1/*
2 * Copyright © 2013 Intel Corporation
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21 * IN THE SOFTWARE.
22 *
23 * Authors:
24 *    Brad Volkin <bradley.d.volkin@intel.com>
25 *
26 */
27
28#include "gt/intel_engine.h"
29
30#include "i915_drv.h"
31#include "i915_memcpy.h"
32
33/**
34 * DOC: batch buffer command parser
35 *
36 * Motivation:
37 * Certain OpenGL features (e.g. transform feedback, performance monitoring)
38 * require userspace code to submit batches containing commands such as
39 * MI_LOAD_REGISTER_IMM to access various registers. Unfortunately, some
40 * generations of the hardware will noop these commands in "unsecure" batches
41 * (which includes all userspace batches submitted via i915) even though the
42 * commands may be safe and represent the intended programming model of the
43 * device.
44 *
45 * The software command parser is similar in operation to the command parsing
46 * done in hardware for unsecure batches. However, the software parser allows
47 * some operations that would be noop'd by hardware, if the parser determines
48 * the operation is safe, and submits the batch as "secure" to prevent hardware
49 * parsing.
50 *
51 * Threats:
52 * At a high level, the hardware (and software) checks attempt to prevent
53 * granting userspace undue privileges. There are three categories of privilege.
54 *
55 * First, commands which are explicitly defined as privileged or which should
56 * only be used by the kernel driver. The parser rejects such commands
57 *
58 * Second, commands which access registers. To support correct/enhanced
59 * userspace functionality, particularly certain OpenGL extensions, the parser
60 * provides a whitelist of registers which userspace may safely access
61 *
62 * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
63 * The parser always rejects such commands.
64 *
65 * The majority of the problematic commands fall in the MI_* range, with only a
66 * few specific commands on each engine (e.g. PIPE_CONTROL and MI_FLUSH_DW).
67 *
68 * Implementation:
69 * Each engine maintains tables of commands and registers which the parser
70 * uses in scanning batch buffers submitted to that engine.
71 *
72 * Since the set of commands that the parser must check for is significantly
73 * smaller than the number of commands supported, the parser tables contain only
74 * those commands required by the parser. This generally works because command
75 * opcode ranges have standard command length encodings. So for commands that
76 * the parser does not need to check, it can easily skip them. This is
77 * implemented via a per-engine length decoding vfunc.
78 *
79 * Unfortunately, there are a number of commands that do not follow the standard
80 * length encoding for their opcode range, primarily amongst the MI_* commands.
81 * To handle this, the parser provides a way to define explicit "skip" entries
82 * in the per-engine command tables.
83 *
84 * Other command table entries map fairly directly to high level categories
85 * mentioned above: rejected, register whitelist. The parser implements a number
86 * of checks, including the privileged memory checks, via a general bitmasking
87 * mechanism.
88 */
89
90/*
91 * A command that requires special handling by the command parser.
92 */
93struct drm_i915_cmd_descriptor {
94	/*
95	 * Flags describing how the command parser processes the command.
96	 *
97	 * CMD_DESC_FIXED: The command has a fixed length if this is set,
98	 *                 a length mask if not set
99	 * CMD_DESC_SKIP: The command is allowed but does not follow the
100	 *                standard length encoding for the opcode range in
101	 *                which it falls
102	 * CMD_DESC_REJECT: The command is never allowed
103	 * CMD_DESC_REGISTER: The command should be checked against the
104	 *                    register whitelist for the appropriate ring
105	 */
106	u32 flags;
107#define CMD_DESC_FIXED    (1<<0)
108#define CMD_DESC_SKIP     (1<<1)
109#define CMD_DESC_REJECT   (1<<2)
110#define CMD_DESC_REGISTER (1<<3)
111#define CMD_DESC_BITMASK  (1<<4)
112
113	/*
114	 * The command's unique identification bits and the bitmask to get them.
115	 * This isn't strictly the opcode field as defined in the spec and may
116	 * also include type, subtype, and/or subop fields.
117	 */
118	struct {
119		u32 value;
120		u32 mask;
121	} cmd;
122
123	/*
124	 * The command's length. The command is either fixed length (i.e. does
125	 * not include a length field) or has a length field mask. The flag
126	 * CMD_DESC_FIXED indicates a fixed length. Otherwise, the command has
127	 * a length mask. All command entries in a command table must include
128	 * length information.
129	 */
130	union {
131		u32 fixed;
132		u32 mask;
133	} length;
134
135	/*
136	 * Describes where to find a register address in the command to check
137	 * against the ring's register whitelist. Only valid if flags has the
138	 * CMD_DESC_REGISTER bit set.
139	 *
140	 * A non-zero step value implies that the command may access multiple
141	 * registers in sequence (e.g. LRI), in that case step gives the
142	 * distance in dwords between individual offset fields.
143	 */
144	struct {
145		u32 offset;
146		u32 mask;
147		u32 step;
148	} reg;
149
150#define MAX_CMD_DESC_BITMASKS 3
151	/*
152	 * Describes command checks where a particular dword is masked and
153	 * compared against an expected value. If the command does not match
154	 * the expected value, the parser rejects it. Only valid if flags has
155	 * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero
156	 * are valid.
157	 *
158	 * If the check specifies a non-zero condition_mask then the parser
159	 * only performs the check when the bits specified by condition_mask
160	 * are non-zero.
161	 */
162	struct {
163		u32 offset;
164		u32 mask;
165		u32 expected;
166		u32 condition_offset;
167		u32 condition_mask;
168	} bits[MAX_CMD_DESC_BITMASKS];
169};
170
171/*
172 * A table of commands requiring special handling by the command parser.
173 *
174 * Each engine has an array of tables. Each table consists of an array of
175 * command descriptors, which must be sorted with command opcodes in
176 * ascending order.
