; } +struct net_device *usnic_get_netdev(struct ib_device *device, u8 port_num) +{ + struct usnic_ib_dev *us_ibdev = to_usdev(device); + + if (us_ibdev->netdev) + dev_hold(us_ibdev->netdev); + + return us_ibdev->netdev; +} + int usnic_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey) { diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h index 172e43b6fa95..1fda94425116 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h @@ -48,6 +48,7 @@ int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, struct ib_qp_init_attr *qp_init_attr); int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index, union ib_gid *gid); +struct net_device *usnic_get_netdev(struct ib_device *device, u8 port_num); int usnic_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey); struct ib_pd *usnic_ib_alloc_pd(struct ib_device *ibdev, diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index 34ebc7615411..5b00156dff30 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -102,12 +102,11 @@ static struct device_attribute *pvrdma_class_attributes[] = { &dev_attr_board_id }; -static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str, - size_t str_len) +static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str) { struct pvrdma_dev *dev = container_of(device, struct pvrdma_dev, ib_dev); - snprintf(str, str_len, "%d.%d.%d\n", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d\n", (int) (dev->dsr->caps.fw_ver >> 32), (int) (dev->dsr->caps.fw_ver >> 16) & 0xffff, (int) dev->dsr->caps.fw_ver & 0xffff); @@ -1078,7 +1077,7 @@ static void pvrdma_pci_remove(struct pci_dev *pdev) pci_set_drvdata(pdev, NULL); } -static struct pci_device_id pvrdma_pci_table[] = { +static const struct pci_device_id pvrdma_pci_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_VMWARE, PCI_DEVICE_ID_VMWARE_PVRDMA), }, { 0 }, }; @@ -1119,5 +1118,4 @@ module_exit(pvrdma_cleanup); MODULE_AUTHOR("VMware, Inc"); MODULE_DESCRIPTION("VMware Paravirtual RDMA driver"); -MODULE_VERSION(DRV_VERSION); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c index 0ae2ff8cf81e..0335a3df74d5 100644 --- a/drivers/infiniband/sw/rdmavt/cq.c +++ b/drivers/infiniband/sw/rdmavt/cq.c @@ -107,7 +107,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited) wc->uqueue[head].src_qp = entry->src_qp; wc->uqueue[head].wc_flags = entry->wc_flags; wc->uqueue[head].pkey_index = entry->pkey_index; - wc->uqueue[head].slid = entry->slid; + wc->uqueue[head].slid = ib_slid_cpu16(entry->slid); wc->uqueue[head].sl = entry->sl; wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits; wc->uqueue[head].port_num = entry->port_num; diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index aa5f9ea318e4..1b3801f78e78 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -778,23 +778,52 @@ out: } /** + * rvt_sge_adjacent - is isge compressible + * @last_sge: last outgoing SGE written + * @sge: SGE to check + * + * If adjacent will update last_sge to add length. + * + * Return: true if isge is adjacent to last sge + */ +static inline bool rvt_sge_adjacent(struct rvt_sge *last_sge, + struct ib_sge *sge) +{ + if (last_sge && sge->lkey == last_sge->mr->lkey && + ((uint64_t)(last_sge->vaddr + last_sge->length) == sge->addr)) { + if (sge->lkey) { + if (unlikely((sge->addr - last_sge->mr->user_base + + sge->length > last_sge->mr->length))) + return false; /* overrun, caller will catch */ + } else { + last_sge->length += sge->length; + } + last_sge->sge_length += sge->length; + trace_rvt_sge_adjacent(last_sge, sge); + return true; + } + return false; +} + +/** * rvt_lkey_ok - check IB SGE for validity and initialize * @rkt: table containing lkey to check SGE against * @pd: protection domain * @isge: outgoing internal SGE + * @last_sge: last outgoing SGE written * @sge: SGE to check * @acc: access flags * * Check the IB SGE for validity and initialize our internal version * of it. * - * Return: 1 if valid and successful, otherwise returns 0. - * - * increments the reference count upon success + * Increments the reference count when a new sge is stored. * + * Return: 0 if compressed, 1 if added , otherwise returns -errno. */ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, - struct rvt_sge *isge, struct ib_sge *sge, int acc) + struct rvt_sge *isge, struct rvt_sge *last_sge, + struct ib_sge *sge, int acc) { struct rvt_mregion *mr; unsigned n, m; @@ -804,12 +833,14 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, * We use LKEY == zero for kernel virtual addresses * (see rvt_get_dma_mr() and dma_virt_ops). */ - rcu_read_lock(); if (sge->lkey == 0) { struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device); if (pd->user) - goto bail; + return -EINVAL; + if (rvt_sge_adjacent(last_sge, sge)) + return 0; + rcu_read_lock(); mr = rcu_dereference(dev->dma_mr); if (!mr) goto bail; @@ -824,6 +855,9 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, isge->n = 0; goto ok; } + if (rvt_sge_adjacent(last_sge, sge)) + return 0; + rcu_read_lock(); mr = rcu_dereference(rkt->table[sge->lkey >> rkt->shift]); if (!mr) goto bail; @@ -874,12 +908,13 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, isge->m = m; isge->n = n; ok: + trace_rvt_sge_new(isge, sge); return 1; bail_unref: rvt_put_mr(mr); bail: rcu_read_unlock(); - return 0; + return -EINVAL; } EXPORT_SYMBOL(rvt_lkey_ok); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 8876ee7bc326..1878a97364aa 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -421,15 +421,6 @@ bail: return ret; } -static void free_qpn(struct rvt_qpn_table *qpt, u32 qpn) -{ - struct rvt_qpn_map *map; - - map = qpt->map + qpn / RVT_BITS_PER_PAGE; - if (map->page) - clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page); -} - /** * rvt_clear_mr_refs - Drop help mr refs * @qp: rvt qp data structure @@ -645,6 +636,19 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, lockdep_assert_held(&qp->s_lock); } +/** rvt_free_qpn - Free a qpn from the bit map + * @qpt: QP table + * @qpn: queue pair number to free + */ +static void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn) +{ + struct rvt_qpn_map *map; + + map = qpt->map + (qpn & RVT_QPN_MASK) / RVT_BITS_PER_PAGE; + if (map->page) + clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page); +} + /** * rvt_create_qp - create a queue pair for a device * @ibpd: the protection domain who's device we create the queue pair for @@ -914,7 +918,7 @@ bail_ip: kref_put(&qp->ip->ref, rvt_release_mmap_info); bail_qpn: - free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); + rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: if (!qp->ip) @@ -1301,19 +1305,6 @@ inval: return -EINVAL; } -/** rvt_free_qpn - Free a qpn from the bit map - * @qpt: QP table - * @qpn: queue pair number to free - */ -static void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn) -{ - struct rvt_qpn_map *map; - - map = qpt->map + qpn / RVT_BITS_PER_PAGE; - if (map->page) - clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page); -} - /** * rvt_destroy_qp - destroy a queue pair * @ibqp: the queue pair to destroy @@ -1695,22 +1686,23 @@ static int rvt_post_one_wr(struct rvt_qp *qp, wqe->length = 0; j = 0; if (wr->num_sge) { + struct rvt_sge *last_sge = NULL; + acc = wr->opcode >= IB_WR_RDMA_READ ? IB_ACCESS_LOCAL_WRITE : 0; for (i = 0; i < wr->num_sge; i++) { u32 length = wr->sg_list[i].length; - int ok; if (length == 0) continue; - ok = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j], - &wr->sg_list[i], acc); - if (!ok) { - ret = -EINVAL; + ret = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j], last_sge, + &wr->sg_list[i], acc); + if (unlikely(ret < 0)) goto bail_inval_free; - } wqe->length += length; - j++; + if (ret) + last_sge = &wqe->sg_list[j]; + j += ret; } wqe->wr.num_sge = j; } @@ -1757,7 +1749,7 @@ static int rvt_post_one_wr(struct rvt_qp *qp, wqe->wr.send_flags &= ~RVT_SEND_RESERVE_USED; qp->s_avail--; } - trace_rvt_post_one_wr(qp, wqe); + trace_rvt_post_one_wr(qp, wqe, wr->num_sge); smp_wmb(); /* see request builders */ qp->s_head = next; diff --git a/drivers/infiniband/sw/rdmavt/trace_mr.h b/drivers/infiniband/sw/rdmavt/trace_mr.h index 3318a6c36373..976e482930a3 100644 --- a/drivers/infiniband/sw/rdmavt/trace_mr.h +++ b/drivers/infiniband/sw/rdmavt/trace_mr.h @@ -103,6 +103,68 @@ DEFINE_EVENT( TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len), TP_ARGS(mr, m, n, v, len)); +DECLARE_EVENT_CLASS( + rvt_sge_template, + TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge), + TP_ARGS(sge, isge), + TP_STRUCT__entry( + RDI_DEV_ENTRY(ib_to_rvt(sge->mr->pd->device)) + __field(struct rvt_mregion *, mr) + __field(struct rvt_sge *, sge) + __field(struct ib_sge *, isge) + __field(void *, vaddr) + __field(u64, ivaddr) + __field(u32, lkey) + __field(u32, sge_length) + __field(u32, length) + __field(u32, ilength) + __field(int, user) + __field(u16, m) + __field(u16, n) + ), + TP_fast_assign( + RDI_DEV_ASSIGN(ib_to_rvt(sge->mr->pd->device)); + __entry->mr = sge->mr; + __entry->sge = sge; + __entry->isge = isge; + __entry->vaddr = sge->vaddr; + __entry->ivaddr = isge->addr; + __entry->lkey = sge->mr->lkey; + __entry->sge_length = sge->sge_length; + __entry->length = sge->length; + __entry->ilength = isge->length; + __entry->m = sge->m; + __entry->n = sge->m; + __entry->user = ibpd_to_rvtpd(sge->mr->pd)->user; + ), + TP_printk( + "[%s] mr %p sge %p isge %p vaddr %p ivaddr %llx lkey %x sge_length %u length %u ilength %u m %u n %u user %u", + __get_str(dev), + __entry->mr, + __entry->sge, + __entry->isge, + __entry->vaddr, + __entry->ivaddr, + __entry->lkey, + __entry->sge_length, + __entry->length, + __entry->ilength, + __entry->m, + __entry->n, + __entry->user + ) +); + +DEFINE_EVENT( + rvt_sge_template, rvt_sge_adjacent, + TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge), + TP_ARGS(sge, isge)); + +DEFINE_EVENT( + rvt_sge_template, rvt_sge_new, + TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge), + TP_ARGS(sge, isge)); + #endif /* __RVT_TRACE_MR_H */ #undef TRACE_INCLUDE_PATH diff --git a/drivers/infiniband/sw/rdmavt/trace_tx.h b/drivers/infiniband/sw/rdmavt/trace_tx.h index a613a2223751..0ef25fc49f25 100644 --- a/drivers/infiniband/sw/rdmavt/trace_tx.h +++ b/drivers/infiniband/sw/rdmavt/trace_tx.h @@ -84,12 +84,12 @@ __print_symbolic(opcode, \ wr_opcode_name(RESERVED10)) #define POS_PRN \ -"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u" +"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u wr_num_sge %u" TRACE_EVENT( rvt_post_one_wr, - TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe), - TP_ARGS(qp, wqe), + TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe, int wr_num_sge), + TP_ARGS(qp, wqe, wr_num_sge), TP_STRUCT__entry( RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device)) __field(u64, wr_id) @@ -108,6 +108,7 @@ TRACE_EVENT( __field(int, send_flags) __field(pid_t, pid) __field(int, num_sge) + __field(int, wr_num_sge) ), TP_fast_assign( RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device)) @@ -127,6 +128,7 @@ TRACE_EVENT( __entry->ssn = wqe->ssn; __entry->send_flags = wqe->wr.send_flags; __entry->num_sge = wqe->wr.num_sge; + __entry->wr_num_sge = wr_num_sge; ), TP_printk( POS_PRN, @@ -146,7 +148,8 @@ TRACE_EVENT( __entry->head, __entry->last, __entry->pid, - __entry->num_sge + __entry->num_sge, + __entry->wr_num_sge ) ); diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 0d7c6bb551d9..64bdd442078a 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -202,8 +202,13 @@ static int rvt_modify_port(struct ib_device *ibdev, u8 port_num, return -EINVAL; rvp = rdi->ports[port_index]; - rvp->port_cap_flags |= props->set_port_cap_mask; - rvp->port_cap_flags &= ~props->clr_port_cap_mask; + if (port_modify_mask & IB_PORT_OPA_MASK_CHG) { + rvp->port_cap3_flags |= props->set_port_cap_mask; + rvp->port_cap3_flags &= ~props->clr_port_cap_mask; + } else { + rvp->port_cap_flags |= props->set_port_cap_mask; + rvp->port_cap_flags &= ~props->clr_port_cap_mask; + } if (props->set_port_cap_mask || props->clr_port_cap_mask) rdi->driver_f.cap_mask_chg(rdi, port_num); diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index c21c913f911a..8c3d30b3092d 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -38,7 +38,6 @@ MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib"); MODULE_DESCRIPTION("Soft RDMA transport"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION("0.2"); /* free resources for all ports on a device */ static void rxe_cleanup_ports(struct rxe_dev *rxe) diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index 1ac5b8551a4d..6447d736d5a4 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -97,7 +97,7 @@ int rxe_rcv(struct sk_buff *skb); void rxe_dev_put(struct rxe_dev *rxe); struct rxe_dev *net_to_rxe(struct net_device *ndev); -struct rxe_dev *get_rxe_by_name(const char* name); +struct rxe_dev *get_rxe_by_name(const char *name); void rxe_port_up(struct rxe_dev *rxe); void rxe_port_down(struct rxe_dev *rxe); diff --git a/drivers/infiniband/sw/rxe/rxe_av.c b/drivers/infiniband/sw/rxe/rxe_av.c index 5bddf469361b..1cc9e2e1365d 100644 --- a/drivers/infiniband/sw/rxe/rxe_av.c +++ b/drivers/infiniband/sw/rxe/rxe_av.c @@ -38,18 +38,13 @@ int rxe_av_chk_attr(struct rxe_dev *rxe, struct rdma_ah_attr *attr) { struct rxe_port *port; - if (rdma_ah_get_port_num(attr) != 1) { - pr_info("invalid port_num = %d\n", rdma_ah_get_port_num(attr)); - return -EINVAL; - } - port = &rxe->port; if (rdma_ah_get_ah_flags(attr) & IB_AH_GRH) { u8 sgid_index = rdma_ah_read_grh(attr)->sgid_index; if (sgid_index > port->attr.gid_tbl_len) { - pr_info("invalid sgid index = %d\n", sgid_index); + pr_warn("invalid sgid index = %d\n", sgid_index); return -EINVAL; } } diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index d6299edf9a5b..6b65c0132289 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -250,7 +250,7 @@ void rxe_resp_queue_pkt(struct rxe_dev *rxe, void rxe_comp_queue_pkt(struct rxe_dev *rxe, struct rxe_qp *qp, struct sk_buff *skb); -static inline unsigned wr_opcode_mask(int opcode, struct rxe_qp *qp) +static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp) { return rxe_wr_opcode_info[opcode].mask[qp->ibqp.qp_type]; } diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c index bd812e00988e..d22431e3a908 100644 --- a/drivers/infiniband/sw/rxe/rxe_mmap.c +++ b/drivers/infiniband/sw/rxe/rxe_mmap.c @@ -76,7 +76,7 @@ static void rxe_vma_close(struct vm_area_struct *vma) kref_put(&ip->ref, rxe_mmap_release); } -static struct vm_operations_struct rxe_vm_ops = { +static const struct vm_operations_struct rxe_vm_ops = { .open = rxe_vma_open, .close = rxe_vma_close, }; diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c index 75d11ee635ec..c1b5f38f31a5 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.c +++ b/drivers/infiniband/sw/rxe/rxe_pool.c @@ -188,7 +188,7 @@ int rxe_pool_init( struct rxe_dev *rxe, struct rxe_pool *pool, enum rxe_elem_type type, - unsigned max_elem) + unsigned int max_elem) { int err = 0; size_t size = rxe_type_info[type].size; diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 7ee465d1a1e1..db7161456f45 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -43,7 +43,7 @@ static int next_opcode(struct rxe_qp *qp, struct rxe_send_wqe *wqe, static inline void retry_first_write_send(struct rxe_qp *qp, struct rxe_send_wqe *wqe, - unsigned mask, int npsn) + unsigned int mask, int npsn) { int i; diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index d2a14a1bdc7f..ea3810b29273 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -78,7 +78,7 @@ void rxe_do_task(unsigned long data) default: spin_unlock_irqrestore(&task->state_lock, flags); - pr_warn("bad state = %d in rxe_do_task\n", task->state); + pr_warn("%s failed with bad state %d\n", __func__, task->state); return; } @@ -105,7 +105,7 @@ void rxe_do_task(unsigned long data) break; default: - pr_warn("bad state = %d in rxe_do_task\n", + pr_warn("%s failed with bad state %d\n", __func__, task->state); } spin_unlock_irqrestore(&task->state_lock, flags); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index af90a7d42b96..e611d0c7314a 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -51,40 +51,16 @@ static int rxe_query_device(struct ib_device *dev, return 0; } -static void rxe_eth_speed_to_ib_speed(int speed, u8 *active_speed, - u8 *active_width) -{ - if (speed <= 1000) { - *active_width = IB_WIDTH_1X; - *active_speed = IB_SPEED_SDR; - } else if (speed <= 10000) { - *active_width = IB_WIDTH_1X; - *active_speed = IB_SPEED_FDR10; - } else if (speed <= 20000) { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_DDR; - } else if (speed <= 30000) { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_QDR; - } else if (speed <= 40000) { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_FDR10; - } else { - *active_width = IB_WIDTH_4X; - *active_speed = IB_SPEED_EDR; - } -} - static int rxe_query_port(struct ib_device *dev, u8 port_num, struct ib_port_attr *attr) { struct rxe_dev *rxe = to_rdev(dev); struct rxe_port *port; - u32 speed; + int rc = -EINVAL; if (unlikely(port_num != 1)) { pr_warn("invalid port_number %d\n", port_num); - goto err1; + goto out; } port = &rxe->port; @@ -93,29 +69,12 @@ static int rxe_query_port(struct ib_device *dev, *attr = port->attr; mutex_lock(&rxe->usdev_lock); - if (rxe->ndev->ethtool_ops->get_link_ksettings) { - struct ethtool_link_ksettings ks; - - rxe->ndev->ethtool_ops->get_link_ksettings(rxe->ndev, &ks); - speed = ks.base.speed; - } else if (rxe->ndev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd; - - rxe->ndev->ethtool_ops->get_settings(rxe->ndev, &cmd); - speed = cmd.speed; - } else { - pr_warn("%s speed is unknown, defaulting to 1000\n", - rxe->ndev->name); - speed = 1000; - } - rxe_eth_speed_to_ib_speed(speed, &attr->active_speed, - &attr->active_width); + rc = ib_get_eth_speed(dev, port_num, &attr->active_speed, + &attr->active_width); mutex_unlock(&rxe->usdev_lock); - return 0; - -err1: - return -EINVAL; +out: + return rc; } static int rxe_query_gid(struct ib_device *device, @@ -1210,8 +1169,8 @@ static int rxe_detach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid) return rxe_mcast_drop_grp_elem(rxe, qp, mgid); } -static ssize_t rxe_show_parent(struct device *device, - struct device_attribute *attr, char *buf) +static ssize_t parent_show(struct device *device, + struct device_attribute *attr, char *buf) { struct rxe_dev *rxe = container_of(device, struct rxe_dev, ib_dev.dev); @@ -1219,7 +1178,7 @@ static ssize_t rxe_show_parent(struct device *device, return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1)); } -static DEVICE_ATTR(parent, S_IRUGO, rxe_show_parent, NULL); +static DEVICE_ATTR_RO(parent); static struct device_attribute *rxe_dev_attributes[] = { &dev_attr_parent, @@ -1336,15 +1295,15 @@ int rxe_register_device(struct rxe_dev *rxe) err = ib_register_device(dev, NULL); if (err) { - pr_warn("rxe_register_device failed, err = %d\n", err); + pr_warn("%s failed with error %d\n", __func__, err); goto err1; } for (i = 0; i < ARRAY_SIZE(rxe_dev_attributes); ++i) { err = device_create_file(&dev->dev, rxe_dev_attributes[i]); if (err) { - pr_warn("device_create_file failed, i = %d, err = %d\n", - i, err); + pr_warn("%s failed with error %d for attr number %d\n", + __func__, err, i); goto err2; } } diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 7ac25059c40f..16c1af1c706e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -367,7 +367,7 @@ struct ipoib_dev_priv { u32 qkey; union ib_gid local_gid; - u16 local_lid; + u32 local_lid; unsigned int admin_mtu; unsigned int mcast_mtu; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c index 184a22f48027..8dc1e6225cc8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c @@ -63,8 +63,7 @@ static void ipoib_get_drvinfo(struct net_device *netdev, { struct ipoib_dev_priv *priv = ipoib_priv(netdev); - ib_get_device_fw_str(priv->ca, drvinfo->fw_version, - sizeof(drvinfo->fw_version)); + ib_get_device_fw_str(priv->ca, drvinfo->fw_version); strlcpy(drvinfo->bus_info, dev_name(priv->ca->dev.parent), sizeof(drvinfo->bus_info)); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 6c77df34869d..ee9f5d281b37 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -60,7 +60,6 @@ const char ipoib_driver_version[] = DRV_VERSION; MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 37b33d708c2d..19624e023ebd 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -77,7 +77,6 @@ MODULE_DESCRIPTION("iSER (iSCSI Extensions for RDMA) Datamover"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Alex Nezhinsky, Dan Bar Dov, Or Gerlitz"); -MODULE_VERSION(DRV_VER); static struct scsi_host_template iscsi_iser_sht; static struct iscsi_transport iscsi_iser_transport; diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 0e662656ef42..ceabdb85df8b 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2710,7 +2710,6 @@ static void __exit isert_exit(void) } MODULE_DESCRIPTION("iSER-Target for mainline target infrastructure"); -MODULE_VERSION("1.0"); MODULE_AUTHOR("nab@Linux-iSCSI.org"); MODULE_LICENSE("GPL"); diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c index cf768dd78d1b..57b862b94dca 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c @@ -52,7 +52,9 @@ #include <linux/module.h> #include <rdma/ib_addr.h> -#include <rdma/ib_smi.h> +#include <rdma/ib_verbs.h> +#include <rdma/opa_smi.h> +#include <rdma/opa_port_info.h> #include "opa_vnic_internal.h" @@ -980,6 +982,27 @@ static int vema_register(struct opa_vnic_ctrl_port *cport) } /** + * opa_vnic_ctrl_config_dev -- This function sends a trap to the EM + * by way of ib_modify_port to indicate support for ethernet on the + * fabric. + * @cport: pointer to control port + * @en: enable or disable ethernet on fabric support + */ +static void opa_vnic_ctrl_config_dev(struct opa_vnic_ctrl_port *cport, bool en) +{ + struct ib_port_modify pm = { 0 }; + int i; + + if (en) + pm.set_port_cap_mask = OPA_CAP_MASK3_IsEthOnFabricSupported; + else + pm.clr_port_cap_mask = OPA_CAP_MASK3_IsEthOnFabricSupported; + + for (i = 1; i <= cport->num_ports; i++) + ib_modify_port(cport->ibdev, i, IB_PORT_OPA_MASK_CHG, &pm); +} + +/** * opa_vnic_vema_add_one -- Handle new ib device * @device: ib device pointer * @@ -1007,6 +1030,7 @@ static void opa_vnic_vema_add_one(struct ib_device *device) c_info("VNIC client initialized\n"); ib_set_client_data(device, &opa_vnic_client, cport); + opa_vnic_ctrl_config_dev(cport, true); } /** @@ -1025,6 +1049,7 @@ static void opa_vnic_vema_rem_one(struct ib_device *device, return; c_info("removing VNIC client\n"); + opa_vnic_ctrl_config_dev(cport, false); vema_unregister(cport); kfree(cport); } @@ -1053,4 +1078,3 @@ module_exit(opa_vnic_deinit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Intel Corporation"); MODULE_DESCRIPTION("Intel OPA Virtual Network driver"); -MODULE_VERSION(DRV_VERSION); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 2354c742caa1..fa5ccdb3bb2a 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -62,7 +62,6 @@ MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRV_VERSION); MODULE_INFO(release_date, DRV_RELDATE); #if !defined(CONFIG_DYNAMIC_DEBUG) diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h index cc1183851af5..1b817e51b84b 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.h +++ b/drivers/infiniband/ulp/srpt/ib_srpt.h @@ -328,8 +328,8 @@ struct srpt_port { u8 port_guid[24]; u8 port_gid[64]; u8 port; - u16 sm_lid; - u16 lid; + u32 sm_lid; + u32 lid; union ib_gid gid; struct work_struct work; struct se_portal_group port_guid_tpg; diff --git a/drivers/irqchip/irq-digicolor.c b/drivers/irqchip/irq-digicolor.c index dad85e74c37c..3aae015469a5 100644 --- a/drivers/irqchip/irq-digicolor.c +++ b/drivers/irqchip/irq-digicolor.c @@ -71,7 +71,7 @@ static void __init digicolor_set_gc(void __iomem *reg_base, unsigned irq_base, static int __init digicolor_of_init(struct device_node *node, struct device_node *parent) { - static void __iomem *reg_base; + void __iomem *reg_base; unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; struct regmap *ucregs; int ret; diff --git a/drivers/irqchip/irq-gic-realview.c b/drivers/irqchip/irq-gic-realview.c index 54c296401525..18d58d2b4ffe 100644 --- a/drivers/irqchip/irq-gic-realview.c +++ b/drivers/irqchip/irq-gic-realview.c @@ -43,7 +43,7 @@ static const struct of_device_id syscon_pldset_of_match[] = { static int __init realview_gic_of_init(struct device_node *node, struct device_node *parent) { - static struct regmap *map; + struct regmap *map; struct device_node *np; const struct of_device_id *gic_id; u32 pld1_ctrl; diff --git a/drivers/irqchip/irq-mips-cpu.c b/drivers/irqchip/irq-mips-cpu.c index 0a8ed1c05518..14461cbfab2f 100644 --- a/drivers/irqchip/irq-mips-cpu.c +++ b/drivers/irqchip/irq-mips-cpu.c @@ -154,7 +154,7 @@ asmlinkage void __weak plat_irq_dispatch(void) static int mips_cpu_intc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { - static struct irq_chip *chip; + struct irq_chip *chip; if (hw < 2 && cpu_has_mipsmt) { /* Software interrupts are used for MT/CMT IPI */ diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 832ebf4062f7..6ab1d3afec02 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -950,7 +950,6 @@ static void __init __gic_init(unsigned long gic_base_addr, &gic_irq_domain_ops, NULL); if (!gic_irq_domain) panic("Failed to add GIC IRQ domain"); - gic_irq_domain->name = "mips-gic-irq"; gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain, IRQ_DOMAIN_FLAG_IPI_PER_CPU, @@ -959,7 +958,6 @@ static void __init __gic_init(unsigned long gic_base_addr, if (!gic_ipi_domain) panic("Failed to add GIC IPI domain"); - gic_ipi_domain->name = "mips-gic-ipi"; irq_domain_update_bus_token(gic_ipi_domain, DOMAIN_BUS_IPI); if (node && diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c index 060d357f107f..6f423bc49d0d 100644 --- a/drivers/isdn/divert/isdn_divert.c +++ b/drivers/isdn/divert/isdn_divert.c @@ -485,18 +485,19 @@ static int isdn_divert_icall(isdn_ctrl *ic) cs->deflect_dest[0] = '\0'; retval = 4; /* only proceed */ } - sprintf(cs->info, "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", - cs->akt_state, - cs->divert_id, - divert_if.drv_to_name(cs->ics.driver), - (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", - cs->ics.parm.setup.phone, - cs->ics.parm.setup.eazmsn, - cs->ics.parm.setup.si1, - cs->ics.parm.setup.si2, - cs->ics.parm.setup.screen, - dv->rule.waittime, - cs->deflect_dest); + snprintf(cs->info, sizeof(cs->info), + "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", + cs->akt_state, + cs->divert_id, + divert_if.drv_to_name(cs->ics.driver), + (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", + cs->ics.parm.setup.phone, + cs->ics.parm.setup.eazmsn, + cs->ics.parm.setup.si1, + cs->ics.parm.setup.si2, + cs->ics.parm.setup.screen, + dv->rule.waittime, + cs->deflect_dest); if ((dv->rule.action == DEFLECT_REPORT) || (dv->rule.action == DEFLECT_REJECT)) { put_info_buffer(cs->info); diff --git a/drivers/isdn/hardware/avm/c4.c b/drivers/isdn/hardware/avm/c4.c index 40c7e2cf423b..034cabac699d 100644 --- a/drivers/isdn/hardware/avm/c4.c +++ b/drivers/isdn/hardware/avm/c4.c @@ -42,7 +42,7 @@ static char *revision = "$Revision: 1.1.2.2 $"; static bool suppress_pollack; -static struct pci_device_id c4_pci_tbl[] = { +static const struct pci_device_id c4_pci_tbl[] = { { PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_C4, 0, 0, (unsigned long)4 }, { PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_C2, 0, 0, (unsigned long)2 }, { } /* Terminating entry */ diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c index 8b7ad4f1ab01..b2023e08dcd2 100644 --- a/drivers/isdn/hardware/eicon/divasmain.c +++ b/drivers/isdn/hardware/eicon/divasmain.c @@ -110,7 +110,7 @@ typedef struct _diva_os_thread_dpc { /* This table should be sorted by PCI device ID */ -static struct pci_device_id divas_pci_tbl[] = { +static const struct pci_device_id divas_pci_tbl[] = { /* Diva Server BRI-2M PCI 0xE010 */ { PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRA), CARDTYPE_MAESTRA_PCI }, diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c index e3fa1cd64470..dce6632daae1 100644 --- a/drivers/isdn/hardware/mISDN/avmfritz.c +++ b/drivers/isdn/hardware/mISDN/avmfritz.c @@ -1142,7 +1142,7 @@ fritz_remove_pci(struct pci_dev *pdev) pr_info("%s: drvdata already removed\n", __func__); } -static struct pci_device_id fcpci_ids[] = { +static const struct pci_device_id fcpci_ids[] = { { PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (unsigned long) "Fritz!Card PCI"}, { PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_A1_V2, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index aea0c9616ea5..3cf07b8ced1c 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -5348,7 +5348,7 @@ static const struct hm_map hfcm_map[] = { #undef H #define H(x) ((unsigned long)&hfcm_map[x]) -static struct pci_device_id hfmultipci_ids[] = { +static const struct pci_device_id hfmultipci_ids[] = { /* Cards with HFC-4S Chip */ { PCI_VENDOR_ID_CCD, PCI_DEVICE_ID_CCD_HFC4S, PCI_VENDOR_ID_CCD, diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index 5dc246d71c16..d2e401a8090e 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -2161,7 +2161,7 @@ static const struct _hfc_map hfc_map[] = {}, }; -static struct pci_device_id hfc_ids[] = +static const struct pci_device_id hfc_ids[] = { { PCI_VDEVICE(CCD, PCI_DEVICE_ID_CCD_2BD0), (unsigned long) &hfc_map[0] }, diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index afde4edef9ae..6a6d848bd18e 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1137,7 +1137,7 @@ static void nj_remove(struct pci_dev *pdev) /* We cannot select cards with PCI_SUB... IDs, since here are cards with * SUB IDs set to PCI_ANY_ID, so we need to match all and reject * known other cards which not work with this driver - see probe function */ -static struct pci_device_id nj_pci_ids[] = { +static const struct pci_device_id nj_pci_ids[] = { { PCI_VENDOR_ID_TIGERJET, PCI_DEVICE_ID_TIGERJET_300, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { } diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c index 3052c836b89f..d80072fef434 100644 --- a/drivers/isdn/hardware/mISDN/w6692.c +++ b/drivers/isdn/hardware/mISDN/w6692.c @@ -1398,7 +1398,7 @@ w6692_remove_pci(struct pci_dev *pdev) pr_notice("%s: drvdata already removed\n", __func__); } -static struct pci_device_id w6692_ids[] = { +static const struct pci_device_id w6692_ids[] = { { PCI_VENDOR_ID_DYNALINK, PCI_DEVICE_ID_DYNALINK_IS64PH, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (ulong)&w6692_map[0]}, { PCI_VENDOR_ID_WINBOND2, PCI_DEVICE_ID_WINBOND2_6692, diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c index c7d68675b028..7108bdb8742e 100644 --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -1909,7 +1909,7 @@ static void EChannel_proc_rcv(struct hisax_d_if *d_if) #ifdef CONFIG_PCI #include <linux/pci.h> -static struct pci_device_id hisax_pci_tbl[] __used = { +static const struct pci_device_id hisax_pci_tbl[] __used = { #ifdef CONFIG_HISAX_FRITZPCI {PCI_VDEVICE(AVM, PCI_DEVICE_ID_AVM_A1) }, #endif diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 90f051ce0259..9090cc1e1f29 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -86,7 +86,7 @@ typedef struct { char *device_name; } hfc4s8s_param; -static struct pci_device_id hfc4s8s_ids[] = { +static const struct pci_device_id hfc4s8s_ids[] = { {.vendor = PCI_VENDOR_ID_CCD, .device = PCI_DEVICE_ID_4S, .subvendor = 0x1397, diff --git a/drivers/isdn/hisax/hisax_fcpcipnp.c b/drivers/isdn/hisax/hisax_fcpcipnp.c index 5a9f39ed1d5d..e4f7573ba9bf 100644 --- a/drivers/isdn/hisax/hisax_fcpcipnp.c +++ b/drivers/isdn/hisax/hisax_fcpcipnp.c @@ -52,7 +52,7 @@ module_param(debug, int, 0); MODULE_AUTHOR("Kai Germaschewski <kai.germaschewski@gmx.de>/Karsten Keil <kkeil@suse.de>"); MODULE_DESCRIPTION("AVM Fritz!PCI/PnP ISDN driver"); -static struct pci_device_id fcpci_ids[] = { +static const struct pci_device_id fcpci_ids[] = { { .vendor = PCI_VENDOR_ID_AVM, .device = PCI_DEVICE_ID_AVM_A1, .subvendor = PCI_ANY_ID, diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index f4eace5ea184..40f3cd7eab0f 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -156,7 +156,8 @@ static int read_sb_page(struct mddev *mddev, loff_t offset, rdev_for_each(rdev, mddev) { if (! test_bit(In_sync, &rdev->flags) - || test_bit(Faulty, &rdev->flags)) + || test_bit(Faulty, &rdev->flags) + || test_bit(Bitmap_sync, &rdev->flags)) continue; target = offset + index * (PAGE_SIZE/512); diff --git a/drivers/md/md.h b/drivers/md/md.h index 991f0fe2dcc6..b50eb4ac1b82 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -134,7 +134,9 @@ enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ Bitmap_sync, /* ..actually, not quite In_sync. Need a - * bitmap-based recovery to get fully in sync + * bitmap-based recovery to get fully in sync. + * The bit is only meaningful before device + * has been passed to pers->hot_add_disk. */ WriteMostly, /* Avoid reading if at all possible */ AutoDetected, /* added by auto-detect */ diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 77cce3573aa8..44ad5baf3206 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf) goto err; } - ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0); + ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS); if (!ppl_conf->bs) { ret = -ENOMEM; goto err; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2ceb338b094b..aeeb8d6854e2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7951,12 +7951,10 @@ static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { - struct md_rdev *rdev; spin_lock_irq(&conf->device_lock); conf->previous_raid_disks = conf->raid_disks; - rdev_for_each(rdev, conf->mddev) - rdev->data_offset = rdev->new_data_offset; + md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; conf->mddev->reshape_position = MaxSector; diff --git a/drivers/mux/Kconfig b/drivers/mux/Kconfig index 7c754a0f14bb..19e4e904c9bf 100644 --- a/drivers/mux/Kconfig +++ b/drivers/mux/Kconfig @@ -2,20 +2,11 @@ # Multiplexer devices # -menuconfig MULTIPLEXER - tristate "Multiplexer subsystem" - help - Multiplexer controller subsystem. Multiplexers are used in a - variety of settings, and this subsystem abstracts their use - so that the rest of the kernel sees a common interface. When - multiple parallel multiplexers are controlled by one single - multiplexer controller, this subsystem also coordinates the - multiplexer accesses. - - To compile the subsystem as a module, choose M here: the module will - be called mux-core. +config MULTIPLEXER + tristate -if MULTIPLEXER +menu "Multiplexer drivers" + depends on MULTIPLEXER config MUX_ADG792A tristate "Analog Devices ADG792A/ADG792G Multiplexers" @@ -56,4 +47,4 @@ config MUX_MMIO To compile the driver as a module, choose M here: the module will be called mux-mmio. -endif +endmenu diff --git a/drivers/mux/mux-core.c b/drivers/mux/mux-core.c index 90b8995f07cb..2fe96c470112 100644 --- a/drivers/mux/mux-core.c +++ b/drivers/mux/mux-core.c @@ -46,7 +46,7 @@ static int __init mux_init(void) static void __exit mux_exit(void) { - class_register(&mux_class); + class_unregister(&mux_class); ida_destroy(&mux_ida); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 14ff622190a5..181839d6fbea 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4596,7 +4596,7 @@ static int bond_check_params(struct bond_params *params) } ad_user_port_key = valptr->value; - if (bond_mode == BOND_MODE_TLB) { + if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) { bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index e68d368e20ac..7f36d3e3c98b 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1665,6 +1665,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .dev_name = "BCM53125", .vlans = 4096, .enabled_ports = 0xff, + .arl_entries = 4, .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 53b088166c28..5bcdd33101b0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3178,6 +3178,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_set_jumbo_size = mv88e6165_port_set_jumbo_size, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_limit = mv88e6390_port_pause_limit, + .port_set_cmode = mv88e6390x_port_set_cmode, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index d3906f6b01bd..86058a9f3417 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1785,16 +1785,18 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_enet_gpiod_get(pdata); - pdata->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pdata->clk)) { - /* Abort if the clock is defined but couldn't be retrived. - * Always abort if the clock is missing on DT system as - * the driver can't cope with this case. - */ - if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) - return PTR_ERR(pdata->clk); - /* Firmware may have set up the clock already. */ - dev_info(dev, "clocks have been setup already\n"); + if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) { + pdata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pdata->clk)) { + /* Abort if the clock is defined but couldn't be + * retrived. Always abort if the clock is missing on + * DT system as the driver can't cope with this case. + */ + if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) + return PTR_ERR(pdata->clk); + /* Firmware may have set up the clock already. */ + dev_info(dev, "clocks have been setup already\n"); + } } if (pdata->phy_mode != PHY_INTERFACE_MODE_XGMII) diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 73aca97a96bc..d937083db9a4 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -50,11 +50,14 @@ static u32 platform_bgmac_idm_read(struct bgmac *bgmac, u16 offset) static void platform_bgmac_idm_write(struct bgmac *bgmac, u16 offset, u32 value) { - return writel(value, bgmac->plat.idm_base + offset); + writel(value, bgmac->plat.idm_base + offset); } static bool platform_bgmac_clk_enabled(struct bgmac *bgmac) { + if (!bgmac->plat.idm_base) + return true; + if ((bgmac_idm_read(bgmac, BCMA_IOCTL) & BGMAC_CLK_EN) != BGMAC_CLK_EN) return false; if (bgmac_idm_read(bgmac, BCMA_RESET_CTL) & BCMA_RESET_CTL_RESET) @@ -66,6 +69,9 @@ static void platform_bgmac_clk_enable(struct bgmac *bgmac, u32 flags) { u32 val; + if (!bgmac->plat.idm_base) + return; + /* The Reset Control register only contains a single bit to show if the * controller is currently in reset. Do a sanity check here, just in * case the bootloader happened to leave the device in reset. @@ -180,6 +186,7 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->feature_flags |= BGMAC_FEAT_CMDCFG_SR_REV4; bgmac->feature_flags |= BGMAC_FEAT_TX_MASK_SETUP; bgmac->feature_flags |= BGMAC_FEAT_RX_MASK_SETUP; + bgmac->feature_flags |= BGMAC_FEAT_IDM_MASK; bgmac->dev = &pdev->dev; bgmac->dma_dev = &pdev->dev; @@ -207,15 +214,13 @@ static int bgmac_probe(struct platform_device *pdev) return PTR_ERR(bgmac->plat.base); regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); - if (!regs) { - dev_err(&pdev->dev, "Unable to obtain idm resource\n"); - return -EINVAL; + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; } - bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); if (regs) { bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index ba4d2e145bb9..48d672b204a4 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -622,9 +622,11 @@ static int bgmac_dma_alloc(struct bgmac *bgmac) BUILD_BUG_ON(BGMAC_MAX_TX_RINGS > ARRAY_SIZE(ring_base)); BUILD_BUG_ON(BGMAC_MAX_RX_RINGS > ARRAY_SIZE(ring_base)); - if (!