1/* SPDX-License-Identifier: MIT */
2#ifndef _INTEL_RINGBUFFER_H_
3#define _INTEL_RINGBUFFER_H_
4
5#include <asm/cacheflush.h>
6#include <drm/drm_util.h>
7#include <drm/drm_cache.h>
8
9#include <linux/hashtable.h>
10#include <linux/irq_work.h>
11#include <linux/random.h>
12#include <linux/seqlock.h>
13
14#include "i915_pmu.h"
15#include "i915_request.h"
16#include "i915_selftest.h"
17#include "intel_engine_types.h"
18#include "intel_gt_types.h"
19#include "intel_timeline.h"
20#include "intel_workarounds.h"
21
22struct drm_printer;
23struct intel_context;
24struct intel_gt;
25struct lock_class_key;
26
27/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
28 * but keeps the logic simple. Indeed, the whole purpose of this macro is just
29 * to give some inclination as to some of the magic values used in the various
30 * workarounds!
31 */
32#define CACHELINE_BYTES 64
33#define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(u32))
34
35#define ENGINE_TRACE(e, fmt, ...) do {					\
36	const struct intel_engine_cs *e__ __maybe_unused = (e);		\
37	GEM_TRACE("%s %s: " fmt,					\
38		  dev_name(e__->i915->drm.dev), e__->name,		\
39		  ##__VA_ARGS__);					\
40} while (0)
41
42/*
43 * The register defines to be used with the following macros need to accept a
44 * base param, e.g:
45 *
46 * REG_FOO(base) _MMIO((base) + <relative offset>)
47 * ENGINE_READ(engine, REG_FOO);
48 *
49 * register arrays are to be defined and accessed as follows:
50 *
51 * REG_BAR(base, i) _MMIO((base) + <relative offset> + (i) * <shift>)
52 * ENGINE_READ_IDX(engine, REG_BAR, i)
53 */
54
55#define __ENGINE_REG_OP(op__, engine__, ...) \
56	intel_uncore_##op__((engine__)->uncore, __VA_ARGS__)
57
58#define __ENGINE_READ_OP(op__, engine__, reg__) \
59	__ENGINE_REG_OP(op__, (engine__), reg__((engine__)->mmio_base))
60
61#define ENGINE_READ16(...)	__ENGINE_READ_OP(read16, __VA_ARGS__)
62#define ENGINE_READ(...)	__ENGINE_READ_OP(read, __VA_ARGS__)
63#define ENGINE_READ_FW(...)	__ENGINE_READ_OP(read_fw, __VA_ARGS__)
64#define ENGINE_POSTING_READ(...) __ENGINE_READ_OP(posting_read_fw, __VA_ARGS__)
65#define ENGINE_POSTING_READ16(...) __ENGINE_READ_OP(posting_read16, __VA_ARGS__)
66
67#define ENGINE_READ64(engine__, lower_reg__, upper_reg__) \
68	__ENGINE_REG_OP(read64_2x32, (engine__), \
69			lower_reg__((engine__)->mmio_base), \
70			upper_reg__((engine__)->mmio_base))
71
72#define ENGINE_READ_IDX(engine__, reg__, idx__) \
73	__ENGINE_REG_OP(read, (engine__), reg__((engine__)->mmio_base, (idx__)))
74
75#define __ENGINE_WRITE_OP(op__, engine__, reg__, val__) \
76	__ENGINE_REG_OP(op__, (engine__), reg__((engine__)->mmio_base), (val__))
77
78#define ENGINE_WRITE16(...)	__ENGINE_WRITE_OP(write16, __VA_ARGS__)
79#define ENGINE_WRITE(...)	__ENGINE_WRITE_OP(write, __VA_ARGS__)
80#define ENGINE_WRITE_FW(...)	__ENGINE_WRITE_OP(write_fw, __VA_ARGS__)
81
82#define GEN6_RING_FAULT_REG_READ(engine__) \
83	intel_uncore_read((engine__)->uncore, RING_FAULT_REG(engine__))
84
85#define GEN6_RING_FAULT_REG_POSTING_READ(engine__) \
86	intel_uncore_posting_read((engine__)->uncore, RING_FAULT_REG(engine__))
87
88#define GEN6_RING_FAULT_REG_RMW(engine__, clear__, set__) \
89({ \
90	u32 __val; \
91\
92	__val = intel_uncore_read((engine__)->uncore, \
93				  RING_FAULT_REG(engine__)); \
94	__val &= ~(clear__); \
95	__val |= (set__); \
96	intel_uncore_write((engine__)->uncore, RING_FAULT_REG(engine__), \
97			   __val); \
98})
99
100/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
101 * do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
102 */
103
104static inline unsigned int
105execlists_num_ports(const struct intel_engine_execlists * const execlists)
106{
107	return execlists->port_mask + 1;
108}
109
110static inline struct i915_request *
111execlists_active(const struct intel_engine_execlists *execlists)
112{
113	struct i915_request * const *cur, * const *old, *active;
114
115	cur = READ_ONCE(execlists->active);
116	smp_rmb(); /* pairs with overwrite protection in process_csb() */
117	do {
118		old = cur;
119
120		active = READ_ONCE(*cur);
121		cur = READ_ONCE(execlists->active);
122
123		smp_rmb(); /* and complete the seqlock retry */
124	} while (unlikely(cur != old));
125
126	return active;
127}
128
129struct i915_request *
130execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
131
132static inline u32
133intel_read_status_page(const struct intel_engine_cs *engine, int reg)
134{
135	/* Ensure that the compiler doesn't optimize away the load. */
136	return READ_ONCE(engine->status_page.addr[reg]);
137}
138
139static inline void
140intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
141{
142	/* Writing into the status page should be done sparingly. Since
143	 * we do when we are uncertain of the device state, we take a bit
144	 * of extra paranoia to try and ensure that the HWS takes the value
145	 * we give and that it doesn't end up trapped inside the CPU!
