summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_gpu_error.h
blob: 8710fb18ed746cface7e9a7b2d6d6ac7cd06b2b4 (plain)
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
/*
 * SPDX-License-Identifier: MIT
 *
 * Copyright � 2008-2018 Intel Corporation
 */

#ifndef _I915_GPU_ERROR_H_
#define _I915_GPU_ERROR_H_

#include <linux/kref.h>
#include <linux/ktime.h>
#include <linux/sched.h>

#include <drm/drm_mm.h>

#include "intel_device_info.h"
#include "intel_ringbuffer.h"
#include "intel_uc_fw.h"

#include "i915_gem.h"
#include "i915_gem_gtt.h"
#include "i915_params.h"
#include "i915_scheduler.h"

struct drm_i915_private;
struct intel_overlay_error_state;
struct intel_display_error_state;

struct i915_gpu_state {
	struct kref ref;
	ktime_t time;
	ktime_t boottime;
	ktime_t uptime;
	unsigned long capture;
	unsigned long epoch;

	struct drm_i915_private *i915;

	char error_msg[128];
	bool simulated;
	bool awake;
	bool wakelock;
	bool suspended;
	int iommu;
	u32 reset_count;
	u32 suspend_count;
	struct intel_device_info device_info;
	struct intel_driver_caps driver_caps;
	struct i915_params params;

	struct i915_error_uc {
		struct intel_uc_fw guc_fw;
		struct intel_uc_fw huc_fw;
		struct drm_i915_error_object *guc_log;
	} uc;

	/* Generic register state */
	u32 eir;
	u32 pgtbl_er;
	u32 ier;
	u32 gtier[6], ngtier;
	u32 ccid;
	u32 derrmr;
	u32 forcewake;
	u32 error; /* gen6+ */
	u32 err_int; /* gen7 */
	u32 fault_data0; /* gen8, gen9 */
	u32 fault_data1; /* gen8, gen9 */
	u32 done_reg;
	u32 gac_eco;
	u32 gam_ecochk;
	u32 gab_ctl;
	u32 gfx_mode;

	u32 nfence;
	u64 fence[I915_MAX_NUM_FENCES];
	struct intel_overlay_error_state *overlay;
	struct intel_display_error_state *display;

	struct drm_i915_error_engine {
		int engine_id;
		/* Software tracked state */
		bool idle;
		bool waiting;
		int num_waiters;
		unsigned long hangcheck_timestamp;
		bool hangcheck_stalled;
		enum intel_engine_hangcheck_action hangcheck_action;
		struct i915_address_space *vm;
		int num_requests;
		u32 reset_count;

		/* position of active request inside the ring */
		u32 rq_head, rq_post, rq_tail;

		/* our own tracking of ring head and tail */
		u32 cpu_ring_head;
		u32 cpu_ring_tail;

		u32 last_seqno;

		/* Register state */
		u32 start;
		u32 tail;
		u32 head;
		u32 ctl;
		u32 mode;
		u32 hws;
		u32 ipeir;
		u32 ipehr;
		u32 bbstate;
		u32 instpm;
		u32 instps;
		u32 seqno;
		u64 bbaddr;
		u64 acthd;
		u32 fault_reg;
		u64 faddr;
		u32 rc_psmi; /* sleep state */
		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
		struct intel_instdone instdone;

		struct drm_i915_error_context {
			char comm[TASK_COMM_LEN];
			pid_t pid;
			u32 handle;
			u32 hw_id;
			int ban_score;
			int active;
			int guilty;
			bool bannable;
			struct i915_sched_attr sched_attr;
		} context;

		struct drm_i915_error_object {
			u64 gtt_offset;
			u64 gtt_size;
			int num_pages;
			int page_count;
			int unused;
			u32 *pages[0];
		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;

		struct drm_i915_error_object **user_bo;
		long user_bo_count;

		struct drm_i915_error_object *wa_ctx;
		struct drm_i915_error_object *default_state;

		struct drm_i915_error_request {
			long jiffies;
			pid_t pid;
			u32 context;
			int ban_score;
			u32 seqno;
			u32 start;
			u32 head;
			u32 tail;
			struct i915_sched_attr sched_attr;
		} *requests, execlist[EXECLIST_MAX_PORTS];
		unsigned int num_ports;

		struct drm_i915_error_waiter {
			char comm[TASK_COMM_LEN];
			pid_t pid;
			u32 seqno;
		} *waiters;

		struct {
			u32 gfx_mode;
			union {
				u64 pdp[4];
				u32 pp_dir_base;
			};
		} vm_info;
	} engine[I915_NUM_ENGINES];

	struct drm_i915_error_buffer {
		u32 size;
		u32 name;
		u32 wseqno;
		u64 gtt_offset;
		u32 read_domains;
		u32 write_domain;
		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
		u32 tiling:2;
		u32 dirty:1;
		u32 purgeable:1;
		u32 userptr:1;
		s32 engine:4;
		u32 cache_level:3;
	} *active_bo[I915_NUM_ENGINES], *pinned_bo;
	u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
	struct i915_address_space *active_vm[I915_NUM_ENGINES];
};

struct i915_gpu_error {
	/* For hangcheck timer */
#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)

	struct delayed_work hangcheck_work;

	/* For reset and error_state handling. */
	spinlock_t lock;
	/* Protected by the above dev->gpu_error.lock. */
	struct i915_gpu_state *first_error;

	atomic_t pending_fb_pin;

	unsigned long missed_irq_rings;

