diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
59 files changed, 10932 insertions, 3555 deletions
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index bea2d67196fb..437e1824d0bf 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -5,6 +5,7 @@ config DRM_I915 depends on (AGP || AGP=n) select INTEL_GTT select AGP_INTEL if AGP + select INTERVAL_TREE # we need shmfs for the swappable backing store, and in particular # the shmem_readpage() which depends upon tmpfs select SHMEM @@ -71,7 +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/Makefile b/drivers/gpu/drm/i915/Makefile index b1445b73465b..cad1683d8bb5 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -18,6 +18,7 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o # GEM code i915-y += i915_cmd_parser.o \ i915_gem_context.o \ + i915_gem_render_state.o \ i915_gem_debug.o \ i915_gem_dmabuf.o \ i915_gem_evict.o \ @@ -26,12 +27,18 @@ i915-y += i915_cmd_parser.o \ i915_gem.o \ i915_gem_stolen.o \ i915_gem_tiling.o \ + i915_gem_userptr.o \ i915_gpu_error.o \ i915_irq.o \ i915_trace_points.o \ intel_ringbuffer.o \ intel_uncore.o +# autogenerated null render state +i915-y += intel_renderstate_gen6.o \ + intel_renderstate_gen7.o \ + intel_renderstate_gen8.o + # modesetting core code i915-y += intel_bios.o \ intel_display.o \ @@ -55,6 +62,7 @@ i915-y += dvo_ch7017.o \ intel_dsi_cmd.o \ intel_dsi.o \ intel_dsi_pll.o \ + intel_dsi_panel_vbt.o \ intel_dvo.o \ intel_hdmi.o \ intel_i2c.o \ diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c index a0f5bdd69491..80449f475960 100644 --- a/drivers/gpu/drm/i915/dvo_ch7xxx.c +++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c @@ -160,7 +160,7 @@ static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) if (i2c_transfer(adapter, msgs, 2) == 2) { *ch = in_buf[0]; return true; - }; + } if (!ch7xxx->quiet) { DRM_DEBUG_KMS("Unable to read register 0x%02x from %s:%02x.\n", diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c index 0f1865d7d4d8..0f2587ff347c 100644 --- a/drivers/gpu/drm/i915/dvo_ivch.c +++ b/drivers/gpu/drm/i915/dvo_ivch.c @@ -195,7 +195,7 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data) if (i2c_transfer(adapter, msgs, 3) == 3) { *data = (in_buf[1] << 8) | in_buf[0]; return true; - }; + } if (!priv->quiet) { DRM_DEBUG_KMS("Unable to read register 0x%02x from " diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c index 8155ded79079..74f2af7c2d3e 100644 --- a/drivers/gpu/drm/i915/dvo_ns2501.c +++ b/drivers/gpu/drm/i915/dvo_ns2501.c @@ -121,7 +121,7 @@ static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, uint8_t * ch) if (i2c_transfer(adapter, msgs, 2) == 2) { *ch = in_buf[0]; return true; - }; + } if (!ns->quiet) { DRM_DEBUG_KMS @@ -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/dvo_sil164.c b/drivers/gpu/drm/i915/dvo_sil164.c index 7b3e9e936200..fa0114967076 100644 --- a/drivers/gpu/drm/i915/dvo_sil164.c +++ b/drivers/gpu/drm/i915/dvo_sil164.c @@ -93,7 +93,7 @@ static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) if (i2c_transfer(adapter, msgs, 2) == 2) { *ch = in_buf[0]; return true; - }; + } if (!sil->quiet) { DRM_DEBUG_KMS("Unable to read register 0x%02x from %s:%02x.\n", diff --git a/drivers/gpu/drm/i915/dvo_tfp410.c b/drivers/gpu/drm/i915/dvo_tfp410.c index 12ea4b164692..7853719a0e81 100644 --- a/drivers/gpu/drm/i915/dvo_tfp410.c +++ b/drivers/gpu/drm/i915/dvo_tfp410.c @@ -118,7 +118,7 @@ static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch) if (i2c_transfer(adapter, msgs, 2) == 2) { *ch = in_buf[0]; return true; - }; + } if (!tfp->quiet) { DRM_DEBUG_KMS("Unable to read register 0x%02x from %s:%02x.\n", diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 4cf6d020d513..9d7954366bd2 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -28,7 +28,7 @@ #include "i915_drv.h" /** - * DOC: i915 batch buffer command parser + * DOC: batch buffer command parser * * Motivation: * Certain OpenGL features (e.g. transform feedback, performance monitoring) @@ -86,6 +86,367 @@ * 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. */ + GEN7_3DPRIM_END_OFFSET, + GEN7_3DPRIM_START_VERTEX, + GEN7_3DPRIM_VERTEX_COUNT, + GEN7_3DPRIM_INSTANCE_COUNT, + GEN7_3DPRIM_START_INSTANCE, + GEN7_3DPRIM_BASE_VERTEX, + 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)), + REG64(GEN7_SO_PRIM_STORAGE_NEEDED(0)), + REG64(GEN7_SO_PRIM_STORAGE_NEEDED(1)), + REG64(GEN7_SO_PRIM_STORAGE_NEEDED(2)), + REG64(GEN7_SO_PRIM_STORAGE_NEEDED(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; @@ -137,15 +498,18 @@ 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_engine_cs *ring, + const struct drm_i915_cmd_table *cmd_tables, + int cmd_table_count) { int i; + bool ret = true; - if (!ring->cmd_tables || ring->cmd_table_count == 0) - return; + if (!cmd_tables || cmd_table_count == 0) + return true; - for (i = 0; i < ring->cmd_table_count; i++) { - const struct drm_i915_cmd_table *table = &ring->cmd_tables[i]; + for (i = 0; i < cmd_table_count; i++) { + const struct drm_i915_cmd_table *table = &cmd_tables[i]; u32 previous = 0; int j; @@ -154,35 +518,107 @@ 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 bool validate_regs_sorted(struct intel_engine_cs *ring) +{ + return check_sorted(ring->id, ring->reg_table, ring->reg_count) && + check_sorted(ring->id, ring->master_reg_table, + ring->master_reg_count); +} + +struct cmd_node { + const struct drm_i915_cmd_descriptor *desc; + struct hlist_node node; +}; + +/* + * Different command ranges have different numbers of bits for the opcode. For + * example, MI commands use bits 31:23 while 3D commands use bits 31:16. The + * problem is that, for example, MI commands use bits 22:16 for other fields + * such as GGTT vs PPGTT bits. If we include those bits in the mask then when + * we mask a command from a batch it could hash to the wrong bucket due to + * non-opcode bits being set. But if we don't include those bits, some 3D + * commands may hash to the same bucket due to not including opcode bits that + * make the command unique. For now, we will risk hashing to the same bucket. + * + * If we attempt to generate a perfect hash, we should be able to look at bits + * 31:29 of a command from a batch buffer and use the full mask for that + * client. The existing INSTR_CLIENT_MASK/SHIFT defines can be used for this. + */ +#define CMD_HASH_MASK STD_MI_OPCODE_MASK + +static int init_hash_table(struct intel_engine_cs *ring, + const struct drm_i915_cmd_table *cmd_tables, + int cmd_table_count) +{ + int i, j; + + hash_init(ring->cmd_hash); + + for (i = 0; i < cmd_table_count; i++) { + const struct drm_i915_cmd_table *table = &cmd_tables[i]; + + for (j = 0; j < table->count; j++) { + const struct drm_i915_cmd_descriptor *desc = + &table->table[j]; + struct cmd_node *desc_node = + kmalloc(sizeof(*desc_node), GFP_KERNEL); + + if (!desc_node) + return -ENOMEM; + + desc_node->desc = desc; + hash_add(ring->cmd_hash, &desc_node->node, + desc->cmd.value & CMD_HASH_MASK); + } + } + + return 0; } -static void validate_regs_sorted(struct intel_ring_buffer *ring) +static void fini_hash_table(struct intel_engine_cs *ring) { - check_sorted(ring->id, ring->reg_table, ring->reg_count); - check_sorted(ring->id, ring->master_reg_table, ring->master_reg_count); + struct hlist_node *tmp; + struct cmd_node *desc_node; + int i; + + hash_for_each_safe(ring->cmd_hash, i, tmp, desc_node, node) { + hash_del(&desc_node->node); + kfree(desc_node); + } } /** @@ -190,25 +626,74 @@ static void validate_regs_sorted(struct intel_ring_buffer *ring) * @ring: the ringbuffer to initialize * * Optionally initializes fields related to batch buffer command parsing in the - * struct intel_ring_buffer based on whether the platform requires software + * struct intel_engine_cs based on whether the platform requires software * command parsing. + * + * Return: non-zero if initialization fails */ -void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) +int i915_cmd_parser_init_ring(struct intel_engine_cs *ring) { + const struct drm_i915_cmd_table *cmd_tables; + int cmd_table_count; + int ret; + if (!IS_GEN7(ring->dev)) - return; + return 0; switch (ring->id) { case RCS: + if (IS_HASWELL(ring->dev)) { + cmd_tables = hsw_render_ring_cmds; + cmd_table_count = + ARRAY_SIZE(hsw_render_ring_cmds); + } else { + cmd_tables = gen7_render_cmds; + 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: + cmd_tables = gen7_video_cmds; + 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)) { + cmd_tables = hsw_blt_ring_cmds; + cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + } else { + cmd_tables = gen7_blt_cmds; + 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: + cmd_tables = hsw_vebox_cmds; + 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; @@ -218,18 +703,45 @@ 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, cmd_tables, cmd_table_count)); + BUG_ON(!validate_regs_sorted(ring)); + + ret = init_hash_table(ring, cmd_tables, cmd_table_count); + if (ret) { + DRM_ERROR("CMD: cmd_parser_init failed!\n"); + fini_hash_table(ring); + return ret; + } + + ring->needs_cmd_parser = true; + + return 0; +} + +/** + * i915_cmd_parser_fini_ring() - clean up cmd parser related fields + * @ring: the ringbuffer to clean up + * + * Releases any resources related to command parsing that may have been + * initialized for the specified ring. + */ +void i915_cmd_parser_fini_ring(struct intel_engine_cs *ring) +{ + if (!ring->needs_cmd_parser) + return; + + fini_hash_table(ring); } static const struct drm_i915_cmd_descriptor* -find_cmd_in_table(const struct drm_i915_cmd_table *table, +find_cmd_in_table(struct intel_engine_cs *ring, u32 cmd_header) { - int i; + struct cmd_node *desc_node; - for (i = 0; i < table->count; i++) { - const struct drm_i915_cmd_descriptor *desc = &table->table[i]; + hash_for_each_possible(ring->cmd_hash, desc_node, node, + cmd_header & CMD_HASH_MASK) { + const struct drm_i915_cmd_descriptor *desc = desc_node->desc; u32 masked_cmd = desc->cmd.mask & cmd_header; u32 masked_value = desc->cmd.value & desc->cmd.mask; @@ -249,20 +761,16 @@ find_cmd_in_table(const struct drm_i915_cmd_table *table, * ring's default length encoding and returns default_desc. */ static const struct drm_i915_cmd_descriptor* -find_cmd(struct intel_ring_buffer *ring, +find_cmd(struct intel_engine_cs *ring, u32 cmd_header, struct drm_i915_cmd_descriptor *default_desc) { + const struct drm_i915_cmd_descriptor *desc; u32 mask; - int i; - for (i = 0; i < ring->cmd_table_count; i++) { - const struct drm_i915_cmd_descriptor *desc; - - desc = find_cmd_in_table(&ring->cmd_tables[i], cmd_header); - if (desc) - return desc; - } + desc = find_cmd_in_table(ring, cmd_header); + if (desc) + return desc; mask = ring->get_cmd_length_mask(cmd_header); if (!mask) @@ -329,15 +837,112 @@ finish: * * Return: true if the ring requires software command parsing */ -bool i915_needs_cmd_parser(struct intel_ring_buffer *ring) +bool i915_needs_cmd_parser(struct intel_engine_cs *ring) { - /* No command tables indicates a platform without parsing */ - if (!ring->cmd_tables) + struct drm_i915_private *dev_priv = ring->dev->dev_private; + + if (!ring->needs_cmd_parser) + 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_engine_cs *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 /** @@ -352,7 +957,7 @@ bool i915_needs_cmd_parser(struct intel_ring_buffer *ring) * * Return: non-zero if the parser finds violations or otherwise fails */ -int i915_parse_cmds(struct intel_ring_buffer *ring, +int i915_parse_cmds(struct intel_engine_cs *ring, struct drm_i915_gem_object *batch_obj, u32 batch_start_offset, bool is_master) @@ -361,6 +966,7 @@ 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) { @@ -402,76 +1008,27 @@ 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)); + batch_end - cmd); ret = -EINVAL; break; } - if (desc->flags & CMD_DESC_REJECT) { - DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd); + if (!check_cmd(ring, desc, cmd, is_master, &oacontrol_set)) { ret = -EINVAL; break; } - if ((desc->flags & CMD_DESC_MASTER) && !is_master) { - DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", - *cmd); - 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 +1040,22 @@ 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 195fe5bc0aac..601caa88c092 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -79,7 +79,7 @@ drm_add_fake_info_node(struct drm_minor *minor, static int i915_capabilities(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; const struct intel_device_info *info = INTEL_INFO(dev); @@ -172,7 +172,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) seq_printf(m, " (%s)", obj->ring->name); } -static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx) +static void describe_ctx(struct seq_file *m, struct intel_context *ctx) { seq_putc(m, ctx->is_initialized ? 'I' : 'i'); seq_putc(m, ctx->remap_slice ? 'R' : 'r'); @@ -181,7 +181,7 @@ static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx) static int i915_gem_object_list_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; uintptr_t list = (uintptr_t) node->info_ent->data; struct list_head *head; struct drm_device *dev = node->minor->dev; @@ -239,7 +239,7 @@ static int obj_rank_by_stolen(void *priv, static int i915_gem_stolen_list_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; @@ -371,7 +371,7 @@ static int per_file_stats(int id, void *ptr, void *data) static int i915_gem_object_info(struct seq_file *m, void* data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 count, mappable_count, purgeable_count; @@ -474,7 +474,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data) static int i915_gem_gtt_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; uintptr_t list = (uintptr_t) node->info_ent->data; struct drm_i915_private *dev_priv = dev->dev_private; @@ -509,12 +509,12 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data) static int i915_gem_pageflip_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; unsigned long flags; struct intel_crtc *crtc; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { const char pipe = pipe_name(crtc->pipe); const char plane = plane_name(crtc->plane); struct intel_unpin_work *work; @@ -559,10 +559,10 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data) static int i915_gem_request_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; struct drm_i915_gem_request *gem_request; int ret, count, i; @@ -594,7 +594,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data) } static void i915_ring_seqno_info(struct seq_file *m, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { if (ring->get_seqno) { seq_printf(m, "Current sequence (%s): %u\n", @@ -604,10 +604,10 @@ static void i915_ring_seqno_info(struct seq_file *m, static int i915_gem_seqno_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i; ret = mutex_lock_interruptible(&dev->struct_mutex); @@ -627,10 +627,10 @@ static int i915_gem_seqno_info(struct seq_file *m, void *data) static int i915_interrupt_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i, pipe; ret = mutex_lock_interruptible(&dev->struct_mutex); @@ -638,7 +638,47 @@ static int i915_interrupt_info(struct seq_file *m, void *data) return ret; intel_runtime_pm_get(dev_priv); - if (INTEL_INFO(dev)->gen >= 8) { + if (IS_CHERRYVIEW(dev)) { + int i; + seq_printf(m, "Master Interrupt Control:\t%08x\n", + I915_READ(GEN8_MASTER_IRQ)); + + seq_printf(m, "Display IER:\t%08x\n", + I915_READ(VLV_IER)); + seq_printf(m, "Display IIR:\t%08x\n", + I915_READ(VLV_IIR)); + seq_printf(m, "Display IIR_RW:\t%08x\n", + I915_READ(VLV_IIR_RW)); + seq_printf(m, "Display IMR:\t%08x\n", + I915_READ(VLV_IMR)); + for_each_pipe(pipe) + seq_printf(m, "Pipe %c stat:\t%08x\n", + pipe_name(pipe), + I915_READ(PIPESTAT(pipe))); + + seq_printf(m, "Port hotplug:\t%08x\n", + I915_READ(PORT_HOTPLUG_EN)); + seq_printf(m, "DPFLIPSTAT:\t%08x\n", + I915_READ(VLV_DPFLIPSTAT)); + seq_printf(m, "DPINVGTT:\t%08x\n", + I915_READ(DPINVGTT)); + + for (i = 0; i < 4; i++) { + seq_printf(m, "GT Interrupt IMR %d:\t%08x\n", + i, I915_READ(GEN8_GT_IMR(i))); + seq_printf(m, "GT Interrupt IIR %d:\t%08x\n", + i, I915_READ(GEN8_GT_IIR(i))); + seq_printf(m, "GT Interrupt IER %d:\t%08x\n", + i, I915_READ(GEN8_GT_IER(i))); + } + + seq_printf(m, "PCU interrupt mask:\t%08x\n", + I915_READ(GEN8_PCU_IMR)); + seq_printf(m, "PCU interrupt identity:\t%08x\n", + I915_READ(GEN8_PCU_IIR)); + seq_printf(m, "PCU interrupt enable:\t%08x\n", + I915_READ(GEN8_PCU_IER)); + } else if (INTEL_INFO(dev)->gen >= 8) { seq_printf(m, "Master Interrupt Control:\t%08x\n", I915_READ(GEN8_MASTER_IRQ)); @@ -768,7 +808,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data) static int i915_gem_fence_regs_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int i, ret; @@ -797,10 +837,10 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data) static int i915_hws_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; const u32 *hws; int i; @@ -945,7 +985,7 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_next_seqno_fops, static int i915_rstdby_delays(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u16 crstanddelay; @@ -966,9 +1006,9 @@ 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_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret = 0; @@ -991,6 +1031,7 @@ 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 +1052,10 @@ 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 +1072,23 @@ 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 & @@ -1094,7 +1148,7 @@ out: static int i915_delayfreq_table(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 delayfreq; @@ -1125,7 +1179,7 @@ static inline int MAP_TO_MV(int map) static int i915_inttoext_table(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 inttoext; @@ -1149,7 +1203,7 @@ static int i915_inttoext_table(struct seq_file *m, void *unused) static int ironlake_drpc_info(struct seq_file *m) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 rgvmodectl, rstdbyctl; @@ -1219,15 +1273,19 @@ static int ironlake_drpc_info(struct seq_file *m) static int vlv_drpc_info(struct seq_file *m) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 rpmodectl1, rcctl1; unsigned fw_rendercount = 0, fw_mediacount = 0; + intel_runtime_pm_get(dev_priv); + rpmodectl1 = I915_READ(GEN6_RP_CONTROL); rcctl1 = I915_READ(GEN6_RC_CONTROL); + intel_runtime_pm_put(dev_priv); + seq_printf(m, "Video Turbo Mode: %s\n", yesno(rpmodectl1 & GEN6_RP_MEDIA_TURBO)); seq_printf(m, "Turbo enabled: %s\n", @@ -1247,6 +1305,11 @@ static int vlv_drpc_info(struct seq_file *m) (I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down"); + seq_printf(m, "Render RC6 residency since boot: %u\n", + I915_READ(VLV_GT_RENDER_RC6)); + seq_printf(m, "Media RC6 residency since boot: %u\n", + I915_READ(VLV_GT_MEDIA_RC6)); + spin_lock_irq(&dev_priv->uncore.lock); fw_rendercount = dev_priv->uncore.fw_rendercount; fw_mediacount = dev_priv->uncore.fw_mediacount; @@ -1263,7 +1326,7 @@ static int vlv_drpc_info(struct seq_file *m) static int gen6_drpc_info(struct seq_file *m) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 rpmodectl1, gt_core_status, rcctl1, rc6vids = 0; @@ -1362,7 +1425,7 @@ static int gen6_drpc_info(struct seq_file *m) static int i915_drpc_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; if (IS_VALLEYVIEW(dev)) @@ -1375,7 +1438,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused) static int i915_fbc_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1437,7 +1500,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused) static int i915_ips_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1460,7 +1523,7 @@ static int i915_ips_status(struct seq_file *m, void *unused) static int i915_sr_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; bool sr_enabled = false; @@ -1486,7 +1549,7 @@ static int i915_sr_status(struct seq_file *m, void *unused) static int i915_emon_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned long temp, chipset, gfx; @@ -1514,7 +1577,7 @@ static int i915_emon_status(struct seq_file *m, void *unused) static int i915_ring_freq_table(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret = 0; @@ -1557,7 +1620,7 @@ out: static int i915_gfxec(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret; @@ -1577,7 +1640,7 @@ static int i915_gfxec(struct seq_file *m, void *unused) static int i915_opregion(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_opregion *opregion = &dev_priv->opregion; @@ -1605,7 +1668,7 @@ out: static int i915_gem_framebuffer_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct intel_fbdev *ifbdev = NULL; struct intel_framebuffer *fb; @@ -1651,11 +1714,11 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) static int i915_context_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; - struct i915_hw_context *ctx; + struct intel_engine_cs *ring; + struct intel_context *ctx; int ret, i; ret = mutex_lock_interruptible(&dev->mode_config.mutex); @@ -1675,6 +1738,9 @@ static int i915_context_status(struct seq_file *m, void *unused) } list_for_each_entry(ctx, &dev_priv->context_list, link) { + if (ctx->obj == NULL) + continue; + seq_puts(m, "HW context "); describe_ctx(m, ctx); for_each_ring(ring, dev_priv, i) @@ -1692,7 +1758,7 @@ static int i915_context_status(struct seq_file *m, void *unused) static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned forcewake_count = 0, fw_rendercount = 0, fw_mediacount = 0; @@ -1740,7 +1806,7 @@ static const char *swizzle_string(unsigned swizzle) static int i915_swizzle_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret; @@ -1788,10 +1854,14 @@ static int i915_swizzle_info(struct seq_file *m, void *data) static int per_file_ctx(int id, void *ptr, void *data) { - struct i915_hw_context *ctx = ptr; + struct intel_context *ctx = ptr; struct seq_file *m = data; struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(ctx); + if (i915_gem_context_is_default(ctx)) + seq_puts(m, " default context:\n"); + else + seq_printf(m, " context %d:\n", ctx->id); ppgtt->debug_dump(ppgtt, m); return 0; @@ -1800,7 +1870,7 @@ static int per_file_ctx(int id, void *ptr, void *data) static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; int unused, i; @@ -1816,8 +1886,7 @@ 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); } } } @@ -1825,7 +1894,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; struct drm_file *file; int i; @@ -1852,12 +1921,9 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) list_for_each_entry_reverse(file, &dev->filelist, lhead) { struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_ppgtt *pvt_ppgtt; - pvt_ppgtt = ctx_to_ppgtt(file_priv->private_default_ctx); seq_printf(m, "proc: %s\n", get_pid_task(file->pid, PIDTYPE_PID)->comm); - seq_puts(m, " default context:\n"); idr_for_each(&file_priv->context_idr, per_file_ctx, m); } seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); @@ -1865,7 +1931,7 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) static int i915_ppgtt_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1885,56 +1951,9 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) return 0; } -static int i915_dpio_info(struct seq_file *m, void *data) -{ - struct drm_info_node *node = (struct drm_info_node *) m->private; - struct drm_device *dev = node->minor->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - int ret; - - - if (!IS_VALLEYVIEW(dev)) { - seq_puts(m, "unsupported\n"); - return 0; - } - - ret = mutex_lock_interruptible(&dev_priv->dpio_lock); - if (ret) - return ret; - - seq_printf(m, "DPIO_CTL: 0x%08x\n", I915_READ(DPIO_CTL)); - - seq_printf(m, "DPIO PLL DW3 CH0 : 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(0))); - seq_printf(m, "DPIO PLL DW3 CH1: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(1))); - - seq_printf(m, "DPIO PLL DW5 CH0: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(0))); - seq_printf(m, "DPIO PLL DW5 CH1: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(1))); - - seq_printf(m, "DPIO PLL DW7 CH0: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(0))); - seq_printf(m, "DPIO PLL DW7 CH1: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(1))); - - seq_printf(m, "DPIO PLL DW10 CH0: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(0))); - seq_printf(m, "DPIO PLL DW10 CH1: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(1))); - - seq_printf(m, "DPIO_FASTCLK_DISABLE: 0x%08x\n", - vlv_dpio_read(dev_priv, PIPE_A, VLV_CMN_DW0)); - - mutex_unlock(&dev_priv->dpio_lock); - - return 0; -} - static int i915_llc(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2040,11 +2059,11 @@ static int i915_energy_uJ(struct seq_file *m, void *data) static int i915_pc8_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; 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; } @@ -2115,7 +2134,7 @@ static const char *power_domain_str(enum intel_display_power_domain domain) static int i915_power_domain_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains = &dev_priv->power_domains; @@ -2170,7 +2189,7 @@ static void intel_encoder_info(struct seq_file *m, struct intel_crtc *intel_crtc, struct intel_encoder *intel_encoder) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_crtc *crtc = &intel_crtc->base; struct intel_connector *intel_connector; @@ -2178,12 +2197,12 @@ static void intel_encoder_info(struct seq_file *m, encoder = &intel_encoder->base; seq_printf(m, "\tencoder %d: type: %s, connectors:\n", - encoder->base.id, drm_get_encoder_name(encoder)); + encoder->base.id, encoder->name); for_each_connector_on_encoder(dev, encoder, intel_connector) { struct drm_connector *connector = &intel_connector->base; seq_printf(m, "\t\tconnector %d: type: %s, status: %s", connector->base.id, - drm_get_connector_name(connector), + connector->name, drm_get_connector_status_name(connector->status)); if (connector->status == connector_status_connected) { struct drm_display_mode *mode = &crtc->mode; @@ -2197,7 +2216,7 @@ static void intel_encoder_info(struct seq_file *m, static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_crtc *crtc = &intel_crtc->base; struct intel_encoder *intel_encoder; @@ -2254,7 +2273,7 @@ static void intel_connector_info(struct seq_file *m, struct drm_display_mode *mode; seq_printf(m, "connector %d: type %s, status: %s\n", - connector->base.id, drm_get_connector_name(connector), + connector->base.id, connector->name, drm_get_connector_status_name(connector->status)); if (connector->status == connector_status_connected) { seq_printf(m, "\tname: %s\n", connector->display_info.name); @@ -2286,10 +2305,8 @@ static bool cursor_active(struct drm_device *dev, int pipe) if (IS_845G(dev) || IS_I865G(dev)) state = I915_READ(_CURACNTR) & CURSOR_ENABLE; - else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) - state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; else - state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE; + state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; return state; } @@ -2299,10 +2316,7 @@ static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y) struct drm_i915_private *dev_priv = dev->dev_private; u32 pos; - if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) - pos = I915_READ(CURPOS_IVB(pipe)); - else - pos = I915_READ(CURPOS(pipe)); + pos = I915_READ(CURPOS(pipe)); *x = (pos >> CURSOR_X_SHIFT) & CURSOR_POS_MASK; if (pos & (CURSOR_POS_SIGN << CURSOR_X_SHIFT)) @@ -2317,7 +2331,7 @@ static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y) static int i915_display_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc; @@ -2327,7 +2341,7 @@ static int i915_display_info(struct seq_file *m, void *unused) drm_modeset_lock_all(dev); seq_printf(m, "CRTC info\n"); seq_printf(m, "---------\n"); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { bool active; int x, y; @@ -2339,10 +2353,14 @@ static int i915_display_info(struct seq_file *m, void *unused) active = cursor_position(dev, crtc->pipe, &x, &y); seq_printf(m, "\tcursor visible? %s, position (%d, %d), addr 0x%08x, active? %s\n", - yesno(crtc->cursor_visible), + yesno(crtc->cursor_base), x, y, crtc->cursor_addr, yesno(active)); } + + seq_printf(m, "\tunderrun reporting: cpu=%s pch=%s \n", + yesno(!crtc->cpu_fifo_underrun_disabled), + yesno(!crtc->pch_fifo_underrun_disabled)); } seq_printf(m, "\n"); @@ -2595,7 +2613,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_device *dev, enum pipe pipe, *source = INTEL_PIPE_CRC_SOURCE_PIPE; - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock_all(dev); list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) { if (!encoder->base.crtc) @@ -2631,7 +2649,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_device *dev, enum pipe pipe, break; } } - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock_all(dev); return ret; } @@ -3106,7 +3124,7 @@ static const struct file_operations i915_display_crc_ctl_fops = { static void wm_latency_show(struct seq_file *m, const uint16_t wm[5]) { struct drm_device *dev = m->private; - int num_levels = IS_HASWELL(dev) || IS_BROADWELL(dev) ? 5 : 4; + int num_levels = ilk_wm_max_level(dev) + 1; int level; drm_modeset_lock_all(dev); @@ -3189,7 +3207,7 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf, struct seq_file *m = file->private_data; struct drm_device *dev = m->private; uint16_t new[5] = { 0 }; - int num_levels = IS_HASWELL(dev) || IS_BROADWELL(dev) ? 5 : 4; + int num_levels = ilk_wm_max_level(dev) + 1; int level; int ret; char tmp[32]; @@ -3286,9 +3304,15 @@ static int i915_wedged_set(void *data, u64 val) { struct drm_device *dev = data; + struct drm_i915_private *dev_priv = dev->dev_private; + + intel_runtime_pm_get(dev_priv); i915_handle_error(dev, val, "Manually setting wedged to %llu", val); + + intel_runtime_pm_put(dev_priv); + return 0; } @@ -3774,7 +3798,7 @@ 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}, @@ -3790,7 +3814,6 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0}, {"i915_swizzle_info", i915_swizzle_info, 0}, {"i915_ppgtt_info", i915_ppgtt_info, 0}, - {"i915_dpio", i915_dpio_info, 0}, {"i915_llc", i915_llc, 0}, {"i915_edp_psr_status", i915_edp_psr_status, 0}, {"i915_sink_crc_eDP1", i915_sink_crc, 0}, diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index eedb023af27d..4c22a5b7f4c5 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -44,6 +44,7 @@ #include <acpi/video.h> #include <linux/pm.h> #include <linux/pm_runtime.h> +#include <linux/oom.h> #define LP_RING(d) (&((struct drm_i915_private *)(d))->ring[RCS]) @@ -63,7 +64,7 @@ * has access to the ring. */ #define RING_LOCK_TEST_WITH_RETURN(dev, file) do { \ - if (LP_RING(dev->dev_private)->obj == NULL) \ + if (LP_RING(dev->dev_private)->buffer->obj == NULL) \ LOCK_TEST_WITH_RETURN(dev, file); \ } while (0) @@ -119,7 +120,7 @@ static void i915_write_hws_pga(struct drm_device *dev) static void i915_free_hws(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); if (dev_priv->status_page_dmah) { drm_pci_free(dev, dev_priv->status_page_dmah); @@ -139,7 +140,8 @@ void i915_kernel_lost_context(struct drm_device * dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_master_private *master_priv; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); + struct intel_ringbuffer *ringbuf = ring->buffer; /* * We should never lose context on the ring with modesetting @@ -148,17 +150,17 @@ void i915_kernel_lost_context(struct drm_device * dev) if (drm_core_check_feature(dev, DRIVER_MODESET)) return; - ring->head = I915_READ_HEAD(ring) & HEAD_ADDR; - ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR; - ring->space = ring->head - (ring->tail + I915_RING_FREE_SPACE); - if (ring->space < 0) - ring->space += ring->size; + ringbuf->head = I915_READ_HEAD(ring) & HEAD_ADDR; + ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR; + ringbuf->space = ringbuf->head - (ringbuf->tail + I915_RING_FREE_SPACE); + if (ringbuf->space < 0) + ringbuf->space += ringbuf->size; if (!dev->primary->master) return; master_priv = dev->primary->master->driver_priv; - if (ring->head == ring->tail && master_priv->sarea_priv) + if (ringbuf->head == ringbuf->tail && master_priv->sarea_priv) master_priv->sarea_priv->perf_boxes |= I915_BOX_RING_EMPTY; } @@ -201,7 +203,7 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init) } if (init->ring_size != 0) { - if (LP_RING(dev_priv)->obj != NULL) { + if (LP_RING(dev_priv)->buffer->obj != NULL) { i915_dma_cleanup(dev); DRM_ERROR("Client tried to initialize ringbuffer in " "GEM mode\n"); @@ -234,11 +236,11 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init) static int i915_dma_resume(struct drm_device * dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); DRM_DEBUG_DRIVER("%s\n", __func__); - if (ring->virtual_start == NULL) { + if (ring->buffer->virtual_start == NULL) { DRM_ERROR("can not ioremap virtual address for" " ring buffer\n"); return -ENOMEM; @@ -360,7 +362,7 @@ static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords) struct drm_i915_private *dev_priv = dev->dev_private; int i, ret; - if ((dwords+1) * sizeof(int) >= LP_RING(dev_priv)->size - 8) + if ((dwords+1) * sizeof(int) >= LP_RING(dev_priv)->buffer->size - 8) return -EINVAL; for (i = 0; i < dwords;) { @@ -782,7 +784,7 @@ static int i915_wait_irq(struct drm_device * dev, int irq_nr) struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv; int ret = 0; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); DRM_DEBUG_DRIVER("irq_nr=%d breadcrumb=%d\n", irq_nr, READ_BREADCRUMB(dev_priv)); @@ -823,7 +825,7 @@ static int i915_irq_emit(struct drm_device *dev, void *data, if (drm_core_check_feature(dev, DRIVER_MODESET)) return -ENODEV; - if (!dev_priv || !LP_RING(dev_priv)->virtual_start) { + if (!dev_priv || !LP_RING(dev_priv)->buffer->virtual_start) { DRM_ERROR("called with no initialization\n"); return -EINVAL; } @@ -1017,6 +1019,9 @@ 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; @@ -1070,7 +1075,7 @@ static int i915_set_status_page(struct drm_device *dev, void *data, { struct drm_i915_private *dev_priv = dev->dev_private; drm_i915_hws_addr_t *hws = data; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; if (drm_core_check_feature(dev, DRIVER_MODESET)) return -ENODEV; @@ -1277,12 +1282,13 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_ static bool i915_switcheroo_can_switch(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); - bool can_switch; - spin_lock(&dev->count_lock); - can_switch = (dev->open_count == 0); - spin_unlock(&dev->count_lock); - return can_switch; + /* + * FIXME: open_count is protected by drm_global_mutex but that would lead to + * locking inversion with the driver load path. And the access here is + * completely racy anyway. So don't bother with locking for now. + */ + return dev->open_count == 0; } static const struct vga_switcheroo_client_ops i915_switcheroo_ops = { @@ -1326,7 +1332,7 @@ static int i915_load_modeset_init(struct drm_device *dev) intel_power_domains_init_hw(dev_priv); - ret = drm_irq_install(dev); + ret = drm_irq_install(dev, dev->pdev->irq); if (ret) goto cleanup_gem_stolen; @@ -1336,7 +1342,7 @@ static int i915_load_modeset_init(struct drm_device *dev) ret = i915_gem_init(dev); if (ret) - goto cleanup_power; + goto cleanup_irq; INIT_WORK(&dev_priv->console_resume_work, intel_console_resume); @@ -1345,10 +1351,8 @@ static int i915_load_modeset_init(struct drm_device *dev) /* Always safe in the mode setting case. */ /* FIXME: do pre/post-mode set stuff in core KMS code */ dev->vblank_disable_allowed = true; - if (INTEL_INFO(dev)->num_pipes == 0) { - intel_display_power_put(dev_priv, POWER_DOMAIN_VGA); + if (INTEL_INFO(dev)->num_pipes == 0) return 0; - } ret = intel_fbdev_init(dev); if (ret) @@ -1383,8 +1387,7 @@ cleanup_gem: mutex_unlock(&dev->struct_mutex); WARN_ON(dev_priv->mm.aliasing_ppgtt); drm_mm_takedown(&dev_priv->gtt.base.mm); -cleanup_power: - intel_display_power_put(dev_priv, POWER_DOMAIN_VGA); +cleanup_irq: drm_irq_uninstall(dev); cleanup_gem_stolen: i915_gem_cleanup_stolen(dev); @@ -1739,8 +1742,8 @@ out_power_well: intel_power_domains_remove(dev_priv); drm_vblank_cleanup(dev); out_gem_unload: - if (dev_priv->mm.inactive_shrinker.scan_objects) - unregister_shrinker(&dev_priv->mm.inactive_shrinker); + WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier)); + unregister_shrinker(&dev_priv->mm.shrinker); if (dev->pdev->msi_enabled) pci_disable_msi(dev->pdev); @@ -1791,8 +1794,8 @@ int i915_driver_unload(struct drm_device *dev) i915_teardown_sysfs(dev); - if (dev_priv->mm.inactive_shrinker.scan_objects) - unregister_shrinker(&dev_priv->mm.inactive_shrinker); + WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier)); + unregister_shrinker(&dev_priv->mm.shrinker); io_mapping_free(dev_priv->gtt.mappable); arch_phys_wc_del(dev_priv->gtt.mtrr); @@ -1864,7 +1867,7 @@ int i915_driver_unload(struct drm_device *dev) kmem_cache_destroy(dev_priv->slab); pci_dev_put(dev_priv->bridge_dev); - kfree(dev->dev_private); + kfree(dev_priv); return 0; } @@ -1925,6 +1928,8 @@ void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; + if (file_priv && file_priv->bsd_ring) + file_priv->bsd_ring = NULL; kfree(file_priv); } @@ -1978,9 +1983,10 @@ const struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), }; -int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls); +int i915_max_ioctl = ARRAY_SIZE(i915_ioctls); /* * This is really ugly: Because old userspace abused the linux agp interface to diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 82f4d1f47d3b..651e65e051c0 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -36,6 +36,7 @@ #include <linux/console.h> #include <linux/module.h> +#include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> static struct drm_driver driver; @@ -49,12 +50,30 @@ static struct drm_driver driver; .dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET }, \ .palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET } +#define GEN_CHV_PIPEOFFSETS \ + .pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \ + CHV_PIPE_C_OFFSET }, \ + .trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \ + CHV_TRANSCODER_C_OFFSET, }, \ + .dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET, \ + CHV_DPLL_C_OFFSET }, \ + .dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET, \ + CHV_DPLL_C_MD_OFFSET }, \ + .palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \ + CHV_PALETTE_C_OFFSET } + +#define CURSOR_OFFSETS \ + .cursor_offsets = { CURSOR_A_OFFSET, CURSOR_B_OFFSET, CHV_CURSOR_C_OFFSET } + +#define IVB_CURSOR_OFFSETS \ + .cursor_offsets = { CURSOR_A_OFFSET, IVB_CURSOR_B_OFFSET, IVB_CURSOR_C_OFFSET } static const struct intel_device_info intel_i830_info = { .gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2, .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_845g_info = { @@ -62,6 +81,7 @@ static const struct intel_device_info intel_845g_info = { .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i85x_info = { @@ -71,6 +91,7 @@ static const struct intel_device_info intel_i85x_info = { .has_fbc = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i865g_info = { @@ -78,6 +99,7 @@ static const struct intel_device_info intel_i865g_info = { .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i915g_info = { @@ -85,6 +107,7 @@ static const struct intel_device_info intel_i915g_info = { .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i915gm_info = { .gen = 3, .is_mobile = 1, .num_pipes = 2, @@ -94,12 +117,14 @@ static const struct intel_device_info intel_i915gm_info = { .has_fbc = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i945g_info = { .gen = 3, .has_hotplug = 1, .cursor_needs_physical = 1, .num_pipes = 2, .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i945gm_info = { .gen = 3, .is_i945gm = 1, .is_mobile = 1, .num_pipes = 2, @@ -109,6 +134,7 @@ static const struct intel_device_info intel_i945gm_info = { .has_fbc = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i965g_info = { @@ -117,6 +143,7 @@ static const struct intel_device_info intel_i965g_info = { .has_overlay = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i965gm_info = { @@ -126,6 +153,7 @@ static const struct intel_device_info intel_i965gm_info = { .supports_tv = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_g33_info = { @@ -134,6 +162,7 @@ static const struct intel_device_info intel_g33_info = { .has_overlay = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_g45_info = { @@ -141,6 +170,7 @@ static const struct intel_device_info intel_g45_info = { .has_pipe_cxsr = 1, .has_hotplug = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_gm45_info = { @@ -150,6 +180,7 @@ static const struct intel_device_info intel_gm45_info = { .supports_tv = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_pineview_info = { @@ -157,6 +188,7 @@ static const struct intel_device_info intel_pineview_info = { .need_gfx_hws = 1, .has_hotplug = 1, .has_overlay = 1, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_ironlake_d_info = { @@ -164,6 +196,7 @@ static const struct intel_device_info intel_ironlake_d_info = { .need_gfx_hws = 1, .has_hotplug = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_ironlake_m_info = { @@ -172,6 +205,7 @@ static const struct intel_device_info intel_ironlake_m_info = { .has_fbc = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_sandybridge_d_info = { @@ -181,6 +215,7 @@ static const struct intel_device_info intel_sandybridge_d_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING, .has_llc = 1, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_sandybridge_m_info = { @@ -190,6 +225,7 @@ static const struct intel_device_info intel_sandybridge_m_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING, .has_llc = 1, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; #define GEN7_FEATURES \ @@ -203,6 +239,7 @@ static const struct intel_device_info intel_ivybridge_d_info = { GEN7_FEATURES, .is_ivybridge = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_ivybridge_m_info = { @@ -210,6 +247,7 @@ static const struct intel_device_info intel_ivybridge_m_info = { .is_ivybridge = 1, .is_mobile = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_ivybridge_q_info = { @@ -217,6 +255,7 @@ static const struct intel_device_info intel_ivybridge_q_info = { .is_ivybridge = 1, .num_pipes = 0, /* legal, last one wins */ GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_valleyview_m_info = { @@ -228,6 +267,7 @@ static const struct intel_device_info intel_valleyview_m_info = { .has_fbc = 0, /* legal, last one wins */ .has_llc = 0, /* legal, last one wins */ GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_valleyview_d_info = { @@ -238,6 +278,7 @@ static const struct intel_device_info intel_valleyview_d_info = { .has_fbc = 0, /* legal, last one wins */ .has_llc = 0, /* legal, last one wins */ GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_haswell_d_info = { @@ -247,6 +288,7 @@ static const struct intel_device_info intel_haswell_d_info = { .has_fpga_dbg = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_haswell_m_info = { @@ -257,6 +299,7 @@ static const struct intel_device_info intel_haswell_m_info = { .has_fpga_dbg = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_broadwell_d_info = { @@ -267,6 +310,7 @@ static const struct intel_device_info intel_broadwell_d_info = { .has_ddi = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_broadwell_m_info = { @@ -277,6 +321,40 @@ static const struct intel_device_info intel_broadwell_m_info = { .has_ddi = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, +}; + +static const struct intel_device_info intel_broadwell_gt3d_info = { + .gen = 8, .num_pipes = 3, + .need_gfx_hws = 1, .has_hotplug = 1, + .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, + .has_llc = 1, + .has_ddi = 1, + .has_fbc = 1, + GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, +}; + +static const struct intel_device_info intel_broadwell_gt3m_info = { + .gen = 8, .is_mobile = 1, .num_pipes = 3, + .need_gfx_hws = 1, .has_hotplug = 1, + .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, + .has_llc = 1, + .has_ddi = 1, + .has_fbc = 1, + GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, +}; + +static const struct intel_device_info intel_cherryview_info = { + .is_preliminary = 1, + .gen = 8, .num_pipes = 3, + .need_gfx_hws = 1, .has_hotplug = 1, + .