146	 */
147	drm_clflush_virt_range(&engine->status_page.addr[reg], sizeof(value));
148	WRITE_ONCE(engine->status_page.addr[reg], value);
149	drm_clflush_virt_range(&engine->status_page.addr[reg], sizeof(value));
150}
151
152/*
153 * Reads a dword out of the status page, which is written to from the command
154 * queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or
155 * MI_STORE_DATA_IMM.
156 *
157 * The following dwords have a reserved meaning:
158 * 0x00: ISR copy, updated when an ISR bit not set in the HWSTAM changes.
159 * 0x04: ring 0 head pointer
160 * 0x05: ring 1 head pointer (915-class)
161 * 0x06: ring 2 head pointer (915-class)
162 * 0x10-0x1b: Context status DWords (GM45)
163 * 0x1f: Last written status offset. (GM45)
164 * 0x20-0x2f: Reserved (Gen6+)
165 *
166 * The area from dword 0x30 to 0x3ff is available for driver usage.
167 */
168#define I915_GEM_HWS_PREEMPT		0x32
169#define I915_GEM_HWS_PREEMPT_ADDR	(I915_GEM_HWS_PREEMPT * sizeof(u32))
170#define I915_GEM_HWS_SEQNO		0x40
171#define I915_GEM_HWS_SEQNO_ADDR		(I915_GEM_HWS_SEQNO * sizeof(u32))
172#define I915_GEM_HWS_MIGRATE		(0x42 * sizeof(u32))
173#define I915_GEM_HWS_PXP		0x60
174#define I915_GEM_HWS_PXP_ADDR		(I915_GEM_HWS_PXP * sizeof(u32))
175#define I915_GEM_HWS_GSC		0x62
176#define I915_GEM_HWS_GSC_ADDR		(I915_GEM_HWS_GSC * sizeof(u32))
177#define I915_GEM_HWS_SCRATCH		0x80
178
179#define I915_HWS_CSB_BUF0_INDEX		0x10
180#define I915_HWS_CSB_WRITE_INDEX	0x1f
181#define ICL_HWS_CSB_WRITE_INDEX		0x2f
182#define INTEL_HWS_CSB_WRITE_INDEX(__i915) \
183	(GRAPHICS_VER(__i915) >= 11 ? ICL_HWS_CSB_WRITE_INDEX : I915_HWS_CSB_WRITE_INDEX)
184
185void intel_engine_stop(struct intel_engine_cs *engine);
186void intel_engine_cleanup(struct intel_engine_cs *engine);
187
188int intel_engines_init_mmio(struct intel_gt *gt);
189int intel_engines_init(struct intel_gt *gt);
190
191void intel_engine_free_request_pool(struct intel_engine_cs *engine);
192
193void intel_engines_release(struct intel_gt *gt);
194void intel_engines_free(struct intel_gt *gt);
195
196int intel_engine_init_common(struct intel_engine_cs *engine);
197void intel_engine_cleanup_common(struct intel_engine_cs *engine);
198
199int intel_engine_resume(struct intel_engine_cs *engine);
200
201int intel_ring_submission_setup(struct intel_engine_cs *engine);
202
203int intel_engine_stop_cs(struct intel_engine_cs *engine);
204void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
205
206void intel_engine_wait_for_pending_mi_fw(struct intel_engine_cs *engine);
207
208void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);
209
210u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
211u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
212
213void intel_engine_get_instdone(const struct intel_engine_cs *engine,
214			       struct intel_instdone *instdone);
215
216void intel_engine_init_execlists(struct intel_engine_cs *engine);
217
218bool intel_engine_irq_enable(struct intel_engine_cs *engine);
219void intel_engine_irq_disable(struct intel_engine_cs *engine);
220
221static inline void __intel_engine_reset(struct intel_engine_cs *engine,
222					bool stalled)
223{
224	if (engine->reset.rewind)
225		engine->reset.rewind(engine, stalled);
226	engine->serial++; /* contexts lost */
227}
228
229bool intel_engines_are_idle(struct intel_gt *gt);
230bool intel_engine_is_idle(struct intel_engine_cs *engine);
231
232void __intel_engine_flush_submission(struct intel_engine_cs *engine, bool sync);
233static inline void intel_engine_flush_submission(struct intel_engine_cs *engine)
234{
235	__intel_engine_flush_submission(engine, true);
236}
237
238void intel_engines_reset_default_submission(struct intel_gt *gt);
239
240bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
241
242__printf(3, 4)
243void intel_engine_dump(struct intel_engine_cs *engine,