177 */
178struct drm_i915_cmd_table {
179	const struct drm_i915_cmd_descriptor *table;
180	int count;
181};
182
183#define STD_MI_OPCODE_SHIFT  (32 - 9)
184#define STD_3D_OPCODE_SHIFT  (32 - 16)
185#define STD_2D_OPCODE_SHIFT  (32 - 10)
186#define STD_MFX_OPCODE_SHIFT (32 - 16)
187#define MIN_OPCODE_SHIFT 16
188
189#define CMD(op, opm, f, lm, fl, ...)				\
190	{							\
191		.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0),	\
192		.cmd = { (op & ~0u << (opm)), ~0u << (opm) },	\
193		.length = { (lm) },				\
194		__VA_ARGS__					\
195	}
196
197/* Convenience macros to compress the tables */
198#define SMI STD_MI_OPCODE_SHIFT
199#define S3D STD_3D_OPCODE_SHIFT
200#define S2D STD_2D_OPCODE_SHIFT
201#define SMFX STD_MFX_OPCODE_SHIFT
202#define F true
203#define S CMD_DESC_SKIP
204#define R CMD_DESC_REJECT
205#define W CMD_DESC_REGISTER
206#define B CMD_DESC_BITMASK
207
208/*            Command                          Mask   Fixed Len   Action
209	      ---------------------------------------------------------- */
210static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
211	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
212	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      R  ),
213	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      R  ),
214	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
215	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
216	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
217	CMD(  MI_SEMAPHORE_MBOX,                SMI,   !F,  0xFF,   R  ),
218	CMD(  MI_STORE_DWORD_INDEX,             SMI,   !F,  0xFF,   R  ),
219	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
220	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 }    ),
221	CMD(  MI_STORE_REGISTER_MEM,            SMI,    F,  3,     W | B,
222	      .reg = { .offset = 1, .mask = 0x007FFFFC },
223	      .bits = {{
224			.offset = 0,
225			.mask = MI_GLOBAL_GTT,
226			.expected = 0,
227	      }},						       ),
228	CMD(  MI_LOAD_REGISTER_MEM,             SMI,    F,  3,     W | B,
229	      .reg = { .offset = 1, .mask = 0x007FFFFC },
230	      .bits = {{
231			.offset = 0,
232			.mask = MI_GLOBAL_GTT,
233			.expected = 0,
234	      }},						       ),
235	/*
236	 * MI_BATCH_BUFFER_START requires some special handling. It's not
237	 * really a 'skip' action but it doesn't seem like it's worth adding
238	 * a new action. See intel_engine_cmd_parser().
239	 */
240	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
241};
242
243static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = {
244	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
245	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
246	CMD(  MI_PREDICATE,                     SMI,    F,  1,      S  ),
247	CMD(  MI_TOPOLOGY_FILTER,               SMI,    F,  1,      S  ),
248	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
249	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
250	CMD(  MI_SET_CONTEXT,                   SMI,   !F,  0xFF,   R  ),
251	CMD(  MI_URB_CLEAR,                     SMI,   !F,  0xFF,   S  ),
252	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3F,   B,
253	      .bits = {{
254			.offset = 0,
255			.mask = MI_GLOBAL_GTT,
256			.expected = 0,
257	      }},						       ),
258	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0xFF,   R  ),
259	CMD(  MI_CLFLUSH,                       SMI,   !F,  0x3FF,  B,
260	      .bits = {{
261			.offset = 0,
262			.mask = MI_GLOBAL_GTT,
263			.expected = 0,
264	      }},						       ),
265	CMD(  MI_REPORT_PERF_COUNT,             SMI,   !F,  0x3F,   B,
266	      .bits = {{
267			.offset = 1,
268			.mask = MI_REPORT_PERF_COUNT_GGTT,
269			.expected = 0,
270	      }},						       ),
271	CMD(  MI_CONDITIONAL_BATCH_BUFFER_END,  SMI,   !F,  0xFF,   B,
272	      .bits = {{
273			.offset = 0,
274			.mask = MI_GLOBAL_GTT,
275			.expected = 0,
276	      }},						       ),
277	CMD(  GFX_OP_3DSTATE_VF_STATISTICS,     S3D,    F,  1,      S  ),
278	CMD(  PIPELINE_SELECT,                  S3D,    F,  1,      S  ),
279	CMD(  MEDIA_VFE_STATE,			S3D,   !F,  0xFFFF, B,
280	      .bits = {{
281			.offset = 2,
282			.mask = MEDIA_VFE_STATE_MMIO_ACCESS_MASK,
283			.expected = 0,
284	      }},						       ),
285	CMD(  GPGPU_OBJECT,                     S3D,   !F,  0xFF,   S  ),
286	CMD(  GPGPU_WALKER,                     S3D,   !F,  0xFF,   S  ),
287	CMD(  GFX_OP_3DSTATE_SO_DECL_LIST,      S3D,   !F,  0x1FF,  S  ),
288	CMD(  GFX_OP_PIPE_CONTROL(5),           S3D,   !F,  0xFF,   B,
289	      .bits = {{
290			.offset = 1,
291			.mask = (PIPE_CONTROL_MMIO_WRITE | PIPE_CONTROL_NOTIFY),
292			.expected = 0,
293	      },
294	      {
295			.offset = 1,
296		        .mask = (PIPE_CONTROL_GLOBAL_GTT_IVB |
297				 PIPE_CONTROL_STORE_DATA_INDEX),
298			.expected = 0,
299			.condition_offset = 1,
300			.condition_mask = PIPE_CONTROL_POST_SYNC_OP_MASK,
301	      }},						       ),
302};
303
304static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
305	CMD(  MI_SET_PREDICATE,                 SMI,    F,  1,      S  ),
306	CMD(  MI_RS_CONTROL,                    SMI,    F,  1,      S  ),
307	CMD(  MI_URB_ATOMIC_ALLOC,              SMI,    F,  1,      S  ),
308	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
309	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
310	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
311	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
312	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   W,
313	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
314	CMD(  MI_RS_STORE_DATA_IMM,             SMI,   !F,  0xFF,   S  ),
315	CMD(  MI_LOAD_URB_MEM,                  SMI,   !F,  0xFF,   S  ),
316	CMD(  MI_STORE_URB_MEM,                 SMI,   !F,  0xFF,   S  ),
317	CMD(  GFX_OP_3DSTATE_DX9_CONSTANTF_VS,  S3D,   !F,  0x7FF,  S  ),
318	CMD(  GFX_OP_3DSTATE_DX9_CONSTANTF_PS,  S3D,   !F,  0x7FF,  S  ),
319
320	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS,  S3D,   !F,  0x1FF,  S  ),
321	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS,  S3D,   !F,  0x1FF,  S  ),
322	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS,  S3D,   !F,  0x1FF,  S  ),
323	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS,  S3D,   !F,  0x1FF,  S  ),
324	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS,  S3D,   !F,  0x1FF,  S  ),
325};
326
327static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = {
328	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
329	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
330	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
331	      .bits = {{
332			.offset = 0,
333			.mask = MI_GLOBAL_GTT,
334			.expected = 0,
335	      }},						       ),
336	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3F,   R  ),
337	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   B,
338	      .bits = {{
339			.offset = 0,
340			.mask = MI_FLUSH_DW_NOTIFY,
341			.expected = 0,
342	      },
343	      {
344			.offset = 1,
345			.mask = MI_FLUSH_DW_USE_GTT,
346			.expected = 0,
347			.condition_offset = 0,
348			.condition_mask = MI_FLUSH_DW_OP_MASK,
349	      },
350	      {
351			.offset = 0,
352			.mask = MI_FLUSH_DW_STORE_INDEX,
353			.expected = 0,
354			.condition_offset = 0,
355			.condition_mask = MI_FLUSH_DW_OP_MASK,
356	      }},						       ),
357	CMD(  MI_CONDITIONAL_BATCH_BUFFER_END,  SMI,   !F,  0xFF,   B,
358	      .bits = {{
359			.offset = 0,
360			.mask = MI_GLOBAL_GTT,
361			.expected = 0,
362	      }},						       ),
363	/*
364	 * MFX_WAIT doesn't fit the way we handle length for most commands.