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, + .is_valleyview = 1, + .display_mmio_offset = VLV_DISPLAY_BASE, + GEN_CHV_PIPEOFFSETS, + CURSOR_OFFSETS, }; /* @@ -311,8 +389,11 @@ static const struct intel_device_info intel_broadwell_m_info = { INTEL_HSW_M_IDS(&intel_haswell_m_info), \ INTEL_VLV_M_IDS(&intel_valleyview_m_info), \ INTEL_VLV_D_IDS(&intel_valleyview_d_info), \ - INTEL_BDW_M_IDS(&intel_broadwell_m_info), \ - INTEL_BDW_D_IDS(&intel_broadwell_d_info) + INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info), \ + INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info), \ + INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info), \ + INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info), \ + INTEL_CHV_IDS(&intel_cherryview_info) static const struct pci_device_id pciidlist[] = { /* aka */ INTEL_PCI_IDS, @@ -445,18 +526,20 @@ static int i915_drm_freeze(struct drm_device *dev) return error; } - cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work); - drm_irq_uninstall(dev); dev_priv->enable_hotplug_processing = false; + + intel_disable_gt_powersave(dev); + /* * Disable CRTCs directly since we want to preserve sw state * for _thaw. */ - mutex_lock(&dev->mode_config.mutex); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + drm_modeset_lock_all(dev); + for_each_crtc(dev, crtc) { dev_priv->display.crtc_disable(crtc); - mutex_unlock(&dev->mode_config.mutex); + } + drm_modeset_unlock_all(dev); intel_modeset_suspend_hw(dev); } @@ -519,24 +602,6 @@ void intel_console_resume(struct work_struct *work) console_unlock(); } -static void intel_resume_hotplug(struct drm_device *dev) -{ - struct drm_mode_config *mode_config = &dev->mode_config; - struct intel_encoder *encoder; - - mutex_lock(&mode_config->mutex); - DRM_DEBUG_KMS("running encoder hotplug functions\n"); - - list_for_each_entry(encoder, &mode_config->encoder_list, base.head) - if (encoder->hot_plug) - encoder->hot_plug(encoder); - - mutex_unlock(&mode_config->mutex); - - /* Just fire off a uevent and let userspace tell us what to do */ - drm_helper_hpd_irq_event(dev); -} - static int i915_drm_thaw_early(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -551,7 +616,6 @@ static int i915_drm_thaw_early(struct drm_device *dev) static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) { struct drm_i915_private *dev_priv = dev->dev_private; - int error = 0; if (drm_core_check_feature(dev, DRIVER_MODESET) && restore_gtt_mappings) { @@ -569,12 +633,14 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) drm_mode_config_reset(dev); mutex_lock(&dev->struct_mutex); - - error = i915_gem_init_hw(dev); + if (i915_gem_init_hw(dev)) { + DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n"); + atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter); + } mutex_unlock(&dev->struct_mutex); /* We need working interrupts for modeset enabling ... */ - drm_irq_install(dev); + drm_irq_install(dev, dev->pdev->irq); intel_modeset_init_hw(dev); @@ -591,7 +657,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) intel_hpd_init(dev); dev_priv->enable_hotplug_processing = true; /* Config may have changed between suspend and resume */ - intel_resume_hotplug(dev); + drm_helper_hpd_irq_event(dev); } intel_opregion_init(dev); @@ -613,7 +679,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) mutex_unlock(&dev_priv->modeset_restore_lock); intel_runtime_pm_put(dev_priv); - return error; + return 0; } static int i915_drm_thaw(struct drm_device *dev) @@ -746,18 +812,20 @@ int i915_reset(struct drm_device *dev) return ret; } - drm_irq_uninstall(dev); - drm_irq_install(dev); + /* + * FIXME: This races pretty badly against concurrent holders of + * ring interrupts. This is possible since we've started to drop + * dev->struct_mutex in select places when waiting for the gpu. + */ - /* rps/rc6 re-init is necessary to restore state lost after the - * reset and the re-install of drm irq. Skip for ironlake per + /* + * rps/rc6 re-init is necessary to restore state lost after the + * reset and the re-install of gt irqs. Skip for ironlake per * previous concerns that it doesn't respond well to some forms - * of re-init after reset. */ - if (INTEL_INFO(dev)->gen > 5) { - mutex_lock(&dev->struct_mutex); - intel_enable_gt_powersave(dev); - mutex_unlock(&dev->struct_mutex); - } + * of re-init after reset. + */ + if (INTEL_INFO(dev)->gen > 5) + intel_reset_gt_powersave(dev); intel_hpd_init(dev); } else { @@ -891,21 +959,453 @@ static int i915_pm_poweroff(struct device *dev) return i915_drm_freeze(drm_dev); } -static int i915_runtime_suspend(struct device *device) +static int hsw_runtime_suspend(struct drm_i915_private *dev_priv) +{ + hsw_enable_pc8(dev_priv); + + return 0; +} + +static int snb_runtime_resume(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + + intel_init_pch_refclk(dev); + + return 0; +} + +static int hsw_runtime_resume(struct drm_i915_private *dev_priv) +{ + hsw_disable_pc8(dev_priv); + + return 0; +} + +/* + * Save all Gunit registers that may be lost after a D3 and a subsequent + * S0i[R123] transition. The list of registers needing a save/restore is + * defined in the VLV2_S0IXRegs document. This documents marks all Gunit + * registers in the following way: + * - Driver: saved/restored by the driver + * - Punit : saved/restored by the Punit firmware + * - No, w/o marking: no need to save/restore, since the register is R/O or + * used internally by the HW in a way that doesn't depend + * keeping the content across a suspend/resume. + * - Debug : used for debugging + * + * We save/restore all registers marked with 'Driver', with the following + * exceptions: + * - Registers out of use, including also registers marked with 'Debug'. + * These have no effect on the driver's operation, so we don't save/restore + * them to reduce the overhead. + * - Registers that are fully setup by an initialization function called from + * the resume path. For example many clock gating and RPS/RC6 registers. + * - Registers that provide the right functionality with their reset defaults. + * + * TODO: Except for registers that based on the above 3 criteria can be safely + * ignored, we save/restore all others, practically treating the HW context as + * a black-box for the driver. Further investigation is needed to reduce the + * saved/restored registers even further, by following the same 3 criteria. + */ +static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) +{ + struct vlv_s0ix_state *s = &dev_priv->vlv_s0ix_state; + int i; + + /* GAM 0x4000-0x4770 */ + s->wr_watermark = I915_READ(GEN7_WR_WATERMARK); + s->gfx_prio_ctrl = I915_READ(GEN7_GFX_PRIO_CTRL); + s->arb_mode = I915_READ(ARB_MODE); + s->gfx_pend_tlb0 = I915_READ(GEN7_GFX_PEND_TLB0); + s->gfx_pend_tlb1 = I915_READ(GEN7_GFX_PEND_TLB1); + + for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++) + s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4); + + s->media_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); + s->gfx_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); + + s->render_hwsp = I915_READ(RENDER_HWS_PGA_GEN7); + s->ecochk = I915_READ(GAM_ECOCHK); + s->bsd_hwsp = I915_READ(BSD_HWS_PGA_GEN7); + s->blt_hwsp = I915_READ(BLT_HWS_PGA_GEN7); + + s->tlb_rd_addr = I915_READ(GEN7_TLB_RD_ADDR); + + /* MBC 0x9024-0x91D0, 0x8500 */ + s->g3dctl = I915_READ(VLV_G3DCTL); + s->gsckgctl = I915_READ(VLV_GSCKGCTL); + s->mbctl = I915_READ(GEN6_MBCTL); + + /* GCP 0x9400-0x9424, 0x8100-0x810C */ + s->ucgctl1 = I915_READ(GEN6_UCGCTL1); + s->ucgctl3 = I915_READ(GEN6_UCGCTL3); + s->rcgctl1 = I915_READ(GEN6_RCGCTL1); + s->rcgctl2 = I915_READ(GEN6_RCGCTL2); + s->rstctl = I915_READ(GEN6_RSTCTL); + s->misccpctl = I915_READ(GEN7_MISCCPCTL); + + /* GPM 0xA000-0xAA84, 0x8000-0x80FC */ + s->gfxpause = I915_READ(GEN6_GFXPAUSE); + s->rpdeuhwtc = I915_READ(GEN6_RPDEUHWTC); + s->rpdeuc = I915_READ(GEN6_RPDEUC); + s->ecobus = I915_READ(ECOBUS); + s->pwrdwnupctl = I915_READ(VLV_PWRDWNUPCTL); + s->rp_down_timeout = I915_READ(GEN6_RP_DOWN_TIMEOUT); + s->rp_deucsw = I915_READ(GEN6_RPDEUCSW); + s->rcubmabdtmr = I915_READ(GEN6_RCUBMABDTMR); + s->rcedata = I915_READ(VLV_RCEDATA); + s->spare2gh = I915_READ(VLV_SPAREG2H); + + /* Display CZ domain, 0x4400C-0x4402C, 0x4F000-0x4F11F */ + s->gt_imr = I915_READ(GTIMR); + s->gt_ier = I915_READ(GTIER); + s->pm_imr = I915_READ(GEN6_PMIMR); + s->pm_ier = I915_READ(GEN6_PMIER); + + for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++) + s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH_BASE + i * 4); + + /* GT SA CZ domain, 0x100000-0x138124 */ + s->tilectl = I915_READ(TILECTL); + s->gt_fifoctl = I915_READ(GTFIFOCTL); + s->gtlc_wake_ctrl = I915_READ(VLV_GTLC_WAKE_CTRL); + s->gtlc_survive = I915_READ(VLV_GTLC_SURVIVABILITY_REG); + s->pmwgicz = I915_READ(VLV_PMWGICZ); + + /* Gunit-Display CZ domain, 0x182028-0x1821CF */ + s->gu_ctl0 = I915_READ(VLV_GU_CTL0); + s->gu_ctl1 = I915_READ(VLV_GU_CTL1); + s->clock_gate_dis2 = I915_READ(VLV_GUNIT_CLOCK_GATE2); + + /* + * Not saving any of: + * DFT, 0x9800-0x9EC0 + * SARB, 0xB000-0xB1FC + * GAC, 0x5208-0x524C, 0x14000-0x14C000 + * PCI CFG + */ +} + +static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) +{ + struct vlv_s0ix_state *s = &dev_priv->vlv_s0ix_state; + u32 val; + int i; + + /* GAM 0x4000-0x4770 */ + I915_WRITE(GEN7_WR_WATERMARK, s->wr_watermark); + I915_WRITE(GEN7_GFX_PRIO_CTRL, s->gfx_prio_ctrl); + I915_WRITE(ARB_MODE, s->arb_mode | (0xffff << 16)); + I915_WRITE(GEN7_GFX_PEND_TLB0, s->gfx_pend_tlb0); + I915_WRITE(GEN7_GFX_PEND_TLB1, s->gfx_pend_tlb1); + + for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++) + I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]); + + I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count); + I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->gfx_max_req_count); + + I915_WRITE(RENDER_HWS_PGA_GEN7, s->render_hwsp); + I915_WRITE(GAM_ECOCHK, s->ecochk); + I915_WRITE(BSD_HWS_PGA_GEN7, s->bsd_hwsp); + I915_WRITE(BLT_HWS_PGA_GEN7, s->blt_hwsp); + + I915_WRITE(GEN7_TLB_RD_ADDR, s->tlb_rd_addr); + + /* MBC 0x9024-0x91D0, 0x8500 */ + I915_WRITE(VLV_G3DCTL, s->g3dctl); + I915_WRITE(VLV_GSCKGCTL, s->gsckgctl); + I915_WRITE(GEN6_MBCTL, s->mbctl); + + /* GCP 0x9400-0x9424, 0x8100-0x810C */ + I915_WRITE(GEN6_UCGCTL1, s->ucgctl1); + I915_WRITE(GEN6_UCGCTL3, s->ucgctl3); + I915_WRITE(GEN6_RCGCTL1, s->rcgctl1); + I915_WRITE(GEN6_RCGCTL2, s->rcgctl2); + I915_WRITE(GEN6_RSTCTL, s->rstctl); + I915_WRITE(GEN7_MISCCPCTL, s->misccpctl); + + /* GPM 0xA000-0xAA84, 0x8000-0x80FC */ + I915_WRITE(GEN6_GFXPAUSE, s->gfxpause); + I915_WRITE(GEN6_RPDEUHWTC, s->rpdeuhwtc); + I915_WRITE(GEN6_RPDEUC, s->rpdeuc); + I915_WRITE(ECOBUS, s->ecobus); + I915_WRITE(VLV_PWRDWNUPCTL, s->pwrdwnupctl); + I915_WRITE(GEN6_RP_DOWN_TIMEOUT,s->rp_down_timeout); + I915_WRITE(GEN6_RPDEUCSW, s->rp_deucsw); + I915_WRITE(GEN6_RCUBMABDTMR, s->rcubmabdtmr); + I915_WRITE(VLV_RCEDATA, s->rcedata); + I915_WRITE(VLV_SPAREG2H, s->spare2gh); + + /* Display CZ domain, 0x4400C-0x4402C, 0x4F000-0x4F11F */ + I915_WRITE(GTIMR, s->gt_imr); + I915_WRITE(GTIER, s->gt_ier); + I915_WRITE(GEN6_PMIMR, s->pm_imr); + I915_WRITE(GEN6_PMIER, s->pm_ier); + + for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++) + I915_WRITE(GEN7_GT_SCRATCH_BASE + i * 4, s->gt_scratch[i]); + + /* GT SA CZ domain, 0x100000-0x138124 */ + I915_WRITE(TILECTL, s->tilectl); + I915_WRITE(GTFIFOCTL, s->gt_fifoctl); + /* + * Preserve the GT allow wake and GFX force clock bit, they are not + * be restored, as they are used to control the s0ix suspend/resume + * sequence by the caller. + */ + val = I915_READ(VLV_GTLC_WAKE_CTRL); + val &= VLV_GTLC_ALLOWWAKEREQ; + val |= s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ; + I915_WRITE(VLV_GTLC_WAKE_CTRL, val); + + val = I915_READ(VLV_GTLC_SURVIVABILITY_REG); + val &= VLV_GFX_CLK_FORCE_ON_BIT; + val |= s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT; + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, val); + + I915_WRITE(VLV_PMWGICZ, s->pmwgicz); + + /* Gunit-Display CZ domain, 0x182028-0x1821CF */ + I915_WRITE(VLV_GU_CTL0, s->gu_ctl0); + I915_WRITE(VLV_GU_CTL1, s->gu_ctl1); + I915_WRITE(VLV_GUNIT_CLOCK_GATE2, s->clock_gate_dis2); +} + +int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on) +{ + u32 val; + int err; + + val = I915_READ(VLV_GTLC_SURVIVABILITY_REG); + WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on); + +#define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT) + /* Wait for a previous force-off to settle */ + if (force_on) { + err = wait_for(!COND, 20); + if (err) { + DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n", + I915_READ(VLV_GTLC_SURVIVABILITY_REG)); + return err; + } + } + + val = I915_READ(VLV_GTLC_SURVIVABILITY_REG); + val &= ~VLV_GFX_CLK_FORCE_ON_BIT; + if (force_on) + val |= VLV_GFX_CLK_FORCE_ON_BIT; + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, val); + + if (!force_on) + return 0; + + err = wait_for(COND, 20); + if (err) + DRM_ERROR("timeout waiting for GFX clock force-on (%08x)\n", + I915_READ(VLV_GTLC_SURVIVABILITY_REG)); + + return err; +#undef COND +} + +static int vlv_allow_gt_wake(struct drm_i915_private *dev_priv, bool allow) +{ + u32 val; + int err = 0; + + val = I915_READ(VLV_GTLC_WAKE_CTRL); + val &= ~VLV_GTLC_ALLOWWAKEREQ; + if (allow) + val |= VLV_GTLC_ALLOWWAKEREQ; + I915_WRITE(VLV_GTLC_WAKE_CTRL, val); + POSTING_READ(VLV_GTLC_WAKE_CTRL); + +#define COND (!!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEACK) == \ + allow) + err = wait_for(COND, 1); + if (err) + DRM_ERROR("timeout disabling GT waking\n"); + return err; +#undef COND +} + +static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, + bool wait_for_on) +{ + u32 mask; + u32 val; + int err; + + mask = VLV_GTLC_PW_MEDIA_STATUS_MASK | VLV_GTLC_PW_RENDER_STATUS_MASK; + val = wait_for_on ? mask : 0; +#define COND ((I915_READ(VLV_GTLC_PW_STATUS) & mask) == val) + if (COND) + return 0; + + DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n", + wait_for_on ? "on" : "off", + I915_READ(VLV_GTLC_PW_STATUS)); + + /* + * RC6 transitioning can be delayed up to 2 msec (see + * valleyview_enable_rps), use 3 msec for safety. + */ + err = wait_for(COND, 3); + if (err) + DRM_ERROR("timeout waiting for GT wells to go %s\n", + wait_for_on ? "on" : "off"); + + return err; +#undef COND +} + +static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv) +{ + if (!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEERR)) + return; + + DRM_ERROR("GT register access while GT waking disabled\n"); + I915_WRITE(VLV_GTLC_PW_STATUS, VLV_GTLC_ALLOWWAKEERR); +} + +static int vlv_runtime_suspend(struct drm_i915_private *dev_priv) +{ + u32 mask; + int err; + + /* + * Bspec defines the following GT well on flags as debug only, so + * don't treat them as hard failures. + */ + (void)vlv_wait_for_gt_wells(dev_priv, false); + + mask = VLV_GTLC_RENDER_CTX_EXISTS | VLV_GTLC_MEDIA_CTX_EXISTS; + WARN_ON((I915_READ(VLV_GTLC_WAKE_CTRL) & mask) != mask); + + vlv_check_no_gt_access(dev_priv); + + err = vlv_force_gfx_clock(dev_priv, true); + if (err) + goto err1; + + err = vlv_allow_gt_wake(dev_priv, false); + if (err) + goto err2; + vlv_save_gunit_s0ix_state(dev_priv); + + err = vlv_force_gfx_clock(dev_priv, false); + if (err) + goto err2; + + return 0; + +err2: + /* For safety always re-enable waking and disable gfx clock forcing */ + vlv_allow_gt_wake(dev_priv, true); +err1: + vlv_force_gfx_clock(dev_priv, false); + + return err; +} + +static int vlv_runtime_resume(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + int err; + int ret; + + /* + * If any of the steps fail just try to continue, that's the best we + * can do at this point. Return the first error code (which will also + * leave RPM permanently disabled). + */ + ret = vlv_force_gfx_clock(dev_priv, true); + + vlv_restore_gunit_s0ix_state(dev_priv); + + err = vlv_allow_gt_wake(dev_priv, true); + if (!ret) + ret = err; + + err = vlv_force_gfx_clock(dev_priv, false); + if (!ret) + ret = err; + + vlv_check_no_gt_access(dev_priv); + + intel_init_clock_gating(dev); + i915_gem_restore_fences(dev); + + return ret; +} + +static int intel_runtime_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct drm_device *dev = pci_get_drvdata(pdev); struct drm_i915_private *dev_priv = dev->dev_private; + int ret; + + if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev)))) + return -ENODEV; WARN_ON(!HAS_RUNTIME_PM(dev)); assert_force_wake_inactive(dev_priv); DRM_DEBUG_KMS("Suspending device\n"); - if (HAS_PC8(dev)) - hsw_enable_pc8(dev_priv); + /* + * We could deadlock here in case another thread holding struct_mutex + * calls RPM suspend concurrently, since the RPM suspend will wait + * first for this RPM suspend to finish. In this case the concurrent + * RPM resume will be followed by its RPM suspend counterpart. Still + * for consistency return -EAGAIN, which will reschedule this suspend. + */ + if (!mutex_trylock(&dev->struct_mutex)) { + DRM_DEBUG_KMS("device lock contention, deffering suspend\n"); + /* + * Bump the expiration timestamp, otherwise the suspend won't + * be rescheduled. + */ + pm_runtime_mark_last_busy(device); + return -EAGAIN; + } + /* + * We are safe here against re-faults, since the fault handler takes + * an RPM reference. + */ i915_gem_release_all_mmaps(dev_priv); + mutex_unlock(&dev->struct_mutex); + + /* + * rps.work can't be rearmed here, since we get here only after making + * sure the GPU is idle and the RPS freq is set to the minimum. See + * intel_mark_idle(). + */ + cancel_work_sync(&dev_priv->rps.work); + intel_runtime_pm_disable_interrupts(dev); + + if (IS_GEN6(dev)) { + ret = 0; + } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { + ret = hsw_runtime_suspend(dev_priv); + } else if (IS_VALLEYVIEW(dev)) { + ret = vlv_runtime_suspend(dev_priv); + } else { + ret = -ENODEV; + WARN_ON(1); + } + + if (ret) { + DRM_ERROR("Runtime suspend failed, disabling it (%d)\n", ret); + intel_runtime_pm_restore_interrupts(dev); + + return ret; + } del_timer_sync(&dev_priv->gpu_error.hangcheck_timer); dev_priv->pm.suspended = true; @@ -923,11 +1423,12 @@ 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); struct drm_i915_private *dev_priv = dev->dev_private; + int ret; WARN_ON(!HAS_RUNTIME_PM(dev)); @@ -936,11 +1437,33 @@ 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)) { + ret = snb_runtime_resume(dev_priv); + } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { + ret = hsw_runtime_resume(dev_priv); + } else if (IS_VALLEYVIEW(dev)) { + ret = vlv_runtime_resume(dev_priv); + } else { + WARN_ON(1); + ret = -ENODEV; + } - DRM_DEBUG_KMS("Device resumed\n"); - return 0; + /* + * No point of rolling back things in case of an error, as the best + * we can do is to hope that things will still work (and disable RPM). + */ + i915_gem_init_swizzling(dev); + gen6_update_ring_freq(dev); + + intel_runtime_pm_restore_interrupts(dev); + intel_reset_gt_powersave(dev); + + if (ret) + DRM_ERROR("Runtime resume failed, disabling it (%d)\n", ret); + else + DRM_DEBUG_KMS("Device resumed\n"); + + return ret; } static const struct dev_pm_ops i915_pm_ops = { @@ -954,8 +1477,8 @@ 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 = { @@ -1062,6 +1585,7 @@ static int __init i915_init(void) driver.get_vblank_timestamp = NULL; #ifndef CONFIG_DRM_I915_UMS /* Silently fail loading to not upset userspace. */ + DRM_DEBUG_DRIVER("KMS and UMS disabled.\n"); return 0; #endif } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 388c028e223c..49414d30e8d4 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -35,11 +35,13 @@ #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> #include <drm/intel-gtt.h> #include <linux/backlight.h> +#include <linux/hashtable.h> #include <linux/intel-iommu.h> #include <linux/kref.h> #include <linux/pm_qos.h> @@ -91,7 +93,7 @@ enum port { }; #define port_name(p) ((p) + 'A') -#define I915_NUM_PHYS_VLV 1 +#define I915_NUM_PHYS_VLV 2 enum dpio_channel { DPIO_CH0, @@ -162,6 +164,12 @@ enum hpd_pin { #define for_each_pipe(p) for ((p) = 0; (p) < INTEL_INFO(dev)->num_pipes; (p)++) #define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++) +#define for_each_crtc(dev, crtc) \ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + +#define for_each_intel_crtc(dev, intel_crtc) \ + list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) + #define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \ list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \ if ((intel_encoder)->base.crtc == (__crtc)) @@ -171,6 +179,7 @@ enum hpd_pin { if ((intel_connector)->base.encoder == (__encoder)) struct drm_i915_private; +struct i915_mmu_object; enum intel_dpll_id { DPLL_ID_PRIVATE = -1, /* non-shared dpll in use */ @@ -312,7 +321,6 @@ struct drm_i915_error_state { u32 gab_ctl; u32 gfx_mode; u32 extra_instdone[I915_NUM_INSTDONE_REG]; - u32 pipestat[I915_MAX_PIPES]; u64 fence[I915_MAX_NUM_FENCES]; struct intel_overlay_error_state *overlay; struct intel_display_error_state *display; @@ -346,7 +354,7 @@ 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]; @@ -385,6 +393,7 @@ struct drm_i915_error_state { u32 tiling:2; u32 dirty:1; u32 purgeable:1; + u32 userptr:1; s32 ring:4; u32 cache_level:3; } **active_bo, **pinned_bo; @@ -449,10 +458,11 @@ struct drm_i915_display_funcs { int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags); - int (*update_primary_plane)(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y); + void (*update_primary_plane)(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y); void (*hpd_irq_setup)(struct drm_device *dev); /* clock updates for mode set */ /* cursor updates */ @@ -545,6 +555,7 @@ struct intel_device_info { int dpll_offsets[I915_MAX_PIPES]; int dpll_md_offsets[I915_MAX_PIPES]; int palette_offsets[I915_MAX_PIPES]; + int cursor_offsets[I915_MAX_PIPES]; }; #undef DEFINE_FLAG @@ -560,168 +571,6 @@ 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; @@ -738,13 +587,13 @@ struct i915_ctx_hang_stats { /* This must match up with the value previously used for execbuf2.rsvd1. */ #define DEFAULT_CONTEXT_ID 0 -struct i915_hw_context { +struct intel_context { struct kref ref; int id; bool is_initialized; uint8_t remap_slice; struct drm_i915_file_private *file_priv; - struct intel_ring_buffer *last_ring; + struct intel_engine_cs *last_ring; struct drm_i915_gem_object *obj; struct i915_ctx_hang_stats hang_stats; struct i915_address_space *vm; @@ -782,6 +631,10 @@ struct i915_fbc { } no_fbc_reason; }; +struct i915_drrs { + struct intel_connector *connector; +}; + struct i915_psr { bool sink_support; bool source_ok; @@ -965,6 +818,67 @@ struct i915_suspend_saved_registers { u32 savePCH_PORT_HOTPLUG; }; +struct vlv_s0ix_state { + /* GAM */ + u32 wr_watermark; + u32 gfx_prio_ctrl; + u32 arb_mode; + u32 gfx_pend_tlb0; + u32 gfx_pend_tlb1; + u32 lra_limits[GEN7_LRA_LIMITS_REG_NUM]; + u32 media_max_req_count; + u32 gfx_max_req_count; + u32 render_hwsp; + u32 ecochk; + u32 bsd_hwsp; + u32 blt_hwsp; + u32 tlb_rd_addr; + + /* MBC */ + u32 g3dctl; + u32 gsckgctl; + u32 mbctl; + + /* GCP */ + u32 ucgctl1; + u32 ucgctl3; + u32 rcgctl1; + u32 rcgctl2; + u32 rstctl; + u32 misccpctl; + + /* GPM */ + u32 gfxpause; + u32 rpdeuhwtc; + u32 rpdeuc; + u32 ecobus; + u32 pwrdwnupctl; + u32 rp_down_timeout; + u32 rp_deucsw; + u32 rcubmabdtmr; + u32 rcedata; + u32 spare2gh; + + /* Display 1 CZ domain */ + u32 gt_imr; + u32 gt_ier; + u32 pm_imr; + u32 pm_ier; + u32 gt_scratch[GEN7_GT_SCRATCH_REG_NUM]; + + /* GT SA CZ domain */ + u32 tilectl; + u32 gt_fifoctl; + u32 gtlc_wake_ctrl; + u32 gtlc_survive; + u32 pmwgicz; + + /* Display 2 CZ domain */ + u32 gu_ctl0; + u32 gu_ctl1; + u32 clock_gate_dis2; +}; + struct intel_gen6_power_mgmt { /* work and pm_iir are protected by dev_priv->irq_lock */ struct work_struct work; @@ -1074,6 +988,7 @@ struct i915_power_domains { * time are on. They are kept on until after the first modeset. */ bool init_power_on; + bool initializing; int power_well_count; struct mutex lock; @@ -1132,7 +1047,8 @@ struct i915_gem_mm { /** PPGTT used for aliasing the PPGTT with the GTT */ struct i915_hw_ppgtt *aliasing_ppgtt; - struct shrinker inactive_shrinker; + struct notifier_block oom_notifier; + struct shrinker shrinker; bool shrinker_no_lock_stealing; /** LRU list of objects with fence regs on them. */ @@ -1170,6 +1086,9 @@ struct i915_gem_mm { */ bool busy; + /* the indicator for dispatch video commands on two BSD rings */ + int bsd_ring_dispatch_index; + /** Bit 6 swizzling required for X tiling */ uint32_t bit_6_swizzle_x; /** Bit 6 swizzling required for Y tiling */ @@ -1245,8 +1164,12 @@ struct i915_gpu_error { */ wait_queue_head_t reset_queue; - /* For gpu hang simulation. */ - unsigned int stop_rings; + /* Userspace knobs for gpu hang simulation; + * combines both a ring mask, and extra flags + */ + u32 stop_rings; +#define I915_STOP_RING_ALLOW_BAN (1 << 31) +#define I915_STOP_RING_ALLOW_WARN (1 << 30) /* For missed irq/seqno simulation. */ unsigned int test_irq_rings; @@ -1266,6 +1189,12 @@ 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 */ @@ -1278,9 +1207,12 @@ struct intel_vbt_data { unsigned int lvds_use_ssc:1; unsigned int display_clock_mode:1; unsigned int fdi_rx_polarity_inverted:1; + unsigned int has_mipi:1; 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; @@ -1299,7 +1231,14 @@ struct intel_vbt_data { /* MIPI DSI */ struct { + u16 port; u16 panel_id; + struct mipi_config *config; + struct mipi_pps_data *pps; + u8 seq_version; + u32 size; + u8 *data; + u8 *sequence[MIPI_SEQ_MAX]; } dsi; int crt_ddc_pin; @@ -1351,23 +1290,13 @@ 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 { @@ -1400,7 +1329,7 @@ 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; @@ -1424,10 +1353,13 @@ typedef struct drm_i915_private { */ uint32_t gpio_mmio_base; + /* MMIO base address for MIPI regs */ + uint32_t mipi_mmio_base; + wait_queue_head_t gmbus_wait_queue; struct pci_dev *bridge_dev; - struct intel_ring_buffer ring[I915_NUM_RINGS]; + struct intel_engine_cs ring[I915_NUM_RINGS]; uint32_t last_seqno, next_seqno; drm_dma_handle_t *status_page_dmah; @@ -1469,6 +1401,7 @@ typedef struct drm_i915_private { struct timer_list hotplug_reenable_timer; struct i915_fbc fbc; + struct i915_drrs drrs; struct intel_opregion opregion; struct intel_vbt_data vbt; @@ -1486,6 +1419,7 @@ 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. @@ -1509,9 +1443,12 @@ 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; +#if defined(CONFIG_MMU_NOTIFIER) + DECLARE_HASHTABLE(mmu_notifiers, 7); +#endif /* Kernel Modesetting */ @@ -1580,6 +1517,7 @@ typedef struct drm_i915_private { u32 suspend_count; struct i915_suspend_saved_registers regfile; + struct vlv_s0ix_state vlv_s0ix_state; struct { /* @@ -1605,7 +1543,12 @@ 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; + + /* + * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch + * will be rejected. Instead look for a better place. + */ +}; static inline struct drm_i915_private *to_i915(const struct drm_device *dev) { @@ -1642,6 +1585,8 @@ struct drm_i915_gem_object_ops { */ int (*get_pages)(struct drm_i915_gem_object *); void (*put_pages)(struct drm_i915_gem_object *); + int (*dmabuf_export)(struct drm_i915_gem_object *); + void (*release)(struct drm_i915_gem_object *); }; struct drm_i915_gem_object { @@ -1732,7 +1677,7 @@ struct drm_i915_gem_object { void *dma_buf_vmapping; int vmapping_count; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; /** Breadcrumb of last rendering to the buffer. */ uint32_t last_read_seqno; @@ -1755,8 +1700,20 @@ struct drm_i915_gem_object { /** for phy allocated objects */ drm_dma_handle_t *phys_handle; -}; + union { + struct i915_gem_userptr { + uintptr_t ptr; + unsigned read_only :1; + unsigned workers :4; +#define I915_GEM_USERPTR_MAX_WORKERS 15 + + struct mm_struct *mm; + struct i915_mmu_object *mn; + struct work_struct *work; + } userptr; + }; +}; #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base) /** @@ -1771,7 +1728,7 @@ struct drm_i915_gem_object { */ struct drm_i915_gem_request { /** On Which ring this request was generated */ - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; /** GEM sequence number associated with this request. */ uint32_t seqno; @@ -1783,7 +1740,7 @@ struct drm_i915_gem_request { u32 tail; /** Context related to this request */ - struct i915_hw_context *ctx; + struct intel_context *ctx; /** Batch buffer related to this request if any */ struct drm_i915_gem_object *batch_obj; @@ -1810,8 +1767,8 @@ struct drm_i915_file_private { } mm; struct idr context_idr; - struct i915_hw_context *private_default_ctx; atomic_t rps_wait_boost; + struct intel_engine_cs *bsd_ring; }; /* @@ -1879,11 +1836,17 @@ 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]; }; @@ -1925,8 +1888,9 @@ struct drm_i915_cmd_table { (dev)->pdev->device == 0x0106 || \ (dev)->pdev->device == 0x010A) #define IS_VALLEYVIEW(dev) (INTEL_INFO(dev)->is_valleyview) +#define IS_CHERRYVIEW(dev) (INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev)) #define IS_HASWELL(dev) (INTEL_INFO(dev)->is_haswell) -#define IS_BROADWELL(dev) (INTEL_INFO(dev)->gen == 8) +#define IS_BROADWELL(dev) (!INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev)) #define IS_MOBILE(dev) (INTEL_INFO(dev)->is_mobile) #define IS_HSW_EARLY_SDV(dev) (IS_HASWELL(dev) && \ ((dev)->pdev->device & 0xFF00) == 0x0C00) @@ -1962,17 +1926,21 @@ struct drm_i915_cmd_table { #define BSD_RING (1<<VCS) #define BLT_RING (1<<BCS) #define VEBOX_RING (1<<VECS) -#define HAS_BSD(dev) (INTEL_INFO(dev)->ring_mask & BSD_RING) -#define HAS_BLT(dev) (INTEL_INFO(dev)->ring_mask & BLT_RING) -#define HAS_VEBOX(dev) (INTEL_INFO(dev)->ring_mask & VEBOX_RING) -#define HAS_LLC(dev) (INTEL_INFO(dev)->has_llc) -#define HAS_WT(dev) (IS_HASWELL(dev) && to_i915(dev)->ellc_size) +#define BSD2_RING (1<<VCS2) +#define HAS_BSD(dev) (INTEL_INFO(dev)->ring_mask & BSD_RING) +#define HAS_BSD2(dev) (INTEL_INFO(dev)->ring_mask & BSD2_RING) +#define HAS_BLT(dev) (INTEL_INFO(dev)->ring_mask & BLT_RING) +#define HAS_VEBOX(dev) (INTEL_INFO(dev)->ring_mask & VEBOX_RING) +#define HAS_LLC(dev) (INTEL_INFO(dev)->has_llc) +#define HAS_WT(dev) ((IS_HASWELL(dev) || IS_BROADWELL(dev)) && \ + to_i915(dev)->ellc_size) #define I915_NEED_GFX_HWS(dev) (INTEL_INFO(dev)->need_gfx_hws) #define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6) -#define HAS_ALIASING_PPGTT(dev) (INTEL_INFO(dev)->gen >= 6 && !IS_VALLEYVIEW(dev)) -#define HAS_PPGTT(dev) (INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev) \ - && !IS_BROADWELL(dev)) +#define HAS_ALIASING_PPGTT(dev) (INTEL_INFO(dev)->gen >= 6 && \ + (!IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))) +#define HAS_PPGTT(dev) (INTEL_INFO(dev)->gen >= 7 \ + && !IS_GEN8(dev)) #define USES_PPGTT(dev) intel_enable_ppgtt(dev, false) #define USES_FULL_PPGTT(dev) intel_enable_ppgtt(dev, true) @@ -2010,8 +1978,8 @@ 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) || IS_VALLEYVIEW(dev)) #define INTEL_PCH_DEVICE_ID_MASK 0xff00 #define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00 @@ -2068,6 +2036,7 @@ struct i915_params { bool prefault_disable; bool reset; bool disable_display; + bool disable_vtd_wa; }; extern struct i915_params i915 __read_mostly; @@ -2096,6 +2065,7 @@ extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv); extern unsigned long i915_mch_val(struct drm_i915_private *dev_priv); extern unsigned long i915_gfx_val(struct drm_i915_private *dev_priv); extern void i915_update_gfx_val(struct drm_i915_private *dev_priv); +int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on); extern void intel_console_resume(struct work_struct *work); @@ -2170,6 +2140,9 @@ int i915_gem_set_tiling(struct drm_device *dev, void *data, struct drm_file *file_priv); int i915_gem_get_tiling(struct drm_device *dev, void *data, struct drm_file *file_priv); +int i915_gem_init_userptr(struct drm_device *dev); +int i915_gem_userptr_ioctl(struct drm_device *dev, void *data, + struct drm_file *file); int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int i915_gem_wait_ioctl(struct drm_device *dev, void *data, @@ -2227,9 +2200,9 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) int __must_check i915_mutex_lock_interruptible(struct drm_device *dev); int i915_gem_object_sync(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *to); + struct intel_engine_cs *to); void i915_vma_move_to_active(struct i915_vma *vma, - struct intel_ring_buffer *ring); + struct intel_engine_cs *ring); int i915_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, struct drm_mode_create_dumb *args); @@ -2249,31 +2222,14 @@ int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno); int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj); int __must_check i915_gem_object_put_fence(struct drm_i915_gem_object *obj); -static inline bool -i915_gem_object_pin_fence(struct drm_i915_gem_object *obj) -{ - if (obj->fence_reg != I915_FENCE_REG_NONE) { - struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - dev_priv->fence_regs[obj->fence_reg].pin_count++; - return true; - } else - return false; -} - -static inline void -i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj) -{ - if (obj->fence_reg != I915_FENCE_REG_NONE) { - struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0); - dev_priv->fence_regs[obj->fence_reg].pin_count--; - } -} +bool i915_gem_object_pin_fence(struct drm_i915_gem_object *obj); +void i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj); struct drm_i915_gem_request * -i915_gem_find_active_request(struct intel_ring_buffer *ring); +i915_gem_find_active_request(struct intel_engine_cs *ring); bool i915_gem_retire_requests(struct drm_device *dev); +void i915_gem_retire_requests_ring(struct intel_engine_cs *ring); int __must_check i915_gem_check_wedge(struct i915_gpu_error *error, bool interruptible); static inline bool i915_reset_in_progress(struct i915_gpu_error *error) @@ -2292,23 +2248,35 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) return ((atomic_read(&error->reset_counter) & ~I915_WEDGED) + 1) / 2; } +static inline bool i915_stop_ring_allow_ban(struct drm_i915_private *dev_priv) +{ + return dev_priv->gpu_error.stop_rings == 0 || + dev_priv->gpu_error.stop_rings & I915_STOP_RING_ALLOW_BAN; +} + +static inline bool i915_stop_ring_allow_warn(struct drm_i915_private *dev_priv) +{ + return dev_priv->gpu_error.stop_rings == 0 || + dev_priv->gpu_error.stop_rings & I915_STOP_RING_ALLOW_WARN; +} + void i915_gem_reset(struct drm_device *dev); bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force); int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj); int __must_check i915_gem_init(struct drm_device *dev); int __must_check i915_gem_init_hw(struct drm_device *dev); -int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice); +int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice); void i915_gem_init_swizzling(struct drm_device *dev); void i915_gem_cleanup_ringbuffer(struct drm_device *dev); int __must_check i915_gpu_idle(struct drm_device *dev); int __must_check i915_gem_suspend(struct drm_device *dev); -int __i915_add_request(struct intel_ring_buffer *ring, +int __i915_add_request(struct intel_engine_cs *ring, struct drm_file *file, struct drm_i915_gem_object *batch_obj, u32 *seqno); #define i915_add_request(ring, seqno) \ __i915_add_request(ring, NULL, NULL, seqno) -int __must_check i915_wait_seqno(struct intel_ring_buffer *ring, +int __must_check i915_wait_seqno(struct intel_engine_cs *ring, uint32_t seqno); int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf); int __must_check @@ -2319,7 +2287,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write); int __must_check i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, - struct intel_ring_buffer *pipelined); + struct intel_engine_cs *pipelined); void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj); int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align); @@ -2416,22 +2384,22 @@ void i915_gem_context_reset(struct drm_device *dev); int i915_gem_context_open(struct drm_device *dev, struct drm_file *file); int i915_gem_context_enable(struct drm_i915_private *dev_priv); void i915_gem_context_close(struct drm_device *dev, struct drm_file *file); -int i915_switch_context(struct intel_ring_buffer *ring, - struct i915_hw_context *to); -struct i915_hw_context * +int i915_switch_context(struct intel_engine_cs *ring, + struct intel_context *to); +struct intel_context * i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id); void i915_gem_context_free(struct kref *ctx_ref); -static inline void i915_gem_context_reference(struct i915_hw_context *ctx) +static inline void i915_gem_context_reference(struct intel_context *ctx) { kref_get(&ctx->ref); } -static inline void i915_gem_context_unreference(struct i915_hw_context *ctx) +static inline void i915_gem_context_unreference(struct intel_context *ctx) { kref_put(&ctx->ref, i915_gem_context_free); } -static inline bool i915_gem_context_is_default(const struct i915_hw_context *c) +static inline bool i915_gem_context_is_default(const struct intel_context *c) { return c->id == DEFAULT_CONTEXT_ID; } @@ -2441,6 +2409,8 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +/* i915_gem_render_state.c */ +int i915_gem_render_state_init(struct intel_engine_cs *ring); /* i915_gem_evict.c */ int __must_check i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm, @@ -2453,23 +2423,12 @@ 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); @@ -2537,9 +2496,11 @@ void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone); const char *i915_cache_level_str(int type); /* i915_cmd_parser.c */ -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, +int i915_cmd_parser_get_version(void); +int i915_cmd_parser_init_ring(struct intel_engine_cs *ring); +void i915_cmd_parser_fini_ring(struct intel_engine_cs *ring); +bool i915_needs_cmd_parser(struct intel_engine_cs *ring); +int i915_parse_cmds(struct intel_engine_cs *ring, struct drm_i915_gem_object *batch_obj, u32 batch_start_offset, bool is_master); @@ -2688,20 +2649,6 @@ 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.c b/drivers/gpu/drm/i915/i915_gem.c index 3326770c9ed2..f36126383d26 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -31,6 +31,7 @@ #include "i915_drv.h" #include "i915_trace.h" #include "intel_drv.h" +#include <linux/oom.h> #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> @@ -43,6 +44,8 @@ static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *o static __must_check int i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj, bool readonly); +static void +i915_gem_object_retire(struct drm_i915_gem_object *obj); static void i915_gem_write_fence(struct drm_device *dev, int reg, struct drm_i915_gem_object *obj); @@ -50,14 +53,15 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj, struct drm_i915_fence_reg *fence, bool enable); -static unsigned long i915_gem_inactive_count(struct shrinker *shrinker, +static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc); -static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker, +static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc); +static int i915_gem_shrinker_oom(struct notifier_block *nb, + unsigned long event, + void *ptr); static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target); static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv); -static void i915_gem_object_truncate(struct drm_i915_gem_object *obj); -static void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring); static bool cpu_cache_is_coherent(struct drm_device *dev, enum i915_cache_level level) @@ -470,6 +474,8 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, ret = i915_gem_object_wait_rendering(obj, true); if (ret) return ret; + + i915_gem_object_retire(obj); } ret = i915_gem_object_get_pages(obj); @@ -885,6 +891,8 @@ i915_gem_shmem_pwrite(struct drm_device *dev, ret = i915_gem_object_wait_rendering(obj, false); if (ret) return ret; + + i915_gem_object_retire(obj); } /* Same trick applies to invalidate partially written cachelines read * before writing. */ @@ -1088,7 +1096,7 @@ i915_gem_check_wedge(struct i915_gpu_error *error, * equal. */ static int -i915_gem_check_olr(struct intel_ring_buffer *ring, u32 seqno) +i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno) { int ret; @@ -1107,7 +1115,7 @@ static void fake_irq(unsigned long data) } static bool missed_irq(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings); } @@ -1138,7 +1146,7 @@ static bool can_wait_boost(struct drm_i915_file_private *file_priv) * Returns 0 if the seqno was found within the alloted time. Else returns the * errno with remaining time filled in timeout argument. */ -static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, +static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, unsigned reset_counter, bool interruptible, struct timespec *timeout, @@ -1245,7 +1253,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, * request and object lists appropriately for that event. */ int -i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno) +i915_wait_seqno(struct intel_engine_cs *ring, uint32_t seqno) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1270,9 +1278,10 @@ i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno) static int i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { - i915_gem_retire_requests_ring(ring); + if (!obj->active) + return 0; /* Manually manage the write flush as we may have not yet * retired the buffer. @@ -1282,7 +1291,6 @@ i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj, * we know we have passed the last write. */ obj->last_write_seqno = 0; - obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS; return 0; } @@ -1295,7 +1303,7 @@ static __must_check int i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj, bool readonly) { - struct intel_ring_buffer *ring = obj->ring; + struct intel_engine_cs *ring = obj->ring; u32 seqno; int ret; @@ -1320,7 +1328,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = obj->ring; + struct intel_engine_cs *ring = obj->ring; unsigned reset_counter; u32 seqno; int ret; @@ -1536,7 +1544,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) /* Access to snoopable pages through the GTT is incoherent. */ if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(dev)) { - ret = -EINVAL; + ret = -EFAULT; goto unlock; } @@ -1803,12 +1811,16 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data, return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset); } +static inline int +i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj) +{ + return obj->madv == I915_MADV_DONTNEED; +} + /* Immediately discard the backing storage */ static void i915_gem_object_truncate(struct drm_i915_gem_object *obj) { - struct inode *inode; - i915_gem_object_free_mmap_offset(obj); if (obj->base.filp == NULL) @@ -1819,16 +1831,28 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj) * To do this we must instruct the shmfs to drop all of its * backing pages, *now*. */ - inode = file_inode(obj->base.filp); - shmem_truncate_range(inode, 0, (loff_t)-1); - + shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1); obj->madv = __I915_MADV_PURGED; } -static inline int -i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj) +/* Try to discard unwanted pages */ +static void +i915_gem_object_invalidate(struct drm_i915_gem_object *obj) { - return obj->madv == I915_MADV_DONTNEED; + struct address_space *mapping; + + switch (obj->madv) { + case I915_MADV_DONTNEED: + i915_gem_object_truncate(obj); + case __I915_MADV_PURGED: + return; + } + + if (obj->base.filp == NULL) + return; + + mapping = file_inode(obj->base.filp)->i_mapping, + invalidate_mapping_pages(mapping, 0, (loff_t)-1); } static void @@ -1893,8 +1917,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj) ops->put_pages(obj); obj->pages = NULL; - if (i915_gem_object_is_purgeable(obj)) - i915_gem_object_truncate(obj); + i915_gem_object_invalidate(obj); return 0; } @@ -1903,58 +1926,58 @@ static unsigned long __i915_gem_shrink(struct drm_i915_private *dev_priv, long target, bool purgeable_only) { - struct list_head still_bound_list; - struct drm_i915_gem_object *obj, *next; + struct list_head still_in_list; + struct drm_i915_gem_object *obj; unsigned long count = 0; - list_for_each_entry_safe(obj, next, - &dev_priv->mm.unbound_list, - global_list) { - if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) && - i915_gem_object_put_pages(obj) == 0) { - count += obj->base.size >> PAGE_SHIFT; - if (count >= target) - return count; - } - } - /* - * As we may completely rewrite the bound list whilst unbinding + * As we may completely rewrite the (un)bound list whilst unbinding * (due to retiring requests) we have to strictly process only * one element of the list at the time, and recheck the list * on every iteration. + * + * In particular, we must hold a reference whilst removing the + * object as we may end up waiting for and/or retiring the objects. + * This might release the final reference (held by the active list) + * and result in the object being freed from under us. This is + * similar to the precautions the eviction code must take whilst + * removing objects. + * + * Also note that although these lists do not hold a reference to + * the object we can safely grab one here: The final object + * unreferencing and the bound_list are both protected by the + * dev->struct_mutex and so we won't ever be able to observe an + * object on the bound_list with a reference count equals 0. */ - INIT_LIST_HEAD(&still_bound_list); + INIT_LIST_HEAD(&still_in_list); + while (count < target && !list_empty(&dev_priv->mm.unbound_list)) { + obj = list_first_entry(&dev_priv->mm.unbound_list, + typeof(*obj), global_list); + list_move_tail(&obj->global_list, &still_in_list); + + if (!i915_gem_object_is_purgeable(obj) && purgeable_only) + continue; + + drm_gem_object_reference(&obj->base); + + if (i915_gem_object_put_pages(obj) == 0) + count += obj->base.size >> PAGE_SHIFT; + + drm_gem_object_unreference(&obj->base); + } + list_splice(&still_in_list, &dev_priv->mm.unbound_list); + + INIT_LIST_HEAD(&still_in_list); while (count < target && !list_empty(&dev_priv->mm.bound_list)) { struct i915_vma *vma, *v; obj = list_first_entry(&dev_priv->mm.bound_list, typeof(*obj), global_list); - list_move_tail(&obj->global_list, &still_bound_list); + list_move_tail(&obj->global_list, &still_in_list); if (!i915_gem_object_is_purgeable(obj) && purgeable_only) continue; - /* - * Hold a reference whilst we unbind this object, as we may - * end up waiting for and retiring requests. This might - * release the final reference (held by the active list) - * and result in the object being freed from under us. - * in this object being freed. - * - * Note 1: Shrinking the bound list is special since only active - * (and hence bound objects) can contain such limbo objects, so - * we don't need special tricks for shrinking the unbound list. - * The only other place where we have to be careful with active - * objects suddenly disappearing due to retiring requests is the - * eviction code. - * - * Note 2: Even though the bound list doesn't hold a reference - * to the object we can safely grab one here: The final object - * unreferencing and the bound_list are both protected by the - * dev->struct_mutex and so we won't ever be able to observe an - * object on the bound_list with a reference count equals 0. - */ drm_gem_object_reference(&obj->base); list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link) @@ -1966,7 +1989,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target, drm_gem_object_unreference(&obj->base); } - list_splice(&still_bound_list, &dev_priv->mm.bound_list); + list_splice(&still_in_list, &dev_priv->mm.bound_list); return count; } @@ -1980,17 +2003,8 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target) static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv) { - struct drm_i915_gem_object *obj, *next; - long freed = 0; - i915_gem_evict_everything(dev_priv->dev); - - list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, - global_list) { - if (i915_gem_object_put_pages(obj) == 0) - freed += obj->base.size >> PAGE_SHIFT; - } - return freed; + return __i915_gem_shrink(dev_priv, LONG_MAX, false); } static int @@ -2094,7 +2108,19 @@ err_pages: page_cache_release(sg_page_iter_page(&sg_iter)); sg_free_table(st); kfree(st); - return PTR_ERR(page); + + /* shmemfs first checks if there is enough memory to allocate the page + * and reports ENOSPC should there be insufficient, along with the usual + * ENOMEM for a genuine allocation failure. + * + * We use ENOSPC in our driver to mean that we have run out of aperture + * space and so want to translate the error from shmemfs back to our + * usual understanding of ENOMEM. + */ + if (PTR_ERR(page) == -ENOSPC) + return -ENOMEM; + else + return PTR_ERR(page); } /* Ensure that the associated pages are gathered from the backing storage @@ -2131,7 +2157,7 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj) static void i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2169,7 +2195,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, } void i915_vma_move_to_active(struct i915_vma *vma, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { list_move_tail(&vma->mm_list, &vma->vm->active_list); return i915_gem_object_move_to_active(vma->obj, ring); @@ -2207,11 +2233,24 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj) WARN_ON(i915_verify_lists(dev)); } +static void +i915_gem_object_retire(struct drm_i915_gem_object *obj) +{ + struct intel_engine_cs *ring = obj->ring; + + if (ring == NULL) + return; + + if (i915_seqno_passed(ring->get_seqno(ring, true), + obj->last_read_seqno)) + i915_gem_object_move_to_inactive(obj); +} + static int i915_gem_init_seqno(struct drm_device *dev, u32 seqno) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i, j; /* Carefully retire all requests without writing to the rings */ @@ -2226,8 +2265,8 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno) for_each_ring(ring, dev_priv, i) { intel_ring_init_seqno(ring, seqno); - for (j = 0; j < ARRAY_SIZE(ring->sync_seqno); j++) - ring->sync_seqno[j] = 0; + for (j = 0; j < ARRAY_SIZE(ring->semaphore.sync_seqno); j++) + ring->semaphore.sync_seqno[j] = 0; } return 0; @@ -2277,7 +2316,7 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno) return 0; } -int __i915_add_request(struct intel_ring_buffer *ring, +int __i915_add_request(struct intel_engine_cs *ring, struct drm_file *file, struct drm_i915_gem_object *obj, u32 *out_seqno) @@ -2382,7 +2421,7 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request) } static bool i915_context_is_banned(struct drm_i915_private *dev_priv, - const struct i915_hw_context *ctx) + const struct intel_context *ctx) { unsigned long elapsed; @@ -2395,8 +2434,9 @@ static bool i915_context_is_banned(struct drm_i915_private *dev_priv, if (!i915_gem_context_is_default(ctx)) { DRM_DEBUG("context hanging too fast, banning!