diff options
Diffstat (limited to 'drivers')
81 files changed, 1308 insertions, 3744 deletions
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index 03856ad280b9..473d36d91644 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -198,7 +198,7 @@ static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev, goto out_err; } - params_head = section_head->params; + params_head = section.params; while (params_head) { if (copy_from_user(&key_val, (void __user *)params_head, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 615ce6d464fb..306f75700bf8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -389,7 +389,6 @@ struct amdgpu_clock { * Fences. */ struct amdgpu_fence_driver { - struct amdgpu_ring *ring; uint64_t gpu_addr; volatile uint32_t *cpu_addr; /* sync_seq is protected by ring emission lock */ @@ -398,7 +397,7 @@ struct amdgpu_fence_driver { bool initialized; struct amdgpu_irq_src *irq_src; unsigned irq_type; - struct delayed_work lockup_work; + struct timer_list fallback_timer; wait_queue_head_t fence_queue; }; @@ -917,8 +916,8 @@ struct amdgpu_ring { #define AMDGPU_VM_FAULT_STOP_ALWAYS 2 struct amdgpu_vm_pt { - struct amdgpu_bo *bo; - uint64_t addr; + struct amdgpu_bo *bo; + uint64_t addr; }; struct amdgpu_vm_id { @@ -926,8 +925,6 @@ struct amdgpu_vm_id { uint64_t pd_gpu_addr; /* last flushed PD/PT update */ struct fence *flushed_updates; - /* last use of vmid */ - struct fence *last_id_use; }; struct amdgpu_vm { @@ -957,24 +954,70 @@ struct amdgpu_vm { /* for id and flush management per ring */ struct amdgpu_vm_id ids[AMDGPU_MAX_RINGS]; + /* for interval tree */ + spinlock_t it_lock; }; struct amdgpu_vm_manager { - struct fence *active[AMDGPU_NUM_VM]; - uint32_t max_pfn; + struct { + struct fence *active; + atomic_long_t owner; + } ids[AMDGPU_NUM_VM]; + + uint32_t max_pfn; /* number of VMIDs */ - unsigned nvm; + unsigned nvm; /* vram base address for page table entry */ - u64 vram_base_offset; + u64 vram_base_offset; /* is vm enabled? */ - bool enabled; - /* for hw to save the PD addr on suspend/resume */ - uint32_t saved_table_addr[AMDGPU_NUM_VM]; + bool enabled; /* vm pte handling */ const struct amdgpu_vm_pte_funcs *vm_pte_funcs; struct amdgpu_ring *vm_pte_funcs_ring; }; +void amdgpu_vm_manager_fini(struct amdgpu_device *adev); +int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm); +void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); +struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct list_head *head); +int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, + struct amdgpu_sync *sync); +void amdgpu_vm_flush(struct amdgpu_ring *ring, + struct amdgpu_vm *vm, + struct fence *updates); +void amdgpu_vm_fence(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct fence *fence); +uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr); +int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, + struct amdgpu_vm *vm); +int amdgpu_vm_clear_freed(struct amdgpu_device *adev, + struct amdgpu_vm *vm); +int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct amdgpu_sync *sync); +int amdgpu_vm_bo_update(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + struct ttm_mem_reg *mem); +void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, + struct amdgpu_bo *bo); +struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm, + struct amdgpu_bo *bo); +struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct amdgpu_bo *bo); +int amdgpu_vm_bo_map(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr, uint64_t offset, + uint64_t size, uint32_t flags); +int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr); +void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va); +int amdgpu_vm_free_job(struct amdgpu_job *job); + /* * context related structures */ @@ -1211,6 +1254,7 @@ struct amdgpu_cs_parser { /* relocations */ struct amdgpu_bo_list_entry *vm_bos; struct list_head validated; + struct fence *fence; struct amdgpu_ib *ibs; uint32_t num_ibs; @@ -1226,7 +1270,7 @@ struct amdgpu_job { struct amdgpu_device *adev; struct amdgpu_ib *ibs; uint32_t num_ibs; - struct mutex job_lock; + void *owner; struct amdgpu_user_fence uf; int (*free_job)(struct amdgpu_job *job); }; @@ -2257,11 +2301,6 @@ void amdgpu_pci_config_reset(struct amdgpu_device *adev); bool amdgpu_card_posted(struct amdgpu_device *adev); void amdgpu_update_display_priority(struct amdgpu_device *adev); bool amdgpu_boot_test_post_card(struct amdgpu_device *adev); -struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev, - struct drm_file *filp, - struct amdgpu_ctx *ctx, - struct amdgpu_ib *ibs, - uint32_t num_ibs); int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data); int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, @@ -2319,49 +2358,6 @@ long amdgpu_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); /* - * vm - */ -int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm); -void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); -struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev, - struct amdgpu_vm *vm, - struct list_head *head); -int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync); -void amdgpu_vm_flush(struct amdgpu_ring *ring, - struct amdgpu_vm *vm, - struct fence *updates); -void amdgpu_vm_fence(struct amdgpu_device *adev, - struct amdgpu_vm *vm, - struct amdgpu_fence *fence); -uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr); -int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, - struct amdgpu_vm *vm); -int amdgpu_vm_clear_freed(struct amdgpu_device *adev, - struct amdgpu_vm *vm); -int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, - struct amdgpu_vm *vm, struct amdgpu_sync *sync); -int amdgpu_vm_bo_update(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va, - struct ttm_mem_reg *mem); -void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, - struct amdgpu_bo *bo); -struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm, - struct amdgpu_bo *bo); -struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, - struct amdgpu_vm *vm, - struct amdgpu_bo *bo); -int amdgpu_vm_bo_map(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va, - uint64_t addr, uint64_t offset, - uint64_t size, uint32_t flags); -int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va, - uint64_t addr); -void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va); -int amdgpu_vm_free_job(struct amdgpu_job *job); -/* * functions used by amdgpu_encoder.c */ struct amdgpu_afmt_acr { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index dfc4d02c7a38..3afcf0237c25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -127,30 +127,6 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, return 0; } -struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev, - struct drm_file *filp, - struct amdgpu_ctx *ctx, - struct amdgpu_ib *ibs, - uint32_t num_ibs) -{ - struct amdgpu_cs_parser *parser; - int i; - - parser = kzalloc(sizeof(struct amdgpu_cs_parser), GFP_KERNEL); - if (!parser) - return NULL; - - parser->adev = adev; - parser->filp = filp; - parser->ctx = ctx; - parser->ibs = ibs; - parser->num_ibs = num_ibs; - for (i = 0; i < num_ibs; i++) - ibs[i].ctx = ctx; - - return parser; -} - int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) { union drm_amdgpu_cs *cs = data; @@ -463,8 +439,18 @@ static int cmp_size_smaller_first(void *priv, struct list_head *a, return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages; } -static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int error, bool backoff) +/** + * cs_parser_fini() - clean parser states + * @parser: parser structure holding parsing context. + * @error: error number + * + * If error is set than unvalidate buffer, otherwise just free memory + * used by parsing context. + **/ +static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff) { + unsigned i; + if (!error) { /* Sort the buffer list from the smallest to largest buffer, * which affects the order of buffers in the LRU list. @@ -479,17 +465,14 @@ static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int err list_sort(NULL, &parser->validated, cmp_size_smaller_first); ttm_eu_fence_buffer_objects(&parser->ticket, - &parser->validated, - &parser->ibs[parser->num_ibs-1].fence->base); + &parser->validated, + parser->fence); } else if (backoff) { ttm_eu_backoff_reservation(&parser->ticket, &parser->validated); } -} + fence_put(parser->fence); -static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser) -{ - unsigned i; if (parser->ctx) amdgpu_ctx_put(parser->ctx); if (parser->bo_list) @@ -499,31 +482,12 @@ static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser) for (i = 0; i < parser->nchunks; i++) drm_free_large(parser->chunks[i].kdata); kfree(parser->chunks); - if (!amdgpu_enable_scheduler) - { - if (parser->ibs) - for (i = 0; i < parser->num_ibs; i++) - amdgpu_ib_free(parser->adev, &parser->ibs[i]); - kfree(parser->ibs); - if (parser->uf.bo) - drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base); - } - - kfree(parser); -} - -/** - * cs_parser_fini() - clean parser states - * @parser: parser structure holding parsing context. - * @error: error number - * - * If error is set than unvalidate buffer, otherwise just free memory - * used by parsing context. - **/ -static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff) -{ - amdgpu_cs_parser_fini_early(parser, error, backoff); - amdgpu_cs_parser_fini_late(parser); + if (parser->ibs) + for (i = 0; i < parser->num_ibs; i++) + amdgpu_ib_free(parser->adev, &parser->ibs[i]); + kfree(parser->ibs); + if (parser->uf.bo) + drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base); } static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p, @@ -610,15 +574,9 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev, } r = amdgpu_bo_vm_update_pte(parser, vm); - if (r) { - goto out; - } - amdgpu_cs_sync_rings(parser); - if (!amdgpu_enable_scheduler) - r = amdgpu_ib_schedule(adev, parser->num_ibs, parser->ibs, - parser->filp); + if (!r) + amdgpu_cs_sync_rings(parser); -out: return r; } @@ -828,36 +786,36 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) union drm_amdgpu_cs *cs = data; struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_vm *vm = &fpriv->vm; - struct amdgpu_cs_parser *parser; + struct amdgpu_cs_parser parser = {}; bool reserved_buffers = false; int i, r; if (!adev->accel_working) return -EBUSY; - parser = amdgpu_cs_parser_create(adev, filp, NULL, NULL, 0); - if (!parser) - return -ENOMEM; - r = amdgpu_cs_parser_init(parser, data); + parser.adev = adev; + parser.filp = filp; + + r = amdgpu_cs_parser_init(&parser, data); if (r) { DRM_ERROR("Failed to initialize parser !\n"); - amdgpu_cs_parser_fini(parser, r, false); + amdgpu_cs_parser_fini(&parser, r, false); r = amdgpu_cs_handle_lockup(adev, r); return r; } mutex_lock(&vm->mutex); - r = amdgpu_cs_parser_relocs(parser); + r = amdgpu_cs_parser_relocs(&parser); if (r == -ENOMEM) DRM_ERROR("Not enough memory for command submission!\n"); else if (r && r != -ERESTARTSYS) DRM_ERROR("Failed to process the buffer list %d!\n", r); else if (!r) { reserved_buffers = true; - r = amdgpu_cs_ib_fill(adev, parser); + r = amdgpu_cs_ib_fill(adev, &parser); } if (!r) { - r = amdgpu_cs_dependencies(adev, parser); + r = amdgpu_cs_dependencies(adev, &parser); if (r) DRM_ERROR("Failed in the dependencies handling %d!\n", r); } @@ -865,62 +823,71 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (r) goto out; - for (i = 0; i < parser->num_ibs; i++) - trace_amdgpu_cs(parser, i); + for (i = 0; i < parser.num_ibs; i++) + trace_amdgpu_cs(&parser, i); - r = amdgpu_cs_ib_vm_chunk(adev, parser); + r = amdgpu_cs_ib_vm_chunk(adev, &parser); if (r) goto out; - if (amdgpu_enable_scheduler && parser->num_ibs) { + if (amdgpu_enable_scheduler && parser.num_ibs) { + struct amdgpu_ring * ring = parser.ibs->ring; + struct amd_sched_fence *fence; struct amdgpu_job *job; - struct amdgpu_ring * ring = parser->ibs->ring; + job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL); if (!job) { r = -ENOMEM; goto out; } + job->base.sched = &ring->sched; - job->base.s_entity = &parser->ctx->rings[ring->idx].entity; - job->adev = parser->adev; - job->ibs = parser->ibs; - job->num_ibs = parser->num_ibs; - job->base.owner = parser->filp; - mutex_init(&job->job_lock); + job->base.s_entity = &parser.ctx->rings[ring->idx].entity; + job->adev = parser.adev; + job->owner = parser.filp; + job->free_job = amdgpu_cs_free_job; + + job->ibs = parser.ibs; + job->num_ibs = parser.num_ibs; + parser.ibs = NULL; + parser.num_ibs = 0; + if (job->ibs[job->num_ibs - 1].user) { - memcpy(&job->uf, &parser->uf, - sizeof(struct amdgpu_user_fence)); + job->uf = parser.uf; job->ibs[job->num_ibs - 1].user = &job->uf; + parser.uf.bo = NULL; } - job->free_job = amdgpu_cs_free_job; - mutex_lock(&job->job_lock); - r = amd_sched_entity_push_job(&job->base); - if (r) { - mutex_unlock(&job->job_lock); + fence = amd_sched_fence_create(job->base.s_entity, + parser.filp); + if (!fence) { + r = -ENOMEM; amdgpu_cs_free_job(job); kfree(job); goto out; } - cs->out.handle = - amdgpu_ctx_add_fence(parser->ctx, ring, - &job->base.s_fence->base); - parser->ibs[parser->num_ibs - 1].sequence = cs->out.handle; + job->base.s_fence = fence; + parser.fence = fence_get(&fence->base); - list_sort(NULL, &parser->validated, cmp_size_smaller_first); - ttm_eu_fence_buffer_objects(&parser->ticket, - &parser->validated, - &job->base.s_fence->base); + cs->out.handle = amdgpu_ctx_add_fence(parser.ctx, ring, + &fence->base); + job->ibs[job->num_ibs - 1].sequence = cs->out.handle; - mutex_unlock(&job->job_lock); - amdgpu_cs_parser_fini_late(parser); - mutex_unlock(&vm->mutex); - return 0; + trace_amdgpu_cs_ioctl(job); + amd_sched_entity_push_job(&job->base); + + } else { + struct amdgpu_fence *fence; + + r = amdgpu_ib_schedule(adev, parser.num_ibs, parser.ibs, + parser.filp); + fence = parser.ibs[parser.num_ibs - 1].fence; + parser.fence = fence_get(&fence->base); + cs->out.handle = parser.ibs[parser.num_ibs - 1].sequence; } - cs->out.handle = parser->ibs[parser->num_ibs - 1].sequence; out: - amdgpu_cs_parser_fini(parser, r, reserved_buffers); + amdgpu_cs_parser_fini(&parser, r, reserved_buffers); mutex_unlock(&vm->mutex); r = amdgpu_cs_handle_lockup(adev, r); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 257d72205bb5..3671f9f220bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -47,6 +47,9 @@ * that the the relevant GPU caches have been flushed. */ +static struct kmem_cache *amdgpu_fence_slab; +static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0); + /** * amdgpu_fence_write - write a fence value * @@ -85,24 +88,6 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring) } /** - * amdgpu_fence_schedule_check - schedule lockup check - * - * @ring: pointer to struct amdgpu_ring - * - * Queues a delayed work item to check for lockups. - */ -static void amdgpu_fence_schedule_check(struct amdgpu_ring *ring) -{ - /* - * Do not reset the timer here with mod_delayed_work, - * this can livelock in an interaction with TTM delayed destroy. - */ - queue_delayed_work(system_power_efficient_wq, - &ring->fence_drv.lockup_work, - AMDGPU_FENCE_JIFFIES_TIMEOUT); -} - -/** * amdgpu_fence_emit - emit a fence on the requested ring * * @ring: ring the fence is associated with @@ -118,7 +103,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner, struct amdgpu_device *adev = ring->adev; /* we are protected by the ring emission mutex */ - *fence = kmalloc(sizeof(struct amdgpu_fence), GFP_KERNEL); + *fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL); if ((*fence) == NULL) { return -ENOMEM; } @@ -132,11 +117,23 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner, amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, (*fence)->seq, AMDGPU_FENCE_FLAG_INT); - trace_amdgpu_fence_emit(ring->adev->ddev, ring->idx, (*fence)->seq); return 0; } /** + * amdgpu_fence_schedule_fallback - schedule fallback check + * + * @ring: pointer to struct amdgpu_ring + * + * Start a timer as fallback to our interrupts. + */ +static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring) +{ + mod_timer(&ring->fence_drv.fallback_timer, + jiffies + AMDGPU_FENCE_JIFFIES_TIMEOUT); +} + +/** * amdgpu_fence_activity - check for fence activity * * @ring: pointer to struct amdgpu_ring @@ -202,45 +199,38 @@ static bool amdgpu_fence_activity(struct amdgpu_ring *ring) } while (atomic64_xchg(&ring->fence_drv.last_seq, seq) > seq); if (seq < last_emitted) - amdgpu_fence_schedule_check(ring); + amdgpu_fence_schedule_fallback(ring); return wake; } /** - * amdgpu_fence_check_lockup - check for hardware lockup + * amdgpu_fence_process - process a fence * - * @work: delayed work item + * @adev: amdgpu_device pointer + * @ring: ring index the fence is associated with * - * Checks for fence activity and if there is none probe - * the hardware if a lockup occured. + * Checks the current fence value and wakes the fence queue + * if the sequence number has increased (all asics). */ -static void amdgpu_fence_check_lockup(struct work_struct *work) +void amdgpu_fence_process(struct amdgpu_ring *ring) { - struct amdgpu_fence_driver *fence_drv; - struct amdgpu_ring *ring; - - fence_drv = container_of(work, struct amdgpu_fence_driver, - lockup_work.work); - ring = fence_drv->ring; - if (amdgpu_fence_activity(ring)) wake_up_all(&ring->fence_drv.fence_queue); } /** - * amdgpu_fence_process - process a fence + * amdgpu_fence_fallback - fallback for hardware interrupts * - * @adev: amdgpu_device pointer - * @ring: ring index the fence is associated with + * @work: delayed work item * - * Checks the current fence value and wakes the fence queue - * if the sequence number has increased (all asics). + * Checks for fence activity. */ -void amdgpu_fence_process(struct amdgpu_ring *ring) +static void amdgpu_fence_fallback(unsigned long arg) { - if (amdgpu_fence_activity(ring)) - wake_up_all(&ring->fence_drv.fence_queue); + struct amdgpu_ring *ring = (void *)arg; + + amdgpu_fence_process(ring); } /** @@ -290,7 +280,7 @@ static int amdgpu_fence_ring_wait_seq(struct amdgpu_ring *ring, uint64_t seq) if (atomic64_read(&ring->fence_drv.last_seq) >= seq) return 0; - amdgpu_fence_schedule_check(ring); + amdgpu_fence_schedule_fallback(ring); wait_event(ring->fence_drv.fence_queue, ( (signaled = amdgpu_fence_seq_signaled(ring, seq)))); @@ -491,9 +481,8 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring) atomic64_set(&ring->fence_drv.last_seq, 0); ring->fence_drv.initialized = false; - INIT_DELAYED_WORK(&ring->fence_drv.lockup_work, - amdgpu_fence_check_lockup); - ring->fence_drv.ring = ring; + setup_timer(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback, + (unsigned long)ring); init_waitqueue_head(&ring->fence_drv.fence_queue); @@ -536,6 +525,13 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring) */ int amdgpu_fence_driver_init(struct amdgpu_device *adev) { + if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) { + amdgpu_fence_slab = kmem_cache_create( + "amdgpu_fence", sizeof(struct amdgpu_fence), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!amdgpu_fence_slab) + return -ENOMEM; + } if (amdgpu_debugfs_fence_init(adev)) dev_err(adev->dev, "fence debugfs file creation failed\n"); @@ -554,9 +550,12 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) { int i, r; + if (atomic_dec_and_test(&amdgpu_fence_slab_ref)) + kmem_cache_destroy(amdgpu_fence_slab); mutex_lock(&adev->ring_lock); for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; + if (!ring || !ring->fence_drv.initialized) continue; r = amdgpu_fence_wait_empty(ring); @@ -568,6 +567,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); amd_sched_fini(&ring->sched); + del_timer_sync(&ring->fence_drv.fallback_timer); ring->fence_drv.initialized = false; } mutex_unlock(&adev->ring_lock); @@ -751,18 +751,25 @@ static bool amdgpu_fence_enable_signaling(struct fence *f) fence->fence_wake.func = amdgpu_fence_check_signaled; __add_wait_queue(&ring->fence_drv.fence_queue, &fence->fence_wake); fence_get(f); - amdgpu_fence_schedule_check(ring); + if (!timer_pending(&ring->fence_drv.fallback_timer)) + amdgpu_fence_schedule_fallback(ring); FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx); return true; } +static void amdgpu_fence_release(struct fence *f) +{ + struct amdgpu_fence *fence = to_amdgpu_fence(f); + kmem_cache_free(amdgpu_fence_slab, fence); +} + const struct fence_ops amdgpu_fence_ops = { .get_driver_name = amdgpu_fence_get_driver_name, .get_timeline_name = amdgpu_fence_get_timeline_name, .enable_signaling = amdgpu_fence_enable_signaling, .signaled = amdgpu_fence_is_signaled, .wait = fence_default_wait, - .release = NULL, + .release = amdgpu_fence_release, }; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 087332858853..00c5b580f56c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -483,6 +483,9 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (domain == AMDGPU_GEM_DOMAIN_CPU) goto error_unreserve; } + r = amdgpu_vm_update_page_directory(adev, bo_va->vm); + if (r) + goto error_unreserve; r = amdgpu_vm_clear_freed(adev, bo_va->vm); if (r) @@ -512,6 +515,9 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_bo *rbo; struct amdgpu_bo_va *bo_va; + struct ttm_validate_buffer tv, tv_pd; + struct ww_acquire_ctx ticket; + struct list_head list, duplicates; uint32_t invalid_flags, va_flags = 0; int r = 0; @@ -549,7 +555,18 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, return -ENOENT; mutex_lock(&fpriv->vm.mutex); rbo = gem_to_amdgpu_bo(gobj); - r = amdgpu_bo_reserve(rbo, false); + INIT_LIST_HEAD(&list); + INIT_LIST_HEAD(&duplicates); + tv.bo = &rbo->tbo; + tv.shared = true; + list_add(&tv.head, &list); + + if (args->operation == AMDGPU_VA_OP_MAP) { + tv_pd.bo = &fpriv->vm.page_directory->tbo; + tv_pd.shared = true; + list_add(&tv_pd.head, &list); + } + r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates); if (r) { mutex_unlock(&fpriv->vm.mutex); drm_gem_object_unreference_unlocked(gobj); @@ -558,7 +575,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, bo_va = amdgpu_vm_bo_find(&fpriv->vm, rbo); if (!bo_va) { - amdgpu_bo_unreserve(rbo); + ttm_eu_backoff_reservation(&ticket, &list); + drm_gem_object_unreference_unlocked(gobj); mutex_unlock(&fpriv->vm.mutex); return -ENOENT; } @@ -581,7 +599,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, default: break; } - + ttm_eu_backoff_reservation(&ticket, &list); if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE)) amdgpu_gem_va_update_vm(adev, bo_va, args->operation); mutex_unlock(&fpriv->vm.