365	 * It has a length field but it uses a non-standard length bias.
366	 * It is always 1 dword though, so just treat it as fixed length.
367	 */
368	CMD(  MFX_WAIT,                         SMFX,   F,  1,      S  ),
369};
370
371static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = {
372	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
373	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
374	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
375	      .bits = {{
376			.offset = 0,
377			.mask = MI_GLOBAL_GTT,
378			.expected = 0,
379	      }},						       ),
380	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3F,   R  ),
381	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   B,
382	      .bits = {{
383			.offset = 0,
384			.mask = MI_FLUSH_DW_NOTIFY,
385			.expected = 0,
386	      },
387	      {
388			.offset = 1,
389			.mask = MI_FLUSH_DW_USE_GTT,
390			.expected = 0,
391			.condition_offset = 0,
392			.condition_mask = MI_FLUSH_DW_OP_MASK,
393	      },
394	      {
395			.offset = 0,
396			.mask = MI_FLUSH_DW_STORE_INDEX,
397			.expected = 0,
398			.condition_offset = 0,
399			.condition_mask = MI_FLUSH_DW_OP_MASK,
400	      }},						       ),
401	CMD(  MI_CONDITIONAL_BATCH_BUFFER_END,  SMI,   !F,  0xFF,   B,
402	      .bits = {{
403			.offset = 0,
404			.mask = MI_GLOBAL_GTT,
405			.expected = 0,
406	      }},						       ),
407};
408
409static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = {
410	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
411	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  B,
412	      .bits = {{
413			.offset = 0,
414			.mask = MI_GLOBAL_GTT,
415			.expected = 0,
416	      }},						       ),
417	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3F,   R  ),
418	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   B,
419	      .bits = {{
420			.offset = 0,
421			.mask = MI_FLUSH_DW_NOTIFY,
422			.expected = 0,
423	      },
424	      {
425			.offset = 1,
426			.mask = MI_FLUSH_DW_USE_GTT,
427			.expected = 0,
428			.condition_offset = 0,
429			.condition_mask = MI_FLUSH_DW_OP_MASK,
430	      },
431	      {
432			.offset = 0,
433			.mask = MI_FLUSH_DW_STORE_INDEX,
434			.expected = 0,
435			.condition_offset = 0,
436			.condition_mask = MI_FLUSH_DW_OP_MASK,
437	      }},						       ),
438	CMD(  COLOR_BLT,                        S2D,   !F,  0x3F,   S  ),
439	CMD(  SRC_COPY_BLT,                     S2D,   !F,  0x3F,   S  ),
440};
441
442static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
443	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
444	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
445};
446
447/*
448 * For Gen9 we can still rely on the h/w to enforce cmd security, and only
449 * need to re-enforce the register access checks. We therefore only need to
450 * teach the cmdparser how to find the end of each command, and identify
451 * register accesses. The table doesn't need to reject any commands, and so
452 * the only commands listed here are:
453 *   1) Those that touch registers
454 *   2) Those that do not have the default 8-bit length
455 *
456 * Note that the default MI length mask chosen for this table is 0xFF, not
457 * the 0x3F used on older devices. This is because the vast majority of MI
458 * cmds on Gen9 use a standard 8-bit Length field.
459 * All the Gen9 blitter instructions are standard 0xFF length mask, and
460 * none allow access to non-general registers, so in fact no BLT cmds are
461 * included in the table at all.
462 *
463 */
464static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
465	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
466	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      S  ),
467	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      S  ),
468	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
469	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
470	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
471	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      S  ),
472	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
473	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   S  ),
474	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   S  ),
475	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  S  ),
476	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
477	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 }    ),
478	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3FF,  S  ),
479	CMD(  MI_STORE_REGISTER_MEM_GEN8,       SMI,    F,  4,      W,
480	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
481	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   S  ),
482	CMD(  MI_LOAD_REGISTER_MEM_GEN8,        SMI,    F,  4,      W,
483	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
484	CMD(  MI_LOAD_REGISTER_REG,             SMI,    !F,  0xFF,  W,
485	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
486
487	/*
488	 * We allow BB_START but apply further checks. We just sanitize the
489	 * basic fields here.
490	 */
491#define MI_BB_START_OPERAND_MASK   GENMASK(SMI-1, 0)
492#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1)
493	CMD(  MI_BATCH_BUFFER_START_GEN8,       SMI,    !F,  0xFF,  B,
494	      .bits = {{
495			.offset = 0,
496			.mask = MI_BB_START_OPERAND_MASK,
497			.expected = MI_BB_START_OPERAND_EXPECT,
498	      }},						       ),
499};
500
501static const struct drm_i915_cmd_descriptor noop_desc =
502	CMD(MI_NOOP, SMI, F, 1, S);
503
504#undef CMD
505#undef SMI
506#undef S3D
507#undef S2D
508#undef SMFX
509#undef F
510#undef S
511#undef R
512#undef W
513#undef B
514
515static const struct drm_i915_cmd_table gen7_render_cmd_table[] = {
516	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
517	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
518};
519
520static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = {
521	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
522	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
523	{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
524};
525
526static const struct drm_i915_cmd_table gen7_video_cmd_table[] = {
527	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
528	{ gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) },
529};
530
531static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = {
532	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
533	{ gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) },
534};
535
536static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = {
537	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
538	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
539};
540
541static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
542	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
543	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
544	{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
545};
546
547static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
548	{ gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
549};
550
551
552/*
553 * Register whitelists, sorted by increasing register offset.
554 */
555
556/*
557 * An individual whitelist entry granting access to register addr.  If
558 * mask is non-zero the argument of immediate register writes will be
559 * AND-ed with mask, and the command will be rejected if the result
560 * doesn't match value.
561 *
562 * Registers with non-zero mask are only allowed to be written using
563 * LRI.
564 */
565struct drm_i915_reg_descriptor {
566	i915_reg_t addr;
567	u32 mask;
568	u32 value;
569};
570
571/* Convenience macro for adding 32-bit registers. */
572#define REG32(_reg, ...) \
573	{ .addr = (_reg), __VA_ARGS__ }
574
575#define REG32_IDX(_reg, idx) \
576	{ .addr = _reg(idx) }
577
578/*
579 * Convenience macro for adding 64-bit registers.
580 *
581 * Some registers that userspace accesses are 64 bits. The register
582 * access commands only allow 32-bit accesses. Hence, we have to include
583 * entries for both halves of the 64-bit registers.