\n"); return true; - } else if (dev_priv->gpu_error.stop_rings == 0) { - DRM_ERROR("gpu hanging too fast, banning!\n"); + } else if (i915_stop_ring_allow_ban(dev_priv)) { + if (i915_stop_ring_allow_warn(dev_priv)) + DRM_ERROR("gpu hanging too fast, banning!\n"); return true; } } @@ -2405,7 +2445,7 @@ static bool i915_context_is_banned(struct drm_i915_private *dev_priv, } static void i915_set_reset_status(struct drm_i915_private *dev_priv, - struct i915_hw_context *ctx, + struct intel_context *ctx, const bool guilty) { struct i915_ctx_hang_stats *hs; @@ -2436,7 +2476,7 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request) } struct drm_i915_gem_request * -i915_gem_find_active_request(struct intel_ring_buffer *ring) +i915_gem_find_active_request(struct intel_engine_cs *ring) { struct drm_i915_gem_request *request; u32 completed_seqno; @@ -2454,7 +2494,7 @@ i915_gem_find_active_request(struct intel_ring_buffer *ring) } static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_i915_gem_request *request; bool ring_hung; @@ -2473,7 +2513,7 @@ static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv, } static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { while (!list_empty(&ring->active_list)) { struct drm_i915_gem_object *obj; @@ -2501,6 +2541,11 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, i915_gem_free_request(request); } + + /* These may not have been flush before the reset, do so now */ + kfree(ring->preallocated_lazy_request); + ring->preallocated_lazy_request = NULL; + ring->outstanding_lazy_seqno = 0; } void i915_gem_restore_fences(struct drm_device *dev) @@ -2527,7 +2572,7 @@ void i915_gem_restore_fences(struct drm_device *dev) void i915_gem_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; /* @@ -2541,8 +2586,6 @@ void i915_gem_reset(struct drm_device *dev) for_each_ring(ring, dev_priv, i) i915_gem_reset_ring_cleanup(dev_priv, ring); - i915_gem_cleanup_ringbuffer(dev); - i915_gem_context_reset(dev); i915_gem_restore_fences(dev); @@ -2551,8 +2594,8 @@ void i915_gem_reset(struct drm_device *dev) /** * This function clears the request list as sequence numbers are passed. */ -static void -i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) +void +i915_gem_retire_requests_ring(struct intel_engine_cs *ring) { uint32_t seqno; @@ -2597,7 +2640,7 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) * of tail of the request to update the last known position * of the GPU head. */ - ring->last_retired_head = request->tail; + ring->buffer->last_retired_head = request->tail; i915_gem_free_request(request); } @@ -2615,7 +2658,7 @@ bool i915_gem_retire_requests(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; bool idle = true; int i; @@ -2709,7 +2752,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_wait *args = data; struct drm_i915_gem_object *obj; - struct intel_ring_buffer *ring = NULL; + struct intel_engine_cs *ring = NULL; struct timespec timeout_stack, *timeout = NULL; unsigned reset_counter; u32 seqno = 0; @@ -2780,9 +2823,9 @@ out: */ int i915_gem_object_sync(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *to) + struct intel_engine_cs *to) { - struct intel_ring_buffer *from = obj->ring; + struct intel_engine_cs *from = obj->ring; u32 seqno; int ret, idx; @@ -2795,7 +2838,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj, idx = intel_ring_sync_index(from, to); seqno = obj->last_read_seqno; - if (seqno <= from->sync_seqno[idx]) + if (seqno <= from->semaphore.sync_seqno[idx]) return 0; ret = i915_gem_check_olr(obj->ring, seqno); @@ -2803,13 +2846,13 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj, return ret; trace_i915_gem_ring_sync_to(from, to, seqno); - ret = to->sync_to(to, from, seqno); + ret = to->semaphore.sync_to(to, from, seqno); if (!ret) /* We use last_read_seqno because sync_to() * might have just caused seqno wrap under * the radar. */ - from->sync_seqno[idx] = obj->last_read_seqno; + from->semaphore.sync_seqno[idx] = obj->last_read_seqno; return ret; } @@ -2865,12 +2908,14 @@ int i915_vma_unbind(struct i915_vma *vma) * cause memory corruption through use-after-free. */ - i915_gem_object_finish_gtt(obj); + if (i915_is_ggtt(vma->vm)) { + i915_gem_object_finish_gtt(obj); - /* release the fence reg _after_ flushing */ - ret = i915_gem_object_put_fence(obj); - if (ret) - return ret; + /* release the fence reg _after_ flushing */ + ret = i915_gem_object_put_fence(obj); + if (ret) + return ret; + } trace_i915_vma_unbind(vma); @@ -2903,7 +2948,7 @@ int i915_vma_unbind(struct i915_vma *vma) int i915_gpu_idle(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i; /* Flush everything onto the inactive list. */ @@ -3144,6 +3189,9 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj) fence = &dev_priv->fence_regs[obj->fence_reg]; + if (WARN_ON(fence->pin_count)) + return -EBUSY; + i915_gem_object_fence_lost(obj); i915_gem_object_update_fence(obj, fence, false); @@ -3548,6 +3596,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) if (ret) return ret; + i915_gem_object_retire(obj); i915_gem_object_flush_cpu_write_domain(obj, false); /* Serialise direct access to this object with the barriers for @@ -3646,6 +3695,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, * in obj->write_domain and have been skipping the clflushes. * Just set it to the CPU cache for now. */ + i915_gem_object_retire(obj); WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU); old_read_domains = obj->base.read_domains; @@ -3743,6 +3793,15 @@ unlock: static bool is_pin_display(struct drm_i915_gem_object *obj) { + struct i915_vma *vma; + + if (list_empty(&obj->vma_list)) + return false; + + vma = i915_gem_obj_to_ggtt(obj); + if (!vma) + return false; + /* There are 3 sources that pin objects: * 1. The display engine (scanouts, sprites, cursors); * 2. Reservations for execbuffer; @@ -3754,7 +3813,7 @@ static bool is_pin_display(struct drm_i915_gem_object *obj) * subtracting the potential reference by the user, any pin_count * remains, it must be due to another use by the display engine. */ - return i915_gem_obj_to_ggtt(obj)->pin_count - !!obj->user_pin_count; + return vma->pin_count - !!obj->user_pin_count; } /* @@ -3765,9 +3824,10 @@ static bool is_pin_display(struct drm_i915_gem_object *obj) int i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, - struct intel_ring_buffer *pipelined) + struct intel_engine_cs *pipelined) { u32 old_read_domains, old_write_domain; + bool was_pin_display; int ret; if (pipelined != obj->ring) { @@ -3779,6 +3839,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, /* Mark the pin_display early so that we account for the * display coherency whilst setting up the cache domains. */ + was_pin_display = obj->pin_display; obj->pin_display = true; /* The display engine is not coherent with the LLC cache on gen6. As @@ -3821,7 +3882,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, return 0; err_unpin_display: - obj->pin_display = is_pin_display(obj); + WARN_ON(was_pin_display != is_pin_display(obj)); + obj->pin_display = was_pin_display; return ret; } @@ -3868,6 +3930,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write) if (ret) return ret; + i915_gem_object_retire(obj); i915_gem_object_flush_gtt_write_domain(obj); old_write_domain = obj->base.write_domain; @@ -3917,7 +3980,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file) struct drm_i915_file_private *file_priv = file->driver_priv; unsigned long recent_enough = jiffies - msecs_to_jiffies(20); struct drm_i915_gem_request *request; - struct intel_ring_buffer *ring = NULL; + struct intel_engine_cs *ring = NULL; unsigned reset_counter; u32 seqno = 0; int ret; @@ -3976,9 +4039,13 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj, uint32_t alignment, uint64_t flags) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; struct i915_vma *vma; int ret; + if (WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base)) + return -ENODEV; + if (WARN_ON(flags & (PIN_GLOBAL | PIN_MAPPABLE) && !i915_is_ggtt(vm))) return -EINVAL; @@ -4032,6 +4099,32 @@ i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj) obj->pin_mappable = false; } +bool +i915_gem_object_pin_fence(struct drm_i915_gem_object *obj) +{ + if (obj->fence_reg != I915_FENCE_REG_NONE) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + struct i915_vma *ggtt_vma = i915_gem_obj_to_ggtt(obj); + + WARN_ON(!ggtt_vma || + dev_priv->fence_regs[obj->fence_reg].pin_count > + ggtt_vma->pin_count); + dev_priv->fence_regs[obj->fence_reg].pin_count++; + return true; + } else + return false; +} + +void +i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj) +{ + if (obj->fence_reg != I915_FENCE_REG_NONE) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0); + dev_priv->fence_regs[obj->fence_reg].pin_count--; + } +} + int i915_gem_pin_ioctl(struct drm_device *dev, void *data, struct drm_file *file) @@ -4292,6 +4385,30 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, return obj; } +static bool discard_backing_storage(struct drm_i915_gem_object *obj) +{ + /* If we are the last user of the backing storage (be it shmemfs + * pages or stolen etc), we know that the pages are going to be + * immediately released. In this case, we can then skip copying + * back the contents from the GPU. + */ + + if (obj->madv != I915_MADV_WILLNEED) + return false; + + if (obj->base.filp == NULL) + return true; + + /* At first glance, this looks racy, but then again so would be + * userspace racing mmap against close. However, the first external + * reference to the filp can only be obtained through the + * i915_gem_mmap_ioctl() which safeguards us against the user + * acquiring such a reference whilst we are in the middle of + * freeing the object. + */ + return atomic_long_read(&obj->base.filp->f_count) == 1; +} + void i915_gem_free_object(struct drm_gem_object *gem_obj) { struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); @@ -4329,6 +4446,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) if (WARN_ON(obj->pages_pin_count)) obj->pages_pin_count = 0; + if (discard_backing_storage(obj)) + obj->madv = I915_MADV_DONTNEED; i915_gem_object_put_pages(obj); i915_gem_object_free_mmap_offset(obj); i915_gem_object_release_stolen(obj); @@ -4338,6 +4457,9 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) if (obj->base.import_attach) drm_prime_gem_destroy(&obj->base, NULL); + if (obj->ops->release) + obj->ops->release(obj); + drm_gem_object_release(&obj->base); i915_gem_info_remove_obj(dev_priv, obj->base.size); @@ -4371,6 +4493,17 @@ void i915_gem_vma_destroy(struct i915_vma *vma) kfree(vma); } +static void +i915_gem_stop_ringbuffers(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_engine_cs *ring; + int i; + + for_each_ring(ring, dev_priv, i) + intel_stop_ring_buffer(ring); +} + int i915_gem_suspend(struct drm_device *dev) { @@ -4392,7 +4525,7 @@ i915_gem_suspend(struct drm_device *dev) i915_gem_evict_everything(dev); i915_kernel_lost_context(dev); - i915_gem_cleanup_ringbuffer(dev); + i915_gem_stop_ringbuffers(dev); /* Hack! Don't let anybody do execbuf while we don't control the chip. * We need to replace this with a semaphore, or something. @@ -4413,7 +4546,7 @@ err: return ret; } -int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice) +int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -4512,13 +4645,20 @@ static int i915_gem_init_rings(struct drm_device *dev) goto cleanup_blt_ring; } + if (HAS_BSD2(dev)) { + ret = intel_init_bsd2_ring_buffer(dev); + if (ret) + goto cleanup_vebox_ring; + } ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000)); if (ret) - goto cleanup_vebox_ring; + goto cleanup_bsd2_ring; return 0; +cleanup_bsd2_ring: + intel_cleanup_ring_buffer(&dev_priv->ring[VCS2]); cleanup_vebox_ring: intel_cleanup_ring_buffer(&dev_priv->ring[VECS]); cleanup_blt_ring: @@ -4576,15 +4716,11 @@ i915_gem_init_hw(struct drm_device *dev) * the do_switch), but before enabling PPGTT. So don't move this. */ ret = i915_gem_context_enable(dev_priv); - if (ret) { + if (ret && ret != -EIO) { DRM_ERROR("Context enable failed %d\n", ret); - goto err_out; + i915_gem_cleanup_ringbuffer(dev); } - return 0; - -err_out: - i915_gem_cleanup_ringbuffer(dev); return ret; } @@ -4597,11 +4733,13 @@ int i915_gem_init(struct drm_device *dev) if (IS_VALLEYVIEW(dev)) { /* VLVA0 (potential hack), BIOS isn't actually waking us */ - I915_WRITE(VLV_GTLC_WAKE_CTRL, 1); - if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) & 1) == 1, 10)) + I915_WRITE(VLV_GTLC_WAKE_CTRL, VLV_GTLC_ALLOWWAKEREQ); + if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) & + VLV_GTLC_ALLOWWAKEACK), 10)) DRM_DEBUG_DRIVER("allow wake ack timed out\n"); } + i915_gem_init_userptr(dev); i915_gem_init_global_gtt(dev); ret = i915_gem_context_init(dev); @@ -4611,25 +4749,28 @@ int i915_gem_init(struct drm_device *dev) } ret = i915_gem_init_hw(dev); - mutex_unlock(&dev->struct_mutex); - if (ret) { - WARN_ON(dev_priv->mm.aliasing_ppgtt); - i915_gem_context_fini(dev); - drm_mm_takedown(&dev_priv->gtt.base.mm); - return ret; + if (ret == -EIO) { + /* Allow ring initialisation to fail by marking the GPU as + * wedged. But we only want to do this where the GPU is angry, + * for all other failure, such as an allocation failure, bail. + */ + DRM_ERROR("Failed to initialize GPU, declaring it wedged\n"); + atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter); + ret = 0; } + mutex_unlock(&dev->struct_mutex); /* Allow hardware batchbuffers unless told otherwise, but not for KMS. */ if (!drm_core_check_feature(dev, DRIVER_MODESET)) dev_priv->dri1.allow_batchbuffer = 1; - return 0; + return ret; } void i915_gem_cleanup_ringbuffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; for_each_ring(ring, dev_priv, i) @@ -4661,16 +4802,15 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, } BUG_ON(!list_empty(&dev_priv->gtt.base.active_list)); - mutex_unlock(&dev->struct_mutex); - ret = drm_irq_install(dev); + ret = drm_irq_install(dev, dev->pdev->irq); if (ret) goto cleanup_ringbuffer; + mutex_unlock(&dev->struct_mutex); return 0; cleanup_ringbuffer: - mutex_lock(&dev->struct_mutex); i915_gem_cleanup_ringbuffer(dev); dev_priv->ums.mm_suspended = 1; mutex_unlock(&dev->struct_mutex); @@ -4685,7 +4825,9 @@ i915_gem_leavevt_ioctl(struct drm_device *dev, void *data, if (drm_core_check_feature(dev, DRIVER_MODESET)) return 0; + mutex_lock(&dev->struct_mutex); drm_irq_uninstall(dev); + mutex_unlock(&dev->struct_mutex); return i915_gem_suspend(dev); } @@ -4704,7 +4846,7 @@ i915_gem_lastclose(struct drm_device *dev) } static void -init_ring_lists(struct intel_ring_buffer *ring) +init_ring_lists(struct intel_engine_cs *ring) { INIT_LIST_HEAD(&ring->active_list); INIT_LIST_HEAD(&ring->request_list); @@ -4752,7 +4894,7 @@ i915_gem_load(struct drm_device *dev) init_waitqueue_head(&dev_priv->gpu_error.reset_queue); /* On GEN3 we really need to make sure the ARB C3 LP bit is set */ - if (IS_GEN3(dev)) { + if (!drm_core_check_feature(dev, DRIVER_MODESET) && IS_GEN3(dev)) { I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE)); } @@ -4779,10 +4921,13 @@ i915_gem_load(struct drm_device *dev) dev_priv->mm.interruptible = true; - dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan; - dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count; - dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS; - register_shrinker(&dev_priv->mm.inactive_shrinker); + dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan; + dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count; + dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS; + register_shrinker(&dev_priv->mm.shrinker); + + dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom; + register_oom_notifier(&dev_priv->mm.oom_notifier); } void i915_gem_release(struct drm_device *dev, struct drm_file *file) @@ -4857,27 +5002,46 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) #endif } +static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) +{ + if (!mutex_trylock(&dev->struct_mutex)) { + if (!mutex_is_locked_by(&dev->struct_mutex, current)) + return false; + + if (to_i915(dev)->mm.shrinker_no_lock_stealing) + return false; + + *unlock = false; + } else + *unlock = true; + + return true; +} + +static int num_vma_bound(struct drm_i915_gem_object *obj) +{ + struct i915_vma *vma; + int count = 0; + + list_for_each_entry(vma, &obj->vma_list, vma_link) + if (drm_mm_node_allocated(&vma->node)) + count++; + + return count; +} + static unsigned long -i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc) +i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = - container_of(shrinker, - struct drm_i915_private, - mm.inactive_shrinker); + container_of(shrinker, struct drm_i915_private, mm.shrinker); struct drm_device *dev = dev_priv->dev; struct drm_i915_gem_object *obj; - bool unlock = true; unsigned long count; + bool unlock; - if (!mutex_trylock(&dev->struct_mutex)) { - if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return 0; - - if (dev_priv->mm.shrinker_no_lock_stealing) - return 0; - - unlock = false; - } + if (!i915_gem_shrinker_lock(dev, &unlock)) + return 0; count = 0; list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) @@ -4885,10 +5049,8 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >> PAGE_SHIFT; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - if (obj->active) - continue; - - if (!i915_gem_obj_is_pinned(obj) && obj->pages_pin_count == 0) + if (!i915_gem_obj_is_pinned(obj) && + obj->pages_pin_count == num_vma_bound(obj)) count += obj->base.size >> PAGE_SHIFT; } @@ -4961,44 +5123,99 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, } static unsigned long -i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc) +i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = - container_of(shrinker, - struct drm_i915_private, - mm.inactive_shrinker); + container_of(shrinker, struct drm_i915_private, mm.shrinker); struct drm_device *dev = dev_priv->dev; unsigned long freed; - bool unlock = true; + bool unlock; - if (!mutex_trylock(&dev->struct_mutex)) { - if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return SHRINK_STOP; - - if (dev_priv->mm.shrinker_no_lock_stealing) - return SHRINK_STOP; - - unlock = false; - } + if (!i915_gem_shrinker_lock(dev, &unlock)) + return SHRINK_STOP; freed = i915_gem_purge(dev_priv, sc->nr_to_scan); if (freed < sc->nr_to_scan) freed += __i915_gem_shrink(dev_priv, sc->nr_to_scan - freed, false); - if (freed < sc->nr_to_scan) - freed += i915_gem_shrink_all(dev_priv); - if (unlock) mutex_unlock(&dev->struct_mutex); return freed; } +static int +i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) +{ + struct drm_i915_private *dev_priv = + container_of(nb, struct drm_i915_private, mm.oom_notifier); + struct drm_device *dev = dev_priv->dev; + struct drm_i915_gem_object *obj; + unsigned long timeout = msecs_to_jiffies(5000) + 1; + unsigned long pinned, bound, unbound, freed; + bool was_interruptible; + bool unlock; + + while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout) + schedule_timeout_killable(1); + if (timeout == 0) { + pr_err("Unable to purge GPU memory due lock contention.\n"); + return NOTIFY_DONE; + } + + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; + + freed = i915_gem_shrink_all(dev_priv); + + dev_priv->mm.interruptible = was_interruptible; + + /* Because we may be allocating inside our own driver, we cannot + * assert that there are no objects with pinned pages that are not + * being pointed to by hardware. + */ + unbound = bound = pinned = 0; + list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) { + if (!obj->base.filp) /* not backed by a freeable object */ + continue; + + if (obj->pages_pin_count) + pinned += obj->base.size; + else + unbound += obj->base.size; + } + list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { + if (!obj->base.filp) + continue; + + if (obj->pages_pin_count) + pinned += obj->base.size; + else + bound += obj->base.size; + } + + if (unlock) + mutex_unlock(&dev->struct_mutex); + + pr_info("Purging GPU memory, %lu bytes freed, %lu bytes still pinned.\n", + freed, pinned); + if (unbound || bound) + pr_err("%lu and %lu bytes still available in the " + "bound and unbound GPU page lists.\n", + bound, unbound); + + *(unsigned long *)ptr += freed; + return NOTIFY_DONE; +} + struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj) { struct i915_vma *vma; + /* This WARN has probably outlived its usefulness (callers already + * WARN if they don't find the GGTT vma they expect). When removing, + * remember to remove the pre-check in is_pin_display() as well */ if (WARN_ON(list_empty(&obj->vma_list))) return NULL; diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index d72db15afa02..3ffe308d5893 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -178,7 +178,7 @@ static int get_context_size(struct drm_device *dev) void i915_gem_context_free(struct kref *ctx_ref) { - struct i915_hw_context *ctx = container_of(ctx_ref, + struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref); struct i915_hw_ppgtt *ppgtt = NULL; @@ -199,7 +199,7 @@ void i915_gem_context_free(struct kref *ctx_ref) } static struct i915_hw_ppgtt * -create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx) +create_vm_for_ctx(struct drm_device *dev, struct intel_context *ctx) { struct i915_hw_ppgtt *ppgtt; int ret; @@ -218,12 +218,12 @@ create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx) return ppgtt; } -static struct i915_hw_context * +static struct intel_context * __create_hw_context(struct drm_device *dev, struct drm_i915_file_private *file_priv) { struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -240,7 +240,15 @@ __create_hw_context(struct drm_device *dev, goto err_out; } - if (INTEL_INFO(dev)->gen >= 7) { + /* + * Try to make the context utilize L3 as well as LLC. + * + * On VLV we don't have L3 controls in the PTEs so we + * shouldn't touch the cache level, especially as that + * would make the object snooped which might have a + * negative performance impact. + */ + if (INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev)) { ret = i915_gem_object_set_cache_level(ctx->obj, I915_CACHE_L3_LLC); /* Failure shouldn't ever happen this early */ @@ -277,14 +285,14 @@ err_out: * context state of the GPU for applications that don't utilize HW contexts, as * well as an idle case. */ -static struct i915_hw_context * +static struct intel_context * i915_gem_create_context(struct drm_device *dev, struct drm_i915_file_private *file_priv, bool create_vm) { const bool is_global_default_ctx = file_priv == NULL; struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret = 0; BUG_ON(!mutex_is_locked(&dev->struct_mutex)); @@ -356,8 +364,8 @@ void i915_gem_context_reset(struct drm_device *dev) /* Prevent the hardware from restoring the last context (which hung) on * the next switch */ for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_ring_buffer *ring = &dev_priv->ring[i]; - struct i915_hw_context *dctx = ring->default_context; + struct intel_engine_cs *ring = &dev_priv->ring[i]; + struct intel_context *dctx = ring->default_context; /* Do a fake switch to the default context */ if (ring->last_context == dctx) @@ -383,7 +391,7 @@ void i915_gem_context_reset(struct drm_device *dev) int i915_gem_context_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; int i; /* Init should only be called once per module load. Eventually the @@ -418,7 +426,7 @@ int i915_gem_context_init(struct drm_device *dev) void i915_gem_context_fini(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *dctx = dev_priv->ring[RCS].default_context; + struct intel_context *dctx = dev_priv->ring[RCS].default_context; int i; if (dctx->obj) { @@ -441,10 +449,12 @@ void i915_gem_context_fini(struct drm_device *dev) i915_gem_context_unreference(dctx); dev_priv->ring[RCS].last_context = NULL; } + + i915_gem_object_ggtt_unpin(dctx->obj); } for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_ring_buffer *ring = &dev_priv->ring[i]; + struct intel_engine_cs *ring = &dev_priv->ring[i]; if (ring->last_context) i915_gem_context_unreference(ring->last_context); @@ -453,13 +463,12 @@ void i915_gem_context_fini(struct drm_device *dev) ring->last_context = NULL; } - i915_gem_object_ggtt_unpin(dctx->obj); i915_gem_context_unreference(dctx); } int i915_gem_context_enable(struct drm_i915_private *dev_priv) { - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i; /* This is the only place the aliasing PPGTT gets enabled, which means @@ -486,11 +495,7 @@ int i915_gem_context_enable(struct drm_i915_private *dev_priv) static int context_idr_cleanup(int id, void *p, void *data) { - struct i915_hw_context *ctx = p; - - /* Ignore the default context because close will handle it */ - if (i915_gem_context_is_default(ctx)) - return 0; + struct intel_context *ctx = p; i915_gem_context_unreference(ctx); return 0; @@ -499,17 +504,17 @@ static int context_idr_cleanup(int id, void *p, void *data) int i915_gem_context_open(struct drm_device *dev, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; + struct intel_context *ctx; idr_init(&file_priv->context_idr); mutex_lock(&dev->struct_mutex); - file_priv->private_default_ctx = - i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev)); + ctx = i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev)); mutex_unlock(&dev->struct_mutex); - if (IS_ERR(file_priv->private_default_ctx)) { + if (IS_ERR(ctx)) { idr_destroy(&file_priv->context_idr); - return PTR_ERR(file_priv->private_default_ctx); + return PTR_ERR(ctx); } return 0; @@ -521,16 +526,14 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file) idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL); idr_destroy(&file_priv->context_idr); - - i915_gem_context_unreference(file_priv->private_default_ctx); } -struct i915_hw_context * +struct intel_context * i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id) { - struct i915_hw_context *ctx; + struct intel_context *ctx; - ctx = (struct i915_hw_context *)idr_find(&file_priv->context_idr, id); + ctx = (struct intel_context *)idr_find(&file_priv->context_idr, id); if (!ctx) return ERR_PTR(-ENOENT); @@ -538,8 +541,8 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id) } static inline int -mi_set_context(struct intel_ring_buffer *ring, - struct i915_hw_context *new_context, +mi_set_context(struct intel_engine_cs *ring, + struct intel_context *new_context, u32 hw_flags) { int ret; @@ -549,7 +552,7 @@ 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; @@ -559,8 +562,8 @@ 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,chv */ + 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); @@ -578,7 +581,7 @@ 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); @@ -588,11 +591,11 @@ mi_set_context(struct intel_ring_buffer *ring, return ret; } -static int do_switch(struct intel_ring_buffer *ring, - struct i915_hw_context *to) +static int do_switch(struct intel_engine_cs *ring, + struct intel_context *to) { struct drm_i915_private *dev_priv = ring->dev->dev_private; - struct i915_hw_context *from = ring->last_context; + struct intel_context *from = ring->last_context; struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(to); u32 hw_flags = 0; int ret, i; @@ -693,13 +696,19 @@ static int do_switch(struct intel_ring_buffer *ring, i915_gem_context_unreference(from); } - to->is_initialized = true; - done: i915_gem_context_reference(to); ring->last_context = to; to->last_ring = ring; + if (ring->id == RCS && !to->is_initialized && from == NULL) { + ret = i915_gem_render_state_init(ring); + if (ret) + DRM_ERROR("init render state: %d\n", ret); + } + + to->is_initialized = true; + return 0; unpin_out: @@ -718,8 +727,8 @@ unpin_out: * it will have a refoucnt > 1. This allows us to destroy the context abstract * object while letting the normal object tracking destroy the backing BO. */ -int i915_switch_context(struct intel_ring_buffer *ring, - struct i915_hw_context *to) +int i915_switch_context(struct intel_engine_cs *ring, + struct intel_context *to) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -748,7 +757,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, { struct drm_i915_gem_context_create *args = data; struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; if (!hw_context_enabled(dev)) @@ -774,7 +783,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, { struct drm_i915_gem_context_destroy *args = data; struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; if (args->ctx_id == DEFAULT_CONTEXT_ID) diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 9bb533e0d762..580aa42443ed 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -161,12 +161,8 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) { struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); struct drm_device *dev = obj->base.dev; - int ret; - - ret = i915_mutex_lock_interruptible(dev); - if (ret) - return; + mutex_lock(&dev->struct_mutex); if (--obj->vmapping_count == 0) { vunmap(obj->dma_buf_vmapping); obj->dma_buf_vmapping = NULL; @@ -233,6 +229,14 @@ static const struct dma_buf_ops i915_dmabuf_ops = { struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags) { + struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); + + if (obj->ops->dmabuf_export) { + int ret = obj->ops->dmabuf_export(obj); + if (ret) + return ERR_PTR(ret); + } + return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags); } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 20fef6c50267..3a30133f93e8 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -265,10 +265,12 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj) static int relocate_entry_cpu(struct drm_i915_gem_object *obj, - struct drm_i915_gem_relocation_entry *reloc) + struct drm_i915_gem_relocation_entry *reloc, + uint64_t target_offset) { struct drm_device *dev = obj->base.dev; uint32_t page_offset = offset_in_page(reloc->offset); + uint64_t delta = reloc->delta + target_offset; char *vaddr; int ret; @@ -278,7 +280,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj, vaddr = kmap_atomic(i915_gem_object_get_page(obj, reloc->offset >> PAGE_SHIFT)); - *(uint32_t *)(vaddr + page_offset) = reloc->delta; + *(uint32_t *)(vaddr + page_offset) = lower_32_bits(delta); if (INTEL_INFO(dev)->gen >= 8) { page_offset = offset_in_page(page_offset + sizeof(uint32_t)); @@ -289,7 +291,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj, (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT)); } - *(uint32_t *)(vaddr + page_offset) = 0; + *(uint32_t *)(vaddr + page_offset) = upper_32_bits(delta); } kunmap_atomic(vaddr); @@ -299,10 +301,12 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj, static int relocate_entry_gtt(struct drm_i915_gem_object *obj, - struct drm_i915_gem_relocation_entry *reloc) + struct drm_i915_gem_relocation_entry *reloc, + uint64_t target_offset) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + uint64_t delta = reloc->delta + target_offset; uint32_t __iomem *reloc_entry; void __iomem *reloc_page; int ret; @@ -321,7 +325,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj, reloc->offset & PAGE_MASK); reloc_entry = (uint32_t __iomem *) (reloc_page + offset_in_page(reloc->offset)); - iowrite32(reloc->delta, reloc_entry); + iowrite32(lower_32_bits(delta), reloc_entry); if (INTEL_INFO(dev)->gen >= 8) { reloc_entry += 1; @@ -334,7 +338,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj, reloc_entry = reloc_page; } - iowrite32(0, reloc_entry); + iowrite32(upper_32_bits(delta), reloc_entry); } io_mapping_unmap_atomic(reloc_page); @@ -351,7 +355,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, struct drm_gem_object *target_obj; struct drm_i915_gem_object *target_i915_obj; struct i915_vma *target_vma; - uint32_t target_offset; + uint64_t target_offset; int ret; /* we've already hold a reference to all valid objects */ @@ -429,11 +433,10 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, if (obj->active && in_atomic()) return -EFAULT; - reloc->delta += target_offset; if (use_cpu_reloc(obj)) - ret = relocate_entry_cpu(obj, reloc); + ret = relocate_entry_cpu(obj, reloc, target_offset); else - ret = relocate_entry_gtt(obj, reloc); + ret = relocate_entry_gtt(obj, reloc, target_offset); if (ret) return ret; @@ -541,7 +544,7 @@ need_reloc_mappable(struct i915_vma *vma) static int i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool *need_reloc) { struct drm_i915_gem_object *obj = vma->obj; @@ -628,7 +631,7 @@ eb_vma_misplaced(struct i915_vma *vma, bool has_fenced_gpu_access) } static int -i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, +i915_gem_execbuffer_reserve(struct intel_engine_cs *ring, struct list_head *vmas, bool *need_relocs) { @@ -642,6 +645,8 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, if (list_empty(vmas)) return 0; + i915_gem_retire_requests_ring(ring); + vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm; INIT_LIST_HEAD(&ordered_vmas); @@ -727,7 +732,7 @@ static int i915_gem_execbuffer_relocate_slow(struct drm_device *dev, struct drm_i915_gem_execbuffer2 *args, struct drm_file *file, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, struct eb_vmas *eb, struct drm_i915_gem_exec_object2 *exec) { @@ -843,7 +848,7 @@ err: } static int -i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, +i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring, struct list_head *vmas) { struct i915_vma *vma; @@ -926,11 +931,11 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, return 0; } -static struct i915_hw_context * +static struct intel_context * i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, - struct intel_ring_buffer *ring, const u32 ctx_id) + struct intel_engine_cs *ring, const u32 ctx_id) { - struct i915_hw_context *ctx = NULL; + struct intel_context *ctx = NULL; struct i915_ctx_hang_stats *hs; if (ring->id != RCS && ctx_id != DEFAULT_CONTEXT_ID) @@ -951,7 +956,7 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, static void i915_gem_execbuffer_move_to_active(struct list_head *vmas, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct i915_vma *vma; @@ -974,6 +979,9 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas, if (i915_gem_obj_ggtt_bound(obj) && i915_gem_obj_to_ggtt(obj)->pin_count) intel_mark_fb_busy(obj, ring); + + /* update for the implicit flush after a batch */ + obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS; } trace_i915_gem_object_change_domain(obj, old_read, old_write); @@ -983,7 +991,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas, static void i915_gem_execbuffer_retire_commands(struct drm_device *dev, struct drm_file *file, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, struct drm_i915_gem_object *obj) { /* Unconditionally force add_request to emit a full flush. */ @@ -995,13 +1003,15 @@ i915_gem_execbuffer_retire_commands(struct drm_device *dev, static int i915_reset_gen7_sol_offsets(struct drm_device *dev, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = dev->dev_private; int ret, i; - if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS]) - return 0; + if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS]) { + DRM_DEBUG("sol reset is gen7/rcs only\n"); + return -EINVAL; + } ret = intel_ring_begin(ring, 4 * 3); if (ret) @@ -1018,6 +1028,37 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev, return 0; } +/** + * Find one BSD ring to dispatch the corresponding BSD command. + * The Ring ID is returned. + */ +static int gen8_dispatch_bsd_ring(struct drm_device *dev, + struct drm_file *file) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_file_private *file_priv = file->driver_priv; + + /* Check whether the file_priv is using one ring */ + if (file_priv->bsd_ring) + return file_priv->bsd_ring->id; + else { + /* If no, use the ping-pong mechanism to select one ring */ + int ring_id; + + mutex_lock(&dev->struct_mutex); + if (dev_priv->mm.bsd_ring_dispatch_index == 0) { + ring_id = VCS; + dev_priv->mm.bsd_ring_dispatch_index = 1; + } else { + ring_id = VCS2; + dev_priv->mm.bsd_ring_dispatch_index = 0; + } + file_priv->bsd_ring = &dev_priv->ring[ring_id]; + mutex_unlock(&dev->struct_mutex); + return ring_id; + } +} + static struct drm_i915_gem_object * eb_get_batch(struct eb_vmas *eb) { @@ -1047,11 +1088,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct eb_vmas *eb; struct drm_i915_gem_object *batch_obj; struct drm_clip_rect *cliprects = NULL; - struct intel_ring_buffer *ring; - struct i915_hw_context *ctx; + struct intel_engine_cs *ring; + struct intel_context *ctx; struct i915_address_space *vm; const u32 ctx_id = i915_execbuffer2_get_context_id(*args); - u32 exec_start = args->batch_start_offset, exec_len; + u64 exec_start = args->batch_start_offset, exec_len; u32 mask, flags; int ret, mode, i; bool need_relocs; @@ -1073,7 +1114,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (args->flags & I915_EXEC_IS_PINNED) flags |= I915_DISPATCH_PINNED; - if ((args->flags & I915_EXEC_RING_MASK) > I915_NUM_RINGS) { + if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) { DRM_DEBUG("execbuf with unknown ring: %d\n", (int)(args->flags & I915_EXEC_RING_MASK)); return -EINVAL; @@ -1081,7 +1122,14 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_DEFAULT) ring = &dev_priv->ring[RCS]; - else + else if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_BSD) { + if (HAS_BSD2(dev)) { + int ring_id; + ring_id = gen8_dispatch_bsd_ring(dev, file); + ring = &dev_priv->ring[ring_id]; + } else + ring = &dev_priv->ring[VCS]; + } else ring = &dev_priv->ring[(args->flags & I915_EXEC_RING_MASK) - 1]; if (!intel_ring_initialized(ring)) { @@ -1096,14 +1144,22 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, case I915_EXEC_CONSTANTS_REL_GENERAL: case I915_EXEC_CONSTANTS_ABSOLUTE: case I915_EXEC_CONSTANTS_REL_SURFACE: - if (ring == &dev_priv->ring[RCS] && - mode != dev_priv->relative_constants_mode) { - if (INTEL_INFO(dev)->gen < 4) + if (mode != 0 && ring != &dev_priv->ring[RCS]) { + DRM_DEBUG("non-0 rel constants mode on non-RCS\n"); + return -EINVAL; + } + + if (mode != dev_priv->relative_constants_mode) { + if (INTEL_INFO(dev)->gen < 4) { + DRM_DEBUG("no rel constants on pre-gen4\n"); return -EINVAL; + } if (INTEL_INFO(dev)->gen > 5 && - mode == I915_EXEC_CONSTANTS_REL_SURFACE) + mode == I915_EXEC_CONSTANTS_REL_SURFACE) { + DRM_DEBUG("rel surface constants mode invalid on gen5+\n"); return -EINVAL; + } /* The HW changed the meaning on this bit on gen6 */ if (INTEL_INFO(dev)->gen >= 6) @@ -1151,6 +1207,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, ret = -EFAULT; goto pre_mutex_err; } + } else { + if (args->DR4 == 0xffffffff) { + DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); + args->DR4 = 0; + } + + if (args->DR1 || args->DR4 || args->cliprects_ptr) { + DRM_DEBUG("0 cliprects but dirt in cliprects fields\n"); + return -EINVAL; + } } intel_runtime_pm_get(dev_priv); @@ -1170,7 +1236,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, mutex_unlock(&dev->struct_mutex); ret = PTR_ERR(ctx); goto pre_mutex_err; - } + } i915_gem_context_reference(ctx); @@ -1180,6 +1246,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, eb = eb_create(args); if (eb == NULL) { + i915_gem_context_unreference(ctx); mutex_unlock(&dev->struct_mutex); ret = -ENOMEM; goto pre_mutex_err; @@ -1430,6 +1497,11 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, return -EINVAL; } + if (args->rsvd2 != 0) { + DRM_DEBUG("dirty rvsd2 field\n"); + return -EINVAL; + } + exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); if (exec2_list == NULL) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 5deb22864c52..eec820aec022 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -30,7 +30,8 @@ #include "i915_trace.h" #include "intel_drv.h" -static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv); +static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv); +static void chv_setup_private_ppat(struct drm_i915_private *dev_priv); bool intel_enable_ppgtt(struct drm_device *dev, bool full) { @@ -65,59 +66,6 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt) return HAS_ALIASING_PPGTT(dev) ? 