Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2016-2019 HabanaLabs, Ltd. * All Rights Reserved. */ #include "habanalabs.h" #include <linux/slab.h> /** * struct hl_eqe_work - This structure is used to schedule work of EQ * entry and cpucp_reset event * * @eq_work: workqueue object to run when EQ entry is received * @hdev: pointer to device structure * @eq_entry: copy of the EQ entry */ struct hl_eqe_work { struct work_struct eq_work; struct hl_device *hdev; struct hl_eq_entry eq_entry; }; /** * hl_cq_inc_ptr - increment ci or pi of cq * * @ptr: the current ci or pi value of the completion queue * * Increment ptr by 1. If it reaches the number of completion queue * entries, set it to 0 */ inline u32 hl_cq_inc_ptr(u32 ptr) { ptr++; if (unlikely(ptr == HL_CQ_LENGTH)) ptr = 0; return ptr; } /** * hl_eq_inc_ptr - increment ci of eq * * @ptr: the current ci value of the event queue * * Increment ptr by 1. If it reaches the number of event queue * entries, set it to 0 */ static inline u32 hl_eq_inc_ptr(u32 ptr) { ptr++; if (unlikely(ptr == HL_EQ_LENGTH)) ptr = 0; return ptr; } static void irq_handle_eqe(struct work_struct *work) { struct hl_eqe_work *eqe_work = container_of(work, struct hl_eqe_work, eq_work); struct hl_device *hdev = eqe_work->hdev; hdev->asic_funcs->handle_eqe(hdev, &eqe_work->eq_entry); kfree(eqe_work); } /** * hl_irq_handler_cq - irq handler for completion queue * * @irq: irq number * @arg: pointer to completion queue structure * */ irqreturn_t hl_irq_handler_cq(int irq, void *arg) { struct hl_cq *cq = arg; struct hl_device *hdev = cq->hdev; struct hl_hw_queue *queue; struct hl_cs_job *job; bool shadow_index_valid; u16 shadow_index; struct hl_cq_entry *cq_entry, *cq_base; if (hdev->disabled) { dev_dbg(hdev->dev, "Device disabled but received IRQ %d for CQ %d\n", irq, cq->hw_queue_id); return IRQ_HANDLED; } cq_base = cq->kernel_address; while (1) { bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) & CQ_ENTRY_READY_MASK) >> CQ_ENTRY_READY_SHIFT); if (!entry_ready) break; cq_entry = (struct hl_cq_entry *) &cq_base[cq->ci]; /* Make sure we read CQ entry contents after we've * checked the ownership bit. */ dma_rmb(); shadow_index_valid = ((le32_to_cpu(cq_entry->data) & CQ_ENTRY_SHADOW_INDEX_VALID_MASK) >> CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT); shadow_index = (u16) ((le32_to_cpu(cq_entry->data) & CQ_ENTRY_SHADOW_INDEX_MASK) >> CQ_ENTRY_SHADOW_INDEX_SHIFT); queue = &hdev->kernel_queues[cq->hw_queue_id]; if ((shadow_index_valid) && (!hdev->disabled)) { job = queue->shadow_queue[hl_pi_2_offset(shadow_index)]; queue_work(hdev->cq_wq[cq->cq_idx], &job->finish_work); } atomic_inc(&queue->ci); /* Clear CQ entry ready bit */ cq_entry->data = cpu_to_le32(le32_to_cpu(cq_entry->data) & ~CQ_ENTRY_READY_MASK); cq->ci = hl_cq_inc_ptr(cq->ci); /* Increment free slots */ atomic_inc(&cq->free_slots_cnt); } return IRQ_HANDLED; } static void handle_user_cq(struct hl_device *hdev, struct hl_user_interrupt *user_cq) { struct hl_user_pending_interrupt *pend; spin_lock(&user_cq->wait_list_lock); list_for_each_entry(pend, &user_cq->wait_list_head, wait_list_node) complete_all(&pend->fence.completion); spin_unlock(&user_cq->wait_list_lock); } /** * hl_irq_handler_user_cq - irq handler for user completion queues * * @irq: irq number * @arg: pointer to user interrupt structure * */ irqreturn_t hl_irq_handler_user_cq(int irq, void *arg) { struct hl_user_interrupt *user_cq = arg; struct hl_device *hdev = user_cq->hdev; dev_dbg(hdev->dev, "got user completion interrupt id %u", user_cq->interrupt_id); /* Handle user cq interrupts registered on all interrupts */ handle_user_cq(hdev, &hdev->common_user_interrupt); /* Handle user cq interrupts registered on this specific interrupt */ handle_user_cq(hdev, user_cq); return IRQ_HANDLED; } /** * hl_irq_handler_default - default irq handler * * @irq: irq number * @arg: pointer to user interrupt structure * */ irqreturn_t hl_irq_handler_default(int irq, void *arg) { struct hl_user_interrupt *user_interrupt = arg; struct