drm/i915: Add gen9 BCS cmdparsing

For gen9 we enable cmdparsing on the BCS ring, specifically
to catch inadvertent accesses to sensitive registers

Unlike gen7/hsw, we use the parser only to block certain
registers. We can rely on h/w to block restricted commands,
so the command tables only provide enough info to allow the
parser to delineate each command, and identify commands that
access registers.

Note: This patch deliberately ignores checkpatch issues in
favour of matching the style of the surrounding code. We'll
correct the entire file in one go in a later patch.

v3: rebase (Mika)
v4: Add RING_TIMESTAMP registers to whitelist (Jon)

Signed-off-by: Jon Bloomfield <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Takashi Iwai <[email protected]>
Cc: Tyler Hicks <[email protected]>
Signed-off-by: Mika Kuoppala <[email protected]>
Reviewed-by: Chris Wilson <[email protected]>

Author: jbloomfi-intel

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -444,6 +444,47 @@ static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 };
 
+/*
+ * For Gen9 we can still rely on the h/w to enforce cmd security, and only
+ * need to re-enforce the register access checks. We therefore only need to
+ * teach the cmdparser how to find the end of each command, and identify
+ * register accesses. The table doesn't need to reject any commands, and so
+ * the only commands listed here are:
+ *   1) Those that touch registers
+ *   2) Those that do not have the default 8-bit length
+ *
+ * Note that the default MI length mask chosen for this table is 0xFF, not
+ * the 0x3F used on older devices. This is because the vast majority of MI
+ * cmds on Gen9 use a standard 8-bit Length field.
+ * All the Gen9 blitter instructions are standard 0xFF length mask, and
+ * none allow access to non-general registers, so in fact no BLT cmds are
+ * included in the table at all.
+ *
+ */
+static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
+	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
+	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      S  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      S  ),
+	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
+	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      S  ),
+	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 }    ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_STORE_REGISTER_MEM_GEN8,       SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_REGISTER_MEM_GEN8,        SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,    !F,  0xFF,  W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
+};
+
 static const struct drm_i915_cmd_descriptor noop_desc =
 	CMD(MI_NOOP, SMI, F, 1, S);
 
@@ -490,6 +531,11 @@ static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
 	{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
 };
 
+static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
+	{ gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
+};
+
+
 /*
  * Register whitelists, sorted by increasing register offset.
  */
@@ -605,6 +651,29 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
 	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
 };
 
+static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
+	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
+	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
+	REG32(BCS_SWCTRL),
+	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
+	REG64_IDX(BCS_GPR, 0),
+	REG64_IDX(BCS_GPR, 1),
+	REG64_IDX(BCS_GPR, 2),
+	REG64_IDX(BCS_GPR, 3),
+	REG64_IDX(BCS_GPR, 4),
+	REG64_IDX(BCS_GPR, 5),
+	REG64_IDX(BCS_GPR, 6),
+	REG64_IDX(BCS_GPR, 7),
+	REG64_IDX(BCS_GPR, 8),
+	REG64_IDX(BCS_GPR, 9),
+	REG64_IDX(BCS_GPR, 10),
+	REG64_IDX(BCS_GPR, 11),
+	REG64_IDX(BCS_GPR, 12),
+	REG64_IDX(BCS_GPR, 13),
+	REG64_IDX(BCS_GPR, 14),
+	REG64_IDX(BCS_GPR, 15),
+};
+
 #undef REG64
 #undef REG32
 
@@ -630,6 +699,10 @@ static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
 	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
 };
 
+static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
+	{ gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
+};
+
 static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
 {
 	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
@@ -685,6 +758,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	return 0;
 }
 
+static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
+		return 0xFF;
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
 static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
 				 const struct drm_i915_cmd_table *cmd_tables,
 				 int cmd_table_count)
@@ -842,7 +926,8 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 	int cmd_table_count;
 	int ret;
 
-	if (!IS_GEN(engine->i915, 7))
+	if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
+					  engine->class == COPY_ENGINE_CLASS))
 		return;
 
 	switch (engine->class) {
@@ -863,7 +948,6 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 			engine->reg_tables = ivb_render_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
 		}
-
 		engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
 		break;
 	case VIDEO_DECODE_CLASS:
@@ -872,23 +956,34 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case COPY_ENGINE_CLASS:
-		if (IS_HASWELL(engine->i915)) {
+		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
+		if (IS_GEN(engine->i915, 9)) {
+			cmd_tables = gen9_blt_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
+			engine->get_cmd_length_mask =
+				gen9_blt_get_cmd_length_mask;
+
+			/* BCS Engine unsafe without parser */
+			engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
+		} else if (IS_HASWELL(engine->i915)) {
 			cmd_tables = hsw_blt_ring_cmd_table;
 			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
 		} else {
 			cmd_tables = gen7_blt_cmd_table;
 			cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
 		}
 
-		if (IS_HASWELL(engine->i915)) {
+		if (IS_GEN(engine->i915, 9)) {
+			engine->reg_tables = gen9_blt_reg_tables;
+			engine->reg_table_count =
+				ARRAY_SIZE(gen9_blt_reg_tables);
+		} else if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
 		} else {
 			engine->reg_tables = ivb_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
 		}
-
-		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
 		break;
 	case VIDEO_ENHANCEMENT_CLASS:
 		cmd_tables = hsw_vebox_cmd_table;
@@ -1261,9 +1356,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 		}
 
 		/*
-		 * If the batch buffer contains a chained batch, return an
-		 * error that tells the caller to abort and dispatch the
-		 * workload as a non-secure batch.
+		 * We don't try to handle BATCH_BUFFER_START because it adds
+		 * non-trivial complexity. Instead we abort the scan and return
+		 * and error to indicate that the batch is unsafe.
 		 */
 		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
 			ret = -EACCES;
@@ -1342,6 +1437,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 	 *    the parser enabled.
 	 * 9. Don't whitelist or handle oacontrol specially, as ownership
 	 *    for oacontrol state is moving to i915-perf.
+	 * 10. Support for Gen9 BCS Parsing
 	 */
-	return 9;
+	return 10;
 }

drivers/gpu/drm/i915/i915_reg.h

@@ -555,6 +555,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  */
 #define BCS_SWCTRL _MMIO(0x22200)
 
+/* There are 16 GPR registers */
+#define BCS_GPR(n)	_MMIO(0x22600 + (n) * 8)
+#define BCS_GPR_UDW(n)	_MMIO(0x22600 + (n) * 8 + 4)
+
 #define GPGPU_THREADS_DISPATCHED        _MMIO(0x2290)
 #define GPGPU_THREADS_DISPATCHED_UDW	_MMIO(0x2290 + 4)
 #define HS_INVOCATION_COUNT             _MMIO(0x2300)