584 */
585#define REG64(_reg) \
586	{ .addr = _reg }, \
587	{ .addr = _reg ## _UDW }
588
589#define REG64_IDX(_reg, idx) \
590	{ .addr = _reg(idx) }, \
591	{ .addr = _reg ## _UDW(idx) }
592
593static const struct drm_i915_reg_descriptor gen7_render_regs[] = {
594	REG64(GPGPU_THREADS_DISPATCHED),
595	REG64(HS_INVOCATION_COUNT),
596	REG64(DS_INVOCATION_COUNT),
597	REG64(IA_VERTICES_COUNT),
598	REG64(IA_PRIMITIVES_COUNT),
599	REG64(VS_INVOCATION_COUNT),
600	REG64(GS_INVOCATION_COUNT),
601	REG64(GS_PRIMITIVES_COUNT),
602	REG64(CL_INVOCATION_COUNT),
603	REG64(CL_PRIMITIVES_COUNT),
604	REG64(PS_INVOCATION_COUNT),
605	REG64(PS_DEPTH_COUNT),
606	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
607	REG64(MI_PREDICATE_SRC0),
608	REG64(MI_PREDICATE_SRC1),
609	REG32(GEN7_3DPRIM_END_OFFSET),
610	REG32(GEN7_3DPRIM_START_VERTEX),
611	REG32(GEN7_3DPRIM_VERTEX_COUNT),
612	REG32(GEN7_3DPRIM_INSTANCE_COUNT),
613	REG32(GEN7_3DPRIM_START_INSTANCE),
614	REG32(GEN7_3DPRIM_BASE_VERTEX),
615	REG32(GEN7_GPGPU_DISPATCHDIMX),
616	REG32(GEN7_GPGPU_DISPATCHDIMY),
617	REG32(GEN7_GPGPU_DISPATCHDIMZ),
618	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
619	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 0),
620	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 1),
621	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 2),
622	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 3),
623	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 0),
624	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 1),
625	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 2),
626	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 3),
627	REG32(GEN7_SO_WRITE_OFFSET(0)),
628	REG32(GEN7_SO_WRITE_OFFSET(1)),
629	REG32(GEN7_SO_WRITE_OFFSET(2)),
630	REG32(GEN7_SO_WRITE_OFFSET(3)),
631	REG32(GEN7_L3SQCREG1),
632	REG32(GEN7_L3CNTLREG2),
633	REG32(GEN7_L3CNTLREG3),
634	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
635};
636
637static const struct drm_i915_reg_descriptor hsw_render_regs[] = {
638	REG64_IDX(HSW_CS_GPR, 0),
639	REG64_IDX(HSW_CS_GPR, 1),
640	REG64_IDX(HSW_CS_GPR, 2),
641	REG64_IDX(HSW_CS_GPR, 3),
642	REG64_IDX(HSW_CS_GPR, 4),
643	REG64_IDX(HSW_CS_GPR, 5),
644	REG64_IDX(HSW_CS_GPR, 6),
645	REG64_IDX(HSW_CS_GPR, 7),
646	REG64_IDX(HSW_CS_GPR, 8),
647	REG64_IDX(HSW_CS_GPR, 9),
648	REG64_IDX(HSW_CS_GPR, 10),
649	REG64_IDX(HSW_CS_GPR, 11),
650	REG64_IDX(HSW_CS_GPR, 12),
651	REG64_IDX(HSW_CS_GPR, 13),
652	REG64_IDX(HSW_CS_GPR, 14),
653	REG64_IDX(HSW_CS_GPR, 15),
654	REG32(HSW_SCRATCH1,
655	      .mask = ~HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE,
656	      .value = 0),
657	REG32(HSW_ROW_CHICKEN3,
658	      .mask = ~(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE << 16 |
659                        HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE),
660	      .value = 0),
661};
662
663static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
664	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
665	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
666	REG32(BCS_SWCTRL),
667	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
668};
669
670static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
671	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
672	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
673	REG32(BCS_SWCTRL),
674	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
675	REG32_IDX(RING_CTX_TIMESTAMP, BLT_RING_BASE),
676	REG64_IDX(BCS_GPR, 0),
677	REG64_IDX(BCS_GPR, 1),
678	REG64_IDX(BCS_GPR, 2),
679	REG64_IDX(BCS_GPR, 3),
680	REG64_IDX(BCS_GPR, 4),
681	REG64_IDX(BCS_GPR, 5),
682	REG64_IDX(BCS_GPR, 6),
683	REG64_IDX(BCS_GPR, 7),
684	REG64_IDX(BCS_GPR, 8),
685	REG64_IDX(BCS_GPR, 9),
686	REG64_IDX(BCS_GPR, 10),
687	REG64_IDX(BCS_GPR, 11),
688	REG64_IDX(BCS_GPR, 12),
689	REG64_IDX(BCS_GPR, 13),
690	REG64_IDX(BCS_GPR, 14),
691	REG64_IDX(BCS_GPR, 15),
692};
693
694#undef REG64
695#undef REG32
696
697struct drm_i915_reg_table {
698	const struct drm_i915_reg_descriptor *regs;
699	int num_regs;
700};
701
702static const struct drm_i915_reg_table ivb_render_reg_tables[] = {
703	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
704};
705
706static const struct drm_i915_reg_table ivb_blt_reg_tables[] = {
707	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
708};
709
710static const struct drm_i915_reg_table hsw_render_reg_tables[] = {
711	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
712	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs) },
713};
714
715static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
716	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
717};
718
719static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
720	{ gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
721};
722
723static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
724{
725	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
726	u32 subclient =
727		(cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT;
728
729	if (client == INSTR_MI_CLIENT)
730		return 0x3F;
731	else if (client == INSTR_RC_CLIENT) {
732		if (subclient == INSTR_MEDIA_SUBCLIENT)
733			return 0xFFFF;
734		else
735			return 0xFF;
736	}
737
738	DRM_DEBUG("CMD: Abnormal rcs cmd length! 0x%08X\n", cmd_header);
739	return 0;
740}
741
742static u32 gen7_bsd_get_cmd_length_mask(u32 cmd_header)
743{
744	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
745	u32 subclient =
746		(cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT;
747	u32 op = (cmd_header & INSTR_26_TO_24_MASK) >> INSTR_26_TO_24_SHIFT;
748
749	if (client == INSTR_MI_CLIENT)
750		return 0x3F;
751	else if (client == INSTR_RC_CLIENT) {
752		if (subclient == INSTR_MEDIA_SUBCLIENT) {
753			if (op == 6)
754				return 0xFFFF;
755			else
756				return 0xFFF;
757		} else
758			return 0xFF;
759	}
760
761	DRM_DEBUG("CMD: Abnormal bsd cmd length! 0x%08X\n", cmd_header);
762	return 0;
763}
764
765static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
766{
767	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
768
769	if (client == INSTR_MI_CLIENT)
770		return 0x3F;
771	else if (client == INSTR_BC_CLIENT)
772		return 0xFF;
773
774	DRM_DEBUG("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
775	return 0;
776}
777
778static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
779{
780	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
781
782	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
783		return 0xFF;
784
785	DRM_DEBUG("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
786	return 0;
787}
788
789static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
790				 const struct drm_i915_cmd_table *cmd_tables,
791				 int cmd_table_count)
792{
793	int i;
794	bool ret = true;
795
796	if (!cmd_tables || cmd_table_count == 0)
797		return true;
798
799	for (i = 0; i < cmd_table_count; i++) {
800		const struct drm_i915_cmd_table *table = &cmd_tables[i];
801		u32 previous = 0;
802		int j;
803
804		for (j = 0; j < table->count; j++) {
805			const struct drm_i915_cmd_descriptor *desc =
806				&table->table[j];
807			u32 curr = desc->cmd.value & desc->cmd.mask;
808
809			if (curr < previous) {
810				drm_err(&engine->i915->drm,
811					"CMD: %s [%d] command table not sorted: "
812					"table=%d entry=%d cmd=0x%08X prev=0x%08X\n",