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index e65987743871..9e25edafa721 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -62,7 +62,7 @@ int amdgpu_ib_get(struct amdgpu_ring *ring, struct amdgpu_vm *vm, int r; if (size) { - r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo, + r = amdgpu_sa_bo_new(&adev->ring_tmp_bo, &ib->sa_bo, size, 256); if (r) { dev_err(adev->dev, "failed to get a new IB (%d)\n", r); @@ -216,7 +216,7 @@ int amdgpu_ib_schedule(struct amdgpu_device *adev, unsigned num_ibs, } if (ib->vm) - amdgpu_vm_fence(adev, ib->vm, ib->fence); + amdgpu_vm_fence(adev, ib->vm, &ib->fence->base); amdgpu_ring_unlock_commit(ring); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 3c2ff4567798..ea756e77b023 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -189,10 +189,9 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev, struct amdgpu_sa_manager *sa_manager); int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev, struct amdgpu_sa_manager *sa_manager); -int amdgpu_sa_bo_new(struct amdgpu_device *adev, - struct amdgpu_sa_manager *sa_manager, - struct amdgpu_sa_bo **sa_bo, - unsigned size, unsigned align); +int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, + struct amdgpu_sa_bo **sa_bo, + unsigned size, unsigned align); void amdgpu_sa_bo_free(struct amdgpu_device *adev, struct amdgpu_sa_bo **sa_bo, struct fence *fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c index 0212b31dc194..8b88edb0434b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c @@ -311,8 +311,7 @@ static bool amdgpu_sa_bo_next_hole(struct amdgpu_sa_manager *sa_manager, return false; } -int amdgpu_sa_bo_new(struct amdgpu_device *adev, - struct amdgpu_sa_manager *sa_manager, +int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, struct amdgpu_sa_bo **sa_bo, unsigned size, unsigned align) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index dcf4a8aca680..438c05254695 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -26,6 +26,7 @@ #include <linux/sched.h> #include <drm/drmP.h> #include "amdgpu.h" +#include "amdgpu_trace.h" static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job) { @@ -44,11 +45,8 @@ static struct fence *amdgpu_sched_run_job(struct amd_sched_job *sched_job) return NULL; } job = to_amdgpu_job(sched_job); - mutex_lock(&job->job_lock); - r = amdgpu_ib_schedule(job->adev, - job->num_ibs, - job->ibs, - job->base.owner); + trace_amdgpu_sched_run_job(job); + r = amdgpu_ib_schedule(job->adev, job->num_ibs, job->ibs, job->owner); if (r) { DRM_ERROR("Error scheduling IBs (%d)\n", r); goto err; @@ -61,8 +59,6 @@ err: if (job->free_job) job->free_job(job); - mutex_unlock(&job->job_lock); - fence_put(&job->base.s_fence->base); kfree(job); return fence ? &fence->base : NULL; } @@ -88,21 +84,19 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev, return -ENOMEM; job->base.sched = &ring->sched; job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity; + job->base.s_fence = amd_sched_fence_create(job->base.s_entity, owner); + if (!job->base.s_fence) { + kfree(job); + return -ENOMEM; + } + *f = fence_get(&job->base.s_fence->base); + job->adev = adev; job->ibs = ibs; job->num_ibs = num_ibs; - job->base.owner = owner; - mutex_init(&job->job_lock); + job->owner = owner; job->free_job = free_job; - mutex_lock(&job->job_lock); - r = amd_sched_entity_push_job(&job->base); - if (r) { - mutex_unlock(&job->job_lock); - kfree(job); - return r; - } - *f = fence_get(&job->base.s_fence->base); - mutex_unlock(&job->job_lock); + amd_sched_entity_push_job(&job->base); } else { r = amdgpu_ib_schedule(adev, num_ibs, ibs, owner); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c index ff3ca52ec6fe..1caaf201b708 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c @@ -40,7 +40,7 @@ int amdgpu_semaphore_create(struct amdgpu_device *adev, if (*semaphore == NULL) { return -ENOMEM; } - r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo, + r = amdgpu_sa_bo_new(&adev->ring_tmp_bo, &(*semaphore)->sa_bo, 8, 8); if (r) { kfree(*semaphore); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index a6697fd05217..dd005c336c97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -302,8 +302,14 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, return -EINVAL; } - if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores || - (count >= AMDGPU_NUM_SYNCS)) { + if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) { + r = fence_wait(&fence->base, true); + if (r) + return r; + continue; + } + + if (count >= AMDGPU_NUM_SYNCS) { /* not enough room, wait manually */ r = fence_wait(&fence->base, false); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 76ecbaf72a2e..8f9834ab1bd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -48,6 +48,57 @@ TRACE_EVENT(amdgpu_cs, __entry->fences) ); +TRACE_EVENT(amdgpu_cs_ioctl, + TP_PROTO(struct amdgpu_job *job), + TP_ARGS(job), + TP_STRUCT__entry( + __field(struct amdgpu_device *, adev) + __field(struct amd_sched_job *, sched_job) + __field(struct amdgpu_ib *, ib) + __field(struct fence *, fence) + __field(char *, ring_name) + __field(u32, num_ibs) + ), + + TP_fast_assign( + __entry->adev = job->adev; + __entry->sched_job = &job->base; + __entry->ib = job->ibs; + __entry->fence = &job->base.s_fence->base; + __entry->ring_name = job->ibs[0].ring->name; + __entry->num_ibs = job->num_ibs; + ), + TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u", + __entry->adev, __entry->sched_job, __entry->ib, + __entry->fence, __entry->ring_name, __entry->num_ibs) +); + +TRACE_EVENT(amdgpu_sched_run_job, + TP_PROTO(struct amdgpu_job *job), + TP_ARGS(job), + TP_STRUCT__entry( + __field(struct amdgpu_device *, adev) + __field(struct amd_sched_job *, sched_job) + __field(struct amdgpu_ib *, ib) + __field(struct fence *, fence) + __field(char *, ring_name) + __field(u32, num_ibs) + ), + + TP_fast_assign( + __entry->adev = job->adev; + __entry->sched_job = &job->base; + __entry->ib = job->ibs; + __entry->fence = &job->base.s_fence->base; + __entry->ring_name = job->ibs[0].ring->name; + __entry->num_ibs = job->num_ibs; + ), + TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u", + __entry->adev, __entry->sched_job, __entry->ib, + __entry->fence, __entry->ring_name, __entry->num_ibs) +); + + TRACE_EVENT(amdgpu_vm_grab_id, TP_PROTO(unsigned vmid, int ring), TP_ARGS(vmid, ring), @@ -196,49 +247,6 @@ TRACE_EVENT(amdgpu_bo_list_set, TP_printk("list=%p, bo=%p", __entry->list, __entry->bo) ); -DECLARE_EVENT_CLASS(amdgpu_fence_request, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno), - - TP_STRUCT__entry( - __field(u32, dev) - __field(int, ring) - __field(u32, seqno) - ), - - TP_fast_assign( - __entry->dev = dev->primary->index; - __entry->ring = ring; - __entry->seqno = seqno; - ), - - TP_printk("dev=%u, ring=%d, seqno=%u", - __entry->dev, __entry->ring, __entry->seqno) -); - -DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_emit, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno) -); - -DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_begin, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno) -); - -DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_end, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno) -); - DECLARE_EVENT_CLASS(amdgpu_semaphore_request, TP_PROTO(int ring, struct amdgpu_semaphore *sem), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 81bb8e9fc26d..d4bac5f49939 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1073,10 +1073,10 @@ static int amdgpu_mm_dump_table(struct seq_file *m, void *data) ret = drm_mm_dump_table(m, mm); spin_unlock(&glob->lru_lock); if (ttm_pl == TTM_PL_VRAM) - seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n", + seq_printf(m, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n", adev->mman.bdev.man[ttm_pl].size, - atomic64_read(&adev->vram_usage) >> 20, - atomic64_read(&adev->vram_vis_usage) >> 20); + (u64)atomic64_read(&adev->vram_usage) >> 20, + (u64)atomic64_read(&adev->vram_vis_usage) >> 20); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 633a32a48560..159ce54bbd8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -143,10 +143,15 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, unsigned i; /* check if the id is still valid */ - if (vm_id->id && vm_id->last_id_use && - vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) { - trace_amdgpu_vm_grab_id(vm_id->id, ring->idx); - return 0; + if (vm_id->id) { + unsigned id = vm_id->id; + long owner; + + owner = atomic_long_read(&adev->vm_manager.ids[id].owner); + if (owner == (long)vm) { + trace_amdgpu_vm_grab_id(vm_id->id, ring->idx); + return 0; + } } /* we definately need to flush */ @@ -154,7 +159,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, /* skip over VMID 0, since it is the system VM */ for (i = 1; i < adev->vm_manager.nvm; ++i) { - struct fence *fence = adev->vm_manager.active[i]; + struct fence *fence = adev->vm_manager.ids[i].active; struct amdgpu_ring *fring; if (fence == NULL) { @@ -176,7 +181,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, if (choices[i]) { struct fence *fence; - fence = adev->vm_manager.active[choices[i]]; + fence = adev->vm_manager.ids[choices[i]].active; vm_id->id = choices[i]; trace_amdgpu_vm_grab_id(choices[i], ring->idx); @@ -207,24 +212,21 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory); struct amdgpu_vm_id *vm_id = &vm->ids[ring->idx]; struct fence *flushed_updates = vm_id->flushed_updates; - bool is_earlier = false; - - if (flushed_updates && updates) { - BUG_ON(flushed_updates->context != updates->context); - is_earlier = (updates->seqno - flushed_updates->seqno <= - INT_MAX) ? true : false; - } + bool is_later; - if (pd_addr != vm_id->pd_gpu_addr || !flushed_updates || - is_earlier) { + if (!flushed_updates) + is_later = true; + else if (!updates) + is_later = false; + else + is_later = fence_is_later(updates, flushed_updates); + if (pd_addr != vm_id->pd_gpu_addr || is_later) { trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id->id); - if (is_earlier) { + if (is_later) { vm_id->flushed_updates = fence_get(updates); fence_put(flushed_updates); } - if (!flushed_updates) - vm_id->flushed_updates = fence_get(updates); vm_id->pd_gpu_addr = pd_addr; amdgpu_ring_emit_vm_flush(ring, vm_id->id, vm_id->pd_gpu_addr); } @@ -244,16 +246,14 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, */ void amdgpu_vm_fence(struct amdgpu_device *adev, struct amdgpu_vm *vm, - struct amdgpu_fence *fence) + struct fence *fence) { - unsigned ridx = fence->ring->idx; - unsigned vm_id = vm->ids[ridx].id; - - fence_put(adev->vm_manager.active[vm_id]); - adev->vm_manager.active[vm_id] = fence_get(&fence->base); + struct amdgpu_ring *ring = amdgpu_ring_from_fence(fence); + unsigned vm_id = vm->ids[ring->idx].id; - fence_put(vm->ids[ridx].last_id_use); - vm->ids[ridx].last_id_use = fence_get(&fence->base); + fence_put(adev->vm_manager.ids[vm_id].active); + adev->vm_manager.ids[vm_id].active = fence_get(fence); + atomic_long_set(&adev->vm_manager.ids[vm_id].owner, (long)vm); } /** @@ -332,6 +332,8 @@ int amdgpu_vm_free_job(struct amdgpu_job *job) * * @adev: amdgpu_device pointer * @bo: bo to clear + * + * need to reserve bo first before calling it. */ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, struct amdgpu_bo *bo) @@ -343,24 +345,20 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, uint64_t addr; int r; - r = amdgpu_bo_reserve(bo, false); - if (r) - return r; - r = reservation_object_reserve_shared(bo->tbo.resv); if (r) return r; r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false); if (r) - goto error_unreserve; + goto error; addr = amdgpu_bo_gpu_offset(bo); entries = amdgpu_bo_size(bo) / 8; ib = kzalloc(sizeof(struct amdgpu_ib), GFP_KERNEL); if (!ib) - goto error_unreserve; + goto error; r = amdgpu_ib_get(ring, NULL, entries * 2 + 64, ib); if (r) @@ -378,16 +376,14 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, if (!r) amdgpu_bo_fence(bo, fence, true); fence_put(fence); - if (amdgpu_enable_scheduler) { - amdgpu_bo_unreserve(bo); + if (amdgpu_enable_scheduler) return 0; - } + error_free: amdgpu_ib_free(adev, ib); kfree(ib); -error_unreserve: - amdgpu_bo_unreserve(bo); +error: return r; } @@ -989,7 +985,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, * Add a mapping of the BO at the specefied addr into the VM. * Returns 0 for success, error for failure. * - * Object has to be reserved and gets unreserved by this function! + * Object has to be reserved and unreserved outside! */ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, @@ -1005,30 +1001,27 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, /* validate the parameters */ if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) { - amdgpu_bo_unreserve(bo_va->bo); + size == 0 || size & AMDGPU_GPU_PAGE_MASK) return -EINVAL; - } /* make sure object fit at this offset */ eaddr = saddr + size; - if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) { - amdgpu_bo_unreserve(bo_va->bo); + if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) return -EINVAL; - } last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE; if (last_pfn > adev->vm_manager.max_pfn) { dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n", last_pfn, adev->vm_manager.max_pfn); - amdgpu_bo_unreserve(bo_va->bo); return -EINVAL; } saddr /= AMDGPU_GPU_PAGE_SIZE; eaddr /= AMDGPU_GPU_PAGE_SIZE; + spin_lock(&vm->it_lock); it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1); + spin_unlock(&vm->it_lock); if (it) { struct amdgpu_bo_va_mapping *tmp; tmp = container_of(it, struct amdgpu_bo_va_mapping, it); @@ -1036,14 +1029,12 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, dev_err(adev->dev, "bo %p va 0x%010Lx-0x%010Lx conflict with " "0x%010lx-0x%010lx\n", bo_va->bo, saddr, eaddr, tmp->it.start, tmp->it.last + 1); - amdgpu_bo_unreserve(bo_va->bo); r = -EINVAL; goto error; } mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); if (!mapping) { - amdgpu_bo_unreserve(bo_va->bo); r = -ENOMEM; goto error; } @@ -1055,7 +1046,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, mapping->flags = flags; list_add(&mapping->list, &bo_va->invalids); + spin_lock(&vm->it_lock); interval_tree_insert(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_map(bo_va, mapping); /* Make sure the page tables are allocated */ @@ -1067,8 +1060,6 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, if (eaddr > vm->max_pde_used) vm->max_pde_used = eaddr; - amdgpu_bo_unreserve(bo_va->bo); - /* walk over the address space and allocate the page tables */ for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) { struct reservation_object *resv = vm->page_directory->tbo.resv; @@ -1077,13 +1068,11 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, if (vm->page_tables[pt_idx].bo) continue; - ww_mutex_lock(&resv->lock, NULL); r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8, AMDGPU_GPU_PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM, AMDGPU_GEM_CREATE_NO_CPU_ACCESS, NULL, resv, &pt); - ww_mutex_unlock(&resv->lock); if (r) goto error_free; @@ -1101,7 +1090,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, error_free: list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); kfree(mapping); @@ -1119,7 +1110,7 @@ error: * Remove a mapping of the BO at the specefied addr from the VM. * Returns 0 for success, error for failure. * - * Object has to be reserved and gets unreserved by this function! + * Object has to be reserved and unreserved outside! */ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, @@ -1144,21 +1135,20 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, break; } - if (&mapping->list == &bo_va->invalids) { - amdgpu_bo_unreserve(bo_va->bo); + if (&mapping->list == &bo_va->invalids) return -ENOENT; - } } list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); if (valid) list_add(&mapping->list, &vm->freed); else kfree(mapping); - amdgpu_bo_unreserve(bo_va->bo); return 0; } @@ -1187,13 +1177,17 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, list_for_each_entry_safe(mapping, next, &bo_va->valids, list) { list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); list_add(&mapping->list, &vm->freed); } list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) { list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); kfree(mapping); } @@ -1241,7 +1235,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { vm->ids[i].id = 0; vm->ids[i].flushed_updates = NULL; - vm->ids[i].last_id_use = NULL; } mutex_init(&vm->mutex); vm->va = RB_ROOT; @@ -1249,7 +1242,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) INIT_LIST_HEAD(&vm->invalidated); INIT_LIST_HEAD(&vm->cleared); INIT_LIST_HEAD(&vm->freed); - + spin_lock_init(&vm->it_lock); pd_size = amdgpu_vm_directory_size(adev); pd_entries = amdgpu_vm_num_pdes(adev); @@ -1269,8 +1262,14 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) NULL, NULL, &vm->page_directory); if (r) return r; - + r = amdgpu_bo_reserve(vm->page_directory, false); + if (r) { + amdgpu_bo_unref(&vm->page_directory); + vm->page_directory = NULL; + return r; + } r = amdgpu_vm_clear_bo(adev, vm->page_directory); + amdgpu_bo_unreserve(vm->page_directory); if (r) { amdgpu_bo_unref(&vm->page_directory); vm->page_directory = NULL; @@ -1313,11 +1312,28 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + unsigned id = vm->ids[i].id; + + atomic_long_cmpxchg(&adev->vm_manager.ids[id].owner, + (long)vm, 0); fence_put(vm->ids[i].flushed_updates); - fence_put(vm->ids[i].last_id_use); } mutex_destroy(&vm->mutex); } + +/** + * amdgpu_vm_manager_fini - cleanup VM manager + * + * @adev: amdgpu_device pointer + * + * Cleanup the VM manager and free resources. + */ +void amdgpu_vm_manager_fini(struct amdgpu_device *adev) +{ + unsigned i; + + for (i = 0; i < AMDGPU_NUM_VM; ++i) + fence_put(adev->vm_manager.ids[i].active); +} diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index a1a35a5df8e7..57a2e347f04d 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -6569,12 +6569,12 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev, switch (state) { case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; + cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; + cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; default: @@ -6586,12 +6586,12 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev, switch (state) { case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; + cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; + cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 6776cf756d40..e1dcab98e249 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -268,7 +268,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmCGTT_CP_CLK_CTRL, 0xffffffff, 0x00000100, mmCGTT_CPC_CLK_CTRL, 0xffffffff, 0x00000100, mmCGTT_CPF_CLK_CTRL, 0xffffffff, 0x40000100, - mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100, mmCGTT_GDS_CLK_CTRL, 0xffffffff, 0x00000100, mmCGTT_IA_CLK_CTRL, 0xffffffff, 0x06000100, mmCGTT_PA_CLK_CTRL, 0xffffffff, 0x00000100, @@ -296,10 +295,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96e00200, mmCP_RB_WPTR_POLL_CNTL, 0xffffffff, 0x00900100, mmRLC_CGCG_CGLS_CTRL, 0xffffffff, 0x0020003c, - mmPCIE_INDEX, 0xffffffff, 0x0140001c, - mmPCIE_DATA, 0x000f0000, 0x00000000, - mmCGTT_DRM_CLK_CTRL0, 0xff000fff, 0x00000100, - mmHDP_XDP_CGTT_BLK_CTRL, 0xc0000fff, 0x00000104, mmCP_MEM_SLP_CNTL, 0x00000001, 0x00000001, }; @@ -1000,7 +995,7 @@ static void gfx_v8_0_gpu_early_init(struct amdgpu_device *adev) adev->gfx.config.max_cu_per_sh = 16; adev->gfx.config.max_sh_per_se = 1; adev->gfx.config.max_backends_per_se = 4; - adev->gfx.config.max_texture_channel_caches = 8; + adev->gfx.config.max_texture_channel_caches = 16; adev->gfx.config.max_gprs = 256; adev->gfx.config.max_gs_threads = 32; adev->gfx.config.max_hw_contexts = 8; @@ -1613,6 +1608,296 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev) WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden); } case CHIP_FIJI: + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) { + switch (reg_offset) { + case 0: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 1: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 2: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 3: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 4: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 5: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 6: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 7: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 8: + gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16)); + break; + case 9: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 10: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 11: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 12: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 13: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 14: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 15: + gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 16: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 17: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 18: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 19: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 20: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 21: + gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 22: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 23: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 24: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 25: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_XTHICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 26: + gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_XTHICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 27: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 28: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 29: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 30: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + default: + gb_tile_moden = 0; + break; + } + adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden; + WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden); + } + for (reg_offset = 0; reg_offset < num_secondary_tile_mode_states; reg_offset++) { + switch (reg_offset) { + case 0: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 1: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 2: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 3: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 4: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 5: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 6: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 8: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 9: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 10: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 11: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 12: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 13: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 14: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_4_BANK)); + break; + case 7: + /* unused idx */ + continue; + default: + gb_tile_moden = 0; + break; + } + adev->gfx.config.macrotile_mode_array[reg_offset] = gb_tile_moden; + WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden); + } + break; case CHIP_TONGA: for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) { switch (reg_offset) { @@ -2971,10 +3256,13 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev) amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START); switch (adev->asic_type) { case CHIP_TONGA: - case CHIP_FIJI: amdgpu_ring_write(ring, 0x16000012); amdgpu_ring_write(ring, 0x0000002A); break; + case CHIP_FIJI: + amdgpu_ring_write(ring, 0x3a00161a); + amdgpu_ring_write(ring, 0x0000002e); + break; case CHIP_TOPAZ: case CHIP_CARRIZO: amdgpu_ring_write(ring, 0x00000002); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 85bbcdc73fff..7427d8cd4c43 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -40,7 +40,7 @@ static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev); -MODULE_FIRMWARE("radeon/boniare_mc.bin"); +MODULE_FIRMWARE("radeon/bonaire_mc.bin"); MODULE_FIRMWARE("radeon/hawaii_mc.bin"); /** @@ -501,6 +501,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1); WREG32(mmVM_L2_CNTL, tmp); tmp = REG_SET_FIELD(0, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1); @@ -960,12 +961,10 @@ static int gmc_v7_0_sw_init(void *handle) static int gmc_v7_0_sw_fini(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v7_0_vm_fini(adev); adev->vm_manager.enabled = false; } @@ -1010,12 +1009,10 @@ static int gmc_v7_0_hw_fini(void *handle) static int gmc_v7_0_suspend(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v7_0_vm_fini(adev); adev->vm_manager.