diff options
27 files changed, 1524 insertions, 803 deletions
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index bb8f5801218..4bfad5f5a84 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -125,11 +125,11 @@ drm_clflush_sg(struct sg_table *st) EXPORT_SYMBOL(drm_clflush_sg); void -drm_clflush_virt_range(char *addr, unsigned long length) +drm_clflush_virt_range(void *addr, unsigned long length) { #if defined(CONFIG_X86) if (cpu_has_clflush) { - char *end = addr + length; + void *end = addr + length; mb(); for (; addr < end; addr += boot_cpu_data.x86_clflush_size) clflush(addr); diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 73ed59eff13..7213c38a4d9 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -72,7 +72,7 @@ config DRM_I915_PRELIMINARY_HW_SUPPORT config DRM_I915_UMS bool "Enable userspace modesetting on Intel hardware (DEPRECATED)" - depends on DRM_I915 + depends on DRM_I915 && BROKEN default n help Choose this option if you still need userspace modesetting. diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c index 8155ded7907..ccac3a151c6 100644 --- a/drivers/gpu/drm/i915/dvo_ns2501.c +++ b/drivers/gpu/drm/i915/dvo_ns2501.c @@ -233,9 +233,8 @@ static enum drm_mode_status ns2501_mode_valid(struct intel_dvo_device *dvo, struct drm_display_mode *mode) { DRM_DEBUG_KMS - ("%s: is mode valid (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d)\n", - __FUNCTION__, mode->hdisplay, mode->htotal, mode->vdisplay, - mode->vtotal); + ("is mode valid (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d)\n", + mode->hdisplay, mode->htotal, mode->vdisplay, mode->vtotal); /* * Currently, these are all the modes I have data from. @@ -261,9 +260,8 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo, struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv); DRM_DEBUG_KMS - ("%s: set mode (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d).\n", - __FUNCTION__, mode->hdisplay, mode->htotal, mode->vdisplay, - mode->vtotal); + ("set mode (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d).\n", + mode->hdisplay, mode->htotal, mode->vdisplay, mode->vtotal); /* * Where do I find the native resolution for which scaling is not required??? @@ -277,8 +275,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo, if (mode->hdisplay == 800 && mode->vdisplay == 600) { /* mode 277 */ ns->reg_8_shadow &= ~NS2501_8_BPAS; - DRM_DEBUG_KMS("%s: switching to 800x600\n", - __FUNCTION__); + DRM_DEBUG_KMS("switching to 800x600\n"); /* * No, I do not know where this data comes from. @@ -341,8 +338,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo, } else if (mode->hdisplay == 640 && mode->vdisplay == 480) { /* mode 274 */ - DRM_DEBUG_KMS("%s: switching to 640x480\n", - __FUNCTION__); + DRM_DEBUG_KMS("switching to 640x480\n"); /* * No, I do not know where this data comes from. * It is just what the video bios left in the DVO, so @@ -406,8 +402,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo, } else if (mode->hdisplay == 1024 && mode->vdisplay == 768) { /* mode 280 */ - DRM_DEBUG_KMS("%s: switching to 1024x768\n", - __FUNCTION__); + DRM_DEBUG_KMS("switching to 1024x768\n"); /* * This might or might not work, actually. I'm silently * assuming here that the native panel resolution is @@ -458,8 +453,7 @@ static void ns2501_dpms(struct intel_dvo_device *dvo, bool enable) struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv); unsigned char ch; - DRM_DEBUG_KMS("%s: Trying set the dpms of the DVO to %i\n", - __FUNCTION__, enable); + DRM_DEBUG_KMS("Trying set the dpms of the DVO to %i\n", enable); ch = ns->reg_8_shadow; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 4cf6d020d51..29184d6c002 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -86,6 +86,357 @@ * general bitmasking mechanism. */ +#define STD_MI_OPCODE_MASK 0xFF800000 +#define STD_3D_OPCODE_MASK 0xFFFF0000 +#define STD_2D_OPCODE_MASK 0xFFC00000 +#define STD_MFX_OPCODE_MASK 0xFFFF0000 + +#define CMD(op, opm, f, lm, fl, ...) \ + { \ + .flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \ + .cmd = { (op), (opm) }, \ + .length = { (lm) }, \ + __VA_ARGS__ \ + } + +/* Convenience macros to compress the tables */ +#define SMI STD_MI_OPCODE_MASK +#define S3D STD_3D_OPCODE_MASK +#define S2D STD_2D_OPCODE_MASK +#define SMFX STD_MFX_OPCODE_MASK +#define F true +#define S CMD_DESC_SKIP +#define R CMD_DESC_REJECT +#define W CMD_DESC_REGISTER +#define B CMD_DESC_BITMASK +#define M CMD_DESC_MASTER + +/* Command Mask Fixed Len Action + ---------------------------------------------------------- */ +static const struct drm_i915_cmd_descriptor common_cmds[] = { + CMD( MI_NOOP, SMI, F, 1, S ), + CMD( MI_USER_INTERRUPT, SMI, F, 1, R ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ), + CMD( MI_ARB_CHECK, SMI, F, 1, S ), + CMD( MI_REPORT_HEAD, SMI, F, 1, S ), + CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), + CMD( MI_SEMAPHORE_MBOX, SMI, !F, 0xFF, R ), + CMD( MI_STORE_DWORD_INDEX, SMI, !F, 0xFF, R ), + CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_STORE_REGISTER_MEM(1), SMI, !F, 0xFF, W | B, + .reg = { .offset = 1, .mask = 0x007FFFFC }, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_LOAD_REGISTER_MEM, SMI, !F, 0xFF, W | B, + .reg = { .offset = 1, .mask = 0x007FFFFC }, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ), +}; + +static const struct drm_i915_cmd_descriptor render_cmds[] = { + CMD( MI_FLUSH, SMI, F, 1, S ), + CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), + CMD( MI_PREDICATE, SMI, F, 1, S ), + CMD( MI_TOPOLOGY_FILTER, SMI, F, 1, S ), + CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), + CMD( MI_SET_CONTEXT, SMI, !F, 0xFF, R ), + CMD( MI_URB_CLEAR, SMI, !F, 0xFF, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_UPDATE_GTT, SMI, !F, 0xFF, R ), + CMD( MI_CLFLUSH, SMI, !F, 0x3FF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_REPORT_PERF_COUNT, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 1, + .mask = MI_REPORT_PERF_COUNT_GGTT, + .expected = 0, + }}, ), + CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( GFX_OP_3DSTATE_VF_STATISTICS, S3D, F, 1, S ), + CMD( PIPELINE_SELECT, S3D, F, 1, S ), + CMD( MEDIA_VFE_STATE, S3D, !F, 0xFFFF, B, + .bits = {{ + .offset = 2, + .mask = MEDIA_VFE_STATE_MMIO_ACCESS_MASK, + .expected = 0, + }}, ), + CMD( GPGPU_OBJECT, S3D, !F, 0xFF, S ), + CMD( GPGPU_WALKER, S3D, !F, 0xFF, S ), + CMD( GFX_OP_3DSTATE_SO_DECL_LIST, S3D, !F, 0x1FF, S ), + CMD( GFX_OP_PIPE_CONTROL(5), S3D, !F, 0xFF, B, + .bits = {{ + .offset = 1, + .mask = (PIPE_CONTROL_MMIO_WRITE | PIPE_CONTROL_NOTIFY), + .expected = 0, + }, + { + .offset = 1, + .mask = (PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_STORE_DATA_INDEX), + .expected = 0, + .condition_offset = 1, + .condition_mask = PIPE_CONTROL_POST_SYNC_OP_MASK, + }}, ), +}; + +static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { + CMD( MI_SET_PREDICATE, SMI, F, 1, S ), + CMD( MI_RS_CONTROL, SMI, F, 1, S ), + CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ), + CMD( MI_RS_CONTEXT, SMI, F, 1, S ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), + CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, R ), + CMD( MI_RS_STORE_DATA_IMM, SMI, !F, 0xFF, S ), + CMD( MI_LOAD_URB_MEM, SMI, !F, 0xFF, S ), + CMD( MI_STORE_URB_MEM, SMI, !F, 0xFF, S ), + CMD( GFX_OP_3DSTATE_DX9_CONSTANTF_VS, S3D, !F, 0x7FF, S ), + CMD( GFX_OP_3DSTATE_DX9_CONSTANTF_PS, S3D, !F, 0x7FF, S ), + + CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS, S3D, !F, 0x1FF, S ), + CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS, S3D, !F, 0x1FF, S ), + CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS, S3D, !F, 0x1FF, S ), + CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS, S3D, !F, 0x1FF, S ), + CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ), +}; + +static const struct drm_i915_cmd_descriptor video_cmds[] = { + CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3F, R ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 0, + .mask = MI_FLUSH_DW_NOTIFY, + .expected = 0, + }, + { + .offset = 1, + .mask = MI_FLUSH_DW_USE_GTT, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }, + { + .offset = 0, + .mask = MI_FLUSH_DW_STORE_INDEX, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }}, ), + CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + /* + * MFX_WAIT doesn't fit the way we handle length for most commands. + * It has a length field but it uses a non-standard length bias. + * It is always 1 dword though, so just treat it as fixed length. + */ + CMD( MFX_WAIT, SMFX, F, 1, S ), +}; + +static const struct drm_i915_cmd_descriptor vecs_cmds[] = { + CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3F, R ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 0, + .mask = MI_FLUSH_DW_NOTIFY, + .expected = 0, + }, + { + .offset = 1, + .mask = MI_FLUSH_DW_USE_GTT, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }, + { + .offset = 0, + .mask = MI_FLUSH_DW_STORE_INDEX, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }}, ), + CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), +}; + +static const struct drm_i915_cmd_descriptor blt_cmds[] = { + CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3F, R ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 0, + .mask = MI_FLUSH_DW_NOTIFY, + .expected = 0, + }, + { + .offset = 1, + .mask = MI_FLUSH_DW_USE_GTT, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }, + { + .offset = 0, + .mask = MI_FLUSH_DW_STORE_INDEX, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }}, ), + CMD( COLOR_BLT, S2D, !F, 0x3F, S ), + CMD( SRC_COPY_BLT, S2D, !F, 0x3F, S ), +}; + +static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = { + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), +}; + +#undef CMD +#undef SMI +#undef S3D +#undef S2D +#undef SMFX +#undef F +#undef S +#undef R +#undef W +#undef B +#undef M + +static const struct drm_i915_cmd_table gen7_render_cmds[] = { + { common_cmds, ARRAY_SIZE(common_cmds) }, + { render_cmds, ARRAY_SIZE(render_cmds) }, +}; + +static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = { + { common_cmds, ARRAY_SIZE(common_cmds) }, + { render_cmds, ARRAY_SIZE(render_cmds) }, + { hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) }, +}; + +static const struct drm_i915_cmd_table gen7_video_cmds[] = { + { common_cmds, ARRAY_SIZE(common_cmds) }, + { video_cmds, ARRAY_SIZE(video_cmds) }, +}; + +static const struct drm_i915_cmd_table hsw_vebox_cmds[] = { + { common_cmds, ARRAY_SIZE(common_cmds) }, + { vecs_cmds, ARRAY_SIZE(vecs_cmds) }, +}; + +static const struct drm_i915_cmd_table gen7_blt_cmds[] = { + { common_cmds, ARRAY_SIZE(common_cmds) }, + { blt_cmds, ARRAY_SIZE(blt_cmds) }, +}; + +static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = { + { common_cmds, ARRAY_SIZE(common_cmds) }, + { blt_cmds, ARRAY_SIZE(blt_cmds) }, + { hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) }, +}; + +/* + * Register whitelists, sorted by increasing register offset. + * + * Some registers that userspace accesses are 64 bits. The register + * access commands only allow 32-bit accesses. Hence, we have to include + * entries for both halves of the 64-bit registers. + */ + +/* Convenience macro for adding 64-bit registers */ +#define REG64(addr) (addr), (addr + sizeof(u32)) + +static const u32 gen7_render_regs[] = { + REG64(HS_INVOCATION_COUNT), + REG64(DS_INVOCATION_COUNT), + REG64(IA_VERTICES_COUNT), + REG64(IA_PRIMITIVES_COUNT), + REG64(VS_INVOCATION_COUNT), + REG64(GS_INVOCATION_COUNT), + REG64(GS_PRIMITIVES_COUNT), + REG64(CL_INVOCATION_COUNT), + REG64(CL_PRIMITIVES_COUNT), + REG64(PS_INVOCATION_COUNT), + REG64(PS_DEPTH_COUNT), + OACONTROL, /* Only allowed for LRI and SRM. See below. */ + REG64(GEN7_SO_NUM_PRIMS_WRITTEN(0)), + REG64(GEN7_SO_NUM_PRIMS_WRITTEN(1)), + REG64(GEN7_SO_NUM_PRIMS_WRITTEN(2)), + REG64(GEN7_SO_NUM_PRIMS_WRITTEN(3)), + GEN7_SO_WRITE_OFFSET(0), + GEN7_SO_WRITE_OFFSET(1), + GEN7_SO_WRITE_OFFSET(2), + GEN7_SO_WRITE_OFFSET(3), +}; + +static const u32 gen7_blt_regs[] = { + BCS_SWCTRL, +}; + +static const u32 ivb_master_regs[] = { + FORCEWAKE_MT, + DERRMR, + GEN7_PIPE_DE_LOAD_SL(PIPE_A), + GEN7_PIPE_DE_LOAD_SL(PIPE_B), + GEN7_PIPE_DE_LOAD_SL(PIPE_C), +}; + +static const u32 hsw_master_regs[] = { + FORCEWAKE_MT, + DERRMR, +}; + +#undef REG64 + static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) { u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT; @@ -137,12 +488,13 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) return 0; } -static void validate_cmds_sorted(struct intel_ring_buffer *ring) +static bool validate_cmds_sorted(struct intel_ring_buffer *ring) { int i; + bool ret = true; if (!ring->cmd_tables || ring->cmd_table_count == 0) - return; + return true; for (i = 0; i < ring->cmd_table_count; i++) { const struct drm_i915_cmd_table *table = &ring->cmd_tables[i]; @@ -154,35 +506,45 @@ static void validate_cmds_sorted(struct intel_ring_buffer *ring) &table->table[i]; u32 curr = desc->cmd.value & desc->cmd.mask; - if (curr < previous) + if (curr < previous) { DRM_ERROR("CMD: table not sorted ring=%d table=%d entry=%d cmd=0x%08X prev=0x%08X\n", ring->id, i, j, curr, previous); + ret = false; + } previous = curr; } } + + return ret; } -static void check_sorted(int ring_id, const u32 *reg_table, int reg_count) +static bool check_sorted(int ring_id, const u32 *reg_table, int reg_count) { int i; u32 previous = 0; + bool ret = true; for (i = 0; i < reg_count; i++) { u32 curr = reg_table[i]; - if (curr < previous) + if (curr < previous) { DRM_ERROR("CMD: table not sorted ring=%d entry=%d reg=0x%08X prev=0x%08X\n", ring_id, i, curr, previous); + ret = false; + } previous = curr; } + + return ret; } -static void validate_regs_sorted(struct intel_ring_buffer *ring) +static bool validate_regs_sorted(struct intel_ring_buffer *ring) { - check_sorted(ring->id, ring->reg_table, ring->reg_count); - check_sorted(ring->id, ring->master_reg_table, ring->master_reg_count); + return check_sorted(ring->id, ring->reg_table, ring->reg_count) && + check_sorted(ring->id, ring->master_reg_table, + ring->master_reg_count); } /** @@ -200,15 +562,58 @@ void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) switch (ring->id) { case RCS: + if (IS_HASWELL(ring->dev)) { + ring->cmd_tables = hsw_render_ring_cmds; + ring->cmd_table_count = + ARRAY_SIZE(hsw_render_ring_cmds); + } else { + ring->cmd_tables = gen7_render_cmds; + ring->cmd_table_count = ARRAY_SIZE(gen7_render_cmds); + } + + ring->reg_table = gen7_render_regs; + ring->reg_count = ARRAY_SIZE(gen7_render_regs); + + if (IS_HASWELL(ring->dev)) { + ring->master_reg_table = hsw_master_regs; + ring->master_reg_count = ARRAY_SIZE(hsw_master_regs); + } else { + ring->master_reg_table = ivb_master_regs; + ring->master_reg_count = ARRAY_SIZE(ivb_master_regs); + } + ring->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VCS: + ring->cmd_tables = gen7_video_cmds; + ring->cmd_table_count = ARRAY_SIZE(gen7_video_cmds); ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case BCS: + if (IS_HASWELL(ring->dev)) { + ring->cmd_tables = hsw_blt_ring_cmds; + ring->cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + } else { + ring->cmd_tables = gen7_blt_cmds; + ring->cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); + } + + ring->reg_table = gen7_blt_regs; + ring->reg_count = ARRAY_SIZE(gen7_blt_regs); + + if (IS_HASWELL(ring->dev)) { + ring->master_reg_table = hsw_master_regs; + ring->master_reg_count = ARRAY_SIZE(hsw_master_regs); + } else { + ring->master_reg_table = ivb_master_regs; + ring->master_reg_count = ARRAY_SIZE(ivb_master_regs); + } + ring->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VECS: + ring->cmd_tables = hsw_vebox_cmds; + ring->cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); /* VECS can use the same length_mask function as VCS */ ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; @@ -218,8 +623,8 @@ void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) BUG(); } - validate_cmds_sorted(ring); - validate_regs_sorted(ring); + BUG_ON(!validate_cmds_sorted(ring)); + BUG_ON(!validate_regs_sorted(ring)); } static const struct drm_i915_cmd_descriptor* @@ -331,13 +736,111 @@ finish: */ bool i915_needs_cmd_parser(struct intel_ring_buffer *ring) { + struct drm_i915_private *dev_priv = ring->dev->dev_private; + /* No command tables indicates a platform without parsing */ if (!ring->cmd_tables) return false; + /* + * XXX: VLV is Gen7 and therefore has cmd_tables, but has PPGTT + * disabled. That will cause all of the parser's PPGTT checks to + * fail. For now, disable parsing when PPGTT is off. + */ + if (!dev_priv->mm.aliasing_ppgtt) + return false; + return (i915.enable_cmd_parser == 1); } +static bool check_cmd(const struct intel_ring_buffer *ring, + const struct drm_i915_cmd_descriptor *desc, + const u32 *cmd, + const bool is_master, + bool *oacontrol_set) +{ + if (desc->flags & CMD_DESC_REJECT) { + DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd); + return false; + } + + if ((desc->flags & CMD_DESC_MASTER) && !is_master) { + DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", + *cmd); + return false; + } + + if (desc->flags & CMD_DESC_REGISTER) { + u32 reg_addr = cmd[desc->reg.offset] & desc->reg.mask; + + /* + * OACONTROL requires some special handling for writes. We + * want to make sure that any batch which enables OA also + * disables it before the end of the batch. The goal is to + * prevent one process from snooping on the perf data from + * another process. To do that, we need to check the value + * that will be written to the register. Hence, limit + * OACONTROL writes to only MI_LOAD_REGISTER_IMM commands. + */ + if (reg_addr == OACONTROL) { + if (desc->cmd.value == MI_LOAD_REGISTER_MEM) + return false; + + if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1)) + *oacontrol_set = (cmd[2] != 0); + } + + if (!valid_reg(ring->reg_table, + ring->reg_count, reg_addr)) { + if (!is_master || + !valid_reg(ring->master_reg_table, + ring->master_reg_count, + reg_addr)) { + DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (ring=%d)\n", + reg_addr, + *cmd, + ring->id); + return false; + } + } + } + + if (desc->flags & CMD_DESC_BITMASK) { + int i; + + for (i = 0; i < MAX_CMD_DESC_BITMASKS; i++) { + u32 dword; + + if (desc->bits[i].mask == 0) + break; + + if (desc->bits[i].condition_mask != 0) { + u32 offset = + desc->bits[i].condition_offset; + u32 condition = cmd[offset] & + desc->bits[i].condition_mask; + + if (condition == 0) + continue; + } + + dword = cmd[desc->bits[i].offset] & + desc->bits[i].mask; + + if (dword != desc->bits[i].expected) { + DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (ring=%d)\n", + *cmd, + desc->bits[i].mask, + desc->bits[i].expected, + dword, ring->id); + return false; + } + } + } + + return true; +} + #define LENGTH_BIAS 2 /** @@ -361,6 +864,7 @@ int i915_parse_cmds(struct intel_ring_buffer *ring, u32 *cmd, *batch_base, *batch_end; struct drm_i915_cmd_descriptor default_desc = { 0 }; int needs_clflush = 0; + bool oacontrol_set = false; /* OACONTROL tracking. See check_cmd() */ ret = i915_gem_obj_prepare_shmem_read(batch_obj, &needs_clflush); if (ret) { @@ -402,7 +906,7 @@ int i915_parse_cmds(struct intel_ring_buffer *ring, length = ((*cmd & desc->length.mask) + LENGTH_BIAS); if ((batch_end - cmd) < length) { - DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%d batchlen=%td\n", + DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n", *cmd, length, (unsigned long)(batch_end - cmd)); @@ -410,68 +914,19 @@ int i915_parse_cmds(struct intel_ring_buffer *ring, break; } - if (desc->flags & CMD_DESC_REJECT) { - DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd); - ret = -EINVAL; - break; - } - - if ((desc->flags & CMD_DESC_MASTER) && !is_master) { - DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", - *cmd); + if (!check_cmd(ring, desc, cmd, is_master, &oacontrol_set)) { ret = -EINVAL; break; } - if (desc->flags & CMD_DESC_REGISTER) { - u32 reg_addr = cmd[desc->reg.offset] & desc->reg.mask; - - if (!valid_reg(ring->reg_table, - ring->reg_count, reg_addr)) { - if (!is_master || - !valid_reg(ring->master_reg_table, - ring->master_reg_count, - reg_addr)) { - DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (ring=%d)\n", - reg_addr, - *cmd, - ring->id); - ret = -EINVAL; - break; - } - } - } - - if (desc->flags & CMD_DESC_BITMASK) { - int i; - - for (i = 0; i < MAX_CMD_DESC_BITMASKS; i++) { - u32 dword; - - if (desc->bits[i].mask == 0) - break; - - dword = cmd[desc->bits[i].offset] & - desc->bits[i].mask; - - if (dword != desc->bits[i].expected) { - DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (ring=%d)\n", - *cmd, - desc->bits[i].mask, - desc->bits[i].expected, - dword, ring->id); - ret = -EINVAL; - break; - } - } - - if (ret) - break; - } - cmd += length; } + if (oacontrol_set) { + DRM_DEBUG_DRIVER("CMD: batch set OACONTROL but did not clear it\n"); + ret = -EINVAL; + } + if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; @@ -483,3 +938,22 @@ int i915_parse_cmds(struct intel_ring_buffer *ring, return ret; } + +/** + * i915_cmd_parser_get_version() - get the cmd parser version number + * + * The cmd parser maintains a simple increasing integer version number suitable + * for passing to userspace clients to determine what operations are permitted. + * + * Return: the current version number of the cmd parser + */ +int i915_cmd_parser_get_version(void) +{ + /* + * Command parser version history + * + * 1. Initial version. Checks batches and reports violations, but leaves + * hardware parsing enabled (so does not allow new use cases). + */ + return 1; +} diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 195fe5bc0aa..1e83ae45041 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -966,7 +966,7 @@ static int i915_rstdby_delays(struct seq_file *m, void *unused) return 0; } -static int i915_cur_delayinfo(struct seq_file *m, void *unused) +static int i915_frequency_info(struct seq_file *m, void *unused) { struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; @@ -991,6 +991,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS); u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS); u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); + u32 rpmodectl, rpinclimit, rpdeclimit; u32 rpstat, cagf, reqf; u32 rpupei, rpcurup, rpprevup; u32 rpdownei, rpcurdown, rpprevdown; @@ -1011,6 +1012,10 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) reqf >>= 25; reqf *= GT_FREQUENCY_MULTIPLIER; + rpmodectl = I915_READ(GEN6_RP_CONTROL); + rpinclimit = I915_READ(GEN6_RP_UP_THRESHOLD); + rpdeclimit = I915_READ(GEN6_RP_DOWN_THRESHOLD); + rpstat = I915_READ(GEN6_RPSTAT1); rpupei = I915_READ(GEN6_RP_CUR_UP_EI); rpcurup = I915_READ(GEN6_RP_CUR_UP); @@ -1027,14 +1032,23 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); mutex_unlock(&dev->struct_mutex); + seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n", + I915_READ(GEN6_PMIER), + I915_READ(GEN6_PMIMR), + I915_READ(GEN6_PMISR), + I915_READ(GEN6_PMIIR), + I915_READ(GEN6_PMINTRMSK)); seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); - seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat); seq_printf(m, "Render p-state ratio: %d\n", (gt_perf_status & 0xff00) >> 8); seq_printf(m, "Render p-state VID: %d\n", gt_perf_status & 0xff); seq_printf(m, "Render p-state limit: %d\n", rp_state_limits & 0xff); + seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat); + seq_printf(m, "RPMODECTL: 0x%08x\n", rpmodectl); + seq_printf(m, "RPINCLIMIT: 0x%08x\n", rpinclimit); + seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit); seq_printf(m, "RPNSWREQ: %dMHz\n", reqf); seq_printf(m, "CAGF: %dMHz\n", cagf); seq_printf(m, "RP CUR UP EI: %dus\n", rpupei & @@ -1816,8 +1830,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) u64 pdp = I915_READ(ring->mmio_base + offset + 4); pdp <<= 32; pdp |= I915_READ(ring->mmio_base + offset); - for (i = 0; i < 4; i++) - seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp); + seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp); } } } @@ -2044,7 +2057,7 @@ static int i915_pc8_status(struct seq_file *m, void *unused) struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - if (!IS_HASWELL(dev)) { + if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) { seq_puts(m, "not supported\n"); return 0; } @@ -3774,7 +3787,7 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS}, {"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS}, {"i915_rstdby_delays", i915_rstdby_delays, 0}, - {"i915_cur_delayinfo", i915_cur_delayinfo, 0}, + {"i915_frequency_info", i915_frequency_info, 0}, {"i915_delayfreq_table", i915_delayfreq_table, 0}, {"i915_inttoext_table", i915_inttoext_table, 0}, {"i915_drpc_info", i915_drpc_info, 0}, diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 96177eec0a0..0b38f88c35f 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1017,6 +1017,9 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_HAS_EXEC_HANDLE_LUT: value = 1; break; + case I915_PARAM_CMD_PARSER_VERSION: + value = i915_cmd_parser_get_version(); + break; default: DRM_DEBUG("Unknown parameter %d\n", param->param); return -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 82f4d1f47d3..5d8250f7145 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -891,7 +891,36 @@ static int i915_pm_poweroff(struct device *dev) return i915_drm_freeze(drm_dev); } -static int i915_runtime_suspend(struct device *device) +static void snb_runtime_suspend(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + + intel_runtime_pm_disable_interrupts(dev); +} + +static void hsw_runtime_suspend(struct drm_i915_private *dev_priv) +{ + hsw_enable_pc8(dev_priv); +} + +static void snb_runtime_resume(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + + intel_runtime_pm_restore_interrupts(dev); + intel_init_pch_refclk(dev); + i915_gem_init_swizzling(dev); + mutex_lock(&dev_priv->rps.hw_lock); + gen6_update_ring_freq(dev); + mutex_unlock(&dev_priv->rps.hw_lock); +} + +static void hsw_runtime_resume(struct drm_i915_private *dev_priv) +{ + hsw_disable_pc8(dev_priv); +} + +static int intel_runtime_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct drm_device *dev = pci_get_drvdata(pdev); @@ -902,8 +931,12 @@ static int i915_runtime_suspend(struct device *device) DRM_DEBUG_KMS("Suspending device\n"); - if (HAS_PC8(dev)) - hsw_enable_pc8(dev_priv); + if (IS_GEN6(dev)) + snb_runtime_suspend(dev_priv); + else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + hsw_runtime_suspend(dev_priv); + else + WARN_ON(1); i915_gem_release_all_mmaps(dev_priv); @@ -923,7 +956,7 @@ static int i915_runtime_suspend(struct device *device) return 0; } -static int i915_runtime_resume(struct device *device) +static int intel_runtime_resume(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct drm_device *dev = pci_get_drvdata(pdev); @@ -936,8 +969,12 @@ static int i915_runtime_resume(struct device *device) intel_opregion_notify_adapter(dev, PCI_D0); dev_priv->pm.suspended = false; - if (HAS_PC8(dev)) - hsw_disable_pc8(dev_priv); + if (IS_GEN6(dev)) + snb_runtime_resume(dev_priv); + else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + hsw_runtime_resume(dev_priv); + else + WARN_ON(1); DRM_DEBUG_KMS("Device resumed\n"); return 0; @@ -954,8 +991,8 @@ static const struct dev_pm_ops i915_pm_ops = { .poweroff = i915_pm_poweroff, .restore_early = i915_pm_resume_early, .restore = i915_pm_resume, - .runtime_suspend = i915_runtime_suspend, - .runtime_resume = i915_runtime_resume, + .runtime_suspend = intel_runtime_suspend, + .runtime_resume = intel_runtime_resume, }; static const struct vm_operations_struct i915_gem_vm_ops = { diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0905cd91558..55addaaa822 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -35,6 +35,7 @@ #include "i915_reg.h" #include "intel_bios.h" #include "intel_ringbuffer.h" +#include "i915_gem_gtt.h" #include <linux/io-mapping.h> #include <linux/i2c.h> #include <linux/i2c-algo-bit.h> @@ -358,7 +359,7 @@ struct drm_i915_error_state { u64 bbaddr; u64 acthd; u32 fault_reg; - u32 faddr; + u64 faddr; u32 rc_psmi; /* sleep state */ u32 semaphore_mboxes[I915_NUM_RINGS - 1]; @@ -572,168 +573,6 @@ enum i915_cache_level { I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */ }; -typedef uint32_t gen6_gtt_pte_t; - -/** - * A VMA represents a GEM BO that is bound into an address space. Therefore, a - * VMA's presence cannot be guaranteed before binding, or after unbinding the - * object into/from the address space. - * - * To make things as simple as possible (ie. no refcounting), a VMA's lifetime - * will always be <= an objects lifetime. So object refcounting should cover us. - */ -struct i915_vma { - struct drm_mm_node node; - struct drm_i915_gem_object *obj; - struct i915_address_space *vm; - - /** This