(bgmac_idm_read(bgmac, BCMA_IOST) & BCMA_IOST_DMA64)) { - dev_err(bgmac->dev, "Core does not report 64-bit DMA\n"); - return -ENOTSUPP; + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + if (!(bgmac_idm_read(bgmac, BCMA_IOST) & BCMA_IOST_DMA64)) { + dev_err(bgmac->dev, "Core does not report 64-bit DMA\n"); + return -ENOTSUPP; + } } for (i = 0; i < BGMAC_MAX_TX_RINGS; i++) { @@ -855,9 +857,11 @@ static void bgmac_mac_speed(struct bgmac *bgmac) static void bgmac_miiconfig(struct bgmac *bgmac) { if (bgmac->feature_flags & BGMAC_FEAT_FORCE_SPEED_2500) { - bgmac_idm_write(bgmac, BCMA_IOCTL, - bgmac_idm_read(bgmac, BCMA_IOCTL) | 0x40 | - BGMAC_BCMA_IOCTL_SW_CLKEN); + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + bgmac_idm_write(bgmac, BCMA_IOCTL, + bgmac_idm_read(bgmac, BCMA_IOCTL) | + 0x40 | BGMAC_BCMA_IOCTL_SW_CLKEN); + } bgmac->mac_speed = SPEED_2500; bgmac->mac_duplex = DUPLEX_FULL; bgmac_mac_speed(bgmac); @@ -874,11 +878,36 @@ static void bgmac_miiconfig(struct bgmac *bgmac) } } +static void bgmac_chip_reset_idm_config(struct bgmac *bgmac) +{ + u32 iost; + + iost = bgmac_idm_read(bgmac, BCMA_IOST); + if (bgmac->feature_flags & BGMAC_FEAT_IOST_ATTACHED) + iost &= ~BGMAC_BCMA_IOST_ATTACHED; + + /* 3GMAC: for BCM4707 & BCM47094, only do core reset at bgmac_probe() */ + if (!(bgmac->feature_flags & BGMAC_FEAT_NO_RESET)) { + u32 flags = 0; + + if (iost & BGMAC_BCMA_IOST_ATTACHED) { + flags = BGMAC_BCMA_IOCTL_SW_CLKEN; + if (!bgmac->has_robosw) + flags |= BGMAC_BCMA_IOCTL_SW_RESET; + } + bgmac_clk_enable(bgmac, flags); + } + + if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) + bgmac_idm_write(bgmac, BCMA_IOCTL, + bgmac_idm_read(bgmac, BCMA_IOCTL) & + ~BGMAC_BCMA_IOCTL_SW_RESET); +} + /* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/chipreset */ static void bgmac_chip_reset(struct bgmac *bgmac) { u32 cmdcfg_sr; - u32 iost; int i; if (bgmac_clk_enabled(bgmac)) { @@ -899,20 +928,8 @@ static void bgmac_chip_reset(struct bgmac *bgmac) /* TODO: Clear software multicast filter list */ } - iost = bgmac_idm_read(bgmac, BCMA_IOST); - if (bgmac->feature_flags & BGMAC_FEAT_IOST_ATTACHED) - iost &= ~BGMAC_BCMA_IOST_ATTACHED; - - /* 3GMAC: for BCM4707 & BCM47094, only do core reset at bgmac_probe() */ - if (!(bgmac->feature_flags & BGMAC_FEAT_NO_RESET)) { - u32 flags = 0; - if (iost & BGMAC_BCMA_IOST_ATTACHED) { - flags = BGMAC_BCMA_IOCTL_SW_CLKEN; - if (!bgmac->has_robosw) - flags |= BGMAC_BCMA_IOCTL_SW_RESET; - } - bgmac_clk_enable(bgmac, flags); - } + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) + bgmac_chip_reset_idm_config(bgmac); /* Request Misc PLL for corerev > 2 */ if (bgmac->feature_flags & BGMAC_FEAT_MISC_PLL_REQ) { @@ -970,11 +987,6 @@ static void bgmac_chip_reset(struct bgmac *bgmac) BGMAC_CHIPCTL_7_IF_TYPE_RGMII); } - if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) - bgmac_idm_write(bgmac, BCMA_IOCTL, - bgmac_idm_read(bgmac, BCMA_IOCTL) & - ~BGMAC_BCMA_IOCTL_SW_RESET); - /* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/gmac_reset * Specs don't say about using BGMAC_CMDCFG_SR, but in this routine * BGMAC_CMDCFG is read _after_ putting chip in a reset. So it has to @@ -1497,8 +1509,10 @@ int bgmac_enet_probe(struct bgmac *bgmac) bgmac_clk_enable(bgmac, 0); /* This seems to be fixing IRQ by assigning OOB #6 to the core */ - if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) - bgmac_idm_write(bgmac, BCMA_OOB_SEL_OUT_A30, 0x86); + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) + bgmac_idm_write(bgmac, BCMA_OOB_SEL_OUT_A30, 0x86); + } bgmac_chip_reset(bgmac); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index c1818766c501..443d57b10264 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -425,6 +425,7 @@ #define BGMAC_FEAT_CC4_IF_SW_TYPE BIT(17) #define BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII BIT(18) #define BGMAC_FEAT_CC7_IF_TYPE_RGMII BIT(19) +#define BGMAC_FEAT_IDM_MASK BIT(20) struct bgmac_slot_info { union { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 43423744fdfa..1e33abde4a3e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2886,7 +2886,7 @@ static int bnx2x_test_nvram_tbl(struct bnx2x *bp, static int bnx2x_test_nvram(struct bnx2x *bp) { - const struct crc_pair nvram_tbl[] = { + static const struct crc_pair nvram_tbl[] = { { 0, 0x14 }, /* bootstrap */ { 0x14, 0xec }, /* dir */ { 0x100, 0x350 }, /* manuf_info */ @@ -2895,7 +2895,7 @@ static int bnx2x_test_nvram(struct bnx2x *bp) { 0x708, 0x70 }, /* manuf_key_info */ { 0, 0 } }; - const struct crc_pair nvram_tbl2[] = { + static const struct crc_pair nvram_tbl2[] = { { 0x7e8, 0x350 }, /* manuf_info2 */ { 0xb38, 0xf0 }, /* feature_info */ { 0, 0 } @@ -3162,7 +3162,8 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) if (is_multi(bp)) { for_each_eth_queue(bp, i) { memset(queue_name, 0, sizeof(queue_name)); - sprintf(queue_name, "%d", i); + snprintf(queue_name, sizeof(queue_name), + "%d", i); for (j = 0; j < BNX2X_NUM_Q_STATS; j++) snprintf(buf + (k + j)*ETH_GSTRING_LEN, ETH_GSTRING_LEN, diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index daca1c9d254b..7b0b399aaedd 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1202,12 +1202,21 @@ static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv, return tx_cb_ptr; } -/* Simple helper to free a control block's resources */ -static void bcmgenet_free_cb(struct enet_cb *cb) +static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv, + struct bcmgenet_tx_ring *ring) { - dev_kfree_skb_any(cb->skb); - cb->skb = NULL; - dma_unmap_addr_set(cb, dma_addr, 0); + struct enet_cb *tx_cb_ptr; + + tx_cb_ptr = ring->cbs; + tx_cb_ptr += ring->write_ptr - ring->cb_ptr; + + /* Rewinding local write pointer */ + if (ring->write_ptr == ring->cb_ptr) + ring->write_ptr = ring->end_ptr; + else + ring->write_ptr--; + + return tx_cb_ptr; } static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring) @@ -1260,18 +1269,72 @@ static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_tx_ring *ring) INTRL2_CPU_MASK_SET); } +/* Simple helper to free a transmit control block's resources + * Returns an skb when the last transmit control block associated with the + * skb is freed. The skb should be freed by the caller if necessary. + */ +static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev, + struct enet_cb *cb) +{ + struct sk_buff *skb; + + skb = cb->skb; + + if (skb) { + cb->skb = NULL; + if (cb == GENET_CB(skb)->first_cb) + dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + else + dma_unmap_page(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + + if (cb == GENET_CB(skb)->last_cb) + return skb; + + } else if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_page(dev, + dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + return 0; +} + +/* Simple helper to free a receive control block's resources */ +static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev, + struct enet_cb *cb) +{ + struct sk_buff *skb; + + skb = cb->skb; + cb->skb = NULL; + + if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), DMA_FROM_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + return skb; +} + /* Unlocked version of the reclaim routine */ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_tx_ring *ring) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int pkts_compl = 0; + unsigned int txbds_processed = 0; unsigned int bytes_compl = 0; - unsigned int c_index; + unsigned int pkts_compl = 0; unsigned int txbds_ready; - unsigned int txbds_processed = 0; + unsigned int c_index; + struct sk_buff *skb; /* Clear status before servicing to reduce spurious interrupts */ if (ring->index == DESC_INDEX) @@ -1292,21 +1355,12 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, /* Reclaim transmitted buffers */ while (txbds_processed < txbds_ready) { - tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr]; - if (tx_cb_ptr->skb) { + skb = bcmgenet_free_tx_cb(&priv->pdev->dev, + &priv->tx_cbs[ring->clean_ptr]); + if (skb) { pkts_compl++; - bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; - dma_unmap_single(kdev, - dma_unmap_addr(tx_cb_ptr, dma_addr), - dma_unmap_len(tx_cb_ptr, dma_len), - DMA_TO_DEVICE); - bcmgenet_free_cb(tx_cb_ptr); - } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dma_unmap_page(kdev, - dma_unmap_addr(tx_cb_ptr, dma_addr), - dma_unmap_len(tx_cb_ptr, dma_len), - DMA_TO_DEVICE); - dma_unmap_addr_set(tx_cb_ptr, dma_addr, 0); + bytes_compl += GENET_CB(skb)->bytes_sent; + dev_kfree_skb_any(skb); } txbds_processed++; @@ -1380,95 +1434,6 @@ static void bcmgenet_tx_reclaim_all(struct net_device *dev) bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]); } -/* Transmits a single SKB (either head of a fragment or a single SKB) - * caller must hold priv->lock - */ -static int bcmgenet_xmit_single(struct net_device *dev, - struct sk_buff *skb, - u16 dma_desc_flags, - struct bcmgenet_tx_ring *ring) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int skb_len; - dma_addr_t mapping; - u32 length_status; - int ret; - - tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - - if (unlikely(!tx_cb_ptr)) - BUG(); - - tx_cb_ptr->skb = skb; - - skb_len = skb_headlen(skb); - - mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { - priv->mib.tx_dma_failed++; - netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); - dev_kfree_skb(skb); - return ret; - } - - dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len); - length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | - (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) | - DMA_TX_APPEND_CRC; - - if (skb->ip_summed == CHECKSUM_PARTIAL) - length_status |= DMA_TX_DO_CSUM; - - dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, length_status); - - return 0; -} - -/* Transmit a SKB fragment */ -static int bcmgenet_xmit_frag(struct net_device *dev, - skb_frag_t *frag, - u16 dma_desc_flags, - struct bcmgenet_tx_ring *ring) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int frag_size; - dma_addr_t mapping; - int ret; - - tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - - if (unlikely(!tx_cb_ptr)) - BUG(); - - tx_cb_ptr->skb = NULL; - - frag_size = skb_frag_size(frag); - - mapping = skb_frag_dma_map(kdev, frag, 0, frag_size, DMA_TO_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { - priv->mib.tx_dma_failed++; - netif_err(priv, tx_err, dev, "%s: Tx DMA map failed\n", - __func__); - return ret; - } - - dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, frag_size); - - dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, - (frag_size << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | - (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT)); - - return 0; -} - /* Reallocate the SKB to put enough headroom in front of it and insert * the transmit checksum offsets in the descriptors */ @@ -1535,11 +1500,16 @@ static struct sk_buff *bcmgenet_put_tx_csum(struct net_device *dev, static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; struct bcmgenet_tx_ring *ring = NULL; + struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned long flags = 0; int nr_frags, index; - u16 dma_desc_flags; + dma_addr_t mapping; + unsigned int size; + skb_frag_t *frag; + u32 len_stat; int ret; int i; @@ -1592,29 +1562,53 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } } - dma_desc_flags = DMA_SOP; - if (nr_frags == 0) - dma_desc_flags |= DMA_EOP; + for (i = 0; i <= nr_frags; i++) { + tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - /* Transmit single SKB or head of fragment list */ - ret = bcmgenet_xmit_single(dev, skb, dma_desc_flags, ring); - if (ret) { - ret = NETDEV_TX_OK; - goto out; - } + if (unlikely(!tx_cb_ptr)) + BUG(); + + if (!i) { + /* Transmit single SKB or head of fragment list */ + GENET_CB(skb)->first_cb = tx_cb_ptr; + size = skb_headlen(skb); + mapping = dma_map_single(kdev, skb->data, size, + DMA_TO_DEVICE); + } else { + /* xmit fragment */ + frag = &skb_shinfo(skb)->frags[i - 1]; + size = skb_frag_size(frag); + mapping = skb_frag_dma_map(kdev, frag, 0, size, + DMA_TO_DEVICE); + } - /* xmit fragment */ - for (i = 0; i < nr_frags; i++) { - ret = bcmgenet_xmit_frag(dev, - &skb_shinfo(skb)->frags[i], - (i == nr_frags - 1) ? DMA_EOP : 0, - ring); + ret = dma_mapping_error(kdev, mapping); if (ret) { + priv->mib.tx_dma_failed++; + netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); ret = NETDEV_TX_OK; - goto out; + goto out_unmap_frags; + } + dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); + dma_unmap_len_set(tx_cb_ptr, dma_len, size); + + tx_cb_ptr->skb = skb; + + len_stat = (size << DMA_BUFLENGTH_SHIFT) | + (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT); + + if (!i) { + len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + if (skb->ip_summed == CHECKSUM_PARTIAL) + len_stat |= DMA_TX_DO_CSUM; } + if (i == nr_frags) + len_stat |= DMA_EOP; + + dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, len_stat); } + GENET_CB(skb)->last_cb = tx_cb_ptr; skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ @@ -1635,6 +1629,19 @@ out: spin_unlock_irqrestore(&ring->lock, flags); return ret; + +out_unmap_frags: + /* Back up for failed control block mapping */ + bcmgenet_put_txcb(priv, ring); + + /* Unmap successfully mapped control blocks */ + while (i-- > 0) { + tx_cb_ptr = bcmgenet_put_txcb(priv, ring); + bcmgenet_free_tx_cb(kdev, tx_cb_ptr); + } + + dev_kfree_skb(skb); + goto out; } static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, @@ -1666,14 +1673,12 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, } /* Grab the current Rx skb from the ring and DMA-unmap it */ - rx_skb = cb->skb; - if (likely(rx_skb)) - dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), - priv->rx_buf_len, DMA_FROM_DEVICE); + rx_skb = bcmgenet_free_rx_cb(kdev, cb); /* Put the new Rx skb on the ring */ cb->skb = skb; dma_unmap_addr_set(cb, dma_addr, mapping); + dma_unmap_len_set(cb, dma_len, priv->rx_buf_len); dmadesc_set_addr(priv, cb->bd_addr, mapping); /* Return the current Rx skb to caller */ @@ -1880,22 +1885,16 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) { - struct device *kdev = &priv->pdev->dev; + struct sk_buff *skb; struct enet_cb *cb; int i; for (i = 0; i < priv->num_rx_bds; i++) { cb = &priv->rx_cbs[i]; - if (dma_unmap_addr(cb, dma_addr)) { - dma_unmap_single(kdev, - dma_unmap_addr(cb, dma_addr), - priv->rx_buf_len, DMA_FROM_DEVICE); - dma_unmap_addr_set(cb, dma_addr, 0); - } - - if (cb->skb) - bcmgenet_free_cb(cb); + skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb); + if (skb) + dev_kfree_skb_any(skb); } } @@ -2479,8 +2478,10 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv) static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) { - int i; struct netdev_queue *txq; + struct sk_buff *skb; + struct enet_cb *cb; + int i; bcmgenet_fini_rx_napi(priv); bcmgenet_fini_tx_napi(priv); @@ -2489,10 +2490,10 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) bcmgenet_dma_teardown(priv); for (i = 0; i < priv->num_tx_bds; i++) { - if (priv->tx_cbs[i].skb != NULL) { - dev_kfree_skb(priv->tx_cbs[i].skb); - priv->tx_cbs[i].skb = NULL; - } + cb = priv->tx_cbs + i; + skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb); + if (skb) + dev_kfree_skb(skb); } for (i = 0; i < priv->hw_params->tx_queues; i++) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index efd07020b89f..b9344de669f8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -544,6 +544,8 @@ struct bcmgenet_hw_params { }; struct bcmgenet_skb_cb { + struct enet_cb *first_cb; /* First control block of SKB */ + struct enet_cb *last_cb; /* Last control block of SKB */ unsigned int bytes_sent; /* bytes on the wire (no TSB) */ }; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 28ecda3d3404..ebd353bc78ff 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -335,7 +335,7 @@ lio_ethtool_get_channels(struct net_device *dev, static int lio_get_eeprom_len(struct net_device *netdev) { - u8 buf[128]; + u8 buf[192]; struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; struct octeon_board_info *board_info; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a0ca68ce3fbb..79112563a25a 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1008,7 +1008,7 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid) { struct device *dev = &bgx->pdev->dev; struct lmac *lmac; - char str[20]; + char str[27]; if (!bgx->is_dlm && lmacid) return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 50517cfd9671..9f9d6cae39d5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -441,7 +441,8 @@ void cxgb4_ptp_init(struct adapter *adapter) adapter->ptp_clock = ptp_clock_register(&adapter->ptp_clock_info, &adapter->pdev->dev); - if (!adapter->ptp_clock) { + if (IS_ERR_OR_NULL(adapter->ptp_clock)) { + adapter->ptp_clock = NULL; dev_err(adapter->pdev_dev, "PTP %s Clock registration has failed\n", __func__); return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 99987d8e437e..aa28299aef5f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -174,6 +174,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50a0), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a1), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a2), /* Custom T540-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a3), /* Custom T580-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a4), /* Custom 2x T540-CR */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index ff864a187d5a..a37166ee577b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -776,8 +776,9 @@ void hns_ae_update_led_status(struct hnae_handle *handle) assert(handle); mac_cb = hns_get_mac_cb(handle); - if (!mac_cb->cpld_ctrl) + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) return; + hns_set_led_opt(mac_cb); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 7a8addda726e..408b63faf9a8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -53,6 +53,34 @@ static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg) return ret; } +static void hns_dsaf_acpi_ledctrl_by_port(struct hns_mac_cb *mac_cb, u8 op_type, + u32 link, u32 port, u32 act) +{ + union acpi_object *obj; + union acpi_object obj_args[3], argv4; + + obj_args[0].integer.type = ACPI_TYPE_INTEGER; + obj_args[0].integer.value = link; + obj_args[1].integer.type = ACPI_TYPE_INTEGER; + obj_args[1].integer.value = port; + obj_args[2].integer.type = ACPI_TYPE_INTEGER; + obj_args[2].integer.value = act; + + argv4.type = ACPI_TYPE_PACKAGE; + argv4.package.count = 3; + argv4.package.elements = obj_args; + + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); + if (!obj) { + dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n", + link, port, act); + return; + } + + ACPI_FREE(obj); +} + static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, u16 speed, int data) { @@ -93,6 +121,18 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, } } +static void hns_cpld_set_led_acpi(struct hns_mac_cb *mac_cb, int link_status, + u16 speed, int data) +{ + if (!mac_cb) { + pr_err("cpld_led_set mac_cb is null!\n"); + return; + } + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + link_status, mac_cb->mac_id, data); +} + static void cpld_led_reset(struct hns_mac_cb *mac_cb) { if (!mac_cb || !mac_cb->cpld_ctrl) @@ -103,6 +143,20 @@ static void cpld_led_reset(struct hns_mac_cb *mac_cb) mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE; } +static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb) +{ + if (!mac_cb) { + pr_err("cpld_led_reset mac_cb is null!\n"); + return; + } + + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) + return; + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + 0, mac_cb->mac_id, 0); +} + static int cpld_set_led_id(struct hns_mac_cb *mac_cb, enum hnae_led_state status) { @@ -604,8 +658,8 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback; } else if (is_acpi_node(dsaf_dev->dev->fwnode)) { - misc_op->cpld_set_led = hns_cpld_set_led; - misc_op->cpld_reset_led = cpld_led_reset; + misc_op->cpld_set_led = hns_cpld_set_led_acpi; + misc_op->cpld_reset_led = cpld_led_reset_acpi; misc_op->cpld_set_led_id = cpld_set_led_id; misc_op->dsaf_reset = hns_dsaf_rst_acpi; diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index d94b3744a5b9..b651c1210555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -283,7 +283,7 @@ int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc, } /* Should be called under a lock */ -static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) +static void __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) { struct mlx4_zone_allocator *zone_alloc = entry->allocator; @@ -315,8 +315,6 @@ static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) } zone_alloc->mask = mask; } - - return 0; } void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc) @@ -457,7 +455,7 @@ struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid) { struct mlx4_zone_entry *zone; - int res; + int res = 0; spin_lock(&zones->lock); @@ -468,7 +466,7 @@ int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid) goto out; } - res = __mlx4_zone_remove_one_entry(zone); + __mlx4_zone_remove_one_entry(zone); out: spin_unlock(&zones->lock); diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index c56a511b918e..72eb50cd5ecd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -241,13 +241,14 @@ err_out: return err; } -static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn) +static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn, u8 usage) { + u32 in_modifier = RES_CQ | (((u32)usage & 3) << 30); u64 out_param; int err; if (mlx4_is_mfunc(dev)) { - err = mlx4_cmd_imm(dev, 0, &out_param, RES_CQ, + err = mlx4_cmd_imm(dev, 0, &out_param, in_modifier, RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (err) @@ -303,7 +304,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, cq->vector = vector; - err = mlx4_cq_alloc_icm(dev, &cq->cqn); + err = mlx4_cq_alloc_icm(dev, &cq->cqn, cq->usage); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 85fe17e4dcfb..f849eec21824 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -140,6 +140,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, (cq->type == RX && priv->hwtstamp_config.rx_filter)) timestamp_en = 1; + cq->mcq.usage = MLX4_RES_USAGE_DRIVER; err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq, cq->vector, 0, timestamp_en); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 3a291fc1780a..e3e6d9fa69fd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -651,7 +651,8 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv) return 0; } - err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP); + err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP, + MLX4_RES_USAGE_DRIVER); en_dbg(DRV, priv, "Reserved qp %d\n", *qpn); if (err) { en_err(priv, "Failed to reserve qp for mac registration\n"); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 436f7689a032..ad1ffd5857cb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -1081,7 +1081,8 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv) u32 qpn; err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn, - MLX4_RESERVE_A0_QP); + MLX4_RESERVE_A0_QP, + MLX4_RES_USAGE_DRIVER); if (err) { en_err(priv, "Failed reserving drop qpn\n"); return err; @@ -1127,7 +1128,8 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv) flags = priv->rx_ring_num == 1 ? MLX4_RESERVE_A0_QP : 0; err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num, priv->rx_ring_num, - &rss_map->base_qpn, flags); + &rss_map->base_qpn, flags, + MLX4_RES_USAGE_DRIVER); if (err) { en_err(priv, "Failed reserving %d qps\n", priv->rx_ring_num); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 73faa3d77921..a81db2582555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -105,7 +105,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, (unsigned long long) ring->sp_wqres.buf.direct.map); err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn, - MLX4_RESERVE_ETH_BF_QP); + MLX4_RESERVE_ETH_BF_QP, + MLX4_RES_USAGE_DRIVER); if (err) { en_err(priv, "failed reserving qp for TX ring\n"); goto err_hwq_res; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index a27c9c13a36e..fb2591d0e735 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2475,7 +2475,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) priv->def_counter[port] = -1; for (port = 0; port < dev->caps.num_ports; port++) { - err = mlx4_counter_alloc(dev, &idx); + err = mlx4_counter_alloc(dev, &idx, MLX4_RES_USAGE_DRIVER); if (!err || err == -ENOSPC) { priv->def_counter[port] = idx; @@ -2517,13 +2517,14 @@ int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx) return 0; } -int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx) +int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage) { + u32 in_modifier = RES_COUNTER | (((u32)usage & 3) << 30); u64 out_param; int err; if (mlx4_is_mfunc(dev)) { - err = mlx4_cmd_imm(dev, 0, &out_param, RES_COUNTER, + err = mlx4_cmd_imm(dev, 0, &out_param, in_modifier, RES_OP_RESERVE, MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 26747212526b..5e5b4475b85e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -245,8 +245,9 @@ int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, } int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, - int *base, u8 flags) + int *base, u8 flags, u8 usage) { + u32 in_modifier = RES_QP | (((u32)usage & 3) << 30); u64 in_param = 0; u64 out_param; int err; @@ -258,7 +259,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, set_param_l(&in_param, (((u32)flags) << 24) | (u32)cnt); set_param_h(&in_param, align); err = mlx4_cmd_imm(dev, in_param, &out_param, - RES_QP, RES_OP_RESERVE, + in_modifier, RES_OP_RESERVE, MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index e1b7ddfecd01..909123243a85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -587,7 +587,6 @@ struct mlx5e_channel { struct mlx5_core_dev *mdev; struct mlx5e_tstamp *tstamp; int ix; - int cpu; }; struct mlx5e_channels { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1eac5003084f..fb647561c592 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -71,6 +71,11 @@ struct mlx5e_channel_param { struct mlx5e_cq_param icosq_cq; }; +static int mlx5e_get_node(struct mlx5e_priv *priv, int ix) +{ + return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix); +} + static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { return MLX5_CAP_GEN(mdev, striding_rq) && @@ -397,7 +402,7 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv) static void mlx5e_disable_async_events(struct mlx5e_priv *priv) { clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state); - synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC)); + synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC)); } static inline int mlx5e_get_wqe_mtt_sz(void) @@ -444,16 +449,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int wq_sz = mlx5_wq_ll_get_size(&rq->wq); int mtt_sz = mlx5e_get_wqe_mtt_sz(); int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1; + int node = mlx5e_get_node(c->priv, c->ix); int i; rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), - GFP_KERNEL, cpu_to_node(c->cpu)); + GFP_KERNEL, node); if (!rq->mpwqe.info) goto err_out; /* We allocate more than mtt_sz as we will align the pointer */ - rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL, - cpu_to_node(c->cpu)); + rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, + GFP_KERNEL, node); if (unlikely(!rq->mpwqe.mtt_no_align)) goto err_free_wqe_info; @@ -561,7 +567,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, int err; int i; - rqp->wq.db_numa_node = cpu_to_node(c->cpu); + rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq, &rq->wq_ctrl); @@ -628,7 +634,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, default: /* MLX5_WQ_TYPE_LINKED_LIST */ rq->wqe.frag_info = kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info), - GFP_KERNEL, cpu_to_node(c->cpu)); + GFP_KERNEL, + mlx5e_get_node(c->priv, c->ix)); if (!rq->wqe.frag_info) { err = -ENOMEM; goto err_rq_wq_destroy; @@ -993,13 +1000,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; - param->wq.db_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu)); + err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix)); if (err) goto err_sq_wq_destroy; @@ -1047,13 +1054,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; - param->wq.db_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu)); + err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix)); if (err) goto err_sq_wq_destroy; @@ -1119,13 +1126,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); - param->wq.db_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu)); + err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix)); if (err) goto err_sq_wq_destroy; @@ -1497,8 +1504,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->priv->mdev; int err; - param->wq.buf_numa_node = cpu_to_node(c->cpu); - param->wq.db_numa_node = cpu_to_node(c->cpu); + param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); param->eq_ix = c->ix; err = mlx5e_alloc_cq_common(mdev, param, cq); @@ -1597,11 +1604,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq) mlx5e_free_cq(cq); } -static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix) -{ - return cpumask_first(priv->mdev->priv.irq_info[ix].mask); -} - static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1750,11 +1752,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, { struct mlx5e_cq_moder icocq_moder = {0, 0}; struct net_device *netdev = priv->netdev; - int cpu = mlx5e_get_cpu(priv, ix); struct mlx5e_channel *c; int err; - c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); + c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix)); if (!c) return -ENOMEM; @@ -1762,7 +1763,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->mdev = priv->mdev; c->tstamp = &priv->tstamp; c->ix = ix; - c->cpu = cpu; c->pdev = &priv->mdev->pdev->dev; c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); @@ -1848,7 +1848,8 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_rq(&c->rq); - netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix); + netif_set_xps_queue(c->netdev, + mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) @@ -3793,18 +3794,8 @@ void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev, u32 *indirection_rqt, int len, int num_channels) { - int node = mdev->priv.numa_node; - int node_num_of_cores; int i; - if (node == -1) - node = first_online_node; - - node_num_of_cores = cpumask_weight(cpumask_of_node(node)); - - if (node_num_of_cores) - num_channels = min_t(int, num_channels, node_num_of_cores); - for (i = 0; i < len; i++) indirection_rqt[i] = i % num_channels; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 898759fcf9ec..1f1f8af87d4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -189,6 +189,7 @@ struct mlx5e_lbt_priv { struct packet_type pt; struct completion comp; bool loopback_ok; + bool local_lb; }; static int @@ -236,6 +237,13 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, { int err = 0; + /* Temporarily enable local_lb */ + if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) { + mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb); + if (!lbtp->local_lb) + mlx5_nic_vport_update_local_lb(priv->mdev, true); + } + err = mlx5e_refresh_tirs(priv, true); if (err) return err; @@ -254,6 +262,11 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, struct mlx5e_lbt_priv *lbtp) { + if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) { + if (!lbtp->local_lb) + mlx5_nic_vport_update_local_lb(priv->mdev, false); + } + dev_remove_pack(&lbtp->pt); mlx5e_refresh_tirs(priv, false); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index af51a5d2b912..261b3c628767 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -161,6 +161,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE"; case MLX5_EVENT_TYPE_FPGA_ERROR: return "MLX5_EVENT_TYPE_FPGA_ERROR"; + case MLX5_EVENT_TYPE_GENERAL_EVENT: + return "MLX5_EVENT_TYPE_GENERAL_EVENT"; default: return "Unrecognized event"; } @@ -378,6 +380,20 @@ int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token, EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume); #endif +static void general_event_handler(struct mlx5_core_dev *dev, + struct mlx5_eqe *eqe) +{ + switch (eqe->sub_type) { + case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT: + if (dev->event) + dev->event(dev, MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, 0); + break; + default: + mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n", + eqe->sub_type); + } +} + static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) { struct mlx5_eq *eq = eq_ptr; @@ -486,6 +502,9 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) mlx5_fpga_event(dev, eqe->type, &eqe->data.raw); break; + case MLX5_EVENT_TYPE_GENERAL_EVENT: + general_event_handler(dev, eqe); + break; default: mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n", eqe->type, eq->eqn); @@ -585,7 +604,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, name, pci_name(dev->pdev)); eq->eqn = MLX5_GET(create_eq_out, out, eq_number); - eq->irqn = priv->msix_arr[vecidx].vector; + eq->irqn = pci_irq_vector(dev->pdev, vecidx); eq->dev = dev; eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET; err = request_irq(eq->irqn, handler, 0, @@ -620,7 +639,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, return 0; err_irq: - free_irq(priv->msix_arr[vecidx].vector, eq); + free_irq(eq->irqn, eq); err_eq: mlx5_cmd_destroy_eq(dev, eq->eqn); @@ -661,11 +680,6 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) } EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq); -u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx) -{ - return dev->priv.msix_arr[MLX5_EQ_VEC_ASYNC].vector; -} - int mlx5_eq_init(struct mlx5_core_dev *dev) { int err; @@ -693,6 +707,10 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) mlx5_core_is_pf(dev)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE); + if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH && + MLX5_CAP_GEN(dev, general_notification_event)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_GENERAL_EVENT); + if (MLX5_CAP_GEN(dev, port_module_event)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_PORT_MODULE_EVENT); else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 89bfda419efe..1ce2543e3889 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1585,7 +1585,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) /* Mark this vport as disabled to discard new events */ vport->enabled = false; - synchronize_irq(mlx5_get_msix_vec(esw->dev, MLX5_EQ_VEC_ASYNC)); + synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC)); /* Wait for current already scheduled events to complete */ flush_workqueue(esw->work_queue); /* Disable events from this vport */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index fa33d59ab485..2c71557d1cee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -120,6 +120,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, pg)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ODP); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 4b6b03d6297f..8aea0a065e56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -81,7 +81,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev) u64 vector; /* wait for pending handlers to complete */ - synchronize_irq(dev->priv.msix_arr[MLX5_EQ_VEC_CMD].vector); + synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD)); spin_lock_irqsave(&dev->cmd.alloc_lock, flags); vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1); if (!vector) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c065132b956d..d8e761cd5448 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -47,6 +47,7 @@ #include <linux/debugfs.h> #include <linux/kmod.