1 : 0; } -#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, @@ -131,10 +79,19 @@ static inline gen8_gtt_pte_t gen8_pte_encode(dma_addr_t addr, { gen8_gtt_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0; pte |= addr; - if (level != I915_CACHE_NONE) - pte |= PPAT_CACHED_INDEX; - else + + switch (level) { + case I915_CACHE_NONE: pte |= PPAT_UNCACHED_INDEX; + break; + case I915_CACHE_WT: + pte |= PPAT_DISPLAY_ELLC_INDEX; + break; + default: + pte |= PPAT_CACHED_INDEX; + break; + } + return pte; } @@ -197,9 +154,6 @@ 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) @@ -253,7 +207,7 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr, } /* Broadwell Page Directory Pointer Descriptors */ -static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry, +static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry, uint64_t val, bool synchronous) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -283,7 +237,7 @@ static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry, } static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { int i, ret; @@ -332,6 +286,8 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, num_entries--; } + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pt_vaddr, PAGE_SIZE); kunmap_atomic(pt_vaddr); pte = 0; @@ -368,6 +324,8 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, gen8_pte_encode(sg_page_iter_dma_address(&sg_iter), cache_level, true); if (++pte == GEN8_PTES_PER_PAGE) { + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pt_vaddr, PAGE_SIZE); kunmap_atomic(pt_vaddr); pt_vaddr = NULL; if (++pde == GEN8_PDES_PER_PAGE) { @@ -377,8 +335,11 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, pte = 0; } } - if (pt_vaddr) + if (pt_vaddr) { + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pt_vaddr, PAGE_SIZE); kunmap_atomic(pt_vaddr); + } } static void gen8_free_page_tables(struct page **pt_pages) @@ -641,6 +602,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr, I915_CACHE_LLC); } + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pd_vaddr, PAGE_SIZE); kunmap_atomic(pd_vaddr); } @@ -753,7 +716,7 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt) } static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { struct drm_device *dev = ppgtt->base.dev; @@ -797,7 +760,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt, } static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { struct drm_device *dev = ppgtt->base.dev; @@ -848,7 +811,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt, } static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { struct drm_device *dev = ppgtt->base.dev; @@ -869,7 +832,7 @@ static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt) { struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int j, ret; for_each_ring(ring, dev_priv, j) { @@ -899,7 +862,7 @@ static int gen7_ppgtt_enable(struct i915_hw_ppgtt *ppgtt) { struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t ecochk, ecobits; int i; @@ -938,7 +901,7 @@ static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt) { struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t ecochk, gab_ctl, ecobits; int i; @@ -1067,8 +1030,6 @@ 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; @@ -1084,8 +1045,7 @@ alloc: &ppgtt->node, GEN6_PD_SIZE, GEN6_PD_ALIGN, 0, 0, dev_priv->gtt.base.total, - DRM_MM_SEARCH_DEFAULT, - DRM_MM_CREATE_DEFAULT); + DRM_MM_TOPDOWN); if (ret == -ENOSPC && !retried) { ret = i915_gem_evict_something(dev, &dev_priv->gtt.base, GEN6_PD_SIZE, GEN6_PD_ALIGN, @@ -1311,7 +1271,7 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible) void i915_check_and_clear_faults(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; if (INTEL_INFO(dev)->gen < 6) @@ -1386,7 +1346,11 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev) if (INTEL_INFO(dev)->gen >= 8) { - gen8_setup_private_ppat(dev_priv); + if (IS_CHERRYVIEW(dev)) + chv_setup_private_ppat(dev_priv); + else + bdw_setup_private_ppat(dev_priv); + return; } @@ -1438,7 +1402,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, (gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry; int i = 0; struct sg_page_iter sg_iter; - dma_addr_t addr; + dma_addr_t addr = 0; for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) { addr = sg_dma_address(sg_iter.sg) + @@ -1811,9 +1775,27 @@ static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl) bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK; if (bdw_gmch_ctl) bdw_gmch_ctl = 1 << bdw_gmch_ctl; + +#ifdef CONFIG_X86_32 + /* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * PAGE_SIZE */ + if (bdw_gmch_ctl > 4) + bdw_gmch_ctl = 4; +#endif + return bdw_gmch_ctl << 20; } +static inline unsigned int chv_get_total_gtt_size(u16 gmch_ctrl) +{ + gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GGMS_MASK; + + if (gmch_ctrl) + return 1 << (20 + gmch_ctrl); + + return 0; +} + static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl) { snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT; @@ -1828,6 +1810,24 @@ static inline size_t gen8_get_stolen_size(u16 bdw_gmch_ctl) return bdw_gmch_ctl << 25; /* 32 MB units */ } +static size_t chv_get_stolen_size(u16 gmch_ctrl) +{ + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + /* + * 0x0 to 0x10: 32MB increments starting at 0MB + * 0x11 to 0x16: 4MB increments starting at 8MB + * 0x17 to 0x1d: 4MB increments start at 36MB + */ + if (gmch_ctrl < 0x11) + return gmch_ctrl << 25; + else if (gmch_ctrl < 0x17) + return (gmch_ctrl - 0x11 + 2) << 22; + else + return (gmch_ctrl - 0x17 + 9) << 22; +} + static int ggtt_probe_common(struct drm_device *dev, size_t gtt_size) { @@ -1858,19 +1858,8 @@ static int ggtt_probe_common(struct drm_device *dev, /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability * bits. When using advanced contexts each context stores its own PAT, but * 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)) +static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv) +{ uint64_t pat; pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) | /* for normal objects, no eLLC */ @@ -1888,6 +1877,33 @@ static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv) I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32); } +static void chv_setup_private_ppat(struct drm_i915_private *dev_priv) +{ + uint64_t pat; + + /* + * Map WB on BDW to snooped on CHV. + * + * Only the snoop bit has meaning for CHV, the rest is + * ignored. + * + * Note that the harware enforces snooping for all page + * table accesses. The snoop bit is actually ignored for + * PDEs. + */ + pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) | + GEN8_PPAT(1, 0) | + GEN8_PPAT(2, 0) | + GEN8_PPAT(3, 0) | + GEN8_PPAT(4, CHV_PPAT_SNOOP) | + GEN8_PPAT(5, CHV_PPAT_SNOOP) | + GEN8_PPAT(6, CHV_PPAT_SNOOP) | + GEN8_PPAT(7, CHV_PPAT_SNOOP); + + I915_WRITE(GEN8_PRIVATE_PAT, pat); + I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32); +} + static int gen8_gmch_probe(struct drm_device *dev, size_t *gtt_total, size_t *stolen, @@ -1908,12 +1924,20 @@ static int gen8_gmch_probe(struct drm_device *dev, pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); - *stolen = gen8_get_stolen_size(snb_gmch_ctl); + if (IS_CHERRYVIEW(dev)) { + *stolen = chv_get_stolen_size(snb_gmch_ctl); + gtt_size = chv_get_total_gtt_size(snb_gmch_ctl); + } else { + *stolen = gen8_get_stolen_size(snb_gmch_ctl); + gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl); + } - gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl); *gtt_total = (gtt_size / sizeof(gen8_gtt_pte_t)) << PAGE_SHIFT; - gen8_setup_private_ppat(dev_priv); + if (IS_CHERRYVIEW(dev)) + chv_setup_private_ppat(dev_priv); + else + bdw_setup_private_ppat(dev_priv); ret = ggtt_probe_common(dev, gtt_size); @@ -2043,6 +2067,10 @@ 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 /* * i915.enable_ppgtt is read-only, so do an early pass to validate the * user's requested state against the hardware/driver capabilities. We 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 000000000000..1b96a06be3cb --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -0,0 +1,284 @@ +/* + * 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 CHV_PPAT_SNOOP (1<<6) +#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 intel_context *ctx; + + int (*enable)(struct i915_hw_ppgtt *ppgtt); + int (*switch_mm)(struct i915_hw_ppgtt *ppgtt, + struct intel_engine_cs *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_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c new file mode 100644 index 000000000000..3521f998a178 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c @@ -0,0 +1,198 @@ +/* + * 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. + * + * Authors: + * Mika Kuoppala <mika.kuoppala@intel.com> + * + */ + +#include "i915_drv.h" +#include "intel_renderstate.h" + +struct i915_render_state { + struct drm_i915_gem_object *obj; + unsigned long ggtt_offset; + void *batch; + u32 size; + u32 len; +}; + +static struct i915_render_state *render_state_alloc(struct drm_device *dev) +{ + struct i915_render_state *so; + struct page *page; + int ret; + + so = kzalloc(sizeof(*so), GFP_KERNEL); + if (!so) + return ERR_PTR(-ENOMEM); + + so->obj = i915_gem_alloc_object(dev, 4096); + if (so->obj == NULL) { + ret = -ENOMEM; + goto free; + } + so->size = 4096; + + ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0); + if (ret) + goto free_gem; + + BUG_ON(so->obj->pages->nents != 1); + page = sg_page(so->obj->pages->sgl); + + so->batch = kmap(page); + if (!so->batch) { + ret = -ENOMEM; + goto unpin; + } + + so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj); + + return so; +unpin: + i915_gem_object_ggtt_unpin(so->obj); +free_gem: + drm_gem_object_unreference(&so->obj->base); +free: + kfree(so); + return ERR_PTR(ret); +} + +static void render_state_free(struct i915_render_state *so) +{ + kunmap(so->batch); + i915_gem_object_ggtt_unpin(so->obj); + drm_gem_object_unreference(&so->obj->base); + kfree(so); +} + +static const struct intel_renderstate_rodata * +render_state_get_rodata(struct drm_device *dev, const int gen) +{ + switch (gen) { + case 6: + return &gen6_null_state; + case 7: + return &gen7_null_state; + case 8: + return &gen8_null_state; + } + + return NULL; +} + +static int render_state_setup(const int gen, + const struct intel_renderstate_rodata *rodata, + struct i915_render_state *so) +{ + const u64 goffset = i915_gem_obj_ggtt_offset(so->obj); + u32 reloc_index = 0; + u32 * const d = so->batch; + unsigned int i = 0; + int ret; + + if (!rodata || rodata->batch_items * 4 > so->size) + return -EINVAL; + + ret = i915_gem_object_set_to_cpu_domain(so->obj, true); + if (ret) + return ret; + + while (i < rodata->batch_items) { + u32 s = rodata->batch[i]; + + if (reloc_index < rodata->reloc_items && + i * 4 == rodata->reloc[reloc_index]) { + + s += goffset & 0xffffffff; + + /* We keep batch offsets max 32bit */ + if (gen >= 8) { + if (i + 1 >= rodata->batch_items || + rodata->batch[i + 1] != 0) + return -EINVAL; + + d[i] = s; + i++; + s = (goffset & 0xffffffff00000000ull) >> 32; + } + + reloc_index++; + } + + d[i] = s; + i++; + } + + ret = i915_gem_object_set_to_gtt_domain(so->obj, false); + if (ret) + return ret; + + if (rodata->reloc_items != reloc_index) { + DRM_ERROR("not all relocs resolved, %d out of %d\n", + reloc_index, rodata->reloc_items); + return -EINVAL; + } + + so->len = rodata->batch_items * 4; + + return 0; +} + +int i915_gem_render_state_init(struct intel_engine_cs *ring) +{ + const int gen = INTEL_INFO(ring->dev)->gen; + struct i915_render_state *so; + const struct intel_renderstate_rodata *rodata; + int ret; + + if (WARN_ON(ring->id != RCS)) + return -ENOENT; + + rodata = render_state_get_rodata(ring->dev, gen); + if (rodata == NULL) + return 0; + + so = render_state_alloc(ring->dev); + if (IS_ERR(so)) + return PTR_ERR(so); + + ret = render_state_setup(gen, rodata, so); + if (ret) + goto out; + + ret = ring->dispatch_execbuffer(ring, + i915_gem_obj_ggtt_offset(so->obj), + so->len, + I915_DISPATCH_SECURE); + if (ret) + goto out; + + i915_vma_move_to_active(i915_gem_obj_to_ggtt(so->obj), ring); + + ret = __i915_add_request(ring, NULL, so->obj, NULL); + /* __i915_add_request moves object to inactive if it fails */ +out: + render_state_free(so); + return ret; +} diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c new file mode 100644 index 000000000000..21ea92886a56 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -0,0 +1,711 @@ +/* + * Copyright © 2012-2014 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. + * + */ + +#include "drmP.h" +#include "i915_drm.h" +#include "i915_drv.h" +#include "i915_trace.h" +#include "intel_drv.h" +#include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> +#include <linux/mempolicy.h> +#include <linux/swap.h> + +#if defined(CONFIG_MMU_NOTIFIER) +#include <linux/interval_tree.h> + +struct i915_mmu_notifier { + spinlock_t lock; + struct hlist_node node; + struct mmu_notifier mn; + struct rb_root objects; + struct drm_device *dev; + struct mm_struct *mm; + struct work_struct work; + unsigned long count; + unsigned long serial; +}; + +struct i915_mmu_object { + struct i915_mmu_notifier *mmu; + struct interval_tree_node it; + struct drm_i915_gem_object *obj; +}; + +static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + struct i915_mmu_notifier *mn = container_of(_mn, struct i915_mmu_notifier, mn); + struct interval_tree_node *it = NULL; + unsigned long serial = 0; + + end--; /* interval ranges are inclusive, but invalidate range is exclusive */ + while (start < end) { + struct drm_i915_gem_object *obj; + + obj = NULL; + spin_lock(&mn->lock); + if (serial == mn->serial) + it = interval_tree_iter_next(it, start, end); + else + it = interval_tree_iter_first(&mn->objects, start, end); + if (it != NULL) { + obj = container_of(it, struct i915_mmu_object, it)->obj; + drm_gem_object_reference(&obj->base); + serial = mn->serial; + } + spin_unlock(&mn->lock); + if (obj == NULL) + return; + + mutex_lock(&mn->dev->struct_mutex); + /* Cancel any active worker and force us to re-evaluate gup */ + obj->userptr.work = NULL; + + if (obj->pages != NULL) { + struct drm_i915_private *dev_priv = to_i915(mn->dev); + struct i915_vma *vma, *tmp; + bool was_interruptible; + + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; + + list_for_each_entry_safe(vma, tmp, &obj->vma_list, vma_link) { + int ret = i915_vma_unbind(vma); + WARN_ON(ret && ret != -EIO); + } + WARN_ON(i915_gem_object_put_pages(obj)); + + dev_priv->mm.interruptible = was_interruptible; + } + + start = obj->userptr.ptr + obj->base.size; + + drm_gem_object_unreference(&obj->base); + mutex_unlock(&mn->dev->struct_mutex); + } +} + +static const struct mmu_notifier_ops i915_gem_userptr_notifier = { + .invalidate_range_start = i915_gem_userptr_mn_invalidate_range_start, +}; + +static struct i915_mmu_notifier * +__i915_mmu_notifier_lookup(struct drm_device *dev, struct mm_struct *mm) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct i915_mmu_notifier *mmu; + + /* Protected by dev->struct_mutex */ + hash_for_each_possible(dev_priv->mmu_notifiers, mmu, node, (unsigned long)mm) + if (mmu->mm == mm) + return mmu; + + return NULL; +} + +static struct i915_mmu_notifier * +i915_mmu_notifier_get(struct drm_device *dev, struct mm_struct *mm) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct i915_mmu_notifier *mmu; + int ret; + + lockdep_assert_held(&dev->struct_mutex); + + mmu = __i915_mmu_notifier_lookup(dev, mm); + if (mmu) + return mmu; + + mmu = kmalloc(sizeof(*mmu), GFP_KERNEL); + if (mmu == NULL) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&mmu->lock); + mmu->dev = dev; + mmu->mn.ops = &i915_gem_userptr_notifier; + mmu->mm = mm; + mmu->objects = RB_ROOT; + mmu->count = 0; + mmu->serial = 0; + + /* Protected by mmap_sem (write-lock) */ + ret = __mmu_notifier_register(&mmu->mn, mm); + if (ret) { + kfree(mmu); + return ERR_PTR(ret); + } + + /* Protected by dev->struct_mutex */ + hash_add(dev_priv->mmu_notifiers, &mmu->node, (unsigned long)mm); + return mmu; +} + +static void +__i915_mmu_notifier_destroy_worker(struct work_struct *work) +{ + struct i915_mmu_notifier *mmu = container_of(work, typeof(*mmu), work); + mmu_notifier_unregister(&mmu->mn, mmu->mm); + kfree(mmu); +} + +static void +__i915_mmu_notifier_destroy(struct i915_mmu_notifier *mmu) +{ + lockdep_assert_held(&mmu->dev->struct_mutex); + + /* Protected by dev->struct_mutex */ + hash_del(&mmu->node); + + /* Our lock ordering is: mmap_sem, mmu_notifier_scru, struct_mutex. + * We enter the function holding struct_mutex, therefore we need + * to drop our mutex prior to calling mmu_notifier_unregister in + * order to prevent lock inversion (and system-wide deadlock) + * between the mmap_sem and struct-mutex. Hence we defer the + * unregistration to a workqueue where we hold no locks. + */ + INIT_WORK(&mmu->work, __i915_mmu_notifier_destroy_worker); + schedule_work(&mmu->work); +} + +static void __i915_mmu_notifier_update_serial(struct i915_mmu_notifier *mmu) +{ + if (++mmu->serial == 0) + mmu->serial = 1; +} + +static void +i915_mmu_notifier_del(struct i915_mmu_notifier *mmu, + struct i915_mmu_object *mn) +{ + lockdep_assert_held(&mmu->dev->struct_mutex); + + spin_lock(&mmu->lock); + interval_tree_remove(&mn->it, &mmu->objects); + __i915_mmu_notifier_update_serial(mmu); + spin_unlock(&mmu->lock); + + /* Protected against _add() by dev->struct_mutex */ + if (--mmu->count == 0) + __i915_mmu_notifier_destroy(mmu); +} + +static int +i915_mmu_notifier_add(struct i915_mmu_notifier *mmu, + struct i915_mmu_object *mn) +{ + struct interval_tree_node *it; + int ret; + + ret = i915_mutex_lock_interruptible(mmu->dev); + if (ret) + return ret; + + /* Make sure we drop the final active reference (and thereby + * remove the objects from the interval tree) before we do + * the check for overlapping objects. + */ + i915_gem_retire_requests(mmu->dev); + + /* Disallow overlapping userptr objects */ + spin_lock(&mmu->lock); + it = interval_tree_iter_first(&mmu->objects, + mn->it.start, mn->it.last); + if (it) { + struct drm_i915_gem_object *obj; + + /* We only need to check the first object in the range as it + * either has cancelled gup work queued and we need to + * return back to the user to give time for the gup-workers + * to flush their object references upon which the object will + * be removed from the interval-tree, or the the range is + * still in use by another client and the overlap is invalid. + */ + + obj = container_of(it, struct i915_mmu_object, it)->obj; + ret = obj->userptr.workers ? -EAGAIN : -EINVAL; + } else { + interval_tree_insert(&mn->it, &mmu->objects); + __i915_mmu_notifier_update_serial(mmu); + ret = 0; + } + spin_unlock(&mmu->lock); + mutex_unlock(&mmu->dev->struct_mutex); + + return ret; +} + +static void +i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj) +{ + struct i915_mmu_object *mn; + + mn = obj->userptr.mn; + if (mn == NULL) + return; + + i915_mmu_notifier_del(mn->mmu, mn); + obj->userptr.mn = NULL; +} + +static int +i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj, + unsigned flags) +{ + struct i915_mmu_notifier *mmu; + struct i915_mmu_object *mn; + int ret; + + if (flags & I915_USERPTR_UNSYNCHRONIZED) + return capable(CAP_SYS_ADMIN) ? 0 : -EPERM; + + down_write(&obj->userptr.mm->mmap_sem); + ret = i915_mutex_lock_interruptible(obj->base.dev); + if (ret == 0) { + mmu = i915_mmu_notifier_get(obj->base.dev, obj->userptr.mm); + if (!IS_ERR(mmu)) + mmu->count++; /* preemptive add to act as a refcount */ + else + ret = PTR_ERR(mmu); + mutex_unlock(&obj->base.dev->struct_mutex); + } + up_write(&obj->userptr.mm->mmap_sem); + if (ret) + return ret; + + mn = kzalloc(sizeof(*mn), GFP_KERNEL); + if (mn == NULL) { + ret = -ENOMEM; + goto destroy_mmu; + } + + mn->mmu = mmu; + mn->it.start = obj->userptr.ptr; + mn->it.last = mn->it.start + obj->base.size - 1; + mn->obj = obj; + + ret = i915_mmu_notifier_add(mmu, mn); + if (ret) + goto free_mn; + + obj->userptr.mn = mn; + return 0; + +free_mn: + kfree(mn); +destroy_mmu: + mutex_lock(&obj->base.dev->struct_mutex); + if (--mmu->count == 0) + __i915_mmu_notifier_destroy(mmu); + mutex_unlock(&obj->base.dev->struct_mutex); + return ret; +} + +#else + +static void +i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj) +{ +} + +static int +i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj, + unsigned flags) +{ + if ((flags & I915_USERPTR_UNSYNCHRONIZED) == 0) + return -ENODEV; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return 0; +} +#endif + +struct get_pages_work { + struct work_struct work; + struct drm_i915_gem_object *obj; + struct task_struct *task; +}; + + +#if IS_ENABLED(CONFIG_SWIOTLB) +#define swiotlb_active() swiotlb_nr_tbl() +#else +#define swiotlb_active() 0 +#endif + +static int +st_set_pages(struct sg_table **st, struct page **pvec, int num_pages) +{ + struct scatterlist *sg; + int ret, n; + + *st = kmalloc(sizeof(**st), GFP_KERNEL); + if (*st == NULL) + return -ENOMEM; + + if (swiotlb_active()) { + ret = sg_alloc_table(*st, num_pages, GFP_KERNEL); + if (ret) + goto err; + + for_each_sg((*st)->sgl, sg, num_pages, n) + sg_set_page(sg, pvec[n], PAGE_SIZE, 0); + } else { + ret = sg_alloc_table_from_pages(*st, pvec, num_pages, + 0, num_pages << PAGE_SHIFT, + GFP_KERNEL); + if (ret) + goto err; + } + + return 0; + +err: + kfree(*st); + *st = NULL; + return ret; +} + +static void +__i915_gem_userptr_get_pages_worker(struct work_struct *_work) +{ + struct get_pages_work *work = container_of(_work, typeof(*work), work); + struct drm_i915_gem_object *obj = work->obj; + struct drm_device *dev = obj->base.dev; + const int num_pages = obj->base.size >> PAGE_SHIFT; + struct page **pvec; + int pinned, ret; + + ret = -ENOMEM; + pinned = 0; + + pvec = kmalloc(num_pages*sizeof(struct page *), + GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + if (pvec == NULL) + pvec = drm_malloc_ab(num_pages, sizeof(struct page *)); + if (pvec != NULL) { + struct mm_struct *mm = obj->userptr.mm; + + down_read(&mm->mmap_sem); + while (pinned < num_pages) { + ret = get_user_pages(work->task, mm, + obj->userptr.ptr + pinned * PAGE_SIZE, + num_pages - pinned, + !obj->userptr.read_only, 0, + pvec + pinned, NULL); + if (ret < 0) + break; + + pinned += ret; + } + up_read(&mm->mmap_sem); + } + + mutex_lock(&dev->struct_mutex); + if (obj->userptr.work != &work->work) { + ret = 0; + } else if (pinned == num_pages) { + ret = st_set_pages(&obj->pages, pvec, num_pages); + if (ret == 0) { + list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list); + pinned = 0; + } + } + + obj->userptr.work = ERR_PTR(ret); + obj->userptr.workers--; + drm_gem_object_unreference(&obj->base); + mutex_unlock(&dev->struct_mutex); + + release_pages(pvec, pinned, 0); + drm_free_large(pvec); + + put_task_struct(work->task); + kfree(work); +} + +static int +i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) +{ + const int num_pages = obj->base.size >> PAGE_SHIFT; + struct page **pvec; + int pinned, ret; + + /* If userspace should engineer that these pages are replaced in + * the vma between us binding this page into the GTT and completion + * of rendering... Their loss. If they change the mapping of their + * pages they need to create a new bo to point to the new vma. + * + * However, that still leaves open the possibility of the vma + * being copied upon fork. Which falls under the same userspace + * synchronisation issue as a regular bo, except that this time + * the process may not be expecting that a particular piece of + * memory is tied to the GPU. + * + * Fortunately, we can hook into the mmu_notifier in order to + * discard the page references prior to anything nasty happening + * to the vma (discard or cloning) which should prevent the more + * egregious cases from causing harm. + */ + + pvec = NULL; + pinned = 0; + if (obj->userptr.mm == current->mm) { + pvec = kmalloc(num_pages*sizeof(struct page *), + GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + if (pvec == NULL) { + pvec = drm_malloc_ab(num_pages, sizeof(struct page *)); + if (pvec == NULL) + return -ENOMEM; + } + + pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages, + !obj->userptr.read_only, pvec); + } + if (pinned < num_pages) { + if (pinned < 0) { + ret = pinned; + pinned = 0; + } else { + /* Spawn a worker so that we can acquire the + * user pages without holding our mutex. Access + * to the user pages requires mmap_sem, and we have + * a strict lock ordering of mmap_sem, struct_mutex - + * we already hold struct_mutex here and so cannot + * call gup without encountering a lock inversion. + * + * Userspace will keep on repeating the operation + * (thanks to EAGAIN) until either we hit the fast + * path or the worker completes. If the worker is + * cancelled or superseded, the task is still run + * but the results ignored. (This leads to + * complications that we may have a stray object + * refcount that we need to be wary of when + * checking for existing objects during creation.) + * If the worker encounters an error, it reports + * that error back to this function through + * obj->userptr.work = ERR_PTR. + */ + ret = -EAGAIN; + if (obj->userptr.work == NULL && + obj->userptr.workers < I915_GEM_USERPTR_MAX_WORKERS) { + struct get_pages_work *work; + + work = kmalloc(sizeof(*work), GFP_KERNEL); + if (work != NULL) { + obj->userptr.work = &work->work; + obj->userptr.workers++; + + work->obj = obj; + drm_gem_object_reference(&obj->base); + + work->task = current; + get_task_struct(work->task); + + INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker); + schedule_work(&work->work); + } else + ret = -ENOMEM; + } else { + if (IS_ERR(obj->userptr.work)) { + ret = PTR_ERR(obj->userptr.work); + obj->userptr.work = NULL; + } + } + } + } else { + ret = st_set_pages(&obj->pages, pvec, num_pages); + if (ret == 0) { + obj->userptr.work = NULL; + pinned = 0; + } + } + + release_pages(pvec, pinned, 0); + drm_free_large(pvec); + return ret; +} + +static void +i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj) +{ + struct scatterlist *sg; + int i; + + BUG_ON(obj->userptr.work != NULL); + + if (obj->madv != I915_MADV_WILLNEED) + obj->dirty = 0; + + for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) { + struct page *page = sg_page(sg); + + if (obj->dirty) + set_page_dirty(page); + + mark_page_accessed(page); + page_cache_release(page); + } + obj->dirty = 0; + + sg_free_table(obj->pages); + kfree(obj->pages); +} + +static void +i915_gem_userptr_release(struct drm_i915_gem_object *obj) +{ + i915_gem_userptr_release__mmu_notifier(obj); + + if (obj->userptr.mm) { + mmput(obj->userptr.mm); + obj->userptr.mm = NULL; + } +} + +static int +i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj) +{ + if (obj->userptr.mn) + return 0; + + return i915_gem_userptr_init__mmu_notifier(obj, 0); +} + +static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = { + .dmabuf_export = i915_gem_userptr_dmabuf_export, + .get_pages = i915_gem_userptr_get_pages, + .put_pages = i915_gem_userptr_put_pages, + .release = i915_gem_userptr_release, +}; + +/** + * Creates a new mm object that wraps some normal memory from the process + * context - user memory. + * + * We impose several restrictions upon the memory being mapped + * into the GPU. + * 1. It must be page aligned (both start/end addresses, i.e ptr and size). + * 2. It cannot overlap any other userptr object in the same address space. + * 3. It must be normal system memory, not a pointer into another map of IO + * space (e.g. it must not be a GTT mmapping of another object). + * 4. We only allow a bo as large as we could in theory map into the GTT, + * that is we limit the size to the total size of the GTT. + * 5. The bo is marked as being snoopable. The backing pages are left + * accessible directly by the CPU, but reads and writes by the GPU may + * incur the cost of a snoop (unless you have an LLC architecture). + * + * Synchronisation between multiple users and the GPU is left to userspace + * through the normal set-domain-ioctl. The kernel will enforce that the + * GPU relinquishes the VMA before it is returned back to the system + * i.e. upon free(), munmap() or process termination. However, the userspace + * malloc() library may not immediately relinquish the VMA after free() and + * instead reuse it whilst the GPU is still reading and writing to the VMA. + * Caveat emptor. + * + * Also note, that the object created here is not currently a "first class" + * object, in that several ioctls are banned. These are the CPU access + * ioctls: mmap(), pwrite and pread. In practice, you are expected to use + * direct access via your pointer rather than use those ioctls. + * + * If you think this is a good interface to use to pass GPU memory between + * drivers, please use dma-buf instead. In fact, wherever possible use + * dma-buf instead. + */ +int +i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_userptr *args = data; + struct drm_i915_gem_object *obj; + int ret; + u32 handle; + + if (args->flags & ~(I915_USERPTR_READ_ONLY | + I915_USERPTR_UNSYNCHRONIZED)) + return -EINVAL; + + if (offset_in_page(args->user_ptr | args->user_size)) + return -EINVAL; + + if (args->user_size > dev_priv->gtt.base.total) + return -E2BIG; + + if (!access_ok(args->flags & I915_USERPTR_READ_ONLY ? VERIFY_READ : VERIFY_WRITE, + (char __user *)(unsigned long)args->user_ptr, args->user_size)) + return -EFAULT; + + if (args->flags & I915_USERPTR_READ_ONLY) { + /* On almost all of the current hw, we cannot tell the GPU that a + * page is readonly, so this is just a placeholder in the uAPI. + */ + return -ENODEV; + } + + /* Allocate the new object */ + obj = i915_gem_object_alloc(dev); + if (obj == NULL) + return -ENOMEM; + + drm_gem_private_object_init(dev, &obj->base, args->user_size); + i915_gem_object_init(obj, &i915_gem_userptr_ops); + obj->cache_level = I915_CACHE_LLC; + obj->base.write_domain = I915_GEM_DOMAIN_CPU; + obj->base.read_domains = I915_GEM_DOMAIN_CPU; + + obj->userptr.ptr = args->user_ptr; + obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY); + + /* And keep a pointer to the current->mm for resolving the user pages + * at binding. This means that we need to hook into the mmu_notifier + * in order to detect if the mmu is destroyed. + */ + ret = -ENOMEM; + if ((obj->userptr.mm = get_task_mm(current))) + ret = i915_gem_userptr_init__mmu_notifier(obj, args->flags); + if (ret == 0) + ret = drm_gem_handle_create(file, &obj->base, &handle); + + /* drop reference from allocate - handle holds it now */ + drm_gem_object_unreference_unlocked(&obj->base); + if (ret) + return ret; + + args->handle = handle; + return 0; +} + +int +i915_gem_init_userptr(struct drm_device *dev) +{ +#if defined(CONFIG_MMU_NOTIFIER) + struct drm_i915_private *dev_priv = to_i915(dev); + hash_init(dev_priv->mmu_notifiers); +#endif + return 0; +} diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 12f1d43b2d68..87ec60e181a7 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -42,6 +42,7 @@ static const char *ring_str(int ring) case VCS: return "bsd"; case BCS: return "blt"; case VECS: return "vebox"; + case VCS2: return "bsd2"; default: return ""; } } @@ -204,6 +205,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m, err_puts(m, tiling_flag(err->tiling)); err_puts(m, dirty_flag(err->dirty)); err_puts(m, purgeable_flag(err->purgeable)); + err_puts(m, err->userptr ? " userptr" : ""); err_puts(m, err->ring != -1 ? " " : ""); err_puts(m, ring_str(err->ring)); err_puts(m, i915_cache_level_str(err->cache_level)); @@ -257,7 +259,8 @@ 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); @@ -452,16 +455,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, err_printf(m, "%s --- HW Context = 0x%08x\n", dev_priv->ring[i].name, obj->gtt_offset); - offset = 0; - for (elt = 0; elt < PAGE_SIZE/16; elt += 4) { - err_printf(m, "[%04x] %08x %08x %08x %08x\n", - offset, - obj->pages[0][elt], - obj->pages[0][elt+1], - obj->pages[0][elt+2], - obj->pages[0][elt+3]); - offset += 16; - } + print_error_obj(m, obj); } } @@ -648,6 +642,7 @@ static void capture_bo(struct drm_i915_error_buffer *err, err->tiling = obj->tiling_mode; err->dirty = obj->dirty; err->purgeable = obj->madv != I915_MADV_WILLNEED; + err->userptr = obj->userptr.mm != NULL; err->ring = obj->ring ? obj->ring->id : -1; err->cache_level = obj->cache_level; } @@ -752,7 +747,7 @@ static void i915_gem_record_fences(struct drm_device *dev, } static void i915_record_ring_state(struct drm_device *dev, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, struct drm_i915_error_ring *ering) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -764,14 +759,14 @@ static void i915_record_ring_state(struct drm_device *dev, = I915_READ(RING_SYNC_0(ring->mmio_base)); ering->semaphore_mboxes[1] = I915_READ(RING_SYNC_1(ring->mmio_base)); - ering->semaphore_seqno[0] = ring->sync_seqno[0]; - ering->semaphore_seqno[1] = ring->sync_seqno[1]; + ering->semaphore_seqno[0] = ring->semaphore.sync_seqno[0]; + ering->semaphore_seqno[1] = ring->semaphore.sync_seqno[1]; } if (HAS_VEBOX(dev)) { ering->semaphore_mboxes[2] = I915_READ(RING_SYNC_2(ring->mmio_base)); - ering->semaphore_seqno[2] = ring->sync_seqno[2]; + ering->semaphore_seqno[2] = ring->semaphore.sync_seqno[2]; } if (INTEL_INFO(dev)->gen >= 4) { @@ -781,8 +776,10 @@ 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); @@ -828,8 +825,8 @@ static void i915_record_ring_state(struct drm_device *dev, ering->hws = I915_READ(mmio); } - ering->cpu_ring_head = ring->head; - ering->cpu_ring_tail = ring->tail; + ering->cpu_ring_head = ring->buffer->head; + ering->cpu_ring_tail = ring->buffer->tail; ering->hangcheck_score = ring->hangcheck.score; ering->hangcheck_action = ring->hangcheck.action; @@ -862,7 +859,7 @@ static void i915_record_ring_state(struct drm_device *dev, } -static void i915_gem_record_active_context(struct intel_ring_buffer *ring, +static void i915_gem_record_active_context(struct intel_engine_cs *ring, struct drm_i915_error_state *error, struct drm_i915_error_ring *ering) { @@ -875,10 +872,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring, list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) { - ering->ctx = i915_error_object_create_sized(dev_priv, - obj, - &dev_priv->gtt.base, - 1); + ering->ctx = i915_error_ggtt_object_create(dev_priv, obj); break; } } @@ -892,7 +886,7 @@ static void i915_gem_record_rings(struct drm_device *dev, int i, count; for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_ring_buffer *ring = &dev_priv->ring[i]; + struct intel_engine_cs *ring = &dev_priv->ring[i]; if (ring->dev == NULL) continue; @@ -936,7 +930,7 @@ static void i915_gem_record_rings(struct drm_device *dev, } error->ring[i].ringbuffer = - i915_error_ggtt_object_create(dev_priv, ring->obj); + i915_error_ggtt_object_create(dev_priv, ring->buffer->obj); if (ring->status_page.obj) error->ring[i].hws_page = @@ -1037,7 +1031,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, struct drm_i915_error_state *error) { struct drm_device *dev = dev_priv->dev; - int pipe; /* General organization * 1. Registers specific to a single generation @@ -1062,9 +1055,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, error->gfx_mode = I915_READ(GFX_MODE); } - if (IS_GEN2(dev)) - error->ier = I915_READ16(IER); - /* 2: Registers which belong to multiple generations */ if (INTEL_INFO(dev)->gen >= 7) error->forcewake = I915_READ(FORCEWAKE_MT); @@ -1088,9 +1078,10 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, if (HAS_PCH_SPLIT(dev)) error->ier = I915_READ(DEIER) | I915_READ(GTIER); else { - error->ier = I915_READ(IER); - for_each_pipe(pipe) - error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); + if (IS_GEN2(dev)) + error->ier = I915_READ16(IER); + else + error->ier = I915_READ(IER); } /* 4: Everything else */ diff --git a/drivers/gpu/drm/i915/i915_ioc32.c b/drivers/gpu/drm/i915/i915_ioc32.c index 3c59584161c2..2e0613e26251 100644 --- a/drivers/gpu/drm/i915/i915_ioc32.c +++ b/drivers/gpu/drm/i915/i915_ioc32.c @@ -208,7 +208,7 @@ long i915_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (nr < DRM_COMMAND_BASE) return drm_compat_ioctl(filp, cmd, arg); - if (nr < DRM_COMMAND_BASE + DRM_ARRAY_SIZE(i915_compat_ioctls)) + if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(i915_compat_ioctls)) fn = i915_compat_ioctls[nr - DRM_COMMAND_BASE]; if (fn != NULL) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0b99de95593b..6f8017a7e937 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; @@ -214,6 +248,46 @@ static bool ivb_can_enable_err_int(struct drm_device *dev) return true; } +/** + * bdw_update_pm_irq - update GT interrupt 2 + * @dev_priv: driver private + * @interrupt_mask: mask of interrupt bits to update + * @enabled_irq_mask: mask of interrupt bits to enable + * + * Copied from the snb function, updated with relevant register offsets + */ +static void bdw_update_pm_irq(struct drm_i915_private *dev_priv, + uint32_t interrupt_mask, + uint32_t enabled_irq_mask) +{ + uint32_t new_val; + + assert_spin_locked(&dev_priv->irq_lock); + + if (WARN_ON(dev_priv->pm.irqs_disabled)) + return; + + new_val = dev_priv->pm_irq_mask; + new_val &= ~interrupt_mask; + new_val |= (~enabled_irq_mask & interrupt_mask); + + if (new_val != dev_priv->pm_irq_mask) { + dev_priv->pm_irq_mask = new_val; + I915_WRITE(GEN8_GT_IMR(2), dev_priv->pm_irq_mask); + POSTING_READ(GEN8_GT_IMR(2)); + } +} + +void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask) +{ + bdw_update_pm_irq(dev_priv, mask, mask); +} + +void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask) +{ + bdw_update_pm_irq(dev_priv, mask, 0); +} + static bool cpt_can_enable_serr_int(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -232,16 +306,51 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev) return true; } -static void i9xx_clear_fifo_underrun(struct drm_device *dev, enum pipe pipe) +void i9xx_check_fifo_underruns(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *crtc; + unsigned long flags; + + spin_lock_irqsave(&dev_priv->irq_lock, flags); + + for_each_intel_crtc(dev, crtc) { + u32 reg = PIPESTAT(crtc->pipe); + u32 pipestat; + + if (crtc->cpu_fifo_underrun_disabled) + continue; + + pipestat = I915_READ(reg) & 0xffff0000; + if ((pipestat & PIPE_FIFO_UNDERRUN_STATUS) == 0) + continue; + + I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS); + POSTING_READ(reg); + + DRM_ERROR("pipe %c underrun\n", pipe_name(crtc->pipe)); + } + + spin_unlock_irqrestore(&dev_priv->irq_lock, flags); +} + +static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev, + enum pipe pipe, + bool enable, bool old) { struct drm_i915_private *dev_priv = dev->dev_private; u32 reg = PIPESTAT(pipe); - u32 pipestat = I915_READ(reg) & 0x7fff0000; + u32 pipestat = I915_READ(reg) & 0xffff0000; assert_spin_locked(&dev_priv->irq_lock); - I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS); - POSTING_READ(reg); + if (enable) { + I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS); + POSTING_READ(reg); + } else { + if (old && pipestat & PIPE_FIFO_UNDERRUN_STATUS) + DRM_ERROR("pipe %c underrun\n", pipe_name(pipe)); + } } static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev, @@ -258,7 +367,8 @@ static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev, } static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev, - enum pipe pipe, bool enable) + enum pipe pipe, + bool enable, bool old) { struct drm_i915_private *dev_priv = dev->dev_private; if (enable) { @@ -269,15 +379,12 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev, ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB); } else { - bool was_enabled = !(I915_READ(DEIMR) & DE_ERR_INT_IVB); - - /* Change the state _after_ we've read out the current one. */ ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB); - if (!was_enabled && - (I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe))) { - DRM_DEBUG_KMS("uncleared fifo underrun on pipe %c\n", - pipe_name(pipe)); + if (old && + I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe)) { + DRM_ERROR("uncleared fifo underrun on pipe %c\n", + pipe_name(pipe)); } } } @@ -313,14 +420,8 @@ 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); @@ -346,7 +447,7 @@ static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, enum transcoder pch_transcoder, - bool enable) + bool enable, bool old) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -359,16 +460,12 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, ibx_enable_display_interrupt(dev_priv, SDE_ERROR_CPT); } else { - uint32_t tmp = I915_READ(SERR_INT); - bool was_enabled = !(I915_READ(SDEIMR) & SDE_ERROR_CPT); - - /* Change the state _after_ we've read out the current one. */ ibx_disable_display_interrupt(dev_priv, SDE_ERROR_CPT); - if (!was_enabled && - (tmp & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder))) { - DRM_DEBUG_KMS("uncleared pch fifo underrun on pch transcoder %c\n", - transcoder_name(pch_transcoder)); + if (old && I915_READ(SERR_INT) & + SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder)) { + DRM_ERROR("uncleared pch fifo underrun on pch transcoder %c\n", + transcoder_name(pch_transcoder)); } } } @@ -387,34 +484,29 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, * * Returns the previous state of underrun reporting. */ -bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, - enum pipe pipe, bool enable) +static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, + enum pipe pipe, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - bool ret; + bool old; assert_spin_locked(&dev_priv->irq_lock); - ret = !intel_crtc->cpu_fifo_underrun_disabled; - - if (enable == ret) - goto done; - + old = !intel_crtc->cpu_fifo_underrun_disabled; intel_crtc->cpu_fifo_underrun_disabled = !enable; - if (enable && (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev))) - i9xx_clear_fifo_underrun(dev, pipe); + if (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev)) + i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old); else if (IS_GEN5(dev) || IS_GEN6(dev)) ironlake_set_fifo_underrun_reporting(dev, pipe, enable); else if (IS_GEN7(dev)) - ivybridge_set_fifo_underrun_reporting(dev, pipe, enable); + ivybridge_set_fifo_underrun_reporting(dev, pipe, enable, old); else if (IS_GEN8(dev)) broadwell_set_fifo_underrun_reporting(dev, pipe, enable); -done: - return ret; + return old; } bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, @@ -463,7 +555,7 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pch_transcoder]; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); unsigned long flags; - bool ret; + bool old; /* * NOTE: Pre-LPT has a fixed cpu pipe -> pch transcoder mapping, but LPT @@ -476,21 +568,16 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, spin_lock_irqsave(&dev_priv->irq_lock, flags); - ret = !intel_crtc->pch_fifo_underrun_disabled; - - if (enable == ret) - goto done; - + old = !intel_crtc->pch_fifo_underrun_disabled; intel_crtc->pch_fifo_underrun_disabled = !enable; if (HAS_PCH_IBX(dev)) ibx_set_fifo_underrun_reporting(dev, pch_transcoder, enable); else - cpt_set_fifo_underrun_reporting(dev, pch_transcoder, enable); + cpt_set_fifo_underrun_reporting(dev, pch_transcoder, enable, old); -done: spin_unlock_irqrestore(&dev_priv->irq_lock, flags); - return ret; + return old; } @@ -503,8 +590,10 @@ __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 +616,10 @@ __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) @@ -546,11 +637,17 @@ static u32 vlv_get_pipestat_enable_mask(struct drm_device *dev, u32 status_mask) u32 enable_mask = status_mask << 16; /* - * On pipe A we don't support the PSR interrupt yet, on pipe B the - * same bit MBZ. + * On pipe A we don't support the PSR interrupt yet, + * on pipe B and C the same bit MBZ. */ if (WARN_ON_ONCE(status_mask & PIPE_A_PSR_STATUS_VLV)) return 0; + /* + * On pipe B and C we don't support the PSR interrupt yet, on pipe + * A the same bit is for perf counters which we don't use either. + */ + if (WARN_ON_ONCE(status_mask & PIPE_B_PSR_STATUS_VLV)) + return 0; enable_mask &= ~(PIPE_FIFO_UNDERRUN_STATUS | SPRITE0_FLIP_DONE_INT_EN_VLV | @@ -637,6 +734,56 @@ i915_pipe_enabled(struct drm_device *dev, int pipe) } } +/* + * This timing diagram depicts the video signal in and + * around the vertical blanking period. + * + * Assumptions about the fictitious mode used in this example: + * vblank_start >= 3 + * vsync_start = vblank_start + 1 + * vsync_end = vblank_start + 2 + * vtotal = vblank_start + 3 + * + * start of vblank: + * latch double buffered registers + * increment frame counter (ctg+) + * generate start of vblank interrupt (gen4+) + * | + * | frame start: + * | generate frame start interrupt (aka. vblank interrupt) (gmch) + * | may be shifted forward 1-3 extra lines via PIPECONF + * | | + * | | start of vsync: + * | | generate vsync interrupt + * | | | + * ___xxxx___ ___xxxx___ ___xxxx___ ___xxxx___ ___xxxx___ ___xxxx + * . \hs/ . \hs/ \hs/ \hs/ . \hs/ + * ----va---> <-----------------vb--------------------> <--------va------------- + * | | <----vs-----> | + * -vbs-----> <---vbs+1---> <---vbs+2---> <-----0-----> <-----1-----> <-----2--- (scanline counter gen2) + * -vbs-2---> <---vbs-1---> <---vbs-----> <---vbs+1---> <---vbs+2---> <-----0--- (scanline counter gen3+) + * -vbs-2---> <---vbs-2---> <---vbs-1---> <---vbs-----> <---vbs+1---> <---vbs+2- (scanline counter hsw+ hdmi) + * | | | + * last visible pixel first visible pixel + * | increment frame counter (gen3/4) + * pixel counter = vblank_start * htotal pixel counter = 0 (gen3/4) + * + * x = horizontal active + * _ = horizontal blanking + * hs = horizontal sync + * va = vertical active + * vb = vertical blanking + * vs = vertical sync + * vbs = vblank_start (number) + * + * Summary: + * - most events happen at the start of horizontal sync + * - frame start happens at the start of horizontal blank, 1-4 lines + * (depending on PIPECONF settings) after the start of vblank + * - gen3/4 pixel and frame counter are synchronized with the start + * of horizontal active on the first line of vertical active + */ + static u32 i8xx_get_vblank_counter(struct drm_device *dev, int pipe) { /* Gen2 doesn't have a hardware frame counter */ @@ -651,7 +798,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) struct drm_i915_private *dev_priv = dev->dev_private; unsigned long high_frame; unsigned long low_frame; - u32 high1, high2, low, pixel, vbl_start; + u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal; if (!i915_pipe_enabled(dev, pipe)) { DRM_DEBUG_DRIVER("trying to get vblank count for disabled " @@ -665,17 +812,28 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) const struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode; - vbl_start = mode->crtc_vblank_start * mode->crtc_htotal; + htotal = mode->crtc_htotal; + hsync_start = mode->crtc_hsync_start; + vbl_start = mode->crtc_vblank_start; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vbl_start = DIV_ROUND_UP(vbl_start, 2); } else { enum transcoder cpu_transcoder = (enum transcoder) pipe; - u32 htotal; htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1; + hsync_start = (I915_READ(HSYNC(cpu_transcoder)) & 0x1fff) + 1; vbl_start = (I915_READ(VBLANK(cpu_transcoder)) & 0x1fff) + 1; - - vbl_start *= htotal; + if ((I915_READ(PIPECONF(cpu_transcoder)) & + PIPECONF_INTERLACE_MASK) != PIPECONF_PROGRESSIVE) + vbl_start = DIV_ROUND_UP(vbl_start, 2); } + /* Convert to pixel count */ + vbl_start *= htotal; + + /* Start of vblank event occurs at start of hsync */ + vbl_start -= htotal - hsync_start; + high_frame = PIPEFRAME(pipe); low_frame = PIPEFRAMEPIXEL(pipe); @@ -719,24 +877,28 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) /* raw reads, only for fast reads of display block, no need for forcewake etc. */ #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__)) -static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe) +static int __intel_get_crtc_scanline(struct intel_crtc *crtc) { + struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t status; - int reg; + const struct drm_display_mode *mode = &crtc->config.adjusted_mode; + enum pipe pipe = crtc->pipe; + int position, vtotal; - if (INTEL_INFO(dev)->gen >= 8) { - status = GEN8_PIPE_VBLANK; - reg = GEN8_DE_PIPE_ISR(pipe); - } else if (INTEL_INFO(dev)->gen >= 7) { - status = DE_PIPE_VBLANK_IVB(pipe); - reg = DEISR; - } else { - status = DE_PIPE_VBLANK(pipe); - reg = DEISR; - } + vtotal = mode->crtc_vtotal; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vtotal /= 2; + + if (IS_GEN2(dev)) + position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2; + else + position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3; - return __raw_i915_read32(dev_priv, reg) & status; + /* + * See update_scanline_offset() for the details on the + * scanline_offset adjustment. + */ + return (position + crtc->scanline_offset) % vtotal; } static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, @@ -748,7 +910,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, struct intel_crtc *intel_crtc = to_intel_crtc(crtc); const struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode; int position; - int vbl_start, vbl_end, htotal, vtotal; + int vbl_start, vbl_end, hsync_start, htotal, vtotal; bool in_vbl = true; int ret = 0; unsigned long irqflags; @@ -760,6 +922,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, } htotal = mode->crtc_htotal; + hsync_start = mode->crtc_hsync_start; vtotal = mode->crtc_vtotal; vbl_start = mode->crtc_vblank_start; vbl_end = mode->crtc_vblank_end; @@ -778,7 +941,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, * following code must not block on uncore.lock. */ spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ /* Get optional system timestamp before query. */ @@ -789,68 +952,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, /* No obvious pixelcount register. Only query vertical * scanout position from Display scan line register. */ - if (IS_GEN2(dev)) - position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2; - else - position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3; - - if (HAS_DDI(dev)) { - /* - * On HSW HDMI outputs there seems to be a 2 line - * difference, whereas eDP has the normal 1 line - * difference that earlier platforms have. External - * DP is unknown. For now just check for the 2 line - * difference case on all output types on HSW+. - * - * This might misinterpret the scanline counter being - * one line too far along on eDP, but that's less - * dangerous than the alternative since that would lead - * the vblank timestamp code astray when it sees a - * scanline count before vblank_start during a vblank - * interrupt. - */ - in_vbl = ilk_pipe_in_vblank_locked(dev, pipe); - if ((in_vbl && (position == vbl_start - 2 || - position == vbl_start - 1)) || - (!in_vbl && (position == vbl_end - 2 || - position == vbl_end - 1))) - position = (position + 2) % vtotal; - } else if (HAS_PCH_SPLIT(dev)) { - /* - * The scanline counter increments at the leading edge - * of hsync, ie. it completely misses the active portion - * of the line. Fix up the counter at both edges of vblank - * to get a more accurate picture whether we're in vblank - * or not. - */ - in_vbl = ilk_pipe_in_vblank_locked(dev, pipe); - if ((in_vbl && position == vbl_start - 1) || - (!in_vbl && position == vbl_end - 1)) - position = (position + 1) % vtotal; - } else { - /* - * ISR vblank status bits don't work the way we'd want - * them to work on non-PCH platforms (for - * ilk_pipe_in_vblank_locked()), and there doesn't - * appear any other way to determine if we're currently - * in vblank. - * - * Instead let's assume that we're already in vblank if - * we got called from the vblank interrupt and the - * scanline counter value indicates that we're on the - * line just prior to vblank start. This should result - * in the correct answer, unless the vblank interrupt - * delivery really got delayed for almost exactly one - * full frame/field. - */ - if (flags & DRM_CALLED_FROM_VBLIRQ && - position == vbl_start - 1) { - position = (position + 1) % vtotal; - - /* Signal this correction as "applied". */ - ret |= 0x8; - } - } + position = __intel_get_crtc_scanline(intel_crtc); } else { /* Have access to pixelcount since start of frame. * We can split this into vertical and horizontal @@ -862,6 +964,29 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, vbl_start *= htotal; vbl_end *= htotal; vtotal *= htotal; + + /* + * In interlaced modes, the pixel counter counts all pixels, + * so one field will have htotal more pixels. In order to avoid + * the reported position from jumping backwards when the pixel + * counter is beyond the length of the shorter field, just + * clamp the position the length of the shorter field. This + * matches how the scanline counter based position works since + * the scanline counter doesn't count the two half lines. + */ + if (position >= vtotal) + position = vtotal - 1; + + /* + * Start of vblank interrupt is triggered at start of hsync, + * just prior to the first active line of vblank. However we + * consider lines to start at the leading edge of horizontal + * active. So, should we get here before we've crossed into + * the horizontal active of the first line in vblank, we would + * not set the DRM_SCANOUTPOS_INVBL flag. In order to fix that, + * always add htotal-hsync_start to the current pixel position. + */ + position = (position + htotal - hsync_start) % vtotal; } /* Get optional system timestamp after query. */ @@ -900,6 +1025,19 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, return ret; } +int intel_get_crtc_scanline(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + unsigned long irqflags; + int position; + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + position = __intel_get_crtc_scanline(crtc); + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + + return position; +} + static int i915_get_vblank_timestamp(struct drm_device *dev, int pipe, int *max_error, struct timeval *vblank_time, @@ -945,7 +1083,7 @@ static bool intel_hpd_irq_event(struct drm_device *dev, DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n", connector->base.id, - drm_get_connector_name(connector), + connector->name, drm_get_connector_status_name(old_status), drm_get_connector_status_name(connector->status)); @@ -990,7 +1128,7 @@ static void i915_hotplug_work_func(struct work_struct *work) connector->polled == DRM_CONNECTOR_POLL_HPD) { DRM_INFO("HPD interrupt storm detected on connector %s: " "switching from hotplug detection to polling\n", - drm_get_connector_name(connector)); + connector->name); dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark = HPD_DISABLED; connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; @@ -998,7 +1136,7 @@ static void i915_hotplug_work_func(struct work_struct *work) } if (hpd_event_bits & (1 << intel_encoder->hpd_pin)) { DRM_DEBUG_KMS("Connector %s (pin %i) received hotplug event.