object's place on the active/inactive lists */ - struct list_head mm_list; - - struct list_head vma_link; /* Link in the object's VMA list */ - - /** This vma's place in the batchbuffer or on the eviction list */ - struct list_head exec_list; - - /** - * Used for performing relocations during execbuffer insertion. - */ - struct hlist_node exec_node; - unsigned long exec_handle; - struct drm_i915_gem_exec_object2 *exec_entry; - - /** - * How many users have pinned this object in GTT space. The following - * users can each hold at most one reference: pwrite/pread, pin_ioctl - * (via user_pin_count), execbuffer (objects are not allowed multiple - * times for the same batchbuffer), and the framebuffer code. When - * switching/pageflipping, the framebuffer code has at most two buffers - * pinned per crtc. - * - * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3 - * bits with absolutely no headroom. So use 4 bits. */ - unsigned int pin_count:4; -#define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf - - /** Unmap an object from an address space. This usually consists of - * setting the valid PTE entries to a reserved scratch page. */ - void (*unbind_vma)(struct i915_vma *vma); - /* Map an object into an address space with the given cache flags. */ -#define GLOBAL_BIND (1<<0) - void (*bind_vma)(struct i915_vma *vma, - enum i915_cache_level cache_level, - u32 flags); -}; - -struct i915_address_space { - struct drm_mm mm; - struct drm_device *dev; - struct list_head global_link; - unsigned long start; /* Start offset always 0 for dri2 */ - size_t total; /* size addr space maps (ex. 2GB for ggtt) */ - - struct { - dma_addr_t addr; - struct page *page; - } scratch; - - /** - * List of objects currently involved in rendering. - * - * Includes buffers having the contents of their GPU caches - * flushed, not necessarily primitives. last_rendering_seqno - * represents when the rendering involved will be completed. - * - * A reference is held on the buffer while on this list. - */ - struct list_head active_list; - - /** - * LRU list of objects which are not in the ringbuffer and - * are ready to unbind, but are still in the GTT. - * - * last_rendering_seqno is 0 while an object is in this list. - * - * A reference is not held on the buffer while on this list, - * as merely being GTT-bound shouldn't prevent its being - * freed, and we'll pull it off the list in the free path. - */ - struct list_head inactive_list; - - /* FIXME: Need a more generic return type */ - gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr, - enum i915_cache_level level, - bool valid); /* Create a valid PTE */ - void (*clear_range)(struct i915_address_space *vm, - uint64_t start, - uint64_t length, - bool use_scratch); - void (*insert_entries)(struct i915_address_space *vm, - struct sg_table *st, - uint64_t start, - enum i915_cache_level cache_level); - void (*cleanup)(struct i915_address_space *vm); -}; - -/* The Graphics Translation Table is the way in which GEN hardware translates a - * Graphics Virtual Address into a Physical Address. In addition to the normal - * collateral associated with any va->pa translations GEN hardware also has a - * portion of the GTT which can be mapped by the CPU and remain both coherent - * and correct (in cases like swizzling). That region is referred to as GMADR in - * the spec. - */ -struct i915_gtt { - struct i915_address_space base; - size_t stolen_size; /* Total size of stolen memory */ - - unsigned long mappable_end; /* End offset that we can CPU map */ - struct io_mapping *mappable; /* Mapping to our CPU mappable region */ - phys_addr_t mappable_base; /* PA of our GMADR */ - - /** "Graphics Stolen Memory" holds the global PTEs */ - void __iomem *gsm; - - bool do_idle_maps; - - int mtrr; - - /* global gtt ops */ - int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total, - size_t *stolen, phys_addr_t *mappable_base, - unsigned long *mappable_end); -}; -#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT) - -#define GEN8_LEGACY_PDPS 4 -struct i915_hw_ppgtt { - struct i915_address_space base; - struct kref ref; - struct drm_mm_node node; - unsigned num_pd_entries; - unsigned num_pd_pages; /* gen8+ */ - union { - struct page **pt_pages; - struct page **gen8_pt_pages[GEN8_LEGACY_PDPS]; - }; - struct page *pd_pages; - union { - uint32_t pd_offset; - dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS]; - }; - union { - dma_addr_t *pt_dma_addr; - dma_addr_t *gen8_pt_dma_addr[4]; - }; - - struct i915_hw_context *ctx; - - int (*enable)(struct i915_hw_ppgtt *ppgtt); - int (*switch_mm)(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, - bool synchronous); - void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m); -}; - struct i915_ctx_hang_stats { /* This context had batch pending when hang was declared */ unsigned batch_pending; @@ -1281,6 +1120,12 @@ struct ddi_vbt_port_info { uint8_t supports_dp:1; }; +enum drrs_support_type { + DRRS_NOT_SUPPORTED = 0, + STATIC_DRRS_SUPPORT = 1, + SEAMLESS_DRRS_SUPPORT = 2 +}; + struct intel_vbt_data { struct drm_display_mode *lfp_lvds_vbt_mode; /* if any */ struct drm_display_mode *sdvo_lvds_vbt_mode; /* if any */ @@ -1296,6 +1141,8 @@ struct intel_vbt_data { int lvds_ssc_freq; unsigned int bios_lvds_val; /* initial [PCH_]LVDS reg val in VBIOS */ + enum drrs_support_type drrs_type; + /* eDP */ int edp_rate; int edp_lanes; @@ -1365,23 +1212,13 @@ struct ilk_wm_values { * goes back to false exactly before we reenable the IRQs. We use this variable * to check if someone is trying to enable/disable IRQs while they're supposed * to be disabled. This shouldn't happen and we'll print some error messages in - * case it happens, but if it actually happens we'll also update the variables - * inside struct regsave so when we restore the IRQs they will contain the - * latest expected values. + * case it happens. * * For more, read the Documentation/power/runtime_pm.txt. */ struct i915_runtime_pm { bool suspended; bool irqs_disabled; - - struct { - uint32_t deimr; - uint32_t sdeimr; - uint32_t gtimr; - uint32_t gtier; - uint32_t gen6_pmimr; - } regsave; }; enum intel_pipe_crc_source { @@ -1414,7 +1251,7 @@ struct intel_pipe_crc { wait_queue_head_t wq; }; -typedef struct drm_i915_private { +struct drm_i915_private { struct drm_device *dev; struct kmem_cache *slab; @@ -1500,6 +1337,7 @@ typedef struct drm_i915_private { int num_fence_regs; /* 8 on pre-965, 16 otherwise */ unsigned int fsb_freq, mem_freq, is_ddr3; + unsigned int vlv_cdclk_freq; /** * wq - Driver workqueue for GEM. @@ -1523,7 +1361,7 @@ typedef struct drm_i915_private { struct mutex modeset_restore_lock; struct list_head vm_list; /* Global list of all address spaces */ - struct i915_gtt gtt; /* VMA representing the global address space */ + struct i915_gtt gtt; /* VM representing the global address space */ struct i915_gem_mm mm; @@ -1619,7 +1457,7 @@ typedef struct drm_i915_private { struct i915_dri1_state dri1; /* Old ums support infrastructure, same warning applies. */ struct i915_ums_state ums; -} drm_i915_private_t; +}; static inline struct drm_i915_private *to_i915(const struct drm_device *dev) { @@ -1893,11 +1731,17 @@ struct drm_i915_cmd_descriptor { * the expected value, the parser rejects it. Only valid if flags has * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero * are valid. + * + * If the check specifies a non-zero condition_mask then the parser + * only performs the check when the bits specified by condition_mask + * are non-zero. */ struct { u32 offset; u32 mask; u32 expected; + u32 condition_offset; + u32 condition_mask; } bits[MAX_CMD_DESC_BITMASKS]; }; @@ -2021,8 +1865,8 @@ struct drm_i915_cmd_table { #define HAS_DDI(dev) (INTEL_INFO(dev)->has_ddi) #define HAS_FPGA_DBG_UNCLAIMED(dev) (INTEL_INFO(dev)->has_fpga_dbg) #define HAS_PSR(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev)) -#define HAS_PC8(dev) (IS_HASWELL(dev)) /* XXX HSW:ULX */ -#define HAS_RUNTIME_PM(dev) (IS_HASWELL(dev)) +#define HAS_RUNTIME_PM(dev) (IS_GEN6(dev) || IS_HASWELL(dev) || \ + IS_BROADWELL(dev)) #define INTEL_PCH_DEVICE_ID_MASK 0xff00 #define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00 @@ -2079,6 +1923,7 @@ struct i915_params { bool prefault_disable; bool reset; bool disable_display; + bool disable_vtd_wa; }; extern struct i915_params i915 __read_mostly; @@ -2467,23 +2312,12 @@ int __must_check i915_gem_evict_something(struct drm_device *dev, int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); int i915_gem_evict_everything(struct drm_device *dev); -/* i915_gem_gtt.c */ -void i915_check_and_clear_faults(struct drm_device *dev); -void i915_gem_suspend_gtt_mappings(struct drm_device *dev); -void i915_gem_restore_gtt_mappings(struct drm_device *dev); -int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj); -void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj); -void i915_gem_init_global_gtt(struct drm_device *dev); -void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start, - unsigned long mappable_end, unsigned long end); -int i915_gem_gtt_init(struct drm_device *dev); +/* belongs in i915_gem_gtt.h */ static inline void i915_gem_chipset_flush(struct drm_device *dev) { if (INTEL_INFO(dev)->gen < 6) intel_gtt_chipset_flush(); } -int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt); -bool intel_enable_ppgtt(struct drm_device *dev, bool full); /* i915_gem_stolen.c */ int i915_gem_init_stolen(struct drm_device *dev); @@ -2551,6 +2385,7 @@ void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone); const char *i915_cache_level_str(int type); /* i915_cmd_parser.c */ +int i915_cmd_parser_get_version(void); void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring); bool i915_needs_cmd_parser(struct intel_ring_buffer *ring); int i915_parse_cmds(struct intel_ring_buffer *ring, @@ -2702,20 +2537,6 @@ void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val); int vlv_gpu_freq(struct drm_i915_private *dev_priv, int val); int vlv_freq_opcode(struct drm_i915_private *dev_priv, int val); -void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine); -void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine); - -#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \ - (((reg) >= 0x2000 && (reg) < 0x4000) ||\ - ((reg) >= 0x5000 && (reg) < 0x8000) ||\ - ((reg) >= 0xB000 && (reg) < 0x12000) ||\ - ((reg) >= 0x2E000 && (reg) < 0x30000)) - -#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\ - (((reg) >= 0x12000 && (reg) < 0x14000) ||\ - ((reg) >= 0x22000 && (reg) < 0x24000) ||\ - ((reg) >= 0x30000 && (reg) < 0x40000)) - #define FORCEWAKE_RENDER (1 << 0) #define FORCEWAKE_MEDIA (1 << 1) #define FORCEWAKE_ALL (FORCEWAKE_RENDER | FORCEWAKE_MEDIA) diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 6043062ffce..8827892a099 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -596,7 +596,7 @@ mi_set_context(struct intel_ring_buffer *ring, * explicitly, so we rely on the value at ring init, stored in * itlb_before_ctx_switch. */ - if (IS_GEN6(ring->dev) && ring->itlb_before_ctx_switch) { + if (IS_GEN6(ring->dev)) { ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, 0); if (ret) return ret; @@ -606,8 +606,8 @@ mi_set_context(struct intel_ring_buffer *ring, if (ret) return ret; - /* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw */ - if (IS_GEN7(ring->dev)) + /* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw */ + if (INTEL_INFO(ring->dev)->gen >= 7) intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_DISABLE); else intel_ring_emit(ring, MI_NOOP); @@ -625,7 +625,7 @@ mi_set_context(struct intel_ring_buffer *ring, */ intel_ring_emit(ring, MI_NOOP); - if (IS_GEN7(ring->dev)) + if (INTEL_INFO(ring->dev)->gen >= 7) intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE); else intel_ring_emit(ring, MI_NOOP); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index ab5e93c30aa..0d514ff9b94 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -50,64 +50,11 @@ bool intel_enable_ppgtt(struct drm_device *dev, bool full) /* Full ppgtt disabled by default for now due to issues. */ if (full) - return false; /* HAS_PPGTT(dev) */ + return HAS_PPGTT(dev) && (i915.enable_ppgtt == 2); else return HAS_ALIASING_PPGTT(dev); } -#define GEN6_PPGTT_PD_ENTRIES 512 -#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t)) -typedef uint64_t gen8_gtt_pte_t; -typedef gen8_gtt_pte_t gen8_ppgtt_pde_t; - -/* PPGTT stuff */ -#define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) -#define HSW_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0x7f0)) - -#define GEN6_PDE_VALID (1 << 0) -/* gen6+ has bit 11-4 for physical addr bit 39-32 */ -#define GEN6_PDE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) - -#define GEN6_PTE_VALID (1 << 0) -#define GEN6_PTE_UNCACHED (1 << 1) -#define HSW_PTE_UNCACHED (0) -#define GEN6_PTE_CACHE_LLC (2 << 1) -#define GEN7_PTE_CACHE_L3_LLC (3 << 1) -#define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) -#define HSW_PTE_ADDR_ENCODE(addr) HSW_GTT_ADDR_ENCODE(addr) - -/* Cacheability Control is a 4-bit value. The low three bits are stored in * - * bits 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE. - */ -#define HSW_CACHEABILITY_CONTROL(bits) ((((bits) & 0x7) << 1) | \ - (((bits) & 0x8) << (11 - 3))) -#define HSW_WB_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x2) -#define HSW_WB_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x3) -#define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb) -#define HSW_WB_ELLC_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x8) -#define HSW_WT_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x6) -#define HSW_WT_ELLC_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x7) - -#define GEN8_PTES_PER_PAGE (PAGE_SIZE / sizeof(gen8_gtt_pte_t)) -#define GEN8_PDES_PER_PAGE (PAGE_SIZE / sizeof(gen8_ppgtt_pde_t)) - -/* GEN8 legacy style addressis defined as a 3 level page table: - * 31:30 | 29:21 | 20:12 | 11:0 - * PDPE | PDE | PTE | offset - * The difference as compared to normal x86 3 level page table is the PDPEs are - * programmed via register. - */ -#define GEN8_PDPE_SHIFT 30 -#define GEN8_PDPE_MASK 0x3 -#define GEN8_PDE_SHIFT 21 -#define GEN8_PDE_MASK 0x1ff -#define GEN8_PTE_SHIFT 12 -#define GEN8_PTE_MASK 0x1ff - -#define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD) -#define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */ -#define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */ -#define PPAT_DISPLAY_ELLC_INDEX _PAGE_PCD /* WT eLLC */ static void ppgtt_bind_vma(struct i915_vma *vma, enum i915_cache_level cache_level, @@ -187,9 +134,6 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr, return pte; } -#define BYT_PTE_WRITEABLE (1 << 1) -#define BYT_PTE_SNOOPED_BY_CPU_CACHES (1 << 2) - static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr, enum i915_cache_level level, bool valid) @@ -1057,8 +1001,6 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm) static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt) { -#define GEN6_PD_ALIGN (PAGE_SIZE * 16) -#define GEN6_PD_SIZE (GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE) struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; bool retried = false; @@ -1848,17 +1790,6 @@ static int ggtt_probe_common(struct drm_device *dev, * writing this data shouldn't be harmful even in those cases. */ static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv) { -#define GEN8_PPAT_UC (0<<0) -#define GEN8_PPAT_WC (1<<0) -#define GEN8_PPAT_WT (2<<0) -#define GEN8_PPAT_WB (3<<0) -#define GEN8_PPAT_ELLC_OVERRIDE (0<<2) -/* FIXME(BDW): Bspec is completely confused about cache control bits. */ -#define GEN8_PPAT_LLC (1<<2) -#define GEN8_PPAT_LLCELLC (2<<2) -#define GEN8_PPAT_LLCeLLC (3<<2) -#define GEN8_PPAT_AGE(x) (x<<4) -#define GEN8_PPAT(i, x) ((uint64_t) (x) << ((i) * 8)) uint64_t pat; pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) | /* for normal objects, no eLLC */ @@ -2031,6 +1962,10 @@ int i915_gem_gtt_init(struct drm_device *dev) gtt->base.total >> 20); DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20); DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20); +#ifdef CONFIG_INTEL_IOMMU + if (intel_iommu_gfx_mapped) + DRM_INFO("VT-d active for gfx access\n"); +#endif return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h new file mode 100644 index 00000000000..b5e8ac0f5ce --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -0,0 +1,283 @@ +/* + * Copyright © 2014 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Please try to maintain the following order within this file unless it makes + * sense to do otherwise. From top to bottom: + * 1. typedefs + * 2. #defines, and macros + * 3. structure definitions + * 4. function prototypes + * + * Within each section, please try to order by generation in ascending order, + * from top to bottom (ie. gen6 on the top, gen8 on the bottom). + */ + +#ifndef __I915_GEM_GTT_H__ +#define __I915_GEM_GTT_H__ + +typedef uint32_t gen6_gtt_pte_t; +typedef uint64_t gen8_gtt_pte_t; +typedef gen8_gtt_pte_t gen8_ppgtt_pde_t; + +#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT) + +#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t)) +/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */ +#define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) +#define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) +#define GEN6_PDE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) +#define GEN6_PTE_CACHE_LLC (2 << 1) +#define GEN6_PTE_UNCACHED (1 << 1) +#define GEN6_PTE_VALID (1 << 0) + +#define GEN6_PPGTT_PD_ENTRIES 512 +#define GEN6_PD_SIZE (GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE) +#define GEN6_PD_ALIGN (PAGE_SIZE * 16) +#define GEN6_PDE_VALID (1 << 0) + +#define GEN7_PTE_CACHE_L3_LLC (3 << 1) + +#define BYT_PTE_SNOOPED_BY_CPU_CACHES (1 << 2) +#define BYT_PTE_WRITEABLE (1 << 1) + +/* Cacheability Control is a 4-bit value. The low three bits are stored in bits + * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE. + */ +#define HSW_CACHEABILITY_CONTROL(bits) ((((bits) & 0x7) << 1) | \ + (((bits) & 0x8) << (11 - 3))) +#define HSW_WB_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x2) +#define HSW_WB_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x3) +#define HSW_WB_ELLC_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x8) +#define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb) +#define HSW_WT_ELLC_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x7) +#define HSW_WT_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x6) +#define HSW_PTE_UNCACHED (0) +#define HSW_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0x7f0)) +#define HSW_PTE_ADDR_ENCODE(addr) HSW_GTT_ADDR_ENCODE(addr) + +/* GEN8 legacy style address is defined as a 3 level page table: + * 31:30 | 29:21 | 20:12 | 11:0 + * PDPE | PDE | PTE | offset + * The difference as compared to normal x86 3 level page table is the PDPEs are + * programmed via register. + */ +#define GEN8_PDPE_SHIFT 30 +#define GEN8_PDPE_MASK 0x3 +#define GEN8_PDE_SHIFT 21 +#define GEN8_PDE_MASK 0x1ff +#define GEN8_PTE_SHIFT 12 +#define GEN8_PTE_MASK 0x1ff +#define GEN8_LEGACY_PDPS 4 +#define GEN8_PTES_PER_PAGE (PAGE_SIZE / sizeof(gen8_gtt_pte_t)) +#define GEN8_PDES_PER_PAGE (PAGE_SIZE / sizeof(gen8_ppgtt_pde_t)) + +#define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD) +#define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */ +#define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */ +#define PPAT_DISPLAY_ELLC_INDEX _PAGE_PCD /* WT eLLC */ + +#define GEN8_PPAT_AGE(x) (x<<4) +#define GEN8_PPAT_LLCeLLC (3<<2) +#define GEN8_PPAT_LLCELLC (2<<2) +#define GEN8_PPAT_LLC (1<<2) +#define GEN8_PPAT_WB (3<<0) +#define GEN8_PPAT_WT (2<<0) +#define GEN8_PPAT_WC (1<<0) +#define GEN8_PPAT_UC (0<<0) +#define GEN8_PPAT_ELLC_OVERRIDE (0<<2) +#define GEN8_PPAT(i, x) ((uint64_t) (x) << ((i) * 8)) + +enum i915_cache_level; +/** + * A VMA represents a GEM BO that is bound into an address space. Therefore, a + * VMA's presence cannot be guaranteed before binding, or after unbinding the + * object into/from the address space. + * + * To make things as simple as possible (ie. no refcounting), a VMA's lifetime + * will always be <= an objects lifetime. So object refcounting should cover us. + */ +struct i915_vma { + struct drm_mm_node node; + struct drm_i915_gem_object *obj; + struct i915_address_space *vm; + + /** This object's place on the active/inactive lists */ + struct list_head mm_list; + + struct list_head vma_link; /* Link in the object's VMA list */ + + /** This vma's place in the batchbuffer or on the eviction list */ + struct list_head exec_list; + + /** + * Used for performing relocations during execbuffer insertion. + */ + struct hlist_node exec_node; + unsigned long exec_handle; + struct drm_i915_gem_exec_object2 *exec_entry; + + /** + * How many users have pinned this object in GTT space. The following + * users can each hold at most one reference: pwrite/pread, pin_ioctl + * (via user_pin_count), execbuffer (objects are not allowed multiple + * times for the same batchbuffer), and the framebuffer code. When + * switching/pageflipping, the framebuffer code has at most two buffers + * pinned per crtc. + * + * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3 + * bits with absolutely no headroom. So use 4 bits. */ + unsigned int pin_count:4; +#define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf + + /** Unmap an object from an address space. This usually consists of + * setting the valid PTE entries to a reserved scratch page. */ + void (*unbind_vma)(struct i915_vma *vma); + /* Map an object into an address space with the given cache flags. */ +#define GLOBAL_BIND (1<<0) + void (*bind_vma)(struct i915_vma *vma, + enum i915_cache_level cache_level, + u32 flags); +}; + +struct i915_address_space { + struct drm_mm mm; + struct drm_device *dev; + struct list_head global_link; + unsigned long start; /* Start offset always 0 for dri2 */ + size_t total; /* size addr space maps (ex. 2GB for ggtt) */ + + struct { + dma_addr_t addr; + struct page *page; + } scratch; + + /** + * List of objects currently involved in rendering. + * + * Includes buffers having the contents of their GPU caches + * flushed, not necessarily primitives. last_rendering_seqno + * represents when the rendering involved will be completed. + * + * A reference is held on the buffer while on this list. + */ + struct list_head active_list; + + /** + * LRU list of objects which are not in the ringbuffer and + * are ready to unbind, but are still in the GTT. + * + * last_rendering_seqno is 0 while an object is in this list. + * + * A reference is not held on the buffer while on this list, + * as merely being GTT-bound shouldn't prevent its being + * freed, and we'll pull it off the list in the free path. + */ + struct list_head inactive_list; + + /* FIXME: Need a more generic return type */ + gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr, + enum i915_cache_level level, + bool valid); /* Create a valid PTE */ + void (*clear_range)(struct i915_address_space *vm, + uint64_t start, + uint64_t length, + bool use_scratch); + void (*insert_entries)(struct i915_address_space *vm, + struct sg_table *st, + uint64_t start, + enum i915_cache_level cache_level); + void (*cleanup)(struct i915_address_space *vm); +}; + +/* The Graphics Translation Table is the way in which GEN hardware translates a + * Graphics Virtual Address into a Physical Address. In addition to the normal + * collateral associated with any va->pa translations GEN hardware also has a + * portion of the GTT which can be mapped by the CPU and remain both coherent + * and correct (in cases like swizzling). That region is referred to as GMADR in + * the spec. + */ +struct i915_gtt { + struct i915_address_space base; + size_t stolen_size; /* Total size of stolen memory */ + + unsigned long mappable_end; /* End offset that we can CPU map */ + struct io_mapping *mappable; /* Mapping to our CPU mappable region */ + phys_addr_t mappable_base; /* PA of our GMADR */ + + /** "Graphics Stolen Memory" holds the global PTEs */ + void __iomem *gsm; + + bool do_idle_maps; + + int mtrr; + + /* global gtt ops */ + int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total, + size_t *stolen, phys_addr_t *mappable_base, + unsigned long *mappable_end); +}; + +struct i915_hw_ppgtt { + struct i915_address_space base; + struct kref ref; + struct drm_mm_node node; + unsigned num_pd_entries; + unsigned num_pd_pages; /* gen8+ */ + union { + struct page **pt_pages; + struct page **gen8_pt_pages[GEN8_LEGACY_PDPS]; + }; + struct page *pd_pages; + union { + uint32_t pd_offset; + dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS]; + }; + union { + dma_addr_t *pt_dma_addr; + dma_addr_t *gen8_pt_dma_addr[4]; + }; + + struct i915_hw_context *ctx; + + int (*enable)(struct i915_hw_ppgtt *ppgtt); + int (*switch_mm)(struct i915_hw_ppgtt *ppgtt, + struct intel_ring_buffer *ring, + bool synchronous); + void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m); +}; + +int i915_gem_gtt_init(struct drm_device *dev); +void i915_gem_init_global_gtt(struct drm_device *dev); +void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start, + unsigned long mappable_end, unsigned long end); + +bool intel_enable_ppgtt(struct drm_device *dev, bool full); +int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt); + +void i915_check_and_clear_faults(struct drm_device *dev); +void i915_gem_suspend_gtt_mappings(struct drm_device *dev); +void i915_gem_restore_gtt_mappings(struct drm_device *dev); + +int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj); +void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj); + +#endif diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 12f1d43b2d6..1005af020a8 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -257,7 +257,8 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m, err_printf(m, " INSTPS: 0x%08x\n", ring->instps); } err_printf(m, " INSTPM: 0x%08x\n", ring->instpm); - err_printf(m, " FADDR: 0x%08x\n", ring->faddr); + err_printf(m, " FADDR: 0x%08x %08x\n", upper_32_bits(ring->faddr), + lower_32_bits(ring->faddr)); if (INTEL_INFO(dev)->gen >= 6) { err_printf(m, " RC PSMI: 0x%08x\n", ring->rc_psmi); err_printf(m, " FAULT_REG: 0x%08x\n", ring->fault_reg); @@ -781,8 +782,10 @@ static void i915_record_ring_state(struct drm_device *dev, ering->instdone = I915_READ(RING_INSTDONE(ring->mmio_base)); ering->instps = I915_READ(RING_INSTPS(ring->mmio_base)); ering->bbaddr = I915_READ(RING_BBADDR(ring->mmio_base)); - if (INTEL_INFO(dev)->gen >= 8) + if (INTEL_INFO(dev)->gen >= 8) { + ering->faddr |= (u64) I915_READ(RING_DMA_FADD_UDW(ring->mmio_base)) << 32; ering->bbaddr |= (u64) I915_READ(RING_BBADDR_UDW(ring->mmio_base)) << 32; + } ering->bbstate = I915_READ(RING_BBSTATE(ring->mmio_base)); } else { ering->faddr = I915_READ(DMA_FADD_I8XX); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 7753249b3a9..4ca0344c2ae 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -80,17 +80,64 @@ static const u32 hpd_status_i915[] = { /* i915 and valleyview are the same */ [HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS }; +/* IIR can theoretically queue up two events. Be paranoid. */ +#define GEN8_IRQ_RESET_NDX(type, which) do { \ + I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \ + POSTING_READ(GEN8_##type##_IMR(which)); \ + I915_WRITE(GEN8_##type##_IER(which), 0); \ + I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ + POSTING_READ(GEN8_##type##_IIR(which)); \ + I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ + POSTING_READ(GEN8_##type##_IIR(which)); \ +} while (0) + +#define GEN5_IRQ_RESET(type) do { \ + I915_WRITE(type##IMR, 0xffffffff); \ + POSTING_READ(type##IMR); \ + I915_WRITE(type##IER, 0); \ + I915_WRITE(type##IIR, 0xffffffff); \ + POSTING_READ(type##IIR); \ + I915_WRITE(type##IIR, 0xffffffff); \ + POSTING_READ(type##IIR); \ +} while (0) + +/* + * We should clear IMR at preinstall/uninstall, and just check at postinstall. + */ +#define GEN5_ASSERT_IIR_IS_ZERO(reg) do { \ + u32 val = I915_READ(reg); \ + if (val) { \ + WARN(1, "Interrupt register 0x%x is not zero: 0x%08x\n", \ + (reg), val); \ + I915_WRITE((reg), 0xffffffff); \ + POSTING_READ(reg); \ + I915_WRITE((reg), 0xffffffff); \ + POSTING_READ(reg); \ + } \ +} while (0) + +#define GEN8_IRQ_INIT_NDX(type, which, imr_val, ier_val) do { \ + GEN5_ASSERT_IIR_IS_ZERO(GEN8_##type##_IIR(which)); \ + I915_WRITE(GEN8_##type##_IMR(which), (imr_val)); \ + I915_WRITE(GEN8_##type##_IER(which), (ier_val)); \ + POSTING_READ(GEN8_##type##_IER(which)); \ +} while (0) + +#define GEN5_IRQ_INIT(type, imr_val, ier_val) do { \ + GEN5_ASSERT_IIR_IS_ZERO(type##IIR); \ + I915_WRITE(type##IMR, (imr_val)); \ + I915_WRITE(type##IER, (ier_val)); \ + POSTING_READ(type##IER); \ +} while (0) + /* For