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/vport.h> #ifdef CONFIG_RFS_ACCEL #include <linux/cpu_rmap.h> #endif @@ -312,13 +313,15 @@ static void release_bar(struct pci_dev *pdev) pci_release_regions(pdev); } -static int mlx5_enable_msix(struct mlx5_core_dev *dev) +static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; struct mlx5_eq_table *table = &priv->eq_table; + struct irq_affinity irqdesc = { + .pre_vectors = MLX5_EQ_VEC_COMP_BASE, + }; int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; - int i; nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE; @@ -326,17 +329,14 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev) if (nvec <= MLX5_EQ_VEC_COMP_BASE) return -ENOMEM; - priv->msix_arr = kcalloc(nvec, sizeof(*priv->msix_arr), GFP_KERNEL); - priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL); - if (!priv->msix_arr || !priv->irq_info) + if (!priv->irq_info) goto err_free_msix; - for (i = 0; i < nvec; i++) - priv->msix_arr[i].entry = i; - - nvec = pci_enable_msix_range(dev->pdev, priv->msix_arr, - MLX5_EQ_VEC_COMP_BASE + 1, nvec); + nvec = pci_alloc_irq_vectors_affinity(dev->pdev, + MLX5_EQ_VEC_COMP_BASE + 1, nvec, + PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, + &irqdesc); if (nvec < 0) return nvec; @@ -346,17 +346,15 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev) err_free_msix: kfree(priv->irq_info); - kfree(priv->msix_arr); return -ENOMEM; } -static void mlx5_disable_msix(struct mlx5_core_dev *dev) +static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - pci_disable_msix(dev->pdev); + pci_free_irq_vectors(dev->pdev); kfree(priv->irq_info); - kfree(priv->msix_arr); } struct mlx5_reg_host_endianness { @@ -579,6 +577,18 @@ static int set_hca_ctrl(struct mlx5_core_dev *dev) return err; } +static int mlx5_core_set_hca_defaults(struct mlx5_core_dev *dev) +{ + int ret = 0; + + /* Disable local_lb by default */ + if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && + MLX5_CAP_GEN(dev, disable_local_lb)) + ret = mlx5_nic_vport_update_local_lb(dev, false); + + return ret; +} + int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id) { u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {0}; @@ -612,65 +622,6 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev) return (u64)timer_l | (u64)timer_h1 << 32; } -static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) -{ - struct mlx5_priv *priv = &mdev->priv; - struct msix_entry *msix = priv->msix_arr; - int irq = msix[i + MLX5_EQ_VEC_COMP_BASE].vector; - - if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) { - mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); - return -ENOMEM; - } - - cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node), - priv->irq_info[i].mask); - - if (IS_ENABLED(CONFIG_SMP) && - irq_set_affinity_hint(irq, priv->irq_info[i].mask)) - mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq); - - return 0; -} - -static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i) -{ - struct mlx5_priv *priv = &mdev->priv; - struct msix_entry *msix = priv->msix_arr; - int irq = msix[i + MLX5_EQ_VEC_COMP_BASE].vector; - - irq_set_affinity_hint(irq, NULL); - free_cpumask_var(priv->irq_info[i].mask); -} - -static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev) -{ - int err; - int i; - - for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) { - err = mlx5_irq_set_affinity_hint(mdev, i); - if (err) - goto err_out; - } - - return 0; - -err_out: - for (i--; i >= 0; i--) - mlx5_irq_clear_affinity_hint(mdev, i); - - return err; -} - -static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) -{ - int i; - - for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) - mlx5_irq_clear_affinity_hint(mdev, i); -} - int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn) { @@ -760,8 +711,8 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev) } #ifdef CONFIG_RFS_ACCEL - irq_cpu_rmap_add(dev->rmap, - dev->priv.msix_arr[i + MLX5_EQ_VEC_COMP_BASE].vector); + irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev, + MLX5_EQ_VEC_COMP_BASE + i)); #endif snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i); err = mlx5_create_map_eq(dev, eq, @@ -1119,9 +1070,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_poll; } - err = mlx5_enable_msix(dev); + err = mlx5_alloc_irq_vectors(dev); if (err) { - dev_err(&pdev->dev, "enable msix failed\n"); + dev_err(&pdev->dev, "alloc irq vectors failed\n"); goto err_cleanup_once; } @@ -1143,15 +1094,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_eqs; } - err = mlx5_irq_set_affinity_hints(dev); + err = mlx5_init_fs(dev); if (err) { - dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); - goto err_affinity_hints; + dev_err(&pdev->dev, "Failed to init flow steering\n"); + goto err_fs; } - err = mlx5_init_fs(dev); + err = mlx5_core_set_hca_defaults(dev); if (err) { - dev_err(&pdev->dev, "Failed to init flow steering\n"); + dev_err(&pdev->dev, "Failed to set hca defaults\n"); goto err_fs; } @@ -1208,9 +1159,6 @@ err_sriov: mlx5_cleanup_fs(dev); err_fs: - mlx5_irq_clear_affinity_hints(dev); - -err_affinity_hints: free_comp_eqs(dev); err_stop_eqs: @@ -1220,7 +1168,7 @@ err_put_uars: mlx5_put_uars_page(dev, priv->uar); err_disable_msix: - mlx5_disable_msix(dev); + mlx5_free_irq_vectors(dev); err_cleanup_once: if (boot) @@ -1283,11 +1231,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_eswitch_detach(dev->priv.eswitch); #endif mlx5_cleanup_fs(dev); - mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_put_uars_page(dev, priv->uar); - mlx5_disable_msix(dev); + mlx5_free_irq_vectors(dev); if (cleanup) mlx5_cleanup_once(dev); mlx5_stop_health_poll(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 6a3d6bef7dd4..ba1d494b016d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -110,7 +110,6 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 element_id); int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev); -u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx); struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn); void mlx5_cq_tasklet_cb(unsigned long data); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 340f281c9801..db9e665ab104 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -242,6 +242,20 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_core_destroy_qp); +int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev, + u32 timeout_usec) +{ + u32 out[MLX5_ST_SZ_DW(set_delay_drop_params_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(set_delay_drop_params_in)] = {0}; + + MLX5_SET(set_delay_drop_params_in, in, opcode, + MLX5_CMD_OP_SET_DELAY_DROP_PARAMS); + MLX5_SET(set_delay_drop_params_in, in, delay_drop_timeout, + timeout_usec / 100); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} +EXPORT_SYMBOL_GPL(mlx5_core_set_delay_drop); + struct mbox_info { u32 *in; u32 *out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index bcdf7779c48d..090b29e05a6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -32,6 +32,7 @@ #include <linux/pci.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include "mlx5_core.h" #ifdef CONFIG_MLX5_CORE_EN #include "eswitch.h" @@ -44,6 +45,38 @@ bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) return !!sriov->num_vfs; } +static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf) +{ + struct mlx5_core_sriov *sriov = &dev->priv.sriov; + struct mlx5_hca_vport_context *in; + int err = 0; + + /* Restore sriov guid and policy settings */ + if (sriov->vfs_ctx[vf].node_guid || + sriov->vfs_ctx[vf].port_guid || + sriov->vfs_ctx[vf].policy != MLX5_POLICY_INVALID) { + in = kzalloc(sizeof(*in), GFP_KERNEL); + if (!in) + return -ENOMEM; + + in->node_guid = sriov->vfs_ctx[vf].node_guid; + in->port_guid = sriov->vfs_ctx[vf].port_guid; + in->policy = sriov->vfs_ctx[vf].policy; + in->field_select = + !!(in->port_guid) * MLX5_HCA_VPORT_SEL_PORT_GUID | + !!(in->node_guid) * MLX5_HCA_VPORT_SEL_NODE_GUID | + !!(in->policy) * MLX5_HCA_VPORT_SEL_STATE_POLICY; + + err = mlx5_core_modify_hca_vport_context(dev, 1, 1, vf + 1, in); + if (err) + mlx5_core_warn(dev, "modify vport context failed, unable to restore VF %d settings\n", vf); + + kfree(in); + } + + return err; +} + static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; @@ -74,6 +107,15 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) } sriov->vfs_ctx[vf].enabled = 1; sriov->enabled_vfs++; + if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) { + err = sriov_restore_guids(dev, vf); + if (err) { + mlx5_core_warn(dev, + "failed to restore VF %d settings, err %d\n", + vf, err); + continue; + } + } mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 5abfec1c3399..d653b0025b13 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -897,6 +897,68 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev, } EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_promisc); +enum { + UC_LOCAL_LB, + MC_LOCAL_LB +}; + +int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); + void *in; + int err; + + mlx5_core_dbg(mdev, "%s local_lb\n", enable ? "enable" : "disable"); + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_nic_vport_context_in, in, + field_select.disable_mc_local_lb, 1); + MLX5_SET(modify_nic_vport_context_in, in, + nic_vport_context.disable_mc_local_lb, !enable); + + MLX5_SET(modify_nic_vport_context_in, in, + field_select.disable_uc_local_lb, 1); + MLX5_SET(modify_nic_vport_context_in, in, + nic_vport_context.disable_uc_local_lb, !enable); + + err = mlx5_modify_nic_vport_context(mdev, in, inlen); + + kvfree(in); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_nic_vport_update_local_lb); + +int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int value; + int err; + + out = kzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out, outlen); + if (err) + goto out; + + value = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.disable_mc_local_lb) << MC_LOCAL_LB; + + value |= MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.disable_uc_local_lb) << UC_LOCAL_LB; + + *status = !value; + +out: + kfree(out); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_nic_vport_query_local_lb); + enum mlx5_vport_roce_state { MLX5_VPORT_ROCE_DISABLED = 0, MLX5_VPORT_ROCE_ENABLED = 1, diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 746d94e28470..60850bfa3d32 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -766,11 +766,13 @@ static void emac_shutdown(struct platform_device *pdev) struct emac_adapter *adpt = netdev_priv(netdev); struct emac_sgmii *sgmii = &adpt->phy; - /* Closing the SGMII turns off its interrupts */ - sgmii->close(adpt); + if (netdev->flags & IFF_UP) { + /* Closing the SGMII turns off its interrupts */ + sgmii->close(adpt); - /* Resetting the MAC turns off all DMA and its interrupts */ - emac_mac_reset(adpt); + /* Resetting the MAC turns off all DMA and its interrupts */ + emac_mac_reset(adpt); + } } static struct platform_driver emac_platform_driver = { diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index b607936e1b3e..9c0488e0f08e 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -90,17 +90,13 @@ struct ioc3_private { spinlock_t ioc3_lock; struct mii_if_info mii; + struct net_device *dev; struct pci_dev *pdev; /* Members used by autonegotiation */ struct timer_list ioc3_timer; }; -static inline struct net_device *priv_netdev(struct ioc3_private *dev) -{ - return (void *)dev - ((sizeof(struct net_device) + 31) & ~31); -} - static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); static void ioc3_set_multicast_list(struct net_device *dev); static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev); @@ -427,7 +423,7 @@ static void ioc3_get_eaddr_nic(struct ioc3_private *ip) nic[i] = nic_read_byte(ioc3); for (i = 2; i < 8; i++) - priv_netdev(ip)->dev_addr[i - 2] = nic[i]; + ip->dev->dev_addr[i - 2] = nic[i]; } /* @@ -439,7 +435,7 @@ static void ioc3_get_eaddr(struct ioc3_private *ip) { ioc3_get_eaddr_nic(ip); - printk("Ethernet address is %pM.\n", priv_netdev(ip)->dev_addr); + printk("Ethernet address is %pM.\n", ip->dev->dev_addr); } static void __ioc3_set_mac_address(struct net_device *dev) @@ -790,13 +786,12 @@ static void ioc3_timer(unsigned long data) */ static int ioc3_mii_init(struct ioc3_private *ip) { - struct net_device *dev = priv_netdev(ip); int i, found = 0, res = 0; int ioc3_phy_workaround = 1; u16 word; for (i = 0; i < 32; i++) { - word = ioc3_mdio_read(dev, i, MII_PHYSID1); + word = ioc3_mdio_read(ip->dev, i, MII_PHYSID1); if (word != 0xffff && word != 0x0000) { found = 1; @@ -1276,6 +1271,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) SET_NETDEV_DEV(dev, &pdev->dev); ip = netdev_priv(dev); + ip->dev = dev; dev->irq = pdev->irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f233bf8b4ebb..c4407e8e39a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -117,7 +117,7 @@ static void dwmac4_tx_queue_routing(struct mac_device_info *hw, void __iomem *ioaddr = hw->pcsr; u32 value; - const struct stmmac_rx_routing route_possibilities[] = { + static const struct stmmac_rx_routing route_possibilities[] = { { GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT }, { GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT }, { GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT }, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1853f7ff6657..1763e48c84e2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4120,8 +4120,15 @@ int stmmac_dvr_probe(struct device *device, if ((phyaddr >= 0) && (phyaddr <= 31)) priv->plat->phy_addr = phyaddr; - if (priv->plat->stmmac_rst) + if (priv->plat->stmmac_rst) { + ret = reset_control_assert(priv->plat->stmmac_rst); reset_control_deassert(priv->plat->stmmac_rst); + /* Some reset controllers have only reset callback instead of + * assert + deassert callbacks pair. + */ + if (ret == -ENOTSUPP) + reset_control_reset(priv->plat->stmmac_rst); + } /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 46cb7f8955a2..4bb04aaf9650 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9532,7 +9532,7 @@ static struct niu_parent *niu_get_parent(struct niu *np, p = niu_new_parent(np, id, ptype); if (p) { - char port_name[6]; + char port_name[8]; int err; sprintf(port_name, "port%d", port); @@ -9553,7 +9553,7 @@ static void niu_put_parent(struct niu *np) { struct niu_parent *p = np->parent; u8 port = np->port; - char port_name[6]; + char port_name[8]; BUG_ON(!p || p->ports[port] != np); diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 711fbbbc4b1f..163d8d16bc24 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -654,6 +654,8 @@ static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd) RET(-EFAULT); } DBG("%d 0x%x 0x%x\n", data[0], data[1], data[2]); + } else { + return -EOPNOTSUPP; } if (!capable(CAP_SYS_RAWIO)) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1850e348f555..badd0a8caeb9 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -3089,6 +3089,31 @@ static int cpsw_probe(struct platform_device *pdev) cpsw->quirk_irq = true; } + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + ndev->netdev_ops = &cpsw_netdev_ops; + ndev->ethtool_ops = &cpsw_ethtool_ops; + netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT); + netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT); + cpsw_split_res(ndev); + + /* register the network device */ + SET_NETDEV_DEV(ndev, &pdev->dev); + ret = register_netdev(ndev); + if (ret) { + dev_err(priv->dev, "error registering net device\n"); + ret = -ENODEV; + goto clean_ale_ret; + } + + if (cpsw->data.dual_emac) { + ret = cpsw_probe_dual_emac(priv); + if (ret) { + cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); + goto clean_unregister_netdev_ret; + } + } + /* Grab RX and TX IRQs. Note that we also have RX_THRESHOLD and * MISC IRQs which are always kept disabled with this driver so * we will not request them. @@ -3127,33 +3152,9 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_ale_ret; } - ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - - ndev->netdev_ops = &cpsw_netdev_ops; - ndev->ethtool_ops = &cpsw_ethtool_ops; - netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT); - netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT); - cpsw_split_res(ndev); - - /* register the network device */ - SET_NETDEV_DEV(ndev, &pdev->dev); - ret = register_netdev(ndev); - if (ret) { - dev_err(priv->dev, "error registering net device\n"); - ret = -ENODEV; - goto clean_ale_ret; - } - cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d, pool size %d)\n", &ss_res->start, ndev->irq, dma_params.descs_pool_size); - if (cpsw->data.dual_emac) { - ret = cpsw_probe_dual_emac(priv); - if (ret) { - cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); - goto clean_unregister_netdev_ret; - } - } pm_runtime_put(&pdev->dev); diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 00755b6a42cf..c608e1dfaf09 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -135,8 +135,8 @@ int mdio_mux_init(struct device *dev, for_each_available_child_of_node(dev->of_node, child_bus_node) { int v; - v = of_mdio_parse_addr(dev, child_bus_node); - if (v < 0) { + r = of_property_read_u32(child_bus_node, "reg", &v); + if (r) { dev_err(dev, "Error: Failed to find reg for child %s\n", of_node_full_name(child_bus_node)); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 13028833bee3..bd4303944e44 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -120,6 +120,7 @@ struct ppp { int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ + int *xmit_recursion __percpu; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ @@ -1025,6 +1026,7 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, struct ppp *ppp = netdev_priv(dev); int indx; int err; + int cpu; ppp->dev = dev; ppp->ppp_net = src_net; @@ -1039,6 +1041,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); + + ppp->xmit_recursion = alloc_percpu(int); + if (!ppp->xmit_recursion) { + err = -ENOMEM; + goto err1; + } + for_each_possible_cpu(cpu) + (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; + #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); @@ -1050,11 +1061,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) - return err; + goto err2; conf->file->private_data = &ppp->file; return 0; +err2: + free_percpu(ppp->xmit_recursion); +err1: + return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { @@ -1400,18 +1415,16 @@ static void __ppp_xmit_process(struct ppp *ppp) ppp_xmit_unlock(ppp); } -static DEFINE_PER_CPU(int, ppp_xmit_recursion); - static void ppp_xmit_process(struct ppp *ppp) { local_bh_disable(); - if (unlikely(__this_cpu_read(ppp_xmit_recursion))) + if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; - __this_cpu_inc(ppp_xmit_recursion); + (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp); - __this_cpu_dec(ppp_xmit_recursion); + (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); @@ -1905,7 +1918,7 @@ static void __ppp_channel_push(struct channel *pch) read_lock(&pch->upl); ppp = pch->ppp; if (ppp) - __ppp_xmit_process(ppp); + ppp_xmit_process(ppp); read_unlock(&pch->upl); } } @@ -1914,9 +1927,7 @@ static void ppp_channel_push(struct channel *pch) { local_bh_disable(); - __this_cpu_inc(ppp_xmit_recursion); __ppp_channel_push(pch); - __this_cpu_dec(ppp_xmit_recursion); local_bh_enable(); } @@ -3057,6 +3068,7 @@ static void ppp_destroy_interface(struct ppp *ppp) #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); + free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index d103a1d4fb36..8f572b9f3625 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -768,8 +768,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ u8 *buf; int len; int temp; + int err; u8 iface_no; struct usb_cdc_parsed_header hdr; + u16 curr_ntb_format; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -874,6 +876,32 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ goto error2; } + /* + * Some Huawei devices have been observed to come out of reset in NDP32 mode. + * Let's check if this is the case, and set the device to NDP16 mode again if + * needed. + */ + if (ctx->drvflags & CDC_NCM_FLAG_RESET_NTB16) { + err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, + 0, iface_no, &curr_ntb_format, 2); + if (err < 0) { + goto error2; + } + + if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) { + dev_info(&intf->dev, "resetting NTB format to 16-bit"); + err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_OUT + | USB_RECIP_INTERFACE, + USB_CDC_NCM_NTB16_FORMAT, + iface_no, NULL, 0); + + if (err < 0) + goto error2; + } + } + cdc_ncm_find_endpoints(dev, ctx->data); cdc_ncm_find_endpoints(dev, ctx->control); if (!dev->in || !dev->out || !dev->status) { diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 2680a65cd5e4..63f28908afda 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -80,6 +80,12 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, * be at the end of the frame. */ drvflags |= CDC_NCM_FLAG_NDP_TO_END; + + /* Additionally, it has been reported that some Huawei E3372H devices, with + * firmware version 21.318.01.00.541, come out of reset in NTB32 format mode, hence + * needing to be set to the NTB16 one again. + */ + drvflags |= CDC_NCM_FLAG_RESET_NTB16; ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags); if (ret) goto err; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2dfca96a63b6..340c13484e5c 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -898,6 +898,7 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .set_wol = smsc95xx_ethtool_set_wol, .get_link_ksettings = smsc95xx_get_link_ksettings, .set_link_ksettings = smsc95xx_set_link_ksettings, + .get_ts_info = ethtool_op_get_ts_info, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index ba1c9f93592b..9c51b8be0038 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -311,7 +311,7 @@ struct vmxnet3_intr { u8 num_intrs; /* # of intr vectors */ u8 event_intr_idx; /* idx of the intr vector for event */ u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */ - char event_msi_vector_name[IFNAMSIZ+11]; + char event_msi_vector_name[IFNAMSIZ+17]; #ifdef CONFIG_PCI_MSI struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT]; #endif diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 6e2e760d98b1..0b75def39c6c 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -5704,7 +5704,7 @@ static void rt2800_init_freq_calibration(struct rt2x00_dev *rt2x00dev) static void rt2800_init_bbp_5592_glrt(struct rt2x00_dev *rt2x00dev) { - const u8 glrt_table[] = { + static const u8 glrt_table[] = { 0xE0, 0x1F, 0X38, 0x32, 0x08, 0x28, 0x19, 0x0A, 0xFF, 0x00, /* 128 ~ 137 */ 0x16, 0x10, 0x10, 0x0B, 0x36, 0x2C, 0x26, 0x24, 0x42, 0x36, /* 138 ~ 147 */ 0x30, 0x2D, 0x4C, 0x46, 0x3D, 0x40, 0x3E, 0x42, 0x3D, 0x40, /* 148 ~ 157 */ diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 7cd99b1f8596..75bc08c6838c 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -421,14 +421,15 @@ static void set_badblock(struct badblocks *bb, sector_t s, int num) static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len) { const unsigned int sector_size = 512; - sector_t start_sector; + sector_t start_sector, end_sector; u64 num_sectors; u32 rem; start_sector = div_u64(ns_offset, sector_size); - num_sectors = div_u64_rem(len, sector_size, &rem); + end_sector = div_u64_rem(ns_offset + len, sector_size, &rem); if (rem) - num_sectors++; + end_sector++; + num_sectors = end_sector - start_sector; if (unlikely(num_sectors > (u64)INT_MAX)) { u64 remaining = num_sectors; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cb96f4a7ae3a..3b77cfe5aa1e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -336,7 +336,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl, c.directive.opcode = nvme_admin_directive_recv; c.directive.nsid = cpu_to_le32(nsid); - c.directive.numd = sizeof(*s); + c.directive.numd = cpu_to_le32(sizeof(*s)); c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; c.directive.dtype = NVME_DIR_STREAMS; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d10d2f279d19..8569ee771269 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -539,7 +539,7 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) } #endif -static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) +static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct dma_pool *pool; @@ -556,7 +556,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) length -= (page_size - offset); if (length <= 0) - return true; + return BLK_STS_OK; dma_len -= (page_size - offset); if (dma_len) { @@ -569,7 +569,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) if (length <= page_size) { iod->first_dma = dma_addr; - return true; + return BLK_STS_OK; } nprps = DIV_ROUND_UP(length, page_size); @@ -585,7 +585,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) if (!prp_list) { iod->first_dma = dma_addr; iod->npages = -1; - return false; + return BLK_STS_RESOURCE; } list[0] = prp_list; iod->first_dma = prp_dma; @@ -595,7 +595,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) __le64 *old_prp_list = prp_list; prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) - return false; + return BLK_STS_RESOURCE; list[iod->npages++] = prp_list; prp_list[0] = old_prp_list[i - 1]; old_prp_list[i - 1] = cpu_to_le64(prp_dma); @@ -609,13 +609,29 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) break; if (dma_len > 0) continue; - BUG_ON(dma_len < 0); + if (unlikely(dma_len < 0)) + goto bad_sgl; sg = sg_next(sg); dma_addr = sg_dma_address(sg); dma_len = sg_dma_len(sg); } - return true; + return BLK_STS_OK; + + bad_sgl: + if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n", + blk_rq_payload_bytes(req), iod->nents)) { + for_each_sg(iod->sg, sg, iod->nents, i) { + dma_addr_t phys = sg_phys(sg); + pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " + "dma_address:%pad dma_length:%d\n", i, &phys, + sg->offset, sg->length, + &sg_dma_address(sg), + sg_dma_len(sg)); + } + } + return BLK_STS_IOERR; + } static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, @@ -637,7 +653,8 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, DMA_ATTR_NO_WARN)) goto out; - if (!nvme_setup_prps(dev, req)) + ret = nvme_setup_prps(dev, req); + if (ret != BLK_STS_OK) goto out_unmap; ret = BLK_STS_IOERR; @@ -2282,7 +2299,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) result = nvme_dev_map(dev); if (result) - goto free; + goto put_pci; INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work); @@ -2291,7 +2308,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) result = nvme_setup_prp_pools(dev); if (result) - goto put_pci; + goto unmap; quirks |= check_dell_samsung_bug(pdev); @@ -2308,9 +2325,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) release_pools: nvme_release_prp_pools(dev); + unmap: + nvme_dev_unmap(dev); put_pci: put_device(dev->dev); - nvme_dev_unmap(dev); free: kfree(dev->queues); kfree(dev); @@ -2466,6 +2484,9 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0x0a54), .driver_data = NVME_QUIRK_STRIPE_SIZE | NVME_QUIRK_DEALLOCATE_ZEROES, }, + { PCI_VDEVICE(INTEL, 0x0a55), + .driver_data = NVME_QUIRK_STRIPE_SIZE | + NVME_QUIRK_DEALLOCATE_ZEROES, }, { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index da04df1af231..9fb6e4caddbd 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -19,6 +19,7 @@ #include <linux/string.h> #include <linux/atomic.h> #include <linux/blk-mq.h> +#include <linux/blk-mq-rdma.h> #include <linux/types.h> #include <linux/list.h> #include <linux/mutex.h> @@ -463,14 +464,10 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) ibdev = queue->device->dev; /* - * The admin queue is barely used once the controller is live, so don't - * bother to spread it out. + * Spread I/O queues completion vectors according their queue index. + * Admin queues can always go on completion vector 0. */ - if (idx == 0) - comp_vector = 0; - else - comp_vector = idx % ibdev->num_comp_vectors; - + comp_vector = idx == 0 ? idx : idx - 1; /* +1 for ib_stop_cq */ queue->ib_cq = ib_alloc_cq(ibdev, queue, @@ -611,10 +608,20 @@ out_free_queues: static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl) { struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; + struct ib_device *ibdev = ctrl->device->dev; unsigned int nr_io_queues; int i, ret; nr_io_queues = min(opts->nr_io_queues, num_online_cpus()); + + /* + * we map queues according to the device irq vectors for + * optimal locality so we don't need more queues than + * completion vectors. + */ + nr_io_queues = min_t(unsigned int, nr_io_queues, + ibdev->num_comp_vectors); + ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) return ret; @@ -1498,6 +1505,13 @@ static void nvme_rdma_complete_rq(struct request *rq) nvme_complete_rq(rq); } +static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_rdma_ctrl *ctrl = set->driver_data; + + return blk_mq_rdma_map_queues(set, ctrl->device->dev, 0); +} + static const struct blk_mq_ops nvme_rdma_mq_ops = { .queue_rq = nvme_rdma_queue_rq, .complete = nvme_rdma_complete_rq, @@ -1507,6 +1521,7 @@ static const struct blk_mq_ops nvme_rdma_mq_ops = { .init_hctx = nvme_rdma_init_hctx, .poll = nvme_rdma_poll, .timeout = nvme_rdma_timeout, + .map_queues = nvme_rdma_map_queues, }; static const struct blk_mq_ops nvme_rdma_admin_mq_ops = { @@ -1946,10 +1961,6 @@ static struct nvmf_transport_ops nvme_rdma_transport = { .create_ctrl = nvme_rdma_create_ctrl, }; -static void nvme_rdma_add_one(struct ib_device *ib_device) -{ -} - static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data) { struct nvme_rdma_ctrl *ctrl; @@ -1971,7 +1982,6 @@ static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data) static struct ib_client nvme_rdma_ib_client = { .name = "nvme_rdma", - .add = nvme_rdma_add_one, .remove = nvme_rdma_remove_one }; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 35f930db3c02..2d7a98ab53fb 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -168,11 +168,21 @@ out: nvmet_req_complete(req, status); } +static void copy_and_pad(char *dst, int dst_len, const char *src, int src_len) +{ + int len = min(src_len, dst_len); + + memcpy(dst, src, len); + if (dst_len > len) + memset(dst + len, ' ', dst_len - len); +} + static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; u16 status = 0; + const char model[] = "Linux"; id = kzalloc(sizeof(*id), GFP_KERNEL); if (!id) { @@ -184,8 +194,10 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->vid = 0; id->ssvid = 0; - memset(id->sn, ' ', sizeof(id->sn)); - snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial); + bin2hex(id->sn, &ctrl->subsys->serial, + min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); + copy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1); + copy_and_pad(id->fr, sizeof(id->fr), UTS_RELEASE, strlen(UTS_RELEASE)); memset(id->mn, ' ', sizeof(id->mn)); strncpy((char *)id->mn, "Linux", sizeof(id->mn)); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index a358ecd93e11..0a0067e771f5 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -650,7 +650,7 @@ out_unlock: CONFIGFS_ATTR(nvmet_subsys_, attr_allow_any_host); -static ssize_t nvmet_subsys_version_show(struct config_item *item, +static ssize_t nvmet_subsys_attr_version_show(struct config_item *item, char *page) { struct nvmet_subsys *subsys = to_subsys(item); @@ -666,7 +666,7 @@ static ssize_t nvmet_subsys_version_show(struct config_item *item, (int)NVME_MINOR(subsys->ver)); } -static ssize_t nvmet_subsys_version_store(struct config_item *item, +static ssize_t nvmet_subsys_attr_version_store(struct config_item *item, const char *page, size_t count) { struct nvmet_subsys *subsys = to_subsys(item); @@ -684,11 +684,33 @@ static ssize_t nvmet_subsys_version_store(struct config_item *item, return count; } -CONFIGFS_ATTR(nvmet_subsys_, version); +CONFIGFS_ATTR(nvmet_subsys_, attr_version); + +static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item, + char *page) +{ + struct nvmet_subsys *subsys = to_subsys(item); + + return snprintf(page, PAGE_SIZE, "%llx\n", subsys->serial); +} + +static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_subsys *subsys = to_subsys(item); + + down_write(&nvmet_config_sem); + sscanf(page, "%llx\n", &subsys->serial); + up_write(&nvmet_config_sem); + + return count; +} +CONFIGFS_ATTR(nvmet_subsys_, attr_serial); static struct configfs_attribute *nvmet_subsys_attrs[] = { &nvmet_subsys_attr_attr_allow_any_host, - &nvmet_subsys_attr_version, + &nvmet_subsys_attr_attr_version, + &nvmet_subsys_attr_attr_serial, NULL, }; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b5b4ac103748..f4b02bb4a1a8 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -767,9 +767,6 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); - /* generate a random serial number as our controllers are ephemeral: */ - get_random_bytes(&ctrl->serial, sizeof(ctrl->serial)); - kref_init(&ctrl->ref); ctrl->subsys = subsys; @@ -928,6 +925,8 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, return NULL; subsys->ver = NVME_VS(1, 3, 0); /* NVMe 1.3.0 */ + /* generate a random serial number as our controllers are ephemeral: */ + get_random_bytes(&subsys->serial, sizeof(subsys->serial)); switch (type) { case NVME_NQN_NVME: diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 1e6dcc241b3c..d5801c150b1c 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1174,14 +1174,14 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport, */ if (iod->rqstdatalen < FCNVME_LSDESC_CRA_RQST_MINLEN) ret = VERR_CR_ASSOC_LEN; - else if (rqst->desc_list_len < - cpu_to_be32(FCNVME_LSDESC_CRA_RQST_MIN_LISTLEN)) + else if (be32_to_cpu(rqst->desc_list_len) < + FCNVME_LSDESC_CRA_RQST_MIN_LISTLEN) ret = VERR_CR_ASSOC_RQST_LEN; else if (rqst->assoc_cmd.desc_tag != cpu_to_be32(FCNVME_LSDESC_CREATE_ASSOC_CMD)) ret = VERR_CR_ASSOC_CMD; - else if (rqst->assoc_cmd.desc_len < - cpu_to_be32(FCNVME_LSDESC_CRA_CMD_DESC_MIN_DESCLEN)) + else if (be32_to_cpu(rqst->assoc_cmd.desc_len) < + FCNVME_LSDESC_CRA_CMD_DESC_MIN_DESCLEN) ret = VERR_CR_ASSOC_CMD_LEN; else if (!rqst->assoc_cmd.ersp_ratio || (be16_to_cpu(rqst->assoc_cmd.ersp_ratio) >= diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 747bbdb4f9c6..e3b244c7e443 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -112,7 +112,6 @@ struct nvmet_ctrl { struct mutex lock; u64 cap; - u64 serial; u32 cc; u32 csts; @@ -152,6 +151,7 @@ struct nvmet_subsys { u16 max_qid; u64 ver; + u64 serial; char *subsysnqn; struct config_group group; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 56a4cba690b5..76d2bb793afe 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1510,10 +1510,6 @@ static struct nvmet_fabrics_ops nvmet_rdma_ops = { .delete_ctrl = nvmet_rdma_delete_ctrl, }; -static void nvmet_rdma_add_one(struct ib_device *ib_device) -{ -} - static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data) { struct nvmet_rdma_queue *queue; @@ -1534,7 +1530,6 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data static struct ib_client nvmet_rdma_ib_client = { .name = "nvmet_rdma", - .add = nvmet_rdma_add_one, .remove = nvmet_rdma_remove_one }; diff --git a/drivers/nvmem/rockchip-efuse.c b/drivers/nvmem/rockchip-efuse.c index a0d4ede9b8fc..63e3eb55f3ac 100644 --- a/drivers/nvmem/rockchip-efuse.c +++ b/drivers/nvmem/rockchip-efuse.c @@ -170,7 +170,7 @@ static const struct of_device_id rockchip_efuse_match[] = { .data = (void *)&rockchip_rk3288_efuse_read, }, { - .compatible = "rockchip,rk322x-efuse", + .compatible = "rockchip,rk3228-efuse", .data = (void *)&rockchip_rk3288_efuse_read, }, { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index d51e8738f9c2..4450feaf5c00 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1307,6 +1307,7 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner, drv->driver.bus = &pci_bus_type; drv->driver.owner = owner; drv->driver.mod_name = mod_name; + drv->driver.groups = drv->groups; spin_lock_init(&drv->dynids.lock); INIT_LIST_HEAD(&drv->dynids.list); diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 077f62e208aa..6a4367cc9caa 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3401,9 +3401,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, if (is_write) { req_flags |= SISL_REQ_FLAGS_HOST_WRITE; - rc = copy_from_user(kbuf, ubuf, ulen); - if (unlikely(rc)) + if (copy_from_user(kbuf, ubuf, ulen)) { + rc = -EFAULT; goto out; + } } } @@ -3431,8 +3432,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, goto out; } - if (ulen && !is_write) - rc = copy_to_user(ubuf, kbuf, ulen); + if (ulen && !is_write) { + if (copy_to_user(ubuf, kbuf, ulen)) + rc = -EFAULT; + } out: kfree(buf); dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 551d103c27f1..2bfea7082e3a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -1693,7 +1693,7 @@ static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba, static int parse_trans_tx_err_code_v2_hw(u32 err_msk) { - const u8 trans_tx_err_code_prio[] = { + static const u8 trans_tx_err_code_prio[] = { TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS, TRANS_TX_ERR_PHY_NOT_ENABLE, TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION, @@ -1738,7 +1738,7 @@ static int parse_trans_tx_err_code_v2_hw(u32 err_msk) static int parse_trans_rx_err_code_v2_hw(u32 err_msk) { - const u8 trans_rx_err_code_prio[] = { + static const u8 trans_rx_err_code_prio[] = { TRANS_RX_ERR_WITH_RXFRAME_CRC_ERR, TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR, TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM, @@ -1784,7 +1784,7 @@ static int parse_trans_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_tx_err_code_v2_hw(u32 err_msk) { - const u8 dma_tx_err_code_prio[] = { + static const u8 dma_tx_err_code_prio[] = { DMA_TX_UNEXP_XFER_ERR, DMA_TX_UNEXP_RETRANS_ERR, DMA_TX_XFER_LEN_OVERFLOW, @@ -1810,7 +1810,7 @@ static int parse_dma_tx_err_code_v2_hw(u32 err_msk) static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) { - const u8 sipc_rx_err_code_prio[] = { + static const u8 sipc_rx_err_code_prio[] = { SIPC_RX_FIS_STATUS_ERR_BIT_VLD, SIPC_RX_PIO_WRSETUP_STATUS_DRQ_ERR, SIPC_RX_FIS_STATUS_BSY_BIT_ERR, @@ -1836,7 +1836,7 @@ static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_rx_err_code_v2_hw(u32 err_msk) { - const u8 dma_rx_err_code_prio[] = { + static const u8 dma_rx_err_code_prio[] = { DMA_RX_UNKNOWN_FRM_ERR, DMA_RX_DATA_LEN_OVERFLOW, DMA_RX_DATA_LEN_UNDERFLOW, diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 47f66e949745..ed197bc8e801 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -213,7 +213,7 @@ static void sci_task_request_build_ssp_task_iu(struct isci_request *ireq) * @task_context: * */ -static void scu_ssp_reqeust_construct_task_context( +static void scu_ssp_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -425,7 +425,7 @@ static void scu_ssp_io_request_construct_task_context(struct isci_request *ireq, u8 prot_type = scsi_get_prot_type(scmd); u8 prot_op = scsi_get_prot_op(scmd); - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->ssp_command_iu_length = sizeof(struct ssp_cmd_iu) / sizeof(u32); @@ -472,7 +472,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire { struct scu_task_context *task_context = ireq->tc; - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->control_frame = 1; task_context->priority = SCU_TASK_PRIORITY_HIGH; @@ -495,7 +495,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire * the command buffer is complete. none Revisit task context construction to * determine what is common for SSP/SMP/STP task context structures. */ -static void scu_sata_reqeust_construct_task_context( +static void scu_sata_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -562,7 +562,7 @@ static void scu_stp_raw_request_construct_task_context(struct isci_request *ireq { struct scu_task_context *task_context = ireq->tc; - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); task_context->control_frame = 0; task_context->priority = SCU_TASK_PRIORITY_NORMAL; @@ -613,7 +613,7 @@ static void sci_stp_optimized_request_construct(struct isci_request *ireq, struct scu_task_context *task_context = ireq->tc; /* Build the STP task context structure */ - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); /* Copy over the SGL elements */ sci_request_build_sgl(ireq); @@ -1401,7 +1401,7 @@ static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_re * @data_buffer: The buffer of data to be copied. * @length: The length of the data transfer. * - * Copy the data from the buffer for the length specified to the IO reqeust SGL + * Copy the data from the buffer for the length specified to the IO request SGL * specified data region. enum sci_status */ static enum sci_status diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index fd501f8dbb11..8660f923ace0 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -573,7 +573,7 @@ static void fc_disc_gpn_ft_resp(struct fc_seq *sp, struct fc_frame *fp, event = DISC_EV_FAILED; } if (error) - fc_disc_error(disc, fp); + fc_disc_error(disc, ERR_PTR(error)); else if (event != DISC_EV_NONE) fc_disc_done(disc, event); fc_frame_free(fp); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index b58bba4604e8..7786c97e033f 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1227,7 +1227,7 @@ static void qedf_rport_event_handler(struct fc_lport *lport, if (rdata->spp_type != FC_TYPE_FCP) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, - "Not offlading since since spp type isn't FCP\n"); + "Not offloading since spp type isn't FCP\n"); break; } if (!