	/**
	 * State variable controlling the reset flow and count
	 *
	 * This is a counter which gets incremented when reset is triggered,
	 *
	 * Before the reset commences, the I915_RESET_BACKOFF bit is set
	 * meaning that any waiters holding onto the struct_mutex should
	 * relinquish the lock immediately in order for the reset to start.
	 *
	 * If reset is not completed successfully, the I915_WEDGE bit is
	 * set meaning that hardware is terminally sour and there is no
	 * recovery. All waiters on the reset_queue will be woken when
	 * that happens.
	 *
	 * This counter is used by the wait_seqno code to notice that reset
	 * event happened and it needs to restart the entire ioctl (since most
	 * likely the seqno it waited for won't ever signal anytime soon).
	 *
	 * This is important for lock-free wait paths, where no contended lock
	 * naturally enforces the correct ordering between the bail-out of the
	 * waiter and the gpu reset work code.
	 */
	unsigned long reset_count;

	/**
	 * flags: Control various stages of the GPU reset
	 *
	 * #I915_RESET_BACKOFF - When we start a reset, we want to stop any
	 * other users acquiring the struct_mutex. To do this we set the
	 * #I915_RESET_BACKOFF bit in the error flags when we detect a reset
	 * and then check for that bit before acquiring the struct_mutex (in
	 * i915_mutex_lock_interruptible()?). I915_RESET_BACKOFF serves a
	 * secondary role in preventing two concurrent global reset attempts.
	 *
	 * #I915_RESET_HANDOFF - To perform the actual GPU reset, we need the
	 * struct_mutex. We try to acquire the struct_mutex in the reset worker,
	 * but it may be held by some long running waiter (that we cannot
	 * interrupt without causing trouble). Once we are ready to do the GPU
	 * reset, we set the I915_RESET_HANDOFF bit and wakeup any waiters. If
	 * they already hold the struct_mutex and want to participate they can
	 * inspect the bit and do the reset directly, otherwise the worker
	 * waits for the struct_mutex.
	 *
	 * #I915_RESET_ENGINE[num_engines] - Since the driver doesn't need to
	 * acquire the struct_mutex to reset an engine, we need an explicit
	 * flag to prevent two concurrent reset attempts in the same engine.
	 * As the number of engines continues to grow, allocate the flags from
	 * the most significant bits.
	 *
	 * #I915_WEDGED - If reset fails and we can no longer use the GPU,
	 * we set the #I915_WEDGED bit. Prior to command submission, e.g.
	 * i915_request_alloc(), this bit is checked and the sequence
	 * aborted (with -EIO reported to userspace) if set.
	 */
	unsigned long flags;
#define I915_RESET_BACKOFF	0
#define I915_RESET_HANDOFF	1
#define I915_RESET_MODESET	2
#define I915_WEDGED		(BITS_PER_LONG - 1)
#define I915_RESET_ENGINE	(I915_WEDGED - I915_NUM_ENGINES)

	/** Number of times an engine has been reset */
	u32 reset_engine_count[I915_NUM_ENGINES];

	/** Set of stalled engines with guilty requests, in the current reset */
	u32 stalled_mask;

	/** Reason for the current *global* reset */
	const char *reason;

	/**
	 * Waitqueue to signal when a hang is detected. Used to for waiters
	 * to release the struct_mutex for the reset to procede.
	 */
	wait_queue_head_t wait_queue;

	/**
	 * Waitqueue to signal when the reset has completed. Used by clients
	 * that wait for dev_priv->mm.wedged to settle.
	 */
	wait_queue_head_t reset_queue;

	/* For missed irq/seqno simulation. */
	unsigned long test_irq_rings;
};

struct drm_i915_error_state_buf {
	struct drm_i915_private *i915;
	unsigned int bytes;
	unsigned int size;
	int err;
	u8 *buf;
	loff_t start;
	loff_t pos;
};

#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)

__printf(2, 3)
void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
			    const struct i915_gpu_state *gpu);
int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb,
			      struct drm_i915_private *i915,
			      size_t count, loff_t pos);

static inline void
i915_error_state_buf_release(struct drm_i915_error_state_buf *eb)
{
	kfree(eb->buf);
}

struct i915_gpu_state *i915_capture_gpu_state(struct drm_i915_private *i915);
void i915_capture_error_state(struct drm_i915_private *dev_priv,
			      u32 engine_mask,
			      const char *error_msg);

static inline struct i915_gpu_state *
i915_gpu_state_get(struct i915_gpu_state *gpu)
{
	kref_get(&gpu->ref);
	return gpu;
}

void __i915_gpu_state_free(struct kref *kref);
static inline void i915_gpu_state_put(struct i915_gpu_state *gpu)
{
	if (gpu)
		kref_put(&gpu->ref, __i915_gpu_state_free);
}

struct i915_gpu_state *i915_first_error_state(struct drm_i915_private *i915);
void i915_reset_error_state(struct drm_i915_private *i915);

#else

static inline void i915_capture_error_state(struct drm_i915_private *dev_priv,
					    u32 engine_mask,
					    const char *error_msg)
{
}

static inline struct i915_gpu_state *
i915_first_error_state(struct drm_i915_private *i915)
{
	return NULL;
}

static inline void i915_reset_error_state(struct drm_i915_private *i915)
{
}

#endif /* IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) */

#endif /* _I915_GPU_ERROR_H_ */