display hotplug interrupt */ static void ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask) { assert_spin_locked(&dev_priv->irq_lock); - if (dev_priv->pm.irqs_disabled) { - WARN(1, "IRQs disabled\n"); - dev_priv->pm.regsave.deimr &= ~mask; + if (WARN_ON(dev_priv->pm.irqs_disabled)) return; - } if ((dev_priv->irq_mask & mask) != 0) { dev_priv->irq_mask &= ~mask; @@ -104,11 +151,8 @@ ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask) { assert_spin_locked(&dev_priv->irq_lock); - if (dev_priv->pm.irqs_disabled) { - WARN(1, "IRQs disabled\n"); - dev_priv->pm.regsave.deimr |= mask; + if (WARN_ON(dev_priv->pm.irqs_disabled)) return; - } if ((dev_priv->irq_mask & mask) != mask) { dev_priv->irq_mask |= mask; @@ -129,13 +173,8 @@ static void ilk_update_gt_irq(struct drm_i915_private *dev_priv, { assert_spin_locked(&dev_priv->irq_lock); - if (dev_priv->pm.irqs_disabled) { - WARN(1, "IRQs disabled\n"); - dev_priv->pm.regsave.gtimr &= ~interrupt_mask; - dev_priv->pm.regsave.gtimr |= (~enabled_irq_mask & - interrupt_mask); + if (WARN_ON(dev_priv->pm.irqs_disabled)) return; - } dev_priv->gt_irq_mask &= ~interrupt_mask; dev_priv->gt_irq_mask |= (~enabled_irq_mask & interrupt_mask); @@ -167,13 +206,8 @@ static void snb_update_pm_irq(struct drm_i915_private *dev_priv, assert_spin_locked(&dev_priv->irq_lock); - if (dev_priv->pm.irqs_disabled) { - WARN(1, "IRQs disabled\n"); - dev_priv->pm.regsave.gen6_pmimr &= ~interrupt_mask; - dev_priv->pm.regsave.gen6_pmimr |= (~enabled_irq_mask & - interrupt_mask); + if (WARN_ON(dev_priv->pm.irqs_disabled)) return; - } new_val = dev_priv->pm_irq_mask; new_val &= ~interrupt_mask; @@ -313,14 +347,8 @@ static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv, assert_spin_locked(&dev_priv->irq_lock); - if (dev_priv->pm.irqs_disabled && - (interrupt_mask & SDE_HOTPLUG_MASK_CPT)) { - WARN(1, "IRQs disabled\n"); - dev_priv->pm.regsave.sdeimr &= ~interrupt_mask; - dev_priv->pm.regsave.sdeimr |= (~enabled_irq_mask & - interrupt_mask); + if (WARN_ON(dev_priv->pm.irqs_disabled)) return; - } I915_WRITE(SDEIMR, sdeimr); POSTING_READ(SDEIMR); @@ -503,8 +531,10 @@ __i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe, assert_spin_locked(&dev_priv->irq_lock); - if (WARN_ON_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK || - status_mask & ~PIPESTAT_INT_STATUS_MASK)) + if (WARN_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK || + status_mask & ~PIPESTAT_INT_STATUS_MASK, + "pipe %c: enable_mask=0x%x, status_mask=0x%x\n", + pipe_name(pipe), enable_mask, status_mask)) return; if ((pipestat & enable_mask) == enable_mask) @@ -527,8 +557,10 @@ __i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe, assert_spin_locked(&dev_priv->irq_lock); - if (WARN_ON_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK || - status_mask & ~PIPESTAT_INT_STATUS_MASK)) + if (WARN_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK || + status_mask & ~PIPESTAT_INT_STATUS_MASK, + "pipe %c: enable_mask=0x%x, status_mask=0x%x\n", + pipe_name(pipe), enable_mask, status_mask)) return; if ((pipestat & enable_mask) == 0) @@ -1609,6 +1641,33 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir) gmbus_irq_handler(dev); } +static void i9xx_hpd_irq_handler(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); + + if (IS_G4X(dev)) { + u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X; + + intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_g4x); + } else { + u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915; + + intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915); + } + + if ((IS_G4X(dev) || IS_VALLEYVIEW(dev)) && + hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X) + dp_aux_irq_handler(dev); + + I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status); + /* + * Make sure hotplug status is cleared before we clear IIR, or else we + * may miss hotplug events. + */ + POSTING_READ(PORT_HOTPLUG_STAT); +} + static irqreturn_t valleyview_irq_handler(int irq, void *arg) { struct drm_device *dev = (struct drm_device *) arg; @@ -1631,19 +1690,8 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg) valleyview_pipestat_irq_handler(dev, iir); /* Consume port. Then clear IIR or we'll miss events */ - if (iir & I915_DISPLAY_PORT_INTERRUPT) { - u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); - u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915; - - intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915); - - if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X) - dp_aux_irq_handler(dev); - - I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status); - I915_READ(PORT_HOTPLUG_STAT); - } - + if (iir & I915_DISPLAY_PORT_INTERRUPT) + i9xx_hpd_irq_handler(dev); if (pm_iir) gen6_rps_irq_handler(dev_priv, pm_iir); @@ -2501,6 +2549,56 @@ ring_idle(struct intel_ring_buffer *ring, u32 seqno) i915_seqno_passed(seqno, ring_last_seqno(ring))); } +static bool +ipehr_is_semaphore_wait(struct drm_device *dev, u32 ipehr) +{ + if (INTEL_INFO(dev)->gen >= 8) { + /* + * FIXME: gen8 semaphore support - currently we don't emit + * semaphores on bdw anyway, but this needs to be addressed when + * we merge that code. + */ + return false; + } else { + ipehr &= ~MI_SEMAPHORE_SYNC_MASK; + return ipehr == (MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE | + MI_SEMAPHORE_REGISTER); + } +} + +static struct intel_ring_buffer * +semaphore_wait_to_signaller_ring(struct intel_ring_buffer *ring, u32 ipehr) +{ + struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct intel_ring_buffer *signaller; + int i; + + if (INTEL_INFO(dev_priv->dev)->gen >= 8) { + /* + * FIXME: gen8 semaphore support - currently we don't emit + * semaphores on bdw anyway, but this needs to be addressed when + * we merge that code. + */ + return NULL; + } else { + u32 sync_bits = ipehr & MI_SEMAPHORE_SYNC_MASK; + + for_each_ring(signaller, dev_priv, i) { + if(ring == signaller) + continue; + + if (sync_bits == + signaller->semaphore_register[ring->id]) + return signaller; + } + } + + DRM_ERROR("No signaller ring found for ring %i, ipehr 0x%08x\n", + ring->id, ipehr); + + return NULL; +} + static struct intel_ring_buffer * semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) { @@ -2509,8 +2607,7 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) int i; ipehr = I915_READ(RING_IPEHR(ring->mmio_base)); - if ((ipehr & ~(0x3 << 16)) != - (MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE | MI_SEMAPHORE_REGISTER)) + if (!ipehr_is_semaphore_wait(ring->dev, ipehr)) return NULL; /* @@ -2542,7 +2639,7 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) return NULL; *seqno = ioread32(ring->virtual_start + head + 4) + 1; - return &dev_priv->ring[(ring->id + (((ipehr >> 17) & 1) + 1)) % 3]; + return semaphore_wait_to_signaller_ring(ring, ipehr); } static int semaphore_passed(struct intel_ring_buffer *ring) @@ -2749,57 +2846,68 @@ void i915_queue_hangcheck(struct drm_device *dev) round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); } -static void ibx_irq_preinstall(struct drm_device *dev) +static void ibx_irq_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; if (HAS_PCH_NOP(dev)) return; - /* south display irq */ - I915_WRITE(SDEIMR, 0xffffffff); - /* - * SDEIER is also touched by the interrupt handler to work around missed - * PCH interrupts. Hence we can't update it after the interrupt handler - * is enabled - instead we unconditionally enable all PCH interrupt - * sources here, but then only unmask them as needed with SDEIMR. - */ + GEN5_IRQ_RESET(SDE); + + if (HAS_PCH_CPT(dev) || HAS_PCH_LPT(dev)) + I915_WRITE(SERR_INT, 0xffffffff); +} + +/* + * SDEIER is also touched by the interrupt handler to work around missed PCH + * interrupts. Hence we can't update it after the interrupt handler is enabled - + * instead we unconditionally enable all PCH interrupt sources here, but then + * only unmask them as needed with SDEIMR. + * + * This function needs to be called before interrupts are enabled. + */ +static void ibx_irq_pre_postinstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (HAS_PCH_NOP(dev)) + return; + + WARN_ON(I915_READ(SDEIER) != 0); I915_WRITE(SDEIER, 0xffffffff); POSTING_READ(SDEIER); } -static void gen5_gt_irq_preinstall(struct drm_device *dev) +static void gen5_gt_irq_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - /* and GT */ - I915_WRITE(GTIMR, 0xffffffff); - I915_WRITE(GTIER, 0x0); - POSTING_READ(GTIER); - - if (INTEL_INFO(dev)->gen >= 6) { - /* and PM */ - I915_WRITE(GEN6_PMIMR, 0xffffffff); - I915_WRITE(GEN6_PMIER, 0x0); - POSTING_READ(GEN6_PMIER); - } + GEN5_IRQ_RESET(GT); + if (INTEL_INFO(dev)->gen >= 6) + GEN5_IRQ_RESET(GEN6_PM); } /* drm_dma.h hooks */ -static void ironlake_irq_preinstall(struct drm_device *dev) +static void ironlake_irq_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - I915_WRITE(HWSTAM, 0xeffe); + I915_WRITE(HWSTAM, 0xffffffff); - I915_WRITE(DEIMR, 0xffffffff); - I915_WRITE(DEIER, 0x0); - POSTING_READ(DEIER); + GEN5_IRQ_RESET(DE); + if (IS_GEN7(dev)) + I915_WRITE(GEN7_ERR_INT, 0xffffffff); - gen5_gt_irq_preinstall(dev); + gen5_gt_irq_reset(dev); + + ibx_irq_reset(dev); +} - ibx_irq_preinstall(dev); +static void ironlake_irq_preinstall(struct drm_device *dev) +{ + ironlake_irq_reset(dev); } static void valleyview_irq_preinstall(struct drm_device *dev) @@ -2817,7 +2925,7 @@ static void valleyview_irq_preinstall(struct drm_device *dev) I915_WRITE(GTIIR, I915_READ(GTIIR)); I915_WRITE(GTIIR, I915_READ(GTIIR)); - gen5_gt_irq_preinstall(dev); + gen5_gt_irq_reset(dev); I915_WRITE(DPINVGTT, 0xff); @@ -2831,7 +2939,7 @@ static void valleyview_irq_preinstall(struct drm_device *dev) POSTING_READ(VLV_IER); } -static void gen8_irq_preinstall(struct drm_device *dev) +static void gen8_irq_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; int pipe; @@ -2839,43 +2947,24 @@ static void gen8_irq_preinstall(struct drm_device *dev) I915_WRITE(GEN8_MASTER_IRQ, 0); POSTING_READ(GEN8_MASTER_IRQ); - /* IIR can theoretically queue up two events. Be paranoid */ -#define GEN8_IRQ_INIT_NDX(type, which) do { \ - I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \ - POSTING_READ(GEN8_##type##_IMR(which)); \ - I915_WRITE(GEN8_##type##_IER(which), 0); \ - I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ - POSTING_READ(GEN8_##type##_IIR(which)); \ - I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ - } while (0) - -#define GEN8_IRQ_INIT(type) do { \ - I915_WRITE(GEN8_##type##_IMR, 0xffffffff); \ - POSTING_READ(GEN8_##type##_IMR); \ - I915_WRITE(GEN8_##type##_IER, 0); \ - I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \ - POSTING_READ(GEN8_##type##_IIR); \ - I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \ - } while (0) - - GEN8_IRQ_INIT_NDX(GT, 0); - GEN8_IRQ_INIT_NDX(GT, 1); - GEN8_IRQ_INIT_NDX(GT, 2); - GEN8_IRQ_INIT_NDX(GT, 3); + GEN8_IRQ_RESET_NDX(GT, 0); + GEN8_IRQ_RESET_NDX(GT, 1); + GEN8_IRQ_RESET_NDX(GT, 2); + GEN8_IRQ_RESET_NDX(GT, 3); - for_each_pipe(pipe) { - GEN8_IRQ_INIT_NDX(DE_PIPE, pipe); - } + for_each_pipe(pipe) + GEN8_IRQ_RESET_NDX(DE_PIPE, pipe); - GEN8_IRQ_INIT(DE_PORT); - GEN8_IRQ_INIT(DE_MISC); - GEN8_IRQ_INIT(PCU); -#undef GEN8_IRQ_INIT -#undef GEN8_IRQ_INIT_NDX + GEN5_IRQ_RESET(GEN8_DE_PORT_); + GEN5_IRQ_RESET(GEN8_DE_MISC_); + GEN5_IRQ_RESET(GEN8_PCU_); - POSTING_READ(GEN8_PCU_IIR); + ibx_irq_reset(dev); +} - ibx_irq_preinstall(dev); +static void gen8_irq_preinstall(struct drm_device *dev) +{ + gen8_irq_reset(dev); } static void ibx_hpd_irq_setup(struct drm_device *dev) @@ -2921,15 +3010,12 @@ static void ibx_irq_postinstall(struct drm_device *dev) if (HAS_PCH_NOP(dev)) return; - if (HAS_PCH_IBX(dev)) { + if (HAS_PCH_IBX(dev)) mask = SDE_GMBUS | SDE_AUX_MASK | SDE_POISON; - } else { + else mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT; - I915_WRITE(SERR_INT, I915_READ(SERR_INT)); - } - - I915_WRITE(SDEIIR, I915_READ(SDEIIR)); + GEN5_ASSERT_IIR_IS_ZERO(SDEIIR); I915_WRITE(SDEIMR, ~mask); } @@ -2955,10 +3041,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev) gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT; } - I915_WRITE(GTIIR, I915_READ(GTIIR)); - I915_WRITE(GTIMR, dev_priv->gt_irq_mask); - I915_WRITE(GTIER, gt_irqs); - POSTING_READ(GTIER); + GEN5_IRQ_INIT(GT, dev_priv->gt_irq_mask, gt_irqs); if (INTEL_INFO(dev)->gen >= 6) { pm_irqs |= dev_priv->pm_rps_events; @@ -2967,10 +3050,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev) pm_irqs |= PM_VEBOX_USER_INTERRUPT; dev_priv->pm_irq_mask = 0xffffffff; - I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR)); - I915_WRITE(GEN6_PMIMR, dev_priv->pm_irq_mask); - I915_WRITE(GEN6_PMIER, pm_irqs); - POSTING_READ(GEN6_PMIER); + GEN5_IRQ_INIT(GEN6_PM, dev_priv->pm_irq_mask, pm_irqs); } } @@ -2987,8 +3067,6 @@ static int ironlake_irq_postinstall(struct drm_device *dev) DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB); extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB | DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB); - - I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT)); } else { display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT | DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE | @@ -3001,11 +3079,11 @@ static int ironlake_irq_postinstall(struct drm_device *dev) dev_priv->irq_mask = ~display_mask; - /* should always can generate irq */ - I915_WRITE(DEIIR, I915_READ(DEIIR)); - I915_WRITE(DEIMR, dev_priv->irq_mask); - I915_WRITE(DEIER, display_mask | extra_mask); - POSTING_READ(DEIER); + I915_WRITE(HWSTAM, 0xeffe); + + ibx_irq_pre_postinstall(dev); + + GEN5_IRQ_INIT(DE, dev_priv->irq_mask, display_mask | extra_mask); gen5_gt_irq_postinstall(dev); @@ -3165,15 +3243,8 @@ static void gen8_gt_irq_postinstall(struct drm_i915_private *dev_priv) GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT }; - for (i = 0; i < ARRAY_SIZE(gt_interrupts); i++) { - u32 tmp = I915_READ(GEN8_GT_IIR(i)); - if (tmp) - DRM_ERROR("Interrupt (%d) should have been masked in pre-install 0x%08x\n", - i, tmp); - I915_WRITE(GEN8_GT_IMR(i), ~gt_interrupts[i]); - I915_WRITE(GEN8_GT_IER(i), gt_interrupts[i]); - } - POSTING_READ(GEN8_GT_IER(0)); + for (i = 0; i < ARRAY_SIZE(gt_interrupts); i++) + GEN8_IRQ_INIT_NDX(GT, i, ~gt_interrupts[i], gt_interrupts[i]); } static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) @@ -3189,25 +3260,19 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked; dev_priv->de_irq_mask[PIPE_C] = ~de_pipe_masked; - for_each_pipe(pipe) { - u32 