(rdata->ids.roles & FC_RPORT_ROLE_FCP_TARGET)) { diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index 32632c9b2276..91d2f51c351b 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -23,11 +23,17 @@ #include <linux/qed/qed_iscsi_if.h> #include <linux/qed/qed_ll2_if.h> #include "qedi_version.h" +#include "qedi_nvm_iscsi_cfg.h" #define QEDI_MODULE_NAME "qedi" struct qedi_endpoint; +#ifndef GET_FIELD2 +#define GET_FIELD2(value, name) \ + (((value) & (name ## _MASK)) >> (name ## _OFFSET)) +#endif + /* * PCI function probe defines */ @@ -66,6 +72,11 @@ struct qedi_endpoint; #define QEDI_HW_DMA_BOUNDARY 0xfff #define QEDI_PATH_HANDLE 0xFE0000000UL +enum qedi_nvm_tgts { + QEDI_NVM_TGT_PRI, + QEDI_NVM_TGT_SEC, +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -283,6 +294,8 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; + struct nvm_iscsi_cfg *iscsi_cfg; + dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; u16 bdq_prod_idx; @@ -337,6 +350,10 @@ struct qedi_ctx { bool use_fast_sge; atomic_t num_offloads; +#define SYSFS_FLAG_FW_SEL_BOOT 2 +#define IPV6_LEN 41 +#define IPV4_LEN 17 + struct iscsi_boot_kset *boot_kset; }; struct qedi_work { diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 19254bd739d9..93d54acd4a22 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -1411,7 +1411,7 @@ static void qedi_tmf_work(struct work_struct *work) list_work = kzalloc(sizeof(*list_work), GFP_ATOMIC); if (!list_work) { - QEDI_ERR(&qedi->dbg_ctx, "Memory alloction failed\n"); + QEDI_ERR(&qedi->dbg_ctx, "Memory allocation failed\n"); goto abort_ret; } diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 5f5a4ef2e529..2c3783684815 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/if_vlan.h> #include <linux/cpu.h> +#include <linux/iscsi_boot_sysfs.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> @@ -1143,6 +1144,30 @@ exit_setup_int: return rc; } +static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + if (qedi->iscsi_cfg) + dma_free_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + qedi->iscsi_cfg, qedi->nvm_buf_dma); +} + +static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + &qedi->nvm_buf_dma, GFP_KERNEL); + if (!qedi->iscsi_cfg) { + QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); + return -ENOMEM; + } + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + qedi->nvm_buf_dma); + + return 0; +} + static void qedi_free_bdq(struct qedi_ctx *qedi) { int i; @@ -1183,6 +1208,7 @@ static void qedi_free_global_queues(struct qedi_ctx *qedi) kfree(gl[i]); } qedi_free_bdq(qedi); + qedi_free_nvm_iscsi_cfg(qedi); } static int qedi_alloc_bdq(struct qedi_ctx *qedi) @@ -1309,6 +1335,11 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (rc) goto mem_alloc_failure; + /* Allocate DMA coherent buffers for NVM_ISCSI_CFG */ + rc = qedi_alloc_nvm_iscsi_cfg(qedi); + if (rc) + goto mem_alloc_failure; + /* Allocate a CQ and an associated PBL for each MSI-X * vector. */ @@ -1671,6 +1702,387 @@ void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu) qedi_ops->ll2->start(qedi->cdev, ¶ms); } +/** + * qedi_get_nvram_block: - Scan through the iSCSI NVRAM block (while accounting + * for gaps) for the matching absolute-pf-id of the QEDI device. + */ +static struct nvm_iscsi_block * +qedi_get_nvram_block(struct qedi_ctx *qedi) +{ + int i; + u8 pf; + u32 flags; + struct nvm_iscsi_block *block; + + pf = qedi->dev_info.common.abs_pf_id; + block = &qedi->iscsi_cfg->block[0]; + for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { + flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> + NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; + if (flags & (NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY | + NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED) && + (pf == (block->id & NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK) + >> NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET)) + return block; + } + return NULL; +} + +static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc = 1; + u32 ipv6_en, dhcp_en, ip_len; + struct nvm_iscsi_block *block; + char *fmt, *ip, *sub, *gw; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + dhcp_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED; + /* Static IP assignments. */ + fmt = ipv6_en ? "%pI6\n" : "%pI4\n"; + ip = ipv6_en ? initiator->ipv6.addr.byte : initiator->ipv4.addr.byte; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + sub = ipv6_en ? initiator->ipv6.subnet_mask.byte : + initiator->ipv4.subnet_mask.byte; + gw = ipv6_en ? initiator->ipv6.gateway.byte : + initiator->ipv4.gateway.byte; + /* DHCP IP adjustments. */ + fmt = dhcp_en ? "%s\n" : fmt; + if (dhcp_en) { + ip = ipv6_en ? "0::0" : "0.0.0.0"; + sub = ip; + gw = ip; + ip_len = ipv6_en ? 5 : 8; + } + + switch (type) { + case ISCSI_BOOT_ETH_IP_ADDR: + rc = snprintf(str, ip_len, fmt, ip); + break; + case ISCSI_BOOT_ETH_SUBNET_MASK: + rc = snprintf(str, ip_len, fmt, sub); + break; + case ISCSI_BOOT_ETH_GATEWAY: + rc = snprintf(str, ip_len, fmt, gw); + break; + case ISCSI_BOOT_ETH_FLAGS: + rc = snprintf(str, 3, "%hhd\n", + SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_ETH_INDEX: + rc = snprintf(str, 3, "0\n"); + break; + case ISCSI_BOOT_ETH_MAC: + rc = sysfs_format_mac(str, qedi->mac, ETH_ALEN); + break; + case ISCSI_BOOT_ETH_VLAN: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(initiator->generic_cont0, + NVM_ISCSI_CFG_INITIATOR_VLAN)); + break; + case ISCSI_BOOT_ETH_ORIGIN: + if (dhcp_en) + rc = snprintf(str, 3, "3\n"); + break; + default: + rc = 0; + break; + } + + return rc; +} + +static umode_t qedi_eth_get_attr_visibility(void *data, int type) +{ + int rc = 1; + + switch (type) { + case ISCSI_BOOT_ETH_FLAGS: + case ISCSI_BOOT_ETH_MAC: + case ISCSI_BOOT_ETH_INDEX: + case ISCSI_BOOT_ETH_IP_ADDR: + case ISCSI_BOOT_ETH_SUBNET_MASK: + case ISCSI_BOOT_ETH_GATEWAY: + case ISCSI_BOOT_ETH_ORIGIN: + case ISCSI_BOOT_ETH_VLAN: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc; + struct nvm_iscsi_block *block; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + initiator->initiator_name.byte); + break; + default: + rc = 0; + break; + } + return rc; +} + +static umode_t qedi_ini_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t +qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, + char *buf, enum qedi_nvm_tgts idx) +{ + char *str = buf; + int rc = 1; + u32 ctrl_flags, ipv6_en, chap_en, mchap_en, ip_len; + struct nvm_iscsi_block *block; + char *chap_name, *chap_secret; + char *mchap_name, *mchap_secret; + + block = qedi_get_nvram_block(qedi); + if (!block) + goto exit_show_tgt_info; + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Port:%d, tgt_idx:%d\n", + GET_FIELD2(block->id, NVM_ISCSI_CFG_BLK_MAPPED_PF_ID), idx); + + ctrl_flags = block->target[idx].ctrl_flags & + NVM_ISCSI_CFG_TARGET_ENABLED; + + if (!ctrl_flags) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Target disabled\n"); + goto exit_show_tgt_info; + } + + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + chap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_ENABLED; + chap_name = chap_en ? block->initiator.chap_name.byte : NULL; + chap_secret = chap_en ? block->initiator.chap_password.byte : NULL; + + mchap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED; + mchap_name = mchap_en ? block->target[idx].chap_name.byte : NULL; + mchap_secret = mchap_en ? block->target[idx].chap_password.byte : NULL; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + block->target[idx].target_name.byte); + break; + case ISCSI_BOOT_TGT_IP_ADDR: + if (ipv6_en) + rc = snprintf(str, ip_len, "%pI6\n", + block->target[idx].ipv6_addr.byte); + else + rc = snprintf(str, ip_len, "%pI4\n", + block->target[idx].ipv4_addr.byte); + break; + case ISCSI_BOOT_TGT_PORT: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(block->target[idx].generic_cont0, + NVM_ISCSI_CFG_TARGET_TCP_PORT)); + break; + case ISCSI_BOOT_TGT_LUN: + rc = snprintf(str, 22, "%.*d\n", + block->target[idx].lun.value[1], + block->target[idx].lun.value[0]); + break; + case ISCSI_BOOT_TGT_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + chap_name); + break; + case ISCSI_BOOT_TGT_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + chap_secret); + break; + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + mchap_name); + break; + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + mchap_secret); + break; + case ISCSI_BOOT_TGT_FLAGS: + rc = snprintf(str, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_TGT_NIC_ASSOC: + rc = snprintf(str, 3, "0\n"); + break; + default: + rc = 0; + break; + } + +exit_show_tgt_info: + return rc; +} + +static ssize_t qedi_show_boot_tgt_pri_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_PRI); +} + +static ssize_t qedi_show_boot_tgt_sec_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_SEC); +} + +static umode_t qedi_tgt_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + case ISCSI_BOOT_TGT_IP_ADDR: + case ISCSI_BOOT_TGT_PORT: + case ISCSI_BOOT_TGT_LUN: + case ISCSI_BOOT_TGT_CHAP_NAME: + case ISCSI_BOOT_TGT_CHAP_SECRET: + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + case ISCSI_BOOT_TGT_NIC_ASSOC: + case ISCSI_BOOT_TGT_FLAGS: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static void qedi_boot_release(void *data) +{ + struct qedi_ctx *qedi = data; + + scsi_host_put(qedi->shost); +} + +static int qedi_get_boot_info(struct qedi_ctx *qedi) +{ + int ret = 1; + u16 len; + + len = sizeof(struct nvm_iscsi_cfg); + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "Get NVM iSCSI CFG image\n"); + ret = qedi_ops->common->nvm_get_image(qedi->cdev, + QED_NVM_IMAGE_ISCSI_CFG, + (char *)qedi->iscsi_cfg, len); + if (ret) + QEDI_ERR(&qedi->dbg_ctx, + "Could not get NVM image. ret = %d\n", ret); + + return ret; +} + +static int qedi_setup_boot_info(struct qedi_ctx *qedi) +{ + struct iscsi_boot_kobj *boot_kobj; + + if (qedi_get_boot_info(qedi)) + return -EPERM; + + qedi->boot_kset = iscsi_boot_create_host_kset(qedi->shost->host_no); + if (!qedi->boot_kset) + goto kset_free; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 0, qedi, + qedi_show_boot_tgt_pri_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 1, qedi, + qedi_show_boot_tgt_sec_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_initiator(qedi->boot_kset, 0, qedi, + qedi_show_boot_ini_info, + qedi_ini_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_ethernet(qedi->boot_kset, 0, qedi, + qedi_show_boot_eth_info, + qedi_eth_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + return 0; + +put_host: + scsi_host_put(qedi->shost); +kset_free: + iscsi_boot_destroy_kset(qedi->boot_kset); + return -ENOMEM; +} + static void __qedi_remove(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi = pci_get_drvdata(pdev); @@ -1724,6 +2136,9 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) qedi->ll2_recv_thread = NULL; } qedi_ll2_free_skbs(qedi); + + if (qedi->boot_kset) + iscsi_boot_destroy_kset(qedi->boot_kset); } } @@ -1967,6 +2382,10 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) /* F/w needs 1st task context memory entry for performance */ set_bit(QEDI_RESERVE_TASK_ID, qedi->task_idx_map); atomic_set(&qedi->num_offloads, 0); + + if (qedi_setup_boot_info(qedi)) + QEDI_ERR(&qedi->dbg_ctx, + "No iSCSI boot target configured\n"); } return 0; diff --git a/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h new file mode 100644 index 000000000000..df39b69b366d --- /dev/null +++ b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h @@ -0,0 +1,210 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef NVM_ISCSI_CFG_H +#define NVM_ISCSI_CFG_H + +#define NUM_OF_ISCSI_TARGET_PER_PF 4 /* Defined as per the + * ISCSI IBFT constraint + */ +#define NUM_OF_ISCSI_PF_SUPPORTED 4 /* One PF per Port - + * assuming 4 port card + */ + +#define NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN 256 + +union nvm_iscsi_dhcp_vendor_id { + u32 value[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_IPV4_ADDR_BYTE_LEN 4 +union nvm_iscsi_ipv4_addr { + u32 addr; + u8 byte[NVM_ISCSI_IPV4_ADDR_BYTE_LEN]; +}; + +#define NVM_ISCSI_IPV6_ADDR_BYTE_LEN 16 +union nvm_iscsi_ipv6_addr { + u32 addr[4]; + u8 byte[NVM_ISCSI_IPV6_ADDR_BYTE_LEN]; +}; + +struct nvm_iscsi_initiator_ipv4 { + union nvm_iscsi_ipv4_addr addr; /* 0x0 */ + union nvm_iscsi_ipv4_addr subnet_mask; /* 0x4 */ + union nvm_iscsi_ipv4_addr gateway; /* 0x8 */ + union nvm_iscsi_ipv4_addr primary_dns; /* 0xC */ + union nvm_iscsi_ipv4_addr secondary_dns; /* 0x10 */ + union nvm_iscsi_ipv4_addr dhcp_addr; /* 0x14 */ + + union nvm_iscsi_ipv4_addr isns_server; /* 0x18 */ + union nvm_iscsi_ipv4_addr slp_server; /* 0x1C */ + union nvm_iscsi_ipv4_addr primay_radius_server; /* 0x20 */ + union nvm_iscsi_ipv4_addr secondary_radius_server; /* 0x24 */ + + union nvm_iscsi_ipv4_addr rsvd[4]; /* 0x28 */ +}; + +struct nvm_iscsi_initiator_ipv6 { + union nvm_iscsi_ipv6_addr addr; /* 0x0 */ + union nvm_iscsi_ipv6_addr subnet_mask; /* 0x10 */ + union nvm_iscsi_ipv6_addr gateway; /* 0x20 */ + union nvm_iscsi_ipv6_addr primary_dns; /* 0x30 */ + union nvm_iscsi_ipv6_addr secondary_dns; /* 0x40 */ + union nvm_iscsi_ipv6_addr dhcp_addr; /* 0x50 */ + + union nvm_iscsi_ipv6_addr isns_server; /* 0x60 */ + union nvm_iscsi_ipv6_addr slp_server; /* 0x70 */ + union nvm_iscsi_ipv6_addr primay_radius_server; /* 0x80 */ + union nvm_iscsi_ipv6_addr secondary_radius_server; /* 0x90 */ + + union nvm_iscsi_ipv6_addr rsvd[3]; /* 0xA0 */ + + u32 config; /* 0xD0 */ +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_MASK 0x000000FF +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_OFFSET 0 + + u32 rsvd_1[3]; +}; + +#define NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN 256 +union nvm_iscsi_name { + u32 value[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN 256 +union nvm_iscsi_chap_name { + u32 value[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN 16 /* md5 need per RFC1996 + * is 16 octets + */ +union nvm_iscsi_chap_password { + u32 value[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN]; +}; + +union nvm_iscsi_lun { + u8 byte[8]; + u32 value[2]; +}; + +struct nvm_iscsi_generic { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_GEN_CHAP_ENABLED BIT(0) +#define NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED BIT(1) +#define NVM_ISCSI_CFG_GEN_DHCP_ISCSI_CONFIG_ENABLED BIT(2) +#define NVM_ISCSI_CFG_GEN_IPV6_ENABLED BIT(3) +#define NVM_ISCSI_CFG_GEN_IPV4_FALLBACK_ENABLED BIT(4) +#define NVM_ISCSI_CFG_GEN_ISNS_WORLD_LOGIN BIT(5) +#define NVM_ISCSI_CFG_GEN_ISNS_SELECTIVE_LOGIN BIT(6) +#define NVM_ISCSI_CFG_GEN_ADDR_REDIRECT_ENABLED BIT(7) +#define NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED BIT(8) + + u32 timeout; /* 0x4 */ +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_OFFSET 0 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_OFFSET 16 + + union nvm_iscsi_dhcp_vendor_id dhcp_vendor_id; /* 0x8 */ + u32 rsvd[62]; /* 0x108 */ +}; + +struct nvm_iscsi_initiator { + struct nvm_iscsi_initiator_ipv4 ipv4; /* 0x0 */ + struct nvm_iscsi_initiator_ipv6 ipv6; /* 0x38 */ + + union nvm_iscsi_name initiator_name; /* 0x118 */ + union nvm_iscsi_chap_name chap_name; /* 0x218 */ + union nvm_iscsi_chap_password chap_password; /* 0x318 */ + + u32 generic_cont0; /* 0x398 */ +#define NVM_ISCSI_CFG_INITIATOR_VLAN_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_INITIATOR_VLAN_OFFSET 0 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_MASK 0x00030000 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_OFFSET 16 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4 1 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_6 2 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4_AND_6 3 + + u32 ctrl_flags; +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_PRIORITY_V6 BIT(0) +#define NVM_ISCSI_CFG_INITIATOR_VLAN_ENABLED BIT(1) + + u32 rsvd[116]; /* 0x32C */ +}; + +struct nvm_iscsi_target { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_TARGET_ENABLED BIT(0) +#define NVM_ISCSI_CFG_BOOT_TIME_LOGIN_STATUS BIT(1) + + u32 generic_cont0; /* 0x4 */ +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_OFFSET 0 + + u32 ip_ver; +#define NVM_ISCSI_CFG_IPv4 4 +#define NVM_ISCSI_CFG_IPv6 6 + + u32 rsvd_1[7]; /* 0x24 */ + union nvm_iscsi_ipv4_addr ipv4_addr; /* 0x28 */ + union nvm_iscsi_ipv6_addr ipv6_addr; /* 0x2C */ + union nvm_iscsi_lun lun; /* 0x3C */ + + union nvm_iscsi_name target_name; /* 0x44 */ + union nvm_iscsi_chap_name chap_name; /* 0x144 */ + union nvm_iscsi_chap_password chap_password; /* 0x244 */ + + u32 rsvd_2[107]; /* 0x2C4 */ +}; + +struct nvm_iscsi_block { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK 0x0000000F +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET 0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK 0x00000FF0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET 4 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY BIT(0) +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED BIT(1) + + u32 rsvd_1[5]; /* 0x4 */ + + struct nvm_iscsi_generic generic; /* 0x18 */ + struct nvm_iscsi_initiator initiator; /* 0x218 */ + struct nvm_iscsi_target target[NUM_OF_ISCSI_TARGET_PER_PF]; + /* 0x718 */ + + u32 rsvd_2[58]; /* 0x1718 */ + /* total size - 0x1800 - 6K block */ +}; + +struct nvm_iscsi_cfg { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR_MASK 0x000000FF +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR_MASK 0x0000FF00 +#define NVM_ISCSI_CFG_BLK_SIGNATURE_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_BLK_SIGNATURE 0x49430000 /* IC - Iscsi + * Config + */ + +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR 0 +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR 10 +#define NVM_ISCSI_CFG_BLK_VERSION ((NVM_ISCSI_CFG_BLK_VERSION_MAJOR << 8) | \ + NVM_ISCSI_CFG_BLK_VERSION_MINOR) + + struct nvm_iscsi_block block[NUM_OF_ISCSI_PF_SUPPORTED]; /* 0x4 */ +}; + +#endif diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index c2dc836dc484..e101cd3043b9 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3727,7 +3727,7 @@ static struct qla_tgt_cmd *qlt_ctio_to_cmd(struct scsi_qla_host *vha, h &= QLA_CMD_HANDLE_MASK; if (h != QLA_TGT_NULL_HANDLE) { - if (unlikely(h > req->num_outstanding_cmds)) { + if (unlikely(h >= req->num_outstanding_cmds)) { ql_dbg(ql_dbg_tgt, vha, 0xe052, "qla_target(%d): Wrong handle %x received\n", vha->vp_idx, handle); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 21225d62b0c1..1e82d4128a84 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -758,8 +758,11 @@ static bool sg_is_valid_dxfer(sg_io_hdr_t *hp) if (hp->dxferp || hp->dxfer_len > 0) return false; return true; - case SG_DXFER_TO_DEV: case SG_DXFER_FROM_DEV: + if (hp->dxfer_len < 0) + return false; + return true; + case SG_DXFER_TO_DEV: case SG_DXFER_TO_FROM_DEV: if (!hp->dxferp || hp->dxfer_len == 0) return false; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 8b93197daefe..9be211d68b15 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -837,6 +837,7 @@ static struct scsi_host_template virtscsi_host_template_multi = { .eh_abort_handler = virtscsi_abort, .eh_device_reset_handler = virtscsi_device_reset, .eh_timed_out = virtscsi_eh_timed_out, + .slave_alloc = virtscsi_device_alloc, .can_queue = 1024, .dma_boundary = UINT_MAX, diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index 2afe3597982e..f4b7a98a7913 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -134,7 +134,6 @@ struct apid_data { * @spmic: SPMI controller object * @ver_ops: version dependent operations. * @ppid_to_apid in-memory copy of PPID -> channel (APID) mapping table. - * v2 only. */ struct spmi_pmic_arb { void __iomem *rd_base; @@ -1016,6 +1015,13 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev) goto err_put_ctrl; } + pa->ppid_to_apid = devm_kcalloc(&ctrl->dev, PMIC_ARB_MAX_PPID, + sizeof(*pa->ppid_to_apid), GFP_KERNEL); + if (!pa->ppid_to_apid) { + err = -ENOMEM; + goto err_put_ctrl; + } + hw_ver = readl_relaxed(core + PMIC_ARB_VERSION); if (hw_ver < PMIC_ARB_VERSION_V2_MIN) { @@ -1048,15 +1054,6 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev) err = PTR_ERR(pa->wr_base); goto err_put_ctrl; } - - pa->ppid_to_apid = devm_kcalloc(&ctrl->dev, - PMIC_ARB_MAX_PPID, - sizeof(*pa->ppid_to_apid), - GFP_KERNEL); - if (!pa->ppid_to_apid) { - err = -ENOMEM; - goto err_put_ctrl; - } } dev_info(&ctrl->dev, "PMIC arbiter version %s (0x%x)\n", diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 2b9b0941d9eb..6d23226e5f69 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -365,11 +365,23 @@ static int spmi_drv_remove(struct device *dev) return 0; } +static int spmi_drv_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + int ret; + + ret = of_device_uevent_modalias(dev, env); + if (ret != -ENODEV) + return ret; + + return 0; +} + static struct bus_type spmi_bus_type = { .name = "spmi", .match = spmi_device_match, .probe = spmi_drv_probe, .remove = spmi_drv_remove, + .uevent = spmi_drv_uevent, }; /** diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 268d4e6ef48a..ef28a1cb64ae 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -110,4 +110,6 @@ source "drivers/staging/ccree/Kconfig" source "drivers/staging/typec/Kconfig" +source "drivers/staging/vboxvideo/Kconfig" + endif # STAGING diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index b93e6f5f0f6e..2918580bdb9e 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -44,3 +44,4 @@ obj-$(CONFIG_KS7010) += ks7010/ obj-$(CONFIG_GREYBUS) += greybus/ obj-$(CONFIG_BCM2835_VCHIQ) += vc04_services/ obj-$(CONFIG_CRYPTO_DEV_CCREE) += ccree/ +obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/ diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index b2e382888981..2f7bfc1c59e5 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -3116,8 +3116,7 @@ static void ni_ao_cmd_set_update(struct comedi_device *dev, /* following line: 2-1 per STC */ ni_stc_writel(dev, 1, NISTC_AO_UI_LOADA_REG); ni_stc_writew(dev, NISTC_AO_CMD1_UI_LOAD, NISTC_AO_CMD1_REG); - /* following line: N-1 per STC */ - ni_stc_writel(dev, trigvar - 1, NISTC_AO_UI_LOADA_REG); + ni_stc_writel(dev, trigvar, NISTC_AO_UI_LOADA_REG); } else { /* TRIG_EXT */ /* FIXME: assert scan_begin_arg != 0, ret failure otherwise */ devpriv->ao_cmd2 |= NISTC_AO_CMD2_BC_GATE_ENA; diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c index 85b242ec5f9b..8fc191d99927 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -1640,8 +1640,13 @@ kiblnd_send(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg) ibmsg = tx->tx_msg; ibmsg->ibm_u.immediate.ibim_hdr = *hdr; - copy_from_iter(&ibmsg->ibm_u.immediate.ibim_payload, IBLND_MSG_SIZE, - &from); + rc = copy_from_iter(&ibmsg->ibm_u.immediate.ibim_payload, payload_nob, + &from); + if (rc != payload_nob) { + kiblnd_pool_free_node(&tx->tx_pool->tpo_pool, &tx->tx_list); + return -EFAULT; + } + nob = offsetof(struct kib_immediate_msg, ibim_payload[payload_nob]); kiblnd_init_tx_msg(ni, tx, IBLND_MSG_IMMEDIATE, nob); @@ -1741,8 +1746,14 @@ kiblnd_recv(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg, break; } - copy_to_iter(&rxmsg->ibm_u.immediate.ibim_payload, - IBLND_MSG_SIZE, to); + rc = copy_to_iter(&rxmsg->ibm_u.immediate.ibim_payload, rlen, + to); + if (rc != rlen) { + rc = -EFAULT; + break; + } + + rc = 0; lnet_finalize(ni, lntmsg, 0); break; diff --git a/drivers/staging/rtl8188eu/core/rtw_cmd.c b/drivers/staging/rtl8188eu/core/rtw_cmd.c index 002d09159896..a69007ef77bf 100644 --- a/drivers/staging/rtl8188eu/core/rtw_cmd.c +++ b/drivers/staging/rtl8188eu/core/rtw_cmd.c @@ -132,7 +132,7 @@ void rtw_free_cmd_obj(struct cmd_obj *pcmd) kfree(pcmd->parmbuf); } - if (!pcmd->rsp) { + if (pcmd->rsp) { if (pcmd->rspsz != 0) { /* free rsp in cmd_obj */ kfree(pcmd->rsp); diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index 963235fd7292..d283341cfe43 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -43,6 +43,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */ {USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */ {USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */ + {USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */ {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/sm750fb/ddk750_chip.c b/drivers/staging/sm750fb/ddk750_chip.c index 944dd25924be..4754f7a20684 100644 --- a/drivers/staging/sm750fb/ddk750_chip.c +++ b/drivers/staging/sm750fb/ddk750_chip.c @@ -40,7 +40,7 @@ static unsigned int get_mxclk_freq(void) pll_reg = peek32(MXCLK_PLL_CTRL); M = (pll_reg & PLL_CTRL_M_MASK) >> PLL_CTRL_M_SHIFT; - N = (pll_reg & PLL_CTRL_N_MASK) >> PLL_CTRL_M_SHIFT; + N = (pll_reg & PLL_CTRL_N_MASK) >> PLL_CTRL_N_SHIFT; OD = (pll_reg & PLL_CTRL_OD_MASK) >> PLL_CTRL_OD_SHIFT; POD = (pll_reg & PLL_CTRL_POD_MASK) >> PLL_CTRL_POD_SHIFT; diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c index 3aa4128703d5..67207b0554cd 100644 --- a/drivers/staging/sm750fb/sm750.c +++ b/drivers/staging/sm750fb/sm750.c @@ -1053,6 +1053,26 @@ release_fb: return err; } +static int lynxfb_kick_out_firmware_fb(struct pci_dev *pdev) +{ + struct apertures_struct *ap; + bool primary = false; + + ap = alloc_apertures(1); + if (!ap) + return -ENOMEM; + + ap->ranges[0].base = pci_resource_start(pdev, 0); + ap->ranges[0].size = pci_resource_len(pdev, 0); +#ifdef CONFIG_X86 + primary = pdev->resource[PCI_ROM_RESOURCE].flags & + IORESOURCE_ROM_SHADOW; +#endif + remove_conflicting_framebuffers(ap, "sm750_fb1", primary); + kfree(ap); + return 0; +} + static int lynxfb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -1061,6 +1081,10 @@ static int lynxfb_pci_probe(struct pci_dev *pdev, int fbidx; int err; + err = lynxfb_kick_out_firmware_fb(pdev); + if (err) + return err; + /* enable device */ err = pcim_enable_device(pdev); if (err) diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 82e5de248947..67956e24779c 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -2314,6 +2314,7 @@ static void __exit speakup_exit(void) mutex_lock(&spk_mutex); synth_release(); mutex_unlock(&spk_mutex); + spk_ttyio_unregister_ldisc(); speakup_kobj_exit(); @@ -2376,6 +2377,7 @@ static int __init speakup_init(void) if (err) goto error_kobjects; + spk_ttyio_register_ldisc(); synth_init(synth_name); speakup_register_devsynth(); /* diff --git a/drivers/staging/speakup/spk_priv.h b/drivers/staging/speakup/spk_priv.h index 87b6a0a4c54d..046040ac074c 100644 --- a/drivers/staging/speakup/spk_priv.h +++ b/drivers/staging/speakup/spk_priv.h @@ -48,6 +48,8 @@ void spk_stop_serial_interrupt(void); int spk_wait_for_xmitr(struct spk_synth *in_synth); void spk_serial_release(void); void spk_ttyio_release(void); +void spk_ttyio_register_ldisc(void); +void spk_ttyio_unregister_ldisc(void); void synth_buffer_skip_nonlatin1(void); u16 synth_buffer_getc(void); diff --git a/drivers/staging/speakup/spk_ttyio.c b/drivers/staging/speakup/spk_ttyio.c index ed8e96b06ead..fe340b07c482 100644 --- a/drivers/staging/speakup/spk_ttyio.c +++ b/drivers/staging/speakup/spk_ttyio.c @@ -154,12 +154,6 @@ static int spk_ttyio_initialise_ldisc(struct spk_synth *synth) struct ktermios tmp_termios; dev_t dev; - ret = tty_register_ldisc(N_SPEAKUP, &spk_ttyio_ldisc_ops); - if (ret) { - pr_err("Error registering line discipline.\n"); - return ret; - } - ret = get_dev_to_use(synth, &dev); if (ret) return ret; @@ -196,10 +190,24 @@ static int spk_ttyio_initialise_ldisc(struct spk_synth *synth) tty_unlock(tty); ret = tty_set_ldisc(tty, N_SPEAKUP); + if (ret) + pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); return ret; } +void spk_ttyio_register_ldisc(void) +{ + if (tty_register_ldisc(N_SPEAKUP, &spk_ttyio_ldisc_ops)) + pr_warn("speakup: Error registering line discipline. Most synths won't work.\n"); +} + +void spk_ttyio_unregister_ldisc(void) +{ + if (tty_unregister_ldisc(N_SPEAKUP)) + pr_warn("speakup: Couldn't unregister ldisc\n"); +} + static int spk_ttyio_out(struct spk_synth *in_synth, const char ch) { if (in_synth->alive && speakup_tty && speakup_tty->ops->write) { @@ -300,7 +308,7 @@ void spk_ttyio_release(void) tty_ldisc_flush(speakup_tty); tty_unlock(speakup_tty); - tty_ldisc_release(speakup_tty); + tty_release_struct(speakup_tty, speakup_tty->index); } EXPORT_SYMBOL_GPL(spk_ttyio_release); diff --git a/drivers/staging/vboxvideo/Kconfig b/drivers/staging/vboxvideo/Kconfig new file mode 100644 index 000000000000..a52746f9a670 --- /dev/null +++ b/drivers/staging/vboxvideo/Kconfig @@ -0,0 +1,12 @@ +config DRM_VBOXVIDEO + tristate "Virtual Box Graphics Card" + depends on DRM && X86 && PCI + select DRM_KMS_HELPER + help + This is a KMS driver for the virtual Graphics Card used in + Virtual Box virtual machines. + + Although it is possible to builtin this module, it is advised + to build this driver as a module, so that it can be updated + independently of the kernel. Select M to built this driver as a + module and add support for these devices via drm/kms interfaces. diff --git a/drivers/staging/vboxvideo/Makefile b/drivers/staging/vboxvideo/Makefile new file mode 100644 index 000000000000..2d0b3bc7ad73 --- /dev/null +++ b/drivers/staging/vboxvideo/Makefile @@ -0,0 +1,7 @@ +ccflags-y := -Iinclude/drm + +vboxvideo-y := hgsmi_base.o modesetting.o vbva_base.o \ + vbox_drv.o vbox_fb.o vbox_hgsmi.o vbox_irq.o vbox_main.o \ + vbox_mode.o vbox_prime.o vbox_ttm.o + +obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo.o diff --git a/drivers/staging/vboxvideo/TODO b/drivers/staging/vboxvideo/TODO new file mode 100644 index 000000000000..ce764309b079 --- /dev/null +++ b/drivers/staging/vboxvideo/TODO @@ -0,0 +1,9 @@ +TODO: +-Move the driver over to the atomic API +-Stop using old load / unload drm_driver hooks +-Get a full review from the drm-maintainers on dri-devel done on this driver +-Extend this TODO with the results of that review + +Please send any patches to Greg Kroah-Hartman <gregkh@linuxfoundation.org>, +Hans de Goede <hdegoede@redhat.com> and +Michael Thayer <michael.thayer@oracle.com>. diff --git a/drivers/staging/vboxvideo/hgsmi_base.c b/drivers/staging/vboxvideo/hgsmi_base.c new file mode 100644 index 000000000000..15ff5f42e2cd --- /dev/null +++ b/drivers/staging/vboxvideo/hgsmi_base.c @@ -0,0 +1,246 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "vbox_drv.h" +#include "vbox_err.h" +#include "vboxvideo_guest.h" +#include "vboxvideo_vbe.h" +#include "hgsmi_channels.h" +#include "hgsmi_ch_setup.h" + +/** + * Inform the host of the location of the host flags in VRAM via an HGSMI cmd. + * @param ctx the context of the guest heap to use. + * @param location the offset chosen for the flags within guest VRAM. + * @returns 0 on success, -errno on failure + */ +int hgsmi_report_flags_location(struct gen_pool *ctx, u32 location) +{ + struct hgsmi_buffer_location *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_HGSMI, + HGSMI_CC_HOST_FLAGS_LOCATION); + if (!p) + return -ENOMEM; + + p->buf_location = location; + p->buf_len = sizeof(struct hgsmi_host_flags); + + hgsmi_buffer_submit(ctx, p); + hgsmi_buffer_free(ctx, p); + + return 0; +} + +/** + * Notify the host of HGSMI-related guest capabilities via an HGSMI command. + * @param ctx the context of the guest heap to use. + * @param caps the capabilities to report, see vbva_caps. + * @returns 0 on success, -errno on failure + */ +int hgsmi_send_caps_info(struct gen_pool *ctx, u32 caps) +{ + struct vbva_caps *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, VBVA_INFO_CAPS); + if (!p) + return -ENOMEM; + + p->rc = VERR_NOT_IMPLEMENTED; + p->caps = caps; + + hgsmi_buffer_submit(ctx, p); + + WARN_ON_ONCE(RT_FAILURE(p->rc)); + + hgsmi_buffer_free(ctx, p); + + return 0; +} + +int hgsmi_test_query_conf(struct gen_pool *ctx) +{ + u32 value = 0; + int ret; + + ret = hgsmi_query_conf(ctx, U32_MAX, &value); + if (ret) + return ret; + + return value == U32_MAX ? 0 : -EIO; +} + +/** + * Query the host for an HGSMI configuration parameter via an HGSMI command. + * @param ctx the context containing the heap used + * @param index the index of the parameter to query, + * @see vbva_conf32::index + * @param value_ret where to store the value of the parameter on success + * @returns 0 on success, -errno on failure + */ +int hgsmi_query_conf(struct gen_pool *ctx, u32 index, u32 *value_ret) +{ + struct vbva_conf32 *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, + VBVA_QUERY_CONF32); + if (!p) + return -ENOMEM; + + p->index = index; + p->value = U32_MAX; + + hgsmi_buffer_submit(ctx, p); + + *value_ret = p->value; + + hgsmi_buffer_free(ctx, p); + + return 0; +} + +/** + * Pass the host a new mouse pointer shape via an HGSMI command. + * + * @param ctx the context containing the heap to be used + * @param flags cursor flags, @see VMMDevReqMousePointer::flags + * @param hot_x horizontal position of the hot spot + * @param hot_y vertical position of the hot spot + * @param width width in pixels of the cursor + * @param height height in pixels of the cursor + * @param pixels pixel data, @see VMMDevReqMousePointer for the format + * @param len size in bytes of the pixel data + * @returns 0 on success, -errno on failure + */ +int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, + u32 hot_x, u32 hot_y, u32 width, u32 height, + u8 *pixels, u32 len) +{ + struct vbva_mouse_pointer_shape *p; + u32 pixel_len = 0; + int rc; + + if (flags & VBOX_MOUSE_POINTER_SHAPE) { + /* + * Size of the pointer data: + * sizeof (AND mask) + sizeof (XOR_MASK) + */ + pixel_len = ((((width + 7) / 8) * height + 3) & ~3) + + width * 4 * height; + if (pixel_len > len) + return -EINVAL; + + /* + * If shape is supplied, then always create the pointer visible. + * See comments in 'vboxUpdatePointerShape' + */ + flags |= VBOX_MOUSE_POINTER_VISIBLE; + } + + p = hgsmi_buffer_alloc(ctx, sizeof(*p) + pixel_len, HGSMI_CH_VBVA, + VBVA_MOUSE_POINTER_SHAPE); + if (!p) + return -ENOMEM; + + p->result = VINF_SUCCESS; + p->flags = flags; + p->hot_X = hot_x; + p->hot_y = hot_y; + p->width = width; + p->height = height; + if (pixel_len) + memcpy(p->data, pixels, pixel_len); + + hgsmi_buffer_submit(ctx, p); + + switch (p->result) { + case VINF_SUCCESS: + rc = 0; + break; + case VERR_NO_MEMORY: + rc = -ENOMEM; + break; + case VERR_NOT_SUPPORTED: + rc = -EBUSY; + break; + default: + rc = -EINVAL; + } + + hgsmi_buffer_free(ctx, p); + + return rc; +} + +/** + * Report the guest cursor position. The host may wish to use this information + * to re-position its own cursor (though this is currently unlikely). The + * current host cursor position is returned. + * @param ctx The context containing the heap used. + * @param report_position Are we reporting a position? + * @param x Guest cursor X position. + * @param y Guest cursor Y position. + * @param x_host Host cursor X position is stored here. Optional. + * @param y_host Host cursor Y position is stored here. Optional. + * @returns 0 on success, -errno on failure + */ +int hgsmi_cursor_position(struct gen_pool *ctx, bool report_position, + u32 x, u32 y, u32 *x_host, u32 *y_host) +{ + struct vbva_cursor_position *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, + VBVA_CURSOR_POSITION); + if (!p) + return -ENOMEM; + + p->report_position = report_position; + p->x = x; + p->y = y; + + hgsmi_buffer_submit(ctx, p); + + *x_host = p->x; + *y_host = p->y; + + hgsmi_buffer_free(ctx, p); + + return 0; +} + +/** + * @todo Mouse pointer position to be read from VMMDev memory, address of the + * memory region can be queried from VMMDev via an IOCTL. This VMMDev memory + * region will contain host information which is needed by the guest. + * + * Reading will not cause a switch to the host. + * + * Have to take into account: + * * synchronization: host must write to the memory only from EMT, + * large structures must be read under flag, which tells the host + * that the guest is currently reading the memory (OWNER flag?). + * * guest writes: may be allocate a page for the host info and make + * the page readonly for the guest. + * * the information should be available only for additions drivers. + * * VMMDev additions driver will inform the host which version of the info + * it expects, host must support all versions. + */ diff --git a/drivers/staging/vboxvideo/hgsmi_ch_setup.h b/drivers/staging/vboxvideo/hgsmi_ch_setup.h new file mode 100644 index 000000000000..8e6d9e11a69c --- /dev/null +++ b/drivers/staging/vboxvideo/hgsmi_ch_setup.h @@ -0,0 +1,66 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef __HGSMI_CH_SETUP_H__ +#define __HGSMI_CH_SETUP_H__ + +/* + * Tell the host the location of hgsmi_host_flags structure, where the host + * can write information about pending buffers, etc, and which can be quickly + * polled by the guest without a need to port IO. + */ +#define HGSMI_CC_HOST_FLAGS_LOCATION 0 + +struct hgsmi_buffer_location { + u32 buf_location; + u32 buf_len; +} __packed; + +/* HGSMI setup and configuration data structures. */ +/* host->guest commands pending, should be accessed under FIFO lock only */ +#define HGSMIHOSTFLAGS_COMMANDS_PENDING 0x01u +/* IRQ is fired, should be accessed under VGAState::lock only */ +#define HGSMIHOSTFLAGS_IRQ 0x02u +/* vsync interrupt flag, should be accessed under VGAState::lock only */ +#define HGSMIHOSTFLAGS_VSYNC 0x10u +/** monitor hotplug flag, should be accessed under VGAState::lock only */ +#define HGSMIHOSTFLAGS_HOTPLUG 0x20u +/** + * Cursor capability state change flag, should be accessed under + * VGAState::lock only. @see vbva_conf32. + */ +#define HGSMIHOSTFLAGS_CURSOR_CAPABILITIES 0x40u + +struct hgsmi_host_flags { + /* + * Host flags can be accessed and modified in multiple threads + * concurrently, e.g. CrOpenGL HGCM and GUI threads when completing + * HGSMI 3D and Video Accel respectively, EMT thread when dealing with + * HGSMI command processing, etc. + * Besides settings/cleaning flags atomically, some flags have their + * own special sync restrictions, see comments for flags above. + */ + u32 host_flags; + u32 reserved[3]; +} __packed; + +#endif diff --git a/drivers/staging/vboxvideo/hgsmi_channels.h b/drivers/staging/vboxvideo/hgsmi_channels.h new file mode 100644 index 000000000000..a2a34b2167b4 --- /dev/null +++ b/drivers/staging/vboxvideo/hgsmi_channels.h @@ -0,0 +1,53 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef __HGSMI_CHANNELS_H__ +#define __HGSMI_CHANNELS_H__ + +/* + * Each channel has an 8 bit identifier. There are a number of predefined + * (hardcoded) channels. + * + * HGSMI_CH_HGSMI channel can be used to map a string channel identifier + * to a free 16 bit numerical value. values are allocated in range + * [HGSMI_CH_STRING_FIRST;HGSMI_CH_STRING_LAST]. + */ + +/* A reserved channel value */ +#define HGSMI_CH_RESERVED 0x00 +/* HGCMI: setup and configuration */ +#define HGSMI_CH_HGSMI 0x01 +/* Graphics: VBVA */ +#define HGSMI_CH_VBVA 0x02 +/* Graphics: Seamless with a single guest region */ +#define HGSMI_CH_SEAMLESS 0x03 +/* Graphics: Seamless with separate host windows */ +#define HGSMI_CH_SEAMLESS2 0x04 +/* Graphics: OpenGL HW acceleration */ +#define HGSMI_CH_OPENGL 0x05 + +/* The first channel index to be used for string mappings (inclusive) */ +#define HGSMI_CH_STRING_FIRST 0x20 +/* The last channel index for string mappings (inclusive) */ +#define HGSMI_CH_STRING_LAST 0xff + +#endif diff --git a/drivers/staging/vboxvideo/hgsmi_defs.h b/drivers/staging/vboxvideo/hgsmi_defs.h new file mode 100644 index 000000000000..5b21fb974d20 --- /dev/null +++ b/drivers/staging/vboxvideo/hgsmi_defs.