\n", - drm_get_connector_name(connector), intel_encoder->hpd_pin); + connector->name, intel_encoder->hpd_pin); } } /* if there were no outputs to poll, poll was disabled, @@ -1073,9 +1211,9 @@ static void ironlake_rps_change_irq_handler(struct drm_device *dev) } static void notify_ring(struct drm_device *dev, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { - if (ring->obj == NULL) + if (!intel_ring_initialized(ring)) return; trace_i915_gem_request_complete(ring); @@ -1094,8 +1232,12 @@ static void gen6_pm_rps_work(struct work_struct *work) spin_lock_irq(&dev_priv->irq_lock); pm_iir = dev_priv->rps.pm_iir; dev_priv->rps.pm_iir = 0; - /* Make sure not to corrupt PMIMR state used by ringbuffer code */ - snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + if (IS_BROADWELL(dev_priv->dev)) + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + else { + /* Make sure not to corrupt PMIMR state used by ringbuffer */ + snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + } spin_unlock_irq(&dev_priv->irq_lock); /* Make sure we didn't queue anything we're not going to process. */ @@ -1292,6 +1434,19 @@ static void snb_gt_irq_handler(struct drm_device *dev, ivybridge_parity_error_irq_handler(dev, gt_iir); } +static void gen8_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir) +{ + if ((pm_iir & dev_priv->pm_rps_events) == 0) + return; + + spin_lock(&dev_priv->irq_lock); + dev_priv->rps.pm_iir |= pm_iir & dev_priv->pm_rps_events; + bdw_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events); + spin_unlock(&dev_priv->irq_lock); + + queue_work(dev_priv->wq, &dev_priv->rps.work); +} + static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev, struct drm_i915_private *dev_priv, u32 master_ctl) @@ -1315,18 +1470,32 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev, DRM_ERROR("The master control interrupt lied (GT0)!\n"); } - if (master_ctl & GEN8_GT_VCS1_IRQ) { + if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) { tmp = I915_READ(GEN8_GT_IIR(1)); if (tmp) { ret = IRQ_HANDLED; vcs = tmp >> GEN8_VCS1_IRQ_SHIFT; if (vcs & GT_RENDER_USER_INTERRUPT) notify_ring(dev, &dev_priv->ring[VCS]); + vcs = tmp >> GEN8_VCS2_IRQ_SHIFT; + if (vcs & GT_RENDER_USER_INTERRUPT) + notify_ring(dev, &dev_priv->ring[VCS2]); I915_WRITE(GEN8_GT_IIR(1), tmp); } else DRM_ERROR("The master control interrupt lied (GT1)!\n"); } + if (master_ctl & GEN8_GT_PM_IRQ) { + tmp = I915_READ(GEN8_GT_IIR(2)); + if (tmp & dev_priv->pm_rps_events) { + ret = IRQ_HANDLED; + gen8_rps_irq_handler(dev_priv, tmp); + I915_WRITE(GEN8_GT_IIR(2), + tmp & dev_priv->pm_rps_events); + } else + DRM_ERROR("The master control interrupt lied (PM)!\n"); + } + if (master_ctl & GEN8_GT_VECS_IRQ) { tmp = I915_READ(GEN8_GT_IIR(3)); if (tmp) { @@ -1549,6 +1718,19 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir) } } +static bool intel_pipe_handle_vblank(struct drm_device *dev, enum pipe pipe) +{ + struct intel_crtc *crtc; + + if (!drm_handle_vblank(dev, pipe)) + return false; + + crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe)); + wake_up(&crtc->vbl_wait); + + return true; +} + static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -1578,6 +1760,9 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir) case PIPE_B: iir_bit = I915_DISPLAY_PIPE_B_EVENT_INTERRUPT; break; + case PIPE_C: + iir_bit = I915_DISPLAY_PIPE_C_EVENT_INTERRUPT; + break; } if (iir & iir_bit) mask |= dev_priv->pipestat_irq_mask[pipe]; @@ -1600,7 +1785,7 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir) for_each_pipe(pipe) { if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS) - drm_handle_vblank(dev, pipe); + intel_pipe_handle_vblank(dev, pipe); if (pipe_stats[pipe] & PLANE_FLIP_DONE_INT_STATUS_VLV) { intel_prepare_page_flip(dev, pipe); @@ -1619,9 +1804,36 @@ 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; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 iir, gt_iir, pm_iir; irqreturn_t ret = IRQ_NONE; @@ -1641,19 +1853,8 @@ 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); @@ -1667,6 +1868,40 @@ out: return ret; } +static irqreturn_t cherryview_irq_handler(int irq, void *arg) +{ + struct drm_device *dev = arg; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 master_ctl, iir; + irqreturn_t ret = IRQ_NONE; + + for (;;) { + master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL; + iir = I915_READ(VLV_IIR); + + if (master_ctl == 0 && iir == 0) + break; + + I915_WRITE(GEN8_MASTER_IRQ, 0); + + gen8_gt_irq_handler(dev, dev_priv, master_ctl); + + valleyview_pipestat_irq_handler(dev, iir); + + /* Consume port. Then clear IIR or we'll miss events */ + i9xx_hpd_irq_handler(dev); + + I915_WRITE(VLV_IIR, iir); + + I915_WRITE(GEN8_MASTER_IRQ, DE_MASTER_IRQ_CONTROL); + POSTING_READ(GEN8_MASTER_IRQ); + + ret = IRQ_HANDLED; + } + + return ret; +} + static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -1827,7 +2062,7 @@ static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir) for_each_pipe(pipe) { if (de_iir & DE_PIPE_VBLANK(pipe)) - drm_handle_vblank(dev, pipe); + intel_pipe_handle_vblank(dev, pipe); if (de_iir & DE_PIPE_FIFO_UNDERRUN(pipe)) if (intel_set_cpu_fifo_underrun_reporting(dev, pipe, false)) @@ -1877,7 +2112,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir) for_each_pipe(pipe) { if (de_iir & (DE_PIPE_VBLANK_IVB(pipe))) - drm_handle_vblank(dev, pipe); + intel_pipe_handle_vblank(dev, pipe); /* plane/pipes map 1:1 on ilk+ */ if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) { @@ -1899,7 +2134,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir) static irqreturn_t ironlake_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 de_iir, gt_iir, de_ier, sde_ier = 0; irqreturn_t ret = IRQ_NONE; @@ -2020,9 +2255,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) pipe_iir = I915_READ(GEN8_DE_PIPE_IIR(pipe)); if (pipe_iir & GEN8_PIPE_VBLANK) - drm_handle_vblank(dev, pipe); + intel_pipe_handle_vblank(dev, pipe); - if (pipe_iir & GEN8_PIPE_FLIP_DONE) { + if (pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE) { intel_prepare_page_flip(dev, pipe); intel_finish_page_flip_plane(dev, pipe); } @@ -2075,7 +2310,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) static void i915_error_wake_up(struct drm_i915_private *dev_priv, bool reset_completed) { - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; /* @@ -2137,6 +2372,14 @@ static void i915_error_work_func(struct work_struct *work) reset_event); /* + * In most cases it's guaranteed that we get here with an RPM + * reference held, for example because there is a pending GPU + * request that won't finish until the reset is done. This + * isn't the case at least when we get here by doing a + * simulated reset via debugs, so get an RPM reference. + */ + intel_runtime_pm_get(dev_priv); + /* * All state reset _must_ be completed before we update the * reset counter, for otherwise waiters might miss the reset * pending state and not properly drop locks, resulting in @@ -2146,6 +2389,8 @@ static void i915_error_work_func(struct work_struct *work) intel_display_handle_reset(dev); + intel_runtime_pm_put(dev_priv); + if (ret == 0) { /* * After all the gem state is reset, increment the reset @@ -2383,10 +2628,6 @@ static int i915_enable_vblank(struct drm_device *dev, int pipe) else i915_enable_pipestat(dev_priv, pipe, PIPE_VBLANK_INTERRUPT_STATUS); - - /* maintain vblank delivery even in deep C-states */ - if (INTEL_INFO(dev)->gen == 3) - I915_WRITE(INSTPM, _MASKED_BIT_DISABLE(INSTPM_AGPBUSY_DIS)); spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); return 0; @@ -2450,9 +2691,6 @@ static void i915_disable_vblank(struct drm_device *dev, int pipe) unsigned long irqflags; spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - if (INTEL_INFO(dev)->gen == 3) - I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_AGPBUSY_DIS)); - i915_disable_pipestat(dev_priv, pipe, PIPE_VBLANK_INTERRUPT_STATUS | PIPE_START_VBLANK_INTERRUPT_STATUS); @@ -2498,29 +2736,77 @@ static void gen8_disable_vblank(struct drm_device *dev, int pipe) } static u32 -ring_last_seqno(struct intel_ring_buffer *ring) +ring_last_seqno(struct intel_engine_cs *ring) { return list_entry(ring->request_list.prev, struct drm_i915_gem_request, list)->seqno; } static bool -ring_idle(struct intel_ring_buffer *ring, u32 seqno) +ring_idle(struct intel_engine_cs *ring, u32 seqno) { return (list_empty(&ring->request_list) || i915_seqno_passed(seqno, ring_last_seqno(ring))); } -static struct intel_ring_buffer * -semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) +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_engine_cs * +semaphore_wait_to_signaller_ring(struct intel_engine_cs *ring, u32 ipehr) +{ + struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct intel_engine_cs *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.mbox.wait[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_engine_cs * +semaphore_waits_for(struct intel_engine_cs *ring, u32 *seqno) { struct drm_i915_private *dev_priv = ring->dev->dev_private; u32 cmd, ipehr, head; 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; /* @@ -2538,10 +2824,10 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) * our ring is smaller than what the hardware (and hence * HEAD_ADDR) allows. Also handles wrap-around. */ - head &= ring->size - 1; + head &= ring->buffer->size - 1; /* This here seems to blow up */ - cmd = ioread32(ring->virtual_start + head); + cmd = ioread32(ring->buffer->virtual_start + head); if (cmd == ipehr) break; @@ -2551,14 +2837,14 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) if (!i) return NULL; - *seqno = ioread32(ring->virtual_start + head + 4) + 1; - return &dev_priv->ring[(ring->id + (((ipehr >> 17) & 1) + 1)) % 3]; + *seqno = ioread32(ring->buffer->virtual_start + head + 4) + 1; + return semaphore_wait_to_signaller_ring(ring, ipehr); } -static int semaphore_passed(struct intel_ring_buffer *ring) +static int semaphore_passed(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; - struct intel_ring_buffer *signaller; + struct intel_engine_cs *signaller; u32 seqno, ctl; ring->hangcheck.deadlock = true; @@ -2577,7 +2863,7 @@ static int semaphore_passed(struct intel_ring_buffer *ring) static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) { - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; for_each_ring(ring, dev_priv, i) @@ -2585,7 +2871,7 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) } static enum intel_ring_hangcheck_action -ring_stuck(struct intel_ring_buffer *ring, u64 acthd) +ring_stuck(struct intel_engine_cs *ring, u64 acthd) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2641,7 +2927,7 @@ static void i915_hangcheck_elapsed(unsigned long data) { struct drm_device *dev = (struct drm_device *)data; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; int busy_count = 0, rings_hung = 0; bool stuck[I915_NUM_RINGS] = { 0 }; @@ -2759,57 +3045,63 @@ 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_preinstall(dev); + ibx_irq_reset(dev); } static void valleyview_irq_preinstall(struct drm_device *dev) @@ -2827,7 +3119,7 @@ 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); @@ -2841,7 +3133,15 @@ 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_gt_irq_reset(struct drm_i915_private *dev_priv) +{ + GEN8_IRQ_RESET_NDX(GT, 0); + GEN8_IRQ_RESET_NDX(GT, 1); + GEN8_IRQ_RESET_NDX(GT, 2); + GEN8_IRQ_RESET_NDX(GT, 3); +} + +static void gen8_irq_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; int pipe; @@ -2849,43 +3149,44 @@ 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_gt_irq_reset(dev_priv); - for_each_pipe(pipe) { - GEN8_IRQ_INIT_NDX(DE_PIPE, pipe); - } + for_each_pipe(pipe) + GEN8_IRQ_RESET_NDX(DE_PIPE, pipe); + + GEN5_IRQ_RESET(GEN8_DE_PORT_); + GEN5_IRQ_RESET(GEN8_DE_MISC_); + GEN5_IRQ_RESET(GEN8_PCU_); + + ibx_irq_reset(dev); +} + +static void cherryview_irq_preinstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe; + + I915_WRITE(GEN8_MASTER_IRQ, 0); + POSTING_READ(GEN8_MASTER_IRQ); - GEN8_IRQ_INIT(DE_PORT); - GEN8_IRQ_INIT(DE_MISC); - GEN8_IRQ_INIT(PCU); -#undef GEN8_IRQ_INIT -#undef GEN8_IRQ_INIT_NDX + gen8_gt_irq_reset(dev_priv); + + GEN5_IRQ_RESET(GEN8_PCU_); POSTING_READ(GEN8_PCU_IIR); - ibx_irq_preinstall(dev); + I915_WRITE(DPINVGTT, DPINVGTT_STATUS_MASK_CHV); + + I915_WRITE(PORT_HOTPLUG_EN, 0); + I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); + + for_each_pipe(pipe) + I915_WRITE(PIPESTAT(pipe), 0xffff); + + I915_WRITE(VLV_IMR, 0xffffffff); + I915_WRITE(VLV_IER, 0x0); + I915_WRITE(VLV_IIR, 0xffffffff); + POSTING_READ(VLV_IIR); } static void ibx_hpd_irq_setup(struct drm_device *dev) @@ -2931,15 +3232,12 @@ 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); } @@ -2965,10 +3263,7 @@ 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; @@ -2977,10 +3272,7 @@ 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); } } @@ -2997,8 +3289,6 @@ 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 | @@ -3011,11 +3301,11 @@ 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); @@ -3175,21 +3465,16 @@ 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]); + + dev_priv->pm_irq_mask = 0xffffffff; } static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; - uint32_t de_pipe_masked = GEN8_PIPE_FLIP_DONE | + uint32_t de_pipe_masked = GEN8_PIPE_PRIMARY_FLIP_DONE | GEN8_PIPE_CDCLK_CRC_DONE | GEN8_DE_PIPE_IRQ_FAULT_ERRORS; uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | @@ -3199,25 +3484,19 @@ 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); @@ -3229,44 +3508,55 @@ static int gen8_irq_postinstall(struct drm_device *dev) return 0; } -static void gen8_irq_uninstall(struct drm_device *dev) +static int cherryview_irq_postinstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + u32 enable_mask = I915_DISPLAY_PORT_INTERRUPT | + I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | + I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | + I915_DISPLAY_PIPE_C_EVENT_INTERRUPT; + u32 pipestat_enable = PLANE_FLIP_DONE_INT_STATUS_VLV | + PIPE_CRC_DONE_INTERRUPT_STATUS; + unsigned long irqflags; int pipe; - if (!dev_priv) - return; + /* + * Leave vblank interrupts masked initially. enable/disable will + * toggle them based on usage. + */ + dev_priv->irq_mask = ~enable_mask; - I915_WRITE(GEN8_MASTER_IRQ, 0); + for_each_pipe(pipe) + I915_WRITE(PIPESTAT(pipe), 0xffff); -#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) + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_INTERRUPT_STATUS); + for_each_pipe(pipe) + i915_enable_pipestat(dev_priv, pipe, pipestat_enable); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); -#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) + I915_WRITE(VLV_IIR, 0xffffffff); + I915_WRITE(VLV_IMR, dev_priv->irq_mask); + I915_WRITE(VLV_IER, enable_mask); - GEN8_IRQ_FINI_NDX(GT, 0); - GEN8_IRQ_FINI_NDX(GT, 1); - GEN8_IRQ_FINI_NDX(GT, 2); - GEN8_IRQ_FINI_NDX(GT, 3); + gen8_gt_irq_postinstall(dev_priv); - for_each_pipe(pipe) { - GEN8_IRQ_FINI_NDX(DE_PIPE, pipe); - } + I915_WRITE(GEN8_MASTER_IRQ, MASTER_INTERRUPT_ENABLE); + POSTING_READ(GEN8_MASTER_IRQ); - GEN8_IRQ_FINI(DE_PORT); - GEN8_IRQ_FINI(DE_MISC); - GEN8_IRQ_FINI(PCU); -#undef GEN8_IRQ_FINI -#undef GEN8_IRQ_FINI_NDX + return 0; +} - POSTING_READ(GEN8_PCU_IIR); +static void gen8_irq_uninstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (!dev_priv) + return; + + intel_hpd_irq_uninstall(dev_priv); + + gen8_irq_reset(dev); } static void valleyview_irq_uninstall(struct drm_device *dev) @@ -3278,6 +3568,8 @@ static void valleyview_irq_uninstall(struct drm_device *dev) if (!dev_priv) return; + I915_WRITE(VLV_MASTER_IER, 0); + intel_hpd_irq_uninstall(dev_priv); for_each_pipe(pipe) @@ -3300,35 +3592,67 @@ static void valleyview_irq_uninstall(struct drm_device *dev) POSTING_READ(VLV_IER); } -static void ironlake_irq_uninstall(struct drm_device *dev) +static void cherryview_irq_uninstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + int pipe; if (!dev_priv) return; - intel_hpd_irq_uninstall(dev_priv); + I915_WRITE(GEN8_MASTER_IRQ, 0); + POSTING_READ(GEN8_MASTER_IRQ); - I915_WRITE(HWSTAM, 0xffffffff); +#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); \ + POSTING_READ(GEN8_##type##_IIR(which)); \ + 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); \ + POSTING_READ(GEN8_##type##_IIR); \ + I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \ +} while (0) - 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)); + GEN8_IRQ_FINI_NDX(GT, 0); + GEN8_IRQ_FINI_NDX(GT, 1); + GEN8_IRQ_FINI_NDX(GT, 2); + GEN8_IRQ_FINI_NDX(GT, 3); - I915_WRITE(GTIMR, 0xffffffff); - I915_WRITE(GTIER, 0x0); - I915_WRITE(GTIIR, I915_READ(GTIIR)); + GEN8_IRQ_FINI(PCU); - if (HAS_PCH_NOP(dev)) +#undef GEN8_IRQ_FINI +#undef GEN8_IRQ_FINI_NDX + + I915_WRITE(PORT_HOTPLUG_EN, 0); + I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); + + for_each_pipe(pipe) + I915_WRITE(PIPESTAT(pipe), 0xffff); + + I915_WRITE(VLV_IMR, 0xffffffff); + I915_WRITE(VLV_IER, 0x0); + I915_WRITE(VLV_IIR, 0xffffffff); + POSTING_READ(VLV_IIR); +} + +static void ironlake_irq_uninstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (!dev_priv) 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)); + intel_hpd_irq_uninstall(dev_priv); + + ironlake_irq_reset(dev); } static void i8xx_irq_preinstall(struct drm_device * dev) @@ -3386,7 +3710,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; u16 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane); - if (!drm_handle_vblank(dev, pipe)) + if (!intel_pipe_handle_vblank(dev, pipe)) return false; if ((iir & flip_pending) == 0) @@ -3410,7 +3734,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev, static irqreturn_t i8xx_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u16 iir, new_iir; u32 pipe_stats[2]; @@ -3571,7 +3895,7 @@ static bool i915_handle_vblank(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; u32 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane); - if (!drm_handle_vblank(dev, pipe)) + if (!intel_pipe_handle_vblank(dev, pipe)) return false; if ((iir & flip_pending) == 0) @@ -3595,7 +3919,7 @@ static bool i915_handle_vblank(struct drm_device *dev, static irqreturn_t i915_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 iir, new_iir, pipe_stats[I915_MAX_PIPES]; unsigned long irqflags; @@ -3636,16 +3960,9 @@ 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 */ @@ -3832,7 +4149,7 @@ static void i915_hpd_irq_setup(struct drm_device *dev) static irqreturn_t i965_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 iir, new_iir; u32 pipe_stats[I915_MAX_PIPES]; @@ -3879,22 +4196,8 @@ 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 */ @@ -3997,7 +4300,7 @@ static void intel_hpd_irq_reenable(unsigned long data) if (intel_connector->encoder->hpd_pin == i) { if (connector->polled != intel_connector->polled) DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n", - drm_get_connector_name(connector)); + connector->name); connector->polled = intel_connector->polled; if (!connector->polled) connector->polled = DRM_CONNECTOR_POLL_HPD; @@ -4045,7 +4348,15 @@ void intel_irq_init(struct drm_device *dev) dev->driver->get_scanout_position = i915_get_crtc_scanoutpos; } - if (IS_VALLEYVIEW(dev)) { + if (IS_CHERRYVIEW(dev)) { + dev->driver->irq_handler = cherryview_irq_handler; + dev->driver->irq_preinstall = cherryview_irq_preinstall; + dev->driver->irq_postinstall = cherryview_irq_postinstall; + dev->driver->irq_uninstall = cherryview_irq_uninstall; + dev->driver->enable_vblank = valleyview_enable_vblank; + dev->driver->disable_vblank = valleyview_disable_vblank; + dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup; + } else if (IS_VALLEYVIEW(dev)) { dev->driver->irq_handler = valleyview_irq_handler; dev->driver->irq_preinstall = valleyview_irq_preinstall; dev->driver->irq_postinstall = valleyview_irq_postinstall; @@ -4055,7 +4366,7 @@ void intel_irq_init(struct drm_device *dev) dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup; } else if (IS_GEN8(dev)) { dev->driver->irq_handler = gen8_irq_handler; - dev->driver->irq_preinstall = gen8_irq_preinstall; + dev->driver->irq_preinstall = gen8_irq_reset; dev->driver->irq_postinstall = gen8_irq_postinstall; dev->driver->irq_uninstall = gen8_irq_uninstall; dev->driver->enable_vblank = gen8_enable_vblank; @@ -4063,7 +4374,7 @@ void intel_irq_init(struct drm_device *dev) dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup; } else if (HAS_PCH_SPLIT(dev)) { dev->driver->irq_handler = ironlake_irq_handler; - dev->driver->irq_preinstall = ironlake_irq_preinstall; + dev->driver->irq_preinstall = ironlake_irq_reset; dev->driver->irq_postinstall = ironlake_irq_postinstall; dev->driver->irq_uninstall = ironlake_irq_uninstall; dev->driver->enable_vblank = ironlake_enable_vblank; @@ -4121,57 +4432,20 @@ 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 d1d7980f0e01..d05a2afa17dc 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 c77af69c2d8f..e691b30b2817 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -29,6 +29,8 @@ #define _TRANSCODER(tran, a, b) ((a) + (tran)*((b)-(a))) #define _PORT(port, a, b) ((a) + (port)*((b)-(a))) +#define _PIPE3(pipe, a, b, c) (pipe < 2 ? _PIPE(pipe, a, b) : c) +#define _PORT3(port, a, b, c) (port < 2 ? _PORT(port, a, b) : c) #define _MASKED_BIT_ENABLE(a) (((a) << 16) | (a)) #define _MASKED_BIT_DISABLE(a) ((a) << 16) @@ -77,13 +79,19 @@ /* Graphics reset regs */ #define I965_GDRST 0xc0 /* PCI config register */ -#define ILK_GDSR 0x2ca4 /* MCHBAR offset */ #define GRDOM_FULL (0<<2) #define GRDOM_RENDER (1<<2) #define GRDOM_MEDIA (3<<2) #define GRDOM_MASK (3<<2) #define GRDOM_RESET_ENABLE (1<<0) +#define ILK_GDSR 0x2ca4 /* MCHBAR offset */ +#define ILK_GRDOM_FULL (0<<1) +#define ILK_GRDOM_RENDER (1<<1) +#define ILK_GRDOM_MEDIA (3<<1) +#define ILK_GRDOM_MASK (3<<1) +#define ILK_GRDOM_RESET_ENABLE (1<<0) + #define GEN6_MBCUNIT_SNPCR 0x900c /* for LLC config */ #define GEN6_MBC_SNPCR_SHIFT 21 #define GEN6_MBC_SNPCR_MASK (3<<21) @@ -92,6 +100,9 @@ #define GEN6_MBC_SNPCR_LOW (2<<21) #define GEN6_MBC_SNPCR_MIN (3<<21) /* only 1/16th of the cache is shared */ +#define VLV_G3DCTL 0x9024 +#define VLV_GSCKGCTL 0x9028 + #define GEN6_MBCTL 0x0907c #define GEN6_MBCTL_ENABLE_BOOT_FETCH (1 << 4) #define GEN6_MBCTL_CTX_FETCH_NEEDED (1 << 3) @@ -190,6 +201,8 @@ * 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 +257,8 @@ #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) @@ -262,13 +276,16 @@ * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! */ -#define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*x-1) -#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*x-1) +#define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*(x)-1) +#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*(x)-1) +#define MI_STORE_REGISTER_MEM_GEN8(x) MI_INSTR(0x24, 3*(x)-1) #define MI_SRM_LRM_GLOBAL_GTT (1<<22) #define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */ #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 +347,12 @@ #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 +367,94 @@ #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 GEN7_SO_PRIM_STORAGE_NEEDED(n) (0x5240 + (n) * 8) + +#define GEN7_3DPRIM_END_OFFSET 0x2420 +#define GEN7_3DPRIM_START_VERTEX 0x2430 +#define GEN7_3DPRIM_VERTEX_COUNT 0x2434 +#define GEN7_3DPRIM_INSTANCE_COUNT 0x2438 +#define GEN7_3DPRIM_START_INSTANCE 0x243C +#define GEN7_3DPRIM_BASE_VERTEX 0x2440 + +#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 @@ -370,6 +478,7 @@ #define IOSF_PORT_PUNIT 0x4 #define IOSF_PORT_NC 0x11 #define IOSF_PORT_DPIO 0x12 +#define IOSF_PORT_DPIO_2 0x1a #define IOSF_PORT_GPIO_NC 0x13 #define IOSF_PORT_CCK 0x14 #define IOSF_PORT_CCU 0xA9 @@ -381,9 +490,6 @@ /* See configdb bunit SB addr map */ #define BUNIT_REG_BISOC 0x11 -#define PUNIT_OPCODE_REG_READ 6 -#define PUNIT_OPCODE_REG_WRITE 7 - #define PUNIT_REG_DSPFREQ 0x36 #define DSPFREQSTAT_SHIFT 30 #define DSPFREQSTAT_MASK (0x3 << DSPFREQSTAT_SHIFT) @@ -469,16 +575,91 @@ enum punit_power_well { #define DSI_PLL_M1_DIV_MASK (0x1ff << 0) #define CCK_DISPLAY_CLOCK_CONTROL 0x6b -/* - * DPIO - a special bus for various display related registers to hide behind +/** + * DOC: DPIO + * + * VLV and CHV have slightly peculiar display PHYs for driving DP/HDMI + * ports. DPIO is the name given to such a display PHY. These PHYs + * don't follow the standard programming model using direct MMIO + * registers, and instead their registers must be accessed trough IOSF + * sideband. VLV has one such PHY for driving ports B and C, and CHV + * adds another PHY for driving port D. Each PHY responds to specific + * IOSF-SB port. + * + * Each display PHY is made up of one or two channels. Each channel + * houses a common lane part which contains the PLL and other common + * logic. CH0 common lane also contains the IOSF-SB logic for the + * Common Register Interface (CRI) ie. the DPIO registers. CRI clock + * must be running when any DPIO registers are accessed. + * + * In addition to having their own registers, the PHYs are also + * controlled through some dedicated signals from the display + * controller. These include PLL reference clock enable, PLL enable, + * and CRI clock selection, for example. * - * DPIO is VLV only. + * Eeach channel also has two splines (also called data lanes), and + * each spline is made up of one Physical Access Coding Sub-Layer + * (PCS) block and two TX lanes. So each channel has two PCS blocks + * and four TX lanes. The TX lanes are used as DP lanes or TMDS + * data/clock pairs depending on the output type. + * + * Additionally the PHY also contains an AUX lane with AUX blocks + * for each channel. This is used for DP AUX communication, but + * this fact isn't really relevant for the driver since AUX is + * controlled from the display controller side. No DPIO registers + * need to be accessed during AUX communication, + * + * Generally the common lane corresponds to the pipe and + * the spline (PCS/TX) correponds to the port. + * + * For dual channel PHY (VLV/CHV): + * + * pipe A == CMN/PLL/REF CH0 + * + * pipe B == CMN/PLL/REF CH1 + * + * port B == PCS/TX CH0 + * + * port C == PCS/TX CH1 + * + * This is especially important when we cross the streams + * ie. drive port B with pipe B, or port C with pipe A. + * + * For single channel PHY (CHV): + * + * pipe C == CMN/PLL/REF CH0 + * + * port D == PCS/TX CH0 + * + * Note: digital port B is DDI0, digital port C is DDI1, + * digital port D is DDI2 + */ +/* + * Dual channel PHY (VLV/CHV) + * --------------------------------- + * | CH0 | CH1 | + * | CMN/PLL/REF | CMN/PLL/REF | + * |---------------|---------------| Display PHY + * | PCS01 | PCS23 | PCS01 | PCS23 | + * |-------|-------|-------|-------| + * |TX0|TX1|TX2|TX3|TX0|TX1|TX2|TX3| + * --------------------------------- + * | DDI0 | DDI1 | DP/HDMI ports + * --------------------------------- * - * Note: digital port B is DDI0, digital pot C is DDI1 + * Single channel PHY (CHV) + * ----------------- + * | CH0 | + * | CMN/PLL/REF | + * |---------------| Display PHY + * | PCS01 | PCS23 | + * |-------|-------| + * |TX0|TX1|TX2|TX3| + * ----------------- + * | DDI2 | DP/HDMI port + * ----------------- */ #define DPIO_DEVFN 0 -#define DPIO_OPCODE_REG_WRITE 1 -#define DPIO_OPCODE_REG_READ 0 #define DPIO_CTL (VLV_DISPLAY_BASE + 0x2110) #define DPIO_MODSEL1 (1<<3) /* if ref clk b == 27 */ @@ -555,14 +736,29 @@ enum punit_power_well { #define DPIO_PCS_TX_LANE1_RESET (1<<7) #define VLV_PCS_DW0(ch) _PORT(ch, _VLV_PCS_DW0_CH0, _VLV_PCS_DW0_CH1) +#define _VLV_PCS01_DW0_CH0 0x200 +#define _VLV_PCS23_DW0_CH0 0x400 +#define _VLV_PCS01_DW0_CH1 0x2600 +#define _VLV_PCS23_DW0_CH1 0x2800 +#define VLV_PCS01_DW0(ch) _PORT(ch, _VLV_PCS01_DW0_CH0, _VLV_PCS01_DW0_CH1) +#define VLV_PCS23_DW0(ch) _PORT(ch, _VLV_PCS23_DW0_CH0, _VLV_PCS23_DW0_CH1) + #define _VLV_PCS_DW1_CH0 0x8204 #define _VLV_PCS_DW1_CH1 0x8404 +#define CHV_PCS_REQ_SOFTRESET_EN (1<<23) #define DPIO_PCS_CLK_CRI_RXEB_EIOS_EN (1<<22) #define DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1<<21) #define DPIO_PCS_CLK_DATAWIDTH_SHIFT (6) #define DPIO_PCS_CLK_SOFT_RESET (1<<5) #define VLV_PCS_DW1(ch) _PORT(ch, _VLV_PCS_DW1_CH0, _VLV_PCS_DW1_CH1) +#define _VLV_PCS01_DW1_CH0 0x204 +#define _VLV_PCS23_DW1_CH0 0x404 +#define _VLV_PCS01_DW1_CH1 0x2604 +#define _VLV_PCS23_DW1_CH1 0x2804 +#define VLV_PCS01_DW1(ch) _PORT(ch, _VLV_PCS01_DW1_CH0, _VLV_PCS01_DW1_CH1) +#define VLV_PCS23_DW1(ch) _PORT(ch, _VLV_PCS23_DW1_CH0, _VLV_PCS23_DW1_CH1) + #define _VLV_PCS_DW8_CH0 0x8220 #define _VLV_PCS_DW8_CH1 0x8420 #define VLV_PCS_DW8(ch) _PORT(ch, _VLV_PCS_DW8_CH0, _VLV_PCS_DW8_CH1) @@ -578,6 +774,19 @@ enum punit_power_well { #define _VLV_PCS_DW9_CH1 0x8424 #define VLV_PCS_DW9(ch) _PORT(ch, _VLV_PCS_DW9_CH0, _VLV_PCS_DW9_CH1) +#define _CHV_PCS_DW10_CH0 0x8228 +#define _CHV_PCS_DW10_CH1 0x8428 +#define DPIO_PCS_SWING_CALC_TX0_TX2 (1<<30) +#define DPIO_PCS_SWING_CALC_TX1_TX3 (1<<31) +#define CHV_PCS_DW10(ch) _PORT(ch, _CHV_PCS_DW10_CH0, _CHV_PCS_DW10_CH1) + +#define _VLV_PCS01_DW10_CH0 0x0228 +#define _VLV_PCS23_DW10_CH0 0x0428 +#define _VLV_PCS01_DW10_CH1 0x2628 +#define _VLV_PCS23_DW10_CH1 0x2828 +#define VLV_PCS01_DW10(port) _PORT(port, _VLV_PCS01_DW10_CH0, _VLV_PCS01_DW10_CH1) +#define VLV_PCS23_DW10(port) _PORT(port, _VLV_PCS23_DW10_CH0, _VLV_PCS23_DW10_CH1) + #define _VLV_PCS_DW11_CH0 0x822c #define _VLV_PCS_DW11_CH1 0x842c #define VLV_PCS_DW11(ch) _PORT(ch, _VLV_PCS_DW11_CH0, _VLV_PCS_DW11_CH1) @@ -596,14 +805,21 @@ enum punit_power_well { #define _VLV_TX_DW2_CH0 0x8288 #define _VLV_TX_DW2_CH1 0x8488 +#define DPIO_SWING_MARGIN_SHIFT 16 +#define DPIO_SWING_MARGIN_MASK (0xff << DPIO_SWING_MARGIN_SHIFT) +#define DPIO_UNIQ_TRANS_SCALE_SHIFT 8 #define VLV_TX_DW2(ch) _PORT(ch, _VLV_TX_DW2_CH0, _VLV_TX_DW2_CH1) #define _VLV_TX_DW3_CH0 0x828c #define _VLV_TX_DW3_CH1 0x848c +/* The following bit for CHV phy */ +#define DPIO_TX_UNIQ_TRANS_SCALE_EN (1<<27) #define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1) #define _VLV_TX_DW4_CH0 0x8290 #define _VLV_TX_DW4_CH1 0x8490 +#define DPIO_SWING_DEEMPH9P5_SHIFT 24 +#define DPIO_SWING_DEEMPH9P5_MASK (0xff << DPIO_SWING_DEEMPH9P5_SHIFT) #define VLV_TX_DW4(ch) _PORT(ch, _VLV_TX_DW4_CH0, _VLV_TX_DW4_CH1) #define _VLV_TX3_DW4_CH0 0x690 @@ -623,6 +839,73 @@ enum punit_power_well { #define _VLV_TX_DW14_CH1 0x84b8 #define VLV_TX_DW14(ch) _PORT(ch, _VLV_TX_DW14_CH0, _VLV_TX_DW14_CH1) +/* CHV dpPhy registers */ +#define _CHV_PLL_DW0_CH0 0x8000 +#define _CHV_PLL_DW0_CH1 0x8180 +#define CHV_PLL_DW0(ch) _PIPE(ch, _CHV_PLL_DW0_CH0, _CHV_PLL_DW0_CH1) + +#define _CHV_PLL_DW1_CH0 0x8004 +#define _CHV_PLL_DW1_CH1 0x8184 +#define DPIO_CHV_N_DIV_SHIFT 8 +#define DPIO_CHV_M1_DIV_BY_2 (0 << 0) +#define CHV_PLL_DW1(ch) _PIPE(ch, _CHV_PLL_DW1_CH0, _CHV_PLL_DW1_CH1) + +#define _CHV_PLL_DW2_CH0 0x8008 +#define _CHV_PLL_DW2_CH1 0x8188 +#define CHV_PLL_DW2(ch) _PIPE(ch, _CHV_PLL_DW2_CH0, _CHV_PLL_DW2_CH1) + +#define _CHV_PLL_DW3_CH0 0x800c +#define _CHV_PLL_DW3_CH1 0x818c +#define DPIO_CHV_FRAC_DIV_EN (1 << 16) +#define DPIO_CHV_FIRST_MOD (0 << 8) +#define DPIO_CHV_SECOND_MOD (1 << 8) +#define DPIO_CHV_FEEDFWD_GAIN_SHIFT 0 +#define CHV_PLL_DW3(ch) _PIPE(ch, _CHV_PLL_DW3_CH0, _CHV_PLL_DW3_CH1) + +#define _CHV_PLL_DW6_CH0 0x8018 +#define _CHV_PLL_DW6_CH1 0x8198 +#define DPIO_CHV_GAIN_CTRL_SHIFT 16 +#define DPIO_CHV_INT_COEFF_SHIFT 8 +#define DPIO_CHV_PROP_COEFF_SHIFT 0 +#define CHV_PLL_DW6(ch) _PIPE(ch, _CHV_PLL_DW6_CH0, _CHV_PLL_DW6_CH1) + +#define _CHV_CMN_DW13_CH0 0x8134 +#define _CHV_CMN_DW0_CH1 0x8080 +#define DPIO_CHV_S1_DIV_SHIFT 21 +#define DPIO_CHV_P1_DIV_SHIFT 13 /* 3 bits */ +#define DPIO_CHV_P2_DIV_SHIFT 8 /* 5 bits */ +#define DPIO_CHV_K_DIV_SHIFT 4 +#define DPIO_PLL_FREQLOCK (1 << 1) +#define DPIO_PLL_LOCK (1 << 0) +#define CHV_CMN_DW13(ch) _PIPE(ch, _CHV_CMN_DW13_CH0, _CHV_CMN_DW0_CH1) + +#define _CHV_CMN_DW14_CH0 0x8138 +#define _CHV_CMN_DW1_CH1 0x8084 +#define DPIO_AFC_RECAL (1 << 14) +#define DPIO_DCLKP_EN (1 << 13) +#define CHV_CMN_DW14(ch) _PIPE(ch, _CHV_CMN_DW14_CH0, _CHV_CMN_DW1_CH1) + +#define CHV_CMN_DW30 0x8178 +#define DPIO_LRC_BYPASS (1 << 3) + +#define _TXLANE(ch, lane, offset) ((ch ? 0x2400 : 0) + \ + (lane) * 0x200 + (offset)) + +#define CHV_TX_DW0(ch, lane) _TXLANE(ch, lane, 0x80) +#define CHV_TX_DW1(ch, lane) _TXLANE(ch, lane, 0x84) +#define CHV_TX_DW2(ch, lane) _TXLANE(ch, lane, 0x88) +#define CHV_TX_DW3(ch, lane) _TXLANE(ch, lane, 0x8c) +#define CHV_TX_DW4(ch, lane) _TXLANE(ch, lane, 0x90) +#define CHV_TX_DW5(ch, lane) _TXLANE(ch, lane, 0x94) +#define CHV_TX_DW6(ch, lane) _TXLANE(ch, lane, 0x98) +#define CHV_TX_DW7(ch, lane) _TXLANE(ch, lane, 0x9c) +#define CHV_TX_DW8(ch, lane) _TXLANE(ch, lane, 0xa0) +#define CHV_TX_DW9(ch, lane) _TXLANE(ch, lane, 0xa4) +#define CHV_TX_DW10(ch, lane) _TXLANE(ch, lane, 0xa8) +#define CHV_TX_DW11(ch, lane) _TXLANE(ch, lane, 0xac) +#define DPIO_FRC_LATENCY_SHFIT 8 +#define CHV_TX_DW14(ch, lane) _TXLANE(ch, lane, 0xb8) +#define DPIO_UPAR_SHIFT 30 /* * Fence registers */ @@ -663,6 +946,7 @@ enum punit_power_well { #define RENDER_RING_BASE 0x02000 #define BSD_RING_BASE 0x04000 #define GEN6_BSD_RING_BASE 0x12000 +#define GEN8_BSD2_RING_BASE 0x1c000 #define VEBOX_RING_BASE 0x1a000 #define BLT_RING_BASE 0x22000 #define RING_TAIL(base) ((base)+0x30) @@ -688,9 +972,20 @@ enum punit_power_well { #define RING_MAX_IDLE(base) ((base)+0x54) #define RING_HWS_PGA(base) ((base)+0x80) #define RING_HWS_PGA_GEN6(base) ((base)+0x2080) -#define ARB_MODE 0x04030 + +#define GEN7_WR_WATERMARK 0x4028 +#define GEN7_GFX_PRIO_CTRL 0x402C +#define ARB_MODE 0x4030 #define ARB_MODE_SWIZZLE_SNB (1<<4) #define ARB_MODE_SWIZZLE_IVB (1<<5) +#define GEN7_GFX_PEND_TLB0 0x4034 +#define GEN7_GFX_PEND_TLB1 0x4038 +/* L3, CVS, ZTLB, RCC, CASC LRA min, max values */ +#define GEN7_LRA_LIMITS_BASE 0x403C +#define GEN7_LRA_LIMITS_REG_NUM 13 +#define GEN7_MEDIA_MAX_REQ_COUNT 0x4070 +#define GEN7_GFX_MAX_REQ_COUNT 0x4074 + #define GAMTARBMODE 0x04a08 #define ARB_MODE_BWGTLB_DISABLE (1<<9) #define ARB_MODE_SWIZZLE_BDW (1<<1) @@ -725,6 +1020,9 @@ enum punit_power_well { #define RING_WAIT_I8XX (1<<0) /* gen2, PRBx_HEAD */ #define RING_WAIT (1<<11) /* gen3+, PRBx_CTL */ #define RING_WAIT_SEMAPHORE (1<<10) /* gen6+ */ + +#define GEN7_TLB_RD_ADDR 0x4700 + #if 0 #define PRB0_TAIL 0x02030 #define PRB0_HEAD 0x02034 @@ -748,6 +1046,7 @@ 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 */ @@ -842,21 +1141,26 @@ 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) #define GFX_PPGTT_ENABLE (1<<9) #define VLV_DISPLAY_BASE 0x180000 +#define VLV_MIPI_BASE VLV_DISPLAY_BASE +#define VLV_GU_CTL0 (VLV_DISPLAY_BASE + 0x2030) +#define VLV_GU_CTL1 (VLV_DISPLAY_BASE + 0x2034) #define SCPD0 0x0209c /* 915+ only */ #define IER 0x020a0 #define IIR 0x020a4 #define IMR 0x020a8 #define ISR 0x020ac #define VLV_GUNIT_CLOCK_GATE (VLV_DISPLAY_BASE + 0x2060) +#define GINT_DIS (1<<22) #define GCFG_DIS (1<<8) +#define VLV_GUNIT_CLOCK_GATE2 (VLV_DISPLAY_BASE + 0x2064) #define VLV_IIR_RW (VLV_DISPLAY_BASE + 0x2084) #define VLV_IER (VLV_DISPLAY_BASE + 0x20a0) #define VLV_IIR (VLV_DISPLAY_BASE + 0x20a4) @@ -875,7 +1179,7 @@ enum punit_power_well { #define I915_ERROR_INSTRUCTION (1<<0) #define INSTPM 0x020c0 #define INSTPM_SELF_EN (1<<12) /* 915GM only */ -#define INSTPM_AGPBUSY_DIS (1<<11) /* gen3: when disabled, pending interrupts +#define INSTPM_AGPBUSY_INT_EN (1<<11) /* gen3: when disabled, pending interrupts will not assert AGPBUSY# and will only be delivered when out of C3. */ #define INSTPM_FORCE_ORDERING (1<<7) /* GEN6+ */ @@ -956,6 +1260,10 @@ enum punit_power_well { #define MI_ARB_DISPLAY_PRIORITY_A_B (0 << 0) /* display A > display B */ #define MI_ARB_DISPLAY_PRIORITY_B_A (1 << 0) /* display B > display A */ +#define MI_STATE 0x020e4 /* gen2 only */ +#define MI_AGPBUSY_INT_EN (1 << 1) /* 85x only */ +#define MI_AGPBUSY_830_MODE (1 << 0) /* 85x only */ + #define CACHE_MODE_0 0x02120 /* 915+ only */ #define CM0_PIPELINED_RENDER_FLUSH_DISABLE (1<<8) #define CM0_IZ_OPT_DISABLE (1<<6) @@ -973,6 +1281,7 @@ enum punit_power_well { #define ECO_FLIP_DONE (1<<0) #define CACHE_MODE_0_GEN7 0x7000 /* IVB+ */ +#define RC_OP_FLUSH_ENABLE (1<<0) #define HIZ_RAW_STALL_OPT_DISABLE (1<<2) #define CACHE_MODE_1 0x7004 /* IVB+ */ #define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE (1<<6) @@ -984,6 +1293,7 @@ enum punit_power_well { #define GEN6_RC_SLEEP_PSMI_CONTROL 0x2050 #define GEN8_RC_SEMA_IDLE_MSG_DISABLE (1 << 12) +#define GEN8_FF_DOP_CLOCK_GATE_DISABLE (1<<10) #define GEN6_BSD_SLEEP_PSMI_CONTROL 0x12050 #define GEN6_BSD_SLEEP_MSG_DISABLE (1 << 0) @@ -1024,24 +1334,43 @@ enum punit_power_well { /* These are all the "old" interrupts */ #define ILK_BSD_USER_INTERRUPT (1<<5) + +#define I915_PM_INTERRUPT (1<<31) +#define I915_ISP_INTERRUPT (1<<22) +#define I915_LPE_PIPE_B_INTERRUPT (1<<21) +#define I915_LPE_PIPE_A_INTERRUPT (1<<20) +#define I915_MIPIB_INTERRUPT (1<<19) +#define I915_MIPIA_INTERRUPT (1<<18) #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT (1<<18) #define I915_DISPLAY_PORT_INTERRUPT (1<<17) +#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT (1<<16) +#define I915_MASTER_ERROR_INTERRUPT (1<<15) #define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT (1<<15) +#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT (1<<14) #define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT (1<<14) /* p-state */ +#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT (1<<13) #define I915_HWB_OOM_INTERRUPT (1<<13) +#define I915_LPE_PIPE_C_INTERRUPT (1<<12) #define I915_SYNC_STATUS_INTERRUPT (1<<12) +#define I915_MISC_INTERRUPT (1<<11) #define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT (1<<11) +#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT (1<<10) #define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT (1<<10) +#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT (1<<9) #define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT (1<<9) +#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT (1<<8) #define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT (1<<8) #define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT (1<<7) #define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT (1<<6) #define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT (1<<5) #define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT (1<<4) +#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT (1<<3) +#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT (1<<2) #define I915_DEBUG_INTERRUPT (1<<2) +#define I915_WINVALID_INTERRUPT (1<<1) #define I915_USER_INTERRUPT (1<<1) #define I915_ASLE_INTERRUPT (1<<0) -#define I915_BSD_USER_INTERRUPT (1 << 25) +#define I915_BSD_USER_INTERRUPT (1<<25) #define GEN6_BSD_RNCID 0x12198 @@ -1198,6 +1527,7 @@ enum punit_power_well { #define GMBUS_PORT_SSC 1 #define GMBUS_PORT_VGADDC 2 #define GMBUS_PORT_PANEL 3 +#define GMBUS_PORT_DPD_CHV 3 /* HDMID_CHV */ #define GMBUS_PORT_DPC 4 /* HDMIC */ #define GMBUS_PORT_DPB 5 /* SDVO, HDMIB */ #define GMBUS_PORT_DPD 6 /* HDMID */ @@ -1239,6 +1569,7 @@ enum punit_power_well { */ #define DPLL_A_OFFSET 0x6014 #define DPLL_B_OFFSET 0x6018 +#define CHV_DPLL_C_OFFSET 0x6030 #define DPLL(pipe) (dev_priv->info.dpll_offsets[pipe] + \ dev_priv->info.display_mmio_offset) @@ -1273,10 +1604,23 @@ enum punit_power_well { #define DPLL_LOCK_VLV (1<<15) #define DPLL_INTEGRATED_CRI_CLK_VLV (1<<14) #define DPLL_INTEGRATED_CLOCK_VLV (1<<13) +#define DPLL_SSC_REF_CLOCK_CHV (1<<13) #define DPLL_PORTC_READY_MASK (0xf << 4) #define DPLL_PORTB_READY_MASK (0xf) #define DPLL_FPA01_P1_POST_DIV_MASK_I830 0x001f0000 + +/* Additional CHV pll/phy registers */ +#define DPIO_PHY_STATUS (VLV_DISPLAY_BASE + 0x6240) +#define DPLL_PORTD_READY_MASK (0xf) +#define DISPLAY_PHY_CONTROL (VLV_DISPLAY_BASE + 0x60100) +#define PHY_COM_LANE_RESET_DEASSERT(phy, val) \ + ((phy == DPIO_PHY0) ? (val | 1) : (val | 2)) +#define PHY_COM_LANE_RESET_ASSERT(phy, val) \ + ((phy == DPIO_PHY0) ? (val & ~1) : (val & ~2)) +#define DISPLAY_PHY_STATUS (VLV_DISPLAY_BASE + 0x60104) +#define PHY_POWERGOOD(phy) ((phy == DPIO_PHY0) ? (1<<31) : (1<<30)) + /* * The i830 generation, in LVDS mode, defines P1 as the bit number set within * this field (only one bit may be set). @@ -1317,6 +1661,7 @@ enum punit_power_well { #define DPLL_A_MD_OFFSET 0x601c /* 965+ only */ #define DPLL_B_MD_OFFSET 0x6020 /* 965+ only */ +#define CHV_DPLL_C_MD_OFFSET 0x603c #define DPLL_MD(pipe) (dev_priv->info.dpll_md_offsets[pipe] + \ dev_priv->info.display_mmio_offset) @@ -1416,7 +1761,7 @@ enum punit_power_well { # define DPIOUNIT_CLOCK_GATE_DISABLE (1 << 6) /* 915-945 */ # define OVFUNIT_CLOCK_GATE_DISABLE (1 << 5) # define OVBUNIT_CLOCK_GATE_DISABLE (1 << 4) -/** +/* * This bit must be set on the 830 to prevent hangs when turning off the * overlay scaler. */ @@ -1436,12 +1781,12 @@ enum punit_power_well { # define COLOR_CALCULATOR_CLOCK_GATE_DISABLE (1 << 7) # define MOTION_COMP_CLOCK_GATE_DISABLE (1 << 6) # define MAG_CLOCK_GATE_DISABLE (1 << 5) -/** This bit must be unset on 855,865 */ +/* This bit must be unset on 855,865 */ # define MECI_CLOCK_GATE_DISABLE (1 << 4) # define DCMP_CLOCK_GATE_DISABLE (1 << 3) # define MEC_CLOCK_GATE_DISABLE (1 << 2) # define MECO_CLOCK_GATE_DISABLE (1 << 1) -/** This bit must be set on 855,865. */ +/* This bit must be set on 855,865. */ # define SV_CLOCK_GATE_DISABLE (1 << 0) # define I915_MPEG_CLOCK_GATE_DISABLE (1 << 16) # define I915_VLD_IP_PR_CLOCK_GATE_DISABLE (1 << 15) @@ -1462,14 +1807,14 @@ enum punit_power_well { # define I915_BY_CLOCK_GATE_DISABLE (1 << 0) # define I965_RCZ_CLOCK_GATE_DISABLE (1 << 30) -/** This bit must always be set on 965G/965GM */ +/* This bit must always be set on 965G/965GM */ # define I965_RCC_CLOCK_GATE_DISABLE (1 << 29) # define I965_RCPB_CLOCK_GATE_DISABLE (1 << 28) # define I965_DAP_CLOCK_GATE_DISABLE (1 << 27) # define I965_ROC_CLOCK_GATE_DISABLE (1 << 26) # define I965_GW_CLOCK_GATE_DISABLE (1 << 25) # define I965_TD_CLOCK_GATE_DISABLE (1 << 24) -/** This bit must always be set on 965G */ +/* This bit must always be set on 965G */ # define I965_ISC_CLOCK_GATE_DISABLE (1 << 23) # define I965_IC_CLOCK_GATE_DISABLE (1 << 22) # define I965_EU_CLOCK_GATE_DISABLE (1 << 21) @@ -1494,6 +1839,10 @@ enum punit_power_well { #define VF_UNIT_CLOCK_GATE_DISABLE (1 << 9) #define GS_UNIT_CLOCK_GATE_DISABLE (1 << 7) #define CL_UNIT_CLOCK_GATE_DISABLE (1 << 6) + +#define VDECCLK_GATE_D 0x620C /* g4x only */ +#define VCP_UNIT_CLOCK_GATE_DISABLE (1 << 4) + #define RAMCLK_GATE_D 0x6210 /* CRL only */ #define DEUC 0x6214 /* CRL only */ @@ -1513,6 +1862,7 @@ enum punit_power_well { */ #define PALETTE_A_OFFSET 0xa000 #define PALETTE_B_OFFSET 0xa800 +#define CHV_PALETTE_C_OFFSET 0xc000 #define PALETTE(pipe) (dev_priv->info.palette_offsets[pipe] + \ dev_priv->info.display_mmio_offset) @@ -1535,7 +1885,7 @@ enum punit_power_well { /* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */ #define DCLK (MCHBAR_MIRROR_BASE_SNB + 0x5e04) -/** 915-945 and GM965 MCH register controlling DRAM channel access */ +/* 915-945 and GM965 MCH register controlling DRAM channel access */ #define DCC 0x10200 #define DCC_ADDRESSING_MODE_SINGLE_CHANNEL (0 << 0) #define DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC (1 << 0) @@ -1544,15 +1894,15 @@ enum punit_power_well { #define DCC_CHANNEL_XOR_DISABLE (1 << 10) #define DCC_CHANNEL_XOR_BIT_17 (1 << 9) -/** Pineview MCH register contains DDR3 setting */ +/* Pineview MCH register contains DDR3 setting */ #define CSHRDDR3CTL 0x101a8 #define CSHRDDR3CTL_DDR3 (1 << 2) -/** 965 MCH register controlling DRAM channel configuration */ +/* 965 MCH register controlling DRAM channel configuration */ #define C0DRB3 0x10206 #define C1DRB3 0x10606 -/** snb MCH registers for reading the DRAM channel configuration */ +/* snb MCH registers