813					engine->name, engine->id,
814					i, j, curr, previous);
815				ret = false;
816			}
817
818			previous = curr;
819		}
820	}
821
822	return ret;
823}
824
825static bool check_sorted(const struct intel_engine_cs *engine,
826			 const struct drm_i915_reg_descriptor *reg_table,
827			 int reg_count)
828{
829	int i;
830	u32 previous = 0;
831	bool ret = true;
832
833	for (i = 0; i < reg_count; i++) {
834		u32 curr = i915_mmio_reg_offset(reg_table[i].addr);
835
836		if (curr < previous) {
837			drm_err(&engine->i915->drm,
838				"CMD: %s [%d] register table not sorted: "
839				"entry=%d reg=0x%08X prev=0x%08X\n",
840				engine->name, engine->id,
841				i, curr, previous);
842			ret = false;
843		}
844
845		previous = curr;
846	}
847
848	return ret;
849}
850
851static bool validate_regs_sorted(struct intel_engine_cs *engine)
852{
853	int i;
854	const struct drm_i915_reg_table *table;
855
856	for (i = 0; i < engine->reg_table_count; i++) {
857		table = &engine->reg_tables[i];
858		if (!check_sorted(engine, table->regs, table->num_regs))
859			return false;
860	}
861
862	return true;
863}
864
865struct cmd_node {
866	const struct drm_i915_cmd_descriptor *desc;
867	struct hlist_node node;
868};
869
870/*
871 * Different command ranges have different numbers of bits for the opcode. For
872 * example, MI commands use bits 31:23 while 3D commands use bits 31:16. The
873 * problem is that, for example, MI commands use bits 22:16 for other fields
874 * such as GGTT vs PPGTT bits. If we include those bits in the mask then when
875 * we mask a command from a batch it could hash to the wrong bucket due to
876 * non-opcode bits being set. But if we don't include those bits, some 3D
877 * commands may hash to the same bucket due to not including opcode bits that
878 * make the command unique. For now, we will risk hashing to the same bucket.
879 */
880static inline u32 cmd_header_key(u32 x)
881{
882	switch (x >> INSTR_CLIENT_SHIFT) {
883	default:
884	case INSTR_MI_CLIENT:
885		return x >> STD_MI_OPCODE_SHIFT;
886	case INSTR_RC_CLIENT:
887		return x >> STD_3D_OPCODE_SHIFT;
888	case INSTR_BC_CLIENT:
889		return x >> STD_2D_OPCODE_SHIFT;
890	}
891}
892
893static int init_hash_table(struct intel_engine_cs *engine,
894			   const struct drm_i915_cmd_table *cmd_tables,
895			   int cmd_table_count)
896{
897	int i, j;
898
899	hash_init(engine->cmd_hash);
900
901	for (i = 0; i < cmd_table_count; i++) {
902		const struct drm_i915_cmd_table *table = &cmd_tables[i];
903
904		for (j = 0; j < table->count; j++) {
905			const struct drm_i915_cmd_descriptor *desc =
906				&table->table[j];
907			struct cmd_node *desc_node =
908				kmalloc(sizeof(*desc_node), GFP_KERNEL);
909
910			if (!desc_node)
911				return -ENOMEM;
912
913			desc_node->desc = desc;
914			hash_add(engine->cmd_hash, &desc_node->node,
915				 cmd_header_key(desc->cmd.value));
916		}
917	}
918
919	return 0;
920}
921
922static void fini_hash_table(struct intel_engine_cs *engine)
923{
924	struct hlist_node *tmp;
925	struct cmd_node *desc_node;
926	int i;
927
928	hash_for_each_safe(engine->cmd_hash, i, tmp, desc_node, node) {
929		hash_del(&desc_node->node);
930		kfree(desc_node);
931	}
932}
933
934/**
935 * intel_engine_init_cmd_parser() - set cmd parser related fields for an engine
936 * @engine: the engine to initialize
937 *
938 * Optionally initializes fields related to batch buffer command parsing in the
939 * struct intel_engine_cs based on whether the platform requires software
940 * command parsing.
941 */
942int intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
943{
944	const struct drm_i915_cmd_table *cmd_tables;
945	int cmd_table_count;
946	int ret;
947
948	if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
949					  engine->class == COPY_ENGINE_CLASS))
950		return 0;
951
952	switch (engine->class) {
953	case RENDER_CLASS:
954		if (IS_HASWELL(engine->i915)) {
955			cmd_tables = hsw_render_ring_cmd_table;
956			cmd_table_count =
957				ARRAY_SIZE(hsw_render_ring_cmd_table);
958		} else {
959			cmd_tables = gen7_render_cmd_table;
960			cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table);
961		}
962
963		if (IS_HASWELL(engine->i915)) {
964			engine->reg_tables = hsw_render_reg_tables;
965			engine->reg_table_count = ARRAY_SIZE(hsw_render_reg_tables);
966		} else {
967			engine->reg_tables = ivb_render_reg_tables;
968			engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
969		}
970		engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
971		break;
972	case VIDEO_DECODE_CLASS:
973		cmd_tables = gen7_video_cmd_table;
974		cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table);
975		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
976		break;
977	case COPY_ENGINE_CLASS:
978		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
979		if (IS_GEN(engine->i915, 9)) {
980			cmd_tables = gen9_blt_cmd_table;
981			cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
982			engine->get_cmd_length_mask =
983				gen9_blt_get_cmd_length_mask;
984
985			/* BCS Engine unsafe without parser */
986			engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
987		} else if (IS_HASWELL(engine->i915)) {
988			cmd_tables = hsw_blt_ring_cmd_table;
989			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
990		} else {
991			cmd_tables = gen7_blt_cmd_table;
992			cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
993		}
994
995		if (IS_GEN(engine->i915, 9)) {
996			engine->reg_tables = gen9_blt_reg_tables;
997			engine->reg_table_count =
998				ARRAY_SIZE(gen9_blt_reg_tables);
999		} else if (IS_HASWELL(engine->i915)) {
1000			engine->reg_tables = hsw_blt_reg_tables;
1001			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
1002		} else {
1003			engine->reg_tables = ivb_blt_reg_tables;
1004			engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
1005		}
1006		break;
1007	case VIDEO_ENHANCEMENT_CLASS:
1008		cmd_tables = hsw_vebox_cmd_table;
1009		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table);
1010		/* VECS can use the same length_mask function as VCS */
1011		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
1012		break;
1013	default:
1014		MISSING_CASE(engine->class);
1015		goto out;
1016	}
1017
1018	if (!validate_cmds_sorted(engine, cmd_tables, cmd_table_count)) {
1019		drm_err(&engine->i915->drm,
1020			"%s: command descriptions are not sorted\n",
1021			engine->name);
1022		goto out;
1023	}
1024	if (!validate_regs_sorted(engine)) {
1025		drm_err(&engine->i915->drm,
1026			"%s: registers are not sorted\n", engine->name);
1027		goto out;
1028	}
1029
1030	ret = init_hash_table(engine, cmd_tables, cmd_table_count);
1031	if (ret) {
1032		drm_err(&engine->i915->drm,
1033			"%s: initialised failed!\n", engine->name);
1034		fini_hash_table(engine);
1035		goto out;
1036	}
1037
1038	engine->flags |= I915_ENGINE_USING_CMD_PARSER;
1039
1040out:
1041	if (intel_engine_requires_cmd_parser(engine) &&
1042	    !intel_engine_using_cmd_parser(engine))
1043		return -EINVAL;
1044
1045	return 0;
1046}
1047
1048/**
1049 * intel_engine_cleanup_cmd_parser() - clean up cmd parser related fields
1050 * @engine: the engine to clean up
1051 *
1052 * Releases any resources related to command parsing that may have been
1053 * initialized for the specified engine.