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 1bcc4e74e3b4..cb0e50ebb528 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -629,6 +629,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1); WREG32(mmVM_L2_CNTL, tmp); tmp = RREG32(mmVM_L2_CNTL2); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1); @@ -979,12 +980,10 @@ static int gmc_v8_0_sw_init(void *handle) static int gmc_v8_0_sw_fini(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v8_0_vm_fini(adev); adev->vm_manager.enabled = false; } @@ -1031,12 +1030,10 @@ static int gmc_v8_0_hw_fini(void *handle) static int gmc_v8_0_suspend(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v8_0_vm_fini(adev); adev->vm_manager.enabled = false; } diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h index 144f50acc971..c89dc777768f 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h @@ -16,6 +16,8 @@ TRACE_EVENT(amd_sched_job, TP_ARGS(sched_job), TP_STRUCT__entry( __field(struct amd_sched_entity *, entity) + __field(struct amd_sched_job *, sched_job) + __field(struct fence *, fence) __field(const char *, name) __field(u32, job_count) __field(int, hw_job_count) @@ -23,16 +25,32 @@ TRACE_EVENT(amd_sched_job, TP_fast_assign( __entry->entity = sched_job->s_entity; + __entry->sched_job = sched_job; + __entry->fence = &sched_job->s_fence->base; __entry->name = sched_job->sched->name; __entry->job_count = kfifo_len( &sched_job->s_entity->job_queue) / sizeof(sched_job); __entry->hw_job_count = atomic_read( &sched_job->sched->hw_rq_count); ), - TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d", - __entry->entity, __entry->name, __entry->job_count, - __entry->hw_job_count) + TP_printk("entity=%p, sched job=%p, fence=%p, ring=%s, job count:%u, hw job count:%d", + __entry->entity, __entry->sched_job, __entry->fence, __entry->name, + __entry->job_count, __entry->hw_job_count) ); + +TRACE_EVENT(amd_sched_process_job, + TP_PROTO(struct amd_sched_fence *fence), + TP_ARGS(fence), + TP_STRUCT__entry( + __field(struct fence *, fence) + ), + + TP_fast_assign( + __entry->fence = &fence->base; + ), + TP_printk("fence=%p signaled", __entry->fence) +); + #endif /* This part must be outside protection */ diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 89619a5a4289..ea30d6ad4c13 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -34,6 +34,9 @@ static struct amd_sched_job * amd_sched_entity_pop_job(struct amd_sched_entity *entity); static void amd_sched_wakeup(struct amd_gpu_scheduler *sched); +struct kmem_cache *sched_fence_slab; +atomic_t sched_fence_slab_ref = ATOMIC_INIT(0); + /* Initialize a given run queue struct */ static void amd_sched_rq_init(struct amd_sched_rq *rq) { @@ -273,22 +276,13 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job) * * Returns 0 for success, negative error code otherwise. */ -int amd_sched_entity_push_job(struct amd_sched_job *sched_job) +void amd_sched_entity_push_job(struct amd_sched_job *sched_job) { struct amd_sched_entity *entity = sched_job->s_entity; - struct amd_sched_fence *fence = amd_sched_fence_create( - entity, sched_job->owner); - - if (!fence) - return -ENOMEM; - - fence_get(&fence->base); - sched_job->s_fence = fence; wait_event(entity->sched->job_scheduled, amd_sched_entity_in(sched_job)); trace_amd_sched_job(sched_job); - return 0; } /** @@ -343,6 +337,7 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb) list_del_init(&s_fence->list); spin_unlock_irqrestore(&sched->fence_list_lock, flags); } + trace_amd_sched_process_job(s_fence); fence_put(&s_fence->base); wake_up_interruptible(&sched->wake_up_worker); } @@ -450,6 +445,13 @@ int amd_sched_init(struct amd_gpu_scheduler *sched, init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled); atomic_set(&sched->hw_rq_count, 0); + if (atomic_inc_return(&sched_fence_slab_ref) == 1) { + sched_fence_slab = kmem_cache_create( + "amd_sched_fence", sizeof(struct amd_sched_fence), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!sched_fence_slab) + return -ENOMEM; + } /* Each scheduler will run on a seperate kernel thread */ sched->thread = kthread_run(amd_sched_main, sched, sched->name); @@ -470,4 +472,6 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched) { if (sched->thread) kthread_stop(sched->thread); + if (atomic_dec_and_test(&sched_fence_slab_ref)) + kmem_cache_destroy(sched_fence_slab); } diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h index 929e9aced041..939692b14f4b 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h @@ -30,6 +30,9 @@ struct amd_gpu_scheduler; struct amd_sched_rq; +extern struct kmem_cache *sched_fence_slab; +extern atomic_t sched_fence_slab_ref; + /** * A scheduler entity is a wrapper around a job queue or a group * of other entities. Entities take turns emitting jobs from their @@ -76,7 +79,6 @@ struct amd_sched_job { struct amd_gpu_scheduler *sched; struct amd_sched_entity *s_entity; struct amd_sched_fence *s_fence; - void *owner; }; extern const struct fence_ops amd_sched_fence_ops; @@ -128,7 +130,7 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched, uint32_t jobs); void amd_sched_entity_fini(struct amd_gpu_scheduler *sched, struct amd_sched_entity *entity); -int amd_sched_entity_push_job(struct amd_sched_job *sched_job); +void amd_sched_entity_push_job(struct amd_sched_job *sched_job); struct amd_sched_fence *amd_sched_fence_create( struct amd_sched_entity *s_entity, void *owner); diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c index d802638094f4..8d2130b9ff05 100644 --- a/drivers/gpu/drm/amd/scheduler/sched_fence.c +++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c @@ -32,7 +32,7 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity struct amd_sched_fence *fence = NULL; unsigned seq; - fence = kzalloc(sizeof(struct amd_sched_fence), GFP_KERNEL); + fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL); if (fence == NULL) return NULL; fence->owner = owner; @@ -71,11 +71,17 @@ static bool amd_sched_fence_enable_signaling(struct fence *f) return true; } +static void amd_sched_fence_release(struct fence *f) +{ + struct amd_sched_fence *fence = to_amd_sched_fence(f); + kmem_cache_free(sched_fence_slab, fence); +} + const struct fence_ops amd_sched_fence_ops = { .get_driver_name = amd_sched_fence_get_driver_name, .get_timeline_name = amd_sched_fence_get_timeline_name, .enable_signaling = amd_sched_fence_enable_signaling, .signaled = NULL, .wait = fence_default_wait, - .release = NULL, + .release = amd_sched_fence_release, }; diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c index 4f2068fe5d88..a7bf6a90eae5 100644 --- a/drivers/gpu/drm/mgag200/mgag200_cursor.c +++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c @@ -70,6 +70,11 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc, BUG_ON(pixels_2 != pixels_current && pixels_2 != pixels_prev); BUG_ON(pixels_current == pixels_prev); + if (!handle || !file_priv) { + mga_hide_cursor(mdev); + return 0; + } + obj = drm_gem_object_lookup(dev, file_priv, handle); if (!obj) return -ENOENT; @@ -88,12 +93,6 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc, goto out_unreserve1; } - if (!handle) { - mga_hide_cursor(mdev); - ret = 0; - goto out1; - } - /* Move cursor buffers into VRAM if they aren't already */ if (!pixels_1->pin_count) { ret = mgag200_bo_pin(pixels_1, TTM_PL_FLAG_VRAM, diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index d3024883b844..84d45633d28c 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -221,11 +221,17 @@ int radeon_bo_create(struct radeon_device *rdev, if (!(rdev->flags & RADEON_IS_PCIE)) bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); + /* Write-combined CPU mappings of GTT cause GPU hangs with RV6xx + * See https://bugs.freedesktop.org/show_bug.cgi?id=91268 + */ + if (rdev->family >= CHIP_RV610 && rdev->family <= CHIP_RV635) + bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); + #ifdef CONFIG_X86_32 /* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit * See https://bugs.freedesktop.org/show_bug.cgi?id=84627 */ - bo->flags &= ~RADEON_GEM_GTT_WC; + bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); #elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT) /* Don't try to enable write-combining when it can't work, or things * may be slow @@ -235,9 +241,10 @@ int radeon_bo_create(struct radeon_device *rdev, #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \ thanks to write-combining - DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " - "better performance thanks to write-combining\n"); - bo->flags &= ~RADEON_GEM_GTT_WC; + if (bo->flags & RADEON_GEM_GTT_WC) + DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " + "better performance thanks to write-combining\n"); + bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); #endif radeon_ttm_placement_from_domain(bo, domain); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 6d80dde23400..f4f03dcc1530 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1542,8 +1542,7 @@ int radeon_pm_late_init(struct radeon_device *rdev) ret = device_create_file(rdev->dev, &dev_attr_power_method); if (ret) DRM_ERROR("failed to create device file for power method\n"); - if (!ret) - rdev->pm.sysfs_initialized = true; + rdev->pm.sysfs_initialized = true; } mutex_lock(&rdev->pm.mutex); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index e72bf46042e0..a82b891ae1fe 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2927,7 +2927,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, - { PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, { 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 7a9f4768591e..265064c62d49 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -168,7 +168,7 @@ static int vc4_get_clock_select(struct drm_crtc *crtc) struct drm_connector *connector; drm_for_each_connector(connector, crtc->dev) { - if (connector && connector->state->crtc == crtc) { + if (connector->state->crtc == crtc) { struct drm_encoder *encoder = connector->encoder; struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder); @@ -401,7 +401,8 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, dlist_next++; HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), - (u32 *)vc4_crtc->dlist - (u32 *)vc4->hvs->dlist); + (u32 __iomem *)vc4_crtc->dlist - + (u32 __iomem *)vc4->hvs->dlist); /* Make the next display list start after ours. */ vc4_crtc->dlist_size -= (dlist_next - vc4_crtc->dlist); @@ -591,14 +592,14 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data) * that will take too much. */ primary_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_PRIMARY); - if (!primary_plane) { + if (IS_ERR(primary_plane)) { dev_err(dev, "failed to construct primary plane\n"); ret = PTR_ERR(primary_plane); goto err; } cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR); - if (!cursor_plane) { + if (IS_ERR(cursor_plane)) { dev_err(dev, "failed to construct cursor plane\n"); ret = PTR_ERR(cursor_plane); goto err_primary; diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 6e730605edcc..d5db9e0f3b73 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -259,7 +259,6 @@ static struct platform_driver vc4_platform_driver = { .remove = vc4_platform_drm_remove, .driver = { .name = "vc4-drm", - .owner = THIS_MODULE, .of_match_table = vc4_of_match, }, }; diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index ab1673f672a4..8098c5b21ba4 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -75,10 +75,10 @@ void vc4_hvs_dump_state(struct drm_device *dev) for (i = 0; i < 64; i += 4) { DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n", i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D", - ((uint32_t *)vc4->hvs->dlist)[i + 0], - ((uint32_t *)vc4->hvs->dlist)[i + 1], - ((uint32_t *)vc4->hvs->dlist)[i + 2], - ((uint32_t *)vc4->hvs->dlist)[i + 3]); + readl((u32 __iomem *)vc4->hvs->dlist + i + 0), + readl((u32 __iomem *)vc4->hvs->dlist + i + 1), + readl((u32 __iomem *)vc4->hvs->dlist + i + 2), + readl((u32 __iomem *)vc4->hvs->dlist + i + 3)); } } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index cdd8b10c0147..887f3caad0be 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -70,7 +70,7 @@ static bool plane_enabled(struct drm_plane_state *state) return state->fb && state->crtc; } -struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane) +static struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane) { struct vc4_plane_state *vc4_state; @@ -97,8 +97,8 @@ struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane) return &vc4_state->base; } -void vc4_plane_destroy_state(struct drm_plane *plane, - struct drm_plane_state *state) +static void vc4_plane_destroy_state(struct drm_plane *plane, + struct drm_plane_state *state) { struct vc4_plane_state *vc4_state = to_vc4_plane_state(state); @@ -108,7 +108,7 @@ void vc4_plane_destroy_state(struct drm_plane *plane, } /* Called during init to allocate the plane's atomic state. */ -void vc4_plane_reset(struct drm_plane *plane) +static void vc4_plane_reset(struct drm_plane *plane) { struct vc4_plane_state *vc4_state; @@ -157,6 +157,16 @@ static int vc4_plane_mode_set(struct drm_plane *plane, int crtc_w = state->crtc_w; int crtc_h = state->crtc_h; + if (state->crtc_w << 16 != state->src_w || + state->crtc_h << 16 != state->src_h) { + /* We don't support scaling yet, which involves + * allocating the LBM memory for scaling temporary + * storage, and putting filter kernels in the HVS + * context. + */ + return -EINVAL; + } + if (crtc_x < 0) { offset += drm_format_plane_cpp(fb->pixel_format, 0) * -crtc_x; crtc_w += crtc_x; diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 842b0043ad94..8f59f057cdf4 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -324,6 +324,7 @@ config SENSORS_APPLESMC config SENSORS_ARM_SCPI tristate "ARM SCPI Sensors" depends on ARM_SCPI_PROTOCOL + depends on THERMAL || !THERMAL_OF help This driver provides support for temperature, voltage, current and power sensors available on ARM Ltd's SCP based platforms. The @@ -1471,6 +1472,7 @@ config SENSORS_INA209 config SENSORS_INA2XX tristate "Texas Instruments INA219 and compatibles" depends on I2C + select REGMAP_I2C help If you say yes here you get support for INA219, INA220, INA226, INA230, and INA231 power monitor chips. diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 1f5e956941b1..0af7fd311979 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -537,7 +537,7 @@ static int applesmc_init_index(struct applesmc_registers *s) static int applesmc_init_smcreg_try(void) { struct applesmc_registers *s = &smcreg; - bool left_light_sensor, right_light_sensor; + bool left_light_sensor = 0, right_light_sensor = 0; unsigned int count; u8 tmp[1]; int ret; diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c index 2c1241bbf9af..7e20567bc369 100644 --- a/drivers/hwmon/scpi-hwmon.c +++ b/drivers/hwmon/scpi-hwmon.c @@ -117,7 +117,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev) struct scpi_ops *scpi_ops; struct device *hwdev, *dev = &pdev->dev; struct scpi_sensors *scpi_sensors; - int ret; + int ret, idx; scpi_ops = get_scpi_ops(); if (!scpi_ops) @@ -146,8 +146,8 @@ static int scpi_hwmon_probe(struct platform_device *pdev) scpi_sensors->scpi_ops = scpi_ops; - for (i = 0; i < nr_sensors; i++) { - struct sensor_data *sensor = &scpi_sensors->data[i]; + for (i = 0, idx = 0; i < nr_sensors; i++) { + struct sensor_data *sensor = &scpi_sensors->data[idx]; ret = scpi_ops->sensor_get_info(i, &sensor->info); if (ret) @@ -183,7 +183,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev) num_power++; break; default: - break; + continue; } sensor->dev_attr_input.attr.mode = S_IRUGO; @@ -194,11 +194,12 @@ static int scpi_hwmon_probe(struct platform_device *pdev) sensor->dev_attr_label.show = scpi_show_label; sensor->dev_attr_label.attr.name = sensor->label; - scpi_sensors->attrs[i << 1] = &sensor->dev_attr_input.attr; - scpi_sensors->attrs[(i << 1) + 1] = &sensor->dev_attr_label.attr; + scpi_sensors->attrs[idx << 1] = &sensor->dev_attr_input.attr; + scpi_sensors->attrs[(idx << 1) + 1] = &sensor->dev_attr_label.attr; - sysfs_attr_init(scpi_sensors->attrs[i << 1]); - sysfs_attr_init(scpi_sensors->attrs[(i << 1) + 1]); + sysfs_attr_init(scpi_sensors->attrs[idx << 1]); + sysfs_attr_init(scpi_sensors->attrs[(idx << 1) + 1]); + idx++; } scpi_sensors->group.attrs = scpi_sensors->attrs; @@ -236,8 +237,8 @@ static int scpi_hwmon_probe(struct platform_device *pdev) zone->sensor_id = i; zone->scpi_sensors = scpi_sensors; - zone->tzd = thermal_zone_of_sensor_register(dev, i, zone, - &scpi_sensor_ops); + zone->tzd = thermal_zone_of_sensor_register(dev, + sensor->info.sensor_id, zone, &scpi_sensor_ops); /* * The call to thermal_zone_of_sensor_register returns * an error for sensors that are not associated with diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index cbe198cb3699..471ee36b9c6e 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -216,6 +216,7 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain, u8 *page_addr = (u8 *) (pa & PAGE_MASK); dma_addr_t start_dma_addr = dma_addr; unsigned long irq_flags, nr_pages, i; + unsigned long *entry; int rc = 0; if (dma_addr < s390_domain->domain.geometry.aperture_start || @@ -228,8 +229,12 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain, spin_lock_irqsave(&s390_domain->dma_table_lock, irq_flags); for (i = 0; i < nr_pages; i++) { - dma_update_cpu_trans(s390_domain->dma_table, page_addr, - dma_addr, flags); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + if (!entry) { + rc = -ENOMEM; + goto undo_cpu_trans; + } + dma_update_cpu_trans(entry, page_addr, flags); page_addr += PAGE_SIZE; dma_addr += PAGE_SIZE; } @@ -242,6 +247,20 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain, break; } spin_unlock(&s390_domain->list_lock); + +undo_cpu_trans: + if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { + flags = ZPCI_PTE_INVALID; + while (i-- > 0) { + page_addr -= PAGE_SIZE; + dma_addr -= PAGE_SIZE; + entry = dma_walk_cpu_trans(s390_domain->dma_table, + dma_addr); + if (!entry) + break; + dma_update_cpu_trans(entry, page_addr, flags); + } + } spin_unlock_irqrestore(&s390_domain->dma_table_lock, irq_flags); return rc; diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 9093577755f6..0527f485c3dc 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -15,9 +15,7 @@ #include <linux/netdevice.h> #include <linux/phy.h> #include <net/dsa.h> - -#define REG_PORT(p) (8 + (p)) -#define REG_GLOBAL 0x0f +#include "mv88e6060.h" static int reg_read(struct dsa_switch *ds, int addr, int reg) { @@ -67,13 +65,14 @@ static char *mv88e6060_probe(struct device *host_dev, int sw_addr) if (bus == NULL) return NULL; - ret = mdiobus_read(bus, sw_addr + REG_PORT(0), 0x03); + ret = mdiobus_read(bus, sw_addr + REG_PORT(0), PORT_SWITCH_ID); if (ret >= 0) { - if (ret == 0x0600) + if (ret == PORT_SWITCH_ID_6060) return "Marvell 88E6060 (A0)"; - if (ret == 0x0601 || ret == 0x0602) + if (ret == PORT_SWITCH_ID_6060_R1 || + ret == PORT_SWITCH_ID_6060_R2) return "Marvell 88E6060 (B0)"; - if ((ret & 0xfff0) == 0x0600) + if ((ret & PORT_SWITCH_ID_6060_MASK) == PORT_SWITCH_ID_6060) return "Marvell 88E6060"; } @@ -87,22 +86,26 @@ static int mv88e6060_switch_reset(struct dsa_switch *ds) unsigned long timeout; /* Set all ports to the disabled state. */ - for (i = 0; i < 6; i++) { - ret = REG_READ(REG_PORT(i), 0x04); - REG_WRITE(REG_PORT(i), 0x04, ret & 0xfffc); + for (i = 0; i < MV88E6060_PORTS; i++) { + ret = REG_READ(REG_PORT(i), PORT_CONTROL); + REG_WRITE(REG_PORT(i), PORT_CONTROL, + ret & ~PORT_CONTROL_STATE_MASK); } /* Wait for transmit queues to drain. */ usleep_range(2000, 4000); /* Reset the switch. */ - REG_WRITE(REG_GLOBAL, 0x0a, 0xa130); + REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_SWRESET | + GLOBAL_ATU_CONTROL_ATUSIZE_1024 | + GLOBAL_ATU_CONTROL_ATE_AGE_5MIN); /* Wait up to one second for reset to complete. */ timeout = jiffies + 1 * HZ; while (time_before(jiffies, timeout)) { - ret = REG_READ(REG_GLOBAL, 0x00); - if ((ret & 0x8000) == 0x0000) + ret = REG_READ(REG_GLOBAL, GLOBAL_STATUS); + if (ret & GLOBAL_STATUS_INIT_READY) break; usleep_range(1000, 2000); @@ -119,13 +122,15 @@ static int mv88e6060_setup_global(struct dsa_switch *ds) * set the maximum frame size to 1536 bytes, and mask all * interrupt sources. */ - REG_WRITE(REG_GLOBAL, 0x04, 0x0800); + REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL, GLOBAL_CONTROL_MAX_FRAME_1536); /* Enable automatic address learning, set the address * database size to 1024 entries, and set the default aging * time to 5 minutes. */ - REG_WRITE(REG_GLOBAL, 0x0a, 0x2130); + REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_ATUSIZE_1024 | + GLOBAL_ATU_CONTROL_ATE_AGE_5MIN); return 0; } @@ -139,25 +144,30 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) * state to Forwarding. Additionally, if this is the CPU * port, enable Ingress and Egress Trailer tagging mode. */ - REG_WRITE(addr, 0x04, dsa_is_cpu_port(ds, p) ? 0x4103 : 0x0003); + REG_WRITE(addr, PORT_CONTROL, + dsa_is_cpu_port(ds, p) ? + PORT_CONTROL_TRAILER | + PORT_CONTROL_INGRESS_MODE | + PORT_CONTROL_STATE_FORWARDING : + PORT_CONTROL_STATE_FORWARDING); /* Port based VLAN map: give each port its own address * database, allow the CPU port to talk to each of the 'real' * ports, and allow each of the 'real' ports to only talk to * the CPU port. */ - REG_WRITE(addr, 0x06, - ((p & 0xf) << 12) | - (dsa_is_cpu_port(ds, p) ? - ds->phys_port_mask : - (1 << ds->dst->cpu_port))); + REG_WRITE(addr, PORT_VLAN_MAP, + ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | + (dsa_is_cpu_port(ds, p) ? + ds->phys_port_mask : + BIT(ds->dst->cpu_port))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using * a port bitmap that has only the bit for this port set and * the other bits clear. */ - REG_WRITE(addr, 0x0b, 1 << p); + REG_WRITE(addr, PORT_ASSOC_VECTOR, BIT(p)); return 0; } @@ -177,7 +187,7 @@ static int mv88e6060_setup(struct dsa_switch *ds) if (ret < 0) return ret; - for (i = 0; i < 6; i++) { + for (i = 0; i < MV88E6060_PORTS; i++) { ret = mv88e6060_setup_port(ds, i); if (ret < 0) return ret; @@ -188,16 +198,17 @@ static int mv88e6060_setup(struct dsa_switch *ds) static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr) { - REG_WRITE(REG_GLOBAL, 0x01, (addr[0] << 8) | addr[1]); - REG_WRITE(REG_GLOBAL, 0x02, (addr[2] << 8) | addr[3]); - REG_WRITE(REG_GLOBAL, 0x03, (addr[4] << 8) | addr[5]); + /* Use the same MAC Address as FD Pause frames for all ports */ + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); return 0; } static int mv88e6060_port_to_phy_addr(int port) { - if (port >= 0 && port <= 5) + if (port >= 0 && port < MV88E6060_PORTS) return port; return -1; } @@ -225,54 +236,6 @@ mv88e6060_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) return reg_write(ds, addr, regnum, val); } -static void mv88e6060_poll_link(struct dsa_switch *ds) -{ - int i; - - for (i = 0; i < DSA_MAX_PORTS; i++) { - struct net_device *dev; - int uninitialized_var(port_status); - int link; - int speed; - int duplex; - int fc; - - dev = ds->ports[i]; - if (dev == NULL) - continue; - - link = 0; - if (dev->flags & IFF_UP) { - port_status = reg_read(ds, REG_PORT(i), 0x00); - if (port_status < 0) - continue; - - link = !!(port_status & 0x1000); - } - - if (!link) { - if (netif_carrier_ok(dev)) { - netdev_info(dev, "link down\n"); - netif_carrier_off(dev); - } - continue; - } - - speed = (port_status & 0x0100) ? 100 : 10; - duplex = (port_status & 0x0200) ? 1 : 0; - fc = ((port_status & 0xc000) == 0xc000) ? 