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef __HGSMI_DEFS_H__ +#define __HGSMI_DEFS_H__ + +/* Buffer sequence type mask. */ +#define HGSMI_BUFFER_HEADER_F_SEQ_MASK 0x03 +/* Single buffer, not a part of a sequence. */ +#define HGSMI_BUFFER_HEADER_F_SEQ_SINGLE 0x00 +/* The first buffer in a sequence. */ +#define HGSMI_BUFFER_HEADER_F_SEQ_START 0x01 +/* A middle buffer in a sequence. */ +#define HGSMI_BUFFER_HEADER_F_SEQ_CONTINUE 0x02 +/* The last buffer in a sequence. */ +#define HGSMI_BUFFER_HEADER_F_SEQ_END 0x03 + +/* 16 bytes buffer header. */ +struct hgsmi_buffer_header { + u32 data_size; /* Size of data that follows the header. */ + u8 flags; /* HGSMI_BUFFER_HEADER_F_* */ + u8 channel; /* The channel the data must be routed to. */ + u16 channel_info; /* Opaque to the HGSMI, used by the channel. */ + + union { + /* Opaque placeholder to make the union 8 bytes. */ + u8 header_data[8]; + + /* HGSMI_BUFFER_HEADER_F_SEQ_SINGLE */ + struct { + u32 reserved1; /* A reserved field, initialize to 0. */ + u32 reserved2; /* A reserved field, initialize to 0. */ + } buffer; + + /* HGSMI_BUFFER_HEADER_F_SEQ_START */ + struct { + /* Must be the same for all buffers in the sequence. */ + u32 sequence_number; + /* The total size of the sequence. */ + u32 sequence_size; + } sequence_start; + + /* + * HGSMI_BUFFER_HEADER_F_SEQ_CONTINUE and + * HGSMI_BUFFER_HEADER_F_SEQ_END + */ + struct { + /* Must be the same for all buffers in the sequence. */ + u32 sequence_number; + /* Data offset in the entire sequence. */ + u32 sequence_offset; + } sequence_continue; + } u; +} __packed; + +/* 8 bytes buffer tail. */ +struct hgsmi_buffer_tail { + /* Reserved, must be initialized to 0. */ + u32 reserved; + /* + * One-at-a-Time Hash: http://www.burtleburtle.net/bob/hash/doobs.html + * Over the header, offset and for first 4 bytes of the tail. + */ + u32 checksum; +} __packed; + +/* + * The size of the array of channels. Array indexes are u8. + * Note: the value must not be changed. + */ +#define HGSMI_NUMBER_OF_CHANNELS 0x100 + +#endif diff --git a/drivers/staging/vboxvideo/modesetting.c b/drivers/staging/vboxvideo/modesetting.c new file mode 100644 index 000000000000..7616b8aab23a --- /dev/null +++ b/drivers/staging/vboxvideo/modesetting.c @@ -0,0 +1,142 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "vbox_drv.h" +#include "vbox_err.h" +#include "vboxvideo_guest.h" +#include "vboxvideo_vbe.h" +#include "hgsmi_channels.h" + +/** + * Set a video mode via an HGSMI request. The views must have been + * initialised first using @a VBoxHGSMISendViewInfo and if the mode is being + * set on the first display then it must be set first using registers. + * @param ctx The context containing the heap to use + * @param display The screen number + * @param origin_x The horizontal displacement relative to the first scrn + * @param origin_y The vertical displacement relative to the first screen + * @param start_offset The offset of the visible area of the framebuffer + * relative to the framebuffer start + * @param pitch The offset in bytes between the starts of two adjecent + * scan lines in video RAM + * @param width The mode width + * @param height The mode height + * @param bpp The colour depth of the mode + * @param flags Flags + */ +void hgsmi_process_display_info(struct gen_pool *ctx, u32 display, + s32 origin_x, s32 origin_y, u32 start_offset, + u32 pitch, u32 width, u32 height, + u16 bpp, u16 flags) +{ + struct vbva_infoscreen *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, + VBVA_INFO_SCREEN); + if (!p) + return; + + p->view_index = display; + p->origin_x = origin_x; + p->origin_y = origin_y; + p->start_offset = start_offset; + p->line_size = pitch; + p->width = width; + p->height = height; + p->bits_per_pixel = bpp; + p->flags = flags; + + hgsmi_buffer_submit(ctx, p); + hgsmi_buffer_free(ctx, p); +} + +/** + * Report the rectangle relative to which absolute pointer events should be + * expressed. This information remains valid until the next VBVA resize event + * for any screen, at which time it is reset to the bounding rectangle of all + * virtual screens. + * @param ctx The context containing the heap to use. + * @param origin_x Upper left X co-ordinate relative to the first screen. + * @param origin_y Upper left Y co-ordinate relative to the first screen. + * @param width Rectangle width. + * @param height Rectangle height. + * @returns 0 on success, -errno on failure + */ +int hgsmi_update_input_mapping(struct gen_pool *ctx, s32 origin_x, s32 origin_y, + u32 width, u32 height) +{ + struct vbva_report_input_mapping *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, + VBVA_REPORT_INPUT_MAPPING); + if (!p) + return -ENOMEM; + + p->x = origin_x; + p->y = origin_y; + p->cx = width; + p->cy = height; + + hgsmi_buffer_submit(ctx, p); + hgsmi_buffer_free(ctx, p); + + return 0; +} + +/** + * Get most recent video mode hints. + * @param ctx The context containing the heap to use. + * @param screens The number of screens to query hints for, starting at 0. + * @param hints Array of vbva_modehint structures for receiving the hints. + * @returns 0 on success, -errno on failure + */ +int hgsmi_get_mode_hints(struct gen_pool *ctx, unsigned int screens, + struct vbva_modehint *hints) +{ + struct vbva_query_mode_hints *p; + size_t size; + + if (WARN_ON(!hints)) + return -EINVAL; + + size = screens * sizeof(struct vbva_modehint); + p = hgsmi_buffer_alloc(ctx, sizeof(*p) + size, HGSMI_CH_VBVA, + VBVA_QUERY_MODE_HINTS); + if (!p) + return -ENOMEM; + + p->hints_queried_count = screens; + p->hint_structure_guest_size = sizeof(struct vbva_modehint); + p->rc = VERR_NOT_SUPPORTED; + + hgsmi_buffer_submit(ctx, p); + + if (RT_FAILURE(p->rc)) { + hgsmi_buffer_free(ctx, p); + return -EIO; + } + + memcpy(hints, ((u8 *)p) + sizeof(struct vbva_query_mode_hints), size); + hgsmi_buffer_free(ctx, p); + + return 0; +} diff --git a/drivers/staging/vboxvideo/vbox_drv.c b/drivers/staging/vboxvideo/vbox_drv.c new file mode 100644 index 000000000000..92ae1560a16d --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_drv.c @@ -0,0 +1,286 @@ +/* + * Copyright (C) 2013-2017 Oracle Corporation + * This file is based on ast_drv.c + * Copyright 2012 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * Authors: Dave Airlie <airlied@redhat.com> + * Michael Thayer <michael.thayer@oracle.com, + * Hans de Goede <hdegoede@redhat.com> + */ +#include <linux/module.h> +#include <linux/console.h> +#include <linux/vt_kern.h> + +#include <drm/drmP.h> +#include <drm/drm_crtc_helper.h> + +#include "vbox_drv.h" + +int vbox_modeset = -1; + +MODULE_PARM_DESC(modeset, "Disable/Enable modesetting"); +module_param_named(modeset, vbox_modeset, int, 0400); + +static struct drm_driver driver; + +static const struct pci_device_id pciidlist[] = { + { 0x80ee, 0xbeef, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, + { 0, 0, 0}, +}; +MODULE_DEVICE_TABLE(pci, pciidlist); + +static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + return drm_get_pci_dev(pdev, ent, &driver); +} + +static void vbox_pci_remove(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + + drm_put_dev(dev); +} + +static int vbox_drm_freeze(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + + drm_kms_helper_poll_disable(dev); + + pci_save_state(dev->pdev); + + drm_fb_helper_set_suspend_unlocked(&vbox->fbdev->helper, true); + + return 0; +} + +static int vbox_drm_thaw(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + + drm_mode_config_reset(dev); + drm_helper_resume_force_mode(dev); + drm_fb_helper_set_suspend_unlocked(&vbox->fbdev->helper, false); + + return 0; +} + +static int vbox_drm_resume(struct drm_device *dev) +{ + int ret; + + if (pci_enable_device(dev->pdev)) + return -EIO; + + ret = vbox_drm_thaw(dev); + if (ret) + return ret; + + drm_kms_helper_poll_enable(dev); + + return 0; +} + +static int vbox_pm_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *ddev = pci_get_drvdata(pdev); + int error; + + error = vbox_drm_freeze(ddev); + if (error) + return error; + + pci_disable_device(pdev); + pci_set_power_state(pdev, PCI_D3hot); + + return 0; +} + +static int vbox_pm_resume(struct device *dev) +{ + struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev)); + + return vbox_drm_resume(ddev); +} + +static int vbox_pm_freeze(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *ddev = pci_get_drvdata(pdev); + + if (!ddev || !ddev->dev_private) + return -ENODEV; + + return vbox_drm_freeze(ddev); +} + +static int vbox_pm_thaw(struct device *dev) +{ + struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev)); + + return vbox_drm_thaw(ddev); +} + +static int vbox_pm_poweroff(struct device *dev) +{ + struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev)); + + return vbox_drm_freeze(ddev); +} + +static const struct dev_pm_ops vbox_pm_ops = { + .suspend = vbox_pm_suspend, + .resume = vbox_pm_resume, + .freeze = vbox_pm_freeze, + .thaw = vbox_pm_thaw, + .poweroff = vbox_pm_poweroff, + .restore = vbox_pm_resume, +}; + +static struct pci_driver vbox_pci_driver = { + .name = DRIVER_NAME, + .id_table = pciidlist, + .probe = vbox_pci_probe, + .remove = vbox_pci_remove, + .driver.pm = &vbox_pm_ops, +}; + +static const struct file_operations vbox_fops = { + .owner = THIS_MODULE, + .open = drm_open, + .release = drm_release, + .unlocked_ioctl = drm_ioctl, + .mmap = vbox_mmap, + .poll = drm_poll, +#ifdef CONFIG_COMPAT + .compat_ioctl = drm_compat_ioctl, +#endif + .read = drm_read, +}; + +static int vbox_master_set(struct drm_device *dev, + struct drm_file *file_priv, bool from_open) +{ + struct vbox_private *vbox = dev->dev_private; + + /* + * We do not yet know whether the new owner can handle hotplug, so we + * do not advertise dynamic modes on the first query and send a + * tentative hotplug notification after that to see if they query again. + */ + vbox->initial_mode_queried = false; + + mutex_lock(&vbox->hw_mutex); + /* + * Disable VBVA when someone releases master in case the next person + * tries tries to do VESA. + */ + /** @todo work out if anyone is likely to and whether it will work. */ + /* + * Update: we also disable it because if the new master does not do + * dirty rectangle reporting (e.g. old versions of Plymouth) then at + * least the first screen will still be updated. We enable it as soon + * as we receive a dirty rectangle report. + */ + vbox_disable_accel(vbox); + mutex_unlock(&vbox->hw_mutex); + + return 0; +} + +static void vbox_master_drop(struct drm_device *dev, struct drm_file *file_priv) +{ + struct vbox_private *vbox = dev->dev_private; + + /* See vbox_master_set() */ + vbox->initial_mode_queried = false; + + mutex_lock(&vbox->hw_mutex); + vbox_disable_accel(vbox); + mutex_unlock(&vbox->hw_mutex); +} + +static struct drm_driver driver = { + .driver_features = + DRIVER_MODESET | DRIVER_GEM | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | + DRIVER_PRIME, + .dev_priv_size = 0, + + .load = vbox_driver_load, + .unload = vbox_driver_unload, + .lastclose = vbox_driver_lastclose, + .master_set = vbox_master_set, + .master_drop = vbox_master_drop, + .set_busid = drm_pci_set_busid, + + .fops = &vbox_fops, + .irq_handler = vbox_irq_handler, + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, + .patchlevel = DRIVER_PATCHLEVEL, + + .gem_free_object = vbox_gem_free_object, + .dumb_create = vbox_dumb_create, + .dumb_map_offset = vbox_dumb_mmap_offset, + .dumb_destroy = drm_gem_dumb_destroy, + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_export = drm_gem_prime_export, + .gem_prime_import = drm_gem_prime_import, + .gem_prime_pin = vbox_gem_prime_pin, + .gem_prime_unpin = vbox_gem_prime_unpin, + .gem_prime_get_sg_table = vbox_gem_prime_get_sg_table, + .gem_prime_import_sg_table = vbox_gem_prime_import_sg_table, + .gem_prime_vmap = vbox_gem_prime_vmap, + .gem_prime_vunmap = vbox_gem_prime_vunmap, + .gem_prime_mmap = vbox_gem_prime_mmap, +}; + +static int __init vbox_init(void) +{ +#ifdef CONFIG_VGA_CONSOLE + if (vgacon_text_force() && vbox_modeset == -1) + return -EINVAL; +#endif + + if (vbox_modeset == 0) + return -EINVAL; + + return drm_pci_init(&driver, &vbox_pci_driver); +} + +static void __exit vbox_exit(void) +{ + drm_pci_exit(&driver, &vbox_pci_driver); +} + +module_init(vbox_init); +module_exit(vbox_exit); + +MODULE_AUTHOR("Oracle Corporation"); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL and additional rights"); diff --git a/drivers/staging/vboxvideo/vbox_drv.h b/drivers/staging/vboxvideo/vbox_drv.h new file mode 100644 index 000000000000..4b9302703b36 --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_drv.h @@ -0,0 +1,296 @@ +/* + * Copyright (C) 2013-2017 Oracle Corporation + * This file is based on ast_drv.h + * Copyright 2012 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * Authors: Dave Airlie <airlied@redhat.com> + * Michael Thayer <michael.thayer@oracle.com, + * Hans de Goede <hdegoede@redhat.com> + */ +#ifndef __VBOX_DRV_H__ +#define __VBOX_DRV_H__ + +#include <linux/genalloc.h> +#include <linux/io.h> +#include <linux/string.h> +#include <linux/version.h> + +#include <drm/drmP.h> +#include <drm/drm_encoder.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem.h> + +#include <drm/ttm/ttm_bo_api.h> +#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_memory.h> +#include <drm/ttm/ttm_module.h> + +#include "vboxvideo_guest.h" +#include "vboxvideo_vbe.h" +#include "hgsmi_ch_setup.h" + +#define DRIVER_NAME "vboxvideo" +#define DRIVER_DESC "Oracle VM VirtualBox Graphics Card" +#define DRIVER_DATE "20130823" + +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 0 +#define DRIVER_PATCHLEVEL 0 + +#define VBOX_MAX_CURSOR_WIDTH 64 +#define VBOX_MAX_CURSOR_HEIGHT 64 +#define CURSOR_PIXEL_COUNT (VBOX_MAX_CURSOR_WIDTH * VBOX_MAX_CURSOR_HEIGHT) +#define CURSOR_DATA_SIZE (CURSOR_PIXEL_COUNT * 4 + CURSOR_PIXEL_COUNT / 8) + +#define VBOX_MAX_SCREENS 32 + +#define GUEST_HEAP_OFFSET(vbox) ((vbox)->full_vram_size - \ + VBVA_ADAPTER_INFORMATION_SIZE) +#define GUEST_HEAP_SIZE VBVA_ADAPTER_INFORMATION_SIZE +#define GUEST_HEAP_USABLE_SIZE (VBVA_ADAPTER_INFORMATION_SIZE - \ + sizeof(struct hgsmi_host_flags)) +#define HOST_FLAGS_OFFSET GUEST_HEAP_USABLE_SIZE + +struct vbox_fbdev; + +struct vbox_private { + struct drm_device *dev; + + u8 __iomem *guest_heap; + u8 __iomem *vbva_buffers; + struct gen_pool *guest_pool; + struct vbva_buf_ctx *vbva_info; + bool any_pitch; + u32 num_crtcs; + /** Amount of available VRAM, including space used for buffers. */ + u32 full_vram_size; + /** Amount of available VRAM, not including space used for buffers. */ + u32 available_vram_size; + /** Array of structures for receiving mode hints. */ + struct vbva_modehint *last_mode_hints; + + struct vbox_fbdev *fbdev; + + int fb_mtrr; + + struct { + struct drm_global_reference mem_global_ref; + struct ttm_bo_global_ref bo_global_ref; + struct ttm_bo_device bdev; + } ttm; + + struct mutex hw_mutex; /* protects modeset and accel/vbva accesses */ + /** + * We decide whether or not user-space supports display hot-plug + * depending on whether they react to a hot-plug event after the initial + * mode query. + */ + bool initial_mode_queried; + struct work_struct hotplug_work; + u32 input_mapping_width; + u32 input_mapping_height; + /** + * Is user-space using an X.Org-style layout of one large frame-buffer + * encompassing all screen ones or is the fbdev console active? + */ + bool single_framebuffer; + u32 cursor_width; + u32 cursor_height; + u32 cursor_hot_x; + u32 cursor_hot_y; + size_t cursor_data_size; + u8 cursor_data[CURSOR_DATA_SIZE]; +}; + +#undef CURSOR_PIXEL_COUNT +#undef CURSOR_DATA_SIZE + +int vbox_driver_load(struct drm_device *dev, unsigned long flags); +void vbox_driver_unload(struct drm_device *dev); +void vbox_driver_lastclose(struct drm_device *dev); + +struct vbox_gem_object; + +struct vbox_connector { + struct drm_connector base; + char name[32]; + struct vbox_crtc *vbox_crtc; + struct { + u16 width; + u16 height; + bool disconnected; + } mode_hint; +}; + +struct vbox_crtc { + struct drm_crtc base; + bool blanked; + bool disconnected; + unsigned int crtc_id; + u32 fb_offset; + bool cursor_enabled; + u16 x_hint; + u16 y_hint; +}; + +struct vbox_encoder { + struct drm_encoder base; +}; + +struct vbox_framebuffer { + struct drm_framebuffer base; + struct drm_gem_object *obj; +}; + +struct vbox_fbdev { + struct drm_fb_helper helper; + struct vbox_framebuffer afb; + int size; + struct ttm_bo_kmap_obj mapping; + int x1, y1, x2, y2; /* dirty rect */ + spinlock_t dirty_lock; +}; + +#define to_vbox_crtc(x) container_of(x, struct vbox_crtc, base) +#define to_vbox_connector(x) container_of(x, struct vbox_connector, base) +#define to_vbox_encoder(x) container_of(x, struct vbox_encoder, base) +#define to_vbox_framebuffer(x) container_of(x, struct vbox_framebuffer, base) + +int vbox_mode_init(struct drm_device *dev); +void vbox_mode_fini(struct drm_device *dev); + +#define DRM_MODE_FB_CMD drm_mode_fb_cmd2 +#define CRTC_FB(crtc) ((crtc)->primary->fb) + +void vbox_enable_accel(struct vbox_private *vbox); +void vbox_disable_accel(struct vbox_private *vbox); +void vbox_report_caps(struct vbox_private *vbox); + +void vbox_framebuffer_dirty_rectangles(struct drm_framebuffer *fb, + struct drm_clip_rect *rects, + unsigned int num_rects); + +int vbox_framebuffer_init(struct drm_device *dev, + struct vbox_framebuffer *vbox_fb, + const struct DRM_MODE_FB_CMD *mode_cmd, + struct drm_gem_object *obj); + +int vbox_fbdev_init(struct drm_device *dev); +void vbox_fbdev_fini(struct drm_device *dev); +void vbox_fbdev_set_base(struct vbox_private *vbox, unsigned long gpu_addr); + +struct vbox_bo { + struct ttm_buffer_object bo; + struct ttm_placement placement; + struct ttm_bo_kmap_obj kmap; + struct drm_gem_object gem; + struct ttm_place placements[3]; + int pin_count; +}; + +#define gem_to_vbox_bo(gobj) container_of((gobj), struct vbox_bo, gem) + +static inline struct vbox_bo *vbox_bo(struct ttm_buffer_object *bo) +{ + return container_of(bo, struct vbox_bo, bo); +} + +#define to_vbox_obj(x) container_of(x, struct vbox_gem_object, base) + +int vbox_dumb_create(struct drm_file *file, + struct drm_device *dev, + struct drm_mode_create_dumb *args); + +void vbox_gem_free_object(struct drm_gem_object *obj); +int vbox_dumb_mmap_offset(struct drm_file *file, + struct drm_device *dev, + u32 handle, u64 *offset); + +#define DRM_FILE_PAGE_OFFSET (0x10000000ULL >> PAGE_SHIFT) + +int vbox_mm_init(struct vbox_private *vbox); +void vbox_mm_fini(struct vbox_private *vbox); + +int vbox_bo_create(struct drm_device *dev, int size, int align, + u32 flags, struct vbox_bo **pvboxbo); + +int vbox_gem_create(struct drm_device *dev, + u32 size, bool iskernel, struct drm_gem_object **obj); + +int vbox_bo_pin(struct vbox_bo *bo, u32 pl_flag, u64 *gpu_addr); +int vbox_bo_unpin(struct vbox_bo *bo); + +static inline int vbox_bo_reserve(struct vbox_bo *bo, bool no_wait) +{ + int ret; + + ret = ttm_bo_reserve(&bo->bo, true, no_wait, NULL); + if (ret) { + if (ret != -ERESTARTSYS && ret != -EBUSY) + DRM_ERROR("reserve failed %p\n", bo); + return ret; + } + return 0; +} + +static inline void vbox_bo_unreserve(struct vbox_bo *bo) +{ + ttm_bo_unreserve(&bo->bo); +} + +void vbox_ttm_placement(struct vbox_bo *bo, int domain); +int vbox_bo_push_sysram(struct vbox_bo *bo); +int vbox_mmap(struct file *filp, struct vm_area_struct *vma); + +/* vbox_prime.c */ +int vbox_gem_prime_pin(struct drm_gem_object *obj); +void vbox_gem_prime_unpin(struct drm_gem_object *obj); +struct sg_table *vbox_gem_prime_get_sg_table(struct drm_gem_object *obj); +struct drm_gem_object *vbox_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *table); +void *vbox_gem_prime_vmap(struct drm_gem_object *obj); +void vbox_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); +int vbox_gem_prime_mmap(struct drm_gem_object *obj, + struct vm_area_struct *area); + +/* vbox_irq.c */ +int vbox_irq_init(struct vbox_private *vbox); +void vbox_irq_fini(struct vbox_private *vbox); +void vbox_report_hotplug(struct vbox_private *vbox); +irqreturn_t vbox_irq_handler(int irq, void *arg); + +/* vbox_hgsmi.c */ +void *hgsmi_buffer_alloc(struct gen_pool *guest_pool, size_t size, + u8 channel, u16 channel_info); +void hgsmi_buffer_free(struct gen_pool *guest_pool, void *buf); +int hgsmi_buffer_submit(struct gen_pool *guest_pool, void *buf); + +static inline void vbox_write_ioport(u16 index, u16 data) +{ + outw(index, VBE_DISPI_IOPORT_INDEX); + outw(data, VBE_DISPI_IOPORT_DATA); +} + +#endif diff --git a/drivers/staging/vboxvideo/vbox_err.h b/drivers/staging/vboxvideo/vbox_err.h new file mode 100644 index 000000000000..562db8630eb0 --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_err.h @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef __VBOX_ERR_H__ +#define __VBOX_ERR_H__ + +/** + * @name VirtualBox virtual-hardware error macros + * @{ + */ + +#define VINF_SUCCESS 0 +#define VERR_INVALID_PARAMETER (-2) +#define VERR_INVALID_POINTER (-6) +#define VERR_NO_MEMORY (-8) +#define VERR_NOT_IMPLEMENTED (-12) +#define VERR_INVALID_FUNCTION (-36) +#define VERR_NOT_SUPPORTED (-37) +#define VERR_TOO_MUCH_DATA (-42) +#define VERR_INVALID_STATE (-79) +#define VERR_OUT_OF_RESOURCES (-80) +#define VERR_ALREADY_EXISTS (-105) +#define VERR_INTERNAL_ERROR (-225) + +#define RT_SUCCESS_NP(rc) ((int)(rc) >= VINF_SUCCESS) +#define RT_SUCCESS(rc) (likely(RT_SUCCESS_NP(rc))) +#define RT_FAILURE(rc) (unlikely(!RT_SUCCESS_NP(rc))) + +/** @} */ + +#endif diff --git a/drivers/staging/vboxvideo/vbox_fb.c b/drivers/staging/vboxvideo/vbox_fb.c new file mode 100644 index 000000000000..35f6d9f8c203 --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_fb.c @@ -0,0 +1,412 @@ +/* + * Copyright (C) 2013-2017 Oracle Corporation + * This file is based on ast_fb.c + * Copyright 2012 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * Authors: Dave Airlie <airlied@redhat.com> + * Michael Thayer <michael.thayer@oracle.com, + */ +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/tty.h> +#include <linux/sysrq.h> +#include <linux/delay.h> +#include <linux/fb.h> +#include <linux/init.h> + +#include <drm/drmP.h> +#include <drm/drm_crtc.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_crtc_helper.h> + +#include "vbox_drv.h" +#include "vboxvideo.h" + +#define VBOX_DIRTY_DELAY (HZ / 30) +/** + * Tell the host about dirty rectangles to update. + */ +static void vbox_dirty_update(struct vbox_fbdev *fbdev, + int x, int y, int width, int height) +{ + struct drm_gem_object *obj; + struct vbox_bo *bo; + int ret = -EBUSY; + bool store_for_later = false; + int x2, y2; + unsigned long flags; + struct drm_clip_rect rect; + + obj = fbdev->afb.obj; + bo = gem_to_vbox_bo(obj); + + /* + * try and reserve the BO, if we fail with busy + * then the BO is being moved and we should + * store up the damage until later. + */ + if (drm_can_sleep()) + ret = vbox_bo_reserve(bo, true); + if (ret) { + if (ret != -EBUSY) + return; + + store_for_later = true; + } + + x2 = x + width - 1; + y2 = y + height - 1; + spin_lock_irqsave(&fbdev->dirty_lock, flags); + + if (fbdev->y1 < y) + y = fbdev->y1; + if (fbdev->y2 > y2) + y2 = fbdev->y2; + if (fbdev->x1 < x) + x = fbdev->x1; + if (fbdev->x2 > x2) + x2 = fbdev->x2; + + if (store_for_later) { + fbdev->x1 = x; + fbdev->x2 = x2; + fbdev->y1 = y; + fbdev->y2 = y2; + spin_unlock_irqrestore(&fbdev->dirty_lock, flags); + return; + } + + fbdev->x1 = INT_MAX; + fbdev->y1 = INT_MAX; + fbdev->x2 = 0; + fbdev->y2 = 0; + + spin_unlock_irqrestore(&fbdev->dirty_lock, flags); + + /* + * Not sure why the original code subtracted 1 here, but I will keep + * it that way to avoid unnecessary differences. + */ + rect.x1 = x; + rect.x2 = x2 + 1; + rect.y1 = y; + rect.y2 = y2 + 1; + vbox_framebuffer_dirty_rectangles(&fbdev->afb.base, &rect, 1); + + vbox_bo_unreserve(bo); +} + +#ifdef CONFIG_FB_DEFERRED_IO +static void vbox_deferred_io(struct fb_info *info, struct list_head *pagelist) +{ + struct vbox_fbdev *fbdev = info->par; + unsigned long start, end, min, max; + struct page *page; + int y1, y2; + + min = ULONG_MAX; + max = 0; + list_for_each_entry(page, pagelist, lru) { + start = page->index << PAGE_SHIFT; + end = start + PAGE_SIZE - 1; + min = min(min, start); + max = max(max, end); + } + + if (min < max) { + y1 = min / info->fix.line_length; + y2 = (max / info->fix.line_length) + 1; + DRM_INFO("%s: Calling dirty update: 0, %d, %d, %d\n", + __func__, y1, info->var.xres, y2 - y1 - 1); + vbox_dirty_update(fbdev, 0, y1, info->var.xres, y2 - y1 - 1); + } +} + +static struct fb_deferred_io vbox_defio = { + .delay = VBOX_DIRTY_DELAY, + .deferred_io = vbox_deferred_io, +}; +#endif + +static void vbox_fillrect(struct fb_info *info, const struct fb_fillrect *rect) +{ + struct vbox_fbdev *fbdev = info->par; + + sys_fillrect(info, rect); + vbox_dirty_update(fbdev, rect->dx, rect->dy, rect->width, rect->height); +} + +static void vbox_copyarea(struct fb_info *info, const struct fb_copyarea *area) +{ + struct vbox_fbdev *fbdev = info->par; + + sys_copyarea(info, area); + vbox_dirty_update(fbdev, area->dx, area->dy, area->width, area->height); +} + +static void vbox_imageblit(struct fb_info *info, const struct fb_image *image) +{ + struct vbox_fbdev *fbdev = info->par; + + sys_imageblit(info, image); + vbox_dirty_update(fbdev, image->dx, image->dy, image->width, + image->height); +} + +static struct fb_ops vboxfb_ops = { + .owner = THIS_MODULE, + .fb_check_var = drm_fb_helper_check_var, + .fb_set_par = drm_fb_helper_set_par, + .fb_fillrect = vbox_fillrect, + .fb_copyarea = vbox_copyarea, + .fb_imageblit = vbox_imageblit, + .fb_pan_display = drm_fb_helper_pan_display, + .fb_blank = drm_fb_helper_blank, + .fb_setcmap = drm_fb_helper_setcmap, + .fb_debug_enter = drm_fb_helper_debug_enter, + .fb_debug_leave = drm_fb_helper_debug_leave, +}; + +static int vboxfb_create_object(struct vbox_fbdev *fbdev, + struct DRM_MODE_FB_CMD *mode_cmd, + struct drm_gem_object **gobj_p) +{ + struct drm_device *dev = fbdev->helper.dev; + u32 size; + struct drm_gem_object *gobj; + u32 pitch = mode_cmd->pitches[0]; + int ret; + + size = pitch * mode_cmd->height; + ret = vbox_gem_create(dev, size, true, &gobj); + if (ret) + return ret; + + *gobj_p = gobj; + + return 0; +} + +static int vboxfb_create(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct vbox_fbdev *fbdev = + container_of(helper, struct vbox_fbdev, helper); + struct drm_device *dev = fbdev->helper.dev; + struct DRM_MODE_FB_CMD mode_cmd; + struct drm_framebuffer *fb; + struct fb_info *info; + struct device *device = &dev->pdev->dev; + struct drm_gem_object *gobj; + struct vbox_bo *bo; + int size, ret; + u32 pitch; + + mode_cmd.width = sizes->surface_width; + mode_cmd.height = sizes->surface_height; + pitch = mode_cmd.width * ((sizes->surface_bpp + 7) / 8); + mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, + sizes->surface_depth); + mode_cmd.pitches[0] = pitch; + + size = pitch * mode_cmd.height; + + ret = vboxfb_create_object(fbdev, &mode_cmd, &gobj); + if (ret) { + DRM_ERROR("failed to create fbcon backing object %d\n", ret); + return ret; + } + + ret = vbox_framebuffer_init(dev, &fbdev->afb, &mode_cmd, gobj); + if (ret) + return ret; + + bo = gem_to_vbox_bo(gobj); + + ret = vbox_bo_reserve(bo, false); + if (ret) + return ret; + + ret = vbox_bo_pin(bo, TTM_PL_FLAG_VRAM, NULL); + if (ret) { + vbox_bo_unreserve(bo); + return ret; + } + + ret = ttm_bo_kmap(&bo->bo, 0, bo->bo.num_pages, &bo->kmap); + vbox_bo_unreserve(bo); + if (ret) { + DRM_ERROR("failed to kmap fbcon\n"); + return ret; + } + + info = framebuffer_alloc(0, device); + if (!info) + return -ENOMEM; + info->par = fbdev; + + fbdev->size = size; + + fb = &fbdev->afb.base; + fbdev->helper.fb = fb; + fbdev->helper.fbdev = info; + + strcpy(info->fix.id, "vboxdrmfb"); + + /* + * The last flag forces a mode set on VT switches even if the kernel + * does not think it is needed. + */ + info->flags = FBINFO_DEFAULT | FBINFO_CAN_FORCE_OUTPUT | + FBINFO_MISC_ALWAYS_SETPAR; + info->fbops = &vboxfb_ops; + + ret = fb_alloc_cmap(&info->cmap, 256, 0); + if (ret) + return -ENOMEM; + + /* + * This seems to be done for safety checking that the framebuffer + * is not registered twice by different drivers. + */ + info->apertures = alloc_apertures(1); + if (!info->apertures) + return -ENOMEM; + info->apertures->ranges[0].base = pci_resource_start(dev->pdev, 0); + info->apertures->ranges[0].size = pci_resource_len(dev->pdev, 0); + + drm_fb_helper_fill_fix(info, fb->pitches[0], fb->format->depth); + drm_fb_helper_fill_var(info, &fbdev->helper, sizes->fb_width, + sizes->fb_height); + + info->screen_base = bo->kmap.virtual; + info->screen_size = size; + +#ifdef CONFIG_FB_DEFERRED_IO + info->fbdefio = &vbox_defio; + fb_deferred_io_init(info); +#endif + + info->pixmap.flags = FB_PIXMAP_SYSTEM; + + DRM_DEBUG_KMS("allocated %dx%d\n", fb->width, fb->height); + + return 0; +} + +static void vbox_fb_gamma_set(struct drm_crtc *crtc, u16 red, u16 green, + u16 blue, int regno) +{ +} + +static void vbox_fb_gamma_get(struct drm_crtc *crtc, u16 *red, u16 *green, + u16 *blue, int regno) +{ + *red = regno; + *green = regno; + *blue = regno; +} + +static struct drm_fb_helper_funcs vbox_fb_helper_funcs = { + .gamma_set = vbox_fb_gamma_set, + .gamma_get = vbox_fb_gamma_get, + .fb_probe = vboxfb_create, +}; + +void vbox_fbdev_fini(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + struct vbox_fbdev *fbdev = vbox->fbdev; + struct vbox_framebuffer *afb = &fbdev->afb; + + drm_fb_helper_unregister_fbi(&fbdev->helper); + + if (afb->obj) { + struct vbox_bo *bo = gem_to_vbox_bo(afb->obj); + + if (!vbox_bo_reserve(bo, false)) { + if (bo->kmap.virtual) + ttm_bo_kunmap(&bo->kmap); + /* + * QXL does this, but is it really needed before + * freeing? + */ + if (bo->pin_count) + vbox_bo_unpin(bo); + vbox_bo_unreserve(bo); + } + drm_gem_object_unreference_unlocked(afb->obj); + afb->obj = NULL; + } + drm_fb_helper_fini(&fbdev->helper); + + drm_framebuffer_unregister_private(&afb->base); + drm_framebuffer_cleanup(&afb->base); +} + +int vbox_fbdev_init(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + struct vbox_fbdev *fbdev; + int ret; + + fbdev = devm_kzalloc(dev->dev, sizeof(*fbdev), GFP_KERNEL); + if (!fbdev) + return -ENOMEM; + + vbox->fbdev = fbdev; + spin_lock_init(&fbdev->dirty_lock); + + drm_fb_helper_prepare(dev, &fbdev->helper, &vbox_fb_helper_funcs); + ret = drm_fb_helper_init(dev, &fbdev->helper, vbox->num_crtcs); + if (ret) + return ret; + + ret = drm_fb_helper_single_add_all_connectors(&fbdev->helper); + if (ret) + goto err_fini; + + /* disable all the possible outputs/crtcs before entering KMS mode */ + drm_helper_disable_unused_functions(dev); + + ret = drm_fb_helper_initial_config(&fbdev->helper, 32); + if (ret) + goto err_fini; + + return 0; + +err_fini: + drm_fb_helper_fini(&fbdev->helper); + return ret; +} + +void vbox_fbdev_set_base(struct vbox_private *vbox, unsigned long gpu_addr) +{ + struct fb_info *fbdev = vbox->fbdev->helper.fbdev; + + fbdev->fix.smem_start = fbdev->apertures->ranges[0].base + gpu_addr; + fbdev->fix.smem_len = vbox->available_vram_size - gpu_addr; +} diff --git a/drivers/staging/vboxvideo/vbox_hgsmi.c b/drivers/staging/vboxvideo/vbox_hgsmi.c new file mode 100644 index 000000000000..822fd31121cb --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_hgsmi.c @@ -0,0 +1,115 @@ +/* + * Copyright (C) 2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * Authors: Hans de Goede <hdegoede@redhat.com> + */ + +#include "vbox_drv.h" +#include "vboxvideo_vbe.h" +#include "hgsmi_defs.h" + +/* One-at-a-Time Hash from http://www.burtleburtle.net/bob/hash/doobs.html */ +static u32 hgsmi_hash_process(u32 hash, const u8 *data, int size) +{ + while (size--) { + hash += *data++; + hash += (hash << 10); + hash ^= (hash >> 6); + } + + return hash; +} + +static u32 hgsmi_hash_end(u32 hash) +{ + hash += (hash << 3); + hash ^= (hash >> 11); + hash += (hash << 15); + + return hash; +} + +/* Not really a checksum but that is the naming used in all vbox code */ +static u32 hgsmi_checksum(u32 offset, + const struct hgsmi_buffer_header *header, + const struct hgsmi_buffer_tail *tail) +{ + u32 checksum; + + checksum = hgsmi_hash_process(0, (u8 *)&offset, sizeof(offset)); + checksum = hgsmi_hash_process(checksum, (u8 *)header, sizeof(*header)); + /* 4 -> Do not checksum the checksum itself */ + checksum = hgsmi_hash_process(checksum, (u8 *)tail, 4); + + return hgsmi_hash_end(checksum); +} + +void *hgsmi_buffer_alloc(struct gen_pool *guest_pool, size_t size, + u8 channel, u16 channel_info) +{ + struct hgsmi_buffer_header *h; + struct hgsmi_buffer_tail *t; + size_t total_size; + dma_addr_t offset; + + total_size = size + sizeof(*h) + sizeof(*t); + h = gen_pool_dma_alloc(guest_pool, total_size, &offset); + if (!h) + return NULL; + + t = (struct hgsmi_buffer_tail *)((u8 *)h + sizeof(*h) + size); + + h->flags = HGSMI_BUFFER_HEADER_F_SEQ_SINGLE; + h->data_size = size; + h->channel = channel; + h->channel_info = channel_info; + memset(&h->u.header_data, 0, sizeof(h->u.header_data)); + + t->reserved = 0; + t->checksum = hgsmi_checksum(offset, h, t); + + return (u8 *)h + sizeof(*h); +} + +void hgsmi_buffer_free(struct gen_pool *guest_pool, void *buf) +{ + struct hgsmi_buffer_header *h = + (struct hgsmi_buffer_header *)((u8 *)buf - sizeof(*h)); + size_t total_size = h->data_size + sizeof(*h) + + sizeof(struct hgsmi_buffer_tail); + + gen_pool_free(guest_pool, (unsigned long)h, total_size); +} + +int hgsmi_buffer_submit(struct gen_pool *guest_pool, void *buf) +{ + phys_addr_t offset; + + offset = gen_pool_virt_to_phys(guest_pool, (unsigned long)buf - + sizeof(struct hgsmi_buffer_header)); + outl(offset, VGA_PORT_HGSMI_GUEST); + /* Make the compiler aware that the host has changed memory. */ + mb(); + + return 0; +} diff --git a/drivers/staging/vboxvideo/vbox_irq.c b/drivers/staging/vboxvideo/vbox_irq.c new file mode 100644 index 000000000000..3ca8bec62ac4 --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_irq.c @@ -0,0 +1,197 @@ +/* + * Copyright (C) 2016-2017 Oracle Corporation + * This file is based on qxl_irq.c + * Copyright 2013 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Dave Airlie + * Alon Levy + * Michael Thayer <michael.thayer@oracle.com, + * Hans de Goede <hdegoede@redhat.com> + */ + +#include <drm/drm_crtc_helper.h> + +#include "vbox_drv.h" +#include "vboxvideo.h" + +static void vbox_clear_irq(void) +{ + outl((u32)~0, VGA_PORT_HGSMI_HOST); +} + +static u32 vbox_get_flags(struct vbox_private *vbox) +{ + return readl(vbox->guest_heap + HOST_FLAGS_OFFSET); +} + +void vbox_report_hotplug(struct vbox_private *vbox) +{ + schedule_work(&vbox->hotplug_work); +} + +irqreturn_t vbox_irq_handler(int irq, void *arg) +{ + struct drm_device *dev = (struct drm_device *)arg; + struct vbox_private *vbox = (struct vbox_private *)dev->dev_private; + u32 host_flags = vbox_get_flags(vbox); + + if (!(host_flags & HGSMIHOSTFLAGS_IRQ)) + return IRQ_NONE; + + /* + * Due to a bug in the initial host implementation of hot-plug irqs, + * the hot-plug and cursor capability flags were never cleared. + * Fortunately we can tell when they would have been set by checking + * that the VSYNC flag is not set. + */ + if (host_flags & + (HGSMIHOSTFLAGS_HOTPLUG | HGSMIHOSTFLAGS_CURSOR_CAPABILITIES) && + !(host_flags & HGSMIHOSTFLAGS_VSYNC)) + vbox_report_hotplug(vbox); + + vbox_clear_irq(); + + return IRQ_HANDLED; +} + +/** + * Check that the position hints provided by the host are suitable for GNOME + * shell (i.e. all screens disjoint and hints for all enabled screens) and if + * not replace them with default ones. Providing valid hints improves the + * chances that we will get a known screen layout for pointer mapping. + */ +static void validate_or_set_position_hints(struct vbox_private *vbox) +{ + struct vbva_modehint *hintsi, *hintsj; + bool valid = true; + u16 currentx = 0; + int i, j; + + for (i = 0; i < vbox->num_crtcs; ++i) { + for (j = 0; j < i; ++j) { + hintsi = &vbox->last_mode_hints[i]; + hintsj = &vbox->last_mode_hints[j]; + + if (hintsi->enabled && hintsj->enabled) { + if (hintsi->dx >= 0xffff || + hintsi->dy >= 0xffff || + hintsj->dx >= 0xffff || + hintsj->dy >= 0xffff || + (hintsi->dx < + hintsj->dx + (hintsj->cx & 0x8fff) && + hintsi->dx + (hintsi->cx & 0x8fff) > + hintsj->dx) || + (hintsi->dy < + hintsj->dy + (hintsj->cy & 0x8fff) && + hintsi->dy + (hintsi->cy & 0x8fff) > + hintsj->dy)) + valid = false; + } + } + } + if (!valid) + for (i = 0; i < vbox->num_crtcs; ++i) { + if (vbox->last_mode_hints[i].enabled) { + vbox->last_mode_hints[i].dx = currentx; + vbox->last_mode_hints[i].dy = 0; + currentx += + vbox->last_mode_hints[i].cx & 0x8fff; + } + } +} + +/** + * Query the host for the most recent video mode hints. + */ +static void vbox_update_mode_hints(struct vbox_private *vbox) +{ + struct drm_device *dev = vbox->dev; + struct drm_connector *connector; + struct vbox_connector *vbox_conn; + struct vbva_modehint *hints; + u16 flags; + bool disconnected; + unsigned int crtc_id; + int ret; + + ret = hgsmi_get_mode_hints(vbox->guest_pool, vbox->num_crtcs, + vbox->last_mode_hints); + if (ret) { + DRM_ERROR("vboxvideo: hgsmi_get_mode_hints failed: %d\n", ret); + return; + } + + validate_or_set_position_hints(vbox); + drm_modeset_lock_all(dev); + list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + vbox_conn = to_vbox_connector(connector); + + hints = &vbox->last_mode_hints[vbox_conn->vbox_crtc->crtc_id]; + if (hints->magic != VBVAMODEHINT_MAGIC) + continue; + + disconnected = !