1054 */
1055void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
1056{
1057	if (!intel_engine_using_cmd_parser(engine))
1058		return;
1059
1060	fini_hash_table(engine);
1061}
1062
1063static const struct drm_i915_cmd_descriptor*
1064find_cmd_in_table(struct intel_engine_cs *engine,
1065		  u32 cmd_header)
1066{
1067	struct cmd_node *desc_node;
1068
1069	hash_for_each_possible(engine->cmd_hash, desc_node, node,
1070			       cmd_header_key(cmd_header)) {
1071		const struct drm_i915_cmd_descriptor *desc = desc_node->desc;
1072		if (((cmd_header ^ desc->cmd.value) & desc->cmd.mask) == 0)
1073			return desc;
1074	}
1075
1076	return NULL;
1077}
1078
1079/*
1080 * Returns a pointer to a descriptor for the command specified by cmd_header.
1081 *
1082 * The caller must supply space for a default descriptor via the default_desc
1083 * parameter. If no descriptor for the specified command exists in the engine's
1084 * command parser tables, this function fills in default_desc based on the
1085 * engine's default length encoding and returns default_desc.
1086 */
1087static const struct drm_i915_cmd_descriptor*
1088find_cmd(struct intel_engine_cs *engine,
1089	 u32 cmd_header,
1090	 const struct drm_i915_cmd_descriptor *desc,
1091	 struct drm_i915_cmd_descriptor *default_desc)
1092{
1093	u32 mask;
1094
1095	if (((cmd_header ^ desc->cmd.value) & desc->cmd.mask) == 0)
1096		return desc;
1097
1098	desc = find_cmd_in_table(engine, cmd_header);
1099	if (desc)
1100		return desc;
1101
1102	mask = engine->get_cmd_length_mask(cmd_header);
1103	if (!mask)
1104		return NULL;
1105
1106	default_desc->cmd.value = cmd_header;
1107	default_desc->cmd.mask = ~0u << MIN_OPCODE_SHIFT;
1108	default_desc->length.mask = mask;
1109	default_desc->flags = CMD_DESC_SKIP;
1110	return default_desc;
1111}
1112
1113static const struct drm_i915_reg_descriptor *
1114__find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr)
1115{
1116	int start = 0, end = count;
1117	while (start < end) {
1118		int mid = start + (end - start) / 2;
1119		int ret = addr - i915_mmio_reg_offset(table[mid].addr);
1120		if (ret < 0)
1121			end = mid;
1122		else if (ret > 0)
1123			start = mid + 1;
1124		else
1125			return &table[mid];
1126	}
1127	return NULL;
1128}
1129
1130static const struct drm_i915_reg_descriptor *
1131find_reg(const struct intel_engine_cs *engine, u32 addr)
1132{
1133	const struct drm_i915_reg_table *table = engine->reg_tables;
1134	const struct drm_i915_reg_descriptor *reg = NULL;
1135	int count = engine->reg_table_count;
1136
1137	for (; !reg && (count > 0); ++table, --count)
1138		reg = __find_reg(table->regs, table->num_regs, addr);
1139
1140	return reg;
1141}
1142
1143/* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
1144static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
1145		       struct drm_i915_gem_object *src_obj,
1146		       u32 offset, u32 length)
1147{
1148	unsigned int src_needs_clflush;
1149	unsigned int dst_needs_clflush;
1150	void *dst, *src;
1151	int ret;
1152
1153	ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
1154	if (ret)
1155		return ERR_PTR(ret);
1156
1157	dst = i915_gem_object_pin_map(dst_obj, I915_MAP_FORCE_WB);
1158	i915_gem_object_finish_access(dst_obj);
1159	if (IS_ERR(dst))
1160		return dst;
1161
1162	ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
1163	if (ret) {
1164		i915_gem_object_unpin_map(dst_obj);
1165		return ERR_PTR(ret);
1166	}
1167
1168	src = ERR_PTR(-ENODEV);
1169	if (src_needs_clflush && i915_has_memcpy_from_wc()) {
1170		src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
1171		if (!IS_ERR(src)) {
1172			i915_unaligned_memcpy_from_wc(dst,
1173						      src + offset,
1174						      length);
1175			i915_gem_object_unpin_map(src_obj);
1176		}
1177	}
1178	if (IS_ERR(src)) {
1179		unsigned long x, n, remain;
1180		void *ptr;
1181
1182		/*
1183		 * We can avoid clflushing partial cachelines before the write
1184		 * if we only every write full cache-lines. Since we know that
1185		 * both the source and destination are in multiples of
1186		 * PAGE_SIZE, we can simply round up to the next cacheline.
1187		 * We don't care about copying too much here as we only
1188		 * validate up to the end of the batch.