tmp = I915_READ(GEN8_DE_PIPE_IIR(pipe)); - if (tmp) - DRM_ERROR("Interrupt (%d) should have been masked in pre-install 0x%08x\n", - pipe, tmp); - I915_WRITE(GEN8_DE_PIPE_IMR(pipe), dev_priv->de_irq_mask[pipe]); - I915_WRITE(GEN8_DE_PIPE_IER(pipe), de_pipe_enables); - } - POSTING_READ(GEN8_DE_PIPE_ISR(0)); + for_each_pipe(pipe) + GEN8_IRQ_INIT_NDX(DE_PIPE, pipe, dev_priv->de_irq_mask[pipe], + de_pipe_enables); - I915_WRITE(GEN8_DE_PORT_IMR, ~GEN8_AUX_CHANNEL_A); - I915_WRITE(GEN8_DE_PORT_IER, GEN8_AUX_CHANNEL_A); - POSTING_READ(GEN8_DE_PORT_IER); + GEN5_IRQ_INIT(GEN8_DE_PORT_, ~GEN8_AUX_CHANNEL_A, GEN8_AUX_CHANNEL_A); } static int gen8_irq_postinstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + ibx_irq_pre_postinstall(dev); + gen8_gt_irq_postinstall(dev_priv); gen8_de_irq_postinstall(dev_priv); @@ -3222,41 +3287,13 @@ static int gen8_irq_postinstall(struct drm_device *dev) static void gen8_irq_uninstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - int pipe; if (!dev_priv) return; - I915_WRITE(GEN8_MASTER_IRQ, 0); - -#define GEN8_IRQ_FINI_NDX(type, which) do { \ - I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \ - I915_WRITE(GEN8_##type##_IER(which), 0); \ - I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ - } while (0) - -#define GEN8_IRQ_FINI(type) do { \ - I915_WRITE(GEN8_##type##_IMR, 0xffffffff); \ - I915_WRITE(GEN8_##type##_IER, 0); \ - I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \ - } while (0) - - GEN8_IRQ_FINI_NDX(GT, 0); - GEN8_IRQ_FINI_NDX(GT, 1); - GEN8_IRQ_FINI_NDX(GT, 2); - GEN8_IRQ_FINI_NDX(GT, 3); - - for_each_pipe(pipe) { - GEN8_IRQ_FINI_NDX(DE_PIPE, pipe); - } - - GEN8_IRQ_FINI(DE_PORT); - GEN8_IRQ_FINI(DE_MISC); - GEN8_IRQ_FINI(PCU); -#undef GEN8_IRQ_FINI -#undef GEN8_IRQ_FINI_NDX + intel_hpd_irq_uninstall(dev_priv); - POSTING_READ(GEN8_PCU_IIR); + gen8_irq_reset(dev); } static void valleyview_irq_uninstall(struct drm_device *dev) @@ -3299,26 +3336,7 @@ static void ironlake_irq_uninstall(struct drm_device *dev) intel_hpd_irq_uninstall(dev_priv); - I915_WRITE(HWSTAM, 0xffffffff); - - I915_WRITE(DEIMR, 0xffffffff); - I915_WRITE(DEIER, 0x0); - I915_WRITE(DEIIR, I915_READ(DEIIR)); - if (IS_GEN7(dev)) - I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT)); - - I915_WRITE(GTIMR, 0xffffffff); - I915_WRITE(GTIER, 0x0); - I915_WRITE(GTIIR, I915_READ(GTIIR)); - - if (HAS_PCH_NOP(dev)) - return; - - I915_WRITE(SDEIMR, 0xffffffff); - I915_WRITE(SDEIER, 0x0); - I915_WRITE(SDEIIR, I915_READ(SDEIIR)); - if (HAS_PCH_CPT(dev) || HAS_PCH_LPT(dev)) - I915_WRITE(SERR_INT, I915_READ(SERR_INT)); + ironlake_irq_reset(dev); } static void i8xx_irq_preinstall(struct drm_device * dev) @@ -3626,16 +3644,9 @@ static irqreturn_t i915_irq_handler(int irq, void *arg) break; /* Consume port. Then clear IIR or we'll miss events */ - if ((I915_HAS_HOTPLUG(dev)) && - (iir & I915_DISPLAY_PORT_INTERRUPT)) { - u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); - u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915; - - intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915); - - I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status); - POSTING_READ(PORT_HOTPLUG_STAT); - } + if (I915_HAS_HOTPLUG(dev) && + iir & I915_DISPLAY_PORT_INTERRUPT) + i9xx_hpd_irq_handler(dev); I915_WRITE(IIR, iir & ~flip_mask); new_iir = I915_READ(IIR); /* Flush posted writes */ @@ -3869,22 +3880,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) ret = IRQ_HANDLED; /* Consume port. Then clear IIR or we'll miss events */ - if (iir & I915_DISPLAY_PORT_INTERRUPT) { - u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); - u32 hotplug_trigger = hotplug_status & (IS_G4X(dev) ? - HOTPLUG_INT_STATUS_G4X : - HOTPLUG_INT_STATUS_I915); - - intel_hpd_irq_handler(dev, hotplug_trigger, - IS_G4X(dev) ? hpd_status_g4x : hpd_status_i915); - - if (IS_G4X(dev) && - (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)) - dp_aux_irq_handler(dev); - - I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status); - I915_READ(PORT_HOTPLUG_STAT); - } + if (iir & I915_DISPLAY_PORT_INTERRUPT) + i9xx_hpd_irq_handler(dev); I915_WRITE(IIR, iir & ~flip_mask); new_iir = I915_READ(IIR); /* Flush posted writes */ @@ -4111,57 +4108,20 @@ void intel_hpd_init(struct drm_device *dev) } /* Disable interrupts so we can allow runtime PM. */ -void hsw_runtime_pm_disable_interrupts(struct drm_device *dev) +void intel_runtime_pm_disable_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long irqflags; - - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - - dev_priv->pm.regsave.deimr = I915_READ(DEIMR); - dev_priv->pm.regsave.sdeimr = I915_READ(SDEIMR); - dev_priv->pm.regsave.gtimr = I915_READ(GTIMR); - dev_priv->pm.regsave.gtier = I915_READ(GTIER); - dev_priv->pm.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR); - - ironlake_disable_display_irq(dev_priv, 0xffffffff); - ibx_disable_display_interrupt(dev_priv, 0xffffffff); - ilk_disable_gt_irq(dev_priv, 0xffffffff); - snb_disable_pm_irq(dev_priv, 0xffffffff); + dev->driver->irq_uninstall(dev); dev_priv->pm.irqs_disabled = true; - - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); } /* Restore interrupts so we can recover from runtime PM. */ -void hsw_runtime_pm_restore_interrupts(struct drm_device *dev) +void intel_runtime_pm_restore_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long irqflags; - uint32_t val; - - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - - val = I915_READ(DEIMR); - WARN(val != 0xffffffff, "DEIMR is 0x%08x\n", val); - - val = I915_READ(SDEIMR); - WARN(val != 0xffffffff, "SDEIMR is 0x%08x\n", val); - - val = I915_READ(GTIMR); - WARN(val != 0xffffffff, "GTIMR is 0x%08x\n", val); - - val = I915_READ(GEN6_PMIMR); - WARN(val != 0xffffffff, "GEN6_PMIMR is 0x%08x\n", val); dev_priv->pm.irqs_disabled = false; - - ironlake_enable_display_irq(dev_priv, ~dev_priv->pm.regsave.deimr); - ibx_enable_display_interrupt(dev_priv, ~dev_priv->pm.regsave.sdeimr); - ilk_enable_gt_irq(dev_priv, ~dev_priv->pm.regsave.gtimr); - snb_enable_pm_irq(dev_priv, ~dev_priv->pm.regsave.gen6_pmimr); - I915_WRITE(GTIER, dev_priv->pm.regsave.gtier); - - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + dev->driver->irq_preinstall(dev); + dev->driver->irq_postinstall(dev); } diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index d1d7980f0e0..d05a2afa17d 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -46,7 +46,8 @@ struct i915_params i915 __read_mostly = { .reset = true, .invert_brightness = 0, .disable_display = 0, - .enable_cmd_parser = 0, + .enable_cmd_parser = 1, + .disable_vtd_wa = 0, }; module_param_named(modeset, i915.modeset, int, 0400); @@ -149,6 +150,9 @@ MODULE_PARM_DESC(invert_brightness, module_param_named(disable_display, i915.disable_display, bool, 0600); MODULE_PARM_DESC(disable_display, "Disable display (default: false)"); +module_param_named(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600); +MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)"); + module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600); MODULE_PARM_DESC(enable_cmd_parser, - "Enable command parsing (1=enabled, 0=disabled [default])"); + "Enable command parsing (1=enabled [default], 0=disabled)"); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 9f5b18d9d88..23153668dac 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -190,6 +190,8 @@ * Memory interface instructions used by the kernel */ #define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags)) +/* Many MI commands use bit 22 of the header dword for GGTT vs PPGTT */ +#define MI_GLOBAL_GTT (1<<22) #define MI_NOOP MI_INSTR(0, 0) #define MI_USER_INTERRUPT MI_INSTR(0x02, 0) @@ -244,7 +246,8 @@ #define MI_SEMAPHORE_SYNC_BVE (0<<16) /* VECS wait for BCS (VEBSYNC) */ #define MI_SEMAPHORE_SYNC_VVE (1<<16) /* VECS wait for VCS (VEVSYNC) */ #define MI_SEMAPHORE_SYNC_RVE (2<<16) /* VECS wait for RCS (VERSYNC) */ -#define MI_SEMAPHORE_SYNC_INVALID (3<<16) +#define MI_SEMAPHORE_SYNC_INVALID (3<<16) +#define MI_SEMAPHORE_SYNC_MASK (3<<16) #define MI_SET_CONTEXT MI_INSTR(0x18, 0) #define MI_MM_SPACE_GTT (1<<8) #define MI_MM_SPACE_PHYSICAL (0<<8) @@ -269,6 +272,8 @@ #define MI_FLUSH_DW_STORE_INDEX (1<<21) #define MI_INVALIDATE_TLB (1<<18) #define MI_FLUSH_DW_OP_STOREDW (1<<14) +#define MI_FLUSH_DW_OP_MASK (3<<14) +#define MI_FLUSH_DW_NOTIFY (1<<8) #define MI_INVALIDATE_BSD (1<<7) #define MI_FLUSH_DW_USE_GTT (1<<2) #define MI_FLUSH_DW_USE_PPGTT (0<<2) @@ -330,9 +335,12 @@ #define DISPLAY_PLANE_B (1<<20) #define GFX_OP_PIPE_CONTROL(len) ((0x3<<29)|(0x3<<27)|(0x2<<24)|(len-2)) #define PIPE_CONTROL_GLOBAL_GTT_IVB (1<<24) /* gen7+ */ +#define PIPE_CONTROL_MMIO_WRITE (1<<23) +#define PIPE_CONTROL_STORE_DATA_INDEX (1<<21) #define PIPE_CONTROL_CS_STALL (1<<20) #define PIPE_CONTROL_TLB_INVALIDATE (1<<18) #define PIPE_CONTROL_QW_WRITE (1<<14) +#define PIPE_CONTROL_POST_SYNC_OP_MASK (3<<14) #define PIPE_CONTROL_DEPTH_STALL (1<<13) #define PIPE_CONTROL_WRITE_FLUSH (1<<12) #define PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH (1<<12) /* gen6+ */ @@ -347,6 +355,85 @@ #define PIPE_CONTROL_DEPTH_CACHE_FLUSH (1<<0) #define PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */ +/* + * Commands used only by the command parser + */ +#define MI_SET_PREDICATE MI_INSTR(0x01, 0) +#define MI_ARB_CHECK MI_INSTR(0x05, 0) +#define MI_RS_CONTROL MI_INSTR(0x06, 0) +#define MI_URB_ATOMIC_ALLOC MI_INSTR(0x09, 0) +#define MI_PREDICATE MI_INSTR(0x0C, 0) +#define MI_RS_CONTEXT MI_INSTR(0x0F, 0) +#define MI_TOPOLOGY_FILTER MI_INSTR(0x0D, 0) +#define MI_LOAD_SCAN_LINES_EXCL MI_INSTR(0x13, 0) +#define MI_URB_CLEAR MI_INSTR(0x19, 0) +#define MI_UPDATE_GTT MI_INSTR(0x23, 0) +#define MI_CLFLUSH MI_INSTR(0x27, 0) +#define MI_REPORT_PERF_COUNT MI_INSTR(0x28, 0) +#define MI_REPORT_PERF_COUNT_GGTT (1<<0) +#define MI_LOAD_REGISTER_MEM MI_INSTR(0x29, 0) +#define MI_LOAD_REGISTER_REG MI_INSTR(0x2A, 0) +#define MI_RS_STORE_DATA_IMM MI_INSTR(0x2B, 0) +#define MI_LOAD_URB_MEM MI_INSTR(0x2C, 0) +#define MI_STORE_URB_MEM MI_INSTR(0x2D, 0) +#define MI_CONDITIONAL_BATCH_BUFFER_END MI_INSTR(0x36, 0) + +#define PIPELINE_SELECT ((0x3<<29)|(0x1<<27)|(0x1<<24)|(0x4<<16)) +#define GFX_OP_3DSTATE_VF_STATISTICS ((0x3<<29)|(0x1<<27)|(0x0<<24)|(0xB<<16)) +#define MEDIA_VFE_STATE ((0x3<<29)|(0x2<<27)|(0x0<<24)|(0x0<<16)) +#define MEDIA_VFE_STATE_MMIO_ACCESS_MASK (0x18) +#define GPGPU_OBJECT ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x4<<16)) +#define GPGPU_WALKER ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x5<<16)) +#define GFX_OP_3DSTATE_DX9_CONSTANTF_VS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x39<<16)) +#define GFX_OP_3DSTATE_DX9_CONSTANTF_PS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x3A<<16)) +#define GFX_OP_3DSTATE_SO_DECL_LIST \ + ((0x3<<29)|(0x3<<27)|(0x1<<24)|(0x17<<16)) + +#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x43<<16)) +#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x44<<16)) +#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x45<<16)) +#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x46<<16)) +#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS \ + ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x47<<16)) + +#define MFX_WAIT ((0x3<<29)|(0x1<<27)|(0x0<<16)) + +#define COLOR_BLT ((0x2<<29)|(0x40<<22)) +#define SRC_COPY_BLT ((0x2<<29)|(0x43<<22)) + +/* + * Registers used only by the command parser + */ +#define BCS_SWCTRL 0x22200 + +#define HS_INVOCATION_COUNT 0x2300 +#define DS_INVOCATION_COUNT 0x2308 +#define IA_VERTICES_COUNT 0x2310 +#define IA_PRIMITIVES_COUNT 0x2318 +#define VS_INVOCATION_COUNT 0x2320 +#define GS_INVOCATION_COUNT 0x2328 +#define GS_PRIMITIVES_COUNT 0x2330 +#define CL_INVOCATION_COUNT 0x2338 +#define CL_PRIMITIVES_COUNT 0x2340 +#define PS_INVOCATION_COUNT 0x2348 +#define PS_DEPTH_COUNT 0x2350 + +/* There are the 4 64-bit counter registers, one for each stream output */ +#define GEN7_SO_NUM_PRIMS_WRITTEN(n) (0x5200 + (n) * 8) + +#define OACONTROL 0x2360 + +#define _GEN7_PIPEA_DE_LOAD_SL 0x70068 +#define _GEN7_PIPEB_DE_LOAD_SL 0x71068 +#define GEN7_PIPE_DE_LOAD_SL(pipe) _PIPE(pipe, \ + _GEN7_PIPEA_DE_LOAD_SL, \ + _GEN7_PIPEB_DE_LOAD_SL) /* * Reset registers @@ -748,6 +835,7 @@ enum punit_power_well { #define RING_INSTDONE(base) ((base)+0x6c) #define RING_INSTPS(base) ((base)+0x70) #define RING_DMA_FADD(base) ((base)+0x78) +#define RING_DMA_FADD_UDW(base) ((base)+0x60) /* gen8+ */ #define RING_INSTPM(base) ((base)+0xc0) #define RING_MI_MODE(base) ((base)+0x9c) #define INSTPS 0x02070 /* 965+ only */ @@ -827,6 +915,7 @@ enum punit_power_well { # define MI_FLUSH_ENABLE (1 << 12) # define ASYNC_FLIP_PERF_DISABLE (1 << 14) # define MODE_IDLE (1 << 9) +# define STOP_RING (1 << 8) #define GEN6_GT_MODE 0x20d0 #define GEN7_GT_MODE 0x7008 @@ -841,7 +930,7 @@ enum punit_power_well { #define GFX_MODE_GEN7 0x0229c #define RING_MODE_GEN7(ring) ((ring)->mmio_base+0x29c) #define GFX_RUN_LIST_ENABLE (1<<15) -#define GFX_TLB_INVALIDATE_ALWAYS (1<<13) +#define GFX_TLB_INVALIDATE_EXPLICIT (1<<13) #define GFX_SURFACE_FAULT_ENABLE (1<<12) #define GFX_REPLAY_MODE (1<<11) #define GFX_PSMI_GRANULARITY (1<<10) @@ -3534,9 +3623,9 @@ enum punit_power_well { #define PIPE_PIXEL_MASK 0x00ffffff #define PIPE_PIXEL_SHIFT 0 /* GM45+ just has to be different */ -#define _PIPEA_FRMCOUNT_GM45 (dev_priv->info.display_mmio_offset + 0x70040) -#define _PIPEA_FLIPCOUNT_GM45 (dev_priv->info.display_mmio_offset + 0x70044) -#define PIPE_FRMCOUNT_GM45(pipe) _PIPE(pipe, _PIPEA_FRMCOUNT_GM45, _PIPEB_FRMCOUNT_GM45) +#define _PIPEA_FRMCOUNT_GM45 0x70040 +#define _PIPEA_FLIPCOUNT_GM45 0x70044 +#define PIPE_FRMCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FRMCOUNT_GM45) /* Cursor A & B regs */ #define _CURACNTR (dev_priv->info.display_mmio_offset + 0x70080) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 4867f4cc093..9b986775c4b 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -206,7 +206,7 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv, const struct lvds_dvo_timing *panel_dvo_timing; const struct lvds_fp_timing *fp_timing; struct drm_display_mode *panel_fixed_mode; - int i, downclock; + int i, downclock, drrs_mode; lvds_options = find_section(bdb, BDB_LVDS_OPTIONS); if (!lvds_options) @@ -218,6 +218,28 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv, panel_type = lvds_options->panel_type; + drrs_mode = (lvds_options->dps_panel_type_bits + >> (panel_type * 