(hints->enabled); + crtc_id = vbox_conn->vbox_crtc->crtc_id; + vbox_conn->mode_hint.width = hints->cx & 0x8fff; + vbox_conn->mode_hint.height = hints->cy & 0x8fff; + vbox_conn->vbox_crtc->x_hint = hints->dx; + vbox_conn->vbox_crtc->y_hint = hints->dy; + vbox_conn->mode_hint.disconnected = disconnected; + + if (vbox_conn->vbox_crtc->disconnected == disconnected) + continue; + + if (disconnected) + flags = VBVA_SCREEN_F_ACTIVE | VBVA_SCREEN_F_DISABLED; + else + flags = VBVA_SCREEN_F_ACTIVE | VBVA_SCREEN_F_BLANK; + + hgsmi_process_display_info(vbox->guest_pool, crtc_id, 0, 0, 0, + hints->cx * 4, hints->cx, + hints->cy, 0, flags); + + vbox_conn->vbox_crtc->disconnected = disconnected; + } + drm_modeset_unlock_all(dev); +} + +static void vbox_hotplug_worker(struct work_struct *work) +{ + struct vbox_private *vbox = container_of(work, struct vbox_private, + hotplug_work); + + vbox_update_mode_hints(vbox); + drm_kms_helper_hotplug_event(vbox->dev); +} + +int vbox_irq_init(struct vbox_private *vbox) +{ + INIT_WORK(&vbox->hotplug_work, vbox_hotplug_worker); + vbox_update_mode_hints(vbox); + + return drm_irq_install(vbox->dev, vbox->dev->pdev->irq); +} + +void vbox_irq_fini(struct vbox_private *vbox) +{ + drm_irq_uninstall(vbox->dev); + flush_work(&vbox->hotplug_work); +} diff --git a/drivers/staging/vboxvideo/vbox_main.c b/drivers/staging/vboxvideo/vbox_main.c new file mode 100644 index 000000000000..d0c6ec75a3c7 --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_main.c @@ -0,0 +1,534 @@ +/* + * Copyright (C) 2013-2017 Oracle Corporation + * This file is based on ast_main.c + * Copyright 2012 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * Authors: Dave Airlie <airlied@redhat.com>, + * Michael Thayer <michael.thayer@oracle.com, + * Hans de Goede <hdegoede@redhat.com> + */ +#include <drm/drm_fb_helper.h> +#include <drm/drm_crtc_helper.h> + +#include "vbox_drv.h" +#include "vbox_err.h" +#include "vboxvideo_guest.h" +#include "vboxvideo_vbe.h" + +static void vbox_user_framebuffer_destroy(struct drm_framebuffer *fb) +{ + struct vbox_framebuffer *vbox_fb = to_vbox_framebuffer(fb); + + if (vbox_fb->obj) + drm_gem_object_unreference_unlocked(vbox_fb->obj); + + drm_framebuffer_cleanup(fb); + kfree(fb); +} + +void vbox_enable_accel(struct vbox_private *vbox) +{ + unsigned int i; + struct vbva_buffer *vbva; + + if (!vbox->vbva_info || !vbox->vbva_buffers) { + /* Should never happen... */ + DRM_ERROR("vboxvideo: failed to set up VBVA.\n"); + return; + } + + for (i = 0; i < vbox->num_crtcs; ++i) { + if (vbox->vbva_info[i].vbva) + continue; + + vbva = (void *)vbox->vbva_buffers + i * VBVA_MIN_BUFFER_SIZE; + if (!vbva_enable(&vbox->vbva_info[i], + vbox->guest_pool, vbva, i)) { + /* very old host or driver error. */ + DRM_ERROR("vboxvideo: vbva_enable failed\n"); + return; + } + } +} + +void vbox_disable_accel(struct vbox_private *vbox) +{ + unsigned int i; + + for (i = 0; i < vbox->num_crtcs; ++i) + vbva_disable(&vbox->vbva_info[i], vbox->guest_pool, i); +} + +void vbox_report_caps(struct vbox_private *vbox) +{ + u32 caps = VBVACAPS_DISABLE_CURSOR_INTEGRATION | + VBVACAPS_IRQ | VBVACAPS_USE_VBVA_ONLY; + + if (vbox->initial_mode_queried) + caps |= VBVACAPS_VIDEO_MODE_HINTS; + + hgsmi_send_caps_info(vbox->guest_pool, caps); +} + +/** + * Send information about dirty rectangles to VBVA. If necessary we enable + * VBVA first, as this is normally disabled after a change of master in case + * the new master does not send dirty rectangle information (is this even + * allowed?) + */ +void vbox_framebuffer_dirty_rectangles(struct drm_framebuffer *fb, + struct drm_clip_rect *rects, + unsigned int num_rects) +{ + struct vbox_private *vbox = fb->dev->dev_private; + struct drm_crtc *crtc; + unsigned int i; + + mutex_lock(&vbox->hw_mutex); + list_for_each_entry(crtc, &fb->dev->mode_config.crtc_list, head) { + if (CRTC_FB(crtc) != fb) + continue; + + vbox_enable_accel(vbox); + + for (i = 0; i < num_rects; ++i) { + struct vbva_cmd_hdr cmd_hdr; + unsigned int crtc_id = to_vbox_crtc(crtc)->crtc_id; + + if ((rects[i].x1 > crtc->x + crtc->hwmode.hdisplay) || + (rects[i].y1 > crtc->y + crtc->hwmode.vdisplay) || + (rects[i].x2 < crtc->x) || + (rects[i].y2 < crtc->y)) + continue; + + cmd_hdr.x = (s16)rects[i].x1; + cmd_hdr.y = (s16)rects[i].y1; + cmd_hdr.w = (u16)rects[i].x2 - rects[i].x1; + cmd_hdr.h = (u16)rects[i].y2 - rects[i].y1; + + if (!vbva_buffer_begin_update(&vbox->vbva_info[crtc_id], + vbox->guest_pool)) + continue; + + vbva_write(&vbox->vbva_info[crtc_id], vbox->guest_pool, + &cmd_hdr, sizeof(cmd_hdr)); + vbva_buffer_end_update(&vbox->vbva_info[crtc_id]); + } + } + mutex_unlock(&vbox->hw_mutex); +} + +static int vbox_user_framebuffer_dirty(struct drm_framebuffer *fb, + struct drm_file *file_priv, + unsigned int flags, unsigned int color, + struct drm_clip_rect *rects, + unsigned int num_rects) +{ + vbox_framebuffer_dirty_rectangles(fb, rects, num_rects); + + return 0; +} + +static const struct drm_framebuffer_funcs vbox_fb_funcs = { + .destroy = vbox_user_framebuffer_destroy, + .dirty = vbox_user_framebuffer_dirty, +}; + +int vbox_framebuffer_init(struct drm_device *dev, + struct vbox_framebuffer *vbox_fb, + const struct DRM_MODE_FB_CMD *mode_cmd, + struct drm_gem_object *obj) +{ + int ret; + + drm_helper_mode_fill_fb_struct(dev, &vbox_fb->base, mode_cmd); + vbox_fb->obj = obj; + ret = drm_framebuffer_init(dev, &vbox_fb->base, &vbox_fb_funcs); + if (ret) { + DRM_ERROR("framebuffer init failed %d\n", ret); + return ret; + } + + return 0; +} + +static struct drm_framebuffer *vbox_user_framebuffer_create( + struct drm_device *dev, + struct drm_file *filp, + const struct drm_mode_fb_cmd2 *mode_cmd) +{ + struct drm_gem_object *obj; + struct vbox_framebuffer *vbox_fb; + int ret = -ENOMEM; + + obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]); + if (!obj) + return ERR_PTR(-ENOENT); + + vbox_fb = kzalloc(sizeof(*vbox_fb), GFP_KERNEL); + if (!vbox_fb) + goto err_unref_obj; + + ret = vbox_framebuffer_init(dev, vbox_fb, mode_cmd, obj); + if (ret) + goto err_free_vbox_fb; + + return &vbox_fb->base; + +err_free_vbox_fb: + kfree(vbox_fb); +err_unref_obj: + drm_gem_object_unreference_unlocked(obj); + return ERR_PTR(ret); +} + +static const struct drm_mode_config_funcs vbox_mode_funcs = { + .fb_create = vbox_user_framebuffer_create, +}; + +static int vbox_accel_init(struct vbox_private *vbox) +{ + unsigned int i; + + vbox->vbva_info = devm_kcalloc(vbox->dev->dev, vbox->num_crtcs, + sizeof(*vbox->vbva_info), GFP_KERNEL); + if (!vbox->vbva_info) + return -ENOMEM; + + /* Take a command buffer for each screen from the end of usable VRAM. */ + vbox->available_vram_size -= vbox->num_crtcs * VBVA_MIN_BUFFER_SIZE; + + vbox->vbva_buffers = pci_iomap_range(vbox->dev->pdev, 0, + vbox->available_vram_size, + vbox->num_crtcs * + VBVA_MIN_BUFFER_SIZE); + if (!vbox->vbva_buffers) + return -ENOMEM; + + for (i = 0; i < vbox->num_crtcs; ++i) + vbva_setup_buffer_context(&vbox->vbva_info[i], + vbox->available_vram_size + + i * VBVA_MIN_BUFFER_SIZE, + VBVA_MIN_BUFFER_SIZE); + + return 0; +} + +static void vbox_accel_fini(struct vbox_private *vbox) +{ + vbox_disable_accel(vbox); + pci_iounmap(vbox->dev->pdev, vbox->vbva_buffers); +} + +/** Do we support the 4.3 plus mode hint reporting interface? */ +static bool have_hgsmi_mode_hints(struct vbox_private *vbox) +{ + u32 have_hints, have_cursor; + int ret; + + ret = hgsmi_query_conf(vbox->guest_pool, + VBOX_VBVA_CONF32_MODE_HINT_REPORTING, + &have_hints); + if (ret) + return false; + + ret = hgsmi_query_conf(vbox->guest_pool, + VBOX_VBVA_CONF32_GUEST_CURSOR_REPORTING, + &have_cursor); + if (ret) + return false; + + return have_hints == VINF_SUCCESS && have_cursor == VINF_SUCCESS; +} + +static bool vbox_check_supported(u16 id) +{ + u16 dispi_id; + + vbox_write_ioport(VBE_DISPI_INDEX_ID, id); + dispi_id = inw(VBE_DISPI_IOPORT_DATA); + + return dispi_id == id; +} + +/** + * Set up our heaps and data exchange buffers in VRAM before handing the rest + * to the memory manager. + */ +static int vbox_hw_init(struct vbox_private *vbox) +{ + int ret = -ENOMEM; + + vbox->full_vram_size = inl(VBE_DISPI_IOPORT_DATA); + vbox->any_pitch = vbox_check_supported(VBE_DISPI_ID_ANYX); + + DRM_INFO("VRAM %08x\n", vbox->full_vram_size); + + /* Map guest-heap at end of vram */ + vbox->guest_heap = + pci_iomap_range(vbox->dev->pdev, 0, GUEST_HEAP_OFFSET(vbox), + GUEST_HEAP_SIZE); + if (!vbox->guest_heap) + return -ENOMEM; + + /* Create guest-heap mem-pool use 2^4 = 16 byte chunks */ + vbox->guest_pool = gen_pool_create(4, -1); + if (!vbox->guest_pool) + goto err_unmap_guest_heap; + + ret = gen_pool_add_virt(vbox->guest_pool, + (unsigned long)vbox->guest_heap, + GUEST_HEAP_OFFSET(vbox), + GUEST_HEAP_USABLE_SIZE, -1); + if (ret) + goto err_destroy_guest_pool; + + ret = hgsmi_test_query_conf(vbox->guest_pool); + if (ret) { + DRM_ERROR("vboxvideo: hgsmi_test_query_conf failed\n"); + goto err_destroy_guest_pool; + } + + /* Reduce available VRAM size to reflect the guest heap. */ + vbox->available_vram_size = GUEST_HEAP_OFFSET(vbox); + /* Linux drm represents monitors as a 32-bit array. */ + hgsmi_query_conf(vbox->guest_pool, VBOX_VBVA_CONF32_MONITOR_COUNT, + &vbox->num_crtcs); + vbox->num_crtcs = clamp_t(u32, vbox->num_crtcs, 1, VBOX_MAX_SCREENS); + + if (!have_hgsmi_mode_hints(vbox)) { + ret = -ENOTSUPP; + goto err_destroy_guest_pool; + } + + vbox->last_mode_hints = devm_kcalloc(vbox->dev->dev, vbox->num_crtcs, + sizeof(struct vbva_modehint), + GFP_KERNEL); + if (!vbox->last_mode_hints) { + ret = -ENOMEM; + goto err_destroy_guest_pool; + } + + ret = vbox_accel_init(vbox); + if (ret) + goto err_destroy_guest_pool; + + return 0; + +err_destroy_guest_pool: + gen_pool_destroy(vbox->guest_pool); +err_unmap_guest_heap: + pci_iounmap(vbox->dev->pdev, vbox->guest_heap); + return ret; +} + +static void vbox_hw_fini(struct vbox_private *vbox) +{ + vbox_accel_fini(vbox); + gen_pool_destroy(vbox->guest_pool); + pci_iounmap(vbox->dev->pdev, vbox->guest_heap); +} + +int vbox_driver_load(struct drm_device *dev, unsigned long flags) +{ + struct vbox_private *vbox; + int ret = 0; + + if (!vbox_check_supported(VBE_DISPI_ID_HGSMI)) + return -ENODEV; + + vbox = devm_kzalloc(dev->dev, sizeof(*vbox), GFP_KERNEL); + if (!vbox) + return -ENOMEM; + + dev->dev_private = vbox; + vbox->dev = dev; + + mutex_init(&vbox->hw_mutex); + + ret = vbox_hw_init(vbox); + if (ret) + return ret; + + ret = vbox_mm_init(vbox); + if (ret) + goto err_hw_fini; + + drm_mode_config_init(dev); + + dev->mode_config.funcs = (void *)&vbox_mode_funcs; + dev->mode_config.min_width = 64; + dev->mode_config.min_height = 64; + dev->mode_config.preferred_depth = 24; + dev->mode_config.max_width = VBE_DISPI_MAX_XRES; + dev->mode_config.max_height = VBE_DISPI_MAX_YRES; + + ret = vbox_mode_init(dev); + if (ret) + goto err_drm_mode_cleanup; + + ret = vbox_irq_init(vbox); + if (ret) + goto err_mode_fini; + + ret = vbox_fbdev_init(dev); + if (ret) + goto err_irq_fini; + + return 0; + +err_irq_fini: + vbox_irq_fini(vbox); +err_mode_fini: + vbox_mode_fini(dev); +err_drm_mode_cleanup: + drm_mode_config_cleanup(dev); + vbox_mm_fini(vbox); +err_hw_fini: + vbox_hw_fini(vbox); + return ret; +} + +void vbox_driver_unload(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + + vbox_fbdev_fini(dev); + vbox_irq_fini(vbox); + vbox_mode_fini(dev); + drm_mode_config_cleanup(dev); + vbox_mm_fini(vbox); + vbox_hw_fini(vbox); +} + +/** + * @note this is described in the DRM framework documentation. AST does not + * have it, but we get an oops on driver unload if it is not present. + */ +void vbox_driver_lastclose(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + + if (vbox->fbdev) + drm_fb_helper_restore_fbdev_mode_unlocked(&vbox->fbdev->helper); +} + +int vbox_gem_create(struct drm_device *dev, + u32 size, bool iskernel, struct drm_gem_object **obj) +{ + struct vbox_bo *vboxbo; + int ret; + + *obj = NULL; + + size = roundup(size, PAGE_SIZE); + if (size == 0) + return -EINVAL; + + ret = vbox_bo_create(dev, size, 0, 0, &vboxbo); + if (ret) { + if (ret != -ERESTARTSYS) + DRM_ERROR("failed to allocate GEM object\n"); + return ret; + } + + *obj = &vboxbo->gem; + + return 0; +} + +int vbox_dumb_create(struct drm_file *file, + struct drm_device *dev, struct drm_mode_create_dumb *args) +{ + int ret; + struct drm_gem_object *gobj; + u32 handle; + + args->pitch = args->width * ((args->bpp + 7) / 8); + args->size = args->pitch * args->height; + + ret = vbox_gem_create(dev, args->size, false, &gobj); + if (ret) + return ret; + + ret = drm_gem_handle_create(file, gobj, &handle); + drm_gem_object_unreference_unlocked(gobj); + if (ret) + return ret; + + args->handle = handle; + + return 0; +} + +static void vbox_bo_unref(struct vbox_bo **bo) +{ + struct ttm_buffer_object *tbo; + + if ((*bo) == NULL) + return; + + tbo = &((*bo)->bo); + ttm_bo_unref(&tbo); + if (!tbo) + *bo = NULL; +} + +void vbox_gem_free_object(struct drm_gem_object *obj) +{ + struct vbox_bo *vbox_bo = gem_to_vbox_bo(obj); + + vbox_bo_unref(&vbox_bo); +} + +static inline u64 vbox_bo_mmap_offset(struct vbox_bo *bo) +{ + return drm_vma_node_offset_addr(&bo->bo.vma_node); +} + +int +vbox_dumb_mmap_offset(struct drm_file *file, + struct drm_device *dev, + u32 handle, u64 *offset) +{ + struct drm_gem_object *obj; + int ret; + struct vbox_bo *bo; + + mutex_lock(&dev->struct_mutex); + obj = drm_gem_object_lookup(file, handle); + if (!obj) { + ret = -ENOENT; + goto out_unlock; + } + + bo = gem_to_vbox_bo(obj); + *offset = vbox_bo_mmap_offset(bo); + + drm_gem_object_unreference(obj); + ret = 0; + +out_unlock: + mutex_unlock(&dev->struct_mutex); + return ret; +} diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c new file mode 100644 index 000000000000..f2b85f3256fa --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_mode.c @@ -0,0 +1,877 @@ +/* + * Copyright (C) 2013-2017 Oracle Corporation + * This file is based on ast_mode.c + * Copyright 2012 Red Hat Inc. + * Parts based on xf86-video-ast + * Copyright (c) 2005 ASPEED Technology Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + */ +/* + * Authors: Dave Airlie <airlied@redhat.com> + * Michael Thayer <michael.thayer@oracle.com, + * Hans de Goede <hdegoede@redhat.com> + */ +#include <linux/export.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_plane_helper.h> + +#include "vbox_drv.h" +#include "vboxvideo.h" +#include "hgsmi_channels.h" + +static int vbox_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv, + u32 handle, u32 width, u32 height, + s32 hot_x, s32 hot_y); +static int vbox_cursor_move(struct drm_crtc *crtc, int x, int y); + +/** + * Set a graphics mode. Poke any required values into registers, do an HGSMI + * mode set and tell the host we support advanced graphics functions. + */ +static void vbox_do_modeset(struct drm_crtc *crtc, + const struct drm_display_mode *mode) +{ + struct vbox_crtc *vbox_crtc = to_vbox_crtc(crtc); + struct vbox_private *vbox; + int width, height, bpp, pitch; + unsigned int crtc_id; + u16 flags; + s32 x_offset, y_offset; + + vbox = crtc->dev->dev_private; + width = mode->hdisplay ? mode->hdisplay : 640; + height = mode->vdisplay ? mode->vdisplay : 480; + crtc_id = vbox_crtc->crtc_id; + bpp = crtc->enabled ? CRTC_FB(crtc)->format->cpp[0] * 8 : 32; + pitch = crtc->enabled ? CRTC_FB(crtc)->pitches[0] : width * bpp / 8; + x_offset = vbox->single_framebuffer ? crtc->x : vbox_crtc->x_hint; + y_offset = vbox->single_framebuffer ? crtc->y : vbox_crtc->y_hint; + + /* + * This is the old way of setting graphics modes. It assumed one screen + * and a frame-buffer at the start of video RAM. On older versions of + * VirtualBox, certain parts of the code still assume that the first + * screen is programmed this way, so try to fake it. + */ + if (vbox_crtc->crtc_id == 0 && crtc->enabled && + vbox_crtc->fb_offset / pitch < 0xffff - crtc->y && + vbox_crtc->fb_offset % (bpp / 8) == 0) { + vbox_write_ioport(VBE_DISPI_INDEX_XRES, width); + vbox_write_ioport(VBE_DISPI_INDEX_YRES, height); + vbox_write_ioport(VBE_DISPI_INDEX_VIRT_WIDTH, pitch * 8 / bpp); + vbox_write_ioport(VBE_DISPI_INDEX_BPP, + CRTC_FB(crtc)->format->cpp[0] * 8); + vbox_write_ioport(VBE_DISPI_INDEX_ENABLE, VBE_DISPI_ENABLED); + vbox_write_ioport( + VBE_DISPI_INDEX_X_OFFSET, + vbox_crtc->fb_offset % pitch / bpp * 8 + crtc->x); + vbox_write_ioport(VBE_DISPI_INDEX_Y_OFFSET, + vbox_crtc->fb_offset / pitch + crtc->y); + } + + flags = VBVA_SCREEN_F_ACTIVE; + flags |= (crtc->enabled && !vbox_crtc->blanked) ? + 0 : VBVA_SCREEN_F_BLANK; + flags |= vbox_crtc->disconnected ? VBVA_SCREEN_F_DISABLED : 0; + hgsmi_process_display_info(vbox->guest_pool, vbox_crtc->crtc_id, + x_offset, y_offset, + crtc->x * bpp / 8 + crtc->y * pitch, + pitch, width, height, + vbox_crtc->blanked ? 0 : bpp, flags); +} + +static int vbox_set_view(struct drm_crtc *crtc) +{ + struct vbox_crtc *vbox_crtc = to_vbox_crtc(crtc); + struct vbox_private *vbox = crtc->dev->dev_private; + struct vbva_infoview *p; + + /* + * Tell the host about the view. This design originally targeted the + * Windows XP driver architecture and assumed that each screen would + * have a dedicated frame buffer with the command buffer following it, + * the whole being a "view". The host works out which screen a command + * buffer belongs to by checking whether it is in the first view, then + * whether it is in the second and so on. The first match wins. We + * cheat around this by making the first view be the managed memory + * plus the first command buffer, the second the same plus the second + * buffer and so on. + */ + p = hgsmi_buffer_alloc(vbox->guest_pool, sizeof(*p), + HGSMI_CH_VBVA, VBVA_INFO_VIEW); + if (!p) + return -ENOMEM; + + p->view_index = vbox_crtc->crtc_id; + p->view_offset = vbox_crtc->fb_offset; + p->view_size = vbox->available_vram_size - vbox_crtc->fb_offset + + vbox_crtc->crtc_id * VBVA_MIN_BUFFER_SIZE; + p->max_screen_size = vbox->available_vram_size - vbox_crtc->fb_offset; + + hgsmi_buffer_submit(vbox->guest_pool, p); + hgsmi_buffer_free(vbox->guest_pool, p); + + return 0; +} + +static void vbox_crtc_load_lut(struct drm_crtc *crtc) +{ +} + +static void vbox_crtc_dpms(struct drm_crtc *crtc, int mode) +{ + struct vbox_crtc *vbox_crtc = to_vbox_crtc(crtc); + struct vbox_private *vbox = crtc->dev->dev_private; + + switch (mode) { + case DRM_MODE_DPMS_ON: + vbox_crtc->blanked = false; + break; + case DRM_MODE_DPMS_STANDBY: + case DRM_MODE_DPMS_SUSPEND: + case DRM_MODE_DPMS_OFF: + vbox_crtc->blanked = true; + break; + } + + mutex_lock(&vbox->hw_mutex); + vbox_do_modeset(crtc, &crtc->hwmode); + mutex_unlock(&vbox->hw_mutex); +} + +static bool vbox_crtc_mode_fixup(struct drm_crtc *crtc, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + return true; +} + +/* + * Try to map the layout of virtual screens to the range of the input device. + * Return true if we need to re-set the crtc modes due to screen offset + * changes. + */ +static bool vbox_set_up_input_mapping(struct vbox_private *vbox) +{ + struct drm_crtc *crtci; + struct drm_connector *connectori; + struct drm_framebuffer *fb1 = NULL; + bool single_framebuffer = true; + bool old_single_framebuffer = vbox->single_framebuffer; + u16 width = 0, height = 0; + + /* + * Are we using an X.Org-style single large frame-buffer for all crtcs? + * If so then screen layout can be deduced from the crtc offsets. + * Same fall-back if this is the fbdev frame-buffer. + */ + list_for_each_entry(crtci, &vbox->dev->mode_config.crtc_list, head) { + if (!fb1) { + fb1 = CRTC_FB(crtci); + if (to_vbox_framebuffer(fb1) == &vbox->fbdev->afb) + break; + } else if (CRTC_FB(crtci) && fb1 != CRTC_FB(crtci)) { + single_framebuffer = false; + } + } + if (single_framebuffer) { + list_for_each_entry(crtci, &vbox->dev->mode_config.crtc_list, + head) { + if (to_vbox_crtc(crtci)->crtc_id != 0) + continue; + + vbox->single_framebuffer = true; + vbox->input_mapping_width = CRTC_FB(crtci)->width; + vbox->input_mapping_height = CRTC_FB(crtci)->height; + return old_single_framebuffer != + vbox->single_framebuffer; + } + } + /* Otherwise calculate the total span of all screens. */ + list_for_each_entry(connectori, &vbox->dev->mode_config.connector_list, + head) { + struct vbox_connector *vbox_connector = + to_vbox_connector(connectori); + struct vbox_crtc *vbox_crtc = vbox_connector->vbox_crtc; + + width = max_t(u16, width, vbox_crtc->x_hint + + vbox_connector->mode_hint.width); + height = max_t(u16, height, vbox_crtc->y_hint + + vbox_connector->mode_hint.height); + } + + vbox->single_framebuffer = false; + vbox->input_mapping_width = width; + vbox->input_mapping_height = height; + + return old_single_framebuffer != vbox->single_framebuffer; +} + +static int vbox_crtc_do_set_base(struct drm_crtc *crtc, + struct drm_framebuffer *old_fb, int x, int y) +{ + struct vbox_private *vbox = crtc->dev->dev_private; + struct vbox_crtc *vbox_crtc = to_vbox_crtc(crtc); + struct drm_gem_object *obj; + struct vbox_framebuffer *vbox_fb; + struct vbox_bo *bo; + int ret; + u64 gpu_addr; + + /* Unpin the previous fb. */ + if (old_fb) { + vbox_fb = to_vbox_framebuffer(old_fb); + obj = vbox_fb->obj; + bo = gem_to_vbox_bo(obj); + ret = vbox_bo_reserve(bo, false); + if (ret) + return ret; + + vbox_bo_unpin(bo); + vbox_bo_unreserve(bo); + } + + vbox_fb = to_vbox_framebuffer(CRTC_FB(crtc)); + obj = vbox_fb->obj; + bo = gem_to_vbox_bo(obj); + + ret = vbox_bo_reserve(bo, false); + if (ret) + return ret; + + ret = vbox_bo_pin(bo, TTM_PL_FLAG_VRAM, &gpu_addr); + if (ret) { + vbox_bo_unreserve(bo); + return ret; + } + + if (&vbox->fbdev->afb == vbox_fb) + vbox_fbdev_set_base(vbox, gpu_addr); + vbox_bo_unreserve(bo); + + /* vbox_set_start_address_crt1(crtc, (u32)gpu_addr); */ + vbox_crtc->fb_offset = gpu_addr; + if (vbox_set_up_input_mapping(vbox)) { + struct drm_crtc *crtci; + + list_for_each_entry(crtci, &vbox->dev->mode_config.crtc_list, + head) { + vbox_set_view(crtc); + vbox_do_modeset(crtci, &crtci->mode); + } + } + + return 0; +} + +static int vbox_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, + struct drm_framebuffer *old_fb) +{ + return vbox_crtc_do_set_base(crtc, old_fb, x, y); +} + +static int vbox_crtc_mode_set(struct drm_crtc *crtc, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode, + int x, int y, struct drm_framebuffer *old_fb) +{ + struct vbox_private *vbox = crtc->dev->dev_private; + int ret; + + vbox_crtc_mode_set_base(crtc, x, y, old_fb); + + mutex_lock(&vbox->hw_mutex); + ret = vbox_set_view(crtc); + if (!ret) + vbox_do_modeset(crtc, mode); + hgsmi_update_input_mapping(vbox->guest_pool, 0, 0, + vbox->input_mapping_width, + vbox->input_mapping_height); + mutex_unlock(&vbox->hw_mutex); + + return ret; +} + +static void vbox_crtc_disable(struct drm_crtc *crtc) +{ +} + +static void vbox_crtc_prepare(struct drm_crtc *crtc) +{ +} + +static void vbox_crtc_commit(struct drm_crtc *crtc) +{ +} + +static const struct drm_crtc_helper_funcs vbox_crtc_helper_funcs = { + .dpms = vbox_crtc_dpms, + .mode_fixup = vbox_crtc_mode_fixup, + .mode_set = vbox_crtc_mode_set, + /* .mode_set_base = vbox_crtc_mode_set_base, */ + .disable = vbox_crtc_disable, + .load_lut = vbox_crtc_load_lut, + .prepare = vbox_crtc_prepare, + .commit = vbox_crtc_commit, +}; + +static void vbox_crtc_reset(struct drm_crtc *crtc) +{ +} + +static void vbox_crtc_destroy(struct drm_crtc *crtc) +{ + drm_crtc_cleanup(crtc); + kfree(crtc); +} + +static const struct drm_crtc_funcs vbox_crtc_funcs = { + .cursor_move = vbox_cursor_move, + .cursor_set2 = vbox_cursor_set2, + .reset = vbox_crtc_reset, + .set_config = drm_crtc_helper_set_config, + /* .gamma_set = vbox_crtc_gamma_set, */ + .destroy = vbox_crtc_destroy, +}; + +static struct vbox_crtc *vbox_crtc_init(struct drm_device *dev, unsigned int i) +{ + struct vbox_crtc *vbox_crtc; + + vbox_crtc = kzalloc(sizeof(*vbox_crtc), GFP_KERNEL); + if (!vbox_crtc) + return NULL; + + vbox_crtc->crtc_id = i; + + drm_crtc_init(dev, &vbox_crtc->base, &vbox_crtc_funcs); + drm_mode_crtc_set_gamma_size(&vbox_crtc->base, 256); + drm_crtc_helper_add(&vbox_crtc->base, &vbox_crtc_helper_funcs); + + return vbox_crtc; +} + +static void vbox_encoder_destroy(struct drm_encoder *encoder) +{ + drm_encoder_cleanup(encoder); + kfree(encoder); +} + +static struct drm_encoder *vbox_best_single_encoder(struct drm_connector + *connector) +{ + int enc_id = connector->encoder_ids[0]; + + /* pick the encoder ids */ + if (enc_id) + return drm_encoder_find(connector->dev, enc_id); + + return NULL; +} + +static const struct drm_encoder_funcs vbox_enc_funcs = { + .destroy = vbox_encoder_destroy, +}; + +static void vbox_encoder_dpms(struct drm_encoder *encoder, int mode) +{ +} + +static bool vbox_mode_fixup(struct drm_encoder *encoder, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + return true; +} + +static void vbox_encoder_mode_set(struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ +} + +static void vbox_encoder_prepare(struct drm_encoder *encoder) +{ +} + +static void vbox_encoder_commit(struct drm_encoder *encoder) +{ +} + +static const struct drm_encoder_helper_funcs vbox_enc_helper_funcs = { + .dpms = vbox_encoder_dpms, + .mode_fixup = vbox_mode_fixup, + .prepare = vbox_encoder_prepare, + .commit = vbox_encoder_commit, + .mode_set = vbox_encoder_mode_set, +}; + +static struct drm_encoder *vbox_encoder_init(struct drm_device *dev, + unsigned int i) +{ + struct vbox_encoder *vbox_encoder; + + vbox_encoder = kzalloc(sizeof(*vbox_encoder), GFP_KERNEL); + if (!vbox_encoder) + return NULL; + + drm_encoder_init(dev, &vbox_encoder->base, &vbox_enc_funcs, + DRM_MODE_ENCODER_DAC, NULL); + drm_encoder_helper_add(&vbox_encoder->base, &vbox_enc_helper_funcs); + + vbox_encoder->base.possible_crtcs = 1 << i; + return &vbox_encoder->base; +} + +/** + * Generate EDID data with a mode-unique serial number for the virtual + * monitor to try to persuade Unity that different modes correspond to + * different monitors and it should not try to force the same resolution on + * them. + */ +static void vbox_set_edid(struct drm_connector *connector, int width, + int height) +{ + enum { EDID_SIZE = 128 }; + unsigned char edid[EDID_SIZE] = { + 0x00, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x00, /* header */ + 0x58, 0x58, /* manufacturer (VBX) */ + 0x00, 0x00, /* product code */ + 0x00, 0x00, 0x00, 0x00, /* serial number goes here */ + 0x01, /* week of manufacture */ + 0x00, /* year of manufacture */ + 0x01, 0x03, /* EDID version */ + 0x80, /* capabilities - digital */ + 0x00, /* horiz. res in cm, zero for projectors */ + 0x00, /* vert. res in cm */ + 0x78, /* display gamma (120 == 2.2). */ + 0xEE, /* features (standby, suspend, off, RGB, std */ + /* colour space, preferred timing mode) */ + 0xEE, 0x91, 0xA3, 0x54, 0x4C, 0x99, 0x26, 0x0F, 0x50, 0x54, + /* chromaticity for standard colour space. */ + 0x00, 0x00, 0x00, /* no default timings */ + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, /* no standard timings */ + 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x06, 0x00, 0x02, 0x02, + 0x02, 0x02, + /* descriptor block 1 goes below */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + /* descriptor block 2, monitor ranges */ + 0x00, 0x00, 0x00, 0xFD, 0x00, + 0x00, 0xC8, 0x00, 0xC8, 0x64, 0x00, 0x0A, 0x20, 0x20, 0x20, + 0x20, 0x20, + /* 0-200Hz vertical, 0-200KHz horizontal, 1000MHz pixel clock */ + 0x20, + /* descriptor block 3, monitor name */ + 0x00, 0x00, 0x00, 0xFC, 0x00, + 'V', 'B', 'O', 'X', ' ', 'm', 'o', 'n', 'i', 't', 'o', 'r', + '\n', + /* descriptor block 4: dummy data */ + 0x00, 0x00, 0x00, 0x10, 0x00, + 0x0A, 0x20, 0x20, 0x20, 0x20, 0x20, + 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, + 0x20, + 0x00, /* number of extensions */ + 0x00 /* checksum goes here */ + }; + int clock = (width + 6) * (height + 6) * 60 / 10000; + unsigned int i, sum = 0; + + edid[12] = width & 0xff; + edid[13] = width >> 8; + edid[14] = height & 0xff; + edid[15] = height >> 8; + edid[54] = clock & 0xff; + edid[55] = clock >> 8; + edid[56] = width & 0xff; + edid[58] = (width >> 4) & 0xf0; + edid[59] = height & 0xff; + edid[61] = (height >> 4) & 0xf0; + for (i = 0; i < EDID_SIZE - 1; ++i) + sum += edid[i]; + edid[EDID_SIZE - 1] = (0x100 - (sum & 0xFF)) & 0xFF; + drm_mode_connector_update_edid_property(connector, (struct edid *)edid); +} + +static int vbox_get_modes(struct drm_connector *connector) +{ + struct vbox_connector *vbox_connector = NULL; + struct drm_display_mode *mode = NULL; + struct vbox_private *vbox = NULL; + unsigned int num_modes = 0; + int preferred_width, preferred_height; + + vbox_connector = to_vbox_connector(connector); + vbox = connector->dev->dev_private; + /* + * Heuristic: we do not want to tell the host that we support dynamic + * resizing unless we feel confident that the user space client using + * the video driver can handle hot-plug events. So the first time modes + * are queried after a "master" switch we tell the host that we do not, + * and immediately after we send the client a hot-plug notification as + * a test to see if they will respond and query again. + * That is also the reason why capabilities are reported to the host at + * this place in the code rather than elsewhere. + * We need to report the flags location before reporting the IRQ + * capability. + */ + hgsmi_report_flags_location(vbox->guest_pool, GUEST_HEAP_OFFSET(vbox) + + HOST_FLAGS_OFFSET); + if (vbox_connector->vbox_crtc->crtc_id == 0) + vbox_report_caps(vbox); + if (!vbox->initial_mode_queried) { + if (vbox_connector->vbox_crtc->crtc_id == 0) { + vbox->initial_mode_queried = true; + vbox_report_hotplug(vbox); + } + return drm_add_modes_noedid(connector, 800, 600); + } + num_modes = drm_add_modes_noedid(connector, 2560, 1600); + preferred_width = vbox_connector->mode_hint.width ? + vbox_connector->mode_hint.width : 1024; + preferred_height = vbox_connector->mode_hint.height ? + vbox_connector->mode_hint.height : 768; + mode = drm_cvt_mode(connector->dev, preferred_width, preferred_height, + 60, false, false, false); + if (mode) { + mode->type |= DRM_MODE_TYPE_PREFERRED; + drm_mode_probed_add(connector, mode); + ++num_modes; + } + vbox_set_edid(connector, preferred_width, preferred_height); + drm_object_property_set_value( + &connector->base, vbox->dev->mode_config.suggested_x_property, + vbox_connector->vbox_crtc->x_hint); + drm_object_property_set_value( + &connector->base, vbox->dev->mode_config.suggested_y_property, + vbox_connector->vbox_crtc->y_hint); + + return num_modes; +} + +static int vbox_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + return MODE_OK; +} + +static void vbox_connector_destroy(struct drm_connector *connector) +{ + struct vbox_connector *vbox_connector; + + vbox_connector = to_vbox_connector(connector); + drm_connector_unregister(connector); + drm_connector_cleanup(connector); + kfree(connector); +} + +static enum drm_connector_status +vbox_connector_detect(struct drm_connector *connector, bool force) +{ + struct vbox_connector *vbox_connector; + + vbox_connector = to_vbox_connector(connector); + + return vbox_connector->mode_hint.disconnected ? + connector_status_disconnected : connector_status_connected; +} + +static int vbox_fill_modes(struct drm_connector *connector, u32 max_x, + u32 max_y) +{ + struct vbox_connector *vbox_connector; + struct drm_device *dev; + struct drm_display_mode *mode, *iterator; + + vbox_connector = to_vbox_connector(connector); + dev = vbox_connector->base.dev; + list_for_each_entry_safe(mode, iterator, &connector->modes, head) { + list_del(&mode->head); + drm_mode_destroy(dev, mode); + } + + return drm_helper_probe_single_connector_modes(connector, max_x, max_y); +} + +static const struct drm_connector_helper_funcs vbox_connector_helper_funcs = { + .mode_valid = vbox_mode_valid, + .get_modes = vbox_get_modes, + .best_encoder = vbox_best_single_encoder, +}; + +static const struct drm_connector_funcs vbox_connector_funcs = { + .dpms = drm_helper_connector_dpms, + .detect = vbox_connector_detect, + .fill_modes = vbox_fill_modes, + .destroy = vbox_connector_destroy, +}; + +static int vbox_connector_init(struct drm_device *dev, + struct vbox_crtc *vbox_crtc, + struct drm_encoder *encoder) +{ + struct vbox_connector *vbox_connector; + struct drm_connector *connector; + + vbox_connector = kzalloc(sizeof(*vbox_connector), GFP_KERNEL); + if (!vbox_connector) + return -ENOMEM; + + connector = &vbox_connector->base; + vbox_connector->vbox_crtc = vbox_crtc; + + drm_connector_init(dev, connector, &vbox_connector_funcs, + DRM_MODE_CONNECTOR_VGA); + drm_connector_helper_add(connector, &vbox_connector_helper_funcs); + + connector->interlace_allowed = 0; + connector->doublescan_allowed = 0; + + drm_mode_create_suggested_offset_properties(dev); + drm_object_attach_property(&connector->base, + dev->mode_config.suggested_x_property, -1); + drm_object_attach_property(&connector->base, + dev->mode_config.suggested_y_property, -1); + drm_connector_register(connector); + + drm_mode_connector_attach_encoder(connector, encoder); + + return 0; +} + +int vbox_mode_init(struct drm_device *dev) +{ + struct vbox_private *vbox = dev->dev_private; + struct drm_encoder *encoder; + struct vbox_crtc *vbox_crtc; + unsigned int i; + int ret; + + /* vbox_cursor_init(dev); */ + for (i = 0; i < vbox->num_crtcs; ++i) { + vbox_crtc = vbox_crtc_init(dev, i); + if (!vbox_crtc) + return -ENOMEM; + encoder = vbox_encoder_init(dev, i); + if (!encoder) + return -ENOMEM; + ret = vbox_connector_init(dev, vbox_crtc, encoder); + if (ret) + return ret; + } + + return 0; +} + +void vbox_mode_fini(struct drm_device *dev) +{ + /* vbox_cursor_fini(dev); */ +} + +/** + * Copy the ARGB image and generate the mask, which is needed in case the host + * does not support ARGB cursors. The mask is a 1BPP bitmap with the bit set + * if the corresponding alpha value in the ARGB image is greater than 0xF0. + */ +static void copy_cursor_image(u8 *src, u8 *dst, u32 width, u32 height, + size_t mask_size) +{ + size_t line_size = (width + 7) / 8; + u32 i, j; + + memcpy(dst + mask_size, src, width * height * 4); + for (i = 0; i < height; ++i) + for (j = 0; j < width; ++j) + if (((u32 *)src)[i * width + j] > 0xf0000000) + dst[i * line_size + j / 8] |= (0x80 >> (j % 8)); +} + +static int vbox_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv, + u32 handle, u32 width, u32 height, + s32 hot_x, s32 hot_y) +{ + struct vbox_private *vbox = crtc->dev->dev_private; + struct vbox_crtc *vbox_crtc = to_vbox_crtc(crtc); + struct ttm_bo_kmap_obj uobj_map; + size_t data_size, mask_size; + struct drm_gem_object *obj; + u32 flags, caps = 0; + struct vbox_bo *bo; + bool src_isiomem; + u8 *dst = NULL; + u8 *src; + int ret; + + /* + * Re-set this regularly as in 5.0.20 and earlier the information was + * lost on save and restore. + */ + hgsmi_update_input_mapping(vbox->guest_pool, 0, 0, + vbox->input_mapping_width, + vbox->input_mapping_height); + if (!handle) { + bool cursor_enabled = false; + struct drm_crtc *crtci; + + /* Hide cursor. */ + vbox_crtc->cursor_enabled = false; + list_for_each_entry(crtci, &vbox->dev->mode_config.crtc_list, + head) { + if (to_vbox_crtc(crtci)->cursor_enabled) + cursor_enabled = true; + } + + if (!cursor_enabled) + hgsmi_update_pointer_shape(vbox->guest_pool, 0, 0, 0, + 0, 0, NULL, 0); + return 0; + } + + vbox_crtc->cursor_enabled = true; + + if (width > VBOX_MAX_CURSOR_WIDTH || height > VBOX_MAX_CURSOR_HEIGHT || + width == 0 || height == 0) + return -EINVAL; + + ret = hgsmi_query_conf(vbox->guest_pool, + VBOX_VBVA_CONF32_CURSOR_CAPABILITIES, &caps); + if (ret) + return ret; + + if (!(caps & VBOX_VBVA_CURSOR_CAPABILITY_HARDWARE)) { + /* + * -EINVAL means cursor_set2() not supported, -EAGAIN means + * retry at once. + */ + return -EBUSY; + } + + obj = drm_gem_object_lookup(file_priv, handle); + if (!obj) { + DRM_ERROR("Cannot find cursor object %x for crtc\n", handle); + return -ENOENT; + } + + bo = gem_to_vbox_bo(obj); + ret = vbox_bo_reserve(bo, false); + if (ret) + goto out_unref_obj; + + /* + * The mask must be calculated based on the alpha + * channel, one bit per ARGB word, and must be 32-bit + * padded. + */ + mask_size = ((width + 7) / 8 * height + 3) & ~3; + data_size = width * height * 4 + mask_size; + vbox->cursor_hot_x = min_t(u32, max(hot_x, 0), width); + vbox->cursor_hot_y = min_t(u32, max(hot_y, 0), height); + vbox->cursor_width = width; + vbox->cursor_height = height; + vbox->cursor_data_size = data_size; + dst = vbox->cursor_data; + + ret = ttm_bo_kmap(&bo->bo, 0, bo->bo.num_pages, &uobj_map); + if (ret) { + vbox->cursor_data_size = 0; + goto out_unreserve_bo; + } + + src = ttm_kmap_obj_virtual(&uobj_map, &src_isiomem); + if (src_isiomem) { + DRM_ERROR("src cursor bo not in main memory\n"); + ret = -EIO; + goto out_unmap_bo; + } + + copy_cursor_image(src, dst, width, height, mask_size); + + flags = VBOX_MOUSE_POINTER_VISIBLE | VBOX_MOUSE_POINTER_SHAPE | + VBOX_MOUSE_POINTER_ALPHA; + ret = hgsmi_update_pointer_shape(vbox->guest_pool, flags, + vbox->cursor_hot_x, vbox->cursor_hot_y, + width, height, dst, data_size); +out_unmap_bo: + ttm_bo_kunmap(&uobj_map); +out_unreserve_bo: + vbox_bo_unreserve(bo); +out_unref_obj: + drm_gem_object_unreference_unlocked(obj); + + return ret; +} + +static int vbox_cursor_move(struct drm_crtc *crtc, int x, int y) +{ + struct vbox_private *vbox = crtc->dev->dev_private; + u32 flags = VBOX_MOUSE_POINTER_VISIBLE | + VBOX_MOUSE_POINTER_SHAPE | VBOX_MOUSE_POINTER_ALPHA; + s32 crtc_x = + vbox->single_framebuffer ? crtc->x : to_vbox_crtc(crtc)->x_hint; + s32 crtc_y = + vbox->single_framebuffer ? crtc->y : to_vbox_crtc(crtc)->y_hint; + u32 host_x, host_y; + u32 hot_x = 0; + u32 hot_y = 0; + int ret; + + /* + * We compare these to unsigned later and don't + * need to handle negative. + */ + if (x + crtc_x < 0 || y + crtc_y < 0 || vbox->cursor_data_size == 0) + return 0; + + ret = hgsmi_cursor_position(vbox->guest_pool, true, x + crtc_x, + y + crtc_y, &host_x, &host_y); + + /* + * The only reason we have vbox_cursor_move() is that some older clients + * might use DRM_IOCTL_MODE_CURSOR instead of DRM_IOCTL_MODE_CURSOR2 and + * use DRM_MODE_CURSOR_MOVE to set the hot-spot. + * + * However VirtualBox 5.0.20 and earlier has a bug causing it to return + * 0,0 as host cursor location after a save and restore. + * + * To work around this we ignore a 0, 0 return, since missing the odd + * time when it legitimately happens is not going to hurt much. + */ + if (ret || (host_x == 0 && host_y == 0)) + return ret; + + if (x + crtc_x < host_x) + hot_x = min(host_x - x - crtc_x, vbox->cursor_width); + if (y + crtc_y < host_y) + hot_y = min(host_y - y - crtc_y, vbox->cursor_height); + + if (hot_x == vbox->cursor_hot_x && hot_y == vbox->cursor_hot_y) + return 0; + + vbox->cursor_hot_x = hot_x; + vbox->cursor_hot_y = hot_y; + + return hgsmi_update_pointer_shape(vbox->guest_pool, flags, + hot_x, hot_y, vbox->cursor_width, vbox->cursor_height, + vbox->cursor_data, vbox->cursor_data_size); +} diff --git a/drivers/staging/vboxvideo/vbox_prime.c b/drivers/staging/vboxvideo/vbox_prime.c new file mode 100644 index 000000000000..b7453e427a1d --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_prime.c @@ -0,0 +1,74 @@ +/* + * Copyright (C) 2017 Oracle Corporation + * Copyright 2017 Canonical + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Andreas Pokorny + */ + +#include "vbox_drv.h" + +/* + * Based on qxl_prime.c: + * Empty Implementations as there should not be any other driver for a virtual + * device that might share buffers with vboxvideo + */ + +int vbox_gem_prime_pin(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); + return -ENOSYS; +} + +void vbox_gem_prime_unpin(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); +} + +struct sg_table *vbox_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); + return ERR_PTR(-ENOSYS); +} + +struct drm_gem_object *vbox_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *table) +{ + WARN_ONCE(1, "not implemented"); + return ERR_PTR(-ENOSYS); +} + +void *vbox_gem_prime_vmap(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); + return ERR_PTR(-ENOSYS); +} + +void vbox_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) +{ + WARN_ONCE(1, "not implemented"); +} + +int vbox_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *area) +{ + WARN_ONCE(1, "not implemented"); + return -ENOSYS; +} diff --git a/drivers/staging/vboxvideo/vbox_ttm.c b/drivers/staging/vboxvideo/vbox_ttm.c new file mode 100644 index 000000000000..34a905d40735 --- /dev/null +++ b/drivers/staging/vboxvideo/vbox_ttm.c @@ -0,0 +1,472 @@ +/* + * Copyright (C) 2013-2017 Oracle Corporation + * This file is based on ast_ttm.c + * Copyright 2012 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * + * Authors: Dave Airlie <airlied@redhat.com> + * Michael Thayer <michael.thayer@oracle.com> + */ +#include "vbox_drv.h" +#include <ttm/ttm_page_alloc.h> + +static inline struct vbox_private *vbox_bdev(struct ttm_bo_device *bd) +{ + return container_of(bd, struct vbox_private, ttm.bdev); +} + +static int vbox_ttm_mem_global_init(struct drm_global_reference *ref) +{ + return ttm_mem_global_init(ref->object); +} + +static void vbox_ttm_mem_global_release(struct drm_global_reference *ref) +{ + ttm_mem_global_release(ref->object); +} + +/** + * Adds the vbox memory manager object/structures to the global memory manager. + */ +static int vbox_ttm_global_init(struct vbox_private *vbox) +{ + struct drm_global_reference *global_ref; + int ret; + + global_ref = &vbox->ttm.mem_global_ref; + global_ref->global_type = DRM_GLOBAL_TTM_MEM; + global_ref->size = sizeof(struct ttm_mem_global); + global_ref->init = &vbox_ttm_mem_global_init; + global_ref->release = &vbox_ttm_mem_global_release; + ret = drm_global_item_ref(global_ref); + if (ret) { + DRM_ERROR("Failed setting up TTM memory subsystem.