244		       struct drm_printer *m,
245		       const char *header, ...);
246void intel_engine_dump_active_requests(struct list_head *requests,
247				       struct i915_request *hung_rq,
248				       struct drm_printer *m);
249
250ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
251				   ktime_t *now);
252
253void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
254				  struct intel_context **ce, struct i915_request **rq);
255
256u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
257struct intel_context *
258intel_engine_create_pinned_context(struct intel_engine_cs *engine,
259				   struct i915_address_space *vm,
260				   unsigned int ring_size,
261				   unsigned int hwsp,
262				   struct lock_class_key *key,
263				   const char *name);
264
265void intel_engine_destroy_pinned_context(struct intel_context *ce);
266
267void xehp_enable_ccs_engines(struct intel_engine_cs *engine);
268
269#define ENGINE_PHYSICAL	0
270#define ENGINE_MOCK	1
271#define ENGINE_VIRTUAL	2
272
273static inline bool intel_engine_uses_guc(const struct intel_engine_cs *engine)
274{
275	return engine->gt->submission_method >= INTEL_SUBMISSION_GUC;
276}
277
278static inline bool
279intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
280{
281	if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT)
282		return false;
283
284	return intel_engine_has_preemption(engine);
285}
286
287#define FORCE_VIRTUAL	BIT(0)
288struct intel_context *
289intel_engine_create_virtual(struct intel_engine_cs **siblings,
290			    unsigned int count, unsigned long flags);
291
292static inline struct intel_context *
293intel_engine_create_parallel(struct intel_engine_cs **engines,
294			     unsigned int num_engines,
295			     unsigned int width)
296{
297	GEM_BUG_ON(!engines[0]->cops->create_parallel);
298	return engines[0]->cops->create_parallel(engines, num_engines, width);
299}
300
301static inline bool
302intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine)
303{
304	/*
305	 * For non-GuC submission we expect the back-end to look at the
306	 * heartbeat status of the actual physical engine that the work
307	 * has been (or is being) scheduled on, so we should only reach
308	 * here with GuC submission enabled.
309	 */
310	GEM_BUG_ON(!intel_engine_uses_guc(engine));
311
312	return intel_guc_virtual_engine_has_heartbeat(engine);
313}
314
315static inline bool
316intel_engine_has_heartbeat(const struct intel_engine_cs *engine)
317{
318	if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL)
319		return false;
320
321	if (intel_engine_is_virtual(engine))
322		return intel_virtual_engine_has_heartbeat(engine);
323	else
324		return READ_ONCE(engine->props.heartbeat_interval_ms);
325}
326
327static inline struct intel_engine_cs *
328intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling)
329{
330	GEM_BUG_ON(!intel_engine_is_virtual(engine));
331	return engine->cops->get_sibling(engine, sibling);
332}
333
334static inline void
335intel_engine_set_hung_context(struct intel_engine_cs *engine,
336			      struct intel_context *ce)
337{
338	engine->hung_ce = ce;
339}
340
341static inline void
342intel_engine_clear_hung_context(struct intel_engine_cs *engine)
343{
344	intel_engine_set_hung_context(engine, NULL);
345}
346
347static inline struct intel_context *
348intel_engine_get_hung_context(struct intel_engine_cs *engine)
349{
350	return engine->hung_ce;
351}
352
353u64 intel_clamp_heartbeat_interval_ms(struct intel_engine_cs *engine, u64 value);
354u64 intel_clamp_max_busywait_duration_ns(struct intel_engine_cs *engine, u64 value);
355u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value);
356u64 intel_clamp_stop_timeout_ms(struct intel_engine_cs *engine, u64 value);
357u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value);
358
359#endif /* _INTEL_RINGBUFFER_H_ */
360