1 : 0; - - if (!netif_carrier_ok(dev)) { - netdev_info(dev, - "link up, %d Mb/s, %s duplex, flow control %sabled\n", - speed, - duplex ? "full" : "half", - fc ? "en" : "dis"); - netif_carrier_on(dev); - } - } -} - static struct dsa_switch_driver mv88e6060_switch_driver = { .tag_protocol = DSA_TAG_PROTO_TRAILER, .probe = mv88e6060_probe, @@ -280,7 +243,6 @@ static struct dsa_switch_driver mv88e6060_switch_driver = { .set_addr = mv88e6060_set_addr, .phy_read = mv88e6060_phy_read, .phy_write = mv88e6060_phy_write, - .poll_link = mv88e6060_poll_link, }; static int __init mv88e6060_init(void) diff --git a/drivers/net/dsa/mv88e6060.h b/drivers/net/dsa/mv88e6060.h new file mode 100644 index 000000000000..cc9b2ed4aff4 --- /dev/null +++ b/drivers/net/dsa/mv88e6060.h @@ -0,0 +1,111 @@ +/* + * drivers/net/dsa/mv88e6060.h - Marvell 88e6060 switch chip support + * Copyright (c) 2015 Neil Armstrong + * + * Based on mv88e6xxx.h + * Copyright (c) 2008 Marvell Semiconductor + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __MV88E6060_H +#define __MV88E6060_H + +#define MV88E6060_PORTS 6 + +#define REG_PORT(p) (0x8 + (p)) +#define PORT_STATUS 0x00 +#define PORT_STATUS_PAUSE_EN BIT(15) +#define PORT_STATUS_MY_PAUSE BIT(14) +#define PORT_STATUS_FC (PORT_STATUS_MY_PAUSE | PORT_STATUS_PAUSE_EN) +#define PORT_STATUS_RESOLVED BIT(13) +#define PORT_STATUS_LINK BIT(12) +#define PORT_STATUS_PORTMODE BIT(11) +#define PORT_STATUS_PHYMODE BIT(10) +#define PORT_STATUS_DUPLEX BIT(9) +#define PORT_STATUS_SPEED BIT(8) +#define PORT_SWITCH_ID 0x03 +#define PORT_SWITCH_ID_6060 0x0600 +#define PORT_SWITCH_ID_6060_MASK 0xfff0 +#define PORT_SWITCH_ID_6060_R1 0x0601 +#define PORT_SWITCH_ID_6060_R2 0x0602 +#define PORT_CONTROL 0x04 +#define PORT_CONTROL_FORCE_FLOW_CTRL BIT(15) +#define PORT_CONTROL_TRAILER BIT(14) +#define PORT_CONTROL_HEADER BIT(11) +#define PORT_CONTROL_INGRESS_MODE BIT(8) +#define PORT_CONTROL_VLAN_TUNNEL BIT(7) +#define PORT_CONTROL_STATE_MASK 0x03 +#define PORT_CONTROL_STATE_DISABLED 0x00 +#define PORT_CONTROL_STATE_BLOCKING 0x01 +#define PORT_CONTROL_STATE_LEARNING 0x02 +#define PORT_CONTROL_STATE_FORWARDING 0x03 +#define PORT_VLAN_MAP 0x06 +#define PORT_VLAN_MAP_DBNUM_SHIFT 12 +#define PORT_VLAN_MAP_TABLE_MASK 0x1f +#define PORT_ASSOC_VECTOR 0x0b +#define PORT_ASSOC_VECTOR_MONITOR BIT(15) +#define PORT_ASSOC_VECTOR_PAV_MASK 0x1f +#define PORT_RX_CNTR 0x10 +#define PORT_TX_CNTR 0x11 + +#define REG_GLOBAL 0x0f +#define GLOBAL_STATUS 0x00 +#define GLOBAL_STATUS_SW_MODE_MASK (0x3 << 12) +#define GLOBAL_STATUS_SW_MODE_0 (0x0 << 12) +#define GLOBAL_STATUS_SW_MODE_1 (0x1 << 12) +#define GLOBAL_STATUS_SW_MODE_2 (0x2 << 12) +#define GLOBAL_STATUS_SW_MODE_3 (0x3 << 12) +#define GLOBAL_STATUS_INIT_READY BIT(11) +#define GLOBAL_STATUS_ATU_FULL BIT(3) +#define GLOBAL_STATUS_ATU_DONE BIT(2) +#define GLOBAL_STATUS_PHY_INT BIT(1) +#define GLOBAL_STATUS_EEINT BIT(0) +#define GLOBAL_MAC_01 0x01 +#define GLOBAL_MAC_01_DIFF_ADDR BIT(8) +#define GLOBAL_MAC_23 0x02 +#define GLOBAL_MAC_45 0x03 +#define GLOBAL_CONTROL 0x04 +#define GLOBAL_CONTROL_DISCARD_EXCESS BIT(13) +#define GLOBAL_CONTROL_MAX_FRAME_1536 BIT(10) +#define GLOBAL_CONTROL_RELOAD_EEPROM BIT(9) +#define GLOBAL_CONTROL_CTRMODE BIT(8) +#define GLOBAL_CONTROL_ATU_FULL_EN BIT(3) +#define GLOBAL_CONTROL_ATU_DONE_EN BIT(2) +#define GLOBAL_CONTROL_PHYINT_EN BIT(1) +#define GLOBAL_CONTROL_EEPROM_DONE_EN BIT(0) +#define GLOBAL_ATU_CONTROL 0x0a +#define GLOBAL_ATU_CONTROL_SWRESET BIT(15) +#define GLOBAL_ATU_CONTROL_LEARNDIS BIT(14) +#define GLOBAL_ATU_CONTROL_ATUSIZE_256 (0x0 << 12) +#define GLOBAL_ATU_CONTROL_ATUSIZE_512 (0x1 << 12) +#define GLOBAL_ATU_CONTROL_ATUSIZE_1024 (0x2 << 12) +#define GLOBAL_ATU_CONTROL_ATE_AGE_SHIFT 4 +#define GLOBAL_ATU_CONTROL_ATE_AGE_MASK (0xff << 4) +#define GLOBAL_ATU_CONTROL_ATE_AGE_5MIN (0x13 << 4) +#define GLOBAL_ATU_OP 0x0b +#define GLOBAL_ATU_OP_BUSY BIT(15) +#define GLOBAL_ATU_OP_NOP (0 << 12) +#define GLOBAL_ATU_OP_FLUSH_ALL ((1 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_UNLOCKED ((2 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_LOAD_DB ((3 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_GET_NEXT_DB ((4 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_DB ((5 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_UNLOCKED_DB ((6 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_DATA 0x0c +#define GLOBAL_ATU_DATA_PORT_VECTOR_MASK 0x3f0 +#define GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT 4 +#define GLOBAL_ATU_DATA_STATE_MASK 0x0f +#define GLOBAL_ATU_DATA_STATE_UNUSED 0x00 +#define GLOBAL_ATU_DATA_STATE_UC_STATIC 0x0e +#define GLOBAL_ATU_DATA_STATE_UC_LOCKED 0x0f +#define GLOBAL_ATU_DATA_STATE_MC_STATIC 0x07 +#define GLOBAL_ATU_DATA_STATE_MC_LOCKED 0x0e +#define GLOBAL_ATU_MAC_01 0x0d +#define GLOBAL_ATU_MAC_23 0x0e +#define GLOBAL_ATU_MAC_45 0x0f + +#endif diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 05aa7597dab9..955d06b9cdba 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -78,7 +78,6 @@ source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" -source "drivers/net/ethernet/icplus/Kconfig" config JME tristate "JMicron(R) PCI-Express Gigabit Ethernet support" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index ddfc808110a1..4a2ee98738f0 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_NET_VENDOR_IBM) += ibm/ obj-$(CONFIG_NET_VENDOR_INTEL) += intel/ obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/ obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/ -obj-$(CONFIG_IP1000) += icplus/ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_KORINA) += korina.o obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index f1d62d5dbaff..c9b036789184 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13207,7 +13207,7 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, /* VF with OLD Hypervisor or old PF do not support filtering */ if (IS_PF(bp)) { - if (CHIP_IS_E1x(bp)) + if (chip_is_e1x) bp->accept_any_vlan = true; else dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index f683d97d7614..b89504405b72 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -560,7 +560,7 @@ static int liquidio_resume(struct pci_dev *pdev) #endif /* For PCI-E Advanced Error Recovery (AER) Interface */ -static struct pci_error_handlers liquidio_err_handler = { +static const struct pci_error_handlers liquidio_err_handler = { .error_detected = liquidio_pcie_error_detected, .mmio_enabled = liquidio_pcie_mmio_enabled, .slot_reset = liquidio_pcie_slot_reset, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index a9377727c11c..7f709cbdcd87 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1583,8 +1583,14 @@ err_disable_device: static void nicvf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct nicvf *nic = netdev_priv(netdev); - struct net_device *pnetdev = nic->pnicvf->netdev; + struct nicvf *nic; + struct net_device *pnetdev; + + if (!netdev) + return; + + nic = netdev_priv(netdev); + pnetdev = nic->pnicvf->netdev; /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig index f6e858d0b9d4..ebdc83247bb6 100644 --- a/drivers/net/ethernet/dlink/Kconfig +++ b/drivers/net/ethernet/dlink/Kconfig @@ -17,15 +17,16 @@ config NET_VENDOR_DLINK if NET_VENDOR_DLINK config DL2K - tristate "DL2000/TC902x-based Gigabit Ethernet support" + tristate "DL2000/TC902x/IP1000A-based Gigabit Ethernet support" depends on PCI select CRC32 ---help--- - This driver supports DL2000/TC902x-based Gigabit ethernet cards, + This driver supports DL2000/TC902x/IP1000A-based Gigabit ethernet cards, which includes D-Link DGE-550T Gigabit Ethernet Adapter. D-Link DL2000-based Gigabit Ethernet Adapter. Sundance/Tamarack TC902x Gigabit Ethernet Adapter. + ICPlus IP1000A-based cards To compile this driver as a module, choose M here: the module will be called dl2k. diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index cf0a5fcdaaaf..ccca4799c27b 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -253,6 +253,19 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_out_unmap_rx; + if (np->chip_id == CHIP_IP1000A && + (np->pdev->revision == 0x40 || np->pdev->revision == 0x41)) { + /* PHY magic taken from ipg driver, undocumented registers */ + mii_write(dev, np->phy_addr, 31, 0x0001); + mii_write(dev, np->phy_addr, 27, 0x01e0); + mii_write(dev, np->phy_addr, 31, 0x0002); + mii_write(dev, np->phy_addr, 27, 0xeb8e); + mii_write(dev, np->phy_addr, 31, 0x0000); + mii_write(dev, np->phy_addr, 30, 0x005e); + /* advertise 1000BASE-T half & full duplex, prefer MASTER */ + mii_write(dev, np->phy_addr, MII_CTRL1000, 0x0700); + } + /* Fiber device? */ np->phy_media = (dr16(ASICCtrl) & PhyMedia) ? 1 : 0; np->link_status = 0; @@ -361,6 +374,11 @@ parse_eeprom (struct net_device *dev) for (i = 0; i < 6; i++) dev->dev_addr[i] = psrom->mac_addr[i]; + if (np->chip_id == CHIP_IP1000A) { + np->led_mode = psrom->led_mode; + return 0; + } + if (np->pdev->vendor != PCI_VENDOR_ID_DLINK) { return 0; } @@ -406,6 +424,28 @@ parse_eeprom (struct net_device *dev) return 0; } +static void rio_set_led_mode(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->ioaddr; + u32 mode; + + if (np->chip_id != CHIP_IP1000A) + return; + + mode = dr32(ASICCtrl); + mode &= ~(IPG_AC_LED_MODE_BIT_1 | IPG_AC_LED_MODE | IPG_AC_LED_SPEED); + + if (np->led_mode & 0x01) + mode |= IPG_AC_LED_MODE; + if (np->led_mode & 0x02) + mode |= IPG_AC_LED_MODE_BIT_1; + if (np->led_mode & 0x08) + mode |= IPG_AC_LED_SPEED; + + dw32(ASICCtrl, mode); +} + static int rio_open (struct net_device *dev) { @@ -424,6 +464,8 @@ rio_open (struct net_device *dev) GlobalReset | DMAReset | FIFOReset | NetworkReset | HostReset); mdelay(10); + rio_set_led_mode(dev); + /* DebugCtrl bit 4, 5, 9 must set */ dw32(DebugCtrl, dr32(DebugCtrl) | 0x0230); @@ -433,9 +475,13 @@ rio_open (struct net_device *dev) alloc_list (dev); - /* Get station address */ - for (i = 0; i < 6; i++) - dw8(StationAddr0 + i, dev->dev_addr[i]); + /* Set station address */ + /* 16 or 32-bit access is required by TC9020 datasheet but 8-bit works + * too. However, it doesn't work on IP1000A so we use 16-bit access. + */ + for (i = 0; i < 3; i++) + dw16(StationAddr0 + 2 * i, + cpu_to_le16(((u16 *)dev->dev_addr)[i])); set_multicast (dev); if (np->coalesce) { @@ -780,6 +826,7 @@ tx_error (struct net_device *dev, int tx_status) break; mdelay (1); } + rio_set_led_mode(dev); rio_free_tx (dev, 1); /* Reset TFDListPtr */ dw32(TFDListPtr0, np->tx_ring_dma + @@ -799,6 +846,7 @@ tx_error (struct net_device *dev, int tx_status) break; mdelay (1); } + rio_set_led_mode(dev); /* Let TxStartThresh stay default value */ } /* Maximum Collisions */ @@ -965,6 +1013,7 @@ rio_error (struct net_device *dev, int int_status) dev->name, int_status); dw16(ASICCtrl + 2, GlobalReset | HostReset); mdelay (500); + rio_set_led_mode(dev); } } diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h index 23c07b007069..8f4f61262d5c 100644 --- a/drivers/net/ethernet/dlink/dl2k.h +++ b/drivers/net/ethernet/dlink/dl2k.h @@ -211,6 +211,10 @@ enum ASICCtrl_HiWord_bits { ResetBusy = 0x0400, }; +#define IPG_AC_LED_MODE BIT(14) +#define IPG_AC_LED_SPEED BIT(27) +#define IPG_AC_LED_MODE_BIT_1 BIT(29) + /* Transmit Frame Control bits */ enum TFC_bits { DwordAlign = 0x00000000, @@ -332,7 +336,10 @@ typedef struct t_SROM { u16 asic_ctrl; /* 0x02 */ u16 sub_vendor_id; /* 0x04 */ u16 sub_system_id; /* 0x06 */ - u16 reserved1[12]; /* 0x08-0x1f */ + u16 pci_base_1; /* 0x08 (IP1000A only) */ + u16 pci_base_2; /* 0x0a (IP1000A only) */ + u16 led_mode; /* 0x0c (IP1000A only) */ + u16 reserved1[9]; /* 0x0e-0x1f */ u8 mac_addr[6]; /* 0x20-0x25 */ u8 reserved2[10]; /* 0x26-0x2f */ u8 sib[204]; /* 0x30-0xfb */ @@ -397,6 +404,7 @@ struct netdev_private { u16 advertising; /* NWay media advertisement */ u16 negotiate; /* Negotiated media */ int phy_addr; /* PHY addresses. */ + u16 led_mode; /* LED mode read from EEPROM (IP1000A only) */ }; /* The station address location in the EEPROM. */ @@ -407,10 +415,15 @@ struct netdev_private { class_mask of the class are honored during the comparison. driver_data Data private to the driver. */ +#define CHIP_IP1000A 1 static const struct pci_device_id rio_pci_tbl[] = { {0x1186, 0x4000, PCI_ANY_ID, PCI_ANY_ID, }, {0x13f0, 0x1021, PCI_ANY_ID, PCI_ANY_ID, }, + { PCI_VDEVICE(SUNDANCE, 0x1023), CHIP_IP1000A }, + { PCI_VDEVICE(SUNDANCE, 0x2021), CHIP_IP1000A }, + { PCI_VDEVICE(DLINK, 0x9021), CHIP_IP1000A }, + { PCI_VDEVICE(DLINK, 0x4020), CHIP_IP1000A }, { } }; MODULE_DEVICE_TABLE (pci, rio_pci_tbl); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index f4cb8e425853..734f655c99c1 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -1062,9 +1062,7 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, static int be_set_rss_hash_opts(struct be_adapter *adapter, struct ethtool_rxnfc *cmd) { - struct be_rx_obj *rxo; - int status = 0, i, j; - u8 rsstable[128]; + int status; u32 rss_flags = adapter->rss_info.rss_flags; if (cmd->data != L3_RSS_FLAGS && @@ -1113,20 +1111,11 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter, } if (rss_flags == adapter->rss_info.rss_flags) - return status; - - if (be_multi_rxq(adapter)) { - for (j = 0; j < 128; j += adapter->num_rss_qs) { - for_all_rss_queues(adapter, rxo, i) { - if ((j + i) >= 128) - break; - rsstable[j + i] = rxo->rss_id; - } - } - } + return 0; status = be_cmd_rss_config(adapter, adapter->rss_info.rsstable, - rss_flags, 128, adapter->rss_info.rss_hkey); + rss_flags, RSS_INDIR_TABLE_LEN, + adapter->rss_info.rss_hkey); if (!status) adapter->rss_info.rss_flags = rss_flags; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index eb48a977f8da..b6ad02909d6b 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3518,7 +3518,7 @@ static int be_rx_qs_create(struct be_adapter *adapter) netdev_rss_key_fill(rss_key, RSS_HASH_KEY_LEN); rc = be_cmd_rss_config(adapter, rss->rsstable, rss->rss_flags, - 128, rss_key); + RSS_INDIR_TABLE_LEN, rss_key); if (rc) { rss->rss_flags = RSS_ENABLE_NONE; return rc; diff --git a/drivers/net/ethernet/icplus/Kconfig b/drivers/net/ethernet/icplus/Kconfig deleted file mode 100644 index 14a66e9d2e26..000000000000 --- a/drivers/net/ethernet/icplus/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# -# IC Plus device configuration -# - -config IP1000 - tristate "IP1000 Gigabit Ethernet support" - depends on PCI - select MII - ---help--- - This driver supports IP1000 gigabit Ethernet cards. - - To compile this driver as a module, choose M here: the module - will be called ipg. This is recommended. diff --git a/drivers/net/ethernet/icplus/Makefile b/drivers/net/ethernet/icplus/Makefile deleted file mode 100644 index 5bc87c1f36aa..000000000000 --- a/drivers/net/ethernet/icplus/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# -# Makefile for the IC Plus device drivers -# - -obj-$(CONFIG_IP1000) += ipg.o diff --git a/drivers/net/ethernet/icplus/ipg.c b/drivers/net/ethernet/icplus/ipg.c deleted file mode 100644 index c3b6af83f070..000000000000 --- a/drivers/net/ethernet/icplus/ipg.c +++ /dev/null @@ -1,2300 +0,0 @@ -/* - * ipg.c: Device Driver for the IP1000 Gigabit Ethernet Adapter - * - * Copyright (C) 2003, 2007 IC Plus Corp - * - * Original Author: - * - * Craig Rich - * Sundance Technology, Inc. - * www.sundanceti.com - * craig_rich@sundanceti.com - * - * Current Maintainer: - * - * Sorbica Shieh. - * http://www.icplus.com.tw - * sorbica@icplus.com.tw - * - * Jesse Huang - * http://www.icplus.com.tw - * jesse@icplus.com.tw - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/crc32.h> -#include <linux/ethtool.h> -#include <linux/interrupt.h> -#include <linux/gfp.h> -#include <linux/mii.h> -#include <linux/mutex.h> - -#include <asm/div64.h> - -#define IPG_RX_RING_BYTES (sizeof(struct ipg_rx) * IPG_RFDLIST_LENGTH) -#define IPG_TX_RING_BYTES (sizeof(struct ipg_tx) * IPG_TFDLIST_LENGTH) -#define IPG_RESET_MASK \ - (IPG_AC_GLOBAL_RESET | IPG_AC_RX_RESET | IPG_AC_TX_RESET | \ - IPG_AC_DMA | IPG_AC_FIFO | IPG_AC_NETWORK | IPG_AC_HOST | \ - IPG_AC_AUTO_INIT) - -#define ipg_w32(val32, reg) iowrite32((val32), ioaddr + (reg)) -#define ipg_w16(val16, reg) iowrite16((val16), ioaddr + (reg)) -#define ipg_w8(val8, reg) iowrite8((val8), ioaddr + (reg)) - -#define ipg_r32(reg) ioread32(ioaddr + (reg)) -#define ipg_r16(reg) ioread16(ioaddr + (reg)) -#define ipg_r8(reg) ioread8(ioaddr + (reg)) - -enum { - netdev_io_size = 128 -}; - -#include "ipg.h" -#define DRV_NAME "ipg" - -MODULE_AUTHOR("IC Plus Corp. 2003"); -MODULE_DESCRIPTION("IC Plus IP1000 Gigabit Ethernet Adapter Linux Driver"); -MODULE_LICENSE("GPL"); - -/* - * Defaults - */ -#define IPG_MAX_RXFRAME_SIZE 0x0600 -#define IPG_RXFRAG_SIZE 0x0600 -#define IPG_RXSUPPORT_SIZE 0x0600 -#define IPG_IS_JUMBO false - -/* - * Variable record -- index by leading revision/length - * Revision/Length(=N*4), Address1, Data1, Address2, Data2,...,AddressN,DataN - */ -static const unsigned short DefaultPhyParam[] = { - /* 11/12/03 IP1000A v1-3 rev=0x40 */ - /*-------------------------------------------------------------------------- - (0x4000|(15*4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 22, 0x85bd, 24, 0xfff2, - 27, 0x0c10, 28, 0x0c10, 29, 0x2c10, 31, 0x0003, 23, 0x92f6, - 31, 0x0000, 23, 0x003d, 30, 0x00de, 20, 0x20e7, 9, 0x0700, - --------------------------------------------------------------------------*/ - /* 12/17/03 IP1000A v1-4 rev=0x40 */ - (0x4000 | (07 * 4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 27, 0xeb8e, 31, - 0x0000, - 30, 0x005e, 9, 0x0700, - /* 01/09/04 IP1000A v1-5 rev=0x41 */ - (0x4100 | (07 * 4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 27, 0xeb8e, 31, - 0x0000, - 30, 0x005e, 9, 0x0700, - 0x0000 -}; - -static const char * const ipg_brand_name[] = { - "IC PLUS IP1000 1000/100/10 based NIC", - "Sundance Technology ST2021 based NIC", - "Tamarack Microelectronics TC9020/9021 based NIC", - "D-Link NIC IP1000A" -}; - -static const struct pci_device_id ipg_pci_tbl[] = { - { PCI_VDEVICE(SUNDANCE, 0x1023), 0 }, - { PCI_VDEVICE(SUNDANCE, 0x2021), 1 }, - { PCI_VDEVICE(DLINK, 0x9021), 2 }, - { PCI_VDEVICE(DLINK, 0x4020), 3 }, - { 0, } -}; - -MODULE_DEVICE_TABLE(pci, ipg_pci_tbl); - -static inline void __iomem *ipg_ioaddr(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - return sp->ioaddr; -} - -#ifdef IPG_DEBUG -static void ipg_dump_rfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - u32 offset; - - IPG_DEBUG_MSG("_dump_rfdlist\n"); - - netdev_info(dev, "rx_current = %02x\n", sp->rx_current); - netdev_info(dev, "rx_dirty = %02x\n", sp->rx_dirty); - netdev_info(dev, "RFDList start address = %016lx\n", - (unsigned long)sp->rxd_map); - netdev_info(dev, "RFDListPtr register = %08x%08x\n", - ipg_r32(IPG_RFDLISTPTR1), ipg_r32(IPG_RFDLISTPTR0)); - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - offset = (u32) &sp->rxd[i].next_desc - (u32) sp->rxd; - netdev_info(dev, "%02x %04x RFDNextPtr = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].next_desc); - offset = (u32) &sp->rxd[i].rfs - (u32) sp->rxd; - netdev_info(dev, "%02x %04x RFS = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].rfs); - offset = (u32) &sp->rxd[i].frag_info - (u32) sp->rxd; - netdev_info(dev, "%02x %04x frag_info = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].frag_info); - } -} - -static void ipg_dump_tfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - u32 offset; - - IPG_DEBUG_MSG("_dump_tfdlist\n"); - - netdev_info(dev, "tx_current = %02x\n", sp->tx_current); - netdev_info(dev, "tx_dirty = %02x\n", sp->tx_dirty); - netdev_info(dev, "TFDList start address = %016lx\n", - (unsigned long) sp->txd_map); - netdev_info(dev, "TFDListPtr register = %08x%08x\n", - ipg_r32(IPG_TFDLISTPTR1), ipg_r32(IPG_TFDLISTPTR0)); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - offset = (u32) &sp->txd[i].next_desc - (u32) sp->txd; - netdev_info(dev, "%02x %04x TFDNextPtr = %016lx\n", - i, offset, (unsigned long)sp->txd[i].next_desc); - - offset = (u32) &sp->txd[i].tfc - (u32) sp->txd; - netdev_info(dev, "%02x %04x TFC = %016lx\n", - i, offset, (unsigned long) sp->txd[i].tfc); - offset = (u32) &sp->txd[i].frag_info - (u32) sp->txd; - netdev_info(dev, "%02x %04x frag_info = %016lx\n", - i, offset, (unsigned long) sp->txd[i].frag_info); - } -} -#endif - -static void ipg_write_phy_ctl(void __iomem *ioaddr, u8 data) -{ - ipg_w8(IPG_PC_RSVD_MASK & data, PHY_CTRL); - ndelay(IPG_PC_PHYCTRLWAIT_NS); -} - -static void ipg_drive_phy_ctl_low_high(void __iomem *ioaddr, u8 data) -{ - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | data); - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | data); -} - -static void send_three_state(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - phyctrlpolarity |= (IPG_PC_MGMTDATA & 0) | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, phyctrlpolarity); -} - -static void send_end(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - ipg_w8((IPG_PC_MGMTCLK_LO | (IPG_PC_MGMTDATA & 0) | IPG_PC_MGMTDIR | - phyctrlpolarity) & IPG_PC_RSVD_MASK, PHY_CTRL); -} - -static u16 read_phy_bit(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - u16 bit_data; - - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | phyctrlpolarity); - - bit_data = ((ipg_r8(PHY_CTRL) & IPG_PC_MGMTDATA) >> 1) & 1; - - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | phyctrlpolarity); - - return bit_data; -} - -/* - * Read a register from the Physical Layer device located - * on the IPG NIC, using the IPG PHYCTRL register. - */ -static int mdio_read(struct net_device *dev, int phy_id, int phy_reg) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - /* - * The GMII mangement frame structure for a read is as follows: - * - * |Preamble|st|op|phyad|regad|ta| data |idle| - * |< 32 1s>|01|10|AAAAA|RRRRR|z0|DDDDDDDDDDDDDDDD|z | - * - * <32 1s> = 32 consecutive logic 1 values - * A = bit of Physical Layer device address (MSB first) - * R = bit of register address (MSB first) - * z = High impedance state - * D = bit of read data (MSB first) - * - * Transmission order is 'Preamble' field first, bits transmitted - * left to right (first to last). - */ - struct { - u32 field; - unsigned int len; - } p[] = { - { GMII_PREAMBLE, 32 }, /* Preamble */ - { GMII_ST, 2 }, /* ST */ - { GMII_READ, 2 }, /* OP */ - { phy_id, 5 }, /* PHYAD */ - { phy_reg, 5 }, /* REGAD */ - { 0x0000, 2 }, /* TA */ - { 0x0000, 16 }, /* DATA */ - { 0x0000, 1 } /* IDLE */ - }; - unsigned int i, j; - u8 polarity, data; - - polarity = ipg_r8(PHY_CTRL); - polarity &= (IPG_PC_DUPLEX_POLARITY | IPG_PC_LINK_POLARITY); - - /* Create the Preamble, ST, OP, PHYAD, and REGAD field. */ - for (j = 0; j < 5; j++) { - for (i = 0; i < p[j].len; i++) { - /* For each variable length field, the MSB must be - * transmitted first. Rotate through the field bits, - * starting with the MSB, and move each bit into the - * the 1st (2^1) bit position (this is the bit position - * corresponding to the MgmtData bit of the PhyCtrl - * register for the IPG). - * - * Example: ST = 01; - * - * First write a '0' to bit 1 of the PhyCtrl - * register, then write a '1' to bit 1 of the - * PhyCtrl register. - * - * To do this, right shift the MSB of ST by the value: - * [field length - 1 - #ST bits already written] - * then left shift this result by 1. - */ - data = (p[j].field >> (p[j].len - 1 - i)) << 1; - data &= IPG_PC_MGMTDATA; - data |= polarity | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, data); - } - } - - send_three_state(ioaddr, polarity); - - read_phy_bit(ioaddr, polarity); - - /* - * For a read cycle, the bits for the next two fields (TA and - * DATA) are driven by the PHY (the IPG reads these bits). - */ - for (i = 0; i < p[6].len; i++) { - p[6].field |= - (read_phy_bit(ioaddr, polarity) << (p[6].len - 1 - i)); - } - - send_three_state(ioaddr, polarity); - send_three_state(ioaddr, polarity); - send_three_state(ioaddr, polarity); - send_end(ioaddr, polarity); - - /* Return the value of the DATA field. */ - return p[6].field; -} - -/* - * Write to a register from the Physical Layer device located - * on the IPG NIC, using the IPG PHYCTRL register. - */ -static void mdio_write(struct net_device *dev, int phy_id, int phy_reg, int val) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - /* - * The GMII mangement frame structure for a read is as follows: - * - * |Preamble|st|op|phyad|regad|ta| data |idle| - * |< 32 1s>|01|10|AAAAA|RRRRR|z0|DDDDDDDDDDDDDDDD|z | - * - * <32 1s> = 32 consecutive logic 1 values - * A = bit of Physical Layer device address (MSB first) - * R = bit of register address (MSB first) - * z = High impedance state - * D = bit of write data (MSB first) - * - * Transmission order is 'Preamble' field first, bits transmitted - * left to right (first to last). - */ - struct { - u32 field; - unsigned int len; - } p[] = { - { GMII_PREAMBLE, 32 }, /* Preamble */ - { GMII_ST, 2 }, /* ST */ - { GMII_WRITE, 2 }, /* OP */ - { phy_id, 5 }, /* PHYAD */ - { phy_reg, 5 }, /* REGAD */ - { 0x0002, 2 }, /* TA */ - { val & 0xffff, 16 }, /* DATA */ - { 0x0000, 1 } /* IDLE */ - }; - unsigned int i, j; - u8 polarity, data; - - polarity = ipg_r8(PHY_CTRL); - polarity &= (IPG_PC_DUPLEX_POLARITY | IPG_PC_LINK_POLARITY); - - /* Create the Preamble, ST, OP, PHYAD, and REGAD field. */ - for (j = 0; j < 7; j++) { - for (i = 0; i < p[j].len; i++) { - /* For each variable length field, the MSB must be - * transmitted first. Rotate through the field bits, - * starting with the MSB, and move each bit into the - * the 1st (2^1) bit position (this is the bit position - * corresponding to the MgmtData bit of the PhyCtrl - * register for the IPG). - * - * Example: ST = 01; - * - * First write a '0' to bit 1 of the PhyCtrl - * register, then write a '1' to bit 1 of the - * PhyCtrl register. - * - * To do this, right shift the MSB of ST by the value: - * [field length - 1 - #ST bits already written] - * then left shift this result by 1. - */ - data = (p[j].field >> (p[j].len - 1 - i)) << 1; - data &= IPG_PC_MGMTDATA; - data |= polarity | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, data); - } - } - - /* The last cycle is a tri-state, so read from the PHY. */ - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity); - ipg_r8(PHY_CTRL); - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity); -} - -static void ipg_set_led_mode(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - u32 mode; - - mode = ipg_r32(ASIC_CTRL); - mode &= ~(IPG_AC_LED_MODE_BIT_1 | IPG_AC_LED_MODE | IPG_AC_LED_SPEED); - - if ((sp->led_mode & 0x03) > 1) - mode |= IPG_AC_LED_MODE_BIT_1; /* Write Asic Control Bit 29 */ - - if ((sp->led_mode & 0x01) == 1) - mode |= IPG_AC_LED_MODE; /* Write Asic Control Bit 14 */ - - if ((sp->led_mode & 0x08) == 8) - mode |= IPG_AC_LED_SPEED; /* Write Asic Control Bit 27 */ - - ipg_w32(mode, ASIC_CTRL); -} - -static void ipg_set_phy_set(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - int physet; - - physet = ipg_r8(PHY_SET); - physet &= ~(IPG_PS_MEM_LENB9B | IPG_PS_MEM_LEN9 | IPG_PS_NON_COMPDET); - physet |= ((sp->led_mode & 0x70) >> 4); - ipg_w8(physet, PHY_SET); -} - -static int ipg_reset(struct net_device *dev, u32 resetflags) -{ - /* Assert functional resets via the IPG AsicCtrl - * register as specified by the 'resetflags' input - * parameter. - */ - void __iomem *ioaddr = ipg_ioaddr(dev); - unsigned int timeout_count = 0; - - IPG_DEBUG_MSG("_reset\n"); - - ipg_w32(ipg_r32(ASIC_CTRL) | resetflags, ASIC_CTRL); - - /* Delay added to account for problem with 10Mbps reset. */ - mdelay(IPG_AC_RESETWAIT); - - while (IPG_AC_RESET_BUSY & ipg_r32(ASIC_CTRL)) { - mdelay(IPG_AC_RESETWAIT); - if (++timeout_count > IPG_AC_RESET_TIMEOUT) - return -ETIME; - } - /* Set LED Mode in Asic Control */ - ipg_set_led_mode(dev); - - /* Set PHYSet Register Value */ - ipg_set_phy_set(dev); - return 0; -} - -/* Find the GMII PHY address. */ -static int ipg_find_phyaddr(struct net_device *dev) -{ - unsigned int phyaddr, i; - - for (i = 0; i < 32; i++) { - u32 status; - - /* Search for the correct PHY address among 32 possible. */ - phyaddr = (IPG_NIC_PHY_ADDRESS + i) % 32; - - /* 10/22/03 Grace change verify from GMII_PHY_STATUS to - GMII_PHY_ID1 - */ - - status = mdio_read(dev, phyaddr, MII_BMSR); - - if ((status != 0xFFFF) && (status != 0)) - return phyaddr; - } - - return 0x1f; -} - -/* - * Configure IPG based on result of IEEE 802.3 PHY - * auto-negotiation. - */ -static int ipg_config_autoneg(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int txflowcontrol; - unsigned int rxflowcontrol; - unsigned int fullduplex; - u32 mac_ctrl_val; - u32 asicctrl; - u8 phyctrl; - const char *speed; - const char *duplex; - const char *tx_desc; - const char *rx_desc; - - IPG_DEBUG_MSG("_config_autoneg\n"); - - asicctrl = ipg_r32(ASIC_CTRL); - phyctrl = ipg_r8(PHY_CTRL); - mac_ctrl_val = ipg_r32(MAC_CTRL); - - /* Set flags for use in resolving auto-negotiation, assuming - * non-1000Mbps, half duplex, no flow control. - */ - fullduplex = 0; - txflowcontrol = 0; - rxflowcontrol = 0; - - /* To accommodate a problem in 10Mbps operation, - * set a global flag if PHY running in 10Mbps mode. - */ - sp->tenmbpsmode = 0; - - /* Determine actual speed of operation. */ - switch (phyctrl & IPG_PC_LINK_SPEED) { - case IPG_PC_LINK_SPEED_10MBPS: - speed = "10Mbps"; - sp->tenmbpsmode = 1; - break; - case IPG_PC_LINK_SPEED_100MBPS: - speed = "100Mbps"; - break; - case IPG_PC_LINK_SPEED_1000MBPS: - speed = "1000Mbps"; - break; - default: - speed = "undefined!"; - return 0; - } - - netdev_info(dev, "Link speed = %s\n", speed); - if (sp->tenmbpsmode == 1) - netdev_info(dev, "10Mbps operational mode enabled\n"); - - if (phyctrl & IPG_PC_DUPLEX_STATUS) { - fullduplex = 1; - txflowcontrol = 1; - rxflowcontrol = 1; - } - - /* Configure full duplex, and flow control. */ - if (fullduplex == 1) { - - /* Configure IPG for full duplex operation. */ - - duplex = "full"; - - mac_ctrl_val |= IPG_MC_DUPLEX_SELECT_FD; - - if (txflowcontrol == 1) { - tx_desc = ""; - mac_ctrl_val |= IPG_MC_TX_FLOW_CONTROL_ENABLE; - } else { - tx_desc = "no "; - mac_ctrl_val &= ~IPG_MC_TX_FLOW_CONTROL_ENABLE; - } - - if (rxflowcontrol == 1) { - rx_desc = ""; - mac_ctrl_val |= IPG_MC_RX_FLOW_CONTROL_ENABLE; - } else { - rx_desc = "no "; - mac_ctrl_val &= ~IPG_MC_RX_FLOW_CONTROL_ENABLE; - } - } else { - duplex = "half"; - tx_desc = "no "; - rx_desc = "no "; - mac_ctrl_val &= (~IPG_MC_DUPLEX_SELECT_FD & - ~IPG_MC_TX_FLOW_CONTROL_ENABLE & - ~IPG_MC_RX_FLOW_CONTROL_ENABLE); - } - - netdev_info(dev, "setting %s duplex, %sTX, %sRX flow control\n", - duplex, tx_desc, rx_desc); - ipg_w32(mac_ctrl_val, MAC_CTRL); - - return 0; -} - -/* Determine and configure multicast operation and set - * receive mode for IPG. - */ -static void ipg_nic_set_multicast_list(struct net_device *dev) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - struct netdev_hw_addr *ha; - unsigned int hashindex; - u32 hashtable[2]; - u8 receivemode; - - IPG_DEBUG_MSG("_nic_set_multicast_list\n"); - - receivemode = IPG_RM_RECEIVEUNICAST | IPG_RM_RECEIVEBROADCAST; - - if (dev->flags & IFF_PROMISC) { - /* NIC to be configured in promiscuous mode. */ - receivemode = IPG_RM_RECEIVEALLFRAMES; - } else if ((dev->flags & IFF_ALLMULTI) || - ((dev->flags & IFF_MULTICAST) && - (netdev_mc_count(dev) > IPG_MULTICAST_HASHTABLE_SIZE))) { - /* NIC to be configured to receive all multicast - * frames. */ - receivemode |= IPG_RM_RECEIVEMULTICAST; - } else if ((dev->flags & IFF_MULTICAST) && !netdev_mc_empty(dev)) { - /* NIC to be configured to receive selected - * multicast addresses. */ - receivemode |= IPG_RM_RECEIVEMULTICASTHASH; - } - - /* Calculate the bits to set for the 64 bit, IPG HASHTABLE. - * The IPG applies a cyclic-redundancy-check (the same CRC - * used to calculate the frame data FCS) to the destination - * address all incoming multicast frames whose destination - * address has the multicast bit set. The least significant - * 6 bits of the CRC result are used as an addressing index - * into the hash table. If the value of the bit addressed by - * this index is a 1, the frame is passed to the host system. - */ - - /* Clear hashtable. */ - hashtable[0] = 0x00000000; - hashtable[1] = 0x00000000; - - /* Cycle through all multicast addresses to filter. */ - netdev_for_each_mc_addr(ha, dev) { - /* Calculate CRC result for each multicast address. */ - hashindex = crc32_le(0xffffffff, ha->addr, - ETH_ALEN); - - /* Use only the least significant 6 bits. */ - hashindex = hashindex & 0x3F; - - /* Within "hashtable", set bit number "hashindex" - * to a logic 1. - */ - set_bit(hashindex, (void *)hashtable); - } - - /* Write the value of the hashtable, to the 4, 16 bit - * HASHTABLE IPG registers. - */ - ipg_w32(hashtable[0], HASHTABLE_0); - ipg_w32(hashtable[1], HASHTABLE_1); - - ipg_w8(IPG_RM_RSVD_MASK & receivemode, RECEIVE_MODE); - - IPG_DEBUG_MSG("ReceiveMode = %x\n", ipg_r8(RECEIVE_MODE)); -} - -static int ipg_io_config(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = ipg_ioaddr(dev); - u32 origmacctrl; - u32 restoremacctrl; - - IPG_DEBUG_MSG("_io_config\n"); - - origmacctrl = ipg_r32(MAC_CTRL); - - restoremacctrl = origmacctrl | IPG_MC_STATISTICS_ENABLE; - - /* Based on compilation option, determine if FCS is to be - * stripped on receive frames by IPG. - */ - if (!IPG_STRIP_FCS_ON_RX) - restoremacctrl |= IPG_MC_RCV_FCS; - - /* Determine if transmitter and/or receiver are - * enabled so we may restore MACCTRL correctly. - */ - if (origmacctrl & IPG_MC_TX_ENABLED) - restoremacctrl |= IPG_MC_TX_ENABLE; - - if (origmacctrl & IPG_MC_RX_ENABLED) - restoremacctrl |= IPG_MC_RX_ENABLE; - - /* Transmitter and receiver must be disabled before setting - * IFSSelect. - */ - ipg_w32((origmacctrl & (IPG_MC_RX_DISABLE | IPG_MC_TX_DISABLE)) & - IPG_MC_RSVD_MASK, MAC_CTRL); - - /* Now that transmitter and receiver are disabled, write - * to IFSSelect. - */ - ipg_w32((origmacctrl & IPG_MC_IFS_96BIT) & IPG_MC_RSVD_MASK, MAC_CTRL); - - /* Set RECEIVEMODE register. */ - ipg_nic_set_multicast_list(dev); - - ipg_w16(sp->max_rxframe_size, MAX_FRAME_SIZE); - - ipg_w8(IPG_RXDMAPOLLPERIOD_VALUE, RX_DMA_POLL_PERIOD); - ipg_w8(IPG_RXDMAURGENTTHRESH_VALUE, RX_DMA_URGENT_THRESH); - ipg_w8(IPG_RXDMABURSTTHRESH_VALUE, RX_DMA_BURST_THRESH); - ipg_w8(IPG_TXDMAPOLLPERIOD_VALUE, TX_DMA_POLL_PERIOD); - ipg_w8(IPG_TXDMAURGENTTHRESH_VALUE, TX_DMA_URGENT_THRESH); - ipg_w8(IPG_TXDMABURSTTHRESH_VALUE, TX_DMA_BURST_THRESH); - ipg_w16((IPG_IE_HOST_ERROR | IPG_IE_TX_DMA_COMPLETE | - IPG_IE_TX_COMPLETE | IPG_IE_INT_REQUESTED | - IPG_IE_UPDATE_STATS | IPG_IE_LINK_EVENT | - IPG_IE_RX_DMA_COMPLETE | IPG_IE_RX_DMA_PRIORITY), INT_ENABLE); - ipg_w16(IPG_FLOWONTHRESH_VALUE, FLOW_ON_THRESH); - ipg_w16(IPG_FLOWOFFTHRESH_VALUE, FLOW_OFF_THRESH); - - /* IPG multi-frag frame bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0200, DEBUG_CTRL); - - /* IPG TX poll now bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0010, DEBUG_CTRL); - - /* IPG RX poll now bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0020, DEBUG_CTRL); - - /* Now restore MACCTRL to original setting. */ - ipg_w32(IPG_MC_RSVD_MASK & restoremacctrl, MAC_CTRL); - - /* Disable unused RMON statistics. */ - ipg_w32(IPG_RZ_ALL, RMON_STATISTICS_MASK); - - /* Disable unused MIB statistics. */ - ipg_w32(IPG_SM_MACCONTROLFRAMESXMTD | IPG_SM_MACCONTROLFRAMESRCVD | - IPG_SM_BCSTOCTETXMTOK_BCSTFRAMESXMTDOK | IPG_SM_TXJUMBOFRAMES | - IPG_SM_MCSTOCTETXMTOK_MCSTFRAMESXMTDOK | IPG_SM_RXJUMBOFRAMES | - IPG_SM_BCSTOCTETRCVDOK_BCSTFRAMESRCVDOK | - IPG_SM_UDPCHECKSUMERRORS | IPG_SM_TCPCHECKSUMERRORS | - IPG_SM_IPCHECKSUMERRORS, STATISTICS_MASK); - - return 0; -} - -/* - * Create a receive buffer within system memory and update - * NIC private structure appropriately. - */ -static int ipg_get_rxbuff(struct net_device *dev, int entry) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct ipg_rx *rxfd = sp->rxd + entry; - struct sk_buff *skb; - u64 rxfragsize; - - IPG_DEBUG_MSG("_get_rxbuff\n"); - - skb = netdev_alloc_skb_ip_align(dev, sp->rxsupport_size); - if (!skb) { - sp->rx_buff[entry] = NULL; - return -ENOMEM; - } - - /* Save the address of the sk_buff structure. */ - sp->rx_buff[entry] = skb; - - rxfd->frag_info = cpu_to_le64(pci_map_single(sp->pdev, skb->data, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE)); - - /* Set the RFD fragment length. */ - rxfragsize = sp->rxfrag_size; - rxfd->frag_info |= cpu_to_le64((rxfragsize << 48) & IPG_RFI_FRAGLEN); - - return 0; -} - -static int init_rfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_init_rfdlist\n"); - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - struct ipg_rx *rxfd = sp->rxd + i; - - if (sp->rx_buff[i]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[i]); - sp->rx_buff[i] = NULL; - } - - /* Clear out the RFS field. */ - rxfd->rfs = 0x0000000000000000; - - if (ipg_get_rxbuff(dev, i) < 0) { - /* - * A receive buffer was not ready, break the - * RFD list here. - */ - IPG_DEBUG_MSG("Cannot allocate Rx buffer\n"); - - /* Just in case we cannot allocate a single RFD. - * Should not occur. - */ - if (i == 0) { - netdev_err(dev, "No memory available for RFD list\n"); - return -ENOMEM; - } - } - - rxfd->next_desc = cpu_to_le64(sp->rxd_map + - sizeof(struct ipg_rx)*(i + 1)); - } - sp->rxd[i - 1].next_desc = cpu_to_le64(sp->rxd_map); - - sp->rx_current = 0; - sp->rx_dirty = 0; - - /* Write the location of the RFDList to the IPG. */ - ipg_w32((u32) sp->rxd_map, RFD_LIST_PTR_0); - ipg_w32(0x00000000, RFD_LIST_PTR_1); - - return 0; -} - -static void init_tfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_init_tfdlist\n"); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - struct ipg_tx *txfd = sp->txd + i; - - txfd->tfc = cpu_to_le64(IPG_TFC_TFDDONE); - - if (sp->tx_buff[i]) { - dev_kfree_skb_irq(sp->tx_buff[i]); - sp->tx_buff[i] = NULL; - } - - txfd->next_desc = cpu_to_le64(sp->txd_map + - sizeof(struct ipg_tx)*(i + 1)); - } - sp->txd[i - 1].next_desc = cpu_to_le64(sp->txd_map); - - sp->tx_current = 0; - sp->tx_dirty = 0; - - /* Write the location of the TFDList to the IPG. */ - IPG_DDEBUG_MSG("Starting TFDListPtr = %08x\n", - (u32) sp->txd_map); - ipg_w32((u32) sp->txd_map, TFD_LIST_PTR_0); - ipg_w32(0x00000000, TFD_LIST_PTR_1); - - sp->reset_current_tfd = 1; -} - -/* - * Free all transmit buffers which have already been transferred - * via DMA to the IPG. - */ -static void ipg_nic_txfree(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int released, pending, dirty; - - IPG_DEBUG_MSG("_nic_txfree\n"); - - pending = sp->tx_current - sp->tx_dirty; - dirty = sp->tx_dirty % IPG_TFDLIST_LENGTH; - - for (released = 0; released < pending; released++) { - struct sk_buff *skb = sp->tx_buff[dirty]; - struct ipg_tx *txfd = sp->txd + dirty; - - IPG_DEBUG_MSG("TFC = %016lx\n", (unsigned long) txfd->tfc); - - /* Look at each TFD's TFC field beginning - * at the last freed TFD up to the current TFD. - * If the TFDDone bit is set, free the associated - * buffer. - */ - if (!(txfd->tfc & cpu_to_le64(IPG_TFC_TFDDONE))) - break; - - /* Free the transmit buffer. */ - if (skb) { - pci_unmap_single(sp->pdev, - le64_to_cpu(txfd->frag_info) & ~IPG_TFI_FRAGLEN, - skb->len, PCI_DMA_TODEVICE); - - dev_kfree_skb_irq(skb); - - sp->tx_buff[dirty] = NULL; - } - dirty = (dirty + 1) % IPG_TFDLIST_LENGTH; - } - - sp->tx_dirty += released; - - if (netif_queue_stopped(dev) && - (sp->tx_current != (sp->tx_dirty + IPG_TFDLIST_LENGTH))) { - netif_wake_queue(dev); - } -} - -static void ipg_tx_timeout(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - - ipg_reset(dev, IPG_AC_TX_RESET | IPG_AC_DMA | IPG_AC_NETWORK | - IPG_AC_FIFO); - - spin_lock_irq(&sp->lock); - - /* Re-configure after DMA reset. */ - if (ipg_io_config(dev) < 0) - netdev_info(dev, "Error during re-configuration\n"); - - init_tfdlist(dev); - - spin_unlock_irq(&sp->lock); - - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & IPG_MC_RSVD_MASK, - MAC_CTRL); -} - -/* - * For TxComplete interrupts, free all transmit - * buffers which have already been transferred via DMA - * to the IPG. - */ -static void ipg_nic_txcleanup(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_nic_txcleanup\n"); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - /* Reading the TXSTATUS register clears the - * TX_COMPLETE interrupt. - */ - u32 txstatusdword = ipg_r32(TX_STATUS); - - IPG_DEBUG_MSG("TxStatus = %08x\n", txstatusdword); - - /* Check for Transmit errors. Error bits only valid if - * TX_COMPLETE bit in the TXSTATUS register is a 1. - */ - if (!(txstatusdword & IPG_TS_TX_COMPLETE)) - break; - - /* If in 10Mbps mode, indicate transmit is ready. */ - if (sp->tenmbpsmode) { - netif_wake_queue(dev); - } - - /* Transmit error, increment stat counters. */ - if (txstatusdword & IPG_TS_TX_ERROR) { - IPG_DEBUG_MSG("Transmit error\n"); - sp->stats.tx_errors++; - } - - /* Late collision, re-enable transmitter. */ - if (txstatusdword & IPG_TS_LATE_COLLISION) { - IPG_DEBUG_MSG("Late collision on transmit\n"); - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - - /* Maximum collisions, re-enable transmitter. */ - if (txstatusdword & IPG_TS_TX_MAX_COLL) { - IPG_DEBUG_MSG("Maximum collisions on transmit\n"); - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - - /* Transmit underrun, reset and re-enable - * transmitter. - */ - if (txstatusdword & IPG_TS_TX_UNDERRUN) { - IPG_DEBUG_MSG("Transmitter underrun\n"); - sp->stats.tx_fifo_errors++; - ipg_reset(dev, IPG_AC_TX_RESET | IPG_AC_DMA | - IPG_AC_NETWORK | IPG_AC_FIFO); - - /* Re-configure after DMA reset. */ - if (ipg_io_config(dev) < 0) { - netdev_info(dev, "Error during re-configuration\n"); - } - init_tfdlist(dev); - - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - } - - ipg_nic_txfree(dev); -} - -/* Provides statistical information about the IPG NIC. */ -static struct net_device_stats *ipg_nic_get_stats(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - u16 temp1; - u16 temp2; - - IPG_DEBUG_MSG("_nic_get_stats\n"); - - /* Check to see if the NIC has been initialized via nic_open, - * before trying to read statistic registers. - */ - if (!netif_running(dev)) - return &sp->stats; - - sp->stats.rx_packets += ipg_r32(IPG_FRAMESRCVDOK); - sp->stats.tx_packets += ipg_r32(IPG_FRAMESXMTDOK); - sp->stats.rx_bytes += ipg_r32(IPG_OCTETRCVOK); - sp->stats.tx_bytes += ipg_r32(IPG_OCTETXMTOK); - temp1 = ipg_r16(IPG_FRAMESLOSTRXERRORS); - sp->stats.rx_errors += temp1; - sp->stats.rx_missed_errors += temp1; - temp1 = ipg_r32(IPG_SINGLECOLFRAMES) + ipg_r32(IPG_MULTICOLFRAMES) + - ipg_r32(IPG_LATECOLLISIONS); - temp2 = ipg_r16(IPG_CARRIERSENSEERRORS); - sp->stats.collisions += temp1; - sp->stats.tx_dropped += ipg_r16(IPG_FRAMESABORTXSCOLLS); - sp->stats.tx_errors += ipg_r16(IPG_FRAMESWEXDEFERRAL) + - ipg_r32(IPG_FRAMESWDEFERREDXMT) + temp1 + temp2; - sp->stats.multicast += ipg_r32(IPG_MCSTOCTETRCVDOK); - - /* detailed tx_errors */ - sp->stats.tx_carrier_errors += temp2; - - /* detailed rx_errors */ - sp->stats.rx_length_errors += ipg_r16(IPG_INRANGELENGTHERRORS) + - ipg_r16(IPG_FRAMETOOLONGERRORS); - sp->stats.rx_crc_errors += ipg_r16(IPG_FRAMECHECKSEQERRORS); - - /* Unutilized IPG statistic registers. */ - ipg_r32(IPG_MCSTFRAMESRCVDOK); - - return &sp->stats; -} - -/* Restore used receive buffers. */ -static int ipg_nic_rxrestore(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - const unsigned int curr = sp->rx_current; - unsigned int dirty = sp->rx_dirty; - - IPG_DEBUG_MSG("_nic_rxrestore\n"); - - for (dirty = sp->rx_dirty; curr - dirty > 0; dirty++) { - unsigned int entry = dirty % IPG_RFDLIST_LENGTH; - - /* rx_copybreak may poke hole here and there. */ - if (sp->rx_buff[entry]) - continue; - - /* Generate a new receive buffer to replace the - * current buffer (which will be released by the - * Linux system). - */ - if (ipg_get_rxbuff(dev, entry) < 0) { - IPG_DEBUG_MSG("Cannot allocate new Rx buffer\n"); - - break; - } - - /* Reset the RFS field. */ - sp->rxd[entry].rfs = 0x0000000000000000; - } - sp->rx_dirty = dirty; - - return 0; -} - -/* use jumboindex and jumbosize to control jumbo frame status - * initial status is jumboindex=-1 and jumbosize=0 - * 1. jumboindex = -1 and jumbosize=0 : previous jumbo frame has been done. - * 2. jumboindex != -1 and jumbosize != 0 : jumbo frame is not over size and receiving - * 3. jumboindex = -1 and jumbosize != 0 : jumbo frame is over size, already dump - * previous receiving and need to continue dumping the current one - */ -enum { - NORMAL_PACKET, - ERROR_PACKET -}; - -enum { - FRAME_NO_START_NO_END = 0, - FRAME_WITH_START = 1, - FRAME_WITH_END = 10, - FRAME_WITH_START_WITH_END = 11 -}; - -static void ipg_nic_rx_free_skb(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; - - if (sp->rx_buff[entry]) { - struct ipg_rx *rxfd = sp->rxd + entry; - - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[entry]); - sp->rx_buff[entry] = NULL; - } -} - -static int ipg_nic_rx_check_frame_type(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct ipg_rx *rxfd = sp->rxd + (sp->rx_current % IPG_RFDLIST_LENGTH); - int type = FRAME_NO_START_NO_END; - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMESTART) - type += FRAME_WITH_START; - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMEEND) - type += FRAME_WITH_END; - return type; -} - -static int ipg_nic_rx_check_error(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; - struct ipg_rx *rxfd = sp->rxd + entry; - - if (IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & - (IPG_RFS_RXFIFOOVERRUN | IPG_RFS_RXRUNTFRAME | - IPG_RFS_RXALIGNMENTERROR | IPG_RFS_RXFCSERROR | - IPG_RFS_RXOVERSIZEDFRAME | IPG_RFS_RXLENGTHERROR))) { - IPG_DEBUG_MSG("Rx error, RFS = %016lx\n", - (unsigned long) rxfd->rfs); - - /* Increment general receive error statistic. */ - sp->stats.rx_errors++; - - /* Increment detailed receive error statistics. */ - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFIFOOVERRUN) { - IPG_DEBUG_MSG("RX FIFO overrun occurred\n"); - - sp->stats.rx_fifo_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXRUNTFRAME) { - IPG_DEBUG_MSG("RX runt occurred\n"); - sp->stats.rx_length_errors++; - } - - /* Do nothing for IPG_RFS_RXOVERSIZEDFRAME, - * error count handled by a IPG statistic register. - */ - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXALIGNMENTERROR) { - IPG_DEBUG_MSG("RX alignment error occurred\n"); - sp->stats.rx_frame_errors++; - } - - /* Do nothing for IPG_RFS_RXFCSERROR, error count - * handled by a IPG statistic register. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (sp->rx_buff[entry]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - dev_kfree_skb_irq(sp->rx_buff[entry]); - sp->rx_buff[entry] = NULL; - } - return ERROR_PACKET; - } - return NORMAL_PACKET; -} - -static void ipg_nic_rx_with_start_and_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - struct sk_buff *skb; - int framelen; - - if (jumbo->found_start) { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) != NORMAL_PACKET) - return; - - skb = sp->rx_buff[entry]; - if (!skb) - return; - - /* accept this frame and send to upper layer */ - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - if (framelen > sp->rxfrag_size) - framelen = sp->rxfrag_size; - - skb_put(skb, framelen); - skb->protocol = eth_type_trans(skb, dev); - skb_checksum_none_assert(skb); - netif_rx(skb); - sp->rx_buff[entry] = NULL; -} - -static void ipg_nic_rx_with_start(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - struct pci_dev *pdev = sp->pdev; - struct sk_buff *skb; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) != NORMAL_PACKET) - return; - - /* accept this frame and send to upper layer */ - skb = sp->rx_buff[entry]; - if (!skb) - return; - - if (jumbo->found_start) - dev_kfree_skb_irq(jumbo->skb); - - pci_unmap_single(pdev, le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - skb_put(skb, sp->rxfrag_size); - - jumbo->found_start = 1; - jumbo->current_size = sp->rxfrag_size; - jumbo->skb = skb; - - sp->rx_buff[entry] = NULL; -} - -static void ipg_nic_rx_with_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) == NORMAL_PACKET) { - struct sk_buff *skb = sp->rx_buff[entry]; - - if (!skb) - return; - - if (jumbo->found_start) { - int framelen, endframelen; - - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - - endframelen = framelen - jumbo->current_size; - if (framelen > sp->rxsupport_size) - dev_kfree_skb_irq(jumbo->skb); - else { - memcpy(skb_put(jumbo->skb, endframelen), - skb->data, endframelen); - - jumbo->skb->protocol = - eth_type_trans(jumbo->skb, dev); - - skb_checksum_none_assert(jumbo->skb); - netif_rx(jumbo->skb); - } - } - - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - - ipg_nic_rx_free_skb(dev); - } else { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } -} - -static void ipg_nic_rx_no_start_no_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) == NORMAL_PACKET) { - struct sk_buff *skb = sp->rx_buff[entry]; - - if (skb) { - if (jumbo->found_start) { - jumbo->current_size += sp->rxfrag_size; - if (jumbo->current_size <= sp->rxsupport_size) { - memcpy(skb_put(jumbo->skb, - sp->rxfrag_size), - skb->data, sp->rxfrag_size); - } - } - ipg_nic_rx_free_skb(dev); - } - } else { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } -} - -static int ipg_nic_rx_jumbo(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int curr = sp->rx_current; - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_nic_rx\n"); - - for (i = 0; i < IPG_MAXRFDPROCESS_COUNT; i++, curr++) { - unsigned int entry = curr % IPG_RFDLIST_LENGTH; - struct ipg_rx *rxfd = sp->rxd + entry; - - if (!(rxfd->rfs & cpu_to_le64(IPG_RFS_RFDDONE))) - break; - - switch (ipg_nic_rx_check_frame_type(dev)) { - case FRAME_WITH_START_WITH_END: - ipg_nic_rx_with_start_and_end(dev, sp, rxfd, entry); - break; - case FRAME_WITH_START: - ipg_nic_rx_with_start(dev, sp, rxfd, entry); - break; - case FRAME_WITH_END: - ipg_nic_rx_with_end(dev, sp, rxfd, entry); - break; - case FRAME_NO_START_NO_END: - ipg_nic_rx_no_start_no_end(dev, sp, rxfd, entry); - break; - } - } - - sp->rx_current = curr; - - if (i == IPG_MAXRFDPROCESS_COUNT) { - /* There are more RFDs to process, however the - * allocated amount of RFD processing time has - * expired. Assert Interrupt Requested to make - * sure we come back to process the remaining RFDs. - */ - ipg_w32(ipg_r32(ASIC_CTRL) | IPG_AC_INT_REQUEST, ASIC_CTRL); - } - - ipg_nic_rxrestore(dev); - - return 0; -} - -static int ipg_nic_rx(struct net_device *dev) -{ - /* Transfer received Ethernet frames to higher network layers. */ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int curr = sp->rx_current; - void __iomem *ioaddr = sp->ioaddr; - struct ipg_rx *rxfd; - unsigned int i; - - IPG_DEBUG_MSG("_nic_rx\n"); - -#define __RFS_MASK \ - cpu_to_le64(IPG_RFS_RFDDONE | IPG_RFS_FRAMESTART | IPG_RFS_FRAMEEND) - - for (i = 0; i < IPG_MAXRFDPROCESS_COUNT; i++, curr++) { - unsigned int entry = curr % IPG_RFDLIST_LENGTH; - struct sk_buff *skb = sp->rx_buff[entry]; - unsigned int framelen; - - rxfd = sp->rxd + entry; - - if (((rxfd->rfs & __RFS_MASK) != __RFS_MASK) || !skb) - break; - - /* Get received frame length. */ - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - - /* Check for jumbo frame arrival with too small - * RXFRAG_SIZE. - */ - if (framelen > sp->rxfrag_size) { - IPG_DEBUG_MSG - ("RFS FrameLen > allocated fragment size\n"); - - framelen = sp->rxfrag_size; - } - - if ((IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & - (IPG_RFS_RXFIFOOVERRUN | IPG_RFS_RXRUNTFRAME | - IPG_RFS_RXALIGNMENTERROR | IPG_RFS_RXFCSERROR | - IPG_RFS_RXOVERSIZEDFRAME | IPG_RFS_RXLENGTHERROR)))) { - - IPG_DEBUG_MSG("Rx error, RFS = %016lx\n", - (unsigned long int) rxfd->rfs); - - /* Increment general receive error statistic. */ - sp->stats.rx_errors++; - - /* Increment detailed receive error statistics. */ - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFIFOOVERRUN) { - IPG_DEBUG_MSG("RX FIFO overrun occurred\n"); - sp->stats.rx_fifo_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXRUNTFRAME) { - IPG_DEBUG_MSG("RX runt occurred\n"); - sp->stats.rx_length_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXOVERSIZEDFRAME) ; - /* Do nothing, error count handled by a IPG - * statistic register. - */ - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXALIGNMENTERROR) { - IPG_DEBUG_MSG("RX alignment error occurred\n"); - sp->stats.rx_frame_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFCSERROR) ; - /* Do nothing, error count handled by a IPG - * statistic register. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (skb) { - __le64 info = rxfd->frag_info; - - pci_unmap_single(sp->pdev, - le64_to_cpu(info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - dev_kfree_skb_irq(skb); - } - } else { - - /* Adjust the new buffer length to accommodate the size - * of the received frame. - */ - skb_put(skb, framelen); - - /* Set the buffer's protocol field to Ethernet. */ - skb->protocol = eth_type_trans(skb, dev); - - /* The IPG encountered an error with (or - * there were no) IP/TCP/UDP checksums. - * This may or may not indicate an invalid - * IP/TCP/UDP frame was received. Let the - * upper layer decide. - */ - skb_checksum_none_assert(skb); - - /* Hand off frame for higher layer processing. - * The function netif_rx() releases the sk_buff - * when processing completes. - */ - netif_rx(skb); - } - - /* Assure RX buffer is not reused by IPG. */ - sp->rx_buff[entry] = NULL; - } - - /* - * If there are more RFDs to process and the allocated amount of RFD - * processing time has expired, assert Interrupt Requested to make - * sure we come back to process the remaining RFDs. - */ - if (i == IPG_MAXRFDPROCESS_COUNT) - ipg_w32(ipg_r32(ASIC_CTRL) | IPG_AC_INT_REQUEST, ASIC_CTRL); - -#ifdef IPG_DEBUG - /* Check if the RFD list contained no receive frame data. */ - if (!i) - sp->EmptyRFDListCount++; -#endif - while ((le64_to_cpu(rxfd->rfs) & IPG_RFS_RFDDONE) && - !((le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMESTART) && - (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMEEND))) { - unsigned int entry = curr++ % IPG_RFDLIST_LENGTH; - - rxfd = sp->rxd + entry; - - IPG_DEBUG_MSG("Frame requires multiple RFDs\n"); - - /* An unexpected event, additional code needed to handle - * properly. So for the time being, just disregard the - * frame. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (sp->rx_buff[entry]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[entry]); - } - - /* Assure RX buffer is not reused by IPG. */ - sp->rx_buff[entry] = NULL; - } - - sp->rx_current = curr; - - /* Check to see if there are a minimum number of used - * RFDs before restoring any (should improve performance.) - */ - if ((curr - sp->rx_dirty) >= IPG_MINUSEDRFDSTOFREE) - ipg_nic_rxrestore(dev); - - return 0; -} - -static void ipg_reset_after_host_error(struct work_struct *work) -{ - struct ipg_nic_private *sp = - container_of(work, struct ipg_nic_private, task.work); - struct net_device *dev = sp->dev; - - /* - * Acknowledge HostError interrupt by resetting - * IPG DMA and HOST. - */ - ipg_reset(dev, IPG_AC_GLOBAL_RESET | IPG_AC_HOST | IPG_AC_DMA); - - init_rfdlist(dev); - init_tfdlist(dev); - - if (ipg_io_config(dev) < 0) { - netdev_info(dev, "Cannot recover from PCI error\n"); - schedule_delayed_work(&sp->task, HZ); - } -} - -static irqreturn_t ipg_interrupt_handler(int irq, void *dev_inst) -{ - struct net_device *dev = dev_inst; - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int handled = 0; - u16 status; - - IPG_DEBUG_MSG("_interrupt_handler\n"); - - if (sp->is_jumbo) - ipg_nic_rxrestore(dev); - - spin_lock(&sp->lock); - - /* Get interrupt source information, and acknowledge - * some (i.e. TxDMAComplete, RxDMAComplete, RxEarly, - * IntRequested, MacControlFrame, LinkEvent) interrupts - * if issued. Also, all IPG interrupts are disabled by - * reading IntStatusAck. - */ - status = ipg_r16(INT_STATUS_ACK); - - IPG_DEBUG_MSG("IntStatusAck = %04x\n", status); - - /* Shared IRQ of remove event. */ - if (!(status & IPG_IS_RSVD_MASK)) - goto out_enable; - - handled = 1; - - if (unlikely(!netif_running(dev))) - goto out_unlock; - - /* If RFDListEnd interrupt, restore all used RFDs. */ - if (status & IPG_IS_RFD_LIST_END) { - IPG_DEBUG_MSG("RFDListEnd Interrupt\n"); - - /* The RFD list end indicates an RFD was encountered - * with a 0 NextPtr, or with an RFDDone bit set to 1 - * (indicating the RFD is not read for use by the - * IPG.) Try to restore all RFDs. - */ - ipg_nic_rxrestore(dev); - -#ifdef IPG_DEBUG - /* Increment the RFDlistendCount counter. */ - sp->RFDlistendCount++; -#endif - } - - /* If RFDListEnd, RxDMAPriority, RxDMAComplete, or - * IntRequested interrupt, process received frames. */ - if ((status & IPG_IS_RX_DMA_PRIORITY) || - (status & IPG_IS_RFD_LIST_END) || - (status & IPG_IS_RX_DMA_COMPLETE) || - (status & IPG_IS_INT_REQUESTED)) { -#ifdef IPG_DEBUG - /* Increment the RFD list checked counter if interrupted - * only to check the RFD list. */ - if (status & (~(IPG_IS_RX_DMA_PRIORITY | IPG_IS_RFD_LIST_END | - IPG_IS_RX_DMA_COMPLETE | IPG_IS_INT_REQUESTED) & - (IPG_IS_HOST_ERROR | IPG_IS_TX_DMA_COMPLETE | - IPG_IS_LINK_EVENT | IPG_IS_TX_COMPLETE | - IPG_IS_UPDATE_STATS))) - sp->RFDListCheckedCount++; -#endif - - if (sp->is_jumbo) - ipg_nic_rx_jumbo(dev); - else - ipg_nic_rx(dev); - } - - /* If TxDMAComplete interrupt, free used TFDs. */ - if (status & IPG_IS_TX_DMA_COMPLETE) - ipg_nic_txfree(dev); - - /* TxComplete interrupts indicate one of numerous actions. - * Determine what action to take based on TXSTATUS register. - */ - if (status & IPG_IS_TX_COMPLETE) - ipg_nic_txcleanup(dev); - - /* If UpdateStats interrupt, update Linux Ethernet statistics */ - if (status & IPG_IS_UPDATE_STATS) - ipg_nic_get_stats(dev); - - /* If HostError interrupt, reset IPG. */ - if (status & IPG_IS_HOST_ERROR) { - IPG_DDEBUG_MSG("HostError Interrupt\n"); - - schedule_delayed_work(&sp->task, 0); - } - - /* If LinkEvent interrupt, resolve autonegotiation. */ - if (status & IPG_IS_LINK_EVENT) { - if (ipg_config_autoneg(dev) < 0) - netdev_info(dev, "Auto-negotiation error\n"); - } - - /* If MACCtrlFrame interrupt, do nothing. */ - if (status & IPG_IS_MAC_CTRL_FRAME) - IPG_DEBUG_MSG("MACCtrlFrame interrupt\n"); - - /* If RxComplete interrupt, do nothing. */ - if (status & IPG_IS_RX_COMPLETE) - IPG_DEBUG_MSG("RxComplete interrupt\n"); - - /* If RxEarly interrupt, do nothing. */ - if (status & IPG_IS_RX_EARLY) - IPG_DEBUG_MSG("RxEarly interrupt\n"); - -out_enable: - /* Re-enable IPG interrupts. */ - ipg_w16(IPG_IE_TX_DMA_COMPLETE | IPG_IE_RX_DMA_COMPLETE | - IPG_IE_HOST_ERROR | IPG_IE_INT_REQUESTED | IPG_IE_TX_COMPLETE | - IPG_IE_LINK_EVENT | IPG_IE_UPDATE_STATS, INT_ENABLE); -out_unlock: - spin_unlock(&sp->lock); - - return IRQ_RETVAL(handled); -} - -static void ipg_rx_clear(struct ipg_nic_private *sp) -{ - unsigned int i; - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - if (sp->rx_buff[i]) { - struct ipg_rx *rxfd = sp->rxd + i; - - dev_kfree_skb_irq(sp->rx_buff[i]); - sp->rx_buff[i] = NULL; - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - } - } -} - -static void ipg_tx_clear(struct ipg_nic_private *sp) -{ - unsigned int i; - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - if (sp->tx_buff[i]) { - struct ipg_tx *txfd = sp->txd + i; - - pci_unmap_single(sp->pdev, - le64_to_cpu(txfd->frag_info) & ~IPG_TFI_FRAGLEN, - sp->tx_buff[i]->len, PCI_DMA_TODEVICE); - - dev_kfree_skb_irq(sp->tx_buff[i]); - - sp->tx_buff[i] = NULL; - } - } -} - -static int ipg_nic_open(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - struct pci_dev *pdev = sp->pdev; - int rc; - - IPG_DEBUG_MSG("_nic_open\n"); - - sp->rx_buf_sz = sp->rxsupport_size; - - /* Check for interrupt line conflicts, and request interrupt - * line for IPG. - * - * IMPORTANT: Disable IPG interrupts prior to registering - * IRQ. - */ - ipg_w16(0x0000, INT_ENABLE); - - /* Register the interrupt line to be used by the IPG within - * the Linux system. - */ - rc = request_irq(pdev->irq, ipg_interrupt_handler, IRQF_SHARED, - dev->name, dev); - if (rc < 0) { - netdev_info(dev, "Error when requesting interrupt\n"); - goto out; - } - - dev->irq = pdev->irq; - - rc = -ENOMEM; - - sp->rxd = dma_alloc_coherent(&pdev->dev, IPG_RX_RING_BYTES, - &sp->rxd_map, GFP_KERNEL); - if (!sp->rxd) - goto err_free_irq_0; - - sp->txd = dma_alloc_coherent(&pdev->dev, IPG_TX_RING_BYTES, - &sp->txd_map, GFP_KERNEL); - if (!sp->txd) - goto err_free_rx_1; - - rc = init_rfdlist(dev); - if (rc < 0) { - netdev_info(dev, "Error during configuration\n"); - goto err_free_tx_2; - } - - init_tfdlist(dev); - - rc = ipg_io_config(dev); - if (rc < 0) { - netdev_info(dev, "Error during configuration\n"); - goto err_release_tfdlist_3; - } - - /* Resolve autonegotiation. */ - if (ipg_config_autoneg(dev) < 0) - netdev_info(dev, "Auto-negotiation error\n"); - - /* initialize JUMBO Frame control variable */ - sp->jumbo.found_start = 0; - sp->jumbo.current_size = 0; - sp->jumbo.skb = NULL; - - /* Enable transmit and receive operation of the IPG. */ - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_RX_ENABLE | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - - netif_start_queue(dev); -out: - return rc; - -err_release_tfdlist_3: - ipg_tx_clear(sp); - ipg_rx_clear(sp); -err_free_tx_2: - dma_free_coherent(&pdev->dev, IPG_TX_RING_BYTES, sp->txd, sp->txd_map); -err_free_rx_1: - dma_free_coherent(&pdev->dev, IPG_RX_RING_BYTES, sp->rxd, sp->rxd_map); -err_free_irq_0: - free_irq(pdev->irq, dev); - goto out; -} - -static int ipg_nic_stop(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - struct pci_dev *pdev = sp->pdev; - - IPG_DEBUG_MSG("_nic_stop\n"); - - netif_stop_queue(dev); - - IPG_DUMPTFDLIST(dev); - - do { - (void) ipg_r16(INT_STATUS_ACK); - - ipg_reset(dev, IPG_AC_GLOBAL_RESET | IPG_AC_HOST | IPG_AC_DMA); - - synchronize_irq(pdev->irq); - } while (ipg_r16(INT_ENABLE) & IPG_IE_RSVD_MASK); - - ipg_rx_clear(sp); - - ipg_tx_clear(sp); - - pci_free_consistent(pdev, IPG_RX_RING_BYTES, sp->rxd, sp->rxd_map); - pci_free_consistent(pdev, IPG_TX_RING_BYTES, sp->txd, sp->txd_map); - - free_irq(pdev->irq, dev); - - return 0; -} - -static netdev_tx_t ipg_nic_hard_start_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int entry = sp->tx_current % IPG_TFDLIST_LENGTH; - unsigned long flags; - struct ipg_tx *txfd; - - IPG_DDEBUG_MSG("_nic_hard_start_xmit\n"); - - /* If in 10Mbps mode, stop the transmit queue so - * no more transmit frames are accepted. - */ - if (sp->tenmbpsmode) - netif_stop_queue(dev); - - if (sp->reset_current_tfd) { - sp->reset_current_tfd = 0; - entry = 0; - } - - txfd = sp->txd + entry; - - sp->tx_buff[entry] = skb; - - /* Clear all TFC fields, except TFDDONE. */ - txfd->tfc = cpu_to_le64(IPG_TFC_TFDDONE); - - /* Specify the TFC field within the TFD. */ - txfd->tfc |= cpu_to_le64(IPG_TFC_WORDALIGNDISABLED | - (IPG_TFC_FRAMEID & sp->tx_current) | - (IPG_TFC_FRAGCOUNT & (1 << 24))); - /* - * 16--17 (WordAlign) <- 3 (disable), - * 0--15 (FrameId) <- sp->tx_current, - * 24--27 (FragCount) <- 1 - */ - - /* Request TxComplete interrupts at an interval defined - * by the constant IPG_FRAMESBETWEENTXCOMPLETES. - * Request TxComplete interrupt for every frame - * if in 10Mbps mode to accommodate problem with 10Mbps - * processing. - */ - if (sp->tenmbpsmode) - txfd->tfc |= cpu_to_le64(IPG_TFC_TXINDICATE); - txfd->tfc |= cpu_to_le64(IPG_TFC_TXDMAINDICATE); - /* Based on compilation option, determine if FCS is to be - * appended to transmit frame by IPG. - */ - if (!(IPG_APPEND_FCS_ON_TX)) - txfd->tfc |= cpu_to_le64(IPG_TFC_FCSAPPENDDISABLE); - - /* Based on compilation option, determine if IP, TCP and/or - * UDP checksums are to be added to transmit frame by IPG. - */ - if (IPG_ADD_IPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_IPCHECKSUMENABLE); - - if (IPG_ADD_TCPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_TCPCHECKSUMENABLE); - - if (IPG_ADD_UDPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_UDPCHECKSUMENABLE); - - /* Based on compilation option, determine if VLAN tag info is to be - * inserted into transmit frame by IPG. - */ - if (IPG_INSERT_MANUAL_VLAN_TAG) { - txfd->tfc |= cpu_to_le64(IPG_TFC_VLANTAGINSERT | - ((u64) IPG_MANUAL_VLAN_VID << 32) | - ((u64) IPG_MANUAL_VLAN_CFI << 44) | - ((u64) IPG_MANUAL_VLAN_USERPRIORITY << 45)); - } - - /* The fragment start location within system memory is defined - * by the sk_buff structure's data field. The physical address - * of this location within the system's virtual memory space - * is determined using the IPG_HOST2BUS_MAP function. - */ - txfd->frag_info = cpu_to_le64(pci_map_single(sp->pdev, skb->data, - skb->len, PCI_DMA_TODEVICE)); - - /* The length of the fragment within system memory is defined by - * the sk_buff structure's len field. - */ - txfd->frag_info |= cpu_to_le64(IPG_TFI_FRAGLEN & - ((u64) (skb->len & 0xffff) << 48)); - - /* Clear the TFDDone bit last to indicate the TFD is ready - * for transfer to the IPG. - */ - txfd->tfc &= cpu_to_le64(~IPG_TFC_TFDDONE); - - spin_lock_irqsave(&sp->lock, flags); - - sp->tx_current++; - - mmiowb(); - - ipg_w32(IPG_DC_TX_DMA_POLL_NOW, DMA_CTRL); - - if (sp->tx_current == (sp->tx_dirty + IPG_TFDLIST_LENGTH)) - netif_stop_queue(dev); - - spin_unlock_irqrestore(&sp->lock, flags); - - return NETDEV_TX_OK; -} - -static void ipg_set_phy_default_param(unsigned char rev, - struct net_device *dev, int phy_address) -{ - unsigned short length; - unsigned char revision; - const unsigned short *phy_param; - unsigned short address, value; - - phy_param = &DefaultPhyParam[0]; - length = *phy_param & 0x00FF; - revision = (unsigned char)((*phy_param) >> 8); - phy_param++; - while (length != 0) { - if (rev == revision) { - while (length > 1) { - address = *phy_param; - value = *(phy_param + 1); - phy_param += 2; - mdio_write(dev, phy_address, address, value); - length -= 4; - } - break; - } else { - phy_param += length / 2; - length = *phy_param & 0x00FF; - revision = (unsigned char)((*phy_param) >> 8); - phy_param++; - } - } -} - -static int read_eeprom(struct net_device *dev, int eep_addr) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - unsigned int i; - int ret = 0; - u16 value; - - value = IPG_EC_EEPROM_READOPCODE | (eep_addr & 0xff); - ipg_w16(value, EEPROM_CTRL); - - for (i = 0; i < 1000; i++) { - u16 data; - - mdelay(10); - data = ipg_r16(EEPROM_CTRL); - if (!(data & IPG_EC_EEPROM_BUSY)) { - ret = ipg_r16(EEPROM_DATA); - break; - } - } - return ret; -} - -static void ipg_init_mii(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct mii_if_info *mii_if = &sp->mii_if; - int phyaddr; - - mii_if->dev = dev; - mii_if->mdio_read = mdio_read; - mii_if->mdio_write = mdio_write; - mii_if->phy_id_mask = 0x1f; - mii_if->reg_num_mask = 0x1f; - - mii_if->phy_id = phyaddr = ipg_find_phyaddr(dev); - - if (phyaddr != 0x1f) { - u16 mii_phyctrl, mii_1000cr; - - mii_1000cr = mdio_read(dev, phyaddr, MII_CTRL1000); - mii_1000cr |= ADVERTISE_1000FULL | ADVERTISE_1000HALF | - GMII_PHY_1000BASETCONTROL_PreferMaster; - mdio_write(dev, phyaddr, MII_CTRL1000, mii_1000cr); - - mii_phyctrl = mdio_read(dev, phyaddr, MII_BMCR); - - /* Set default phyparam */ - ipg_set_phy_default_param(sp->pdev->revision, dev, phyaddr); - - /* Reset PHY */ - mii_phyctrl |= BMCR_RESET | BMCR_ANRESTART; - mdio_write(dev, phyaddr, MII_BMCR, mii_phyctrl); - - } -} - -static int ipg_hw_init(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - int rc; - - /* Read/Write and Reset EEPROM Value */ - /* Read LED Mode Configuration from EEPROM */ - sp->led_mode = read_eeprom(dev, 6); - - /* Reset all functions within the IPG. Do not assert - * RST_OUT as not compatible with some PHYs. - */ - rc = ipg_reset(dev, IPG_RESET_MASK); - if (rc < 0) - goto out; - - ipg_init_mii(dev); - - /* Read MAC Address from EEPROM */ - for (i = 0; i < 3; i++) - sp->station_addr[i] = read_eeprom(dev, 16 + i); - - for (i = 0; i < 3; i++) - ipg_w16(sp->station_addr[i], STATION_ADDRESS_0 + 2*i); - - /* Set station address in ethernet_device structure. */ - dev->dev_addr[0] = ipg_r16(STATION_ADDRESS_0) & 0x00ff; - dev->dev_addr[1] = (ipg_r16(STATION_ADDRESS_0) & 0xff00) >> 8; - dev->dev_addr[2] = ipg_r16(STATION_ADDRESS_1) & 0x00ff; - dev->dev_addr[3] = (ipg_r16(STATION_ADDRESS_1) & 0xff00) >> 8; - dev->dev_addr[4] = ipg_r16(STATION_ADDRESS_2) & 0x00ff; - dev->dev_addr[5] = (ipg_r16(STATION_ADDRESS_2) & 0xff00) >> 8; -out: - return rc; -} - -static int ipg_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = generic_mii_ioctl(&sp->mii_if, if_mii(ifr), cmd, NULL); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_nic_change_mtu(struct net_device *dev, int new_mtu) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int err; - - /* Function to accommodate changes to Maximum Transfer Unit - * (or MTU) of IPG NIC. Cannot use default function since - * the default will not allow for MTU > 1500 bytes. - */ - - IPG_DEBUG_MSG("_nic_change_mtu\n"); - - /* - * Check that the new MTU value is between 68 (14 byte header, 46 byte - * payload, 4 byte FCS) and 10 KB, which is the largest supported MTU. - */ - if (new_mtu < 68 || new_mtu > 10240) - return -EINVAL; - - err = ipg_nic_stop(dev); - if (err) - return err; - - dev->mtu = new_mtu; - - sp->max_rxframe_size = new_mtu; - - sp->rxfrag_size = new_mtu; - if (sp->rxfrag_size > 4088) - sp->rxfrag_size = 4088; - - sp->rxsupport_size = sp->max_rxframe_size; - - if (new_mtu > 0x0600) - sp->is_jumbo = true; - else - sp->is_jumbo = false; - - return ipg_nic_open(dev); -} - -static int ipg_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_ethtool_gset(&sp->mii_if, cmd); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_ethtool_sset(&sp->mii_if, cmd); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_nway_reset(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_nway_restart(&sp->mii_if); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static const struct ethtool_ops ipg_ethtool_ops = { - .get_settings = ipg_get_settings, - .set_settings = ipg_set_settings, - .nway_reset = ipg_nway_reset, -}; - -static void ipg_remove(struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata(pdev); - struct ipg_nic_private *sp = netdev_priv(dev); - - IPG_DEBUG_MSG("_remove\n"); - - /* Un-register Ethernet device. */ - unregister_netdev(dev); - - pci_iounmap(pdev, sp->ioaddr); - - pci_release_regions(pdev); - - free_netdev(dev); - pci_disable_device(pdev); -} - -static const struct net_device_ops ipg_netdev_ops = { - .ndo_open = ipg_nic_open, - .ndo_stop = ipg_nic_stop, - .ndo_start_xmit = ipg_nic_hard_start_xmit, - .ndo_get_stats = ipg_nic_get_stats, - .ndo_set_rx_mode = ipg_nic_set_multicast_list, - .ndo_do_ioctl = ipg_ioctl, - .ndo_tx_timeout = ipg_tx_timeout, - .ndo_change_mtu = ipg_nic_change_mtu, - .ndo_set_mac_address = eth_mac_addr, - .ndo_validate_addr = eth_validate_addr, -}; - -static int ipg_probe(struct pci_dev *pdev, const struct pci_device_id *id) -{ - unsigned int i = id->driver_data; - struct ipg_nic_private *sp; - struct net_device *dev; - void __iomem *ioaddr; - int rc; - - rc = pci_enable_device(pdev); - if (rc < 0) - goto out; - - pr_info("%s: %s\n", pci_name(pdev), ipg_brand_name[i]); - - pci_set_master(pdev); - - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(40)); - if (rc < 0) { - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc < 0) { - pr_err("%s: DMA config failed\n", pci_name(pdev)); - goto err_disable_0; - } - } - - /* - * Initialize net device. - */ - dev = alloc_etherdev(sizeof(struct ipg_nic_private)); - if (!dev) { - rc = -ENOMEM; - goto err_disable_0; - } - - sp = netdev_priv(dev); - spin_lock_init(&sp->lock); - mutex_init(&sp->mii_mutex); - - sp->is_jumbo = IPG_IS_JUMBO; - sp->rxfrag_size = IPG_RXFRAG_SIZE; - sp->rxsupport_size = IPG_RXSUPPORT_SIZE; - sp->max_rxframe_size = IPG_MAX_RXFRAME_SIZE; - - /* Declare IPG NIC functions for Ethernet device methods. - */ - dev->netdev_ops = &ipg_netdev_ops; - SET_NETDEV_DEV(dev, &pdev->dev); - dev->ethtool_ops = &ipg_ethtool_ops; - - rc = pci_request_regions(pdev, DRV_NAME); - if (rc) - goto err_free_dev_1; - - ioaddr = pci_iomap(pdev, 1, pci_resource_len(pdev, 1)); - if (!ioaddr) { - pr_err("%s: cannot map MMIO\n", pci_name(pdev)); - rc = -EIO; - goto err_release_regions_2; - } - - /* Save the pointer to the PCI device information. */ - sp->ioaddr = ioaddr; - sp->pdev = pdev; - sp->dev = dev; - - INIT_DELAYED_WORK(&sp->task, ipg_reset_after_host_error); - - pci_set_drvdata(pdev, dev); - - rc = ipg_hw_init(dev); - if (rc < 0) - goto err_unmap_3; - - rc = register_netdev(dev); - if (rc < 0) - goto err_unmap_3; - - netdev_info(dev, "Ethernet device registered\n"); -out: - return rc; - -err_unmap_3: - pci_iounmap(pdev, ioaddr); -err_release_regions_2: - pci_release_regions(pdev); -err_free_dev_1: - free_netdev(dev); -err_disable_0: - pci_disable_device(pdev); - goto out; -} - -static struct pci_driver ipg_pci_driver = { - .name = IPG_DRIVER_NAME, - .id_table = ipg_pci_tbl, - .probe = ipg_probe, - .remove = ipg_remove, -}; - -module_pci_driver(ipg_pci_driver); diff --git a/drivers/net/ethernet/icplus/ipg.h b/drivers/net/ethernet/icplus/ipg.h deleted file mode 100644 index de606281f97b..000000000000 --- a/drivers/net/ethernet/icplus/ipg.h +++ /dev/null @@ -1,748 +0,0 @@ -/* - * Include file for Gigabit Ethernet device driver for Network - * Interface Cards (NICs) utilizing the Tamarack Microelectronics - * Inc. IPG Gigabit or Triple Speed Ethernet Media Access - * Controller. - */ -#ifndef __LINUX_IPG_H -#define __LINUX_IPG_H - -#include <linux/module.h> - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/ioport.h> -#include <linux/errno.h> -#include <asm/io.h> -#include <linux/delay.h> -#include <linux/types.