2)) & MODE_MASK; + /* + * VBT has static DRRS = 0 and seamless DRRS = 2. + * The below piece of code is required to adjust vbt.drrs_type + * to match the enum drrs_support_type. + */ + switch (drrs_mode) { + case 0: + dev_priv->vbt.drrs_type = STATIC_DRRS_SUPPORT; + DRM_DEBUG_KMS("DRRS supported mode is static\n"); + break; + case 2: + dev_priv->vbt.drrs_type = SEAMLESS_DRRS_SUPPORT; + DRM_DEBUG_KMS("DRRS supported mode is seamless\n"); + break; + default: + dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED; + DRM_DEBUG_KMS("DRRS not supported (VBT input)\n"); + break; + } + lvds_lfp_data = find_section(bdb, BDB_LVDS_LFP_DATA); if (!lvds_lfp_data) return; @@ -516,6 +538,16 @@ parse_driver_features(struct drm_i915_private *dev_priv, if (driver->dual_frequency) dev_priv->render_reclock_avail = true; + + DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled); + /* + * If DRRS is not supported, drrs_type has to be set to 0. + * This is because, VBT is configured in such a way that + * static DRRS is 0 and DRRS not supported is represented by + * driver->drrs_enabled=false + */ + if (!driver->drrs_enabled) + dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED; } static void diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h index 83b7629e436..d02e5f93c36 100644 --- a/drivers/gpu/drm/i915/intel_bios.h +++ b/drivers/gpu/drm/i915/intel_bios.h @@ -282,6 +282,9 @@ struct bdb_general_definitions { union child_device_config devices[0]; } __packed; +/* Mask for DRRS / Panel Channel / SSC / BLT control bits extraction */ +#define MODE_MASK 0x3 + struct bdb_lvds_options { u8 panel_type; u8 rsvd1; @@ -294,6 +297,18 @@ struct bdb_lvds_options { u8 lvds_edid:1; u8 rsvd2:1; u8 rsvd4; + /* LVDS Panel channel bits stored here */ + u32 lvds_panel_channel_bits; + /* LVDS SSC (Spread Spectrum Clock) bits stored here. */ + u16 ssc_bits; + u16 ssc_freq; + u16 ssc_ddt; + /* Panel color depth defined here */ + u16 panel_color_depth; + /* LVDS panel type bits stored here */ + u32 dps_panel_type_bits; + /* LVDS backlight control type bits stored here */ + u32 blt_control_type_bits; } __packed; /* LFP pointer table contains entries to the struct below */ @@ -479,6 +494,20 @@ struct bdb_driver_features { u8 hdmi_termination; u8 custom_vbt_version; + /* Driver features data block */ + u16 rmpm_enabled:1; + u16 s2ddt_enabled:1; + u16 dpst_enabled:1; + u16 bltclt_enabled:1; + u16 adb_enabled:1; + u16 drrs_enabled:1; + u16 grs_enabled:1; + u16 gpmt_enabled:1; + u16 tbt_enabled:1; + u16 psr_enabled:1; + u16 ips_enabled:1; + u16 reserved3:4; + u16 pc_feature_valid:1; } __packed; #define EDP_18BPP 0 diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index dae976f51d8..373ffdb97ae 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2166,15 +2166,6 @@ static int i9xx_update_primary_plane(struct drm_crtc *crtc, u32 dspcntr; u32 reg; - switch (plane) { - case 0: - case 1: - break; - default: - DRM_ERROR("Can't update plane %c in SAREA\n", plane_name(plane)); - return -EINVAL; - } - intel_fb = to_intel_framebuffer(fb); obj = intel_fb->obj; @@ -2267,16 +2258,6 @@ static int ironlake_update_primary_plane(struct drm_crtc *crtc, u32 dspcntr; u32 reg; - switch (plane) { - case 0: - case 1: - case 2: - break; - default: - DRM_ERROR("Can't update plane %c in SAREA\n", plane_name(plane)); - return -EINVAL; - } - intel_fb = to_intel_framebuffer(fb); obj = intel_fb->obj; @@ -4207,6 +4188,9 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk) struct drm_i915_private *dev_priv = dev->dev_private; u32 val, cmd; + WARN_ON(valleyview_cur_cdclk(dev_priv) != dev_priv->vlv_cdclk_freq); + dev_priv->vlv_cdclk_freq = cdclk; + if (cdclk >= 320) /* jump to highest voltage for 400MHz too */ cmd = 2; else if (cdclk == 266) @@ -4261,7 +4245,7 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk) intel_i2c_reset(dev); } -static int valleyview_cur_cdclk(struct drm_i915_private *dev_priv) +int valleyview_cur_cdclk(struct drm_i915_private *dev_priv) { int cur_cdclk, vco; int divider; @@ -4282,10 +4266,6 @@ static int valleyview_cur_cdclk(struct drm_i915_private *dev_priv) static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv, int max_pixclk) { - int cur_cdclk; - - cur_cdclk = valleyview_cur_cdclk(dev_priv); - /* * Really only a few cases to deal with, as only 4 CDclks are supported: * 200MHz @@ -4327,9 +4307,9 @@ static void valleyview_modeset_global_pipes(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc; int max_pixclk = intel_mode_max_pixclk(dev_priv); - int cur_cdclk = valleyview_cur_cdclk(dev_priv); - if (valleyview_calc_cdclk(dev_priv, max_pixclk) == cur_cdclk) + if (valleyview_calc_cdclk(dev_priv, max_pixclk) == + dev_priv->vlv_cdclk_freq) return; /* disable/enable all currently active pipes while we change cdclk */ @@ -4343,10 +4323,9 @@ static void valleyview_modeset_global_resources(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; int max_pixclk = intel_mode_max_pixclk(dev_priv); - int cur_cdclk = valleyview_cur_cdclk(dev_priv); int req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk); - if (req_cdclk != cur_cdclk) + if (req_cdclk != dev_priv->vlv_cdclk_freq) valleyview_set_cdclk(dev, req_cdclk); modeset_update_crtc_power_domains(dev); } @@ -5245,9 +5224,6 @@ static void vlv_update_pll(struct intel_crtc *crtc) << DPLL_MD_UDI_MULTIPLIER_SHIFT; crtc->config.dpll_hw_state.dpll_md = dpll_md; - if (crtc->config.has_dp_encoder) - intel_dp_set_m_n(crtc); - mutex_unlock(&dev_priv->dpio_lock); } @@ -5325,9 +5301,6 @@ static void i9xx_update_pll(struct intel_crtc *crtc, << DPLL_MD_UDI_MULTIPLIER_SHIFT; crtc->config.dpll_hw_state.dpll_md = dpll_md; } - - if (crtc->config.has_dp_encoder) - intel_dp_set_m_n(crtc); } static void i8xx_update_pll(struct intel_crtc *crtc, @@ -5656,6 +5629,9 @@ skip_dpll: dspcntr |= DISPPLANE_SEL_PIPE_B; } + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + intel_set_pipe_timings(intel_crtc); /* pipesrc and dspsize control the size that is scaled from, @@ -6880,8 +6856,6 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) struct drm_device *dev = dev_priv->dev; struct intel_ddi_plls *plls = &dev_priv->ddi_plls; struct intel_crtc *crtc; - unsigned long irqflags; - uint32_t val; list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) WARN(crtc->active, "CRTC for pipe %c enabled\n", @@ -6902,14 +6876,29 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) "Utility pin enabled\n"); WARN(I915_READ(PCH_GTC_CTL) & PCH_GTC_ENABLE, "PCH GTC enabled\n"); - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - val = I915_READ(DEIMR); - WARN((val | DE_PCH_EVENT_IVB) != 0xffffffff, - "Unexpected DEIMR bits enabled: 0x%x\n", val); - val = I915_READ(SDEIMR); - WARN((val | SDE_HOTPLUG_MASK_CPT) != 0xffffffff, - "Unexpected SDEIMR bits enabled: 0x%x\n", val); - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + /* + * In theory we can still leave IRQs enabled, as long as only the HPD + * interrupts remain enabled. We used to check for that, but since it's + * gen-specific and since we only disable LCPLL after we fully disable + * the interrupts, the check below should be enough. + */ + WARN(!dev_priv->pm.irqs_disabled, "IRQs enabled\n"); +} + +static void hsw_write_dcomp(struct drm_i915_private *dev_priv, uint32_t val) +{ + struct drm_device *dev = dev_priv->dev; + + if (IS_HASWELL(dev)) { + mutex_lock(&dev_priv->rps.hw_lock); + if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP, + val)) + DRM_ERROR("Failed to disable D_COMP\n"); + mutex_unlock(&dev_priv->rps.hw_lock); + } else { + I915_WRITE(D_COMP, val); + } + POSTING_READ(D_COMP); } /* @@ -6949,11 +6938,7 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv, val = I915_READ(D_COMP); val |= D_COMP_COMP_DISABLE; - mutex_lock(&dev_priv->rps.hw_lock); - if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP, val)) - DRM_ERROR("Failed to disable D_COMP\n"); - mutex_unlock(&dev_priv->rps.hw_lock); - POSTING_READ(D_COMP); + hsw_write_dcomp(dev_priv, val); ndelay(100); if (wait_for((I915_READ(D_COMP) & D_COMP_RCOMP_IN_PROGRESS) == 0, 1)) @@ -7008,11 +6993,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv) val = I915_READ(D_COMP); val |= D_COMP_COMP_FORCE; val &= ~D_COMP_COMP_DISABLE; - mutex_lock(&dev_priv->rps.hw_lock); - if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP, val)) - DRM_ERROR("Failed to enable D_COMP\n"); - mutex_unlock(&dev_priv->rps.hw_lock); - POSTING_READ(D_COMP); + hsw_write_dcomp(dev_priv, val); val = I915_READ(LCPLL_CTL); val &= ~LCPLL_PLL_DISABLE; @@ -7066,8 +7047,6 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv) struct drm_device *dev = dev_priv->dev; uint32_t val; - WARN_ON(!HAS_PC8(dev)); - DRM_DEBUG_KMS("Enabling package C8+\n"); if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { @@ -7077,7 +7056,7 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv) } lpt_disable_clkout_dp(dev); - hsw_runtime_pm_disable_interrupts(dev); + intel_runtime_pm_disable_interrupts(dev); hsw_disable_lcpll(dev_priv, true, true); } @@ -7086,12 +7065,10 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) struct drm_device *dev = dev_priv->dev; uint32_t val; - WARN_ON(!HAS_PC8(dev)); - DRM_DEBUG_KMS("Disabling package C8+\n"); hsw_restore_lcpll(dev_priv); - hsw_runtime_pm_restore_interrupts(dev); + intel_runtime_pm_restore_interrupts(dev); lpt_init_pch_refclk(dev); if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { @@ -7107,6 +7084,11 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) mutex_unlock(&dev_priv->rps.hw_lock); } +static void snb_modeset_global_resources(struct drm_device *dev) +{ + modeset_update_crtc_power_domains(dev); +} + static void haswell_modeset_global_resources(struct drm_device *dev) { modeset_update_crtc_power_domains(dev); @@ -10567,16 +10549,6 @@ static void intel_crtc_init(struct drm_device *dev, int pipe) drm_crtc_init(dev, &intel_crtc->base, &intel_crtc_funcs); - if (IS_GEN2(dev)) { - intel_crtc->max_cursor_width = GEN2_CURSOR_WIDTH; - intel_crtc->max_cursor_height = GEN2_CURSOR_HEIGHT; - } else { - intel_crtc->max_cursor_width = CURSOR_WIDTH; - intel_crtc->max_cursor_height = CURSOR_HEIGHT; - } - dev->mode_config.cursor_width = intel_crtc->max_cursor_width; - dev->mode_config.cursor_height = intel_crtc->max_cursor_height; - drm_mode_crtc_set_gamma_size(&intel_crtc->base, 256); for (i = 0; i < 256; i++) { intel_crtc->lut_r[i] = i; @@ -11077,6 +11049,8 @@ static void intel_init_display(struct drm_device *dev) } else if (IS_GEN6(dev)) { dev_priv->display.fdi_link_train = gen6_fdi_link_train; dev_priv->display.write_eld = ironlake_write_eld; + dev_priv->display.modeset_global_resources = + snb_modeset_global_resources; } else if (IS_IVYBRIDGE(dev)) { /* FIXME: detect B0+ stepping and use auto training */ dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train; @@ -11327,6 +11301,15 @@ void intel_modeset_init(struct drm_device *dev) dev->mode_config.max_width = 8192; dev->mode_config.max_height = 8192; } + + if (IS_GEN2(dev)) { + dev->mode_config.cursor_width = GEN2_CURSOR_WIDTH; + dev->mode_config.cursor_height = GEN2_CURSOR_HEIGHT; + } else { + dev->mode_config.cursor_width = MAX_CURSOR_WIDTH; + dev->mode_config.cursor_height = MAX_CURSOR_HEIGHT; + } + dev->mode_config.fb_base = dev_priv->gtt.mappable_base; DRM_DEBUG_KMS("%d display pipe%s available.\n", diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index a0dad1a2f81..e48d47ced57 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1043,7 +1043,10 @@ static u32 ironlake_get_pp_control(struct intel_dp *intel_dp) static bool _edp_panel_vdd_on(struct intel_dp *intel_dp) { struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct intel_encoder *intel_encoder = &intel_dig_port->base; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; u32 pp; u32 pp_stat_reg, pp_ctrl_reg; bool need_to_disable = !intel_dp->want_panel_vdd; @@ -1056,7 +1059,8 @@ static bool _edp_panel_vdd_on(struct intel_dp *intel_dp) if (edp_have_panel_vdd(intel_dp)) return need_to_disable; - intel_runtime_pm_get(dev_priv); + power_domain = intel_display_port_power_domain(intel_encoder); + intel_display_power_get(dev_priv, power_domain); DRM_DEBUG_KMS("Turning eDP VDD on\n"); @@ -1103,6 +1107,11 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp) WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); if (!intel_dp->want_panel_vdd && edp_have_panel_vdd(intel_dp)) { + struct intel_digital_port *intel_dig_port = + dp_to_dig_port(intel_dp); + struct intel_encoder *intel_encoder = &intel_dig_port->base; + enum intel_display_power_domain power_domain; + DRM_DEBUG_KMS("Turning eDP VDD off\n"); pp = ironlake_get_pp_control(intel_dp); @@ -1121,7 +1130,8 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp) if ((pp & POWER_TARGET_ON) == 0) intel_dp->last_power_cycle = jiffies; - intel_runtime_pm_put(dev_priv); + power_domain = intel_display_port_power_domain(intel_encoder); + intel_display_power_put(dev_priv, power_domain); } } @@ -1205,8 +1215,11 @@ void intel_edp_panel_on(struct intel_dp *intel_dp) void intel_edp_panel_off(struct intel_dp *intel_dp) { + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct intel_encoder *intel_encoder = &intel_dig_port->base; struct drm_device *dev = intel_dp_to_dev(intel_dp); struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; u32 pp; u32 pp_ctrl_reg; @@ -1236,7 +1249,8 @@ void intel_edp_panel_off(struct intel_dp *intel_dp) wait_panel_off(intel_dp); /* We got a reference when we enabled the VDD. */ - intel_runtime_pm_put(dev_priv); + power_domain = intel_display_port_power_domain(intel_encoder); + intel_display_power_put(dev_priv, power_domain); } void intel_edp_backlight_on(struct intel_dp *intel_dp) @@ -1777,17 +1791,23 @@ static void intel_disable_dp(struct intel_encoder *encoder) intel_dp_link_down(intel_dp); } -static void intel_post_disable_dp(struct intel_encoder *encoder) +static void g4x_post_disable_dp(struct intel_encoder *encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = dp_to_dig_port(intel_dp)->port; - struct drm_device *dev = encoder->base.dev; - if (port == PORT_A || IS_VALLEYVIEW(dev)) { - intel_dp_link_down(intel_dp); - if (!IS_VALLEYVIEW(dev)) - ironlake_edp_pll_off(intel_dp); - } + if (port != PORT_A) + return; + + intel_dp_link_down(intel_dp); + ironlake_edp_pll_off(intel_dp); +} + +static void vlv_post_disable_dp(struct intel_encoder *encoder) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + + intel_dp_link_down(intel_dp); } static