\n"); + return ret; + } + + vbox->ttm.bo_global_ref.mem_glob = vbox->ttm.mem_global_ref.object; + global_ref = &vbox->ttm.bo_global_ref.ref; + global_ref->global_type = DRM_GLOBAL_TTM_BO; + global_ref->size = sizeof(struct ttm_bo_global); + global_ref->init = &ttm_bo_global_init; + global_ref->release = &ttm_bo_global_release; + + ret = drm_global_item_ref(global_ref); + if (ret) { + DRM_ERROR("Failed setting up TTM BO subsystem.\n"); + drm_global_item_unref(&vbox->ttm.mem_global_ref); + return ret; + } + + return 0; +} + +/** + * Removes the vbox memory manager object from the global memory manager. + */ +static void vbox_ttm_global_release(struct vbox_private *vbox) +{ + drm_global_item_unref(&vbox->ttm.bo_global_ref.ref); + drm_global_item_unref(&vbox->ttm.mem_global_ref); +} + +static void vbox_bo_ttm_destroy(struct ttm_buffer_object *tbo) +{ + struct vbox_bo *bo; + + bo = container_of(tbo, struct vbox_bo, bo); + + drm_gem_object_release(&bo->gem); + kfree(bo); +} + +static bool vbox_ttm_bo_is_vbox_bo(struct ttm_buffer_object *bo) +{ + if (bo->destroy == &vbox_bo_ttm_destroy) + return true; + + return false; +} + +static int +vbox_bo_init_mem_type(struct ttm_bo_device *bdev, u32 type, + struct ttm_mem_type_manager *man) +{ + switch (type) { + case TTM_PL_SYSTEM: + man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; + man->available_caching = TTM_PL_MASK_CACHING; + man->default_caching = TTM_PL_FLAG_CACHED; + break; + case TTM_PL_VRAM: + man->func = &ttm_bo_manager_func; + man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; + man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; + man->default_caching = TTM_PL_FLAG_WC; + break; + default: + DRM_ERROR("Unsupported memory type %u\n", (unsigned int)type); + return -EINVAL; + } + + return 0; +} + +static void +vbox_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl) +{ + struct vbox_bo *vboxbo = vbox_bo(bo); + + if (!vbox_ttm_bo_is_vbox_bo(bo)) + return; + + vbox_ttm_placement(vboxbo, TTM_PL_FLAG_SYSTEM); + *pl = vboxbo->placement; +} + +static int vbox_bo_verify_access(struct ttm_buffer_object *bo, + struct file *filp) +{ + return 0; +} + +static int vbox_ttm_io_mem_reserve(struct ttm_bo_device *bdev, + struct ttm_mem_reg *mem) +{ + struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; + struct vbox_private *vbox = vbox_bdev(bdev); + + mem->bus.addr = NULL; + mem->bus.offset = 0; + mem->bus.size = mem->num_pages << PAGE_SHIFT; + mem->bus.base = 0; + mem->bus.is_iomem = false; + if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE)) + return -EINVAL; + switch (mem->mem_type) { + case TTM_PL_SYSTEM: + /* system memory */ + return 0; + case TTM_PL_VRAM: + mem->bus.offset = mem->start << PAGE_SHIFT; + mem->bus.base = pci_resource_start(vbox->dev->pdev, 0); + mem->bus.is_iomem = true; + break; + default: + return -EINVAL; + } + return 0; +} + +static void vbox_ttm_io_mem_free(struct ttm_bo_device *bdev, + struct ttm_mem_reg *mem) +{ +} + +static int vbox_bo_move(struct ttm_buffer_object *bo, + bool evict, bool interruptible, + bool no_wait_gpu, struct ttm_mem_reg *new_mem) +{ + return ttm_bo_move_memcpy(bo, interruptible, no_wait_gpu, new_mem); +} + +static void vbox_ttm_backend_destroy(struct ttm_tt *tt) +{ + ttm_tt_fini(tt); + kfree(tt); +} + +static struct ttm_backend_func vbox_tt_backend_func = { + .destroy = &vbox_ttm_backend_destroy, +}; + +static struct ttm_tt *vbox_ttm_tt_create(struct ttm_bo_device *bdev, + unsigned long size, + u32 page_flags, + struct page *dummy_read_page) +{ + struct ttm_tt *tt; + + tt = kzalloc(sizeof(*tt), GFP_KERNEL); + if (!tt) + return NULL; + + tt->func = &vbox_tt_backend_func; + if (ttm_tt_init(tt, bdev, size, page_flags, dummy_read_page)) { + kfree(tt); + return NULL; + } + + return tt; +} + +static int vbox_ttm_tt_populate(struct ttm_tt *ttm) +{ + return ttm_pool_populate(ttm); +} + +static void vbox_ttm_tt_unpopulate(struct ttm_tt *ttm) +{ + ttm_pool_unpopulate(ttm); +} + +struct ttm_bo_driver vbox_bo_driver = { + .ttm_tt_create = vbox_ttm_tt_create, + .ttm_tt_populate = vbox_ttm_tt_populate, + .ttm_tt_unpopulate = vbox_ttm_tt_unpopulate, + .init_mem_type = vbox_bo_init_mem_type, + .eviction_valuable = ttm_bo_eviction_valuable, + .evict_flags = vbox_bo_evict_flags, + .move = vbox_bo_move, + .verify_access = vbox_bo_verify_access, + .io_mem_reserve = &vbox_ttm_io_mem_reserve, + .io_mem_free = &vbox_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, +}; + +int vbox_mm_init(struct vbox_private *vbox) +{ + int ret; + struct drm_device *dev = vbox->dev; + struct ttm_bo_device *bdev = &vbox->ttm.bdev; + + ret = vbox_ttm_global_init(vbox); + if (ret) + return ret; + + ret = ttm_bo_device_init(&vbox->ttm.bdev, + vbox->ttm.bo_global_ref.ref.object, + &vbox_bo_driver, + dev->anon_inode->i_mapping, + DRM_FILE_PAGE_OFFSET, true); + if (ret) { + DRM_ERROR("Error initialising bo driver; %d\n", ret); + goto err_ttm_global_release; + } + + ret = ttm_bo_init_mm(bdev, TTM_PL_VRAM, + vbox->available_vram_size >> PAGE_SHIFT); + if (ret) { + DRM_ERROR("Failed ttm VRAM init: %d\n", ret); + goto err_device_release; + } + +#ifdef DRM_MTRR_WC + vbox->fb_mtrr = drm_mtrr_add(pci_resource_start(dev->pdev, 0), + pci_resource_len(dev->pdev, 0), + DRM_MTRR_WC); +#else + vbox->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0), + pci_resource_len(dev->pdev, 0)); +#endif + return 0; + +err_device_release: + ttm_bo_device_release(&vbox->ttm.bdev); +err_ttm_global_release: + vbox_ttm_global_release(vbox); + return ret; +} + +void vbox_mm_fini(struct vbox_private *vbox) +{ +#ifdef DRM_MTRR_WC + drm_mtrr_del(vbox->fb_mtrr, + pci_resource_start(vbox->dev->pdev, 0), + pci_resource_len(vbox->dev->pdev, 0), DRM_MTRR_WC); +#else + arch_phys_wc_del(vbox->fb_mtrr); +#endif + ttm_bo_device_release(&vbox->ttm.bdev); + vbox_ttm_global_release(vbox); +} + +void vbox_ttm_placement(struct vbox_bo *bo, int domain) +{ + unsigned int i; + u32 c = 0; + + bo->placement.placement = bo->placements; + bo->placement.busy_placement = bo->placements; + + if (domain & TTM_PL_FLAG_VRAM) + bo->placements[c++].flags = + TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM; + if (domain & TTM_PL_FLAG_SYSTEM) + bo->placements[c++].flags = + TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM; + if (!c) + bo->placements[c++].flags = + TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM; + + bo->placement.num_placement = c; + bo->placement.num_busy_placement = c; + + for (i = 0; i < c; ++i) { + bo->placements[i].fpfn = 0; + bo->placements[i].lpfn = 0; + } +} + +int vbox_bo_create(struct drm_device *dev, int size, int align, + u32 flags, struct vbox_bo **pvboxbo) +{ + struct vbox_private *vbox = dev->dev_private; + struct vbox_bo *vboxbo; + size_t acc_size; + int ret; + + vboxbo = kzalloc(sizeof(*vboxbo), GFP_KERNEL); + if (!vboxbo) + return -ENOMEM; + + ret = drm_gem_object_init(dev, &vboxbo->gem, size); + if (ret) + goto err_free_vboxbo; + + vboxbo->bo.bdev = &vbox->ttm.bdev; + + vbox_ttm_placement(vboxbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM); + + acc_size = ttm_bo_dma_acc_size(&vbox->ttm.bdev, size, + sizeof(struct vbox_bo)); + + ret = ttm_bo_init(&vbox->ttm.bdev, &vboxbo->bo, size, + ttm_bo_type_device, &vboxbo->placement, + align >> PAGE_SHIFT, false, NULL, acc_size, + NULL, NULL, vbox_bo_ttm_destroy); + if (ret) + goto err_free_vboxbo; + + *pvboxbo = vboxbo; + + return 0; + +err_free_vboxbo: + kfree(vboxbo); + return ret; +} + +static inline u64 vbox_bo_gpu_offset(struct vbox_bo *bo) +{ + return bo->bo.offset; +} + +int vbox_bo_pin(struct vbox_bo *bo, u32 pl_flag, u64 *gpu_addr) +{ + int i, ret; + + if (bo->pin_count) { + bo->pin_count++; + if (gpu_addr) + *gpu_addr = vbox_bo_gpu_offset(bo); + + return 0; + } + + vbox_ttm_placement(bo, pl_flag); + + for (i = 0; i < bo->placement.num_placement; i++) + bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; + + ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false); + if (ret) + return ret; + + bo->pin_count = 1; + + if (gpu_addr) + *gpu_addr = vbox_bo_gpu_offset(bo); + + return 0; +} + +int vbox_bo_unpin(struct vbox_bo *bo) +{ + int i, ret; + + if (!bo->pin_count) { + DRM_ERROR("unpin bad %p\n", bo); + return 0; + } + bo->pin_count--; + if (bo->pin_count) + return 0; + + for (i = 0; i < bo->placement.num_placement; i++) + bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT; + + ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false); + if (ret) + return ret; + + return 0; +} + +/* + * Move a vbox-owned buffer object to system memory if no one else has it + * pinned. The caller must have pinned it previously, and this call will + * release the caller's pin. + */ +int vbox_bo_push_sysram(struct vbox_bo *bo) +{ + int i, ret; + + if (!bo->pin_count) { + DRM_ERROR("unpin bad %p\n", bo); + return 0; + } + bo->pin_count--; + if (bo->pin_count) + return 0; + + if (bo->kmap.virtual) + ttm_bo_kunmap(&bo->kmap); + + vbox_ttm_placement(bo, TTM_PL_FLAG_SYSTEM); + + for (i = 0; i < bo->placement.num_placement; i++) + bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; + + ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false); + if (ret) { + DRM_ERROR("pushing to VRAM failed\n"); + return ret; + } + + return 0; +} + +int vbox_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct drm_file *file_priv; + struct vbox_private *vbox; + + if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET)) + return -EINVAL; + + file_priv = filp->private_data; + vbox = file_priv->minor->dev->dev_private; + + return ttm_bo_mmap(filp, vma, &vbox->ttm.bdev); +} diff --git a/drivers/staging/vboxvideo/vboxvideo.h b/drivers/staging/vboxvideo/vboxvideo.h new file mode 100644 index 000000000000..d835d75d761c --- /dev/null +++ b/drivers/staging/vboxvideo/vboxvideo.h @@ -0,0 +1,491 @@ +/* + * Copyright (C) 2006-2016 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + */ + +#ifndef __VBOXVIDEO_H__ +#define __VBOXVIDEO_H__ + +/* + * This should be in sync with monitorCount <xsd:maxInclusive value="64"/> in + * src/VBox/Main/xml/VirtualBox-settings-common.xsd + */ +#define VBOX_VIDEO_MAX_SCREENS 64 + +/* + * The last 4096 bytes of the guest VRAM contains the generic info for all + * DualView chunks: sizes and offsets of chunks. This is filled by miniport. + * + * Last 4096 bytes of each chunk contain chunk specific data: framebuffer info, + * etc. This is used exclusively by the corresponding instance of a display + * driver. + * + * The VRAM layout: + * Last 4096 bytes - Adapter information area. + * 4096 bytes aligned miniport heap (value specified in the config rouded up). + * Slack - what left after dividing the VRAM. + * 4096 bytes aligned framebuffers: + * last 4096 bytes of each framebuffer is the display information area. + * + * The Virtual Graphics Adapter information in the guest VRAM is stored by the + * guest video driver using structures prepended by VBOXVIDEOINFOHDR. + * + * When the guest driver writes dword 0 to the VBE_DISPI_INDEX_VBOX_VIDEO + * the host starts to process the info. The first element at the start of + * the 4096 bytes region should be normally be a LINK that points to + * actual information chain. That way the guest driver can have some + * fixed layout of the information memory block and just rewrite + * the link to point to relevant memory chain. + * + * The processing stops at the END element. + * + * The host can access the memory only when the port IO is processed. + * All data that will be needed later must be copied from these 4096 bytes. + * But other VRAM can be used by host until the mode is disabled. + * + * The guest driver writes dword 0xffffffff to the VBE_DISPI_INDEX_VBOX_VIDEO + * to disable the mode. + * + * VBE_DISPI_INDEX_VBOX_VIDEO is used to read the configuration information + * from the host and issue commands to the host. + * + * The guest writes the VBE_DISPI_INDEX_VBOX_VIDEO index register, the the + * following operations with the VBE data register can be performed: + * + * Operation Result + * write 16 bit value NOP + * read 16 bit value count of monitors + * write 32 bit value set the vbox cmd value and the cmd processed by the host + * read 32 bit value result of the last vbox command is returned + */ + +/** + * VBVA command header. + * + * @todo Where does this fit in? + */ +struct vbva_cmd_hdr { + /** Coordinates of affected rectangle. */ + s16 x; + s16 y; + u16 w; + u16 h; +} __packed; + +/** @name VBVA ring defines. + * + * The VBVA ring buffer is suitable for transferring large (< 2GB) amount of + * data. For example big bitmaps which do not fit to the buffer. + * + * Guest starts writing to the buffer by initializing a record entry in the + * records queue. VBVA_F_RECORD_PARTIAL indicates that the record is being + * written. As data is written to the ring buffer, the guest increases + * free_offset. + * + * The host reads the records on flushes and processes all completed records. + * When host encounters situation when only a partial record presents and + * len_and_flags & ~VBVA_F_RECORD_PARTIAL >= VBVA_RING_BUFFER_SIZE - + * VBVA_RING_BUFFER_THRESHOLD, the host fetched all record data and updates + * data_offset. After that on each flush the host continues fetching the data + * until the record is completed. + * + */ +#define VBVA_RING_BUFFER_SIZE (4194304 - 1024) +#define VBVA_RING_BUFFER_THRESHOLD (4096) + +#define VBVA_MAX_RECORDS (64) + +#define VBVA_F_MODE_ENABLED 0x00000001u +#define VBVA_F_MODE_VRDP 0x00000002u +#define VBVA_F_MODE_VRDP_RESET 0x00000004u +#define VBVA_F_MODE_VRDP_ORDER_MASK 0x00000008u + +#define VBVA_F_STATE_PROCESSING 0x00010000u + +#define VBVA_F_RECORD_PARTIAL 0x80000000u + +/** + * VBVA record. + */ +struct vbva_record { + /** The length of the record. Changed by guest. */ + u32 len_and_flags; +} __packed; + +/* + * The minimum HGSMI heap size is PAGE_SIZE (4096 bytes) and is a restriction of + * the runtime heapsimple API. Use minimum 2 pages here, because the info area + * also may contain other data (for example hgsmi_host_flags structure). + */ +#define VBVA_ADAPTER_INFORMATION_SIZE 65536 +#define VBVA_MIN_BUFFER_SIZE 65536 + +/* The value for port IO to let the adapter to interpret the adapter memory. */ +#define VBOX_VIDEO_DISABLE_ADAPTER_MEMORY 0xFFFFFFFF + +/* The value for port IO to let the adapter to interpret the adapter memory. */ +#define VBOX_VIDEO_INTERPRET_ADAPTER_MEMORY 0x00000000 + +/* The value for port IO to let the adapter to interpret the display memory. + * The display number is encoded in low 16 bits. + */ +#define VBOX_VIDEO_INTERPRET_DISPLAY_MEMORY_BASE 0x00010000 + +struct vbva_host_flags { + u32 host_events; + u32 supported_orders; +} __packed; + +struct vbva_buffer { + struct vbva_host_flags host_flags; + + /* The offset where the data start in the buffer. */ + u32 data_offset; + /* The offset where next data must be placed in the buffer. */ + u32 free_offset; + + /* The queue of record descriptions. */ + struct vbva_record records[VBVA_MAX_RECORDS]; + u32 record_first_index; + u32 record_free_index; + + /* Space to leave free when large partial records are transferred. */ + u32 partial_write_tresh; + + u32 data_len; + /* variable size for the rest of the vbva_buffer area in VRAM. */ + u8 data[0]; +} __packed; + +#define VBVA_MAX_RECORD_SIZE (128 * 1024 * 1024) + +/* guest->host commands */ +#define VBVA_QUERY_CONF32 1 +#define VBVA_SET_CONF32 2 +#define VBVA_INFO_VIEW 3 +#define VBVA_INFO_HEAP 4 +#define VBVA_FLUSH 5 +#define VBVA_INFO_SCREEN 6 +#define VBVA_ENABLE 7 +#define VBVA_MOUSE_POINTER_SHAPE 8 +/* informs host about HGSMI caps. see vbva_caps below */ +#define VBVA_INFO_CAPS 12 +/* configures scanline, see VBVASCANLINECFG below */ +#define VBVA_SCANLINE_CFG 13 +/* requests scanline info, see VBVASCANLINEINFO below */ +#define VBVA_SCANLINE_INFO 14 +/* inform host about VBVA Command submission */ +#define VBVA_CMDVBVA_SUBMIT 16 +/* inform host about VBVA Command submission */ +#define VBVA_CMDVBVA_FLUSH 17 +/* G->H DMA command */ +#define VBVA_CMDVBVA_CTL 18 +/* Query most recent mode hints sent */ +#define VBVA_QUERY_MODE_HINTS 19 +/** + * Report the guest virtual desktop position and size for mapping host and + * guest pointer positions. + */ +#define VBVA_REPORT_INPUT_MAPPING 20 +/** Report the guest cursor position and query the host position. */ +#define VBVA_CURSOR_POSITION 21 + +/* host->guest commands */ +#define VBVAHG_EVENT 1 +#define VBVAHG_DISPLAY_CUSTOM 2 + +/* vbva_conf32::index */ +#define VBOX_VBVA_CONF32_MONITOR_COUNT 0 +#define VBOX_VBVA_CONF32_HOST_HEAP_SIZE 1 +/** + * Returns VINF_SUCCESS if the host can report mode hints via VBVA. + * Set value to VERR_NOT_SUPPORTED before calling. + */ +#define VBOX_VBVA_CONF32_MODE_HINT_REPORTING 2 +/** + * Returns VINF_SUCCESS if the host can report guest cursor enabled status via + * VBVA. Set value to VERR_NOT_SUPPORTED before calling. + */ +#define VBOX_VBVA_CONF32_GUEST_CURSOR_REPORTING 3 +/** + * Returns the currently available host cursor capabilities. Available if + * vbva_conf32::VBOX_VBVA_CONF32_GUEST_CURSOR_REPORTING returns success. + * @see VMMDevReqMouseStatus::mouseFeatures. + */ +#define VBOX_VBVA_CONF32_CURSOR_CAPABILITIES 4 +/** Returns the supported flags in vbva_infoscreen::flags. */ +#define VBOX_VBVA_CONF32_SCREEN_FLAGS 5 +/** Returns the max size of VBVA record. */ +#define VBOX_VBVA_CONF32_MAX_RECORD_SIZE 6 + +struct vbva_conf32 { + u32 index; + u32 value; +} __packed; + +/** Reserved for historical reasons. */ +#define VBOX_VBVA_CURSOR_CAPABILITY_RESERVED0 BIT(0) +/** + * Guest cursor capability: can the host show a hardware cursor at the host + * pointer location? + */ +#define VBOX_VBVA_CURSOR_CAPABILITY_HARDWARE BIT(1) +/** Reserved for historical reasons. */ +#define VBOX_VBVA_CURSOR_CAPABILITY_RESERVED2 BIT(2) +/** Reserved for historical reasons. Must always be unset. */ +#define VBOX_VBVA_CURSOR_CAPABILITY_RESERVED3 BIT(3) +/** Reserved for historical reasons. */ +#define VBOX_VBVA_CURSOR_CAPABILITY_RESERVED4 BIT(4) +/** Reserved for historical reasons. */ +#define VBOX_VBVA_CURSOR_CAPABILITY_RESERVED5 BIT(5) + +struct vbva_infoview { + /* Index of the screen, assigned by the guest. */ + u32 view_index; + + /* The screen offset in VRAM, the framebuffer starts here. */ + u32 view_offset; + + /* The size of the VRAM memory that can be used for the view. */ + u32 view_size; + + /* The recommended maximum size of the VRAM memory for the screen. */ + u32 max_screen_size; +} __packed; + +struct vbva_flush { + u32 reserved; +} __packed; + +/* vbva_infoscreen::flags */ +#define VBVA_SCREEN_F_NONE 0x0000 +#define VBVA_SCREEN_F_ACTIVE 0x0001 +/** + * The virtual monitor has been disabled by the guest and should be removed + * by the host and ignored for purposes of pointer position calculation. + */ +#define VBVA_SCREEN_F_DISABLED 0x0002 +/** + * The virtual monitor has been blanked by the guest and should be blacked + * out by the host using width, height, etc values from the vbva_infoscreen + * request. + */ +#define VBVA_SCREEN_F_BLANK 0x0004 +/** + * The virtual monitor has been blanked by the guest and should be blacked + * out by the host using the previous mode values for width. height, etc. + */ +#define VBVA_SCREEN_F_BLANK2 0x0008 + +struct vbva_infoscreen { + /* Which view contains the screen. */ + u32 view_index; + + /* Physical X origin relative to the primary screen. */ + s32 origin_x; + + /* Physical Y origin relative to the primary screen. */ + s32 origin_y; + + /* Offset of visible framebuffer relative to the framebuffer start. */ + u32 start_offset; + + /* The scan line size in bytes. */ + u32 line_size; + + /* Width of the screen. */ + u32 width; + + /* Height of the screen. */ + u32 height; + + /* Color depth. */ + u16 bits_per_pixel; + + /* VBVA_SCREEN_F_* */ + u16 flags; +} __packed; + +/* vbva_enable::flags */ +#define VBVA_F_NONE 0x00000000 +#define VBVA_F_ENABLE 0x00000001 +#define VBVA_F_DISABLE 0x00000002 +/* extended VBVA to be used with WDDM */ +#define VBVA_F_EXTENDED 0x00000004 +/* vbva offset is absolute VRAM offset */ +#define VBVA_F_ABSOFFSET 0x00000008 + +struct vbva_enable { + u32 flags; + u32 offset; + s32 result; +} __packed; + +struct vbva_enable_ex { + struct vbva_enable base; + u32 screen_id; +} __packed; + +struct vbva_mouse_pointer_shape { + /* The host result. */ + s32 result; + + /* VBOX_MOUSE_POINTER_* bit flags. */ + u32 flags; + + /* X coordinate of the hot spot. */ + u32 hot_X; + + /* Y coordinate of the hot spot. */ + u32 hot_y; + + /* Width of the pointer in pixels. */ + u32 width; + + /* Height of the pointer in scanlines. */ + u32 height; + + /* Pointer data. + * + **** + * The data consists of 1 bpp AND mask followed by 32 bpp XOR (color) + * mask. + * + * For pointers without alpha channel the XOR mask pixels are 32 bit + * values: (lsb)BGR0(msb). For pointers with alpha channel the XOR mask + * consists of (lsb)BGRA(msb) 32 bit values. + * + * Guest driver must create the AND mask for pointers with alpha chan., + * so if host does not support alpha, the pointer could be displayed as + * a normal color pointer. The AND mask can be constructed from alpha + * values. For example alpha value >= 0xf0 means bit 0 in the AND mask. + * + * The AND mask is 1 bpp bitmap with byte aligned scanlines. Size of AND + * mask, therefore, is and_len = (width + 7) / 8 * height. The padding + * bits at the end of any scanline are undefined. + * + * The XOR mask follows the AND mask on the next 4 bytes aligned offset: + * u8 *xor = and + (and_len + 3) & ~3 + * Bytes in the gap between the AND and the XOR mask are undefined. + * XOR mask scanlines have no gap between them and size of XOR mask is: + * xor_len = width * 4 * height. + **** + * + * Preallocate 4 bytes for accessing actual data as p->data. + */ + u8 data[4]; +} __packed; + +/** + * @name vbva_mouse_pointer_shape::flags + * @note The VBOX_MOUSE_POINTER_* flags are used in the guest video driver, + * values must be <= 0x8000 and must not be changed. (try make more sense + * of this, please). + * @{ + */ + +/** pointer is visible */ +#define VBOX_MOUSE_POINTER_VISIBLE 0x0001 +/** pointer has alpha channel */ +#define VBOX_MOUSE_POINTER_ALPHA 0x0002 +/** pointerData contains new pointer shape */ +#define VBOX_MOUSE_POINTER_SHAPE 0x0004 + +/** @} */ + +/* + * The guest driver can handle asynch guest cmd completion by reading the + * command offset from io port. + */ +#define VBVACAPS_COMPLETEGCMD_BY_IOREAD 0x00000001 +/* the guest driver can handle video adapter IRQs */ +#define VBVACAPS_IRQ 0x00000002 +/** The guest can read video mode hints sent via VBVA. */ +#define VBVACAPS_VIDEO_MODE_HINTS 0x00000004 +/** The guest can switch to a software cursor on demand. */ +#define VBVACAPS_DISABLE_CURSOR_INTEGRATION 0x00000008 +/** The guest does not depend on host handling the VBE registers. */ +#define VBVACAPS_USE_VBVA_ONLY 0x00000010 + +struct vbva_caps { + s32 rc; + u32 caps; +} __packed; + +/** Query the most recent mode hints received from the host. */ +struct vbva_query_mode_hints { + /** The maximum number of screens to return hints for. */ + u16 hints_queried_count; + /** The size of the mode hint structures directly following this one. */ + u16 hint_structure_guest_size; + /** Return code for the operation. Initialise to VERR_NOT_SUPPORTED. */ + s32 rc; +} __packed; + +/** + * Structure in which a mode hint is returned. The guest allocates an array + * of these immediately after the vbva_query_mode_hints structure. + * To accommodate future extensions, the vbva_query_mode_hints structure + * specifies the size of the vbva_modehint structures allocated by the guest, + * and the host only fills out structure elements which fit into that size. The + * host should fill any unused members (e.g. dx, dy) or structure space on the + * end with ~0. The whole structure can legally be set to ~0 to skip a screen. + */ +struct vbva_modehint { + u32 magic; + u32 cx; + u32 cy; + u32 bpp; /* Which has never been used... */ + u32 display; + u32 dx; /**< X offset into the virtual frame-buffer. */ + u32 dy; /**< Y offset into the virtual frame-buffer. */ + u32 enabled; /* Not flags. Add new members for new flags. */ +} __packed; + +#define VBVAMODEHINT_MAGIC 0x0801add9u + +/** + * Report the rectangle relative to which absolute pointer events should be + * expressed. This information remains valid until the next VBVA resize event + * for any screen, at which time it is reset to the bounding rectangle of all + * virtual screens and must be re-set. + * @see VBVA_REPORT_INPUT_MAPPING. + */ +struct vbva_report_input_mapping { + s32 x; /**< Upper left X co-ordinate relative to the first screen. */ + s32 y; /**< Upper left Y co-ordinate relative to the first screen. */ + u32 cx; /**< Rectangle width. */ + u32 cy; /**< Rectangle height. */ +} __packed; + +/** + * Report the guest cursor position and query the host one. The host may wish + * to use the guest information to re-position its own cursor (though this is + * currently unlikely). + * @see VBVA_CURSOR_POSITION + */ +struct vbva_cursor_position { + u32 report_position; /**< Are we reporting a position? */ + u32 x; /**< Guest cursor X position */ + u32 y; /**< Guest cursor Y position */ +} __packed; + +#endif diff --git a/drivers/staging/vboxvideo/vboxvideo_guest.h b/drivers/staging/vboxvideo/vboxvideo_guest.h new file mode 100644 index 000000000000..d09da841711a --- /dev/null +++ b/drivers/staging/vboxvideo/vboxvideo_guest.h @@ -0,0 +1,95 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef __VBOXVIDEO_GUEST_H__ +#define __VBOXVIDEO_GUEST_H__ + +#include <linux/genalloc.h> +#include "vboxvideo.h" + +/** + * Structure grouping the context needed for sending graphics acceleration + * information to the host via VBVA. Each screen has its own VBVA buffer. + */ +struct vbva_buf_ctx { + /** Offset of the buffer in the VRAM section for the screen */ + u32 buffer_offset; + /** Length of the buffer in bytes */ + u32 buffer_length; + /** Set if we wrote to the buffer faster than the host could read it */ + bool buffer_overflow; + /** VBVA record that we are currently preparing for the host, or NULL */ + struct vbva_record *record; + /** + * Pointer to the VBVA buffer mapped into the current address space. + * Will be NULL if VBVA is not enabled. + */ + struct vbva_buffer *vbva; +}; + +/** + * @name Base HGSMI APIs + * @{ + */ +int hgsmi_report_flags_location(struct gen_pool *ctx, u32 location); +int hgsmi_send_caps_info(struct gen_pool *ctx, u32 caps); +int hgsmi_test_query_conf(struct gen_pool *ctx); +int hgsmi_query_conf(struct gen_pool *ctx, u32 index, u32 *value_ret); +int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, + u32 hot_x, u32 hot_y, u32 width, u32 height, + u8 *pixels, u32 len); +int hgsmi_cursor_position(struct gen_pool *ctx, bool report_position, + u32 x, u32 y, u32 *x_host, u32 *y_host); +/** @} */ + +/** + * @name VBVA APIs + * @{ + */ +bool vbva_enable(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, + struct vbva_buffer *vbva, s32 screen); +void vbva_disable(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, + s32 screen); +bool vbva_buffer_begin_update(struct vbva_buf_ctx *vbva_ctx, + struct gen_pool *ctx); +void vbva_buffer_end_update(struct vbva_buf_ctx *vbva_ctx); +bool vbva_write(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, + const void *p, u32 len); +void vbva_setup_buffer_context(struct vbva_buf_ctx *vbva_ctx, + u32 buffer_offset, u32 buffer_length); +/** @} */ + +/** + * @name Modesetting APIs + * @{ + */ +void hgsmi_process_display_info(struct gen_pool *ctx, u32 display, + s32 origin_x, s32 origin_y, u32 start_offset, + u32 pitch, u32 width, u32 height, + u16 bpp, u16 flags); +int hgsmi_update_input_mapping(struct gen_pool *ctx, s32 origin_x, s32 origin_y, + u32 width, u32 height); +int hgsmi_get_mode_hints(struct gen_pool *ctx, unsigned int screens, + struct vbva_modehint *hints); +/** @} */ + +#endif diff --git a/drivers/staging/vboxvideo/vboxvideo_vbe.h b/drivers/staging/vboxvideo/vboxvideo_vbe.h new file mode 100644 index 000000000000..f842f4d9c80a --- /dev/null +++ b/drivers/staging/vboxvideo/vboxvideo_vbe.h @@ -0,0 +1,84 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef __VBOXVIDEO_VBE_H__ +#define __VBOXVIDEO_VBE_H__ + +/* GUEST <-> HOST Communication API */ + +/** + * @todo FIXME: Either dynamicly ask host for this or put somewhere high in + * physical memory like 0xE0000000. + */ + +#define VBE_DISPI_BANK_ADDRESS 0xA0000 +#define VBE_DISPI_BANK_SIZE_KB 64 + +#define VBE_DISPI_MAX_XRES 16384 +#define VBE_DISPI_MAX_YRES 16384 +#define VBE_DISPI_MAX_BPP 32 + +#define VBE_DISPI_IOPORT_INDEX 0x01CE +#define VBE_DISPI_IOPORT_DATA 0x01CF + +#define VBE_DISPI_IOPORT_DAC_WRITE_INDEX 0x03C8 +#define VBE_DISPI_IOPORT_DAC_DATA 0x03C9 + +#define VBE_DISPI_INDEX_ID 0x0 +#define VBE_DISPI_INDEX_XRES 0x1 +#define VBE_DISPI_INDEX_YRES 0x2 +#define VBE_DISPI_INDEX_BPP 0x3 +#define VBE_DISPI_INDEX_ENABLE 0x4 +#define VBE_DISPI_INDEX_BANK 0x5 +#define VBE_DISPI_INDEX_VIRT_WIDTH 0x6 +#define VBE_DISPI_INDEX_VIRT_HEIGHT 0x7 +#define VBE_DISPI_INDEX_X_OFFSET 0x8 +#define VBE_DISPI_INDEX_Y_OFFSET 0x9 +#define VBE_DISPI_INDEX_VBOX_VIDEO 0xa +#define VBE_DISPI_INDEX_FB_BASE_HI 0xb + +#define VBE_DISPI_ID0 0xB0C0 +#define VBE_DISPI_ID1 0xB0C1 +#define VBE_DISPI_ID2 0xB0C2 +#define VBE_DISPI_ID3 0xB0C3 +#define VBE_DISPI_ID4 0xB0C4 + +#define VBE_DISPI_ID_VBOX_VIDEO 0xBE00 +/* The VBOX interface id. Indicates support for VBVA shared memory interface. */ +#define VBE_DISPI_ID_HGSMI 0xBE01 +#define VBE_DISPI_ID_ANYX 0xBE02 + +#define VBE_DISPI_DISABLED 0x00 +#define VBE_DISPI_ENABLED 0x01 +#define VBE_DISPI_GETCAPS 0x02 +#define VBE_DISPI_8BIT_DAC 0x20 +/** + * @note this definition is a BOCHS legacy, used only in the video BIOS + * code and ignored by the emulated hardware. + */ +#define VBE_DISPI_LFB_ENABLED 0x40 +#define VBE_DISPI_NOCLEARMEM 0x80 + +#define VGA_PORT_HGSMI_HOST 0x3b0 +#define VGA_PORT_HGSMI_GUEST 0x3d0 + +#endif diff --git a/drivers/staging/vboxvideo/vbva_base.c b/drivers/staging/vboxvideo/vbva_base.c new file mode 100644 index 000000000000..c10c782f94e1 --- /dev/null +++ b/drivers/staging/vboxvideo/vbva_base.c @@ -0,0 +1,233 @@ +/* + * Copyright (C) 2006-2017 Oracle Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "vbox_drv.h" +#include "vbox_err.h" +#include "vboxvideo_guest.h" +#include "hgsmi_channels.h" + +/* + * There is a hardware ring buffer in the graphics device video RAM, formerly + * in the VBox VMMDev PCI memory space. + * All graphics commands go there serialized by vbva_buffer_begin_update. + * and vbva_buffer_end_update. + * + * free_offset is writing position. data_offset is reading position. + * free_offset == data_offset means buffer is empty. + * There must be always gap between data_offset and free_offset when data + * are in the buffer. + * Guest only changes free_offset, host changes data_offset. + */ + +static u32 vbva_buffer_available(const struct vbva_buffer *vbva) +{ + s32 diff = vbva->data_offset - vbva->free_offset; + + return diff > 0 ? diff : vbva->data_len + diff; +} + +static void vbva_buffer_place_data_at(struct vbva_buf_ctx *vbva_ctx, + const void *p, u32 len, u32 offset) +{ + struct vbva_buffer *vbva = vbva_ctx->vbva; + u32 bytes_till_boundary = vbva->data_len - offset; + u8 *dst = &vbva->data[offset]; + s32 diff = len - bytes_till_boundary; + + if (diff <= 0) { + /* Chunk will not cross buffer boundary. */ + memcpy(dst, p, len); + } else { + /* Chunk crosses buffer boundary. */ + memcpy(dst, p, bytes_till_boundary); + memcpy(&vbva->data[0], (u8 *)p + bytes_till_boundary, diff); + } +} + +static void vbva_buffer_flush(struct gen_pool *ctx) +{ + struct vbva_flush *p; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, VBVA_FLUSH); + if (!p) + return; + + p->reserved = 0; + + hgsmi_buffer_submit(ctx, p); + hgsmi_buffer_free(ctx, p); +} + +bool vbva_write(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, + const void *p, u32 len) +{ + struct vbva_record *record; + struct vbva_buffer *vbva; + u32 available; + + vbva = vbva_ctx->vbva; + record = vbva_ctx->record; + + if (!vbva || vbva_ctx->buffer_overflow || + !record || !(record->len_and_flags & VBVA_F_RECORD_PARTIAL)) + return false; + + available = vbva_buffer_available(vbva); + + while (len > 0) { + u32 chunk = len; + + if (chunk >= available) { + vbva_buffer_flush(ctx); + available = vbva_buffer_available(vbva); + } + + if (chunk >= available) { + if (WARN_ON(available <= vbva->partial_write_tresh)) { + vbva_ctx->buffer_overflow = true; + return false; + } + chunk = available - vbva->partial_write_tresh; + } + + vbva_buffer_place_data_at(vbva_ctx, p, chunk, + vbva->free_offset); + + vbva->free_offset = (vbva->free_offset + chunk) % + vbva->data_len; + record->len_and_flags += chunk; + available -= chunk; + len -= chunk; + p += chunk; + } + + return true; +} + +static bool vbva_inform_host(struct vbva_buf_ctx *vbva_ctx, + struct gen_pool *ctx, s32 screen, bool enable) +{ + struct vbva_enable_ex *p; + bool ret; + + p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, VBVA_ENABLE); + if (!p) + return false; + + p->base.flags = enable ? VBVA_F_ENABLE : VBVA_F_DISABLE; + p->base.offset = vbva_ctx->buffer_offset; + p->base.result = VERR_NOT_SUPPORTED; + if (screen >= 0) { + p->base.flags |= VBVA_F_EXTENDED | VBVA_F_ABSOFFSET; + p->screen_id = screen; + } + + hgsmi_buffer_submit(ctx, p); + + if (enable) + ret = RT_SUCCESS(p->base.result); + else + ret = true; + + hgsmi_buffer_free(ctx, p); + + return ret; +} + +bool vbva_enable(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, + struct vbva_buffer *vbva, s32 screen) +{ + bool ret = false; + + memset(vbva, 0, sizeof(*vbva)); + vbva->partial_write_tresh = 256; + vbva->data_len = vbva_ctx->buffer_length - sizeof(struct vbva_buffer); + vbva_ctx->vbva = vbva; + + ret = vbva_inform_host(vbva_ctx, ctx, screen, true); + if (!ret) + vbva_disable(vbva_ctx, ctx, screen); + + return ret; +} + +void vbva_disable(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, + s32 screen) +{ + vbva_ctx->buffer_overflow = false; + vbva_ctx->record = NULL; + vbva_ctx->vbva = NULL; + + vbva_inform_host(vbva_ctx, ctx, screen, false); +} + +bool vbva_buffer_begin_update(struct vbva_buf_ctx *vbva_ctx, + struct gen_pool *ctx) +{ + struct vbva_record *record; + u32 next; + + if (!vbva_ctx->vbva || + !(vbva_ctx->vbva->host_flags.host_events & VBVA_F_MODE_ENABLED)) + return false; + + WARN_ON(vbva_ctx->buffer_overflow || vbva_ctx->record); + + next = (vbva_ctx->vbva->record_free_index + 1) % VBVA_MAX_RECORDS; + + /* Flush if all slots in the records queue are used */ + if (next == vbva_ctx->vbva->record_first_index) + vbva_buffer_flush(ctx); + + /* If even after flush there is no place then fail the request */ + if (next == vbva_ctx->vbva->record_first_index) + return false; + + record = &vbva_ctx->vbva->records[vbva_ctx->vbva->record_free_index]; + record->len_and_flags = VBVA_F_RECORD_PARTIAL; + vbva_ctx->vbva->record_free_index = next; + /* Remember which record we are using. */ + vbva_ctx->record = record; + + return true; +} + +void vbva_buffer_end_update(struct vbva_buf_ctx *vbva_ctx) +{ + struct vbva_record *record = vbva_ctx->record; + + WARN_ON(!vbva_ctx->vbva || !record || + !