hl_device *hdev = user_interrupt->hdev; u32 interrupt_id = user_interrupt->interrupt_id; dev_err(hdev->dev, "got invalid user interrupt %u", interrupt_id); return IRQ_HANDLED; } /** * hl_irq_handler_eq - irq handler for event queue * * @irq: irq number * @arg: pointer to event queue structure * */ irqreturn_t hl_irq_handler_eq(int irq, void *arg) { struct hl_eq *eq = arg; struct hl_device *hdev = eq->hdev; struct hl_eq_entry *eq_entry; struct hl_eq_entry *eq_base; struct hl_eqe_work *handle_eqe_work; eq_base = eq->kernel_address; while (1) { bool entry_ready = ((le32_to_cpu(eq_base[eq->ci].hdr.ctl) & EQ_CTL_READY_MASK) >> EQ_CTL_READY_SHIFT); if (!entry_ready) break; eq_entry = &eq_base[eq->ci]; /* * Make sure we read EQ entry contents after we've * checked the ownership bit. */ dma_rmb(); if (hdev->disabled) { dev_warn(hdev->dev, "Device disabled but received IRQ %d for EQ\n", irq); goto skip_irq; } handle_eqe_work = kmalloc(sizeof(*handle_eqe_work), GFP_ATOMIC); if (handle_eqe_work) { INIT_WORK(&handle_eqe_work->eq_work, irq_handle_eqe); handle_eqe_work->hdev = hdev; memcpy(&handle_eqe_work->eq_entry, eq_entry, sizeof(*eq_entry)); queue_work(hdev->eq_wq, &handle_eqe_work->eq_work); } skip_irq: /* Clear EQ entry ready bit */ eq_entry->hdr.ctl = cpu_to_le32(le32_to_cpu(eq_entry->hdr.ctl) & ~EQ_CTL_READY_MASK); eq->ci = hl_eq_inc_ptr(eq->ci); hdev->asic_funcs->update_eq_ci(hdev, eq->ci); } return IRQ_HANDLED; } /** * hl_cq_init - main initialization function for an cq object * * @hdev: pointer to device structure * @q: pointer to cq structure * @hw_queue_id: The H/W queue ID this completion queue belongs to * * Allocate dma-able memory for the completion queue and initialize fields * Returns 0 on success */ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) { void *p; p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, HL_CQ_SIZE_IN_BYTES, &q->bus_address, GFP_KERNEL | __GFP_ZERO); if (!p) return -ENOMEM; q->hdev = hdev; q->kernel_address = p; q->hw_queue_id = hw_queue_id; q->ci = 0; q->pi = 0; atomic_set(&q->free_slots_cnt, HL_CQ_LENGTH); return 0; } /** * hl_cq_fini - destroy completion queue * * @hdev: pointer to device structure * @q: pointer to cq structure * * Free the completion queue memory */ void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q) { hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES, q->kernel_address, q->bus_address); } void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) { q->ci = 0; q->pi = 0; atomic_set(&q->free_slots_cnt, HL_CQ_LENGTH); /* * It's not enough to just reset the PI/CI because the H/W may have * written valid completion entries before it was halted and therefore * we need to clean the actual queues so we won't process old entries * when the device is operational again */ memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); } /** * hl_eq_init - main initialization function for an event queue object * * @hdev: pointer to device structure * @q: pointer to eq structure * * Allocate dma-able memory for the event queue and initialize fields * Returns 0 on success */ int hl_eq_init(struct hl_device *hdev, struct hl_eq *q) { void *p; p = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, HL_EQ_SIZE_IN_BYTES, &q->bus_address); if (!p) return -ENOMEM; q->hdev = hdev; q->kernel_address = p; q->ci = 0; return 0; } /** * hl_eq_fini - destroy event queue * * @hdev: pointer to device structure * @q: pointer to eq structure * * Free the event queue memory */ void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q) { flush_workqueue(hdev->eq_wq); hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_EQ_SIZE_IN_BYTES, q->kernel_address); } void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) { q->ci = 0; /* * It's not enough to just reset the PI/CI because the H/W may have * written valid completion entries before it was halted and therefore * we need to clean the actual queues so we won't process old entries * when the device is operational again */ memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); } |