1189		 */
1190		remain = length;
1191		if (dst_needs_clflush & CLFLUSH_BEFORE)
1192			remain = round_up(remain,
1193					  boot_cpu_data.x86_clflush_size);
1194
1195		ptr = dst;
1196		x = offset_in_page(offset);
1197		for (n = offset >> PAGE_SHIFT; remain; n++) {
1198			int len = min(remain, PAGE_SIZE - x);
1199
1200			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
1201			if (src_needs_clflush)
1202				drm_clflush_virt_range(src + x, len);
1203			memcpy(ptr, src + x, len);
1204			kunmap_atomic(src);
1205
1206			ptr += len;
1207			remain -= len;
1208			x = 0;
1209		}
1210	}
1211
1212	i915_gem_object_finish_access(src_obj);
1213
1214	memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
1215
1216	return dst;
1217}
1218
1219static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc,
1220			       const u32 cmd)
1221{
1222	return desc->cmd.value == (cmd & desc->cmd.mask);
1223}
1224
1225static bool check_cmd(const struct intel_engine_cs *engine,
1226		      const struct drm_i915_cmd_descriptor *desc,
1227		      const u32 *cmd, u32 length)
1228{
1229	if (desc->flags & CMD_DESC_SKIP)
1230		return true;
1231
1232	if (desc->flags & CMD_DESC_REJECT) {
1233		DRM_DEBUG("CMD: Rejected command: 0x%08X\n", *cmd);
1234		return false;
1235	}
1236
1237	if (desc->flags & CMD_DESC_REGISTER) {
1238		/*
1239		 * Get the distance between individual register offset
1240		 * fields if the command can perform more than one
1241		 * access at a time.
1242		 */
1243		const u32 step = desc->reg.step ? desc->reg.step : length;
1244		u32 offset;
1245
1246		for (offset = desc->reg.offset; offset < length;
1247		     offset += step) {
1248			const u32 reg_addr = cmd[offset] & desc->reg.mask;
1249			const struct drm_i915_reg_descriptor *reg =
1250				find_reg(engine, reg_addr);
1251
1252			if (!reg) {
1253				DRM_DEBUG("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
1254					  reg_addr, *cmd, engine->name);
1255				return false;
1256			}
1257
1258			/*
1259			 * Check the value written to the register against the
1260			 * allowed mask/value pair given in the whitelist entry.
1261			 */
1262			if (reg->mask) {
1263				if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) {
1264					DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n",
1265						  reg_addr);
1266					return false;
1267				}
1268
1269				if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) {
1270					DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n",
1271						  reg_addr);
1272					return false;
1273				}
1274
1275				if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) &&
1276				    (offset + 2 > length ||
1277				     (cmd[offset + 1] & reg->mask) != reg->value)) {
1278					DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n",
1279						  reg_addr);
1280					return false;
1281				}
1282			}
1283		}
1284	}
1285
1286	if (desc->flags & CMD_DESC_BITMASK) {
1287		int i;
1288
1289		for (i = 0; i < MAX_CMD_DESC_BITMASKS; i++) {
1290			u32 dword;
1291
1292			if (desc->bits[i].mask == 0)
1293				break;
1294
1295			if (desc->bits[i].condition_mask != 0) {
1296				u32 offset =
1297					desc->bits[i].condition_offset;
1298				u32 condition = cmd[offset] &
1299					desc->bits[i].condition_mask;
1300
1301				if (condition == 0)
1302					continue;
1303			}
1304
1305			if (desc->bits[i].offset >= length) {
1306				DRM_DEBUG("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
1307					  *cmd, engine->name);
1308				return false;
1309			}
1310
1311			dword = cmd[desc->bits[i].offset] &
1312				desc->bits[i].mask;
1313
1314			if (dword != desc->bits[i].expected) {
1315				DRM_DEBUG("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (%s)\n",
1316					  *cmd,
1317					  desc->bits[i].mask,
1318					  desc->bits[i].expected,
1319					  dword, engine->name);
1320				return false;
1321			}
1322		}
1323	}
1324
1325	return true;
1326}
1327
1328static int check_bbstart(u32 *cmd, u32 offset, u32 length,
1329			 u32 batch_length,
1330			 u64 batch_addr,
1331			 u64 shadow_addr,
1332			 const unsigned long *jump_whitelist)
1333{
1334	u64 jump_offset, jump_target;
1335	u32 target_cmd_offset, target_cmd_index;
1336
1337	/* For igt compatibility on older platforms */
1338	if (!jump_whitelist) {
1339		DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
1340		return -EACCES;
1341	}
1342
1343	if (length != 3) {
1344		DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n",
1345			  length);
1346		return -EINVAL;
1347	}
1348
1349	jump_target = *(u64 *)(cmd + 1);
1350	jump_offset = jump_target - batch_addr;
1351
1352	/*
1353	 * Any underflow of jump_target is guaranteed to be outside the range
1354	 * of a u32, so >= test catches both too large and too small
1355	 */
1356	if (jump_offset >= batch_length) {
1357		DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
1358			  jump_target);
1359		return -EINVAL;
1360	}
1361
1362	/*
1363	 * This cannot overflow a u32 because we already checked jump_offset
1364	 * is within the BB, and the batch_length is a u32
1365	 */
1366	target_cmd_offset = lower_32_bits(jump_offset);
1367	target_cmd_index = target_cmd_offset / sizeof(u32);
1368
1369	*(u64 *)(cmd + 1) = shadow_addr + target_cmd_offset;
1370
1371	if (target_cmd_index == offset)
1372		return 0;
1373
1374	if (IS_ERR(jump_whitelist))
1375		return PTR_ERR(jump_whitelist);
1376
1377	if (!test_bit(target_cmd_index, jump_whitelist)) {
1378		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
1379			  jump_target);
1380		return -EINVAL;
1381	}
1382
1383	return 0;
1384}
1385
1386static unsigned long *alloc_whitelist(u32 batch_length)
1387{
1388	unsigned long *jmp;
1389
1390	/*
1391	 * We expect batch_length to be less than 256KiB for known users,
1392	 * i.e. we need at most an 8KiB bitmap allocation which should be
1393	 * reasonably cheap due to kmalloc caches.
1394	 */
1395
1396	/* Prefer to report transient allocation failure rather than hit oom */
1397	jmp = bitmap_zalloc(DIV_ROUND_UP(batch_length, sizeof(u32)),
1398			    GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
1399	if (!jmp)
1400		return ERR_PTR(-ENOMEM);
1401
1402	return jmp;
1403}
1404
1405#define LENGTH_BIAS 2
1406
1407/**
1408 * intel_engine_cmd_parser() - parse a batch buffer for privilege violations
1409 * @engine: the engine on which the batch is to execute
1410 * @batch: the batch buffer in question
1411 * @batch_offset: byte offset in the batch at which execution starts
1412 * @batch_length: length of the commands in batch_obj
1413 * @shadow: validated copy of the batch buffer in question
1414 * @trampoline: whether to emit a conditional trampoline at the end of the batch
1415 *
1416 * Parses the specified batch buffer looking for privilege violations as
1417 * described in the overview.