(record->len_and_flags & VBVA_F_RECORD_PARTIAL)); + + /* Mark the record completed. */ + record->len_and_flags &= ~VBVA_F_RECORD_PARTIAL; + + vbva_ctx->buffer_overflow = false; + vbva_ctx->record = NULL; +} + +void vbva_setup_buffer_context(struct vbva_buf_ctx *vbva_ctx, + u32 buffer_offset, u32 buffer_length) +{ + vbva_ctx->buffer_offset = buffer_offset; + vbva_ctx->buffer_length = buffer_length; +} diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 030bec855d86..314ffac50bb8 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -3391,7 +3391,6 @@ static int vchiq_probe(struct platform_device *pdev) struct device_node *fw_node; struct rpi_firmware *fw; int err; - void *ptr_err; fw_node = of_parse_phandle(pdev->dev.of_node, "firmware", 0); if (!fw_node) { @@ -3427,14 +3426,14 @@ static int vchiq_probe(struct platform_device *pdev) /* create sysfs entries */ vchiq_class = class_create(THIS_MODULE, DEVICE_NAME); - ptr_err = vchiq_class; - if (IS_ERR(ptr_err)) + err = PTR_ERR(vchiq_class); + if (IS_ERR(vchiq_class)) goto failed_class_create; vchiq_dev = device_create(vchiq_class, NULL, vchiq_devid, NULL, "vchiq"); - ptr_err = vchiq_dev; - if (IS_ERR(ptr_err)) + err = PTR_ERR(vchiq_dev); + if (IS_ERR(vchiq_dev)) goto failed_device_create; /* create debugfs entries */ @@ -3455,7 +3454,6 @@ failed_device_create: class_destroy(vchiq_class); failed_class_create: cdev_del(&vchiq_cdev); - err = PTR_ERR(ptr_err); failed_cdev_add: unregister_chrdev_region(vchiq_devid, 1); failed_platform_init: diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index ab3e8f410444..40219a706309 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -281,9 +281,11 @@ static struct nvmem_device *register_nvmem(struct tb_switch *sw, int id, if (active) { config.name = "nvm_active"; config.reg_read = tb_switch_nvm_read; + config.read_only = true; } else { config.name = "nvm_non_active"; config.reg_write = tb_switch_nvm_write; + config.root_only = true; } config.id = id; @@ -292,7 +294,6 @@ static struct nvmem_device *register_nvmem(struct tb_switch *sw, int id, config.size = size; config.dev = &sw->dev; config.owner = THIS_MODULE; - config.root_only = true; config.priv = sw; return nvmem_register(&config); diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index d1399aac05a1..284749fb0f6b 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -448,48 +448,6 @@ err: return retval; } -/** - * pty_open_peer - open the peer of a pty - * @tty: the peer of the pty being opened - * - * Open the cached dentry in tty->link, providing a safe way for userspace - * to get the slave end of a pty (where they have the master fd and cannot - * access or trust the mount namespace /dev/pts was mounted inside). - */ -static struct file *pty_open_peer(struct tty_struct *tty, int flags) -{ - if (tty->driver->subtype != PTY_TYPE_MASTER) - return ERR_PTR(-EIO); - return dentry_open(tty->link->driver_data, flags, current_cred()); -} - -static int pty_get_peer(struct tty_struct *tty, int flags) -{ - int fd = -1; - struct file *filp = NULL; - int retval = -EINVAL; - - fd = get_unused_fd_flags(0); - if (fd < 0) { - retval = fd; - goto err; - } - - filp = pty_open_peer(tty, flags); - if (IS_ERR(filp)) { - retval = PTR_ERR(filp); - goto err_put; - } - - fd_install(fd, filp); - return fd; - -err_put: - put_unused_fd(fd); -err: - return retval; -} - static void pty_cleanup(struct tty_struct *tty) { tty_port_put(tty->port); @@ -646,9 +604,50 @@ static inline void legacy_pty_init(void) { } /* Unix98 devices */ #ifdef CONFIG_UNIX98_PTYS - static struct cdev ptmx_cdev; +/** + * pty_open_peer - open the peer of a pty + * @tty: the peer of the pty being opened + * + * Open the cached dentry in tty->link, providing a safe way for userspace + * to get the slave end of a pty (where they have the master fd and cannot + * access or trust the mount namespace /dev/pts was mounted inside). + */ +static struct file *pty_open_peer(struct tty_struct *tty, int flags) +{ + if (tty->driver->subtype != PTY_TYPE_MASTER) + return ERR_PTR(-EIO); + return dentry_open(tty->link->driver_data, flags, current_cred()); +} + +static int pty_get_peer(struct tty_struct *tty, int flags) +{ + int fd = -1; + struct file *filp = NULL; + int retval = -EINVAL; + + fd = get_unused_fd_flags(0); + if (fd < 0) { + retval = fd; + goto err; + } + + filp = pty_open_peer(tty, flags); + if (IS_ERR(filp)) { + retval = PTR_ERR(filp); + goto err_put; + } + + fd_install(fd, filp); + return fd; + +err_put: + put_unused_fd(fd); +err: + return retval; +} + static int pty_unix98_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 343de8c384b0..898dcb091a27 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -619,6 +619,12 @@ static unsigned int lpuart32_tx_empty(struct uart_port *port) TIOCSER_TEMT : 0; } +static bool lpuart_is_32(struct lpuart_port *sport) +{ + return sport->port.iotype == UPIO_MEM32 || + sport->port.iotype == UPIO_MEM32BE; +} + static irqreturn_t lpuart_txint(int irq, void *dev_id) { struct lpuart_port *sport = dev_id; @@ -627,7 +633,7 @@ static irqreturn_t lpuart_txint(int irq, void *dev_id) spin_lock_irqsave(&sport->port.lock, flags); if (sport->port.x_char) { - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) lpuart32_write(&sport->port, sport->port.x_char, UARTDATA); else writeb(sport->port.x_char, sport->port.membase + UARTDR); @@ -635,14 +641,14 @@ static irqreturn_t lpuart_txint(int irq, void *dev_id) } if (uart_circ_empty(xmit) || uart_tx_stopped(&sport->port)) { - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) lpuart32_stop_tx(&sport->port); else lpuart_stop_tx(&sport->port); goto out; } - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) lpuart32_transmit_buffer(sport); else lpuart_transmit_buffer(sport); @@ -1978,12 +1984,12 @@ static int __init lpuart_console_setup(struct console *co, char *options) if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) lpuart32_console_get_options(sport, &baud, &parity, &bits); else lpuart_console_get_options(sport, &baud, &parity, &bits); - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) lpuart32_setup_watermark(sport); else lpuart_setup_watermark(sport); @@ -2118,7 +2124,7 @@ static int lpuart_probe(struct platform_device *pdev) } sport->port.irq = ret; sport->port.iotype = sdata->iotype; - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) sport->port.ops = &lpuart32_pops; else sport->port.ops = &lpuart_pops; @@ -2145,7 +2151,7 @@ static int lpuart_probe(struct platform_device *pdev) platform_set_drvdata(pdev, &sport->port); - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) + if (lpuart_is_32(sport)) lpuart_reg.cons = LPUART32_CONSOLE; else lpuart_reg.cons = LPUART_CONSOLE; @@ -2198,7 +2204,7 @@ static int lpuart_suspend(struct device *dev) struct lpuart_port *sport = dev_get_drvdata(dev); unsigned long temp; - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) { + if (lpuart_is_32(sport)) { /* disable Rx/Tx and interrupts */ temp = lpuart32_read(&sport->port, UARTCTRL); temp &= ~(UARTCTRL_TE | UARTCTRL_TIE | UARTCTRL_TCIE); @@ -2249,7 +2255,7 @@ static int lpuart_resume(struct device *dev) if (sport->port.suspended && !sport->port.irq_wake) clk_prepare_enable(sport->clk); - if (sport->port.iotype & (UPIO_MEM32 | UPIO_MEM32BE)) { + if (lpuart_is_32(sport)) { lpuart32_setup_watermark(sport); temp = lpuart32_read(&sport->port, UARTCTRL); temp |= (UARTCTRL_RIE | UARTCTRL_TIE | UARTCTRL_RE | diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 9e3162bf3bd1..80934e7bd67f 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -186,11 +186,6 @@ #define UART_NR 8 -/* RX DMA buffer periods */ -#define RX_DMA_PERIODS 4 -#define RX_BUF_SIZE (PAGE_SIZE) - - /* i.MX21 type uart runs on all i.mx except i.MX1 and i.MX6q */ enum imx_uart_type { IMX1_UART, @@ -226,7 +221,6 @@ struct imx_port { struct dma_chan *dma_chan_rx, *dma_chan_tx; struct scatterlist rx_sgl, tx_sgl[2]; void *rx_buf; - unsigned int rx_buf_size; struct circ_buf rx_ring; unsigned int rx_periods; dma_cookie_t rx_cookie; @@ -464,7 +458,7 @@ static inline void imx_transmit_buffer(struct imx_port *sport) } } - while (!uart_circ_empty(xmit) && + while (!uart_circ_empty(xmit) && !sport->dma_is_txing && !(readl(sport->port.membase + uts_reg(sport)) & UTS_TXFULL)) { /* send xmit->buf[xmit->tail] * out the port here */ @@ -967,6 +961,8 @@ static void imx_timeout(unsigned long data) } } +#define RX_BUF_SIZE (PAGE_SIZE) + /* * There are two kinds of RX DMA interrupts(such as in the MX6Q): * [1] the RX DMA buffer is full. @@ -1049,6 +1045,9 @@ static void dma_rx_callback(void *data) } } +/* RX DMA buffer periods */ +#define RX_DMA_PERIODS 4 + static int start_rx_dma(struct imx_port *sport) { struct scatterlist *sgl = &sport->rx_sgl; @@ -1059,8 +1058,9 @@ static int start_rx_dma(struct imx_port *sport) sport->rx_ring.head = 0; sport->rx_ring.tail = 0; + sport->rx_periods = RX_DMA_PERIODS; - sg_init_one(sgl, sport->rx_buf, sport->rx_buf_size); + sg_init_one(sgl, sport->rx_buf, RX_BUF_SIZE); ret = dma_map_sg(dev, sgl, 1, DMA_FROM_DEVICE); if (ret == 0) { dev_err(dev, "DMA mapping error for RX.\n"); @@ -1171,7 +1171,7 @@ static int imx_uart_dma_init(struct imx_port *sport) goto err; } - sport->rx_buf = kzalloc(sport->rx_buf_size, GFP_KERNEL); + sport->rx_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!sport->rx_buf) { ret = -ENOMEM; goto err; @@ -2036,7 +2036,6 @@ static int serial_imx_probe_dt(struct imx_port *sport, { struct device_node *np = pdev->dev.of_node; int ret; - u32 dma_buf_size[2]; sport->devdata = of_device_get_match_data(&pdev->dev); if (!sport->devdata) @@ -2060,14 +2059,6 @@ static int serial_imx_probe_dt(struct imx_port *sport, if (of_get_property(np, "rts-gpios", NULL)) sport->have_rtsgpio = 1; - if (!of_property_read_u32_array(np, "fsl,dma-size", dma_buf_size, 2)) { - sport->rx_buf_size = dma_buf_size[0] * dma_buf_size[1]; - sport->rx_periods = dma_buf_size[1]; - } else { - sport->rx_buf_size = RX_BUF_SIZE; - sport->rx_periods = RX_DMA_PERIODS; - } - return 0; } #else diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index da5ddfc14778..e08b16b070c0 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1085,10 +1085,12 @@ static ssize_t rx_trigger_store(struct device *dev, { struct uart_port *port = dev_get_drvdata(dev); struct sci_port *sci = to_sci_port(port); + int ret; long r; - if (kstrtol(buf, 0, &r) == -EINVAL) - return -EINVAL; + ret = kstrtol(buf, 0, &r); + if (ret) + return ret; sci->rx_trigger = scif_set_rtrg(port, r); if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) @@ -1116,10 +1118,12 @@ static ssize_t rx_fifo_timeout_store(struct device *dev, { struct uart_port *port = dev_get_drvdata(dev); struct sci_port *sci = to_sci_port(port); + int ret; long r; - if (kstrtol(buf, 0, &r) == -EINVAL) - return -EINVAL; + ret = kstrtol(buf, 0, &r); + if (ret) + return ret; sci->rx_fifo_timeout = r; scif_set_rtrg(port, 1); if (r > 0) diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c index f5335be344f6..6b0ca65027d0 100644 --- a/drivers/tty/serial/st-asc.c +++ b/drivers/tty/serial/st-asc.c @@ -758,6 +758,7 @@ static int asc_init_port(struct asc_port *ascport, if (IS_ERR(ascport->pinctrl)) { ret = PTR_ERR(ascport->pinctrl); dev_err(&pdev->dev, "Failed to get Pinctrl: %d\n", ret); + return ret; } ascport->states[DEFAULT] = diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 5357d83bbda2..5e056064259c 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1829,6 +1829,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x1576, 0x03b1), /* Maretron USB100 */ .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ }, + { USB_DEVICE(0xfff0, 0x0100), /* DATECS FP-2000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index bc3b3fda5000..c4066cd77e47 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3573,6 +3573,9 @@ irq_retry: /* Report disconnection if it is not already done. */ dwc2_hsotg_disconnect(hsotg); + /* Reset device address to zero */ + __bic32(hsotg->regs + DCFG, DCFG_DEVADDR_MASK); + if (usb_status & GOTGCTL_BSESVLD && connected) dwc2_hsotg_core_init_disconnected(hsotg, true); } diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 326b302fc440..03474d3575ab 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -766,15 +766,15 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc->maximum_speed = USB_SPEED_HIGH; } - ret = dwc3_core_soft_reset(dwc); + ret = dwc3_core_get_phy(dwc); if (ret) goto err0; - ret = dwc3_phy_setup(dwc); + ret = dwc3_core_soft_reset(dwc); if (ret) goto err0; - ret = dwc3_core_get_phy(dwc); + ret = dwc3_phy_setup(dwc); if (ret) goto err0; diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index 98926504b55b..f5aaa0cf3873 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -512,15 +512,6 @@ static int dwc3_omap_probe(struct platform_device *pdev) /* check the DMA Status */ reg = dwc3_omap_readl(omap->base, USBOTGSS_SYSCONFIG); - irq_set_status_flags(omap->irq, IRQ_NOAUTOEN); - ret = devm_request_threaded_irq(dev, omap->irq, dwc3_omap_interrupt, - dwc3_omap_interrupt_thread, IRQF_SHARED, - "dwc3-omap", omap); - if (ret) { - dev_err(dev, "failed to request IRQ #%d --> %d\n", - omap->irq, ret); - goto err1; - } ret = dwc3_omap_extcon_register(omap); if (ret < 0) @@ -532,8 +523,15 @@ static int dwc3_omap_probe(struct platform_device *pdev) goto err1; } + ret = devm_request_threaded_irq(dev, omap->irq, dwc3_omap_interrupt, + dwc3_omap_interrupt_thread, IRQF_SHARED, + "dwc3-omap", omap); + if (ret) { + dev_err(dev, "failed to request IRQ #%d --> %d\n", + omap->irq, ret); + goto err1; + } dwc3_omap_enable_irqs(omap); - enable_irq(omap->irq); return 0; err1: diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 9e41605a276b..6b299c7b7656 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -191,14 +191,16 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req, req->started = false; list_del(&req->list); - req->trb = NULL; req->remaining = 0; if (req->request.status == -EINPROGRESS) req->request.status = status; - usb_gadget_unmap_request_by_dev(dwc->sysdev, - &req->request, req->direction); + if (req->trb) + usb_gadget_unmap_request_by_dev(dwc->sysdev, + &req->request, req->direction); + + req->trb = NULL; trace_dwc3_gadget_giveback(req); diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index e80b9c123a9d..f95bddd6513f 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2490,7 +2490,7 @@ static int fsg_main_thread(void *common_) int i; down_write(&common->filesem); - for (i = 0; i < ARRAY_SIZE(common->luns); --i) { + for (i = 0; i < ARRAY_SIZE(common->luns); i++) { struct fsg_lun *curlun = common->luns[i]; if (!curlun || !fsg_lun_is_open(curlun)) continue; diff --git a/drivers/usb/gadget/function/f_uac1.c b/drivers/usb/gadget/function/f_uac1.c index 8656f84e17d9..29efbedc91f9 100644 --- a/drivers/usb/gadget/function/f_uac1.c +++ b/drivers/usb/gadget/function/f_uac1.c @@ -92,9 +92,9 @@ static struct uac_input_terminal_descriptor usb_out_it_desc = { .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubtype = UAC_INPUT_TERMINAL, .bTerminalID = USB_OUT_IT_ID, - .wTerminalType = UAC_TERMINAL_STREAMING, + .wTerminalType = cpu_to_le16(UAC_TERMINAL_STREAMING), .bAssocTerminal = 0, - .wChannelConfig = 0x3, + .wChannelConfig = cpu_to_le16(0x3), }; #define IO_OUT_OT_ID 2 @@ -103,7 +103,7 @@ static struct uac1_output_terminal_descriptor io_out_ot_desc = { .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubtype = UAC_OUTPUT_TERMINAL, .bTerminalID = IO_OUT_OT_ID, - .wTerminalType = UAC_OUTPUT_TERMINAL_SPEAKER, + .wTerminalType = cpu_to_le16(UAC_OUTPUT_TERMINAL_SPEAKER), .bAssocTerminal = 0, .bSourceID = USB_OUT_IT_ID, }; @@ -114,9 +114,9 @@ static struct uac_input_terminal_descriptor io_in_it_desc = { .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubtype = UAC_INPUT_TERMINAL, .bTerminalID = IO_IN_IT_ID, - .wTerminalType = UAC_INPUT_TERMINAL_MICROPHONE, + .wTerminalType = cpu_to_le16(UAC_INPUT_TERMINAL_MICROPHONE), .bAssocTerminal = 0, - .wChannelConfig = 0x3, + .wChannelConfig = cpu_to_le16(0x3), }; #define USB_IN_OT_ID 4 @@ -125,7 +125,7 @@ static struct uac1_output_terminal_descriptor usb_in_ot_desc = { .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubtype = UAC_OUTPUT_TERMINAL, .bTerminalID = USB_IN_OT_ID, - .wTerminalType = UAC_TERMINAL_STREAMING, + .wTerminalType = cpu_to_le16(UAC_TERMINAL_STREAMING), .bAssocTerminal = 0, .bSourceID = IO_IN_IT_ID, }; @@ -174,7 +174,7 @@ static struct uac1_as_header_descriptor as_out_header_desc = { .bDescriptorSubtype = UAC_AS_GENERAL, .bTerminalLink = USB_OUT_IT_ID, .bDelay = 1, - .wFormatTag = UAC_FORMAT_TYPE_I_PCM, + .wFormatTag = cpu_to_le16(UAC_FORMAT_TYPE_I_PCM), }; static struct uac1_as_header_descriptor as_in_header_desc = { @@ -183,7 +183,7 @@ static struct uac1_as_header_descriptor as_in_header_desc = { .bDescriptorSubtype = UAC_AS_GENERAL, .bTerminalLink = USB_IN_OT_ID, .bDelay = 1, - .wFormatTag = UAC_FORMAT_TYPE_I_PCM, + .wFormatTag = cpu_to_le16(UAC_FORMAT_TYPE_I_PCM), }; DECLARE_UAC_FORMAT_TYPE_I_DISCRETE_DESC(1); @@ -606,8 +606,8 @@ static int f_audio_bind(struct usb_configuration *c, struct usb_function *f) if (status) goto fail; - audio->out_ep_maxpsize = as_out_ep_desc.wMaxPacketSize; - audio->in_ep_maxpsize = as_in_ep_desc.wMaxPacketSize; + audio->out_ep_maxpsize = le16_to_cpu(as_out_ep_desc.wMaxPacketSize); + audio->in_ep_maxpsize = le16_to_cpu(as_in_ep_desc.wMaxPacketSize); audio->params.c_chmask = audio_opts->c_chmask; audio->params.c_srate = audio_opts->c_srate; audio->params.c_ssize = audio_opts->c_ssize; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 9082ce261e70..f05c3f3e6103 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -168,7 +168,7 @@ static struct uac2_input_terminal_descriptor usb_out_it_desc = { .bAssocTerminal = 0, .bCSourceID = USB_OUT_CLK_ID, .iChannelNames = 0, - .bmControls = (CONTROL_RDWR << COPY_CTRL), + .bmControls = cpu_to_le16(CONTROL_RDWR << COPY_CTRL), }; /* Input Terminal for I/O-In */ @@ -182,7 +182,7 @@ static struct uac2_input_terminal_descriptor io_in_it_desc = { .bAssocTerminal = 0, .bCSourceID = USB_IN_CLK_ID, .iChannelNames = 0, - .bmControls = (CONTROL_RDWR << COPY_CTRL), + .bmControls = cpu_to_le16(CONTROL_RDWR << COPY_CTRL), }; /* Ouput Terminal for USB_IN */ @@ -196,7 +196,7 @@ static struct uac2_output_terminal_descriptor usb_in_ot_desc = { .bAssocTerminal = 0, .bSourceID = IO_IN_IT_ID, .bCSourceID = USB_IN_CLK_ID, - .bmControls = (CONTROL_RDWR << COPY_CTRL), + .bmControls = cpu_to_le16(CONTROL_RDWR << COPY_CTRL), }; /* Ouput Terminal for I/O-Out */ @@ -210,7 +210,7 @@ static struct uac2_output_terminal_descriptor io_out_ot_desc = { .bAssocTerminal = 0, .bSourceID = USB_OUT_IT_ID, .bCSourceID = USB_OUT_CLK_ID, - .bmControls = (CONTROL_RDWR << COPY_CTRL), + .bmControls = cpu_to_le16(CONTROL_RDWR << COPY_CTRL), }; static struct uac2_ac_header_descriptor ac_hdr_desc = { @@ -220,9 +220,10 @@ static struct uac2_ac_header_descriptor ac_hdr_desc = { .bDescriptorSubtype = UAC_MS_HEADER, .bcdADC = cpu_to_le16(0x200), .bCategory = UAC2_FUNCTION_IO_BOX, - .wTotalLength = sizeof in_clk_src_desc + sizeof out_clk_src_desc - + sizeof usb_out_it_desc + sizeof io_in_it_desc - + sizeof usb_in_ot_desc + sizeof io_out_ot_desc, + .wTotalLength = cpu_to_le16(sizeof in_clk_src_desc + + sizeof out_clk_src_desc + sizeof usb_out_it_desc + + sizeof io_in_it_desc + sizeof usb_in_ot_desc + + sizeof io_out_ot_desc), .bmControls = 0, }; @@ -569,10 +570,12 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) return ret; } - agdev->in_ep_maxpsize = max(fs_epin_desc.wMaxPacketSize, - hs_epin_desc.wMaxPacketSize); - agdev->out_ep_maxpsize = max(fs_epout_desc.wMaxPacketSize, - hs_epout_desc.wMaxPacketSize); + agdev->in_ep_maxpsize = max_t(u16, + le16_to_cpu(fs_epin_desc.wMaxPacketSize), + le16_to_cpu(hs_epin_desc.wMaxPacketSize)); + agdev->out_ep_maxpsize = max_t(u16, + le16_to_cpu(fs_epout_desc.wMaxPacketSize), + le16_to_cpu(hs_epout_desc.wMaxPacketSize)); hs_epout_desc.bEndpointAddress = fs_epout_desc.bEndpointAddress; hs_epin_desc.bEndpointAddress = fs_epin_desc.bEndpointAddress; diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig index 9ffb11ec9ed9..7cd5c969fcbe 100644 --- a/drivers/usb/gadget/udc/Kconfig +++ b/drivers/usb/gadget/udc/Kconfig @@ -192,7 +192,7 @@ config USB_RENESAS_USBHS_UDC config USB_RENESAS_USB3 tristate 'Renesas USB3.0 Peripheral controller' depends on ARCH_RENESAS || COMPILE_TEST - depends on EXTCON + depends on EXTCON && HAS_DMA help Renesas USB3.0 Peripheral controller is a USB peripheral controller that supports super, high, and full speed USB 3.0 data transfers. @@ -257,6 +257,7 @@ config USB_MV_U3D config USB_SNP_CORE depends on (USB_AMD5536UDC || USB_SNP_UDC_PLAT) + depends on HAS_DMA tristate help This enables core driver support for Synopsys USB 2.0 Device @@ -271,7 +272,7 @@ config USB_SNP_CORE config USB_SNP_UDC_PLAT tristate "Synopsys USB 2.0 Device controller" - depends on (USB_GADGET && OF) + depends on USB_GADGET && OF && HAS_DMA select USB_GADGET_DUALSPEED select USB_SNP_CORE default ARCH_BCM_IPROC diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index d8278322d5ac..62dc9c7798e7 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -89,6 +89,9 @@ /* USB_COM_CON */ #define USB_COM_CON_CONF BIT(24) +#define USB_COM_CON_PN_WDATAIF_NL BIT(23) +#define USB_COM_CON_PN_RDATAIF_NL BIT(22) +#define USB_COM_CON_PN_LSTTR_PP BIT(21) #define USB_COM_CON_SPD_MODE BIT(17) #define USB_COM_CON_EP0_EN BIT(16) #define USB_COM_CON_DEV_ADDR_SHIFT 8 @@ -686,6 +689,9 @@ static void renesas_usb3_init_controller(struct renesas_usb3 *usb3) { usb3_init_axi_bridge(usb3); usb3_init_epc_registers(usb3); + usb3_set_bit(usb3, USB_COM_CON_PN_WDATAIF_NL | + USB_COM_CON_PN_RDATAIF_NL | USB_COM_CON_PN_LSTTR_PP, + USB3_USB_COM_CON); usb3_write(usb3, USB_OTG_IDMON, USB3_USB_OTG_INT_STA); usb3_write(usb3, USB_OTG_IDMON, USB3_USB_OTG_INT_ENA); @@ -1369,7 +1375,7 @@ static int renesas_usb3_dma_free_prd(struct renesas_usb3 *usb3, usb3_for_each_dma(usb3, dma, i) { if (dma->prd) { - dma_free_coherent(dev, USB3_DMA_MAX_XFER_SIZE, + dma_free_coherent(dev, USB3_DMA_PRD_SIZE, dma->prd, dma->prd_dma); dma->prd = NULL; } @@ -1409,12 +1415,12 @@ static void usb3_start_pipen(struct renesas_usb3_ep *usb3_ep, int ret = -EAGAIN; u32 enable_bits = 0; + spin_lock_irqsave(&usb3->lock, flags); if (usb3_ep->halt || usb3_ep->started) - return; + goto out; if (usb3_req != usb3_req_first) - return; + goto out; - spin_lock_irqsave(&usb3->lock, flags); if (usb3_pn_change(usb3, usb3_ep->num) < 0) goto out; diff --git a/drivers/usb/gadget/udc/snps_udc_plat.c b/drivers/usb/gadget/udc/snps_udc_plat.c index 2e11f19e07ae..f7b4d0f159e4 100644 --- a/drivers/usb/gadget/udc/snps_udc_plat.c +++ b/drivers/usb/gadget/udc/snps_udc_plat.c @@ -28,7 +28,7 @@ /* description */ #define UDC_MOD_DESCRIPTION "Synopsys UDC platform driver" -void start_udc(struct udc *udc) +static void start_udc(struct udc *udc) { if (udc->driver) { dev_info(udc->dev, "Connecting...\n"); @@ -38,7 +38,7 @@ void start_udc(struct udc *udc) } } -void stop_udc(struct udc *udc) +static void stop_udc(struct udc *udc) { int tmp; u32 reg; @@ -76,7 +76,7 @@ void stop_udc(struct udc *udc) dev_info(udc->dev, "Device disconnected\n"); } -void udc_drd_work(struct work_struct *work) +static void udc_drd_work(struct work_struct *work) { struct udc *udc; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index a9a1e4c40480..c8989c62a262 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -77,6 +77,16 @@ #define USB_INTEL_USB3_PSSEN 0xD8 #define USB_INTEL_USB3PRM 0xDC +/* ASMEDIA quirk use */ +#define ASMT_DATA_WRITE0_REG 0xF8 +#define ASMT_DATA_WRITE1_REG 0xFC +#define ASMT_CONTROL_REG 0xE0 +#define ASMT_CONTROL_WRITE_BIT 0x02 +#define ASMT_WRITEREG_CMD 0x10423 +#define ASMT_FLOWCTL_ADDR 0xFA30 +#define ASMT_FLOWCTL_DATA 0xBA +#define ASMT_PSEUDO_DATA 0 + /* * amd_chipset_gen values represent AMD different chipset generations */ @@ -412,6 +422,50 @@ void usb_amd_quirk_pll_disable(void) } EXPORT_SYMBOL_GPL(usb_amd_quirk_pll_disable); +static int usb_asmedia_wait_write(struct pci_dev *pdev) +{ + unsigned long retry_count; + unsigned char value; + + for (retry_count = 1000; retry_count > 0; --retry_count) { + + pci_read_config_byte(pdev, ASMT_CONTROL_REG, &value); + + if (value == 0xff) { + dev_err(&pdev->dev, "%s: check_ready ERROR", __func__); + return -EIO; + } + + if ((value & ASMT_CONTROL_WRITE_BIT) == 0) + return 0; + + usleep_range(40, 60); + } + + dev_warn(&pdev->dev, "%s: check_write_ready timeout", __func__); + return -ETIMEDOUT; +} + +void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev) +{ + if (usb_asmedia_wait_write(pdev) != 0) + return; + + /* send command and address to device */ + pci_write_config_dword(pdev, ASMT_DATA_WRITE0_REG, ASMT_WRITEREG_CMD); + pci_write_config_dword(pdev, ASMT_DATA_WRITE1_REG, ASMT_FLOWCTL_ADDR); + pci_write_config_byte(pdev, ASMT_CONTROL_REG, ASMT_CONTROL_WRITE_BIT); + + if (usb_asmedia_wait_write(pdev) != 0) + return; + + /* send data to device */ + pci_write_config_dword(pdev, ASMT_DATA_WRITE0_REG, ASMT_FLOWCTL_DATA); + pci_write_config_dword(pdev, ASMT_DATA_WRITE1_REG, ASMT_PSEUDO_DATA); + pci_write_config_byte(pdev, ASMT_CONTROL_REG, ASMT_CONTROL_WRITE_BIT); +} +EXPORT_SYMBOL_GPL(usb_asmedia_modifyflowcontrol); + void usb_amd_quirk_pll_enable(void) { usb_amd_quirk_pll(0); diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h index 0222195bd5b0..655994480198 100644 --- a/drivers/usb/host/pci-quirks.h +++ b/drivers/usb/host/pci-quirks.h @@ -11,6 +11,7 @@ bool usb_amd_prefetch_quirk(void); void usb_amd_dev_put(void); void usb_amd_quirk_pll_disable(void); void usb_amd_quirk_pll_enable(void); +void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev); void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev); void usb_disable_xhci_ports(struct pci_dev *xhci_pdev); void sb800_prefetch(struct device *dev, int on); @@ -18,6 +19,7 @@ void sb800_prefetch(struct device *dev, int on); struct pci_dev; static inline void usb_amd_quirk_pll_disable(void) {} static inline void usb_amd_quirk_pll_enable(void) {} +static inline void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev) {} static inline void usb_amd_dev_put(void) {} static inline void usb_disable_xhci_ports(struct pci_dev *xhci_pdev) {} static inline void sb800_prefetch(struct device *dev, int on) {} diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 1adae9eab831..00721e8807ab 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -398,14 +398,21 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) spin_lock_irqsave(&xhci->lock, flags); for (i = LAST_EP_INDEX; i > 0; i--) { if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue) { + struct xhci_ep_ctx *ep_ctx; struct xhci_command *command; + + ep_ctx = xhci_get_ep_ctx(xhci, virt_dev->out_ctx, i); + + /* Check ep is running, required by AMD SNPS 3.1 xHC */ + if (GET_EP_CTX_STATE(ep_ctx) != EP_STATE_RUNNING) + continue; + command = xhci_alloc_command(xhci, false, false, GFP_NOWAIT); if (!command) { spin_unlock_irqrestore(&xhci->lock, flags); xhci_free_command(xhci, cmd); return -ENOMEM; - } xhci_queue_stop_endpoint(xhci, command, slot_id, i, suspend); @@ -603,12 +610,14 @@ static int xhci_enter_test_mode(struct xhci_hcd *xhci, /* Disable all Device Slots */ xhci_dbg(xhci, "Disable all slots\n"); + spin_unlock_irqrestore(&xhci->lock, *flags); for (i = 1; i <= HCS_MAX_SLOTS(xhci->hcs_params1); i++) { retval = xhci_disable_slot(xhci, NULL, i); if (retval) xhci_err(xhci, "Failed to disable slot %d, %d. Enter test mode anyway\n", i, retval); } + spin_lock_irqsave(&xhci->lock, *flags); /* Put all ports to the Disable state by clear PP */ xhci_dbg(xhci, "Disable all port (PP = 0)\n"); /* Power off USB3 ports*/ @@ -897,6 +906,9 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, clear_bit(wIndex, &bus_state->resuming_ports); set_bit(wIndex, &bus_state->rexit_ports); + + xhci_test_and_clear_bit(xhci, port_array, wIndex, + PORT_PLC); xhci_set_link_state(xhci, port_array, wIndex, XDEV_U0); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 53882e2babbb..5b0fa553c8bc 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -59,6 +59,8 @@ #define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb #define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc +#define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 + static const char hcd_name[] = "xhci_hcd"; static struct hc_driver __read_mostly xhci_pci_hc_driver; @@ -217,6 +219,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == 0x1142) xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && + pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) + xhci->quirks |= XHCI_ASMEDIA_MODIFY_FLOWCONTROL; + if (pdev->vendor == PCI_VENDOR_ID_TI && pdev->device == 0x8241) xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_7; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index c50c902d009e..cc368ad2b51e 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -864,13 +864,16 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci, (ep->ep_state & EP_GETTING_NO_STREAMS)) { int stream_id; - for (stream_id = 0; stream_id < ep->stream_info->num_streams; + for (stream_id = 1; stream_id < ep->stream_info->num_streams; stream_id++) { + ring = ep->stream_info->stream_rings[stream_id]; + if (!ring) + continue; + xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "Killing URBs for slot ID %u, ep index %u, stream %u", - slot_id, ep_index, stream_id + 1); - xhci_kill_ring_urbs(xhci, - ep->stream_info->stream_rings[stream_id]); + slot_id, ep_index, stream_id); + xhci_kill_ring_urbs(xhci, ring); } } else { ring = ep->ring; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 56f85df013db..b2ff1ff1a02f 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -198,6 +198,9 @@ int xhci_reset(struct xhci_hcd *xhci) if (ret) return ret; + if (xhci->quirks & XHCI_ASMEDIA_MODIFY_FLOWCONTROL) + usb_asmedia_modifyflowcontrol(to_pci_dev(xhci_to_hcd(xhci)->self.controller)); + xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Wait for controller to be ready for doorbell rings"); /* @@ -622,8 +625,10 @@ int xhci_run(struct usb_hcd *hcd) if (!command) return -ENOMEM; - xhci_queue_vendor_command(xhci, command, 0, 0, 0, + ret = xhci_queue_vendor_command(xhci, command, 0, 0, 0, TRB_TYPE(TRB_NEC_GET_FW)); + if (ret) + xhci_free_command(xhci, command); } xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Finished xhci_run for USB2 roothub"); @@ -1085,6 +1090,9 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && !comp_timer_running) compliance_mode_recovery_timer_init(xhci); + if (xhci->quirks & XHCI_ASMEDIA_MODIFY_FLOWCONTROL) + usb_asmedia_modifyflowcontrol(to_pci_dev(hcd->self.controller)); + /* Re-enable port polling. */ xhci_dbg(xhci, "%s: starting port polling.\n", __func__); set_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 3c6da1f93c84..e3e935291ed6 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1820,6 +1820,7 @@ struct xhci_hcd { #define XHCI_BROKEN_PORT_PED (1 << 25) #define XHCI_LIMIT_ENDPOINT_INTERVAL_7 (1 << 26) #define XHCI_U2_DISABLE_WAKE (1 << 27) +#define XHCI_ASMEDIA_MODIFY_FLOWCONTROL (1 << 28) unsigned int num_active_eps; unsigned int limit_active_eps; diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index 623c51300393..f0ce304c5aaf 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -752,8 +752,10 @@ static int usbhsc_resume(struct device *dev) struct usbhs_priv *priv = dev_get_drvdata(dev); struct platform_device *pdev = usbhs_priv_to_pdev(priv); - if (!usbhsc_flags_has(priv, USBHSF_RUNTIME_PWCTRL)) + if (!usbhsc_flags_has(priv, USBHSF_RUNTIME_PWCTRL)) { usbhsc_power_ctrl(priv, 1); + usbhs_mod_autonomy_mode(priv); + } usbhs_platform_call(priv, phy_reset, pdev); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 5bc7a6138855..93fba9033b00 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -37,6 +37,7 @@ struct usbhsg_gpriv; struct usbhsg_uep { struct usb_ep ep; struct usbhs_pipe *pipe; + spinlock_t lock; /* protect the pipe */ char ep_name[EP_NAME_SIZE]; @@ -636,10 +637,16 @@ usbhsg_ep_enable_end: static int usbhsg_ep_disable(struct usb_ep *ep) { struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep); - struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep); + struct usbhs_pipe *pipe; + unsigned long flags; + int ret = 0; - if (!pipe) - return -EINVAL; + spin_lock_irqsave(&uep->lock, flags); + pipe = usbhsg_uep_to_pipe(uep); + if (!pipe) { + ret = -EINVAL; + goto out; + } usbhsg_pipe_disable(uep); usbhs_pipe_free(pipe); @@ -647,6 +654,9 @@ static int usbhsg_ep_disable(struct usb_ep *ep) uep->pipe->mod_private = NULL; uep->pipe = NULL; +out: + spin_unlock_irqrestore(&uep->lock, flags); + return 0; } @@ -696,8 +706,11 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req) { struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep); struct usbhsg_request *ureq = usbhsg_req_to_ureq(req); - struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep); + struct usbhs_pipe *pipe; + unsigned long flags; + spin_lock_irqsave(&uep->lock, flags); + pipe = usbhsg_uep_to_pipe(uep); if (pipe) usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq)); @@ -706,6 +719,7 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req) * even if the pipe is NULL. */ usbhsg_queue_pop(uep, ureq, -ECONNRESET); + spin_unlock_irqrestore(&uep->lock, flags); return 0; } @@ -852,10 +866,10 @@ static int usbhsg_try_stop(struct usbhs_priv *priv, u32 status) { struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv); struct usbhs_mod *mod = usbhs_mod_get_current(priv); - struct usbhsg_uep *dcp = usbhsg_gpriv_to_dcp(gpriv); + struct usbhsg_uep *uep; struct device *dev = usbhs_priv_to_dev(priv); unsigned long flags; - int ret = 0; + int ret = 0, i; /******************** spin lock ********************/ usbhs_lock(priv, flags); @@ -887,7 +901,9 @@ static int usbhsg_try_stop(struct usbhs_priv *priv, u32 status) usbhs_sys_set_test_mode(priv, 0); usbhs_sys_function_ctrl(priv, 0); - usbhsg_ep_disable(&dcp->ep); + /* disable all eps */ + usbhsg_for_each_uep_with_dcp(uep, gpriv, i) + usbhsg_ep_disable(&uep->ep); dev_dbg(dev, "stop gadget\n"); @@ -1069,6 +1085,7 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv) ret = -ENOMEM; goto usbhs_mod_gadget_probe_err_gpriv; } + spin_lock_init(&uep->lock); gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED); dev_info(dev, "%stransceiver found\n", diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index fba4005dd737..6a7720e66595 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -1529,8 +1529,11 @@ static void isd200_ata_command(struct scsi_cmnd *srb, struct us_data *us) /* Make sure driver was initialized */ - if (us->extra == NULL) + if (us->extra == NULL) { usb_stor_dbg(us, "ERROR Driver not initialized\n"); + srb->result = DID_ERROR << 16; + return; + } scsi_set_resid(srb, 0); /* scsi_bufflen might change in protocol translation to ata */ diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 6b0d2f0918c6..8a88f45822e3 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -3,6 +3,7 @@ #define __DRIVER_USB_TYPEC_UCSI_H #include <linux/bitops.h> +#include <linux/device.h> #include <linux/types.h> /* -------------------------------------------------------------------------- */ diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c index 3612542b6044..83fc9aab34e8 100644 --- a/drivers/w1/masters/omap_hdq.c +++ b/drivers/w1/masters/omap_hdq.c @@ -704,7 +704,8 @@ static int omap_hdq_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - ret = -ENXIO; + dev_dbg(&pdev->dev, "Failed to get IRQ: %d\n", irq); + ret = irq; goto err_irq; } diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 95ea7e6b1d99..74471e7aa5cc 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -728,6 +728,7 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) memcpy(&sl->reg_num, rn, sizeof(sl->reg_num)); atomic_set(&sl->refcnt, 1); atomic_inc(&sl->master->refcnt); + dev->slave_count++; /* slave modules need to be loaded in a context with unlocked mutex */ mutex_unlock(&dev->mutex); @@ -747,11 +748,11 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) sl->family = f; - err = __w1_attach_slave_device(sl); if (err < 0) { dev_err(&dev->dev, "%s: Attaching %s failed.\n", __func__, sl->name); + dev->slave_count--; w1_family_put(sl->family); atomic_dec(&sl->master->refcnt); kfree(sl); @@ -759,7 +760,6 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) } sl->ttl = dev->slave_ttl; - dev->slave_count++; memcpy(msg.id.id, rn, sizeof(msg.id)); msg.type = W1_SLAVE_ADD; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 50dcb68d8070..ab609255a0f3 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -780,6 +780,9 @@ static int __init balloon_init(void) } #endif + /* Init the xen-balloon driver. */ + xen_balloon_init(); + return 0; } subsys_initcall(balloon_init); diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index d6786b87e13b..2c6a9114d332 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -42,6 +42,7 @@ #include <linux/delay.h> #include <linux/hardirq.h> #include <linux/workqueue.h> +#include <linux/ratelimit.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -1072,8 +1073,14 @@ static int gnttab_expand(unsigned int req_entries) cur = nr_grant_frames; extra = ((req_entries + (grefs_per_grant_frame-1)) / grefs_per_grant_frame); - if (cur + extra > gnttab_max_grant_frames()) + if (cur + extra > gnttab_max_grant_frames()) { + pr_warn_ratelimited("xen/grant-table: max_grant_frames reached" + " cur=%u extra=%u limit=%u" + " gnttab_free_count=%u req_entries=%u\n", + cur, extra, gnttab_max_grant_frames(), + gnttab_free_count, req_entries); return -ENOSPC; + } rc = gnttab_map(cur, cur + extra - 1); if (rc == 0) diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index e7715cb62eef..e89136ab851e 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -59,6 +59,8 @@ static void watch_target(struct xenbus_watch *watch, { unsigned long long new_target; int err; + static bool watch_fired; + static long target_diff; err = xenbus_scanf(XBT_NIL, "memory", "target", "%llu", &new_target); if (err != 1) { @@ -69,7 +71,14 @@ static void watch_target(struct xenbus_watch *watch, /* The given memory/target value is in KiB, so it needs converting to * pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10. */ - balloon_set_new_target(new_target >> (PAGE_SHIFT - 10)); + new_target >>= PAGE_SHIFT - 10; + if (watch_fired) { + balloon_set_new_target(new_target - target_diff); + return; + } + + watch_fired = true; + target_diff = new_target - balloon_stats.target_pages; } static struct xenbus_watch target_watch = { .node = "memory/target", @@ -94,22 +103,15 @@ static struct notifier_block xenstore_notifier = { .notifier_call = balloon_init_watcher, }; -static int __init balloon_init(void) +void xen_balloon_init(void) { - if (!xen_domain()) - return -ENODEV; - - pr_info("Initialising balloon driver\n"); - register_balloon(&balloon_dev); register_xen_selfballooning(&balloon_dev); register_xenstore_notifier(&xenstore_notifier); - - return 0; } -subsys_initcall(balloon_init); +EXPORT_SYMBOL_GPL(xen_balloon_init); #define BALLOON_SHOW(name, format, args...) \ static ssize_t show_##name(struct device *dev, \ |