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <asm/bitops.h> - -/* - * Constants - */ - -/* GMII based PHY IDs */ -#define NS 0x2000 -#define MARVELL 0x0141 -#define ICPLUS_PHY 0x243 - -/* NIC Physical Layer Device MII register fields. */ -#define MII_PHY_SELECTOR_IEEE8023 0x0001 -#define MII_PHY_TECHABILITYFIELD 0x1FE0 - -/* GMII_PHY_1000 need to set to prefer master */ -#define GMII_PHY_1000BASETCONTROL_PreferMaster 0x0400 - -/* NIC Physical Layer Device GMII constants. */ -#define GMII_PREAMBLE 0xFFFFFFFF -#define GMII_ST 0x1 -#define GMII_READ 0x2 -#define GMII_WRITE 0x1 -#define GMII_TA_READ_MASK 0x1 -#define GMII_TA_WRITE 0x2 - -/* I/O register offsets. */ -enum ipg_regs { - DMA_CTRL = 0x00, - RX_DMA_STATUS = 0x08, /* Unused + reserved */ - TFD_LIST_PTR_0 = 0x10, - TFD_LIST_PTR_1 = 0x14, - TX_DMA_BURST_THRESH = 0x18, - TX_DMA_URGENT_THRESH = 0x19, - TX_DMA_POLL_PERIOD = 0x1a, - RFD_LIST_PTR_0 = 0x1c, - RFD_LIST_PTR_1 = 0x20, - RX_DMA_BURST_THRESH = 0x24, - RX_DMA_URGENT_THRESH = 0x25, - RX_DMA_POLL_PERIOD = 0x26, - DEBUG_CTRL = 0x2c, - ASIC_CTRL = 0x30, - FIFO_CTRL = 0x38, /* Unused */ - FLOW_OFF_THRESH = 0x3c, - FLOW_ON_THRESH = 0x3e, - EEPROM_DATA = 0x48, - EEPROM_CTRL = 0x4a, - EXPROM_ADDR = 0x4c, /* Unused */ - EXPROM_DATA = 0x50, /* Unused */ - WAKE_EVENT = 0x51, /* Unused */ - COUNTDOWN = 0x54, /* Unused */ - INT_STATUS_ACK = 0x5a, - INT_ENABLE = 0x5c, - INT_STATUS = 0x5e, /* Unused */ - TX_STATUS = 0x60, - MAC_CTRL = 0x6c, - VLAN_TAG = 0x70, /* Unused */ - PHY_SET = 0x75, - PHY_CTRL = 0x76, - STATION_ADDRESS_0 = 0x78, - STATION_ADDRESS_1 = 0x7a, - STATION_ADDRESS_2 = 0x7c, - MAX_FRAME_SIZE = 0x86, - RECEIVE_MODE = 0x88, - HASHTABLE_0 = 0x8c, - HASHTABLE_1 = 0x90, - RMON_STATISTICS_MASK = 0x98, - STATISTICS_MASK = 0x9c, - RX_JUMBO_FRAMES = 0xbc, /* Unused */ - TCP_CHECKSUM_ERRORS = 0xc0, /* Unused */ - IP_CHECKSUM_ERRORS = 0xc2, /* Unused */ - UDP_CHECKSUM_ERRORS = 0xc4, /* Unused */ - TX_JUMBO_FRAMES = 0xf4 /* Unused */ -}; - -/* Ethernet MIB statistic register offsets. */ -#define IPG_OCTETRCVOK 0xA8 -#define IPG_MCSTOCTETRCVDOK 0xAC -#define IPG_BCSTOCTETRCVOK 0xB0 -#define IPG_FRAMESRCVDOK 0xB4 -#define IPG_MCSTFRAMESRCVDOK 0xB8 -#define IPG_BCSTFRAMESRCVDOK 0xBE -#define IPG_MACCONTROLFRAMESRCVD 0xC6 -#define IPG_FRAMETOOLONGERRORS 0xC8 -#define IPG_INRANGELENGTHERRORS 0xCA -#define IPG_FRAMECHECKSEQERRORS 0xCC -#define IPG_FRAMESLOSTRXERRORS 0xCE -#define IPG_OCTETXMTOK 0xD0 -#define IPG_MCSTOCTETXMTOK 0xD4 -#define IPG_BCSTOCTETXMTOK 0xD8 -#define IPG_FRAMESXMTDOK 0xDC -#define IPG_MCSTFRAMESXMTDOK 0xE0 -#define IPG_FRAMESWDEFERREDXMT 0xE4 -#define IPG_LATECOLLISIONS 0xE8 -#define IPG_MULTICOLFRAMES 0xEC -#define IPG_SINGLECOLFRAMES 0xF0 -#define IPG_BCSTFRAMESXMTDOK 0xF6 -#define IPG_CARRIERSENSEERRORS 0xF8 -#define IPG_MACCONTROLFRAMESXMTDOK 0xFA -#define IPG_FRAMESABORTXSCOLLS 0xFC -#define IPG_FRAMESWEXDEFERRAL 0xFE - -/* RMON statistic register offsets. */ -#define IPG_ETHERSTATSCOLLISIONS 0x100 -#define IPG_ETHERSTATSOCTETSTRANSMIT 0x104 -#define IPG_ETHERSTATSPKTSTRANSMIT 0x108 -#define IPG_ETHERSTATSPKTS64OCTESTSTRANSMIT 0x10C -#define IPG_ETHERSTATSPKTS65TO127OCTESTSTRANSMIT 0x110 -#define IPG_ETHERSTATSPKTS128TO255OCTESTSTRANSMIT 0x114 -#define IPG_ETHERSTATSPKTS256TO511OCTESTSTRANSMIT 0x118 -#define IPG_ETHERSTATSPKTS512TO1023OCTESTSTRANSMIT 0x11C -#define IPG_ETHERSTATSPKTS1024TO1518OCTESTSTRANSMIT 0x120 -#define IPG_ETHERSTATSCRCALIGNERRORS 0x124 -#define IPG_ETHERSTATSUNDERSIZEPKTS 0x128 -#define IPG_ETHERSTATSFRAGMENTS 0x12C -#define IPG_ETHERSTATSJABBERS 0x130 -#define IPG_ETHERSTATSOCTETS 0x134 -#define IPG_ETHERSTATSPKTS 0x138 -#define IPG_ETHERSTATSPKTS64OCTESTS 0x13C -#define IPG_ETHERSTATSPKTS65TO127OCTESTS 0x140 -#define IPG_ETHERSTATSPKTS128TO255OCTESTS 0x144 -#define IPG_ETHERSTATSPKTS256TO511OCTESTS 0x148 -#define IPG_ETHERSTATSPKTS512TO1023OCTESTS 0x14C -#define IPG_ETHERSTATSPKTS1024TO1518OCTESTS 0x150 - -/* RMON statistic register equivalents. */ -#define IPG_ETHERSTATSMULTICASTPKTSTRANSMIT 0xE0 -#define IPG_ETHERSTATSBROADCASTPKTSTRANSMIT 0xF6 -#define IPG_ETHERSTATSMULTICASTPKTS 0xB8 -#define IPG_ETHERSTATSBROADCASTPKTS 0xBE -#define IPG_ETHERSTATSOVERSIZEPKTS 0xC8 -#define IPG_ETHERSTATSDROPEVENTS 0xCE - -/* Serial EEPROM offsets */ -#define IPG_EEPROM_CONFIGPARAM 0x00 -#define IPG_EEPROM_ASICCTRL 0x01 -#define IPG_EEPROM_SUBSYSTEMVENDORID 0x02 -#define IPG_EEPROM_SUBSYSTEMID 0x03 -#define IPG_EEPROM_STATIONADDRESS0 0x10 -#define IPG_EEPROM_STATIONADDRESS1 0x11 -#define IPG_EEPROM_STATIONADDRESS2 0x12 - -/* Register & data structure bit masks */ - -/* PCI register masks. */ - -/* IOBaseAddress */ -#define IPG_PIB_RSVD_MASK 0xFFFFFE01 -#define IPG_PIB_IOBASEADDRESS 0xFFFFFF00 -#define IPG_PIB_IOBASEADDRIND 0x00000001 - -/* MemBaseAddress */ -#define IPG_PMB_RSVD_MASK 0xFFFFFE07 -#define IPG_PMB_MEMBASEADDRIND 0x00000001 -#define IPG_PMB_MEMMAPTYPE 0x00000006 -#define IPG_PMB_MEMMAPTYPE0 0x00000002 -#define IPG_PMB_MEMMAPTYPE1 0x00000004 -#define IPG_PMB_MEMBASEADDRESS 0xFFFFFE00 - -/* ConfigStatus */ -#define IPG_CS_RSVD_MASK 0xFFB0 -#define IPG_CS_CAPABILITIES 0x0010 -#define IPG_CS_66MHZCAPABLE 0x0020 -#define IPG_CS_FASTBACK2BACK 0x0080 -#define IPG_CS_DATAPARITYREPORTED 0x0100 -#define IPG_CS_DEVSELTIMING 0x0600 -#define IPG_CS_SIGNALEDTARGETABORT 0x0800 -#define IPG_CS_RECEIVEDTARGETABORT 0x1000 -#define IPG_CS_RECEIVEDMASTERABORT 0x2000 -#define IPG_CS_SIGNALEDSYSTEMERROR 0x4000 -#define IPG_CS_DETECTEDPARITYERROR 0x8000 - -/* TFD data structure masks. */ - -/* TFDList, TFC */ -#define IPG_TFC_RSVD_MASK 0x0000FFFF9FFFFFFFULL -#define IPG_TFC_FRAMEID 0x000000000000FFFFULL -#define IPG_TFC_WORDALIGN 0x0000000000030000ULL -#define IPG_TFC_WORDALIGNTODWORD 0x0000000000000000ULL -#define IPG_TFC_WORDALIGNTOWORD 0x0000000000020000ULL -#define IPG_TFC_WORDALIGNDISABLED 0x0000000000030000ULL -#define IPG_TFC_TCPCHECKSUMENABLE 0x0000000000040000ULL -#define IPG_TFC_UDPCHECKSUMENABLE 0x0000000000080000ULL -#define IPG_TFC_IPCHECKSUMENABLE 0x0000000000100000ULL -#define IPG_TFC_FCSAPPENDDISABLE 0x0000000000200000ULL -#define IPG_TFC_TXINDICATE 0x0000000000400000ULL -#define IPG_TFC_TXDMAINDICATE 0x0000000000800000ULL -#define IPG_TFC_FRAGCOUNT 0x000000000F000000ULL -#define IPG_TFC_VLANTAGINSERT 0x0000000010000000ULL -#define IPG_TFC_TFDDONE 0x0000000080000000ULL -#define IPG_TFC_VID 0x00000FFF00000000ULL -#define IPG_TFC_CFI 0x0000100000000000ULL -#define IPG_TFC_USERPRIORITY 0x0000E00000000000ULL - -/* TFDList, FragInfo */ -#define IPG_TFI_RSVD_MASK 0xFFFF00FFFFFFFFFFULL -#define IPG_TFI_FRAGADDR 0x000000FFFFFFFFFFULL -#define IPG_TFI_FRAGLEN 0xFFFF000000000000ULL - -/* RFD data structure masks. */ - -/* RFDList, RFS */ -#define IPG_RFS_RSVD_MASK 0x0000FFFFFFFFFFFFULL -#define IPG_RFS_RXFRAMELEN 0x000000000000FFFFULL -#define IPG_RFS_RXFIFOOVERRUN 0x0000000000010000ULL -#define IPG_RFS_RXRUNTFRAME 0x0000000000020000ULL -#define IPG_RFS_RXALIGNMENTERROR 0x0000000000040000ULL -#define IPG_RFS_RXFCSERROR 0x0000000000080000ULL -#define IPG_RFS_RXOVERSIZEDFRAME 0x0000000000100000ULL -#define IPG_RFS_RXLENGTHERROR 0x0000000000200000ULL -#define IPG_RFS_VLANDETECTED 0x0000000000400000ULL -#define IPG_RFS_TCPDETECTED 0x0000000000800000ULL -#define IPG_RFS_TCPERROR 0x0000000001000000ULL -#define IPG_RFS_UDPDETECTED 0x0000000002000000ULL -#define IPG_RFS_UDPERROR 0x0000000004000000ULL -#define IPG_RFS_IPDETECTED 0x0000000008000000ULL -#define IPG_RFS_IPERROR 0x0000000010000000ULL -#define IPG_RFS_FRAMESTART 0x0000000020000000ULL -#define IPG_RFS_FRAMEEND 0x0000000040000000ULL -#define IPG_RFS_RFDDONE 0x0000000080000000ULL -#define IPG_RFS_TCI 0x0000FFFF00000000ULL - -/* RFDList, FragInfo */ -#define IPG_RFI_RSVD_MASK 0xFFFF00FFFFFFFFFFULL -#define IPG_RFI_FRAGADDR 0x000000FFFFFFFFFFULL -#define IPG_RFI_FRAGLEN 0xFFFF000000000000ULL - -/* I/O Register masks. */ - -/* RMON Statistics Mask */ -#define IPG_RZ_ALL 0x0FFFFFFF - -/* Statistics Mask */ -#define IPG_SM_ALL 0x0FFFFFFF -#define IPG_SM_OCTETRCVOK_FRAMESRCVDOK 0x00000001 -#define IPG_SM_MCSTOCTETRCVDOK_MCSTFRAMESRCVDOK 0x00000002 -#define IPG_SM_BCSTOCTETRCVDOK_BCSTFRAMESRCVDOK 0x00000004 -#define IPG_SM_RXJUMBOFRAMES 0x00000008 -#define IPG_SM_TCPCHECKSUMERRORS 0x00000010 -#define IPG_SM_IPCHECKSUMERRORS 0x00000020 -#define IPG_SM_UDPCHECKSUMERRORS 0x00000040 -#define IPG_SM_MACCONTROLFRAMESRCVD 0x00000080 -#define IPG_SM_FRAMESTOOLONGERRORS 0x00000100 -#define IPG_SM_INRANGELENGTHERRORS 0x00000200 -#define IPG_SM_FRAMECHECKSEQERRORS 0x00000400 -#define IPG_SM_FRAMESLOSTRXERRORS 0x00000800 -#define IPG_SM_OCTETXMTOK_FRAMESXMTOK 0x00001000 -#define IPG_SM_MCSTOCTETXMTOK_MCSTFRAMESXMTDOK 0x00002000 -#define IPG_SM_BCSTOCTETXMTOK_BCSTFRAMESXMTDOK 0x00004000 -#define IPG_SM_FRAMESWDEFERREDXMT 0x00008000 -#define IPG_SM_LATECOLLISIONS 0x00010000 -#define IPG_SM_MULTICOLFRAMES 0x00020000 -#define IPG_SM_SINGLECOLFRAMES 0x00040000 -#define IPG_SM_TXJUMBOFRAMES 0x00080000 -#define IPG_SM_CARRIERSENSEERRORS 0x00100000 -#define IPG_SM_MACCONTROLFRAMESXMTD 0x00200000 -#define IPG_SM_FRAMESABORTXSCOLLS 0x00400000 -#define IPG_SM_FRAMESWEXDEFERAL 0x00800000 - -/* Countdown */ -#define IPG_CD_RSVD_MASK 0x0700FFFF -#define IPG_CD_COUNT 0x0000FFFF -#define IPG_CD_COUNTDOWNSPEED 0x01000000 -#define IPG_CD_COUNTDOWNMODE 0x02000000 -#define IPG_CD_COUNTINTENABLED 0x04000000 - -/* TxDMABurstThresh */ -#define IPG_TB_RSVD_MASK 0xFF - -/* TxDMAUrgentThresh */ -#define IPG_TU_RSVD_MASK 0xFF - -/* TxDMAPollPeriod */ -#define IPG_TP_RSVD_MASK 0xFF - -/* RxDMAUrgentThresh */ -#define IPG_RU_RSVD_MASK 0xFF - -/* RxDMAPollPeriod */ -#define IPG_RP_RSVD_MASK 0xFF - -/* ReceiveMode */ -#define IPG_RM_RSVD_MASK 0x3F -#define IPG_RM_RECEIVEUNICAST 0x01 -#define IPG_RM_RECEIVEMULTICAST 0x02 -#define IPG_RM_RECEIVEBROADCAST 0x04 -#define IPG_RM_RECEIVEALLFRAMES 0x08 -#define IPG_RM_RECEIVEMULTICASTHASH 0x10 -#define IPG_RM_RECEIVEIPMULTICAST 0x20 - -/* PhySet */ -#define IPG_PS_MEM_LENB9B 0x01 -#define IPG_PS_MEM_LEN9 0x02 -#define IPG_PS_NON_COMPDET 0x04 - -/* PhyCtrl */ -#define IPG_PC_RSVD_MASK 0xFF -#define IPG_PC_MGMTCLK_LO 0x00 -#define IPG_PC_MGMTCLK_HI 0x01 -#define IPG_PC_MGMTCLK 0x01 -#define IPG_PC_MGMTDATA 0x02 -#define IPG_PC_MGMTDIR 0x04 -#define IPG_PC_DUPLEX_POLARITY 0x08 -#define IPG_PC_DUPLEX_STATUS 0x10 -#define IPG_PC_LINK_POLARITY 0x20 -#define IPG_PC_LINK_SPEED 0xC0 -#define IPG_PC_LINK_SPEED_10MBPS 0x40 -#define IPG_PC_LINK_SPEED_100MBPS 0x80 -#define IPG_PC_LINK_SPEED_1000MBPS 0xC0 - -/* DMACtrl */ -#define IPG_DC_RSVD_MASK 0xC07D9818 -#define IPG_DC_RX_DMA_COMPLETE 0x00000008 -#define IPG_DC_RX_DMA_POLL_NOW 0x00000010 -#define IPG_DC_TX_DMA_COMPLETE 0x00000800 -#define IPG_DC_TX_DMA_POLL_NOW 0x00001000 -#define IPG_DC_TX_DMA_IN_PROG 0x00008000 -#define IPG_DC_RX_EARLY_DISABLE 0x00010000 -#define IPG_DC_MWI_DISABLE 0x00040000 -#define IPG_DC_TX_WRITE_BACK_DISABLE 0x00080000 -#define IPG_DC_TX_BURST_LIMIT 0x00700000 -#define IPG_DC_TARGET_ABORT 0x40000000 -#define IPG_DC_MASTER_ABORT 0x80000000 - -/* ASICCtrl */ -#define IPG_AC_RSVD_MASK 0x07FFEFF2 -#define IPG_AC_EXP_ROM_SIZE 0x00000002 -#define IPG_AC_PHY_SPEED10 0x00000010 -#define IPG_AC_PHY_SPEED100 0x00000020 -#define IPG_AC_PHY_SPEED1000 0x00000040 -#define IPG_AC_PHY_MEDIA 0x00000080 -#define IPG_AC_FORCED_CFG 0x00000700 -#define IPG_AC_D3RESETDISABLE 0x00000800 -#define IPG_AC_SPEED_UP_MODE 0x00002000 -#define IPG_AC_LED_MODE 0x00004000 -#define IPG_AC_RST_OUT_POLARITY 0x00008000 -#define IPG_AC_GLOBAL_RESET 0x00010000 -#define IPG_AC_RX_RESET 0x00020000 -#define IPG_AC_TX_RESET 0x00040000 -#define IPG_AC_DMA 0x00080000 -#define IPG_AC_FIFO 0x00100000 -#define IPG_AC_NETWORK 0x00200000 -#define IPG_AC_HOST 0x00400000 -#define IPG_AC_AUTO_INIT 0x00800000 -#define IPG_AC_RST_OUT 0x01000000 -#define IPG_AC_INT_REQUEST 0x02000000 -#define IPG_AC_RESET_BUSY 0x04000000 -#define IPG_AC_LED_SPEED 0x08000000 -#define IPG_AC_LED_MODE_BIT_1 0x20000000 - -/* EepromCtrl */ -#define IPG_EC_RSVD_MASK 0x83FF -#define IPG_EC_EEPROM_ADDR 0x00FF -#define IPG_EC_EEPROM_OPCODE 0x0300 -#define IPG_EC_EEPROM_SUBCOMMAD 0x0000 -#define IPG_EC_EEPROM_WRITEOPCODE 0x0100 -#define IPG_EC_EEPROM_READOPCODE 0x0200 -#define IPG_EC_EEPROM_ERASEOPCODE 0x0300 -#define IPG_EC_EEPROM_BUSY 0x8000 - -/* FIFOCtrl */ -#define IPG_FC_RSVD_MASK 0xC001 -#define IPG_FC_RAM_TEST_MODE 0x0001 -#define IPG_FC_TRANSMITTING 0x4000 -#define IPG_FC_RECEIVING 0x8000 - -/* TxStatus */ -#define IPG_TS_RSVD_MASK 0xFFFF00DD -#define IPG_TS_TX_ERROR 0x00000001 -#define IPG_TS_LATE_COLLISION 0x00000004 -#define IPG_TS_TX_MAX_COLL 0x00000008 -#define IPG_TS_TX_UNDERRUN 0x00000010 -#define IPG_TS_TX_IND_REQD 0x00000040 -#define IPG_TS_TX_COMPLETE 0x00000080 -#define IPG_TS_TX_FRAMEID 0xFFFF0000 - -/* WakeEvent */ -#define IPG_WE_WAKE_PKT_ENABLE 0x01 -#define IPG_WE_MAGIC_PKT_ENABLE 0x02 -#define IPG_WE_LINK_EVT_ENABLE 0x04 -#define IPG_WE_WAKE_POLARITY 0x08 -#define IPG_WE_WAKE_PKT_EVT 0x10 -#define IPG_WE_MAGIC_PKT_EVT 0x20 -#define IPG_WE_LINK_EVT 0x40 -#define IPG_WE_WOL_ENABLE 0x80 - -/* IntEnable */ -#define IPG_IE_RSVD_MASK 0x1FFE -#define IPG_IE_HOST_ERROR 0x0002 -#define IPG_IE_TX_COMPLETE 0x0004 -#define IPG_IE_MAC_CTRL_FRAME 0x0008 -#define IPG_IE_RX_COMPLETE 0x0010 -#define IPG_IE_RX_EARLY 0x0020 -#define IPG_IE_INT_REQUESTED 0x0040 -#define IPG_IE_UPDATE_STATS 0x0080 -#define IPG_IE_LINK_EVENT 0x0100 -#define IPG_IE_TX_DMA_COMPLETE 0x0200 -#define IPG_IE_RX_DMA_COMPLETE 0x0400 -#define IPG_IE_RFD_LIST_END 0x0800 -#define IPG_IE_RX_DMA_PRIORITY 0x1000 - -/* IntStatus */ -#define IPG_IS_RSVD_MASK 0x1FFF -#define IPG_IS_INTERRUPT_STATUS 0x0001 -#define IPG_IS_HOST_ERROR 0x0002 -#define IPG_IS_TX_COMPLETE 0x0004 -#define IPG_IS_MAC_CTRL_FRAME 0x0008 -#define IPG_IS_RX_COMPLETE 0x0010 -#define IPG_IS_RX_EARLY 0x0020 -#define IPG_IS_INT_REQUESTED 0x0040 -#define IPG_IS_UPDATE_STATS 0x0080 -#define IPG_IS_LINK_EVENT 0x0100 -#define IPG_IS_TX_DMA_COMPLETE 0x0200 -#define IPG_IS_RX_DMA_COMPLETE 0x0400 -#define IPG_IS_RFD_LIST_END 0x0800 -#define IPG_IS_RX_DMA_PRIORITY 0x1000 - -/* MACCtrl */ -#define IPG_MC_RSVD_MASK 0x7FE33FA3 -#define IPG_MC_IFS_SELECT 0x00000003 -#define IPG_MC_IFS_4352BIT 0x00000003 -#define IPG_MC_IFS_1792BIT 0x00000002 -#define IPG_MC_IFS_1024BIT 0x00000001 -#define IPG_MC_IFS_96BIT 0x00000000 -#define IPG_MC_DUPLEX_SELECT 0x00000020 -#define IPG_MC_DUPLEX_SELECT_FD 0x00000020 -#define IPG_MC_DUPLEX_SELECT_HD 0x00000000 -#define IPG_MC_TX_FLOW_CONTROL_ENABLE 0x00000080 -#define IPG_MC_RX_FLOW_CONTROL_ENABLE 0x00000100 -#define IPG_MC_RCV_FCS 0x00000200 -#define IPG_MC_FIFO_LOOPBACK 0x00000400 -#define IPG_MC_MAC_LOOPBACK 0x00000800 -#define IPG_MC_AUTO_VLAN_TAGGING 0x00001000 -#define IPG_MC_AUTO_VLAN_UNTAGGING 0x00002000 -#define IPG_MC_COLLISION_DETECT 0x00010000 -#define IPG_MC_CARRIER_SENSE 0x00020000 -#define IPG_MC_STATISTICS_ENABLE 0x00200000 -#define IPG_MC_STATISTICS_DISABLE 0x00400000 -#define IPG_MC_STATISTICS_ENABLED 0x00800000 -#define IPG_MC_TX_ENABLE 0x01000000 -#define IPG_MC_TX_DISABLE 0x02000000 -#define IPG_MC_TX_ENABLED 0x04000000 -#define IPG_MC_RX_ENABLE 0x08000000 -#define IPG_MC_RX_DISABLE 0x10000000 -#define IPG_MC_RX_ENABLED 0x20000000 -#define IPG_MC_PAUSED 0x40000000 - -/* - * Tune - */ - -/* Assign IPG_APPEND_FCS_ON_TX > 0 for auto FCS append on TX. */ -#define IPG_APPEND_FCS_ON_TX 1 - -/* Assign IPG_APPEND_FCS_ON_TX > 0 for auto FCS strip on RX. */ -#define IPG_STRIP_FCS_ON_RX 1 - -/* Assign IPG_DROP_ON_RX_ETH_ERRORS > 0 to drop RX frames with - * Ethernet errors. - */ -#define IPG_DROP_ON_RX_ETH_ERRORS 1 - -/* Assign IPG_INSERT_MANUAL_VLAN_TAG > 0 to insert VLAN tags manually - * (via TFC). - */ -#define IPG_INSERT_MANUAL_VLAN_TAG 0 - -/* Assign IPG_ADD_IPCHECKSUM_ON_TX > 0 for auto IP checksum on TX. */ -#define IPG_ADD_IPCHECKSUM_ON_TX 0 - -/* Assign IPG_ADD_TCPCHECKSUM_ON_TX > 0 for auto TCP checksum on TX. - * DO NOT USE FOR SILICON REVISIONS B3 AND EARLIER. - */ -#define IPG_ADD_TCPCHECKSUM_ON_TX 0 - -/* Assign IPG_ADD_UDPCHECKSUM_ON_TX > 0 for auto UDP checksum on TX. - * DO NOT USE FOR SILICON REVISIONS B3 AND EARLIER. - */ -#define IPG_ADD_UDPCHECKSUM_ON_TX 0 - -/* If inserting VLAN tags manually, assign the IPG_MANUAL_VLAN_xx - * constants as desired. - */ -#define IPG_MANUAL_VLAN_VID 0xABC -#define IPG_MANUAL_VLAN_CFI 0x1 -#define IPG_MANUAL_VLAN_USERPRIORITY 0x5 - -#define IPG_IO_REG_RANGE 0xFF -#define IPG_MEM_REG_RANGE 0x154 -#define IPG_DRIVER_NAME "Sundance Technology IPG Triple-Speed Ethernet" -#define IPG_NIC_PHY_ADDRESS 0x01 -#define IPG_DMALIST_ALIGN_PAD 0x07 -#define IPG_MULTICAST_HASHTABLE_SIZE 0x40 - -/* Number of milliseconds to wait after issuing a software reset. - * 0x05 <= IPG_AC_RESETWAIT to account for proper 10Mbps operation. - */ -#define IPG_AC_RESETWAIT 0x05 - -/* Number of IPG_AC_RESETWAIT timeperiods before declaring timeout. */ -#define IPG_AC_RESET_TIMEOUT 0x0A - -/* Minimum number of nanoseconds used to toggle MDC clock during - * MII/GMII register access. - */ -#define IPG_PC_PHYCTRLWAIT_NS 200 - -#define IPG_TFDLIST_LENGTH 0x100 - -/* Number of frames between TxDMAComplete interrupt. - * 0 < IPG_FRAMESBETWEENTXDMACOMPLETES <= IPG_TFDLIST_LENGTH - */ -#define IPG_FRAMESBETWEENTXDMACOMPLETES 0x1 - -#define IPG_RFDLIST_LENGTH 0x100 - -/* Maximum number of RFDs to process per interrupt. - * 1 < IPG_MAXRFDPROCESS_COUNT < IPG_RFDLIST_LENGTH - */ -#define IPG_MAXRFDPROCESS_COUNT 0x80 - -/* Minimum margin between last freed RFD, and current RFD. - * 1 < IPG_MINUSEDRFDSTOFREE < IPG_RFDLIST_LENGTH - */ -#define IPG_MINUSEDRFDSTOFREE 0x80 - -/* specify the jumbo frame maximum size - * per unit is 0x600 (the rx_buffer size that one RFD can carry) - */ -#define MAX_JUMBOSIZE 0x8 /* max is 12K */ - -/* Key register values loaded at driver start up. */ - -/* TXDMAPollPeriod is specified in 320ns increments. - * - * Value Time - * --------------------- - * 0x00-0x01 320ns - * 0x03 ~1us - * 0x1F ~10us - * 0xFF ~82us - */ -#define IPG_TXDMAPOLLPERIOD_VALUE 0x26 - -/* TxDMAUrgentThresh specifies the minimum amount of - * data in the transmit FIFO before asserting an - * urgent transmit DMA request. - * - * Value Min TxFIFO occupied space before urgent TX request - * --------------------------------------------------------------- - * 0x00-0x04 128 bytes (1024 bits) - * 0x27 1248 bytes (~10000 bits) - * 0x30 1536 bytes (12288 bits) - * 0xFF 8192 bytes (65535 bits) - */ -#define IPG_TXDMAURGENTTHRESH_VALUE 0x04 - -/* TxDMABurstThresh specifies the minimum amount of - * free space in the transmit FIFO before asserting an - * transmit DMA request. - * - * Value Min TxFIFO free space before TX request - * ---------------------------------------------------- - * 0x00-0x08 256 bytes - * 0x30 1536 bytes - * 0xFF 8192 bytes - */ -#define IPG_TXDMABURSTTHRESH_VALUE 0x30 - -/* RXDMAPollPeriod is specified in 320ns increments. - * - * Value Time - * --------------------- - * 0x00-0x01 320ns - * 0x03 ~1us - * 0x1F ~10us - * 0xFF ~82us - */ -#define IPG_RXDMAPOLLPERIOD_VALUE 0x01 - -/* RxDMAUrgentThresh specifies the minimum amount of - * free space within the receive FIFO before asserting - * a urgent receive DMA request. - * - * Value Min RxFIFO free space before urgent RX request - * --------------------------------------------------------------- - * 0x00-0x04 128 bytes (1024 bits) - * 0x27 1248 bytes (~10000 bits) - * 0x30 1536 bytes (12288 bits) - * 0xFF 8192 bytes (65535 bits) - */ -#define IPG_RXDMAURGENTTHRESH_VALUE 0x30 - -/* RxDMABurstThresh specifies the minimum amount of - * occupied space within the receive FIFO before asserting - * a receive DMA request. - * - * Value Min TxFIFO free space before TX request - * ---------------------------------------------------- - * 0x00-0x08 256 bytes - * 0x30 1536 bytes - * 0xFF 8192 bytes - */ -#define IPG_RXDMABURSTTHRESH_VALUE 0x30 - -/* FlowOnThresh specifies the maximum amount of occupied - * space in the receive FIFO before a PAUSE frame with - * maximum pause time transmitted. - * - * Value Max RxFIFO occupied space before PAUSE - * --------------------------------------------------- - * 0x0000 0 bytes - * 0x0740 29,696 bytes - * 0x07FF 32,752 bytes - */ -#define IPG_FLOWONTHRESH_VALUE 0x0740 - -/* FlowOffThresh specifies the minimum amount of occupied - * space in the receive FIFO before a PAUSE frame with - * zero pause time is transmitted. - * - * Value Max RxFIFO occupied space before PAUSE - * --------------------------------------------------- - * 0x0000 0 bytes - * 0x00BF 3056 bytes - * 0x07FF 32,752 bytes - */ -#define IPG_FLOWOFFTHRESH_VALUE 0x00BF - -/* - * Miscellaneous macros. - */ - -/* Macros for printing debug statements. */ -#ifdef IPG_DEBUG -# define IPG_DEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DDEBUG_MSG(fmt, args...) \ - printk(KERN_DEBUG "IPG: " fmt, ##args) -# define IPG_DUMPRFDLIST(args) ipg_dump_rfdlist(args) -# define IPG_DUMPTFDLIST(args) ipg_dump_tfdlist(args) -#else -# define IPG_DEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DDEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DUMPRFDLIST(args) -# define IPG_DUMPTFDLIST(args) -#endif - -/* - * End miscellaneous macros. - */ - -/* Transmit Frame Descriptor. The IPG supports 15 fragments, - * however Linux requires only a single fragment. Note, each - * TFD field is 64 bits wide. - */ -struct ipg_tx { - __le64 next_desc; - __le64 tfc; - __le64 frag_info; -}; - -/* Receive Frame Descriptor. Note, each RFD field is 64 bits wide. - */ -struct ipg_rx { - __le64 next_desc; - __le64 rfs; - __le64 frag_info; -}; - -struct ipg_jumbo { - int found_start; - int current_size; - struct sk_buff *skb; -}; - -/* Structure of IPG NIC specific data. */ -struct ipg_nic_private { - void __iomem *ioaddr; - struct ipg_tx *txd; - struct ipg_rx *rxd; - dma_addr_t txd_map; - dma_addr_t rxd_map; - struct sk_buff *tx_buff[IPG_TFDLIST_LENGTH]; - struct sk_buff *rx_buff[IPG_RFDLIST_LENGTH]; - unsigned int tx_current; - unsigned int tx_dirty; - unsigned int rx_current; - unsigned int rx_dirty; - bool is_jumbo; - struct ipg_jumbo jumbo; - unsigned long rxfrag_size; - unsigned long rxsupport_size; - unsigned long max_rxframe_size; - unsigned int rx_buf_sz; - struct pci_dev *pdev; - struct net_device *dev; - struct net_device_stats stats; - spinlock_t lock; - int tenmbpsmode; - - u16 led_mode; - u16 station_addr[3]; /* Station Address in EEPROM Reg 0x10..0x12 */ - - struct mutex mii_mutex; - struct mii_if_info mii_if; - int reset_current_tfd; -#ifdef IPG_DEBUG - int RFDlistendCount; - int RFDListCheckedCount; - int EmptyRFDListCount; -#endif - struct delayed_work task; -}; - -#endif /* __LINUX_IPG_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 85f1b1e7e505..31c491e02e69 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -892,9 +892,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn; dev->caps.port_mask[i] = dev->caps.port_type[i]; dev->caps.phys_port_id[i] = func_cap.phys_port_id; - if (mlx4_get_slave_pkey_gid_tbl_len(dev, i, - &dev->caps.gid_table_len[i], - &dev->caps.pkey_table_len[i])) + err = mlx4_get_slave_pkey_gid_tbl_len(dev, i, + &dev->caps.gid_table_len[i], + &dev->caps.pkey_table_len[i]); + if (err) goto err_mem; } @@ -906,6 +907,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.uar_page_size * dev->caps.num_uars, (unsigned long long) pci_resource_len(dev->persist->pdev, 2)); + err = -ENOMEM; goto err_mem; } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 9813d34f3e5b..6fec3e993d02 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4952,26 +4952,41 @@ static void rem_slave_counters(struct mlx4_dev *dev, int slave) struct res_counter *counter; struct res_counter *tmp; int err; - int index; + int *counters_arr = NULL; + int i, j; err = move_all_busy(dev, slave, RES_COUNTER); if (err) mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n", slave); - spin_lock_irq(mlx4_tlock(dev)); - list_for_each_entry_safe(counter, tmp, counter_list, com.list) { - if (counter->com.owner == slave) { - index = counter->com.res_id; - rb_erase(&counter->com.node, - &tracker->res_tree[RES_COUNTER]); - list_del(&counter->com.list); - kfree(counter); - __mlx4_counter_free(dev, index); + counters_arr = kmalloc_array(dev->caps.max_counters, + sizeof(*counters_arr), GFP_KERNEL); + if (!counters_arr) + return; + + do { + i = 0; + j = 0; + spin_lock_irq(mlx4_tlock(dev)); + list_for_each_entry_safe(counter, tmp, counter_list, com.list) { + if (counter->com.owner == slave) { + counters_arr[i++] = counter->com.res_id; + rb_erase(&counter->com.node, + &tracker->res_tree[RES_COUNTER]); + list_del(&counter->com.list); + kfree(counter); + } + } + spin_unlock_irq(mlx4_tlock(dev)); + + while (j < i) { + __mlx4_counter_free(dev, counters_arr[j++]); mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0); } - } - spin_unlock_irq(mlx4_tlock(dev)); + } while (i); + + kfree(counters_arr); } static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f2ae62dd8c09..22e72bf1ae48 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -334,9 +334,15 @@ struct mlx5e_tx_skb_cb { #define MLX5E_TX_SKB_CB(__skb) ((struct mlx5e_tx_skb_cb *)__skb->cb) +enum mlx5e_dma_map_type { + MLX5E_DMA_MAP_SINGLE, + MLX5E_DMA_MAP_PAGE +}; + struct mlx5e_sq_dma { - dma_addr_t addr; - u32 size; + dma_addr_t addr; + u32 size; + enum mlx5e_dma_map_type type; }; enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5fc4d2d78cdf..1e52db32c73d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1332,6 +1332,42 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) return err; } +static int mlx5e_refresh_tir_self_loopback_enable(struct mlx5_core_dev *mdev, + u32 tirn) +{ + void *in; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); + + err = mlx5_core_modify_tir(mdev, tirn, in, inlen); + + kvfree(in); + + return err; +} + +static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv) +{ + int err; + int i; + + for (i = 0; i < MLX5E_NUM_TT; i++) { + err = mlx5e_refresh_tir_self_loopback_enable(priv->mdev, + priv->tirn[i]); + if (err) + return err; + } + + return 0; +} + static int mlx5e_set_dev_port_mtu(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -1376,6 +1412,13 @@ int mlx5e_open_locked(struct net_device *netdev) goto err_clear_state_opened_flag; } + err = mlx5e_refresh_tirs_self_loopback_enable(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n", + __func__, err); + goto err_close_channels; + } + mlx5e_update_carrier(priv); mlx5e_redirect_rqts(priv); @@ -1383,6 +1426,8 @@ int mlx5e_open_locked(struct net_device *netdev) return 0; +err_close_channels: + mlx5e_close_channels(priv); err_clear_state_opened_flag: clear_bit(MLX5E_STATE_OPENED, &priv->state); return err; @@ -1856,6 +1901,8 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + max_mtu = MLX5E_HW2SW_MTU(max_mtu); + if (new_mtu > max_mtu) { netdev_err(netdev, "%s: Bad MTU (%d) > (%d) Max\n", @@ -1909,6 +1956,9 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) "Not creating net device, some required device capabilities are missing\n"); return -ENOTSUPP; } + if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) + mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index cd8f85a251d7..1341b1d3c421 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -61,39 +61,47 @@ void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw) } } -static void mlx5e_dma_pop_last_pushed(struct mlx5e_sq *sq, dma_addr_t *addr, - u32 *size) +static inline void mlx5e_tx_dma_unmap(struct device *pdev, + struct mlx5e_sq_dma *dma) { - sq->dma_fifo_pc--; - *addr = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr; - *size = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size; -} - -static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) -{ - dma_addr_t addr; - u32 size; - int i; - - for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { - mlx5e_dma_pop_last_pushed(sq, &addr, &size); - dma_unmap_single(sq->pdev, addr, size, DMA_TO_DEVICE); + switch (dma->type) { + case MLX5E_DMA_MAP_SINGLE: + dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + break; + case MLX5E_DMA_MAP_PAGE: + dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + break; + default: + WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n"); } } -static inline void mlx5e_dma_push(struct mlx5e_sq *sq, dma_addr_t addr, - u32 size) +static inline void mlx5e_dma_push(struct mlx5e_sq *sq, + dma_addr_t addr, + u32 size, + enum mlx5e_dma_map_type map_type) { sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr = addr; sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size = size; + sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].type = map_type; sq->dma_fifo_pc++; } -static inline void mlx5e_dma_get(struct mlx5e_sq *sq, u32 i, dma_addr_t *addr, - u32 *size) +static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i) { - *addr = sq->dma_fifo[i & sq->dma_fifo_mask].addr; - *size = sq->dma_fifo[i & sq->dma_fifo_mask].size; + return &sq->dma_fifo[i & sq->dma_fifo_mask]; +} + +static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) +{ + int i; + + for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { + struct mlx5e_sq_dma *last_pushed_dma = + mlx5e_dma_get(sq, --sq->dma_fifo_pc); + + mlx5e_tx_dma_unmap(sq->pdev, last_pushed_dma); + } } u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, @@ -118,8 +126,15 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, */ #define MLX5E_MIN_INLINE ETH_HLEN - if (bf && (skb_headlen(skb) <= sq->max_inline)) - return skb_headlen(skb); + if (bf) { + u16 ihs = skb_headlen(skb); + + if (skb_vlan_tag_present(skb)) + ihs += VLAN_HLEN; + + if (ihs <= sq->max_inline) + return skb_headlen(skb); + } return MLX5E_MIN_INLINE; } @@ -218,7 +233,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(headlen); - mlx5e_dma_push(sq, dma_addr, headlen); + mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE); MLX5E_TX_SKB_CB(skb)->num_dma++; dseg++; @@ -237,7 +252,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(fsz); - mlx5e_dma_push(sq, dma_addr, fsz); + mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); MLX5E_TX_SKB_CB(skb)->num_dma++; dseg++; @@ -353,13 +368,10 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) } for (j = 0; j < MLX5E_TX_SKB_CB(skb)->num_dma; j++) { - dma_addr_t addr; - u32 size; + struct mlx5e_sq_dma *dma = + mlx5e_dma_get(sq, dma_fifo_cc++); - mlx5e_dma_get(sq, dma_fifo_cc, &addr, &size); - dma_fifo_cc++; - dma_unmap_single(sq->pdev, addr, size, - DMA_TO_DEVICE); + mlx5e_tx_dma_unmap(sq->pdev, dma); } npkts++; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b4f21232019a..79ef799f88ab 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7429,15 +7429,15 @@ process_pkt: rtl8169_rx_vlan_tag(desc, skb); + if (skb->pkt_type == PACKET_MULTICAST) + dev->stats.multicast++; + napi_gro_receive(&tp->napi, skb); u64_stats_update_begin(&tp->rx_stats.syncp); tp->rx_stats.packets++; tp->rx_stats.bytes += pkt_size; u64_stats_update_end(&tp->rx_stats.syncp); - - if (skb->pkt_type == PACKET_MULTICAST) - dev->stats.multicast++; } release_descriptor: desc->opts2 = 0; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index aa7b2083cb53..ee8d1ec61fab 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -408,8 +408,6 @@ static int ravb_dmac_init(struct net_device *ndev) /* Interrupt enable: */ /* Frame receive */ ravb_write(ndev, RIC0_FRE0 | RIC0_FRE1, RIC0); - /* Receive FIFO full warning */ - ravb_write(ndev, RIC1_RFWE, RIC1); /* Receive FIFO full error, descriptor empty */ ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2); /* Frame transmitted, timestamp FIFO updated */ @@ -733,8 +731,10 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id) ((tis & tic) & BIT(q))) { if (napi_schedule_prep(&priv->napi[q])) { /* Mask RX and TX interrupts */ - ravb_write(ndev, ric0 & ~BIT(q), RIC0); - ravb_write(ndev, tic & ~BIT(q), TIC); + ric0 &= ~BIT(q); + tic &= ~BIT(q); + ravb_write(ndev, ric0, RIC0); + ravb_write(ndev, tic, TIC); __napi_schedule(&priv->napi[q]); } else { netdev_warn(ndev, diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index d288f1c928de..a3c42a376741 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -3422,7 +3422,7 @@ out: * with our request for slot reset the mmio_enabled callback will never be * called, and the link_reset callback is not used by AER or EEH mechanisms. */ -static struct pci_error_handlers efx_err_handlers = { +static const struct pci_error_handlers efx_err_handlers = { .error_detected = efx_io_error_detected, .slot_reset = efx_io_slot_reset, .resume = efx_io_resume, diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index c860c9007e49..219a99b7a631 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -809,22 +809,17 @@ static int smsc911x_phy_check_loopbackpkt(struct smsc911x_data *pdata) static int smsc911x_phy_reset(struct smsc911x_data *pdata) { - struct phy_device *phy_dev = pdata->phy_dev; unsigned int temp; unsigned int i = 100000; - BUG_ON(!phy_dev); - BUG_ON(!phy_dev->bus); - - SMSC_TRACE(pdata, hw, "Performing PHY BCR Reset"); - smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, BMCR_RESET); + temp = smsc911x_reg_read(pdata, PMT_CTRL); + smsc911x_reg_write(pdata, PMT_CTRL, temp | PMT_CTRL_PHY_RST_); do { msleep(1); - temp = smsc911x_mii_read(phy_dev->bus, phy_dev->addr, - MII_BMCR); - } while ((i--) && (temp & BMCR_RESET)); + temp = smsc911x_reg_read(pdata, PMT_CTRL); + } while ((i--) && (temp & PMT_CTRL_PHY_RST_)); - if (temp & BMCR_RESET) { + if (unlikely(temp & PMT_CTRL_PHY_RST_)) { SMSC_WARN(pdata, hw, "PHY reset failed to complete"); return -EIO; } @@ -2296,7 +2291,7 @@ static int smsc911x_init(struct net_device *dev) } /* Reset the LAN911x */ - if (smsc911x_soft_reset(pdata)) + if (smsc911x_phy_reset(pdata) || smsc911x_soft_reset(pdata)) return -ENODEV; dev->flags |= IFF_MULTICAST; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 9d89bdbf029f..82de68b1a452 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -337,11 +337,11 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) QSGMII_PHY_RX_SIGNAL_DETECT_EN | QSGMII_PHY_TX_DRIVER_EN | QSGMII_PHY_QSGMII_EN | - 0x4 << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | - 0x3 << QSGMII_PHY_RX_DC_BIAS_OFFSET | - 0x1 << QSGMII_PHY_RX_INPUT_EQU_OFFSET | - 0x2 << QSGMII_PHY_CDR_PI_SLEW_OFFSET | - 0xC << QSGMII_PHY_TX_DRV_AMP_OFFSET); + 0x4ul << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | + 0x3ul << QSGMII_PHY_RX_DC_BIAS_OFFSET | + 0x1ul << QSGMII_PHY_RX_INPUT_EQU_OFFSET | + 0x2ul << QSGMII_PHY_CDR_PI_SLEW_OFFSET | + 0xCul << QSGMII_PHY_TX_DRV_AMP_OFFSET); } plat_dat->has_gmac = true; diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index ae68afd50a15..f38696ceee74 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -345,13 +345,6 @@ VELOCITY_PARAM(flow_control, "Enable flow control ability"); */ VELOCITY_PARAM(speed_duplex, "Setting the speed and duplex mode"); -#define VAL_PKT_LEN_DEF 0 -/* ValPktLen[] is used for setting the checksum offload ability of NIC. - 0: Receive frame with invalid layer 2 length (Default) - 1: Drop frame with invalid layer 2 length -*/ -VELOCITY_PARAM(ValPktLen, "Receiving or Drop invalid 802.3 frame"); - #define WOL_OPT_DEF 0 #define WOL_OPT_MIN 0 #define WOL_OPT_MAX 7 @@ -494,7 +487,6 @@ static void velocity_get_options(struct velocity_opt *opts, int index, velocity_set_int_opt(&opts->flow_cntl, flow_control[index], FLOW_CNTL_MIN, FLOW_CNTL_MAX, FLOW_CNTL_DEF, "flow_control", devname); velocity_set_bool_opt(&opts->flags, IP_byte_align[index], IP_ALIG_DEF, VELOCITY_FLAGS_IP_ALIGN, "IP_byte_align", devname); - velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname); velocity_set_int_opt((int *) &opts->spd_dpx, speed_duplex[index], MED_LNK_MIN, MED_LNK_MAX, MED_LNK_DEF, "Media link mode", devname); velocity_set_int_opt(&opts->wol_opts, wol_opts[index], WOL_OPT_MIN, WOL_OPT_MAX, WOL_OPT_DEF, "Wake On Lan options", devname); opts->numrx = (opts->numrx & ~3); @@ -2055,8 +2047,9 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) int pkt_len = le16_to_cpu(rd->rdesc0.len) & 0x3fff; struct sk_buff *skb; - if (rd->rdesc0.RSR & (RSR_STP | RSR_EDP)) { - VELOCITY_PRT(MSG_LEVEL_VERBOSE, KERN_ERR " %s : the received frame spans multiple RDs.\n", vptr->netdev->name); + if (unlikely(rd->rdesc0.RSR & (RSR_STP | RSR_EDP | RSR_RL))) { + if (rd->rdesc0.RSR & (RSR_STP | RSR_EDP)) + VELOCITY_PRT(MSG_LEVEL_VERBOSE, KERN_ERR " %s : the received frame spans multiple RDs.\n", vptr->netdev->name); stats->rx_length_errors++; return -EINVAL; } @@ -2069,17 +2062,6 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) dma_sync_single_for_cpu(vptr->dev, rd_info->skb_dma, vptr->rx.buf_sz, DMA_FROM_DEVICE); - /* - * Drop frame not meeting IEEE 802.3 - */ - - if (vptr->flags & VELOCITY_FLAGS_VAL_PKT_LEN) { - if (rd->rdesc0.RSR & RSR_RL) { - stats->rx_length_errors++; - return -EINVAL; - } - } - velocity_rx_csum(rd, skb); if (velocity_rx_copy(&skb, pkt_len, vptr) < 0) { diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index bb8b5304d851..b103adb8d62e 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -599,7 +599,7 @@ int fjes_hw_unregister_buff_addr(struct fjes_hw *hw, int dest_epid) FJES_CMD_REQ_RES_CODE_BUSY) && (timeout > 0)) { msleep(200 + hw->my_epid * 20); - timeout -= (200 + hw->my_epid * 20); + timeout -= (200 + hw->my_epid * 20); res_buf->unshare_buffer.length = 0; res_buf->unshare_buffer.code = 0; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index d50887e3df6d..8c48bb2a94ea 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -254,7 +254,7 @@ acct: } } -static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, +static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb, bool local) { struct ipvl_dev *ipvlan = addr->master; @@ -262,6 +262,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, unsigned int len; rx_handler_result_t ret = RX_HANDLER_CONSUMED; bool success = false; + struct sk_buff *skb = *pskb; len = skb->len + ETH_HLEN; if (unlikely(!(dev->flags & IFF_UP))) { @@ -273,6 +274,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, if (!skb) goto out; + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; @@ -486,7 +488,7 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) - return ipvlan_rcv_frame(addr, skb, true); + return ipvlan_rcv_frame(addr, &skb, true); out: skb->dev = ipvlan->phy_dev; @@ -506,7 +508,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) - return ipvlan_rcv_frame(addr, skb, true); + return ipvlan_rcv_frame(addr, &skb, true); } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) @@ -589,7 +591,7 @@ static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb, addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) - ret = ipvlan_rcv_frame(addr, skb, false); + ret = ipvlan_rcv_frame(addr, pskb, false); out: return ret; @@ -626,7 +628,7 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) - ret = ipvlan_rcv_frame(addr, skb, false); + ret = ipvlan_rcv_frame(addr, pskb, false); } return ret; @@ -651,5 +653,5 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n", port->mode); kfree_skb(skb); - return NET_RX_DROP; + return RX_HANDLER_CONSUMED; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 86f6c6292c27..06c8bfeaccd6 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -415,6 +415,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; + *pskb = skb; eth = eth_hdr(skb); macvlan_forward_source(skb, port, eth->h_source); src = macvlan_hash_lookup(port, eth->h_source); @@ -456,6 +457,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) goto out; } + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index fabf11d32d27..2d020a3ec0b5 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -308,6 +308,8 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_HAS_INTERRUPT, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, .driver = { .owner = THIS_MODULE, }, @@ -327,6 +329,8 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_HAS_INTERRUPT, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, .driver = { .owner = THIS_MODULE, }, diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 5de8d5827536..0240552b50f3 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1154,6 +1154,21 @@ static struct phy_driver marvell_drivers[] = { .driver = { .owner = THIS_MODULE }, }, { + .phy_id = MARVELL_PHY_ID_88E1540, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "Marvell 88E1540", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_aneg = &m88e1510_config_aneg, + .read_status = &marvell_read_status, + .ack_interrupt = &marvell_ack_interrupt, + .config_intr = &marvell_config_intr, + .did_interrupt = &m88e1121_did_interrupt, + .resume = &genphy_resume, + .suspend = &genphy_suspend, + .driver = { .owner = THIS_MODULE }, + }, + { .phy_id = MARVELL_PHY_ID_88E3016, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E3016", @@ -1186,6 +1201,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1318S, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1116R, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1510, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1540, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index adb48abafc87..48ce6ef400fe 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -863,6 +863,9 @@ void phy_state_machine(struct work_struct *work) needs_aneg = true; break; case PHY_NOLINK: + if (phy_interrupt_is_valid(phydev)) + break; + err = phy_read_status(phydev); if (err) break; diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 76cad712ddb2..dd295dbaa074 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -66,6 +66,7 @@ #define PHY_ID_VSC8244 0x000fc6c0 #define PHY_ID_VSC8514 0x00070670 #define PHY_ID_VSC8574 0x000704a0 +#define PHY_ID_VSC8601 0x00070420 #define PHY_ID_VSC8662 0x00070660 #define PHY_ID_VSC8221 0x000fc550 #define PHY_ID_VSC8211 0x000fc4b0 @@ -133,7 +134,8 @@ static int vsc82xx_config_intr(struct phy_device *phydev) (phydev->drv->phy_id == PHY_ID_VSC8234 || phydev->drv->phy_id == PHY_ID_VSC8244 || phydev->drv->phy_id == PHY_ID_VSC8514 || - phydev->drv->phy_id == PHY_ID_VSC8574) ? + phydev->drv->phy_id == PHY_ID_VSC8574 || + phydev->drv->phy_id == PHY_ID_VSC8601) ? MII_VSC8244_IMASK_MASK : MII_VSC8221_IMASK_MASK); else { @@ -272,6 +274,18 @@ static struct phy_driver vsc82xx_driver[] = { .config_intr = &vsc82xx_config_intr, .driver = { .owner = THIS_MODULE,}, }, { + .phy_id = PHY_ID_VSC8601, + .name = "Vitesse VSC8601", + .phy_id_mask = 0x000ffff0, + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = &genphy_config_init, + .config_aneg = &genphy_config_aneg, + .read_status = &genphy_read_status, + .ack_interrupt = &vsc824x_ack_interrupt, + .config_intr = &vsc82xx_config_intr, + .driver = { .owner = THIS_MODULE,}, +}, { .phy_id = PHY_ID_VSC8662, .name = "Vitesse VSC8662", .phy_id_mask = 0x000ffff0, diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c78d3cb1b464..3da70bf9936a 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -696,6 +696,11 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (kernel_ulong_t) &wwan_info, }, { + /* Dell DW5580 modules */ + USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, 0x81ba, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = (kernel_ulong_t)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 46f4caddccbe..899ea4288197 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2157,12 +2157,13 @@ vmxnet3_set_mc(struct net_device *netdev) if (!netdev_mc_empty(netdev)) { new_table = vmxnet3_copy_mc(netdev); if (new_table) { - rxConf->mfTableLen = cpu_to_le16( - netdev_mc_count(netdev) * ETH_ALEN); + size_t sz = netdev_mc_count(netdev) * ETH_ALEN; + + rxConf->mfTableLen = cpu_to_le16(sz); new_table_pa = dma_map_single( &adapter->pdev->dev, new_table, - rxConf->mfTableLen, + sz, PCI_DMA_TODEVICE); } diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 3f859a55c035..4c58c83dc225 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.3.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.4.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040300 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040400 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 548a18916a31..a831d18596a5 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -1080,28 +1080,10 @@ void __init chsc_init_cleanup(void) free_page((unsigned long)sei_page); } -int chsc_enable_facility(int operation_code) +int __chsc_enable_facility(struct chsc_sda_area *sda_area, int operation_code) { - unsigned long flags; int ret; - struct { - struct chsc_header request; - u8 reserved1:4; - u8 format:4; - u8 reserved2; - u16 operation_code; - u32 reserved3; - u32 reserved4; - u32 operation_data_area[252]; - struct chsc_header response; - u32 reserved5:4; - u32 format2:4; - u32 reserved6:24; - } __attribute__ ((packed)) *sda_area; - spin_lock_irqsave(&chsc_page_lock, flags); - memset(chsc_page, 0, PAGE_SIZE); - sda_area = chsc_page; sda_area->request.length = 0x0400; sda_area->request.code = 0x0031; sda_area->operation_code = operation_code; @@ -1119,10 +1101,25 @@ int chsc_enable_facility(int operation_code) default: ret = chsc_error_from_response(sda_area->response.code); } +out: + return ret; +} + +int chsc_enable_facility(int operation_code) +{ + struct chsc_sda_area *sda_area; + unsigned long flags; + int ret; + + spin_lock_irqsave(&chsc_page_lock, flags); + memset(chsc_page, 0, PAGE_SIZE); + sda_area = chsc_page; + + ret = __chsc_enable_facility(sda_area, operation_code); if (ret != 0) CIO_CRW_EVENT(2, "chsc: sda (oc=%x) failed (rc=%04x)\n", operation_code, sda_area->response.code); -out: + spin_unlock_irqrestore(&chsc_page_lock, flags); return ret; } diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h index 76c9b50700b2..0de134c3a204 100644 --- a/drivers/s390/cio/chsc.h +++ b/drivers/s390/cio/chsc.h @@ -115,6 +115,20 @@ struct chsc_scpd { u8 data[PAGE_SIZE - 20]; } __attribute__ ((packed)); +struct chsc_sda_area { + struct chsc_header request; + u8 :4; + u8 format:4; + u8 :8; + u16 operation_code; + u32 :32; + u32 :32; + u32 operation_data_area[252]; + struct chsc_header response; + u32 :4; + u32 format2:4; + u32 :24; +} __packed __aligned(PAGE_SIZE); extern int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd); @@ -122,6 +136,7 @@ extern int chsc_determine_css_characteristics(void); extern int chsc_init(void); extern void chsc_init_cleanup(void); +int __chsc_enable_facility(struct chsc_sda_area *sda_area, int operation_code); extern int chsc_enable_facility(int); struct channel_subsystem; extern int chsc_secm(struct channel_subsystem *, int); diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index b5620e818d6b..690b8547e828 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -925,18 +925,32 @@ void reipl_ccw_dev(struct ccw_dev_id *devid) int __init cio_get_iplinfo(struct cio_iplinfo *iplinfo) { + static struct chsc_sda_area sda_area __initdata; struct subchannel_id schid; struct schib schib; schid = *(struct subchannel_id *)&S390_lowcore.subchannel_id; if (!schid.one) return -ENODEV; + + if (schid.ssid) { + /* + * Firmware should have already enabled MSS but whoever started + * the kernel might have initiated a channel subsystem reset. + * Ensure that MSS is enabled. + */ + memset(&sda_area, 0, sizeof(sda_area)); + if (__chsc_enable_facility(&sda_area, CHSC_SDA_OC_MSS)) + return -ENODEV; + } if (stsch_err(schid, &schib)) return -ENODEV; if (schib.pmcw.st != SUBCHANNEL_TYPE_IO) return -ENODEV; if (!schib.pmcw.dnv) return -ENODEV; + + iplinfo->ssid = schid.ssid; iplinfo->devno = schib.pmcw.dev; iplinfo->is_qdio = schib.pmcw.qf; return 0; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 2ee3053bdc12..489e703dc82d 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -702,17 +702,12 @@ css_generate_pgid(struct channel_subsystem *css, u32 tod_high) css->global_pgid.pgid_high.ext_cssid.version = 0x80; css->global_pgid.pgid_high.ext_cssid.cssid = css->cssid; } else { -#ifdef CONFIG_SMP css->global_pgid.pgid_high.cpu_addr = stap(); -#else - css->global_pgid.pgid_high.cpu_addr = 0; -#endif } get_cpu_id(&cpu_id); css->global_pgid.cpu_id = cpu_id.ident; css->global_pgid.cpu_model = cpu_id.machine; css->global_pgid.tod_high = tod_high; - } static void diff --git a/drivers/s390/crypto/Makefile b/drivers/s390/crypto/Makefile index 57f710b3c8a4..b8ab18676e69 100644 --- a/drivers/s390/crypto/Makefile +++ b/drivers/s390/crypto/Makefile @@ -3,6 +3,9 @@ # ap-objs := ap_bus.o -obj-$(CONFIG_ZCRYPT) += ap.o zcrypt_api.o zcrypt_pcixcc.o -obj-$(CONFIG_ZCRYPT) += zcrypt_cex2a.o zcrypt_cex4.o +# zcrypt_api depends on ap +obj-$(CONFIG_ZCRYPT) += ap.o zcrypt_api.o +# msgtype* depend on zcrypt_api obj-$(CONFIG_ZCRYPT) += zcrypt_msgtype6.o zcrypt_msgtype50.o +# adapter drivers depend on ap, zcrypt_api and msgtype* +obj-$(CONFIG_ZCRYPT) += zcrypt_pcixcc.o zcrypt_cex2a.o zcrypt_cex4.o diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 9cb3dfbcaddb..61f768518a34 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -74,6 +74,7 @@ static struct device *ap_root_device = NULL; static struct ap_config_info *ap_configuration; static DEFINE_SPINLOCK(ap_device_list_lock); static LIST_HEAD(ap_device_list); +static bool initialised; /* * Workqueue timer for bus rescan. @@ -1384,6 +1385,9 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner, { struct device_driver *drv = &ap_drv->driver; + if (!initialised) + return -ENODEV; + drv->bus = &ap_bus_type; drv->probe = ap_device_probe; drv->remove = ap_device_remove; @@ -1808,6 +1812,7 @@ int __init ap_module_init(void) goto out_pm; queue_work(system_long_wq, &ap_scan_work); + initialised = true; return 0; @@ -1837,6 +1842,7 @@ void ap_module_exit(void) { int i; + initialised = false; ap_reset_domain(); ap_poll_thread_stop(); del_timer_sync(&ap_config_timer); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index a9603ebbc1f8..9f8fa42c062c 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -317,11 +317,9 @@ EXPORT_SYMBOL(zcrypt_device_unregister); void zcrypt_msgtype_register(struct zcrypt_ops *zops) { - if (zops->owner) { - spin_lock_bh(&zcrypt_ops_list_lock); - list_add_tail(&zops->list, &zcrypt_ops_list); - spin_unlock_bh(&zcrypt_ops_list_lock); - } + spin_lock_bh(&zcrypt_ops_list_lock); + list_add_tail(&zops->list, &zcrypt_ops_list); + spin_unlock_bh(&zcrypt_ops_list_lock); } EXPORT_SYMBOL(zcrypt_msgtype_register); @@ -342,7 +340,7 @@ struct zcrypt_ops *__ops_lookup(unsigned char *name, int variant) spin_lock_bh(&zcrypt_ops_list_lock); list_for_each_entry(zops, &zcrypt_ops_list, list) { if ((zops->variant == variant) && - (!strncmp(zops->owner->name, name, MODULE_NAME_LEN))) { + (!strncmp(zops->name, name, sizeof(zops->name)))) { found = 1; break; } diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 750876891931..38618f05ad92 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -96,6 +96,7 @@ struct zcrypt_ops { struct list_head list; /* zcrypt ops list. */ struct module *owner; int variant; + char name[128]; }; struct zcrypt_device { diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 71ceee9137a8..74edf2934e7c 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -513,6 +513,7 @@ static struct zcrypt_ops zcrypt_msgtype50_ops = { .rsa_modexpo = zcrypt_cex2a_modexpo, .rsa_modexpo_crt = zcrypt_cex2a_modexpo_crt, .owner = THIS_MODULE, + .name = MSGTYPE50_NAME, .variant = MSGTYPE50_VARIANT_DEFAULT, }; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 74762214193b..9a2dd472c1cc 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1119,6 +1119,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_device *zdev, */ static struct zcrypt_ops zcrypt_msgtype6_norng_ops = { .owner = THIS_MODULE, + .name = MSGTYPE06_NAME, .variant = MSGTYPE06_VARIANT_NORNG, .rsa_modexpo = zcrypt_msgtype6_modexpo, .rsa_modexpo_crt = zcrypt_msgtype6_modexpo_crt, @@ -1127,6 +1128,7 @@ static struct zcrypt_ops zcrypt_msgtype6_norng_ops = { static struct zcrypt_ops zcrypt_msgtype6_ops = { .owner = THIS_MODULE, + .name = MSGTYPE06_NAME, .variant = MSGTYPE06_VARIANT_DEFAULT, .rsa_modexpo = zcrypt_msgtype6_modexpo, .rsa_modexpo_crt = zcrypt_msgtype6_modexpo_crt, @@ -1136,6 +1138,7 @@ static struct zcrypt_ops zcrypt_msgtype6_ops = { static struct zcrypt_ops zcrypt_msgtype6_ep11_ops = { .owner = THIS_MODULE, + .name = MSGTYPE06_NAME, .variant = MSGTYPE06_VARIANT_EP11, .rsa_modexpo = NULL, .rsa_modexpo_crt = NULL, |