1418 *
1419 * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
1420 * if the batch appears legal but should use hardware parsing
1421 */
1422
1423int intel_engine_cmd_parser(struct intel_engine_cs *engine,
1424			    struct i915_vma *batch,
1425			    unsigned long batch_offset,
1426			    unsigned long batch_length,
1427			    struct i915_vma *shadow,
1428			    bool trampoline)
1429{
1430	u32 *cmd, *batch_end, offset = 0;
1431	struct drm_i915_cmd_descriptor default_desc = noop_desc;
1432	const struct drm_i915_cmd_descriptor *desc = &default_desc;
1433	unsigned long *jump_whitelist;
1434	u64 batch_addr, shadow_addr;
1435	int ret = 0;
1436
1437	GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
1438	GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
1439	GEM_BUG_ON(range_overflows_t(u64, batch_offset, batch_length,
1440				     batch->size));
1441	GEM_BUG_ON(!batch_length);
1442
1443	cmd = copy_batch(shadow->obj, batch->obj,
1444			 batch_offset, batch_length);
1445	if (IS_ERR(cmd)) {
1446		DRM_DEBUG("CMD: Failed to copy batch\n");
1447		return PTR_ERR(cmd);
1448	}
1449
1450	jump_whitelist = NULL;
1451	if (!trampoline)
1452		/* Defer failure until attempted use */
1453		jump_whitelist = alloc_whitelist(batch_length);
1454
1455	shadow_addr = gen8_canonical_addr(shadow->node.start);
1456	batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
1457
1458	/*
1459	 * We use the batch length as size because the shadow object is as
1460	 * large or larger and copy_batch() will write MI_NOPs to the extra
1461	 * space. Parsing should be faster in some cases this way.
1462	 */
1463	batch_end = cmd + batch_length / sizeof(*batch_end);
1464	do {
1465		u32 length;
1466
1467		if (*cmd == MI_BATCH_BUFFER_END)
1468			break;
1469
1470		desc = find_cmd(engine, *cmd, desc, &default_desc);
1471		if (!desc) {
1472			DRM_DEBUG("CMD: Unrecognized command: 0x%08X\n", *cmd);
1473			ret = -EINVAL;
1474			break;
1475		}
1476
1477		if (desc->flags & CMD_DESC_FIXED)
1478			length = desc->length.fixed;
1479		else
1480			length = (*cmd & desc->length.mask) + LENGTH_BIAS;
1481
1482		if ((batch_end - cmd) < length) {
1483			DRM_DEBUG("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
1484				  *cmd,
1485				  length,
1486				  batch_end - cmd);
1487			ret = -EINVAL;
1488			break;
1489		}
1490
1491		if (!check_cmd(engine, desc, cmd, length)) {
1492			ret = -EACCES;
1493			break;
1494		}
1495
1496		if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) {
1497			ret = check_bbstart(cmd, offset, length, batch_length,
1498					    batch_addr, shadow_addr,
1499					    jump_whitelist);
1500			break;
1501		}
1502
1503		if (!IS_ERR_OR_NULL(jump_whitelist))
1504			__set_bit(offset, jump_whitelist);
1505
1506		cmd += length;
1507		offset += length;
1508		if  (cmd >= batch_end) {
1509			DRM_DEBUG("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
1510			ret = -EINVAL;
1511			break;
1512		}
1513	} while (1);
1514
1515	if (trampoline) {
1516		/*
1517		 * With the trampoline, the shadow is executed twice.
1518		 *
1519		 *   1 - starting at offset 0, in privileged mode
1520		 *   2 - starting at offset batch_len, as non-privileged
1521		 *
1522		 * Only if the batch is valid and safe to execute, do we
1523		 * allow the first privileged execution to proceed. If not,
1524		 * we terminate the first batch and use the second batchbuffer
1525		 * entry to chain to the original unsafe non-privileged batch,
1526		 * leaving it to the HW to validate.
1527		 */
1528		*batch_end = MI_BATCH_BUFFER_END;
1529
1530		if (ret) {
1531			/* Batch unsafe to execute with privileges, cancel! */
1532			cmd = page_mask_bits(shadow->obj->mm.mapping);
1533			*cmd = MI_BATCH_BUFFER_END;
1534
1535			/* If batch is unsafe but valid, jump to the original */
1536			if (ret == -EACCES) {
1537				unsigned int flags;
1538
1539				flags = MI_BATCH_NON_SECURE_I965;
1540				if (IS_HASWELL(engine->i915))
1541					flags = MI_BATCH_NON_SECURE_HSW;
1542
1543				GEM_BUG_ON(!IS_GEN_RANGE(engine->i915, 6, 7));
1544				__gen6_emit_bb_start(batch_end,
1545						     batch_addr,
1546						     flags);
1547
1548				ret = 0; /* allow execution */
1549			}
1550		}
1551	}
1552
1553	i915_gem_object_flush_map(shadow->obj);
1554
1555	if (!IS_ERR_OR_NULL(jump_whitelist))
1556		kfree(jump_whitelist);
1557	i915_gem_object_unpin_map(shadow->obj);
1558	return ret;
1559}
1560
1561/**
1562 * i915_cmd_parser_get_version() - get the cmd parser version number
1563 * @dev_priv: i915 device private
1564 *
1565 * The cmd parser maintains a simple increasing integer version number suitable
1566 * for passing to userspace clients to determine what operations are permitted.
1567 *
1568 * Return: the current version number of the cmd parser
1569 */
1570int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
1571{
1572	struct intel_engine_cs *engine;
1573	bool active = false;
1574
1575	/* If the command parser is not enabled, report 0 - unsupported */
1576	for_each_uabi_engine(engine, dev_priv) {
1577		if (intel_engine_using_cmd_parser(engine)) {
1578			active = true;
1579			break;
1580		}
1581	}
1582	if (!active)
1583		return 0;
1584
1585	/*
1586	 * Command parser version history
1587	 *
1588	 * 1. Initial version. Checks batches and reports violations, but leaves
1589	 *    hardware parsing enabled (so does not allow new use cases).
1590	 * 2. Allow access to the MI_PREDICATE_SRC0 and
1591	 *    MI_PREDICATE_SRC1 registers.
1592	 * 3. Allow access to the GPGPU_THREADS_DISPATCHED register.
1593	 * 4. L3 atomic chicken bits of HSW_SCRATCH1 and HSW_ROW_CHICKEN3.
1594	 * 5. GPGPU dispatch compute indirect registers.
1595	 * 6. TIMESTAMP register and Haswell CS GPR registers
1596	 * 7. Allow MI_LOAD_REGISTER_REG between whitelisted registers.
1597	 * 8. Don't report cmd_check() failures as EINVAL errors to userspace;
1598	 *    rely on the HW to NOOP disallowed commands as it would without
1599	 *    the parser enabled.
1600	 * 9. Don't whitelist or handle oacontrol specially, as ownership
1601	 *    for oacontrol state is moving to i915-perf.
1602	 * 10. Support for Gen9 BCS Parsing
1603	 */
1604	return 10;
1605}
1606