void intel_enable_dp(struct intel_encoder *encoder) @@ -3831,16 +3851,17 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) intel_encoder->compute_config = intel_dp_compute_config; intel_encoder->mode_set = intel_dp_mode_set; intel_encoder->disable = intel_disable_dp; - intel_encoder->post_disable = intel_post_disable_dp; intel_encoder->get_hw_state = intel_dp_get_hw_state; intel_encoder->get_config = intel_dp_get_config; if (IS_VALLEYVIEW(dev)) { intel_encoder->pre_pll_enable = vlv_dp_pre_pll_enable; intel_encoder->pre_enable = vlv_pre_enable_dp; intel_encoder->enable = vlv_enable_dp; + intel_encoder->post_disable = vlv_post_disable_dp; } else { intel_encoder->pre_enable = g4x_pre_enable_dp; intel_encoder->enable = g4x_enable_dp; + intel_encoder->post_disable = g4x_post_disable_dp; } intel_dig_port->port = port; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0542de98226..42762b798cb 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -81,8 +81,8 @@ /* Maximum cursor sizes */ #define GEN2_CURSOR_WIDTH 64 #define GEN2_CURSOR_HEIGHT 64 -#define CURSOR_WIDTH 256 -#define CURSOR_HEIGHT 256 +#define MAX_CURSOR_WIDTH 256 +#define MAX_CURSOR_HEIGHT 256 #define INTEL_I2C_BUS_DVO 1 #define INTEL_I2C_BUS_SDVO 2 @@ -373,7 +373,6 @@ struct intel_crtc { uint32_t cursor_addr; int16_t cursor_x, cursor_y; int16_t cursor_width, cursor_height; - int16_t max_cursor_width, max_cursor_height; bool cursor_visible; struct intel_plane_config plane_config; @@ -628,8 +627,8 @@ void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); -void hsw_runtime_pm_disable_interrupts(struct drm_device *dev); -void hsw_runtime_pm_restore_interrupts(struct drm_device *dev); +void intel_runtime_pm_disable_interrupts(struct drm_device *dev); +void intel_runtime_pm_restore_interrupts(struct drm_device *dev); /* intel_crt.c */ @@ -665,6 +664,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder, const char *intel_output_name(int output); bool intel_has_pending_fb_unpin(struct drm_device *dev); int intel_pch_rawclk(struct drm_device *dev); +int valleyview_cur_cdclk(struct drm_i915_private *dev_priv); void intel_mark_busy(struct drm_device *dev); void intel_mark_fb_busy(struct drm_i915_gem_object *obj, struct intel_ring_buffer *ring); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 5874716774a..04af065a932 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3041,7 +3041,7 @@ void gen6_set_rps(struct drm_device *dev, u8 val) if (val != dev_priv->rps.cur_freq) { gen6_set_rps_thresholds(dev_priv, val); - if (IS_HASWELL(dev)) + if (IS_HASWELL(dev) || IS_BROADWELL(dev)) I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(val)); else @@ -3242,6 +3242,27 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev) spin_unlock_irq(&dev_priv->irq_lock); } +static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_cap) +{ + /* All of these values are in units of 50MHz */ + dev_priv->rps.cur_freq = 0; + /* static values from HW: RP0 < RPe < RP1 < RPn (min_freq) */ + dev_priv->rps.rp1_freq = (rp_state_cap >> 8) & 0xff; + dev_priv->rps.rp0_freq = (rp_state_cap >> 0) & 0xff; + dev_priv->rps.min_freq = (rp_state_cap >> 16) & 0xff; + /* XXX: only BYT has a special efficient freq */ + dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq; + /* hw_max = RP0 until we check for overclocking */ + dev_priv->rps.max_freq = dev_priv->rps.rp0_freq; + + /* Preserve min/max settings in case of re-init */ + if (dev_priv->rps.max_freq_softlimit == 0) + dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq; + + if (dev_priv->rps.min_freq_softlimit == 0) + dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq; +} + static void gen8_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3260,6 +3281,7 @@ static void gen8_enable_rps(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); + parse_rp_state_cap(dev_priv, rp_state_cap); /* 2b: Program RC6 thresholds.*/ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16); @@ -3279,8 +3301,10 @@ static void gen8_enable_rps(struct drm_device *dev) rc6_mask); /* 4 Program defaults and thresholds for RPS*/ - I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(10)); /* Request 500 MHz */ - I915_WRITE(GEN6_RC_VIDEO_FREQ, HSW_FREQUENCY(12)); /* Request 600 MHz */ + I915_WRITE(GEN6_RPNSWREQ, + HSW_FREQUENCY(dev_priv->rps.rp1_freq)); + I915_WRITE(GEN6_RC_VIDEO_FREQ, + HSW_FREQUENCY(dev_priv->rps.rp1_freq)); /* NB: Docs say 1s, and 1000000 - which aren't equivalent */ I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */ @@ -3346,23 +3370,7 @@ static void gen6_enable_rps(struct drm_device *dev) rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS); - /* All of these values are in units of 50MHz */ - dev_priv->rps.cur_freq = 0; - /* static values from HW: RP0 < RPe < RP1 < RPn (min_freq) */ - dev_priv->rps.rp1_freq = (rp_state_cap >> 8) & 0xff; - dev_priv->rps.rp0_freq = (rp_state_cap >> 0) & 0xff; - dev_priv->rps.min_freq = (rp_state_cap >> 16) & 0xff; - /* XXX: only BYT has a special efficient freq */ - dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq; - /* hw_max = RP0 until we check for overclocking */ - dev_priv->rps.max_freq = dev_priv->rps.rp0_freq; - - /* Preserve min/max settings in case of re-init */ - if (dev_priv->rps.max_freq_softlimit == 0) - dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq; - - if (dev_priv->rps.min_freq_softlimit == 0) - dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq; + parse_rp_state_cap(dev_priv, rp_state_cap); /* disable the counters and set deterministic thresholds */ I915_WRITE(GEN6_RC_CONTROL, 0); @@ -3479,7 +3487,8 @@ void gen6_update_ring_freq(struct drm_device *dev) * to use for memory access. We do this by specifying the IA frequency * the PCU should use as a reference to determine the ring frequency. */ - for (gpu_freq = dev_priv->rps.max_freq_softlimit; gpu_freq >= dev_priv->rps.min_freq_softlimit; + for (gpu_freq = dev_priv->rps.max_freq_softlimit; + gpu_freq >= dev_priv->rps.min_freq_softlimit && gpu_freq != 0; gpu_freq--) { int diff = dev_priv->rps.max_freq_softlimit - gpu_freq; unsigned int ia_freq = 0, ring_freq = 0; @@ -5076,6 +5085,10 @@ static void valleyview_init_clock_gating(struct drm_device *dev) } DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq); + dev_priv->vlv_cdclk_freq = valleyview_cur_cdclk(dev_priv); + DRM_DEBUG_DRIVER("Current CD clock rate: %d MHz", + dev_priv->vlv_cdclk_freq); + I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE); /* WaDisableEarlyCull:vlv */ diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 6bc68bdcf43..3d76ce135a0 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -437,32 +437,41 @@ static void ring_setup_phys_status_page(struct intel_ring_buffer *ring) I915_WRITE(HWS_PGA, addr); } -static int init_ring_common(struct intel_ring_buffer *ring) +static bool stop_ring(struct intel_ring_buffer *ring) { - struct drm_device *dev = ring->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_i915_gem_object *obj = ring->obj; - int ret = 0; - u32 head; + struct drm_i915_private *dev_priv = to_i915(ring->dev); - gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); + if (!IS_GEN2(ring->dev)) { + I915_WRITE_MODE(ring, _MASKED_BIT_ENABLE(STOP_RING)); + if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) { + DRM_ERROR("%s :timed out trying to stop ring\n", ring->name); + return false; + } + } - /* Stop the ring if it's running. */ I915_WRITE_CTL(ring, 0); I915_WRITE_HEAD(ring, 0); ring->write_tail(ring, 0); - if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) - DRM_ERROR("%s :timed out trying to stop ring\n", ring->name); - if (I915_NEED_GFX_HWS(dev)) - intel_ring_setup_status_page(ring); - else - ring_setup_phys_status_page(ring); + if (!IS_GEN2(ring->dev)) { + (void)I915_READ_CTL(ring); + I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING)); + } - head = I915_READ_HEAD(ring) & HEAD_ADDR; + return (I915_READ_HEAD(ring) & HEAD_ADDR) == 0; +} - /* G45 ring initialization fails to reset head to zero */ - if (head != 0) { +static int init_ring_common(struct intel_ring_buffer *ring) +{ + struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_object *obj = ring->obj; + int ret = 0; + + gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); + + if (!stop_ring(ring)) { + /* G45 ring initialization often fails to reset head to zero */ DRM_DEBUG_KMS("%s head not reset to zero " "ctl %08x head %08x tail %08x start %08x\n", ring->name, @@ -471,9 +480,7 @@ static int init_ring_common(struct intel_ring_buffer *ring) I915_READ_TAIL(ring), I915_READ_START(ring)); - I915_WRITE_HEAD(ring, 0); - - if (I915_READ_HEAD(ring) & HEAD_ADDR) { + if (!stop_ring(ring)) { DRM_ERROR("failed to set %s head to zero " "ctl %08x head %08x tail %08x start %08x\n", ring->name, @@ -481,9 +488,16 @@ static int init_ring_common(struct intel_ring_buffer *ring) I915_READ_HEAD(ring), I915_READ_TAIL(ring), I915_READ_START(ring)); + ret = -EIO; + goto out; } } + if (I915_NEED_GFX_HWS(dev)) + intel_ring_setup_status_page(ring); + else + ring_setup_phys_status_page(ring); + /* Initialize the ring. This must happen _after_ we've cleared the ring * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring @@ -587,13 +601,15 @@ static int init_render_ring(struct intel_ring_buffer *ring) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE)); /* Required for the hardware to program scanline values for waiting */ + /* WaEnableFlushTlbInvalidationMode:snb */ if (INTEL_INFO(dev)->gen == 6) I915_WRITE(GFX_MODE, - _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_ALWAYS)); + _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT)); + /* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */ if (IS_GEN7(dev)) I915_WRITE(GFX_MODE_GEN7, - _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) | + _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) | _MASKED_BIT_ENABLE(GFX_REPLAY_MODE)); if (INTEL_INFO(dev)->gen >= 5) { @@ -610,13 +626,6 @@ static int init_render_ring(struct intel_ring_buffer *ring) */ I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB)); - - /* This is not explicitly set for GEN6, so read the register. - * see intel_ring_mi_set_context() for why we care. - * TODO: consider explicitly setting the bit for GEN5 - */ - ring->itlb_before_ctx_switch = - !!(I915_READ(GFX_MODE) & GFX_TLB_INVALIDATE_ALWAYS); } if (INTEL_INFO(dev)->gen >= 6) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 270a6a97343..413cdc74ed5 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -34,6 +34,7 @@ struct intel_hw_status_page { #define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val) #define I915_READ_MODE(ring) I915_READ(RING_MI_MODE((ring)->mmio_base)) +#define I915_WRITE_MODE(ring, val) I915_WRITE(RING_MI_MODE((ring)->mmio_base), val) enum intel_ring_hangcheck_action { HANGCHECK_IDLE = 0, @@ -152,10 +153,6 @@ struct intel_ring_buffer { wait_queue_head_t irq_queue; - /** - * Do an explicit TLB flush before MI_SET_CONTEXT - */ - bool itlb_before_ctx_switch; struct i915_hw_context *default_context; struct i915_hw_context *last_context; diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 0954f132726..b1a5514e695 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -182,6 +182,14 @@ u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)), DPIO_OPCODE_REG_READ, reg, &val); + + /* + * FIXME: There might be some registers where all 1's is a valid value, + * so ideally we should check the register offset instead... + */ + WARN(val == 0xffffffff, "DPIO read pipe %c reg 0x%x == 0x%x\n", + pipe_name(pipe), reg, val); + return val; } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index f729dc71d5b..2a72bab106d 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -253,8 +253,7 @@ static void __vlv_force_wake_put(struct drm_i915_private *dev_priv, } -void vlv_force_wake_get(struct drm_i915_private *dev_priv, - int fw_engine) +static void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine) { unsigned long irqflags; @@ -273,8 +272,7 @@ void vlv_force_wake_get(struct drm_i915_private *dev_priv, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -void vlv_force_wake_put(struct drm_i915_private *dev_priv, - int fw_engine) +static void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine) { unsigned long irqflags; @@ -486,6 +484,17 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv) #define NEEDS_FORCE_WAKE(dev_priv, reg) \ ((reg) < 0x40000 && (reg) != FORCEWAKE) +#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \ + (((reg) >= 0x2000 && (reg) < 0x4000) ||\ + ((reg) >= 0x5000 && (reg) < 0x8000) ||\ + ((reg) >= 0xB000 && (reg) < 0x12000) ||\ + ((reg) >= 0x2E000 && (reg) < 0x30000)) + +#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\ + (((reg) >= 0x12000 && (reg) < 0x14000) ||\ + ((reg) >= 0x22000 && (reg) < 0x24000) ||\ + ((reg) >= 0x30000 && (reg) < 0x40000)) + static void ilk_dummy_write(struct drm_i915_private *dev_priv) { @@ -852,12 +861,15 @@ void intel_uncore_fini(struct drm_device *dev) intel_uncore_forcewake_reset(dev, false); } +#define GEN_RANGE(l, h) GENMASK(h, l) + static const struct register_whitelist { uint64_t offset; uint32_t size; - uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */ + /* supported gens, 0x10 for 4, 0x30 for 4 and 5, etc. */ + uint32_t gen_bitmask; } whitelist[] = { - { RING_TIMESTAMP(RENDER_RING_BASE), 8, 0x1F0 }, + { RING_TIMESTAMP(RENDER_RING_BASE), 8, GEN_RANGE(4, 8) }, }; int i915_reg_read_ioctl(struct drm_device *dev, diff --git a/include/drm/drmP.h b/include/drm/drmP.h index a7c2a862b4f..f3c9a63e370 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1310,7 +1310,7 @@ extern int drm_remove_magic(struct drm_master *master, drm_magic_t magic); /* Cache management (drm_cache.c) */ void drm_clflush_pages(struct page *pages[], unsigned long num_pages); void drm_clflush_sg(struct sg_table *st); -void drm_clflush_virt_range(char *addr, unsigned long length); +void drm_clflush_virt_range(void *addr, unsigned long length); /* Locking IOCTL support (drm_lock.h) */ extern int drm_lock(struct drm_device *dev, void *data, diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 126bfaa8bb6..8a3e4ef00c3 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -337,6 +337,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_EXEC_NO_RELOC 25 #define I915_PARAM_HAS_EXEC_HANDLE_LUT 26 #define I915_PARAM_HAS_WT 27 +#define I915_PARAM_CMD_PARSER_VERSION 28 typedef struct drm_i915_getparam { int param; |