for reading the DRAM channel configuration */ #define MAD_DIMM_C0 (MCHBAR_MIRROR_BASE_SNB + 0x5004) #define MAD_DIMM_C1 (MCHBAR_MIRROR_BASE_SNB + 0x5008) #define MAD_DIMM_C2 (MCHBAR_MIRROR_BASE_SNB + 0x500C) @@ -1574,7 +1924,7 @@ enum punit_power_well { #define MAD_DIMM_A_SIZE_SHIFT 0 #define MAD_DIMM_A_SIZE_MASK (0xff << MAD_DIMM_A_SIZE_SHIFT) -/** snb MCH registers for priority tuning */ +/* snb MCH registers for priority tuning */ #define MCH_SSKPD (MCHBAR_MIRROR_BASE_SNB + 0x5d10) #define MCH_SSKPD_WM0_MASK 0x3f #define MCH_SSKPD_WM0_VAL 0xc @@ -2002,6 +2352,7 @@ enum punit_power_well { #define TRANSCODER_A_OFFSET 0x60000 #define TRANSCODER_B_OFFSET 0x61000 #define TRANSCODER_C_OFFSET 0x62000 +#define CHV_TRANSCODER_C_OFFSET 0x63000 #define TRANSCODER_EDP_OFFSET 0x6f000 #define _TRANSCODER2(pipe, reg) (dev_priv->info.trans_offsets[(pipe)] - \ @@ -2226,6 +2577,7 @@ enum punit_power_well { #define GEN3_SDVOC 0x61160 #define GEN4_HDMIB GEN3_SDVOB #define GEN4_HDMIC GEN3_SDVOC +#define CHV_HDMID 0x6116C #define PCH_SDVOB 0xe1140 #define PCH_HDMIB PCH_SDVOB #define PCH_HDMIC 0xe1150 @@ -2246,7 +2598,7 @@ enum punit_power_well { #define SDVO_PIPE_B_SELECT (1 << 30) #define SDVO_STALL_SELECT (1 << 29) #define SDVO_INTERRUPT_ENABLE (1 << 26) -/** +/* * 915G/GM SDVO pixel multiplier. * Programmed value is multiplier - 1, up to 5x. * \sa DPLL_MD_UDI_MULTIPLIER_MASK @@ -2286,6 +2638,10 @@ enum punit_power_well { #define SDVO_PIPE_SEL_CPT(pipe) ((pipe) << 29) #define SDVO_PIPE_SEL_MASK_CPT (3 << 29) +/* CHV SDVO/HDMI bits: */ +#define SDVO_PIPE_SEL_CHV(pipe) ((pipe) << 24) +#define SDVO_PIPE_SEL_MASK_CHV (3 << 24) + /* DVO port control */ #define DVOA 0x61120 @@ -2556,65 +2912,65 @@ enum punit_power_well { /* TV port control */ #define TV_CTL 0x68000 -/** Enables the TV encoder */ +/* Enables the TV encoder */ # define TV_ENC_ENABLE (1 << 31) -/** Sources the TV encoder input from pipe B instead of A. */ +/* Sources the TV encoder input from pipe B instead of A. */ # define TV_ENC_PIPEB_SELECT (1 << 30) -/** Outputs composite video (DAC A only) */ +/* Outputs composite video (DAC A only) */ # define TV_ENC_OUTPUT_COMPOSITE (0 << 28) -/** Outputs SVideo video (DAC B/C) */ +/* Outputs SVideo video (DAC B/C) */ # define TV_ENC_OUTPUT_SVIDEO (1 << 28) -/** Outputs Component video (DAC A/B/C) */ +/* Outputs Component video (DAC A/B/C) */ # define TV_ENC_OUTPUT_COMPONENT (2 << 28) -/** Outputs Composite and SVideo (DAC A/B/C) */ +/* Outputs Composite and SVideo (DAC A/B/C) */ # define TV_ENC_OUTPUT_SVIDEO_COMPOSITE (3 << 28) # define TV_TRILEVEL_SYNC (1 << 21) -/** Enables slow sync generation (945GM only) */ +/* Enables slow sync generation (945GM only) */ # define TV_SLOW_SYNC (1 << 20) -/** Selects 4x oversampling for 480i and 576p */ +/* Selects 4x oversampling for 480i and 576p */ # define TV_OVERSAMPLE_4X (0 << 18) -/** Selects 2x oversampling for 720p and 1080i */ +/* Selects 2x oversampling for 720p and 1080i */ # define TV_OVERSAMPLE_2X (1 << 18) -/** Selects no oversampling for 1080p */ +/* Selects no oversampling for 1080p */ # define TV_OVERSAMPLE_NONE (2 << 18) -/** Selects 8x oversampling */ +/* Selects 8x oversampling */ # define TV_OVERSAMPLE_8X (3 << 18) -/** Selects progressive mode rather than interlaced */ +/* Selects progressive mode rather than interlaced */ # define TV_PROGRESSIVE (1 << 17) -/** Sets the colorburst to PAL mode. Required for non-M PAL modes. */ +/* Sets the colorburst to PAL mode. Required for non-M PAL modes. */ # define TV_PAL_BURST (1 << 16) -/** Field for setting delay of Y compared to C */ +/* Field for setting delay of Y compared to C */ # define TV_YC_SKEW_MASK (7 << 12) -/** Enables a fix for 480p/576p standard definition modes on the 915GM only */ +/* Enables a fix for 480p/576p standard definition modes on the 915GM only */ # define TV_ENC_SDP_FIX (1 << 11) -/** +/* * Enables a fix for the 915GM only. * * Not sure what it does. */ # define TV_ENC_C0_FIX (1 << 10) -/** Bits that must be preserved by software */ +/* Bits that must be preserved by software */ # define TV_CTL_SAVE ((1 << 11) | (3 << 9) | (7 << 6) | 0xf) # define TV_FUSE_STATE_MASK (3 << 4) -/** Read-only state that reports all features enabled */ +/* Read-only state that reports all features enabled */ # define TV_FUSE_STATE_ENABLED (0 << 4) -/** Read-only state that reports that Macrovision is disabled in hardware*/ +/* Read-only state that reports that Macrovision is disabled in hardware*/ # define TV_FUSE_STATE_NO_MACROVISION (1 << 4) -/** Read-only state that reports that TV-out is disabled in hardware. */ +/* Read-only state that reports that TV-out is disabled in hardware. */ # define TV_FUSE_STATE_DISABLED (2 << 4) -/** Normal operation */ +/* Normal operation */ # define TV_TEST_MODE_NORMAL (0 << 0) -/** Encoder test pattern 1 - combo pattern */ +/* Encoder test pattern 1 - combo pattern */ # define TV_TEST_MODE_PATTERN_1 (1 << 0) -/** Encoder test pattern 2 - full screen vertical 75% color bars */ +/* Encoder test pattern 2 - full screen vertical 75% color bars */ # define TV_TEST_MODE_PATTERN_2 (2 << 0) -/** Encoder test pattern 3 - full screen horizontal 75% color bars */ +/* Encoder test pattern 3 - full screen horizontal 75% color bars */ # define TV_TEST_MODE_PATTERN_3 (3 << 0) -/** Encoder test pattern 4 - random noise */ +/* Encoder test pattern 4 - random noise */ # define TV_TEST_MODE_PATTERN_4 (4 << 0) -/** Encoder test pattern 5 - linear color ramps */ +/* Encoder test pattern 5 - linear color ramps */ # define TV_TEST_MODE_PATTERN_5 (5 << 0) -/** +/* * This test mode forces the DACs to 50% of full output. * * This is used for load detection in combination with TVDAC_SENSE_MASK @@ -2624,35 +2980,35 @@ enum punit_power_well { #define TV_DAC 0x68004 # define TV_DAC_SAVE 0x00ffff00 -/** +/* * Reports that DAC state change logic has reported change (RO). * * This gets cleared when TV_DAC_STATE_EN is cleared */ # define TVDAC_STATE_CHG (1 << 31) # define TVDAC_SENSE_MASK (7 << 28) -/** Reports that DAC A voltage is above the detect threshold */ +/* Reports that DAC A voltage is above the detect threshold */ # define TVDAC_A_SENSE (1 << 30) -/** Reports that DAC B voltage is above the detect threshold */ +/* Reports that DAC B voltage is above the detect threshold */ # define TVDAC_B_SENSE (1 << 29) -/** Reports that DAC C voltage is above the detect threshold */ +/* Reports that DAC C voltage is above the detect threshold */ # define TVDAC_C_SENSE (1 << 28) -/** +/* * Enables DAC state detection logic, for load-based TV detection. * * The PLL of the chosen pipe (in TV_CTL) must be running, and the encoder set * to off, for load detection to work. */ # define TVDAC_STATE_CHG_EN (1 << 27) -/** Sets the DAC A sense value to high */ +/* Sets the DAC A sense value to high */ # define TVDAC_A_SENSE_CTL (1 << 26) -/** Sets the DAC B sense value to high */ +/* Sets the DAC B sense value to high */ # define TVDAC_B_SENSE_CTL (1 << 25) -/** Sets the DAC C sense value to high */ +/* Sets the DAC C sense value to high */ # define TVDAC_C_SENSE_CTL (1 << 24) -/** Overrides the ENC_ENABLE and DAC voltage levels */ +/* Overrides the ENC_ENABLE and DAC voltage levels */ # define DAC_CTL_OVERRIDE (1 << 7) -/** Sets the slew rate. Must be preserved in software */ +/* Sets the slew rate. Must be preserved in software */ # define ENC_TVDAC_SLEW_FAST (1 << 6) # define DAC_A_1_3_V (0 << 4) # define DAC_A_1_1_V (1 << 4) @@ -2667,7 +3023,7 @@ enum punit_power_well { # define DAC_C_0_7_V (2 << 0) # define DAC_C_MASK (3 << 0) -/** +/* * CSC coefficients are stored in a floating point format with 9 bits of * mantissa and 2 or 3 bits of exponent. The exponent is represented as 2**-n, * where 2-bit exponents are unsigned n, and 3-bit exponents are signed n with @@ -2682,7 +3038,7 @@ enum punit_power_well { #define TV_CSC_Y2 0x68014 # define TV_BY_MASK 0x07ff0000 # define TV_BY_SHIFT 16 -/** +/* * Y attenuation for component video. * * Stored in 1.9 fixed point. @@ -2699,7 +3055,7 @@ enum punit_power_well { #define TV_CSC_U2 0x6801c # define TV_BU_MASK 0x07ff0000 # define TV_BU_SHIFT 16 -/** +/* * U attenuation for component video. * * Stored in 1.9 fixed point. @@ -2716,7 +3072,7 @@ enum punit_power_well { #define TV_CSC_V2 0x68024 # define TV_BV_MASK 0x07ff0000 # define TV_BV_SHIFT 16 -/** +/* * V attenuation for component video. * * Stored in 1.9 fixed point. @@ -2725,74 +3081,74 @@ enum punit_power_well { # define TV_AV_SHIFT 0 #define TV_CLR_KNOBS 0x68028 -/** 2s-complement brightness adjustment */ +/* 2s-complement brightness adjustment */ # define TV_BRIGHTNESS_MASK 0xff000000 # define TV_BRIGHTNESS_SHIFT 24 -/** Contrast adjustment, as a 2.6 unsigned floating point number */ +/* Contrast adjustment, as a 2.6 unsigned floating point number */ # define TV_CONTRAST_MASK 0x00ff0000 # define TV_CONTRAST_SHIFT 16 -/** Saturation adjustment, as a 2.6 unsigned floating point number */ +/* Saturation adjustment, as a 2.6 unsigned floating point number */ # define TV_SATURATION_MASK 0x0000ff00 # define TV_SATURATION_SHIFT 8 -/** Hue adjustment, as an integer phase angle in degrees */ +/* Hue adjustment, as an integer phase angle in degrees */ # define TV_HUE_MASK 0x000000ff # define TV_HUE_SHIFT 0 #define TV_CLR_LEVEL 0x6802c -/** Controls the DAC level for black */ +/* Controls the DAC level for black */ # define TV_BLACK_LEVEL_MASK 0x01ff0000 # define TV_BLACK_LEVEL_SHIFT 16 -/** Controls the DAC level for blanking */ +/* Controls the DAC level for blanking */ # define TV_BLANK_LEVEL_MASK 0x000001ff # define TV_BLANK_LEVEL_SHIFT 0 #define TV_H_CTL_1 0x68030 -/** Number of pixels in the hsync. */ +/* Number of pixels in the hsync. */ # define TV_HSYNC_END_MASK 0x1fff0000 # define TV_HSYNC_END_SHIFT 16 -/** Total number of pixels minus one in the line (display and blanking). */ +/* Total number of pixels minus one in the line (display and blanking). */ # define TV_HTOTAL_MASK 0x00001fff # define TV_HTOTAL_SHIFT 0 #define TV_H_CTL_2 0x68034 -/** Enables the colorburst (needed for non-component color) */ +/* Enables the colorburst (needed for non-component color) */ # define TV_BURST_ENA (1 << 31) -/** Offset of the colorburst from the start of hsync, in pixels minus one. */ +/* Offset of the colorburst from the start of hsync, in pixels minus one. */ # define TV_HBURST_START_SHIFT 16 # define TV_HBURST_START_MASK 0x1fff0000 -/** Length of the colorburst */ +/* Length of the colorburst */ # define TV_HBURST_LEN_SHIFT 0 # define TV_HBURST_LEN_MASK 0x0001fff #define TV_H_CTL_3 0x68038 -/** End of hblank, measured in pixels minus one from start of hsync */ +/* End of hblank, measured in pixels minus one from start of hsync */ # define TV_HBLANK_END_SHIFT 16 # define TV_HBLANK_END_MASK 0x1fff0000 -/** Start of hblank, measured in pixels minus one from start of hsync */ +/* Start of hblank, measured in pixels minus one from start of hsync */ # define TV_HBLANK_START_SHIFT 0 # define TV_HBLANK_START_MASK 0x0001fff #define TV_V_CTL_1 0x6803c -/** XXX */ +/* XXX */ # define TV_NBR_END_SHIFT 16 # define TV_NBR_END_MASK 0x07ff0000 -/** XXX */ +/* XXX */ # define TV_VI_END_F1_SHIFT 8 # define TV_VI_END_F1_MASK 0x00003f00 -/** XXX */ +/* XXX */ # define TV_VI_END_F2_SHIFT 0 # define TV_VI_END_F2_MASK 0x0000003f #define TV_V_CTL_2 0x68040 -/** Length of vsync, in half lines */ +/* Length of vsync, in half lines */ # define TV_VSYNC_LEN_MASK 0x07ff0000 # define TV_VSYNC_LEN_SHIFT 16 -/** Offset of the start of vsync in field 1, measured in one less than the +/* Offset of the start of vsync in field 1, measured in one less than the * number of half lines. */ # define TV_VSYNC_START_F1_MASK 0x00007f00 # define TV_VSYNC_START_F1_SHIFT 8 -/** +/* * Offset of the start of vsync in field 2, measured in one less than the * number of half lines. */ @@ -2800,17 +3156,17 @@ enum punit_power_well { # define TV_VSYNC_START_F2_SHIFT 0 #define TV_V_CTL_3 0x68044 -/** Enables generation of the equalization signal */ +/* Enables generation of the equalization signal */ # define TV_EQUAL_ENA (1 << 31) -/** Length of vsync, in half lines */ +/* Length of vsync, in half lines */ # define TV_VEQ_LEN_MASK 0x007f0000 # define TV_VEQ_LEN_SHIFT 16 -/** Offset of the start of equalization in field 1, measured in one less than +/* Offset of the start of equalization in field 1, measured in one less than * the number of half lines. */ # define TV_VEQ_START_F1_MASK 0x0007f00 # define TV_VEQ_START_F1_SHIFT 8 -/** +/* * Offset of the start of equalization in field 2, measured in one less than * the number of half lines. */ @@ -2818,13 +3174,13 @@ enum punit_power_well { # define TV_VEQ_START_F2_SHIFT 0 #define TV_V_CTL_4 0x68048 -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F1_MASK 0x003f0000 # define TV_VBURST_START_F1_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2832,13 +3188,13 @@ enum punit_power_well { # define TV_VBURST_END_F1_SHIFT 0 #define TV_V_CTL_5 0x6804c -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F2_MASK 0x003f0000 # define TV_VBURST_START_F2_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2846,13 +3202,13 @@ enum punit_power_well { # define TV_VBURST_END_F2_SHIFT 0 #define TV_V_CTL_6 0x68050 -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F3_MASK 0x003f0000 # define TV_VBURST_START_F3_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2860,13 +3216,13 @@ enum punit_power_well { # define TV_VBURST_END_F3_SHIFT 0 #define TV_V_CTL_7 0x68054 -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F4_MASK 0x003f0000 # define TV_VBURST_START_F4_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2874,56 +3230,56 @@ enum punit_power_well { # define TV_VBURST_END_F4_SHIFT 0 #define TV_SC_CTL_1 0x68060 -/** Turns on the first subcarrier phase generation DDA */ +/* Turns on the first subcarrier phase generation DDA */ # define TV_SC_DDA1_EN (1 << 31) -/** Turns on the first subcarrier phase generation DDA */ +/* Turns on the first subcarrier phase generation DDA */ # define TV_SC_DDA2_EN (1 << 30) -/** Turns on the first subcarrier phase generation DDA */ +/* Turns on the first subcarrier phase generation DDA */ # define TV_SC_DDA3_EN (1 << 29) -/** Sets the subcarrier DDA to reset frequency every other field */ +/* Sets the subcarrier DDA to reset frequency every other field */ # define TV_SC_RESET_EVERY_2 (0 << 24) -/** Sets the subcarrier DDA to reset frequency every fourth field */ +/* Sets the subcarrier DDA to reset frequency every fourth field */ # define TV_SC_RESET_EVERY_4 (1 << 24) -/** Sets the subcarrier DDA to reset frequency every eighth field */ +/* Sets the subcarrier DDA to reset frequency every eighth field */ # define TV_SC_RESET_EVERY_8 (2 << 24) -/** Sets the subcarrier DDA to never reset the frequency */ +/* Sets the subcarrier DDA to never reset the frequency */ # define TV_SC_RESET_NEVER (3 << 24) -/** Sets the peak amplitude of the colorburst.*/ +/* Sets the peak amplitude of the colorburst.*/ # define TV_BURST_LEVEL_MASK 0x00ff0000 # define TV_BURST_LEVEL_SHIFT 16 -/** Sets the increment of the first subcarrier phase generation DDA */ +/* Sets the increment of the first subcarrier phase generation DDA */ # define TV_SCDDA1_INC_MASK 0x00000fff # define TV_SCDDA1_INC_SHIFT 0 #define TV_SC_CTL_2 0x68064 -/** Sets the rollover for the second subcarrier phase generation DDA */ +/* Sets the rollover for the second subcarrier phase generation DDA */ # define TV_SCDDA2_SIZE_MASK 0x7fff0000 # define TV_SCDDA2_SIZE_SHIFT 16 -/** Sets the increent of the second subcarrier phase generation DDA */ +/* Sets the increent of the second subcarrier phase generation DDA */ # define TV_SCDDA2_INC_MASK 0x00007fff # define TV_SCDDA2_INC_SHIFT 0 #define TV_SC_CTL_3 0x68068 -/** Sets the rollover for the third subcarrier phase generation DDA */ +/* Sets the rollover for the third subcarrier phase generation DDA */ # define TV_SCDDA3_SIZE_MASK 0x7fff0000 # define TV_SCDDA3_SIZE_SHIFT 16 -/** Sets the increent of the third subcarrier phase generation DDA */ +/* Sets the increent of the third subcarrier phase generation DDA */ # define TV_SCDDA3_INC_MASK 0x00007fff # define TV_SCDDA3_INC_SHIFT 0 #define TV_WIN_POS 0x68070 -/** X coordinate of the display from the start of horizontal active */ +/* X coordinate of the display from the start of horizontal active */ # define TV_XPOS_MASK 0x1fff0000 # define TV_XPOS_SHIFT 16 -/** Y coordinate of the display from the start of vertical active (NBR) */ +/* Y coordinate of the display from the start of vertical active (NBR) */ # define TV_YPOS_MASK 0x00000fff # define TV_YPOS_SHIFT 0 #define TV_WIN_SIZE 0x68074 -/** Horizontal size of the display window, measured in pixels*/ +/* Horizontal size of the display window, measured in pixels*/ # define TV_XSIZE_MASK 0x1fff0000 # define TV_XSIZE_SHIFT 16 -/** +/* * Vertical size of the display window, measured in pixels. * * Must be even for interlaced modes. @@ -2932,28 +3288,28 @@ enum punit_power_well { # define TV_YSIZE_SHIFT 0 #define TV_FILTER_CTL_1 0x68080 -/** +/* * Enables automatic scaling calculation. * * If set, the rest of the registers are ignored, and the calculated values can * be read back from the register. */ # define TV_AUTO_SCALE (1 << 31) -/** +/* * Disables the vertical filter. * * This is required on modes more than 1024 pixels wide */ # define TV_V_FILTER_BYPASS (1 << 29) -/** Enables adaptive vertical filtering */ +/* Enables adaptive vertical filtering */ # define TV_VADAPT (1 << 28) # define TV_VADAPT_MODE_MASK (3 << 26) -/** Selects the least adaptive vertical filtering mode */ +/* Selects the least adaptive vertical filtering mode */ # define TV_VADAPT_MODE_LEAST (0 << 26) -/** Selects the moderately adaptive vertical filtering mode */ +/* Selects the moderately adaptive vertical filtering mode */ # define TV_VADAPT_MODE_MODERATE (1 << 26) -/** Selects the most adaptive vertical filtering mode */ +/* Selects the most adaptive vertical filtering mode */ # define TV_VADAPT_MODE_MOST (3 << 26) -/** +/* * Sets the horizontal scaling factor. * * This should be the fractional part of the horizontal scaling factor divided @@ -2965,14 +3321,14 @@ enum punit_power_well { # define TV_HSCALE_FRAC_SHIFT 0 #define TV_FILTER_CTL_2 0x68084 -/** +/* * Sets the integer part of the 3.15 fixed-point vertical scaling factor. * * TV_VSCALE should be (src height - 1) / ((interlace * dest height) - 1) */ # define TV_VSCALE_INT_MASK 0x00038000 # define TV_VSCALE_INT_SHIFT 15 -/** +/* * Sets the fractional part of the 3.15 fixed-point vertical scaling factor. * * \sa TV_VSCALE_INT_MASK @@ -2981,7 +3337,7 @@ enum punit_power_well { # define TV_VSCALE_FRAC_SHIFT 0 #define TV_FILTER_CTL_3 0x68088 -/** +/* * Sets the integer part of the 3.15 fixed-point vertical scaling factor. * * TV_VSCALE should be (src height - 1) / (1/4 * (dest height - 1)) @@ -2990,7 +3346,7 @@ enum punit_power_well { */ # define TV_VSCALE_IP_INT_MASK 0x00038000 # define TV_VSCALE_IP_INT_SHIFT 15 -/** +/* * Sets the fractional part of the 3.15 fixed-point vertical scaling factor. * * For progressive modes, TV_VSCALE_IP_INT should be set to zeroes. @@ -3002,26 +3358,26 @@ enum punit_power_well { #define TV_CC_CONTROL 0x68090 # define TV_CC_ENABLE (1 << 31) -/** +/* * Specifies which field to send the CC data in. * * CC data is usually sent in field 0. */ # define TV_CC_FID_MASK (1 << 27) # define TV_CC_FID_SHIFT 27 -/** Sets the horizontal position of the CC data. Usually 135. */ +/* Sets the horizontal position of the CC data. Usually 135. */ # define TV_CC_HOFF_MASK 0x03ff0000 # define TV_CC_HOFF_SHIFT 16 -/** Sets the vertical position of the CC data. Usually 21 */ +/* Sets the vertical position of the CC data. Usually 21 */ # define TV_CC_LINE_MASK 0x0000003f # define TV_CC_LINE_SHIFT 0 #define TV_CC_DATA 0x68094 # define TV_CC_RDY (1 << 31) -/** Second word of CC data to be transmitted. */ +/* Second word of CC data to be transmitted. */ # define TV_CC_DATA_2_MASK 0x007f0000 # define TV_CC_DATA_2_SHIFT 16 -/** First word of CC data to be transmitted. */ +/* First word of CC data to be transmitted. */ # define TV_CC_DATA_1_MASK 0x0000007f # define TV_CC_DATA_1_SHIFT 0 @@ -3043,6 +3399,8 @@ enum punit_power_well { #define DP_PORT_EN (1 << 31) #define DP_PIPEB_SELECT (1 << 30) #define DP_PIPE_MASK (1 << 30) +#define DP_PIPE_SELECT_CHV(pipe) ((pipe) << 16) +#define DP_PIPE_MASK_CHV (3 << 16) /* Link training mode - select a suitable mode for each stage */ #define DP_LINK_TRAIN_PAT_1 (0 << 28) @@ -3090,32 +3448,32 @@ enum punit_power_well { #define DP_PLL_FREQ_160MHZ (1 << 16) #define DP_PLL_FREQ_MASK (3 << 16) -/** locked once port is enabled */ +/* locked once port is enabled */ #define DP_PORT_REVERSAL (1 << 15) /* eDP */ #define DP_PLL_ENABLE (1 << 14) -/** sends the clock on lane 15 of the PEG for debug */ +/* sends the clock on lane 15 of the PEG for debug */ #define DP_CLOCK_OUTPUT_ENABLE (1 << 13) #define DP_SCRAMBLING_DISABLE (1 << 12) #define DP_SCRAMBLING_DISABLE_IRONLAKE (1 << 7) -/** limit RGB values to avoid confusing TVs */ +/* limit RGB values to avoid confusing TVs */ #define DP_COLOR_RANGE_16_235 (1 << 8) -/** Turn on the audio link */ +/* Turn on the audio link */ #define DP_AUDIO_OUTPUT_ENABLE (1 << 6) -/** vs and hs sync polarity */ +/* vs and hs sync polarity */ #define DP_SYNC_VS_HIGH (1 << 4) #define DP_SYNC_HS_HIGH (1 << 3) -/** A fantasy */ +/* A fantasy */ #define DP_DETECTED (1 << 2) -/** The aux channel provides a way to talk to the +/* The aux channel provides a way to talk to the * signal sink for DDC etc. Max packet size supported * is 20 bytes in each direction, hence the 5 fixed * data registers @@ -3258,6 +3616,7 @@ enum punit_power_well { #define PIPECONF_INTERLACED_DBL_ILK (4 << 21) /* ilk/snb only */ #define PIPECONF_PFIT_PF_INTERLACED_DBL_ILK (5 << 21) /* ilk/snb only */ #define PIPECONF_INTERLACE_MODE_MASK (7 << 21) +#define PIPECONF_EDP_RR_MODE_SWITCH (1 << 20) #define PIPECONF_CXSR_DOWNCLOCK (1<<16) #define PIPECONF_COLOR_RANGE_SELECT (1 << 13) #define PIPECONF_BPC_MASK (0x7 << 5) @@ -3276,6 +3635,7 @@ enum punit_power_well { #define SPRITE1_FLIP_DONE_INT_EN_VLV (1UL<<30) #define PIPE_CRC_ERROR_ENABLE (1UL<<29) #define PIPE_CRC_DONE_ENABLE (1UL<<28) +#define PERF_COUNTER2_INTERRUPT_EN (1UL<<27) #define PIPE_GMBUS_EVENT_ENABLE (1UL<<27) #define PLANE_FLIP_DONE_INT_EN_VLV (1UL<<26) #define PIPE_HOTPLUG_INTERRUPT_ENABLE (1UL<<26) @@ -3287,8 +3647,10 @@ enum punit_power_well { #define PIPE_ODD_FIELD_INTERRUPT_ENABLE (1UL<<21) #define PIPE_EVEN_FIELD_INTERRUPT_ENABLE (1UL<<20) #define PIPE_B_PSR_INTERRUPT_ENABLE_VLV (1UL<<19) +#define PERF_COUNTER_INTERRUPT_EN (1UL<<19) #define PIPE_HOTPLUG_TV_INTERRUPT_ENABLE (1UL<<18) /* pre-965 */ #define PIPE_START_VBLANK_INTERRUPT_ENABLE (1UL<<18) /* 965 or later */ +#define PIPE_FRAMESTART_INTERRUPT_ENABLE (1UL<<17) #define PIPE_VBLANK_INTERRUPT_ENABLE (1UL<<17) #define PIPEA_HBLANK_INT_EN_VLV (1UL<<16) #define PIPE_OVERLAY_UPDATED_ENABLE (1UL<<16) @@ -3296,6 +3658,7 @@ enum punit_power_well { #define SPRITE0_FLIP_DONE_INT_STATUS_VLV (1UL<<14) #define PIPE_CRC_ERROR_INTERRUPT_STATUS (1UL<<13) #define PIPE_CRC_DONE_INTERRUPT_STATUS (1UL<<12) +#define PERF_COUNTER2_INTERRUPT_STATUS (1UL<<11) #define PIPE_GMBUS_INTERRUPT_STATUS (1UL<<11) #define PLANE_FLIP_DONE_INT_STATUS_VLV (1UL<<10) #define PIPE_HOTPLUG_INTERRUPT_STATUS (1UL<<10) @@ -3304,20 +3667,25 @@ enum punit_power_well { #define PIPE_DPST_EVENT_STATUS (1UL<<7) #define PIPE_LEGACY_BLC_EVENT_STATUS (1UL<<6) #define PIPE_A_PSR_STATUS_VLV (1UL<<6) +#define PIPE_LEGACY_BLC_EVENT_STATUS (1UL<<6) #define PIPE_ODD_FIELD_INTERRUPT_STATUS (1UL<<5) #define PIPE_EVEN_FIELD_INTERRUPT_STATUS (1UL<<4) #define PIPE_B_PSR_STATUS_VLV (1UL<<3) +#define PERF_COUNTER_INTERRUPT_STATUS (1UL<<3) #define PIPE_HOTPLUG_TV_INTERRUPT_STATUS (1UL<<2) /* pre-965 */ #define PIPE_START_VBLANK_INTERRUPT_STATUS (1UL<<2) /* 965 or later */ +#define PIPE_FRAMESTART_INTERRUPT_STATUS (1UL<<1) #define PIPE_VBLANK_INTERRUPT_STATUS (1UL<<1) +#define PIPE_HBLANK_INT_STATUS (1UL<<0) #define PIPE_OVERLAY_UPDATED_STATUS (1UL<<0) #define PIPESTAT_INT_ENABLE_MASK 0x7fff0000 #define PIPESTAT_INT_STATUS_MASK 0x0000ffff -#define PIPE_A_OFFSET 0x70000 -#define PIPE_B_OFFSET 0x71000 -#define PIPE_C_OFFSET 0x72000 +#define PIPE_A_OFFSET 0x70000 +#define PIPE_B_OFFSET 0x71000 +#define PIPE_C_OFFSET 0x72000 +#define CHV_PIPE_C_OFFSET 0x74000 /* * There's actually no pipe EDP. Some pipe registers have * simply shifted from the pipe to the transcoder, while @@ -3355,14 +3723,25 @@ enum punit_power_well { #define SPRITED_FLIP_DONE_INT_EN (1<<26) #define SPRITEC_FLIP_DONE_INT_EN (1<<25) #define PLANEB_FLIP_DONE_INT_EN (1<<24) +#define PIPE_PSR_INT_EN (1<<22) #define PIPEA_LINE_COMPARE_INT_EN (1<<21) #define PIPEA_HLINE_INT_EN (1<<20) #define PIPEA_VBLANK_INT_EN (1<<19) #define SPRITEB_FLIP_DONE_INT_EN (1<<18) #define SPRITEA_FLIP_DONE_INT_EN (1<<17) #define PLANEA_FLIPDONE_INT_EN (1<<16) - -#define DPINVGTT (VLV_DISPLAY_BASE + 0x7002c) /* VLV only */ +#define PIPEC_LINE_COMPARE_INT_EN (1<<13) +#define PIPEC_HLINE_INT_EN (1<<12) +#define PIPEC_VBLANK_INT_EN (1<<11) +#define SPRITEF_FLIPDONE_INT_EN (1<<10) +#define SPRITEE_FLIPDONE_INT_EN (1<<9) +#define PLANEC_FLIPDONE_INT_EN (1<<8) + +#define DPINVGTT (VLV_DISPLAY_BASE + 0x7002c) /* VLV/CHV only */ +#define SPRITEF_INVALID_GTT_INT_EN (1<<27) +#define SPRITEE_INVALID_GTT_INT_EN (1<<26) +#define PLANEC_INVALID_GTT_INT_EN (1<<25) +#define CURSORC_INVALID_GTT_INT_EN (1<<24) #define CURSORB_INVALID_GTT_INT_EN (1<<23) #define CURSORA_INVALID_GTT_INT_EN (1<<22) #define SPRITED_INVALID_GTT_INT_EN (1<<21) @@ -3372,6 +3751,11 @@ enum punit_power_well { #define SPRITEA_INVALID_GTT_INT_EN (1<<17) #define PLANEA_INVALID_GTT_INT_EN (1<<16) #define DPINVGTT_EN_MASK 0xff0000 +#define DPINVGTT_EN_MASK_CHV 0xfff0000 +#define SPRITEF_INVALID_GTT_STATUS (1<<11) +#define SPRITEE_INVALID_GTT_STATUS (1<<10) +#define PLANEC_INVALID_GTT_STATUS (1<<9) +#define CURSORC_INVALID_GTT_STATUS (1<<8) #define CURSORB_INVALID_GTT_STATUS (1<<7) #define CURSORA_INVALID_GTT_STATUS (1<<6) #define SPRITED_INVALID_GTT_STATUS (1<<5) @@ -3381,6 +3765,7 @@ enum punit_power_well { #define SPRITEA_INVALID_GTT_STATUS (1<<1) #define PLANEA_INVALID_GTT_STATUS (1<<0) #define DPINVGTT_STATUS_MASK 0xff +#define DPINVGTT_STATUS_MASK_CHV 0xfff #define DSPARB 0x70030 #define DSPARB_CSTART_MASK (0x7f << 7) @@ -3420,14 +3805,43 @@ enum punit_power_well { #define DDL_CURSORA_PRECISION_32 (1<<31) #define DDL_CURSORA_PRECISION_16 (0<<31) #define DDL_CURSORA_SHIFT 24 +#define DDL_SPRITEB_PRECISION_32 (1<<23) +#define DDL_SPRITEB_PRECISION_16 (0<<23) +#define DDL_SPRITEB_SHIFT 16 +#define DDL_SPRITEA_PRECISION_32 (1<<15) +#define DDL_SPRITEA_PRECISION_16 (0<<15) +#define DDL_SPRITEA_SHIFT 8 #define DDL_PLANEA_PRECISION_32 (1<<7) #define DDL_PLANEA_PRECISION_16 (0<<7) +#define DDL_PLANEA_SHIFT 0 + #define VLV_DDL2 (VLV_DISPLAY_BASE + 0x70054) #define DDL_CURSORB_PRECISION_32 (1<<31) #define DDL_CURSORB_PRECISION_16 (0<<31) #define DDL_CURSORB_SHIFT 24 +#define DDL_SPRITED_PRECISION_32 (1<<23) +#define DDL_SPRITED_PRECISION_16 (0<<23) +#define DDL_SPRITED_SHIFT 16 +#define DDL_SPRITEC_PRECISION_32 (1<<15) +#define DDL_SPRITEC_PRECISION_16 (0<<15) +#define DDL_SPRITEC_SHIFT 8 #define DDL_PLANEB_PRECISION_32 (1<<7) #define DDL_PLANEB_PRECISION_16 (0<<7) +#define DDL_PLANEB_SHIFT 0 + +#define VLV_DDL3 (VLV_DISPLAY_BASE + 0x70058) +#define DDL_CURSORC_PRECISION_32 (1<<31) +#define DDL_CURSORC_PRECISION_16 (0<<31) +#define DDL_CURSORC_SHIFT 24 +#define DDL_SPRITEF_PRECISION_32 (1<<23) +#define DDL_SPRITEF_PRECISION_16 (0<<23) +#define DDL_SPRITEF_SHIFT 16 +#define DDL_SPRITEE_PRECISION_32 (1<<15) +#define DDL_SPRITEE_PRECISION_16 (0<<15) +#define DDL_SPRITEE_SHIFT 8 +#define DDL_PLANEC_PRECISION_32 (1<<7) +#define DDL_PLANEC_PRECISION_16 (0<<7) +#define DDL_PLANEC_SHIFT 0 /* FIFO watermark sizes etc */ #define G4X_FIFO_LINE_SIZE 64 @@ -3535,12 +3949,13 @@ 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) +#define PIPE_FLIPCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FLIPCOUNT_GM45) /* Cursor A & B regs */ -#define _CURACNTR (dev_priv->info.display_mmio_offset + 0x70080) +#define _CURACNTR 0x70080 /* Old style CUR*CNTR flags (desktop 8xx) */ #define CURSOR_ENABLE 0x80000000 #define CURSOR_GAMMA_ENABLE 0x40000000 @@ -3567,28 +3982,34 @@ enum punit_power_well { #define MCURSOR_PIPE_B (1 << 28) #define MCURSOR_GAMMA_ENABLE (1 << 26) #define CURSOR_TRICKLE_FEED_DISABLE (1 << 14) -#define _CURABASE (dev_priv->info.display_mmio_offset + 0x70084) -#define _CURAPOS (dev_priv->info.display_mmio_offset + 0x70088) +#define _CURABASE 0x70084 +#define _CURAPOS 0x70088 #define CURSOR_POS_MASK 0x007FF #define CURSOR_POS_SIGN 0x8000 #define CURSOR_X_SHIFT 0 #define CURSOR_Y_SHIFT 16 #define CURSIZE 0x700a0 -#define _CURBCNTR (dev_priv->info.display_mmio_offset + 0x700c0) -#define _CURBBASE (dev_priv->info.display_mmio_offset + 0x700c4) -#define _CURBPOS (dev_priv->info.display_mmio_offset + 0x700c8) +#define _CURBCNTR 0x700c0 +#define _CURBBASE 0x700c4 +#define _CURBPOS 0x700c8 #define _CURBCNTR_IVB 0x71080 #define _CURBBASE_IVB 0x71084 #define _CURBPOS_IVB 0x71088 -#define CURCNTR(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR) -#define CURBASE(pipe) _PIPE(pipe, _CURABASE, _CURBBASE) -#define CURPOS(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS) +#define _CURSOR2(pipe, reg) (dev_priv->info.cursor_offsets[(pipe)] - \ + dev_priv->info.cursor_offsets[PIPE_A] + (reg) + \ + dev_priv->info.display_mmio_offset) + +#define CURCNTR(pipe) _CURSOR2(pipe, _CURACNTR) +#define CURBASE(pipe) _CURSOR2(pipe, _CURABASE) +#define CURPOS(pipe) _CURSOR2(pipe, _CURAPOS) -#define CURCNTR_IVB(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR_IVB) -#define CURBASE_IVB(pipe) _PIPE(pipe, _CURABASE, _CURBBASE_IVB) -#define CURPOS_IVB(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS_IVB) +#define CURSOR_A_OFFSET 0x70080 +#define CURSOR_B_OFFSET 0x700c0 +#define CHV_CURSOR_C_OFFSET 0x700e0 +#define IVB_CURSOR_B_OFFSET 0x71080 +#define IVB_CURSOR_C_OFFSET 0x72080 /* Display A control */ #define _DSPACNTR 0x70180 @@ -4093,6 +4514,7 @@ enum punit_power_well { #define GEN8_DE_PIPE_A_IRQ (1<<16) #define GEN8_DE_PIPE_IRQ(pipe) (1<<(16+pipe)) #define GEN8_GT_VECS_IRQ (1<<6) +#define GEN8_GT_PM_IRQ (1<<4) #define GEN8_GT_VCS2_IRQ (1<<3) #define GEN8_GT_VCS1_IRQ (1<<2) #define GEN8_GT_BCS_IRQ (1<<1) @@ -4120,7 +4542,7 @@ enum punit_power_well { #define GEN8_PIPE_SPRITE_FAULT (1 << 9) #define GEN8_PIPE_PRIMARY_FAULT (1 << 8) #define GEN8_PIPE_SPRITE_FLIP_DONE (1 << 5) -#define GEN8_PIPE_FLIP_DONE (1 << 4) +#define GEN8_PIPE_PRIMARY_FLIP_DONE (1 << 4) #define GEN8_PIPE_SCAN_LINE_EVENT (1 << 2) #define GEN8_PIPE_VSYNC (1 << 1) #define GEN8_PIPE_VBLANK (1 << 0) @@ -4832,6 +5254,8 @@ enum punit_power_well { #define PORT_TRANS_SEL_CPT(pipe) ((pipe) << 29) #define PORT_TO_PIPE(val) (((val) & (1<<30)) >> 30) #define PORT_TO_PIPE_CPT(val) (((val) & PORT_TRANS_SEL_MASK) >> 29) +#define SDVO_PORT_TO_PIPE_CHV(val) (((val) & (3<<24)) >> 24) +#define DP_PORT_TO_PIPE_CHV(val) (((val) & (3<<16)) >> 16) #define TRANS_DP_CTL_A 0xe0300 #define TRANS_DP_CTL_B 0xe1300 @@ -4888,6 +5312,8 @@ enum punit_power_well { #define EDP_LINK_TRAIN_VOL_EMP_MASK_IVB (0x3f<<22) +#define VLV_PMWGICZ 0x1300a4 + #define FORCEWAKE 0xA18C #define FORCEWAKE_VLV 0x1300b0 #define FORCEWAKE_ACK_VLV 0x1300b4 @@ -4896,15 +5322,22 @@ enum punit_power_well { #define FORCEWAKE_ACK_HSW 0x130044 #define FORCEWAKE_ACK 0x130090 #define VLV_GTLC_WAKE_CTRL 0x130090 +#define VLV_GTLC_RENDER_CTX_EXISTS (1 << 25) +#define VLV_GTLC_MEDIA_CTX_EXISTS (1 << 24) +#define VLV_GTLC_ALLOWWAKEREQ (1 << 0) + #define VLV_GTLC_PW_STATUS 0x130094 -#define VLV_GTLC_PW_RENDER_STATUS_MASK 0x80 -#define VLV_GTLC_PW_MEDIA_STATUS_MASK 0x20 +#define VLV_GTLC_ALLOWWAKEACK (1 << 0) +#define VLV_GTLC_ALLOWWAKEERR (1 << 1) +#define VLV_GTLC_PW_MEDIA_STATUS_MASK (1 << 5) +#define VLV_GTLC_PW_RENDER_STATUS_MASK (1 << 7) #define FORCEWAKE_MT 0xa188 /* multi-threaded */ #define FORCEWAKE_KERNEL 0x1 #define FORCEWAKE_USER 0x2 #define FORCEWAKE_MT_ACK 0x130040 #define ECOBUS 0xa180 #define FORCEWAKE_MT_ENABLE (1<<5) +#define VLV_SPAREG2H 0xA194 #define GTFIFODBG 0x120000 #define GT_FIFO_SBDROPERR (1<<6) @@ -4924,6 +5357,7 @@ enum punit_power_well { #define HSW_EDRAM_PRESENT 0x120010 #define GEN6_UCGCTL1 0x9400 +# define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE (1 << 16) # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -4934,12 +5368,19 @@ enum punit_power_well { # define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE (1 << 12) # define GEN6_RCCUNIT_CLOCK_GATE_DISABLE (1 << 11) +#define GEN6_UCGCTL3 0x9408 + #define GEN7_UCGCTL4 0x940c #define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25) +#define GEN6_RCGCTL1 0x9410 +#define GEN6_RCGCTL2 0x9414 +#define GEN6_RSTCTL 0x9420 + #define GEN8_UCGCTL6 0x9430 #define GEN8_SDEUNIT_CLOCK_GATE_DISABLE (1<<14) +#define GEN6_GFXPAUSE 0xA000 #define GEN6_RPNSWREQ 0xA008 #define GEN6_TURBO_DISABLE (1<<31) #define GEN6_FREQUENCY(x) ((x)<<25) @@ -4992,6 +5433,9 @@ enum punit_power_well { #define GEN6_RP_UP_EI 0xA068 #define GEN6_RP_DOWN_EI 0xA06C #define GEN6_RP_IDLE_HYSTERSIS 0xA070 +#define GEN6_RPDEUHWTC 0xA080 +#define GEN6_RPDEUC 0xA084 +#define GEN6_RPDEUCSW 0xA088 #define GEN6_RC_STATE 0xA094 #define GEN6_RC1_WAKE_RATE_LIMIT 0xA098 #define GEN6_RC6_WAKE_RATE_LIMIT 0xA09C @@ -4999,11 +5443,15 @@ enum punit_power_well { #define GEN6_RC_EVALUATION_INTERVAL 0xA0A8 #define GEN6_RC_IDLE_HYSTERSIS 0xA0AC #define GEN6_RC_SLEEP 0xA0B0 +#define GEN6_RCUBMABDTMR 0xA0B0 #define GEN6_RC1e_THRESHOLD 0xA0B4 #define GEN6_RC6_THRESHOLD 0xA0B8 #define GEN6_RC6p_THRESHOLD 0xA0BC +#define VLV_RCEDATA 0xA0BC #define GEN6_RC6pp_THRESHOLD 0xA0C0 #define GEN6_PMINTRMSK 0xA168 +#define GEN8_PMINTR_REDIRECT_TO_NON_DISP (1<<31) +#define VLV_PWRDWNUPCTL 0xA294 #define GEN6_PMISR 0x44020 #define GEN6_PMIMR 0x44024 /* rps_lock */ @@ -5020,6 +5468,9 @@ enum punit_power_well { GEN6_PM_RP_DOWN_THRESHOLD | \ GEN6_PM_RP_DOWN_TIMEOUT) +#define GEN7_GT_SCRATCH_BASE 0x4F100 +#define GEN7_GT_SCRATCH_REG_NUM 8 + #define VLV_GTLC_SURVIVABILITY_REG 0x130098 #define VLV_GFX_CLK_STATUS_BIT (1<<3) #define VLV_GFX_CLK_FORCE_ON_BIT (1<<2) @@ -5030,6 +5481,9 @@ enum punit_power_well { #define VLV_MEDIA_RC6_COUNT_EN (1<<1) #define VLV_RENDER_RC6_COUNT_EN (1<<0) #define GEN6_GT_GFX_RC6 0x138108 +#define VLV_GT_RENDER_RC6 0x138108 +#define VLV_GT_MEDIA_RC6 0x13810C + #define GEN6_GT_GFX_RC6p 0x13810C #define GEN6_GT_GFX_RC6pp 0x138110 diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 56785e8fb2eb..043123c77a1f 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -328,8 +328,6 @@ int i915_save_state(struct drm_device *dev) } } - intel_disable_gt_powersave(dev); - /* Cache mode state */ if (INTEL_INFO(dev)->gen < 7) dev_priv->regfile.saveCACHE_MODE_0 = I915_READ(CACHE_MODE_0); diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 9c57029f6f4b..86ce39aad0ff 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -186,7 +186,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj, struct drm_minor *dminor = dev_to_drm_minor(dev); struct drm_device *drm_dev = dminor->dev; struct drm_i915_private *dev_priv = drm_dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; u32 *temp = NULL; /* Just here to make handling failures easy */ int slice = (int)(uintptr_t)attr->private; int ret; @@ -263,6 +263,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev, flush_delayed_work(&dev_priv->rps.delayed_resume_work); + intel_runtime_pm_get(dev_priv); + mutex_lock(&dev_priv->rps.hw_lock); if (IS_VALLEYVIEW(dev_priv->dev)) { u32 freq; @@ -273,6 +275,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev, } mutex_unlock(&dev_priv->rps.hw_lock); + intel_runtime_pm_put(dev_priv); + return snprintf(buf, PAGE_SIZE, "%d\n", ret); } diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 23c26f1f8b37..f5aa0067755a 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -7,6 +7,7 @@ #include <drm/drmP.h> #include "i915_drv.h" +#include "intel_drv.h" #include "intel_ringbuffer.h" #undef TRACE_SYSTEM @@ -14,6 +15,80 @@ #define TRACE_SYSTEM_STRING __stringify(TRACE_SYSTEM) #define TRACE_INCLUDE_FILE i915_trace +/* pipe updates */ + +TRACE_EVENT(i915_pipe_update_start, + TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max), + TP_ARGS(crtc, min, max), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u32, min) + __field(u32, max) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, + crtc->pipe); + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->min = min; + __entry->max = max; + ), + + TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u", + pipe_name(__entry->pipe), __entry->frame, + __entry->scanline, __entry->min, __entry->max) +); + +TRACE_EVENT(i915_pipe_update_vblank_evaded, + TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max, u32 frame), + TP_ARGS(crtc, min, max, frame), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u32, min) + __field(u32, max) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = frame; + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->min = min; + __entry->max = max; + ), + + TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u", + pipe_name(__entry->pipe), __entry->frame, + __entry->scanline, __entry->min, __entry->max) +); + +TRACE_EVENT(i915_pipe_update_end, + TP_PROTO(struct intel_crtc *crtc, u32 frame), + TP_ARGS(crtc, frame), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = frame; + __entry->scanline = intel_get_crtc_scanline(crtc); + ), + + TP_printk("pipe %c, frame=%u, scanline=%u", + pipe_name(__entry->pipe), __entry->frame, + __entry->scanline) +); + /* object tracking */ TRACE_EVENT(i915_gem_object_create, @@ -251,8 +326,8 @@ TRACE_EVENT(i915_gem_evict_vm, ); TRACE_EVENT(i915_gem_ring_sync_to, - TP_PROTO(struct intel_ring_buffer *from, - struct intel_ring_buffer *to, + TP_PROTO(struct intel_engine_cs *from, + struct intel_engine_cs *to, u32 seqno), TP_ARGS(from, to, seqno), @@ -277,7 +352,7 @@ TRACE_EVENT(i915_gem_ring_sync_to, ); TRACE_EVENT(i915_gem_ring_dispatch, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno, u32 flags), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno, u32 flags), TP_ARGS(ring, seqno, flags), TP_STRUCT__entry( @@ -300,7 +375,7 @@ TRACE_EVENT(i915_gem_ring_dispatch, ); TRACE_EVENT(i915_gem_ring_flush, - TP_PROTO(struct intel_ring_buffer *ring, u32 invalidate, u32 flush), + TP_PROTO(struct intel_engine_cs *ring, u32 invalidate, u32 flush), TP_ARGS(ring, invalidate, flush), TP_STRUCT__entry( @@ -323,7 +398,7 @@ TRACE_EVENT(i915_gem_ring_flush, ); DECLARE_EVENT_CLASS(i915_gem_request, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno), TP_STRUCT__entry( @@ -343,12 +418,12 @@ DECLARE_EVENT_CLASS(i915_gem_request, ); DEFINE_EVENT(i915_gem_request, i915_gem_request_add, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno) ); TRACE_EVENT(i915_gem_request_complete, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring), TP_STRUCT__entry( @@ -368,12 +443,12 @@ TRACE_EVENT(i915_gem_request_complete, ); DEFINE_EVENT(i915_gem_request, i915_gem_request_retire, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno) ); TRACE_EVENT(i915_gem_request_wait_begin, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno), TP_STRUCT__entry( @@ -402,12 +477,12 @@ TRACE_EVENT(i915_gem_request_wait_begin, ); DEFINE_EVENT(i915_gem_request, i915_gem_request_wait_end, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno) ); DECLARE_EVENT_CLASS(i915_ring, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring), TP_STRUCT__entry( @@ -424,12 +499,12 @@ DECLARE_EVENT_CLASS(i915_ring, ); DEFINE_EVENT(i915_ring, i915_ring_wait_begin, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring) ); DEFINE_EVENT(i915_ring, i915_ring_wait_end, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring) ); diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index aff4a113cda3..1ee98f121a00 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -49,13 +49,19 @@ find_section(struct bdb_header *bdb, int section_id) total = bdb->bdb_size; /* walk the sections looking for section_id */ - while (index < total) { + while (index + 3 < total) { current_id = *(base + index); index++; + current_size = *((u16 *)(base + index)); index += 2; + + if (index + current_size > total) + return NULL; + if (current_id == section_id) return base + index; + index += current_size; } @@ -206,7 +212,7 @@ 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 +224,28 @@ 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; @@ -526,6 +554,16 @@ 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 @@ -628,19 +666,221 @@ parse_edp(struct drm_i915_private *dev_priv, struct bdb_header *bdb) } } +static u8 *goto_next_sequence(u8 *data, int *size) +{ + u16 len; + int tmp = *size; + + if (--tmp < 0) + return NULL; + + /* goto first element */ + data++; + while (1) { + switch (*data) { + case MIPI_SEQ_ELEM_SEND_PKT: + /* + * skip by this element payload size + * skip elem id, command flag and data type + */ + tmp -= 5; + if (tmp < 0) + return NULL; + + data += 3; + len = *((u16 *)data); + + tmp -= len; + if (tmp < 0) + return NULL; + + /* skip by len */ + data = data + 2 + len; + break; + case MIPI_SEQ_ELEM_DELAY: + /* skip by elem id, and delay is 4 bytes */ + tmp -= 5; + if (tmp < 0) + return NULL; + + data += 5; + break; + case MIPI_SEQ_ELEM_GPIO: + tmp -= 3; + if (tmp < 0) + return NULL; + + data += 3; + break; + default: + DRM_ERROR("Unknown element\n"); + return NULL; + } + + /* end of sequence ? */ + if (*data == 0) + break; + } + + /* goto next sequence or end of block byte */ + if (--tmp < 0) + return NULL; + + data++; + + /* update amount of data left for the sequence block to be parsed */ + *size = tmp; + return data; +} + static void parse_mipi(struct drm_i915_private *dev_priv, struct bdb_header *bdb) { - struct bdb_mipi *mipi; + struct bdb_mipi_config *start; + struct bdb_mipi_sequence *sequence; + struct mipi_config *config; + struct mipi_pps_data *pps; + u8 *data, *seq_data; + int i, panel_id, seq_size; + u16 block_size; + + /* parse MIPI blocks only if LFP type is MIPI */ + if (!dev_priv->vbt.has_mipi) + return; + + /* Initialize this to undefined indicating no generic MIPI support */ + dev_priv->vbt.dsi.panel_id = MIPI_DSI_UNDEFINED_PANEL_ID; + + /* Block #40 is already parsed and panel_fixed_mode is + * stored in dev_priv->lfp_lvds_vbt_mode + * resuse this when needed + */ + + /* Parse #52 for panel index used from panel_type already + * parsed + */ + start = find_section(bdb, BDB_MIPI_CONFIG); + if (!start) { + DRM_DEBUG_KMS("No MIPI config BDB found"); + return; + } + + DRM_DEBUG_DRIVER("Found MIPI Config block, panel index = %d\n", + panel_type); - mipi = find_section(bdb, BDB_MIPI_CONFIG); - if (!mipi) { - DRM_DEBUG_KMS("No MIPI BDB found"); + /* + * get hold of the correct configuration block and pps data as per + * the panel_type as index + */ + config = &start->config[panel_type]; + pps = &start->pps[panel_type]; + + /* store as of now full data. Trim when we realise all is not needed */ + dev_priv->vbt.dsi.config = kmemdup(config, sizeof(struct mipi_config), GFP_KERNEL); + if (!dev_priv->vbt.dsi.config) + return; + + dev_priv->vbt.dsi.pps = kmemdup(pps, sizeof(struct mipi_pps_data), GFP_KERNEL); + if (!dev_priv->vbt.dsi.pps) { + kfree(dev_priv->vbt.dsi.config); return; } - /* XXX: add more info */ + /* We have mandatory mipi config blocks. Initialize as generic panel */ dev_priv->vbt.dsi.panel_id = MIPI_DSI_GENERIC_PANEL_ID; + + /* Check if we have sequence block as well */ + sequence = find_section(bdb, BDB_MIPI_SEQUENCE); + if (!sequence) { + DRM_DEBUG_KMS("No MIPI Sequence found, parsing complete\n"); + return; + } + + DRM_DEBUG_DRIVER("Found MIPI sequence block\n"); + + block_size = get_blocksize(sequence); + + /* + * parse the sequence block for individual sequences + */ + dev_priv->vbt.dsi.seq_version = sequence->version; + + seq_data = &sequence->data[0]; + + /* + * sequence block is variable length and hence we need to parse and + * get the sequence data for specific panel id + */ + for (i = 0; i < MAX_MIPI_CONFIGURATIONS; i++) { + panel_id = *seq_data; + seq_size = *((u16 *) (seq_data + 1)); + if (panel_id == panel_type) + break; + + /* skip the sequence including seq header of 3 bytes */ + seq_data = seq_data + 3 + seq_size; + if ((seq_data - &sequence->data[0]) > block_size) { + DRM_ERROR("Sequence start is beyond sequence block size, corrupted sequence block\n"); + return; + } + } + + if (i == MAX_MIPI_CONFIGURATIONS) { + DRM_ERROR("Sequence block detected but no valid configuration\n"); + return; + } + + /* check if found sequence is completely within the sequence block + * just being paranoid */ + if (seq_size > block_size) { + DRM_ERROR("Corrupted sequence/size, bailing out\n"); + return; + } + + /* skip the panel id(1 byte) and seq size(2 bytes) */ + dev_priv->vbt.dsi.data = kmemdup(seq_data + 3, seq_size, GFP_KERNEL); + if (!dev_priv->vbt.dsi.data) + return; + + /* + * loop into the sequence data and split into multiple sequneces + * There are only 5 types of sequences as of now + */ + data = dev_priv->vbt.dsi.data; + dev_priv->vbt.dsi.size = seq_size; + + /* two consecutive 0x00 indicate end of all sequences */ + while (1) { + int seq_id = *data; + if (MIPI_SEQ_MAX > seq_id && seq_id > MIPI_SEQ_UNDEFINED) { + dev_priv->vbt.dsi.sequence[seq_id] = data; + DRM_DEBUG_DRIVER("Found mipi sequence - %d\n", seq_id); + } else { + DRM_ERROR("undefined sequence\n"); + goto err; + } + + /* partial parsing to skip elements */ + data = goto_next_sequence(data, &seq_size); + + if (data == NULL) { + DRM_ERROR("Sequence elements going beyond block itself. Sequence block parsing failed\n"); + goto err; + } + + if (*data == 0) + break; /* end of sequence reached */ + } + + DRM_DEBUG_DRIVER("MIPI related vbt parsing complete\n"); + return; +err: + kfree(dev_priv->vbt.dsi.data); + dev_priv->vbt.dsi.data = NULL; + + /* error during parsing so set all pointers to null + * because of partial parsing */ + memset(dev_priv->vbt.dsi.sequence, 0, MIPI_SEQ_MAX); } static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, @@ -823,6 +1063,15 @@ parse_device_mapping(struct drm_i915_private *dev_priv, /* skip the device block if device type is invalid */ continue; } + + if (p_child->common.dvo_port >= DVO_PORT_MIPIA + && p_child->common.dvo_port <= DVO_PORT_MIPID + &&p_child->common.device_type & DEVICE_TYPE_MIPI_OUTPUT) { + DRM_DEBUG_KMS("Found MIPI as LFP\n"); + dev_priv->vbt.has_mipi = 1; + dev_priv->vbt.dsi.port = p_child->common.dvo_port; + } + child_dev_ptr = dev_priv->vbt.child_dev + count; count++; memcpy((void *)child_dev_ptr, (void *)p_child, @@ -893,6 +1142,46 @@ static const struct dmi_system_id intel_no_opregion_vbt[] = { { } }; +static struct bdb_header *validate_vbt(char *base, size_t size, + struct vbt_header *vbt, + const char *source) +{ + size_t offset; + struct bdb_header *bdb; + + if (vbt == NULL) { + DRM_DEBUG_DRIVER("VBT signature missing\n"); + return NULL; + } + + offset = (char *)vbt - base; + if (offset + sizeof(struct vbt_header) > size) { + DRM_DEBUG_DRIVER("VBT header incomplete\n"); + return NULL; + } + + if (memcmp(vbt->signature, "$VBT", 4)) { + DRM_DEBUG_DRIVER("VBT invalid signature\n"); + return NULL; + } + + offset += vbt->bdb_offset; + if (offset + sizeof(struct bdb_header) > size) { + DRM_DEBUG_DRIVER("BDB header incomplete\n"); + return NULL; + } + + bdb = (struct bdb_header *)(base + offset); + if (offset + bdb->bdb_size > size) { + DRM_DEBUG_DRIVER("BDB incomplete\n"); + return NULL; + } + + DRM_DEBUG_KMS("Using VBT from %s: %20s\n", + source, vbt->signature); + return bdb; +} + /** * intel_parse_bios - find VBT and initialize settings from the BIOS * @dev: DRM device @@ -916,20 +1205,13 @@ intel_parse_bios(struct drm_device *dev) init_vbt_defaults(dev_priv); /* XXX Should this validation be moved to intel_opregion.c? */ - if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt) { - struct vbt_header *vbt = dev_priv->opregion.vbt; - if (memcmp(vbt->signature, "$VBT", 4) == 0) { - DRM_DEBUG_KMS("Using VBT from OpRegion: %20s\n", - vbt->signature); - bdb = (struct bdb_header *)((char *)vbt + vbt->bdb_offset); - } else - dev_priv->opregion.vbt = NULL; - } + if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt) + bdb = validate_vbt((char *)dev_priv->opregion.header, OPREGION_SIZE, + (struct vbt_header *)dev_priv->opregion.vbt, + "OpRegion"); if (bdb == NULL) { - struct vbt_header *vbt = NULL; - size_t size; - int i; + size_t i, size; bios = pci_map_rom(pdev, &size); if (!bios) @@ -937,19 +1219,18 @@ intel_parse_bios(struct drm_device *dev) /* Scour memory looking for the VBT signature */ for (i = 0; i + 4 < size; i++) { - if (!memcmp(bios + i, "$VBT", 4)) { - vbt = (struct vbt_header *)(bios + i); + if (memcmp(bios + i, "$VBT", 4) == 0) { + bdb = validate_vbt(bios, size, + (struct vbt_header *)(bios + i), + "PCI ROM"); break; } } - if (!vbt) { - DRM_DEBUG_DRIVER("VBT signature missing\n"); + if (!bdb) { pci_unmap_rom(pdev, bios); return -1; } - - bdb = (struct bdb_header *)(bios + i + vbt->bdb_offset); } /* Grab useful general definitions */ diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h index f27f7b282465..b98667796337 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 */ @@ -482,6 +497,20 @@ 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 @@ -714,6 +743,10 @@ int intel_parse_bios(struct drm_device *dev); #define DVO_PORT_DPC 8 #define DVO_PORT_DPD 9 #define DVO_PORT_DPA 10 +#define DVO_PORT_MIPIA 21 +#define DVO_PORT_MIPIB 22 +#define DVO_PORT_MIPIC 23 +#define DVO_PORT_MIPID 24 /* Block 52 contains MIPI Panel info * 6 such enteries will there. Index into correct @@ -870,4 +903,35 @@ struct bdb_mipi_sequence { u8 data[0]; }; +/* MIPI Sequnece Block definitions */ +enum mipi_seq { + MIPI_SEQ_UNDEFINED = 0, + MIPI_SEQ_ASSERT_RESET, + MIPI_SEQ_INIT_OTP, + MIPI_SEQ_DISPLAY_ON, + MIPI_SEQ_DISPLAY_OFF, + MIPI_SEQ_DEASSERT_RESET, + MIPI_SEQ_MAX +}; + +enum mipi_seq_element { + MIPI_SEQ_ELEM_UNDEFINED = 0, + MIPI_SEQ_ELEM_SEND_PKT, + MIPI_SEQ_ELEM_DELAY, + MIPI_SEQ_ELEM_GPIO, + MIPI_SEQ_ELEM_STATUS, + MIPI_SEQ_ELEM_MAX +}; + +enum mipi_gpio_pin_index { + MIPI_GPIO_UNDEFINED = 0, + MIPI_GPIO_PANEL_ENABLE, + MIPI_GPIO_BL_ENABLE, + MIPI_GPIO_PWM_ENABLE, + MIPI_GPIO_RESET_N, + MIPI_GPIO_PWR_DOWN_R, + MIPI_GPIO_STDBY_RST_N, + MIPI_GPIO_MAX +}; + #endif /* _I830_BIOS_H_ */ diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index aa5a3dc43342..5a045d3bd77e 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -144,28 +144,49 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crt *crt = intel_encoder_to_crt(encoder); - u32 temp; + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); + struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode; + u32 adpa; + + if (INTEL_INFO(dev)->gen >= 5) + adpa = ADPA_HOTPLUG_BITS; + else + adpa = 0; - temp = I915_READ(crt->adpa_reg); - temp &= ~(ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE); - temp &= ~ADPA_DAC_ENABLE; + if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) + adpa |= ADPA_HSYNC_ACTIVE_HIGH; + if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) + adpa |= ADPA_VSYNC_ACTIVE_HIGH; + + /* For CPT allow 3 pipe config, for others just use A or B */ + if (HAS_PCH_LPT(dev)) + ; /* Those bits don't exist here */ + else if (HAS_PCH_CPT(dev)) + adpa |= PORT_TRANS_SEL_CPT(crtc->pipe); + else if (crtc->pipe == 0) + adpa |= ADPA_PIPE_A_SELECT; + else + adpa |= ADPA_PIPE_B_SELECT; + + if (!HAS_PCH_SPLIT(dev)) + I915_WRITE(BCLRPAT(crtc->pipe), 0); switch (mode) { case DRM_MODE_DPMS_ON: - temp |= ADPA_DAC_ENABLE; + adpa |= ADPA_DAC_ENABLE; break; case DRM_MODE_DPMS_STANDBY: - temp |= ADPA_DAC_ENABLE | ADPA_HSYNC_CNTL_DISABLE; + adpa |= ADPA_DAC_ENABLE | ADPA_HSYNC_CNTL_DISABLE; break; case DRM_MODE_DPMS_SUSPEND: - temp |= ADPA_DAC_ENABLE | ADPA_VSYNC_CNTL_DISABLE; + adpa |= ADPA_DAC_ENABLE | ADPA_VSYNC_CNTL_DISABLE; break; case DRM_MODE_DPMS_OFF: - temp |= ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE; + adpa |= ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE; break; } - I915_WRITE(crt->adpa_reg, temp); + I915_WRITE(crt->adpa_reg, adpa); } static void intel_disable_crt(struct intel_encoder *encoder) @@ -274,42 +295,6 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder, return true; } -static void intel_crt_mode_set(struct intel_encoder *encoder) -{ - - struct drm_device *dev = encoder->base.dev; - struct intel_crt *crt = intel_encoder_to_crt(encoder); - struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode; - u32 adpa; - - if (INTEL_INFO(dev)->gen >= 5) - adpa = ADPA_HOTPLUG_BITS; - else - adpa = 0; - - if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) - adpa |= ADPA_HSYNC_ACTIVE_HIGH; - if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) - adpa |= ADPA_VSYNC_ACTIVE_HIGH; - - /* For CPT allow 3 pipe config, for others just use A or B */ - if (HAS_PCH_LPT(dev)) - ; /* Those bits don't exist here */ - else if (HAS_PCH_CPT(dev)) - adpa |= PORT_TRANS_SEL_CPT(crtc->pipe); - else if (crtc->pipe == 0) - adpa |= ADPA_PIPE_A_SELECT; - else - adpa |= ADPA_PIPE_B_SELECT; - - if (!HAS_PCH_SPLIT(dev)) - I915_WRITE(BCLRPAT(crtc->pipe), 0); - - I915_WRITE(crt->adpa_reg, adpa); -} - static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector) { struct drm_device *dev = connector->dev; @@ -645,11 +630,12 @@ intel_crt_detect(struct drm_connector *connector, bool force) enum intel_display_power_domain power_domain; enum drm_connector_status status; struct intel_load_detect_pipe tmp; + struct drm_modeset_acquire_ctx ctx; intel_runtime_pm_get(dev_priv); DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n", - connector->base.id, drm_get_connector_name(connector), + connector->base.id, connector->name, force); power_domain = intel_display_port_power_domain(intel_encoder); @@ -688,12 +674,12 @@ intel_crt_detect(struct drm_connector *connector, bool force) } /* for pre-945g platforms use load detect */ - if (intel_get_load_detect_pipe(connector, NULL, &tmp)) { + if (intel_get_load_detect_pipe(connector, NULL, &tmp, &ctx)) { if (intel_crt_detect_ddc(connector)) status = connector_status_connected; else status = intel_crt_load_detect(crt); - intel_release_load_detect_pipe(connector, &tmp); + intel_release_load_detect_pipe(connector, &tmp, &ctx); } else status = connector_status_unknown; @@ -867,7 +853,6 @@ void intel_crt_init(struct drm_device *dev) crt->adpa_reg = ADPA; crt->base.compute_config = intel_crt_compute_config; - crt->base.mode_set = intel_crt_mode_set; crt->base.disable = intel_disable_crt; crt->base.enable = intel_enable_crt; if (I915_HAS_HOTPLUG(dev)) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 0ad4e9600063..b17b9c7c769f 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -364,55 +364,6 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) DRM_ERROR("FDI link training failed!\n"); } -static void intel_ddi_mode_set(struct intel_encoder *encoder) -{ - struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - int port = intel_ddi_get_encoder_port(encoder); - int pipe = crtc->pipe; - int type = encoder->type; - struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode; - - DRM_DEBUG_KMS("Preparing DDI mode on port %c, pipe %c\n", - port_name(port), pipe_name(pipe)); - - crtc->eld_vld = false; - if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { - struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); - struct intel_digital_port *intel_dig_port = - enc_to_dig_port(&encoder->base); - - intel_dp->DP = intel_dig_port->saved_port_bits | - DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW; - intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count); - - if (intel_dp->has_audio) { - DRM_DEBUG_DRIVER("DP audio on pipe %c on DDI\n", - pipe_name(crtc->pipe)); - - /* write eld */ - DRM_DEBUG_DRIVER("DP audio: write eld information\n"); - intel_write_eld(&encoder->base, adjusted_mode); - } - } else if (type == INTEL_OUTPUT_HDMI) { - struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); - - if (intel_hdmi->has_audio) { - /* Proper support for digital audio needs a new logic - * and a new set of registers, so we leave it for future - * patch bombing. - */ - DRM_DEBUG_DRIVER("HDMI audio on pipe %c on DDI\n", - pipe_name(crtc->pipe)); - - /* write eld */ - DRM_DEBUG_DRIVER("HDMI audio: write eld information\n"); - intel_write_eld(&encoder->base, adjusted_mode); - } - - intel_hdmi->set_infoframes(&encoder->base, adjusted_mode); - } -} - static struct intel_encoder * intel_ddi_get_crtc_encoder(struct drm_crtc *crtc) { @@ -1062,9 +1013,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc) } if (type == INTEL_OUTPUT_HDMI) { - struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); - - if (intel_hdmi->has_hdmi_sink) + if (intel_crtc->config.has_hdmi_sink) temp |= TRANS_DDI_MODE_SELECT_HDMI; else temp |= TRANS_DDI_MODE_SELECT_DVI; @@ -1293,28 +1242,48 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc) static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; - struct drm_crtc *crtc = encoder->crtc; struct drm_i915_private *dev_priv = encoder->dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc *crtc = to_intel_crtc(encoder->crtc); enum port port = intel_ddi_get_encoder_port(intel_encoder); int type = intel_encoder->type; + if (crtc->config.has_audio) { + DRM_DEBUG_DRIVER("Audio on pipe %c on DDI\n", + pipe_name(crtc->pipe)); + + /* write eld */ + DRM_DEBUG_DRIVER("DDI audio: write eld information\n"); + intel_write_eld(encoder, &crtc->config.adjusted_mode); + } + if (type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); intel_edp_panel_on(intel_dp); } - WARN_ON(intel_crtc->ddi_pll_sel == PORT_CLK_SEL_NONE); - I915_WRITE(PORT_CLK_SEL(port), intel_crtc->ddi_pll_sel); + WARN_ON(crtc->ddi_pll_sel == PORT_CLK_SEL_NONE); + I915_WRITE(PORT_CLK_SEL(port), crtc->ddi_pll_sel); if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + struct intel_digital_port *intel_dig_port = + enc_to_dig_port(encoder); + + intel_dp->DP = intel_dig_port->saved_port_bits | + DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW; + intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count); intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); intel_dp_start_link_train(intel_dp); intel_dp_complete_link_train(intel_dp); if (port != PORT_A) intel_dp_stop_link_train(intel_dp); + } else if (type == INTEL_OUTPUT_HDMI) { + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + + intel_hdmi->set_infoframes(encoder, + crtc->config.has_hdmi_sink, + &crtc->config.adjusted_mode); } } @@ -1385,7 +1354,8 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder) intel_edp_psr_enable(intel_dp); } - if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) { + if (intel_crtc->config.has_audio) { + intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO); tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); tmp |= ((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4)); I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); @@ -1403,11 +1373,14 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder) struct drm_i915_private *dev_priv = dev->dev_private; uint32_t tmp; - if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) { + /* We can't touch HSW_AUD_PIN_ELD_CP_VLD uncionditionally because this + * register is part of the power well on Haswell. */ + if (intel_crtc->config.has_audio) { tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); tmp &= ~((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4)); I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); + intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); } if (type == INTEL_OUTPUT_EDP) { @@ -1580,6 +1553,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder, switch (temp & TRANS_DDI_MODE_SELECT_MASK) { case TRANS_DDI_MODE_SELECT_HDMI: + pipe_config->has_hdmi_sink = true; case TRANS_DDI_MODE_SELECT_DVI: case TRANS_DDI_MODE_SELECT_FDI: break; @@ -1592,6 +1566,12 @@ void intel_ddi_get_config(struct intel_encoder *encoder, break; } + if (intel_display_power_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { + temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + if (temp & (AUDIO_OUTPUT_ENABLE_A << (intel_crtc->pipe * 4))) + pipe_config->has_audio = true; + } + if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp_bpp && pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) { /* @@ -1708,7 +1688,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port) DRM_MODE_ENCODER_TMDS); intel_encoder->compute_config = intel_ddi_compute_config; - intel_encoder->mode_set = intel_ddi_mode_set; intel_encoder->enable = intel_enable_ddi; intel_encoder->pre_enable = intel_ddi_pre_enable; intel_encoder->disable = intel_disable_ddi; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5b60e25baa32..efd3cf50cb0f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -41,6 +41,9 @@ #include <drm/drm_crtc_helper.h> #include <linux/dma_remapping.h> +#define DIV_ROUND_CLOSEST_ULL(ll, d) \ + ({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; }) + static void intel_increase_pllclock(struct drm_crtc *crtc); static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on); @@ -55,6 +58,15 @@ static int intel_framebuffer_init(struct drm_device *dev, struct intel_framebuffer *ifb, struct drm_mode_fb_cmd2 *mode_cmd, struct drm_i915_gem_object *obj); +static void intel_dp_set_m_n(struct intel_crtc *crtc); +static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc); +static void intel_set_pipe_timings(struct intel_crtc *intel_crtc); +static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc, + struct intel_link_m_n *m_n); +static void ironlake_set_pipeconf(struct drm_crtc *crtc); +static void haswell_set_pipeconf(struct drm_crtc *crtc); +static void intel_set_pipe_csc(struct drm_crtc *crtc); +static void vlv_prepare_pll(struct intel_crtc *crtc); typedef struct { int min, max; @@ -328,6 +340,22 @@ static const intel_limit_t intel_limits_vlv = { .p2 = { .p2_slow = 2, .p2_fast = 20 }, /* slow=min, fast=max */ }; +static const intel_limit_t intel_limits_chv = { + /* + * These are the data rate limits (measured in fast clocks) + * since those are the strictest limits we have. The fast + * clock and actual rate limits are more relaxed, so checking + * them would make no difference. + */ + .dot = { .min = 25000 * 5, .max = 540000 * 5}, + .vco = { .min = 4860000, .max = 6700000 }, + .n = { .min = 1, .max = 1 }, + .m1 = { .min = 2, .max = 2 }, + .m2 = { .min = 24 << 22, .max = 175 << 22 }, + .p1 = { .min = 2, .max = 4 }, + .p2 = { .p2_slow = 1, .p2_fast = 14 }, +}; + static void vlv_clock(int refclk, intel_clock_t *clock) { clock->m = clock->m1 * clock->m2; @@ -412,6 +440,8 @@ static const intel_limit_t *intel_limit(struct drm_crtc *crtc, int refclk) limit = &intel_limits_pineview_lvds; else limit = &intel_limits_pineview_sdvo; + } else if (IS_CHERRYVIEW(dev)) { + limit = &intel_limits_chv; } else if (IS_VALLEYVIEW(dev)) { limit = &intel_limits_vlv; } else if (!IS_GEN2(dev)) { @@ -456,6 +486,17 @@ static void i9xx_clock(int refclk, intel_clock_t *clock) clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p); } +static void chv_clock(int refclk, intel_clock_t *clock) +{ + clock->m = clock->m1 * clock->m2; + clock->p = clock->p1 * clock->p2; + if (WARN_ON(clock->n == 0 || clock->p == 0)) + return; + clock->vco = DIV_ROUND_CLOSEST_ULL((uint64_t)refclk * clock->m, + clock->n << 22); + clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p); +} + #define INTELPllInvalid(s) do { /* DRM_DEBUG(s); */ return false; } while (0) /** * Returns whether the given set of divisors are valid for a given refclk with @@ -731,6 +772,58 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc, return found; } +static bool +chv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc, + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock) +{ + struct drm_device *dev = crtc->dev; + intel_clock_t clock; + uint64_t m2; + int found = false; + + memset(best_clock, 0, sizeof(*best_clock)); + + /* + * Based on hardware doc, the n always set to 1, and m1 always + * set to 2. If requires to support 200Mhz refclk, we need to + * revisit this because n may not 1 anymore. + */ + clock.n = 1, clock.m1 = 2; + target *= 5; /* fast clock */ + + for (clock.p1 = limit->p1.max; clock.p1 >= limit->p1.min; clock.p1--) { + for (clock.p2 = limit->p2.p2_fast; + clock.p2 >= limit->p2.p2_slow; + clock.p2 -= clock.p2 > 10 ? 2 : 1) { + + clock.p = clock.p1 * clock.p2; + + m2 = DIV_ROUND_CLOSEST_ULL(((uint64_t)target * clock.p * + clock.n) << 22, refclk * clock.m1); + + if (m2 > INT_MAX/clock.m1) + continue; + + clock.m2 = m2; + + chv_clock(refclk, &clock); + + if (!intel_PLL_is_valid(dev, limit, &clock)) + continue; + + /* based on hardware requirement, prefer bigger p + */ + if (clock.p > best_clock->p) { + *best_clock = clock; + found = true; + } + } + } + + return found; +} + bool intel_crtc_active(struct drm_crtc *crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); @@ -765,7 +858,7 @@ static void g4x_wait_for_vblank(struct drm_device *dev, int pipe) frame = I915_READ(frame_reg); if (wait_for(I915_READ_NOTRACE(frame_reg) != frame, 50)) - DRM_DEBUG_KMS("vblank wait timed out\n"); + WARN(1, "vblank wait timed out\n"); } /** @@ -878,7 +971,7 @@ bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, u32 bit; if (HAS_PCH_IBX(dev_priv->dev)) { - switch(port->port) { + switch (port->port) { case PORT_B: bit = SDE_PORTB_HOTPLUG; break; @@ -892,7 +985,7 @@ bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, return true; } } else { - switch(port->port) { + switch (port->port) { case PORT_B: bit = SDE_PORTB_HOTPLUG_CPT; break; @@ -1097,10 +1190,8 @@ static void assert_cursor(struct drm_i915_private *dev_priv, if (IS_845G(dev) || IS_I865G(dev)) cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE; - else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) - cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; else - cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE; + cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; WARN(cur_state != state, "cursor on pipe %c assertion failure (expected %s, current %s)\n", @@ -1253,6 +1344,9 @@ static bool dp_pipe_enabled(struct drm_i915_private *dev_priv, u32 trans_dp_ctl = I915_READ(trans_dp_ctl_reg); if ((trans_dp_ctl & TRANS_DP_PORT_SEL_MASK) != port_sel) return false; + } else if (IS_CHERRYVIEW(dev_priv->dev)) { + if ((val & DP_PIPE_MASK_CHV) != DP_PIPE_SELECT_CHV(pipe)) + return false; } else { if ((val & DP_PIPE_MASK) != (pipe << 30)) return false; @@ -1269,6 +1363,9 @@ static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv, if (HAS_PCH_CPT(dev_priv->dev)) { if ((val & SDVO_PIPE_SEL_MASK_CPT) != SDVO_PIPE_SEL_CPT(pipe)) return false; + } else if (IS_CHERRYVIEW(dev_priv->dev)) { + if ((val & SDVO_PIPE_SEL_MASK_CHV) != SDVO_PIPE_SEL_CHV(pipe)) + return false; } else { if ((val & SDVO_PIPE_SEL_MASK) != SDVO_PIPE_SEL(pipe)) return false; @@ -1367,7 +1464,17 @@ static void intel_init_dpio(struct drm_device *dev) if (!IS_VALLEYVIEW(dev)) return; - DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; + /* + * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C), + * CHV x1 PHY (DP/HDMI D) + * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C) + */ + if (IS_CHERRYVIEW(dev)) { + DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2; + DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO; + } else { + DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; + } } static void intel_reset_dpio(struct drm_device *dev) @@ -1377,25 +1484,48 @@ static void intel_reset_dpio(struct drm_device *dev) if (!IS_VALLEYVIEW(dev)) return; - /* - * Enable the CRI clock source so we can get at the display and the - * reference clock for VGA hotplug / manual detection. - */ - I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | - DPLL_REFA_CLK_ENABLE_VLV | - DPLL_INTEGRATED_CRI_CLK_VLV); + if (IS_CHERRYVIEW(dev)) { + enum dpio_phy phy; + u32 val; - /* - * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx - - * 6. De-assert cmn_reset/side_reset. Same as VLV X0. - * a. GUnit 0x2110 bit[0] set to 1 (def 0) - * b. The other bits such as sfr settings / modesel may all be set - * to 0. - * - * This should only be done on init and resume from S3 with both - * PLLs disabled, or we risk losing DPIO and PLL synchronization. - */ - I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST); + for (phy = DPIO_PHY0; phy < I915_NUM_PHYS_VLV; phy++) { + /* Poll for phypwrgood signal */ + if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & + PHY_POWERGOOD(phy), 1)) + DRM_ERROR("Display PHY %d is not power up\n", phy); + + /* + * Deassert common lane reset for PHY. + * + * This should only be done on init and resume from S3 + * with both PLLs disabled, or we risk losing DPIO and + * PLL synchronization. + */ + val = I915_READ(DISPLAY_PHY_CONTROL); + I915_WRITE(DISPLAY_PHY_CONTROL, + PHY_COM_LANE_RESET_DEASSERT(phy, val)); + } + + } else { + /* + * If DPIO has already been reset, e.g. by BIOS, just skip all + * this. + */ + if (I915_READ(DPIO_CTL) & DPIO_CMNRST) + return; + + /* + * From VLV2A0_DP_eDP_HDMI_DPIO_driver_vbios_notes_11.docx: + * Need to assert and de-assert PHY SB reset by gating the + * common lane power, then un-gating it. + * Simply ungating isn't enough to reset the PHY enough to get + * ports and lanes running. + */ + __vlv_set_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_BC, + false); + __vlv_set_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_BC, + true); + } } static void vlv_enable_pll(struct intel_crtc *crtc) @@ -1436,6 +1566,44 @@ static void vlv_enable_pll(struct intel_crtc *crtc) udelay(150); /* wait for warmup */ } +static void chv_enable_pll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = crtc->pipe; + enum dpio_channel port = vlv_pipe_to_channel(pipe); + u32 tmp; + + assert_pipe_disabled(dev_priv, crtc->pipe); + + BUG_ON(!IS_CHERRYVIEW(dev_priv->dev)); + + mutex_lock(&dev_priv->dpio_lock); + + /* Enable back the 10bit clock to display controller */ + tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)); + tmp |= DPIO_DCLKP_EN; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), tmp); + + /* + * Need to wait > 100ns between dclkp clock enable bit and PLL enable. + */ + udelay(1); + + /* Enable PLL */ + I915_WRITE(DPLL(pipe), crtc->config.dpll_hw_state.dpll); + + /* Check PLL is locked */ + if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1)) + DRM_ERROR("PLL %d failed to lock\n", pipe); + + /* not sure when this should be written */ + I915_WRITE(DPLL_MD(pipe), crtc->config.dpll_hw_state.dpll_md); + POSTING_READ(DPLL_MD(pipe)); + + mutex_unlock(&dev_priv->dpio_lock); +} + static void i9xx_enable_pll(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; @@ -1519,45 +1687,92 @@ static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) val = DPLL_INTEGRATED_CRI_CLK_VLV | DPLL_REFA_CLK_ENABLE_VLV; I915_WRITE(DPLL(pipe), val); POSTING_READ(DPLL(pipe)); + +} + +static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) +{ + enum dpio_channel port = vlv_pipe_to_channel(pipe); + u32 val; + + /* Make sure the pipe isn't still relying on us */ + assert_pipe_disabled(dev_priv, pipe); + + /* Set PLL en = 0 */ + val = DPLL_SSC_REF_CLOCK_CHV; + if (pipe != PIPE_A) + val |= DPLL_INTEGRATED_CRI_CLK_VLV; + I915_WRITE(DPLL(pipe), val); + POSTING_READ(DPLL(pipe)); + + mutex_lock(&dev_priv->dpio_lock); + + /* Disable 10bit clock to display controller */ + val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)); + val &= ~DPIO_DCLKP_EN; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), val); + + mutex_unlock(&dev_priv->dpio_lock); } void vlv_wait_port_ready(struct drm_i915_private *dev_priv, struct intel_digital_port *dport) { u32 port_mask; + int dpll_reg; switch (dport->port) { case PORT_B: port_mask = DPLL_PORTB_READY_MASK; + dpll_reg = DPLL(0); break; case PORT_C: port_mask = DPLL_PORTC_READY_MASK; + dpll_reg = DPLL(0); + break; + case PORT_D: + port_mask = DPLL_PORTD_READY_MASK; + dpll_reg = DPIO_PHY_STATUS; break; default: BUG(); } - if (wait_for((I915_READ(DPLL(0)) & port_mask) == 0, 1000)) + if (wait_for((I915_READ(dpll_reg) & port_mask) == 0, 1000)) WARN(1, "timed out waiting for port %c ready: 0x%08x\n", - port_name(dport->port), I915_READ(DPLL(0))); + port_name(dport->port), I915_READ(dpll_reg)); +} + +static void intel_prepare_shared_dpll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc); + + WARN_ON(!pll->refcount); + if (pll->active == 0) { + DRM_DEBUG_DRIVER("setting up %s\n", pll->name); + WARN_ON(pll->on); + assert_shared_dpll_disabled(dev_priv, pll); + + pll->mode_set(dev_priv, pll); + } } /** - * ironlake_enable_shared_dpll - enable PCH PLL + * intel_enable_shared_dpll - enable PCH PLL * @dev_priv: i915 private structure * @pipe: pipe PLL to enable * * The PCH PLL needs to be enabled before the PCH transcoder, since it * drives the transcoder clock. */ -static void ironlake_enable_shared_dpll(struct intel_crtc *crtc) +static void intel_enable_shared_dpll(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc); - /* PCH PLLs only available on ILK, SNB and IVB */ - BUG_ON(INTEL_INFO(dev)->gen < 5); if (WARN_ON(pll == NULL)) return; @@ -1804,16 +2019,6 @@ static void intel_enable_pipe(struct intel_crtc *crtc) I915_WRITE(reg, val | PIPECONF_ENABLE); POSTING_READ(reg); - - /* - * There's no guarantee the pipe will really start running now. It - * depends on the Gen, the output type and the relative order between - * pipe and plane enabling. Avoid waiting on HSW+ since it's not - * necessary. - * TODO: audit the previous gens. - */ - if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) - intel_wait_for_vblank(dev_priv->dev, pipe); } /** @@ -1890,18 +2095,17 @@ static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv, /* If the pipe isn't enabled, we can't pump pixels and may hang */ assert_pipe_enabled(dev_priv, pipe); - WARN(intel_crtc->primary_enabled, "Primary plane already enabled\n"); + if (intel_crtc->primary_enabled) + return; intel_crtc->primary_enabled = true; reg = DSPCNTR(plane); val = I915_READ(reg); - if (val & DISPLAY_PLANE_ENABLE) - return; + WARN_ON(val & DISPLAY_PLANE_ENABLE); I915_WRITE(reg, val | DISPLAY_PLANE_ENABLE); intel_flush_primary_plane(dev_priv, plane); - intel_wait_for_vblank(dev_priv->dev, pipe); } /** @@ -1920,18 +2124,17 @@ static void intel_disable_primary_hw_plane(struct drm_i915_private *dev_priv, int reg; u32 val; - WARN(!intel_crtc->primary_enabled, "Primary plane already disabled\n"); + if (!intel_crtc->primary_enabled) + return; intel_crtc->primary_enabled = false; reg = DSPCNTR(plane); val = I915_READ(reg); - if ((val & DISPLAY_PLANE_ENABLE) == 0) - return; + WARN_ON((val & DISPLAY_PLANE_ENABLE) == 0); I915_WRITE(reg, val & ~DISPLAY_PLANE_ENABLE); intel_flush_primary_plane(dev_priv, plane); - intel_wait_for_vblank(dev_priv->dev, pipe); } static bool need_vtd_wa(struct drm_device *dev) @@ -1954,7 +2157,7 @@ static int intel_align_height(struct drm_device *dev, int height, bool tiled) int intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_i915_gem_object *obj, - struct intel_ring_buffer *pipelined) + struct intel_engine_cs *pipelined) { struct drm_i915_private *dev_priv = dev->dev_private; u32 alignment; @@ -2134,7 +2337,7 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc, * Failed to alloc the obj, check to see if we should share * an fb with another CRTC instead */ - list_for_each_entry(c, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, c) { i = to_intel_crtc(c); if (c == &intel_crtc->base) @@ -2152,9 +2355,9 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc, } } -static int i9xx_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void i9xx_update_primary_plane(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2166,15 +2369,6 @@ 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; @@ -2249,13 +2443,11 @@ static int i9xx_update_primary_plane(struct drm_crtc *crtc, } else I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset); POSTING_READ(reg); - - return 0; } -static int ironlake_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void ironlake_update_primary_plane(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2267,16 +2459,6 @@ 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; @@ -2343,8 +2525,6 @@ static int ironlake_update_primary_plane(struct drm_crtc *crtc, I915_WRITE(DSPLINOFF(plane), linear_offset); } POSTING_READ(reg); - - return 0; } /* Assume fb object is pinned & idle & fenced and just update base pointers */ @@ -2359,7 +2539,9 @@ intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb, dev_priv->display.disable_fbc(dev); intel_increase_pllclock(crtc); - return dev_priv->display.update_primary_plane(crtc, fb, x, y); + dev_priv->display.update_primary_plane(crtc, fb, x, y); + + return 0; } void intel_display_handle_reset(struct drm_device *dev) @@ -2381,7 +2563,7 @@ void intel_display_handle_reset(struct drm_device *dev) * pending_flip_queue really got woken up. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum plane plane = intel_crtc->plane; @@ -2389,10 +2571,10 @@ void intel_display_handle_reset(struct drm_device *dev) intel_finish_page_flip_plane(dev, plane); } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - mutex_lock(&crtc->mutex); + drm_modeset_lock(&crtc->mutex, NULL); /* * FIXME: Once we have proper support for primary planes (and * disabling them without disabling the entire crtc) allow again @@ -2403,7 +2585,7 @@ void intel_display_handle_reset(struct drm_device *dev) crtc->primary->fb, crtc->x, crtc->y); - mutex_unlock(&crtc->mutex); + drm_modeset_unlock(&crtc->mutex); } } @@ -2518,14 +2700,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, intel_crtc->config.pipe_src_h = adjusted_mode->crtc_vdisplay; } - ret = dev_priv->display.update_primary_plane(crtc, fb, x, y); - if (ret) { - mutex_lock(&dev->struct_mutex); - intel_unpin_fb_obj(to_intel_framebuffer(fb)->obj); - mutex_unlock(&dev->struct_mutex); - DRM_ERROR("failed to update base address\n"); - return ret; - } + dev_priv->display.update_primary_plane(crtc, fb, x, y); old_fb = crtc->primary->fb; crtc->primary->fb = fb; @@ -2628,12 +2803,10 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; u32 reg, temp, tries; - /* FDI needs bits from pipe & plane first */ + /* FDI needs bits from pipe first */ assert_pipe_enabled(dev_priv, pipe); - assert_plane_enabled(dev_priv, plane); /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit for train result */ @@ -3064,9 +3237,8 @@ static void ironlake_fdi_disable(struct drm_crtc *crtc) udelay(100); /* Ironlake workaround, disable clock pointer after downing FDI */ - if (HAS_PCH_IBX(dev)) { + if (HAS_PCH_IBX(dev)) I915_WRITE(FDI_RX_CHICKEN(pipe), FDI_RX_PHASE_SYNC_POINTER_OVR); - } /* still set train pattern 1 */ reg = FDI_TX_CTL(pipe); @@ -3104,7 +3276,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev) * cannot claim and pin a new fb without at least acquring the * struct_mutex and so serialising with us. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { if (atomic_read(&crtc->unpin_work_count) == 0) continue; @@ -3117,7 +3289,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev) return false; } -static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) +void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -3127,8 +3299,9 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue)); - wait_event(dev_priv->pending_flip_queue, - !intel_crtc_has_pending_flip(crtc)); + WARN_ON(wait_event_timeout(dev_priv->pending_flip_queue, + !intel_crtc_has_pending_flip(crtc), + 60*HZ) == 0); mutex_lock(&dev->struct_mutex); intel_finish_fb(crtc->primary->fb); @@ -3341,7 +3514,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) * Note that enable_shared_dpll tries to do the right thing, but * get_shared_dpll unconditionally resets the pll - we need that to have * the right LVDS enable sequence. */ - ironlake_enable_shared_dpll(intel_crtc); + intel_enable_shared_dpll(intel_crtc); /* set transcoder timing, panel must allow it */ assert_panel_unlocked(dev_priv, pipe); @@ -3445,6 +3618,8 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc) DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n", crtc->base.base.id, pll->name); + WARN_ON(pll->refcount); + goto found; } @@ -3478,20 +3653,13 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc) return NULL; found: + if (pll->refcount == 0) + pll->hw_state = crtc->config.dpll_hw_state; + crtc->config.shared_dpll = i; DRM_DEBUG_DRIVER("using %s for pipe %c\n", pll->name, pipe_name(crtc->pipe)); - if (pll->active == 0) { - memcpy(&pll->hw_state, &crtc->config.dpll_hw_state, - sizeof(pll->hw_state)); - - DRM_DEBUG_DRIVER("setting up %s\n", pll->name); - WARN_ON(pll->on); - assert_shared_dpll_disabled(dev_priv, pll); - - pll->mode_set(dev_priv, pll); - } pll->refcount++; return pll; @@ -3562,17 +3730,17 @@ static void intel_disable_planes(struct drm_crtc *crtc) void hsw_enable_ips(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; if (!crtc->config.ips_enabled) return; - /* We can only enable IPS after we enable a plane and wait for a vblank. - * We guarantee that the plane is enabled by calling intel_enable_ips - * only after intel_enable_plane. And intel_enable_plane already waits - * for a vblank, so all we need to do here is to enable the IPS bit. */ + /* We can only enable IPS after we enable a plane and wait for a vblank */ + intel_wait_for_vblank(dev, crtc->pipe); + assert_plane_enabled(dev_priv, crtc->plane); - if (IS_BROADWELL(crtc->base.dev)) { + if (IS_BROADWELL(dev)) { mutex_lock(&dev_priv->rps.hw_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0xc0000000)); mutex_unlock(&dev_priv->rps.hw_lock); @@ -3602,10 +3770,13 @@ void hsw_disable_ips(struct intel_crtc *crtc) return; assert_plane_enabled(dev_priv, crtc->plane); - if (IS_BROADWELL(crtc->base.dev)) { + if (IS_BROADWELL(dev)) { mutex_lock(&dev_priv->rps.hw_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0)); mutex_unlock(&dev_priv->rps.hw_lock); + /* wait for pcode to finish disabling IPS, which may take up to 42ms */ + if (wait_for((I915_READ(IPS_CTL) & IPS_ENABLE) == 0, 42)) + DRM_ERROR("Timed out waiting for IPS disable\n"); } else { I915_WRITE(IPS_CTL, 0); POSTING_READ(IPS_CTL); @@ -3662,6 +3833,94 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc) hsw_enable_ips(intel_crtc); } +static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable) +{ + if (!enable && intel_crtc->overlay) { + struct drm_device *dev = intel_crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + mutex_lock(&dev->struct_mutex); + dev_priv->mm.interruptible = false; + (void) intel_overlay_switch_off(intel_crtc->overlay); + dev_priv->mm.interruptible = true; + mutex_unlock(&dev->struct_mutex); + } + + /* Let userspace switch the overlay on again. In most cases userspace + * has to recompute where to put it anyway. + */ +} + +/** + * i9xx_fixup_plane - ugly workaround for G45 to fire up the hardware + * cursor plane briefly if not already running after enabling the display + * plane. + * This workaround avoids occasional blank screens when self refresh is + * enabled. + */ +static void +g4x_fixup_plane(struct drm_i915_private *dev_priv, enum pipe pipe) +{ + u32 cntl = I915_READ(CURCNTR(pipe)); + + if ((cntl & CURSOR_MODE) == 0) { + u32 fw_bcl_self = I915_READ(FW_BLC_SELF); + + I915_WRITE(FW_BLC_SELF, fw_bcl_self & ~FW_BLC_SELF_EN); + I915_WRITE(CURCNTR(pipe), CURSOR_MODE_64_ARGB_AX); + intel_wait_for_vblank(dev_priv->dev, pipe); + I915_WRITE(CURCNTR(pipe), cntl); + I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe))); + I915_WRITE(FW_BLC_SELF, fw_bcl_self); + } +} + +static void intel_crtc_enable_planes(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int pipe = intel_crtc->pipe; + int plane = intel_crtc->plane; + + intel_enable_primary_hw_plane(dev_priv, plane, pipe); + intel_enable_planes(crtc); + /* The fixup needs to happen before cursor is enabled */ + if (IS_G4X(dev)) + g4x_fixup_plane(dev_priv, pipe); + intel_crtc_update_cursor(crtc, true); + intel_crtc_dpms_overlay(intel_crtc, true); + + hsw_enable_ips(intel_crtc); + + mutex_lock(&dev->struct_mutex); + intel_update_fbc(dev); + intel_edp_psr_update(dev); + mutex_unlock(&dev->struct_mutex); +} + +static void intel_crtc_disable_planes(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int pipe = intel_crtc->pipe; + int plane = intel_crtc->plane; + + intel_crtc_wait_for_pending_flips(crtc); + drm_crtc_vblank_off(crtc); + + if (dev_priv->fbc.plane == plane) + intel_disable_fbc(dev); + + hsw_disable_ips(intel_crtc); + + intel_crtc_dpms_overlay(intel_crtc, false); + intel_crtc_update_cursor(crtc, false); + intel_disable_planes(crtc); + intel_disable_primary_hw_plane(dev_priv, plane, pipe); +} + static void ironlake_crtc_enable(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -3669,13 +3928,35 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; + enum plane plane = intel_crtc->plane; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + if (intel_crtc->config.has_pch_encoder) + intel_prepare_shared_dpll(intel_crtc); + + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + + intel_set_pipe_timings(intel_crtc); + + if (intel_crtc->config.has_pch_encoder) { + intel_cpu_transcoder_set_m_n(intel_crtc, + &intel_crtc->config.fdi_m_n); + } + + ironlake_set_pipeconf(crtc); + + /* Set up the display plane register */ + I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); @@ -3705,32 +3986,19 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) intel_update_watermarks(crtc); intel_enable_pipe(intel_crtc); - intel_enable_primary_hw_plane(dev_priv, plane, pipe); - intel_enable_planes(crtc); - intel_crtc_update_cursor(crtc, true); if (intel_crtc->config.has_pch_encoder) ironlake_pch_enable(crtc); - mutex_lock(&dev->struct_mutex); - intel_update_fbc(dev); - mutex_unlock(&dev->struct_mutex); - for_each_encoder_on_crtc(dev, crtc, encoder) encoder->enable(encoder); if (HAS_PCH_CPT(dev)) cpt_verify_modeset(dev, intel_crtc->pipe); - /* - * There seems to be a race in PCH platform hw (at least on some - * outputs) where an enabled pipe still completes any pageflip right - * away (as if the pipe is off) instead of waiting for vblank. As soon - * as the first vblank happend, everything works as expected. Hence just - * wait for one vblank before returning to avoid strange things - * happening. - */ - intel_wait_for_vblank(dev, intel_crtc->pipe); + intel_crtc_enable_planes(crtc); + + drm_crtc_vblank_on(crtc); } /* IPS only exists on ULT machines and is tied to pipe A. */ @@ -3739,47 +4007,6 @@ static bool hsw_crtc_supports_ips(struct intel_crtc *crtc) return HAS_IPS(crtc->base.dev) && crtc->pipe == PIPE_A; } -static void haswell_crtc_enable_planes(struct drm_crtc *crtc) -{ - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; - - intel_enable_primary_hw_plane(dev_priv, plane, pipe); - intel_enable_planes(crtc); - intel_crtc_update_cursor(crtc, true); - - hsw_enable_ips(intel_crtc); - - mutex_lock(&dev->struct_mutex); - intel_update_fbc(dev); - mutex_unlock(&dev->struct_mutex); -} - -static void haswell_crtc_disable_planes(struct drm_crtc *crtc) -{ - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; - - intel_crtc_wait_for_pending_flips(crtc); - drm_vblank_off(dev, pipe); - - /* FBC must be disabled before disabling the plane on HSW. */ - if (dev_priv->fbc.plane == plane) - intel_disable_fbc(dev); - - hsw_disable_ips(intel_crtc); - - intel_crtc_update_cursor(crtc, false); - intel_disable_planes(crtc); - intel_disable_primary_hw_plane(dev_priv, plane, pipe); -} - /* * This implements the workaround described in the "notes" section of the mode * set sequence documentation. When going from no pipes or single pipe to @@ -3793,7 +4020,7 @@ static void haswell_mode_set_planes_workaround(struct intel_crtc *crtc) /* We want to get the other_active_crtc only if there's only 1 other * active crtc. */ - list_for_each_entry(crtc_it, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc_it) { if (!crtc_it->active || crtc_it == crtc) continue; @@ -3816,12 +4043,34 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; + enum plane plane = intel_crtc->plane; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + + intel_set_pipe_timings(intel_crtc); + + if (intel_crtc->config.has_pch_encoder) { + intel_cpu_transcoder_set_m_n(intel_crtc, + &intel_crtc->config.fdi_m_n); + } + + haswell_set_pipeconf(crtc); + + intel_set_pipe_csc(crtc); + + /* Set up the display plane register */ + I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); @@ -3862,7 +4111,9 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) /* If we change the relative order between pipe/planes enabling, we need * to change the workaround. */ haswell_mode_set_planes_workaround(intel_crtc); - haswell_crtc_enable_planes(crtc); + intel_crtc_enable_planes(crtc); + + drm_crtc_vblank_on(crtc); } static void ironlake_pfit_disable(struct intel_crtc *crtc) @@ -3887,26 +4138,16 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; u32 reg, temp; - if (!intel_crtc->active) return; + intel_crtc_disable_planes(crtc); + for_each_encoder_on_crtc(dev, crtc, encoder) encoder->disable(encoder); - intel_crtc_wait_for_pending_flips(crtc); - drm_vblank_off(dev, pipe); - - if (dev_priv->fbc.plane == plane) - intel_disable_fbc(dev); - - intel_crtc_update_cursor(crtc, false); - intel_disable_planes(crtc); - intel_disable_primary_hw_plane(dev_priv, plane, pipe); - if (intel_crtc->config.has_pch_encoder) intel_set_pch_fifo_underrun_reporting(dev, pipe, false); @@ -3950,6 +4191,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); mutex_unlock(&dev->struct_mutex); } @@ -3965,7 +4207,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) if (!intel_crtc->active) return; - haswell_crtc_disable_planes(crtc); + intel_crtc_disable_planes(crtc); for_each_encoder_on_crtc(dev, crtc, encoder) { intel_opregion_notify_encoder(encoder, false); @@ -3997,6 +4239,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); mutex_unlock(&dev->struct_mutex); } @@ -4011,48 +4254,6 @@ static void haswell_crtc_off(struct drm_crtc *crtc) intel_ddi_put_crtc_pll(crtc); } -static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable) -{ - if (!enable && intel_crtc->overlay) { - struct drm_device *dev = intel_crtc->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - - mutex_lock(&dev->struct_mutex); - dev_priv->mm.interruptible = false; - (void) intel_overlay_switch_off(intel_crtc->overlay); - dev_priv->mm.interruptible = true; - mutex_unlock(&dev->struct_mutex); - } - - /* Let userspace switch the overlay on again. In most cases userspace - * has to recompute where to put it anyway. - */ -} - -/** - * i9xx_fixup_plane - ugly workaround for G45 to fire up the hardware - * cursor plane briefly if not already running after enabling the display - * plane. - * This workaround avoids occasional blank screens when self refresh is - * enabled. - */ -static void -g4x_fixup_plane(struct drm_i915_private *dev_priv, enum pipe pipe) -{ - u32 cntl = I915_READ(CURCNTR(pipe)); - - if ((cntl & CURSOR_MODE) == 0) { - u32 fw_bcl_self = I915_READ(FW_BLC_SELF); - - I915_WRITE(FW_BLC_SELF, fw_bcl_self & ~FW_BLC_SELF_EN); - I915_WRITE(CURCNTR(pipe), CURSOR_MODE_64_ARGB_AX); - intel_wait_for_vblank(dev_priv->dev, pipe); - I915_WRITE(CURCNTR(pipe), cntl); - I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe))); - I915_WRITE(FW_BLC_SELF, fw_bcl_self); - } -} - static void i9xx_pfit_enable(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; @@ -4164,7 +4365,7 @@ static void modeset_update_crtc_power_domains(struct drm_device *dev) * First get all needed power domains, then put all unneeded, to avoid * any unnecessary toggling of the power wells. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { enum intel_display_power_domain domain; if (!crtc->base.enabled) @@ -4176,7 +4377,7 @@ static void modeset_update_crtc_power_domains(struct drm_device *dev) intel_display_power_get(dev_priv, domain); } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { enum intel_display_power_domain domain; for_each_power_domain(domain, crtc->enabled_power_domains) @@ -4207,6 +4408,9 @@ 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 +4465,7 @@ 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 +4486,6 @@ 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 @@ -4311,8 +4511,7 @@ static int intel_mode_max_pixclk(struct drm_i915_private *dev_priv) struct intel_crtc *intel_crtc; int max_pixclk = 0; - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, intel_crtc) { if (intel_crtc->new_enabled) max_pixclk = max(max_pixclk, intel_crtc->new_config->adjusted_mode.crtc_clock); @@ -4327,14 +4526,13 @@ 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 */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) + for_each_intel_crtc(dev, intel_crtc) if (intel_crtc->base.enabled) *prepare_pipes |= (1 << intel_crtc->pipe); } @@ -4343,10 +4541,9 @@ 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); } @@ -4360,22 +4557,55 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) int pipe = intel_crtc->pipe; int plane = intel_crtc->plane; bool is_dsi; + u32 dspcntr; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + vlv_prepare_pll(intel_crtc); + + /* Set up the display plane register */ + dspcntr = DISPPLANE_GAMMA_ENABLE; + + 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, + * which should always be the user's requested size. + */ + I915_WRITE(DSPSIZE(plane), + ((intel_crtc->config.pipe_src_h - 1) << 16) | + (intel_crtc->config.pipe_src_w - 1)); + I915_WRITE(DSPPOS(plane), 0); + + i9xx_set_pipeconf(intel_crtc); + + I915_WRITE(DSPCNTR(plane), dspcntr); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; + intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); + for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_pll_enable) encoder->pre_pll_enable(encoder); is_dsi = intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI); - if (!is_dsi) - vlv_enable_pll(intel_crtc); + if (!is_dsi) { + if (IS_CHERRYVIEW(dev)) + chv_enable_pll(intel_crtc); + else + vlv_enable_pll(intel_crtc); + } for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_enable) @@ -4387,15 +4617,25 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) intel_update_watermarks(crtc); intel_enable_pipe(intel_crtc); - intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); - intel_enable_primary_hw_plane(dev_priv, plane, pipe); - intel_enable_planes(crtc); - intel_crtc_update_cursor(crtc, true); - - intel_update_fbc(dev); for_each_encoder_on_crtc(dev, crtc, encoder) encoder->enable(encoder); + + intel_crtc_enable_planes(crtc); + + drm_crtc_vblank_on(crtc); + + /* Underruns don't raise interrupts, so check manually. */ + i9xx_check_fifo_underruns(dev); +} + +static void i9xx_set_pll_dividers(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + I915_WRITE(FP0(crtc->pipe), crtc->config.dpll_hw_state.fp0); + I915_WRITE(FP1(crtc->pipe), crtc->config.dpll_hw_state.fp1); } static void i9xx_crtc_enable(struct drm_crtc *crtc) @@ -4406,14 +4646,49 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc) struct intel_encoder *encoder; int pipe = intel_crtc->pipe; int plane = intel_crtc->plane; + u32 dspcntr; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + i9xx_set_pll_dividers(intel_crtc); + + /* Set up the display plane register */ + dspcntr = DISPPLANE_GAMMA_ENABLE; + + if (pipe == 0) + dspcntr &= ~DISPPLANE_SEL_PIPE_MASK; + else + 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, + * which should always be the user's requested size. + */ + I915_WRITE(DSPSIZE(plane), + ((intel_crtc->config.pipe_src_h - 1) << 16) | + (intel_crtc->config.pipe_src_w - 1)); + I915_WRITE(DSPPOS(plane), 0); + + i9xx_set_pipeconf(intel_crtc); + + I915_WRITE(DSPCNTR(plane), dspcntr); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; + if (!IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); + for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_enable) encoder->pre_enable(encoder); @@ -4426,21 +4701,26 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc) intel_update_watermarks(crtc); intel_enable_pipe(intel_crtc); - intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); - intel_enable_primary_hw_plane(dev_priv, plane, pipe); - intel_enable_planes(crtc); - /* The fixup needs to happen before cursor is enabled */ - if (IS_G4X(dev)) - g4x_fixup_plane(dev_priv, pipe); - intel_crtc_update_cursor(crtc, true); - - /* Give the overlay scaler a chance to enable if it's on this pipe */ - intel_crtc_dpms_overlay(intel_crtc, true); - - intel_update_fbc(dev); for_each_encoder_on_crtc(dev, crtc, encoder) encoder->enable(encoder); + + intel_crtc_enable_planes(crtc); + + /* + * Gen2 reports pipe underruns whenever all planes are disabled. + * So don't enable underrun reporting before at least some planes + * are enabled. + * FIXME: Need to fix the logic to work when we turn off all planes + * but leave the pipe running. + */ + if (IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); + + drm_crtc_vblank_on(crtc); + + /* Underruns don't raise interrupts, so check manually. */ + i9xx_check_fifo_underruns(dev); } static void i9xx_pfit_disable(struct intel_crtc *crtc) @@ -4465,27 +4745,31 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; if (!intel_crtc->active) return; - for_each_encoder_on_crtc(dev, crtc, encoder) - encoder->disable(encoder); + /* + * Gen2 reports pipe underruns whenever all planes are disabled. + * So diasble underrun reporting before all the planes get disabled. + * FIXME: Need to fix the logic to work when we turn off all planes + * but leave the pipe running. + */ + if (IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); - /* Give the overlay scaler a chance to disable if it's on this pipe */ - intel_crtc_wait_for_pending_flips(crtc); - drm_vblank_off(dev, pipe); + intel_crtc_disable_planes(crtc); - if (dev_priv->fbc.plane == plane) - intel_disable_fbc(dev); + for_each_encoder_on_crtc(dev, crtc, encoder) + encoder->disable(encoder); - intel_crtc_dpms_overlay(intel_crtc, false); - intel_crtc_update_cursor(crtc, false); - intel_disable_planes(crtc); - intel_disable_primary_hw_plane(dev_priv, plane, pipe); + /* + * On gen2 planes are double buffered but the pipe isn't, so we must + * wait for planes to fully turn off before disabling the pipe. + */ + if (IS_GEN2(dev)) + intel_wait_for_vblank(dev, pipe); - intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); intel_disable_pipe(dev_priv, pipe); i9xx_pfit_disable(intel_crtc); @@ -4494,15 +4778,25 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) if (encoder->post_disable) encoder->post_disable(encoder); - if (IS_VALLEYVIEW(dev) && !intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI)) - vlv_disable_pll(dev_priv, pipe); - else if (!IS_VALLEYVIEW(dev)) - i9xx_disable_pll(dev_priv, pipe); + if (!intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI)) { + if (IS_CHERRYVIEW(dev)) + chv_disable_pll(dev_priv, pipe); + else if (IS_VALLEYVIEW(dev)) + vlv_disable_pll(dev_priv, pipe); + else + i9xx_disable_pll(dev_priv, pipe); + } + + if (!IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); intel_crtc->active = false; intel_update_watermarks(crtc); + mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); + mutex_unlock(&dev->struct_mutex); } static void i9xx_crtc_off(struct drm_crtc *crtc) @@ -4565,13 +4859,11 @@ static void intel_crtc_disable(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_connector *connector; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); /* crtc should still be enabled when we disable it. */ WARN_ON(!crtc->enabled); dev_priv->display.crtc_disable(crtc); - intel_crtc->eld_vld = false; intel_crtc_update_sarea(crtc, false); dev_priv->display.off(crtc); @@ -4635,7 +4927,7 @@ static void intel_connector_check_state(struct intel_connector *connector) DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.base.id, - drm_get_connector_name(&connector->base)); + connector->base.name); WARN(connector->base.dpms == DRM_MODE_DPMS_OFF, "wrong connector dpms state\n"); @@ -5039,8 +5331,6 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc, intel_clock_t *reduced_clock) { struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - int pipe = crtc->pipe; u32 fp, fp2 = 0; if (IS_PINEVIEW(dev)) { @@ -5053,17 +5343,14 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc, fp2 = i9xx_dpll_compute_fp(reduced_clock); } - I915_WRITE(FP0(pipe), fp); crtc->config.dpll_hw_state.fp0 = fp; crtc->lowfreq_avail = false; if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) && reduced_clock && i915.powersave) { - I915_WRITE(FP1(pipe), fp2); crtc->config.dpll_hw_state.fp1 = fp2; crtc->lowfreq_avail = true; } else { - I915_WRITE(FP1(pipe), fp); crtc->config.dpll_hw_state.fp1 = fp; } } @@ -5141,12 +5428,34 @@ static void intel_dp_set_m_n(struct intel_crtc *crtc) static void vlv_update_pll(struct intel_crtc *crtc) { + u32 dpll, dpll_md; + + /* + * Enable DPIO clock input. We should never disable the reference + * clock for pipe B, since VGA hotplug / manual detection depends + * on it. + */ + dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV | + DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV; + /* We should never disable this, set it here for state tracking */ + if (crtc->pipe == PIPE_B) + dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; + dpll |= DPLL_VCO_ENABLE; + crtc->config.dpll_hw_state.dpll = dpll; + + dpll_md = (crtc->config.pixel_multiplier - 1) + << DPLL_MD_UDI_MULTIPLIER_SHIFT; + crtc->config.dpll_hw_state.dpll_md = dpll_md; +} + +static void vlv_prepare_pll(struct intel_crtc *crtc) +{ struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; int pipe = crtc->pipe; - u32 dpll, mdiv; + u32 mdiv; u32 bestn, bestm1, bestm2, bestp1, bestp2; - u32 coreclk, reg_val, dpll_md; + u32 coreclk, reg_val; mutex_lock(&dev_priv->dpio_lock); @@ -5159,7 +5468,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) /* See eDP HDMI DPIO driver vbios notes doc */ /* PLL B needs special handling */ - if (pipe) + if (pipe == PIPE_B) vlv_pllb_recal_opamp(dev_priv, pipe); /* Set up Tx target for periodic Rcomp update */ @@ -5203,7 +5512,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP) || intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT)) { /* Use SSC source */ - if (!pipe) + if (pipe == PIPE_A) vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe), 0x0df40000); else @@ -5211,7 +5520,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) 0x0df70000); } else { /* HDMI or VGA */ /* Use bend source */ - if (!pipe) + if (pipe == PIPE_A) vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe), 0x0df70000); else @@ -5227,26 +5536,84 @@ static void vlv_update_pll(struct intel_crtc *crtc) vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW7(pipe), coreclk); vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW11(pipe), 0x87871000); + mutex_unlock(&dev_priv->dpio_lock); +} + +static void chv_update_pll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = crtc->pipe; + int dpll_reg = DPLL(crtc->pipe); + enum dpio_channel port = vlv_pipe_to_channel(pipe); + u32 loopfilter, intcoeff; + u32 bestn, bestm1, bestm2, bestp1, bestp2, bestm2_frac; + int refclk; + + crtc->config.dpll_hw_state.dpll = DPLL_SSC_REF_CLOCK_CHV | + DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS | + DPLL_VCO_ENABLE; + if (pipe != PIPE_A) + crtc->config.dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; + + crtc->config.dpll_hw_state.dpll_md = + (crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT; + + bestn = crtc->config.dpll.n; + bestm2_frac = crtc->config.dpll.m2 & 0x3fffff; + bestm1 = crtc->config.dpll.m1; + bestm2 = crtc->config.dpll.m2 >> 22; + bestp1 = crtc->config.dpll.p1; + bestp2 = crtc->config.dpll.p2; /* - * Enable DPIO clock input. We should never disable the reference - * clock for pipe B, since VGA hotplug / manual detection depends - * on it. + * Enable Refclk and SSC */ - dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV | - DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV; - /* We should never disable this, set it here for state tracking */ - if (pipe == PIPE_B) - dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; - dpll |= DPLL_VCO_ENABLE; - crtc->config.dpll_hw_state.dpll = dpll; + I915_WRITE(dpll_reg, + crtc->config.dpll_hw_state.dpll & ~DPLL_VCO_ENABLE); - dpll_md = (crtc->config.pixel_multiplier - 1) - << DPLL_MD_UDI_MULTIPLIER_SHIFT; - crtc->config.dpll_hw_state.dpll_md = dpll_md; + mutex_lock(&dev_priv->dpio_lock); + + /* p1 and p2 divider */ + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW13(port), + 5 << DPIO_CHV_S1_DIV_SHIFT | + bestp1 << DPIO_CHV_P1_DIV_SHIFT | + bestp2 << DPIO_CHV_P2_DIV_SHIFT | + 1 << DPIO_CHV_K_DIV_SHIFT); + + /* Feedback post-divider - m2 */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW0(port), bestm2); + + /* Feedback refclk divider - n and m1 */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW1(port), + DPIO_CHV_M1_DIV_BY_2 | + 1 << DPIO_CHV_N_DIV_SHIFT); + + /* M2 fraction division */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac); + + /* M2 fraction division enable */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW3(port), + DPIO_CHV_FRAC_DIV_EN | + (2 << DPIO_CHV_FEEDFWD_GAIN_SHIFT)); + + /* Loop filter */ + refclk = i9xx_get_refclk(&crtc->base, 0); + loopfilter = 5 << DPIO_CHV_PROP_COEFF_SHIFT | + 2 << DPIO_CHV_GAIN_CTRL_SHIFT; + if (refclk == 100000) + intcoeff = 11; + else if (refclk == 38400) + intcoeff = 10; + else + intcoeff = 9; + loopfilter |= intcoeff << DPIO_CHV_INT_COEFF_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW6(port), loopfilter); - if (crtc->config.has_dp_encoder) - intel_dp_set_m_n(crtc); + /* AFC Recal */ + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), + vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)) | + DPIO_AFC_RECAL); mutex_unlock(&dev_priv->dpio_lock); } @@ -5325,9 +5692,6 @@ 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, @@ -5567,16 +5931,12 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; int refclk, num_connectors = 0; intel_clock_t clock, reduced_clock; - u32 dspcntr; bool ok, has_reduced_clock = false; bool is_lvds = false, is_dsi = false; struct intel_encoder *encoder; const intel_limit_t *limit; - int ret; for_each_encoder_on_crtc(dev, crtc, encoder) { switch (encoder->type) { @@ -5592,7 +5952,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, } if (is_dsi) - goto skip_dpll; + return 0; if (!intel_crtc->config.clock_set) { refclk = i9xx_get_refclk(crtc, num_connectors); @@ -5637,43 +5997,17 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, i8xx_update_pll(intel_crtc, has_reduced_clock ? &reduced_clock : NULL, num_connectors); + } else if (IS_CHERRYVIEW(dev)) { + chv_update_pll(intel_crtc); } else if (IS_VALLEYVIEW(dev)) { vlv_update_pll(intel_crtc); } else { i9xx_update_pll(intel_crtc, has_reduced_clock ? &reduced_clock : NULL, - num_connectors); - } - -skip_dpll: - /* Set up the display plane register */ - dspcntr = DISPPLANE_GAMMA_ENABLE; - - if (!IS_VALLEYVIEW(dev)) { - if (pipe == 0) - dspcntr &= ~DISPPLANE_SEL_PIPE_MASK; - else - dspcntr |= DISPPLANE_SEL_PIPE_B; + num_connectors); } - intel_set_pipe_timings(intel_crtc); - - /* pipesrc and dspsize control the size that is scaled from, - * which should always be the user's requested size. - */ - I915_WRITE(DSPSIZE(plane), - ((intel_crtc->config.pipe_src_h - 1) << 16) | - (intel_crtc->config.pipe_src_w - 1)); - I915_WRITE(DSPPOS(plane), 0); - - i9xx_set_pipeconf(intel_crtc); - - I915_WRITE(DSPCNTR(plane), dspcntr); - POSTING_READ(DSPCNTR(plane)); - - ret = intel_pipe_set_base(crtc, x, y, fb); - - return ret; + return 0; } static void i9xx_get_pfit_config(struct intel_crtc *crtc, @@ -5793,6 +6127,36 @@ static void i9xx_get_plane_config(struct intel_crtc *crtc, } +static void chv_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_config *pipe_config) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = pipe_config->cpu_transcoder; + enum dpio_channel port = vlv_pipe_to_channel(pipe); + intel_clock_t clock; + u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2; + int refclk = 100000; + + mutex_lock(&dev_priv->dpio_lock); + cmn_dw13 = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW13(port)); + pll_dw0 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW0(port)); + pll_dw1 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW1(port)); + pll_dw2 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW2(port)); + mutex_unlock(&dev_priv->dpio_lock); + + clock.m1 = (pll_dw1 & 0x7) == DPIO_CHV_M1_DIV_BY_2 ? 2 : 0; + clock.m2 = ((pll_dw0 & 0xff) << 22) | (pll_dw2 & 0x3fffff); + clock.n = (pll_dw1 >> DPIO_CHV_N_DIV_SHIFT) & 0xf; + clock.p1 = (cmn_dw13 >> DPIO_CHV_P1_DIV_SHIFT) & 0x7; + clock.p2 = (cmn_dw13 >> DPIO_CHV_P2_DIV_SHIFT) & 0x1f; + + chv_clock(refclk, &clock); + + /* clock.dot is the fast clock */ + pipe_config->port_clock = clock.dot / 5; +} + static bool i9xx_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_config *pipe_config) { @@ -5827,6 +6191,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, } } + if (IS_VALLEYVIEW(dev) && (tmp & PIPECONF_COLOR_RANGE_SELECT)) + pipe_config->limited_color_range = true; + if (INTEL_INFO(dev)->gen < 4) pipe_config->double_wide = tmp & PIPECONF_DOUBLE_WIDE; @@ -5862,7 +6229,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, DPLL_PORTB_READY_MASK); } - if (IS_VALLEYVIEW(dev)) + if (IS_CHERRYVIEW(dev)) + chv_crtc_clock_get(crtc, pipe_config); + else if (IS_VALLEYVIEW(dev)) vlv_crtc_clock_get(crtc, pipe_config); else i9xx_crtc_clock_get(crtc, pipe_config); @@ -5983,8 +6352,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) if (intel_panel_use_ssc(dev_priv) && can_ssc) { DRM_DEBUG_KMS("Using SSC on eDP\n"); val |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD; - } - else + } else val |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; } else val |= DREF_CPU_SOURCE_OUTPUT_DISABLE; @@ -6563,10 +6931,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, struct drm_framebuffer *fb) { struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; int num_connectors = 0; intel_clock_t clock, reduced_clock; u32 dpll = 0, fp = 0, fp2 = 0; @@ -6574,7 +6939,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, bool is_lvds = false; struct intel_encoder *encoder; struct intel_shared_dpll *pll; - int ret; for_each_encoder_on_crtc(dev, crtc, encoder) { switch (encoder->type) { @@ -6624,36 +6988,18 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, pll = intel_get_shared_dpll(intel_crtc); if (pll == NULL) { DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n", - pipe_name(pipe)); + pipe_name(intel_crtc->pipe)); return -EINVAL; } } else intel_put_shared_dpll(intel_crtc); - if (intel_crtc->config.has_dp_encoder) - intel_dp_set_m_n(intel_crtc); - if (is_lvds && has_reduced_clock && i915.powersave) intel_crtc->lowfreq_avail = true; else intel_crtc->lowfreq_avail = false; - intel_set_pipe_timings(intel_crtc); - - if (intel_crtc->config.has_pch_encoder) { - intel_cpu_transcoder_set_m_n(intel_crtc, - &intel_crtc->config.fdi_m_n); - } - - ironlake_set_pipeconf(crtc); - - /* Set up the display plane register */ - I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE); - POSTING_READ(DSPCNTR(plane)); - - ret = intel_pipe_set_base(crtc, x, y, fb); - - return ret; + return 0; } static void intel_pch_transcoder_get_m_n(struct intel_crtc *crtc, @@ -6831,6 +7177,9 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, break; } + if (tmp & PIPECONF_COLOR_RANGE_SELECT) + pipe_config->limited_color_range = true; + if (I915_READ(PCH_TRANSCONF(crtc->pipe)) & TRANS_ENABLE) { struct intel_shared_dpll *pll; @@ -6880,10 +7229,8 @@ 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) + for_each_intel_crtc(dev, crtc) WARN(crtc->active, "CRTC for pipe %c enabled\n", pipe_name(crtc->pipe)); @@ -6902,14 +7249,29 @@ 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 +7311,7 @@ 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 +7366,7 @@ 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 +7420,6 @@ 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 +7429,6 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv) } lpt_disable_clkout_dp(dev); - hsw_runtime_pm_disable_interrupts(dev); hsw_disable_lcpll(dev_priv, true, true); } @@ -7086,12 +7437,9 @@ 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); lpt_init_pch_refclk(dev); if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { @@ -7101,10 +7449,11 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) } intel_prepare_ddi(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 snb_modeset_global_resources(struct drm_device *dev) +{ + modeset_update_crtc_power_domains(dev); } static void haswell_modeset_global_resources(struct drm_device *dev) @@ -7116,39 +7465,15 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *fb) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int plane = intel_crtc->plane; - int ret; if (!intel_ddi_pll_select(intel_crtc)) return -EINVAL; intel_ddi_pll_enable(intel_crtc); - if (intel_crtc->config.has_dp_encoder) - intel_dp_set_m_n(intel_crtc); - intel_crtc->lowfreq_avail = false; - intel_set_pipe_timings(intel_crtc); - - if (intel_crtc->config.has_pch_encoder) { - intel_cpu_transcoder_set_m_n(intel_crtc, - &intel_crtc->config.fdi_m_n); - } - - haswell_set_pipeconf(crtc); - - intel_set_pipe_csc(crtc); - - /* Set up the display plane register */ - I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE); - POSTING_READ(DSPCNTR(plane)); - - ret = intel_pipe_set_base(crtc, x, y, fb); - - return ret; + return 0; } static bool haswell_get_pipe_config(struct intel_crtc *crtc, @@ -7228,38 +7553,6 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, return true; } -static int intel_crtc_mode_set(struct drm_crtc *crtc, - int x, int y, - struct drm_framebuffer *fb) -{ - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *encoder; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_display_mode *mode = &intel_crtc->config.requested_mode; - int pipe = intel_crtc->pipe; - int ret; - - drm_vblank_pre_modeset(dev, pipe); - - ret = dev_priv->display.crtc_mode_set(crtc, x, y, fb); - - drm_vblank_post_modeset(dev, pipe); - - if (ret != 0) - return ret; - - for_each_encoder_on_crtc(dev, crtc, encoder) { - DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n", - encoder->base.base.id, - drm_get_encoder_name(&encoder->base), - mode->base.id, mode->name); - encoder->mode_set(encoder); - } - - return 0; -} - static struct { int clock; u32 config; @@ -7374,8 +7667,6 @@ static void haswell_write_eld(struct drm_connector *connector, { struct drm_i915_private *dev_priv = connector->dev->dev_private; uint8_t *eld = connector->eld; - struct drm_device *dev = crtc->dev; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t eldv; uint32_t i; int len; @@ -7387,17 +7678,14 @@ static void haswell_write_eld(struct drm_connector *connector, int aud_config = HSW_AUD_CFG(pipe); int aud_cntrl_st2 = HSW_AUD_PIN_ELD_CP_VLD; - - DRM_DEBUG_DRIVER("HDMI: Haswell Audio initialize....\n"); - /* Audio output enable */ DRM_DEBUG_DRIVER("HDMI audio: enable codec\n"); tmp = I915_READ(aud_cntrl_st2); tmp |= (AUDIO_OUTPUT_ENABLE_A << (pipe * 4)); I915_WRITE(aud_cntrl_st2, tmp); + POSTING_READ(aud_cntrl_st2); - /* Wait for 1 vertical blank */ - intel_wait_for_vblank(dev, pipe); + assert_pipe_disabled(dev_priv, to_intel_crtc(crtc)->pipe); /* Set ELD valid state */ tmp = I915_READ(aud_cntrl_st2); @@ -7417,7 +7705,6 @@ static void haswell_write_eld(struct drm_connector *connector, DRM_DEBUG_DRIVER("ELD on pipe %c\n", pipe_name(pipe)); eldv = AUDIO_ELD_VALID_A << (pipe * 4); - intel_crtc->eld_vld = true; if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) { DRM_DEBUG_DRIVER("ELD: DisplayPort detected\n"); @@ -7564,9 +7851,9 @@ void intel_write_eld(struct drm_encoder *encoder, DRM_DEBUG_DRIVER("ELD on [CONNECTOR:%d:%s], [ENCODER:%d:%s]\n", connector->base.id, - drm_get_connector_name(connector), + connector->name, connector->encoder->base.id, - drm_get_encoder_name(connector->encoder)); + connector->encoder->name); connector->eld[6] = drm_av_sync_delay(connector, mode) / 2; @@ -7579,29 +7866,33 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base) struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - bool visible = base != 0; - u32 cntl; + uint32_t cntl; - if (intel_crtc->cursor_visible == visible) - return; - - cntl = I915_READ(_CURACNTR); - if (visible) { + if (base != intel_crtc->cursor_base) { /* On these chipsets we can only modify the base whilst * the cursor is disabled. */ + if (intel_crtc->cursor_cntl) { + I915_WRITE(_CURACNTR, 0); + POSTING_READ(_CURACNTR); + intel_crtc->cursor_cntl = 0; + } + I915_WRITE(_CURABASE, base); + POSTING_READ(_CURABASE); + } - cntl &= ~(CURSOR_FORMAT_MASK); - /* XXX width must be 64, stride 256 => 0x00 << 28 */ - cntl |= CURSOR_ENABLE | + /* XXX width must be 64, stride 256 => 0x00 << 28 */ + cntl = 0; + if (base) + cntl = (CURSOR_ENABLE | CURSOR_GAMMA_ENABLE | - CURSOR_FORMAT_ARGB; - } else - cntl &= ~(CURSOR_ENABLE | CURSOR_GAMMA_ENABLE); - I915_WRITE(_CURACNTR, cntl); - - intel_crtc->cursor_visible = visible; + CURSOR_FORMAT_ARGB); + if (intel_crtc->cursor_cntl != cntl) { + I915_WRITE(_CURACNTR, cntl); + POSTING_READ(_CURACNTR); + intel_crtc->cursor_cntl = cntl; + } } static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) @@ -7610,16 +7901,12 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - bool visible = base != 0; + uint32_t cntl; - if (intel_crtc->cursor_visible != visible) { - int16_t width = intel_crtc->cursor_width; - uint32_t cntl = I915_READ(CURCNTR(pipe)); - if (base) { - cntl &= ~(CURSOR_MODE | MCURSOR_PIPE_SELECT); - cntl |= MCURSOR_GAMMA_ENABLE; - - switch (width) { + cntl = 0; + if (base) { + cntl = MCURSOR_GAMMA_ENABLE; + switch (intel_crtc->cursor_width) { case 64: cntl |= CURSOR_MODE_64_ARGB_AX; break; @@ -7632,18 +7919,16 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) default: WARN_ON(1); return; - } - cntl |= pipe << 28; /* Connect to correct pipe */ - } else { - cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE); - cntl |= CURSOR_MODE_DISABLE; } + cntl |= pipe << 28; /* Connect to correct pipe */ + } + if (intel_crtc->cursor_cntl != cntl) { I915_WRITE(CURCNTR(pipe), cntl); - - intel_crtc->cursor_visible = visible; + POSTING_READ(CURCNTR(pipe)); + intel_crtc->cursor_cntl = cntl; } + /* and commit changes on next vblank */ - POSTING_READ(CURCNTR(pipe)); I915_WRITE(CURBASE(pipe), base); POSTING_READ(CURBASE(pipe)); } @@ -7654,15 +7939,12 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - bool visible = base != 0; - - if (intel_crtc->cursor_visible != visible) { - int16_t width = intel_crtc->cursor_width; - uint32_t cntl = I915_READ(CURCNTR_IVB(pipe)); - if (base) { - cntl &= ~CURSOR_MODE; - cntl |= MCURSOR_GAMMA_ENABLE; - switch (width) { + uint32_t cntl; + + cntl = 0; + if (base) { + cntl = MCURSOR_GAMMA_ENABLE; + switch (intel_crtc->cursor_width) { case 64: cntl |= CURSOR_MODE_64_ARGB_AX; break; @@ -7675,23 +7957,20 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) default: WARN_ON(1); return; - } - } else { - cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE); - cntl |= CURSOR_MODE_DISABLE; - } - if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { - cntl |= CURSOR_PIPE_CSC_ENABLE; - cntl &= ~CURSOR_TRICKLE_FEED_DISABLE; } - I915_WRITE(CURCNTR_IVB(pipe), cntl); + } + if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + cntl |= CURSOR_PIPE_CSC_ENABLE; - intel_crtc->cursor_visible = visible; + if (intel_crtc->cursor_cntl != cntl) { + I915_WRITE(CURCNTR(pipe), cntl); + POSTING_READ(CURCNTR(pipe)); + intel_crtc->cursor_cntl = cntl; } + /* and commit changes on next vblank */ - POSTING_READ(CURCNTR_IVB(pipe)); - I915_WRITE(CURBASE_IVB(pipe), base); - POSTING_READ(CURBASE_IVB(pipe)); + I915_WRITE(CURBASE(pipe), base); + POSTING_READ(CURBASE(pipe)); } /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */ @@ -7705,7 +7984,6 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, int x = intel_crtc->cursor_x; int y = intel_crtc->cursor_y; u32 base = 0, pos = 0; - bool visible; if (on) base = intel_crtc->cursor_addr; @@ -7734,20 +8012,18 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, } pos |= y << CURSOR_Y_SHIFT; - visible = base != 0; - if (!visible && !intel_crtc->cursor_visible) + if (base == 0 && intel_crtc->cursor_base == 0) return; - if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) { - I915_WRITE(CURPOS_IVB(pipe), pos); + I915_WRITE(CURPOS(pipe), pos); + + if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) ivb_update_cursor(crtc, base); - } else { - I915_WRITE(CURPOS(pipe), pos); - if (IS_845G(dev) || IS_I865G(dev)) - i845_update_cursor(crtc, base); - else - i9xx_update_cursor(crtc, base); - } + else if (IS_845G(dev) || IS_I865G(dev)) + i845_update_cursor(crtc, base); + else + i9xx_update_cursor(crtc, base); + intel_crtc->cursor_base = base; } static int intel_crtc_cursor_set(struct drm_crtc *crtc, @@ -8015,7 +8291,8 @@ mode_fits_in_fbdev(struct drm_device *dev, bool intel_get_load_detect_pipe(struct drm_connector *connector, struct drm_display_mode *mode, - struct intel_load_detect_pipe *old) + struct intel_load_detect_pipe *old, + struct drm_modeset_acquire_ctx *ctx) { struct intel_crtc *intel_crtc; struct intel_encoder *intel_encoder = @@ -8025,11 +8302,19 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector, struct drm_crtc *crtc = NULL; struct drm_device *dev = encoder->dev; struct drm_framebuffer *fb; - int i = -1; + struct drm_mode_config *config = &dev->mode_config; + int ret, i = -1; DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector), - encoder->base.id, drm_get_encoder_name(encoder)); + connector->base.id, connector->name, + encoder->base.id, encoder->name); + + drm_modeset_acquire_init(ctx, 0); + +retry: + ret = drm_modeset_lock(&config->connection_mutex, ctx); + if (ret) + goto fail_unlock; /* * Algorithm gets a little messy: @@ -8045,7 +8330,9 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector, if (encoder->crtc) { crtc = encoder->crtc; - mutex_lock(&crtc->mutex); + ret = drm_modeset_lock(&crtc->mutex, ctx); + if (ret) + goto fail_unlock; old->dpms_mode = connector->dpms; old->load_detect_temp = false; @@ -8058,7 +8345,7 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector, } /* Find an unused one (if possible) */ - list_for_each_entry(possible_crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, possible_crtc) { i++; if (!(encoder->possible_crtcs & (1 << i))) continue; @@ -8073,10 +8360,12 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector, */ if (!crtc) { DRM_DEBUG_KMS("no pipe available for load-detect\n"); - return false; + goto fail_unlock; } - mutex_lock(&crtc->mutex); + ret = drm_modeset_lock(&crtc->mutex, ctx); + if (ret) + goto fail_unlock; intel_encoder->new_crtc = to_intel_crtc(crtc); to_intel_connector(connector)->new_encoder = intel_encoder; @@ -8126,12 +8415,21 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector, intel_crtc->new_config = &intel_crtc->config; else intel_crtc->new_config = NULL; - mutex_unlock(&crtc->mutex); +fail_unlock: + if (ret == -EDEADLK) { + drm_modeset_backoff(ctx); + goto retry; + } + + drm_modeset_drop_locks(ctx); + drm_modeset_acquire_fini(ctx); + return false; } void intel_release_load_detect_pipe(struct drm_connector *connector, - struct intel_load_detect_pipe *old) + struct intel_load_detect_pipe *old, + struct drm_modeset_acquire_ctx *ctx) { struct intel_encoder *intel_encoder = intel_attached_encoder(connector); @@ -8140,8 +8438,8 @@ void intel_release_load_detect_pipe(struct drm_connector *connector, struct intel_crtc *intel_crtc = to_intel_crtc(crtc); DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector), - encoder->base.id, drm_get_encoder_name(encoder)); + connector->base.id, connector->name, + encoder->base.id, encoder->name); if (old->load_detect_temp) { to_intel_connector(connector)->new_encoder = NULL; @@ -8155,7 +8453,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector, drm_framebuffer_unreference(old->release_fb); } - mutex_unlock(&crtc->mutex); + goto unlock; return; } @@ -8163,7 +8461,9 @@ void intel_release_load_detect_pipe(struct drm_connector *connector, if (old->dpms_mode != DRM_MODE_DPMS_ON) connector->funcs->dpms(connector, old->dpms_mode); - mutex_unlock(&crtc->mutex); +unlock: + drm_modeset_drop_locks(ctx); + drm_modeset_acquire_fini(ctx); } static int i9xx_pll_refclk(struct drm_device *dev, @@ -8449,7 +8749,7 @@ void intel_mark_idle(struct drm_device *dev) if (!i915.powersave) goto out; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (!crtc->primary->fb) continue; @@ -8464,7 +8764,7 @@ out: } void intel_mark_fb_busy(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_device *dev = obj->base.dev; struct drm_crtc *crtc; @@ -8472,7 +8772,7 @@ void intel_mark_fb_busy(struct drm_i915_gem_object *obj, if (!i915.powersave) return; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (!crtc->primary->fb) continue; @@ -8560,7 +8860,7 @@ static void do_intel_finish_page_flip(struct drm_device *dev, if (work->event) drm_send_vblank_event(dev, intel_crtc->pipe, work->event); - drm_vblank_put(dev, intel_crtc->pipe); + drm_crtc_vblank_put(crtc); spin_unlock_irqrestore(&dev->event_lock, flags); @@ -8587,6 +8887,48 @@ void intel_finish_page_flip_plane(struct drm_device *dev, int plane) do_intel_finish_page_flip(dev, crtc); } +/* Is 'a' after or equal to 'b'? */ +static bool g4x_flip_count_after_eq(u32 a, u32 b) +{ + return !((a - b) & 0x80000000); +} + +static bool page_flip_finished(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + /* + * The relevant registers doen't exist on pre-ctg. + * As the flip done interrupt doesn't trigger for mmio + * flips on gmch platforms, a flip count check isn't + * really needed there. But since ctg has the registers, + * include it in the check anyway. + */ + if (INTEL_INFO(dev)->gen < 5 && !IS_G4X(dev)) + return true; + + /* + * A DSPSURFLIVE check isn't enough in case the mmio and CS flips + * used the same base address. In that case the mmio flip might + * have completed, but the CS hasn't even executed the flip yet. + * + * A flip count check isn't enough as the CS might have updated + * the base address just after start of vblank, but before we + * managed to process the interrupt. This means we'd complete the + * CS flip too soon. + * + * Combining both checks should get us a good enough result. It may + * still happen that the CS flip has been executed, but has not + * yet actually completed. But in case the base address is the same + * anyway, we don't really care. + */ + return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) == + crtc->unpin_work->gtt_offset && + g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_GM45(crtc->pipe)), + crtc->unpin_work->flip_count); +} + void intel_prepare_page_flip(struct drm_device *dev, int plane) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -8599,12 +8941,12 @@ void intel_prepare_page_flip(struct drm_device *dev, int plane) * is also accompanied by a spurious intel_prepare_page_flip(). */ spin_lock_irqsave(&dev->event_lock, flags); - if (intel_crtc->unpin_work) + if (intel_crtc->unpin_work && page_flip_finished(intel_crtc)) atomic_inc_not_zero(&intel_crtc->unpin_work->pending); spin_unlock_irqrestore(&dev->event_lock, flags); } -inline static void intel_mark_page_flip_active(struct intel_crtc *intel_crtc) +static inline void intel_mark_page_flip_active(struct intel_crtc *intel_crtc) { /* Ensure that the work item is consistent when activating it ... */ smp_wmb(); @@ -8617,21 +8959,16 @@ static int intel_gen2_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); u32 flip_mask; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 6); if (ret) - goto err_unpin; + return ret; /* Can't queue multiple flips, so wait for the previous * one to finish before executing the next. @@ -8645,38 +8982,28 @@ static int intel_gen2_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); intel_ring_emit(ring, 0); /* aux display base address, unused */ intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen3_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); u32 flip_mask; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 6); if (ret) - goto err_unpin; + return ret; if (intel_crtc->plane) flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; @@ -8687,38 +9014,29 @@ static int intel_gen3_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); intel_ring_emit(ring, MI_NOOP); intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen4_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t pf, pipesrc; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 4); if (ret) - goto err_unpin; + return ret; /* i965+ uses the linear or tiled offsets from the * Display Registers (which do not change across a page-flip) @@ -8727,8 +9045,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, - (i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) | + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset | obj->tiling_mode); /* XXX Enabling the panel-fitter across page-flip is so far @@ -8742,37 +9059,28 @@ static int intel_gen4_queue_flip(struct drm_device *dev, intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen6_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; uint32_t pf, pipesrc; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 4); if (ret) - goto err_unpin; + return ret; intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); /* Contrary to the suggestions in the documentation, * "Enable Panel Fitter" does not seem to be required when page @@ -8787,34 +9095,20 @@ static int intel_gen6_queue_flip(struct drm_device *dev, intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen7_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_ring_buffer *ring; uint32_t plane_bit = 0; int len, ret; - ring = obj->ring; - if (IS_VALLEYVIEW(dev) || ring == NULL || ring->id != RCS) - ring = &dev_priv->ring[BCS]; - - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - - switch(intel_crtc->plane) { + switch (intel_crtc->plane) { case PLANE_A: plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_A; break; @@ -8826,13 +9120,20 @@ static int intel_gen7_queue_flip(struct drm_device *dev, break; default: WARN_ONCE(1, "unknown plane in flip command\n"); - ret = -ENODEV; - goto err_unpin; + return -ENODEV; } len = 4; - if (ring->id == RCS) + if (ring->id == RCS) { len += 6; + /* + * On Gen 8, SRM is now taking an extra dword to accommodate + * 48bits addresses, and we need a NOOP for the batch size to + * stay even. + */ + if (IS_GEN8(dev)) + len += 2; + } /* * BSpec MI_DISPLAY_FLIP for IVB: @@ -8846,11 +9147,11 @@ static int intel_gen7_queue_flip(struct drm_device *dev, */ ret = intel_ring_cacheline_align(ring); if (ret) - goto err_unpin; + return ret; ret = intel_ring_begin(ring, len); if (ret) - goto err_unpin; + return ret; /* Unmask the flip-done completion message. Note that the bspec says that * we should do this for both the BCS and RCS, and that we must not unmask @@ -8867,31 +9168,35 @@ static int intel_gen7_queue_flip(struct drm_device *dev, intel_ring_emit(ring, ~(DERRMR_PIPEA_PRI_FLIP_DONE | DERRMR_PIPEB_PRI_FLIP_DONE | DERRMR_PIPEC_PRI_FLIP_DONE)); - intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) | - MI_SRM_LRM_GLOBAL_GTT); + if (IS_GEN8(dev)) + intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8(1) | + MI_SRM_LRM_GLOBAL_GTT); + else + intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) | + MI_SRM_LRM_GLOBAL_GTT); intel_ring_emit(ring, DERRMR); intel_ring_emit(ring, ring->scratch.gtt_offset + 256); + if (IS_GEN8(dev)) { + intel_ring_emit(ring, 0); + intel_ring_emit(ring, MI_NOOP); + } } intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit); intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode)); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); intel_ring_emit(ring, (MI_NOOP)); intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_default_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { return -ENODEV; @@ -8908,6 +9213,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, struct drm_i915_gem_object *obj = to_intel_framebuffer(fb)->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_unpin_work *work; + struct intel_engine_cs *ring; unsigned long flags; int ret; @@ -8936,7 +9242,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, work->old_fb_obj = to_intel_framebuffer(old_fb)->obj; INIT_WORK(&work->work, intel_unpin_work_fn); - ret = drm_vblank_get(dev, intel_crtc->pipe); + ret = drm_crtc_vblank_get(crtc); if (ret) goto free_work; @@ -8945,7 +9251,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, if (intel_crtc->unpin_work) { spin_unlock_irqrestore(&dev->event_lock, flags); kfree(work); - drm_vblank_put(dev, intel_crtc->pipe); + drm_crtc_vblank_put(crtc); DRM_DEBUG_DRIVER("flip queue: crtc already busy\n"); return -EBUSY; @@ -8973,10 +9279,30 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, atomic_inc(&intel_crtc->unpin_work_count); intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); - ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, page_flip_flags); + if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev)) + work->flip_count = I915_READ(PIPE_FLIPCOUNT_GM45(intel_crtc->pipe)) + 1; + + if (IS_VALLEYVIEW(dev)) { + ring = &dev_priv->ring[BCS]; + } else if (INTEL_INFO(dev)->gen >= 7) { + ring = obj->ring; + if (ring == NULL || ring->id != RCS) + ring = &dev_priv->ring[BCS]; + } else { + ring = &dev_priv->ring[RCS]; + } + + ret = intel_pin_and_fence_fb_obj(dev, obj, ring); if (ret) goto cleanup_pending; + work->gtt_offset = + i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset; + + ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring, page_flip_flags); + if (ret) + goto cleanup_unpin; + intel_disable_fbc(dev); intel_mark_fb_busy(obj, NULL); mutex_unlock(&dev->struct_mutex); @@ -8985,6 +9311,8 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, return 0; +cleanup_unpin: + intel_unpin_fb_obj(obj); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); crtc->primary->fb = old_fb; @@ -8997,7 +9325,7 @@ cleanup: intel_crtc->unpin_work = NULL; spin_unlock_irqrestore(&dev->event_lock, flags); - drm_vblank_put(dev, intel_crtc->pipe); + drm_crtc_vblank_put(crtc); free_work: kfree(work); @@ -9040,8 +9368,7 @@ static void intel_modeset_update_staged_output_state(struct drm_device *dev) to_intel_crtc(encoder->base.crtc); } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { crtc->new_enabled = crtc->base.enabled; if (crtc->new_enabled) @@ -9072,21 +9399,20 @@ static void intel_modeset_commit_output_state(struct drm_device *dev) encoder->base.crtc = &encoder->new_crtc->base; } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { crtc->base.enabled = crtc->new_enabled; } } static void -connected_sink_compute_bpp(struct intel_connector * connector, +connected_sink_compute_bpp(struct intel_connector *connector, struct intel_crtc_config *pipe_config) { int bpp = pipe_config->pipe_bpp; DRM_DEBUG_KMS("[CONNECTOR:%d:%s] checking for sink bpp constrains\n", connector->base.base.id, - drm_get_connector_name(&connector->base)); + connector->base.name); /* Don't use an invalid EDID bpc value */ if (connector->base.display_info.bpc && @@ -9427,8 +9753,7 @@ intel_modeset_affected_pipes(struct drm_crtc *crtc, unsigned *modeset_pipes, } /* Check for pipes that will be enabled/disabled ... */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, intel_crtc) { if (intel_crtc->base.enabled == intel_crtc->new_enabled) continue; @@ -9501,8 +9826,7 @@ intel_modeset_update_state(struct drm_device *dev, unsigned prepare_pipes) intel_modeset_commit_output_state(dev); /* Double check state. */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, intel_crtc) { WARN_ON(intel_crtc->base.enabled != intel_crtc_in_use(&intel_crtc->base)); WARN_ON(intel_crtc->new_config && intel_crtc->new_config != &intel_crtc->config); @@ -9631,6 +9955,12 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_end); PIPE_CONF_CHECK_I(pixel_multiplier); + PIPE_CONF_CHECK_I(has_hdmi_sink); + if ((INTEL_INFO(dev)->gen < 8 && !IS_HASWELL(dev)) || + IS_VALLEYVIEW(dev)) + PIPE_CONF_CHECK_I(limited_color_range); + + PIPE_CONF_CHECK_I(has_audio); PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags, DRM_MODE_FLAG_INTERLACE); @@ -9728,7 +10058,7 @@ check_encoder_state(struct drm_device *dev) DRM_DEBUG_KMS("[ENCODER:%d:%s]\n", encoder->base.base.id, - drm_get_encoder_name(&encoder->base)); + encoder->base.name); WARN(&encoder->new_crtc->base != encoder->base.crtc, "encoder's stage crtc doesn't match current crtc\n"); @@ -9780,8 +10110,7 @@ check_crtc_state(struct drm_device *dev) struct intel_encoder *encoder; struct intel_crtc_config pipe_config; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { bool enabled = false; bool active = false; @@ -9870,8 +10199,7 @@ check_shared_dpll_state(struct drm_device *dev) "pll on state mismatch (expected %i, found %i)\n", pll->on, active); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (crtc->base.enabled && intel_crtc_to_shared_dpll(crtc) == pll) enabled_crtcs++; if (crtc->active && intel_crtc_to_shared_dpll(crtc) == pll) @@ -9911,6 +10239,44 @@ void ironlake_check_encoder_dotclock(const struct intel_crtc_config *pipe_config pipe_config->adjusted_mode.crtc_clock, dotclock); } +static void update_scanline_offset(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + + /* + * The scanline counter increments at the leading edge of hsync. + * + * On most platforms it starts counting from vtotal-1 on the + * first active line. That means the scanline counter value is + * always one less than what we would expect. Ie. just after + * start of vblank, which also occurs at start of hsync (on the + * last active line), the scanline counter will read vblank_start-1. + * + * On gen2 the scanline counter starts counting from 1 instead + * of vtotal-1, so we have to subtract one (or rather add vtotal-1 + * to keep the value positive), instead of adding one. + * + * On HSW+ the behaviour of the scanline counter depends on the output + * type. For DP ports it behaves like most other platforms, but on HDMI + * there's an extra 1 line difference. So we need to add two instead of + * one to the value. + */ + if (IS_GEN2(dev)) { + const struct drm_display_mode *mode = &crtc->config.adjusted_mode; + int vtotal; + + vtotal = mode->crtc_vtotal; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vtotal /= 2; + + crtc->scanline_offset = vtotal - 1; + } else if (HAS_DDI(dev) && + intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI)) { + crtc->scanline_offset = 2; + } else + crtc->scanline_offset = 1; +} + static int __intel_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode, int x, int y, struct drm_framebuffer *fb) @@ -10002,15 +10368,38 @@ static int __intel_set_mode(struct drm_crtc *crtc, * on the DPLL. */ for_each_intel_crtc_masked(dev, modeset_pipes, intel_crtc) { - ret = intel_crtc_mode_set(&intel_crtc->base, - x, y, fb); + struct drm_framebuffer *old_fb; + + mutex_lock(&dev->struct_mutex); + ret = intel_pin_and_fence_fb_obj(dev, + to_intel_framebuffer(fb)->obj, + NULL); + if (ret != 0) { + DRM_ERROR("pin & fence failed\n"); + mutex_unlock(&dev->struct_mutex); + goto done; + } + old_fb = crtc->primary->fb; + if (old_fb) + intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj); + mutex_unlock(&dev->struct_mutex); + + crtc->primary->fb = fb; + crtc->x = x; + crtc->y = y; + + ret = dev_priv->display.crtc_mode_set(&intel_crtc->base, + x, y, fb); if (ret) goto done; } /* Now enable the clocks, plane, pipe, and connectors that we set up. */ - for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc) + for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc) { + update_scanline_offset(intel_crtc); + dev_priv->display.crtc_enable(&intel_crtc->base); + } /* FIXME: add subpixel order */ done: @@ -10086,7 +10475,7 @@ static int intel_set_config_save_state(struct drm_device *dev, * restored, not the drivers personal bookkeeping. */ count = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { config->save_crtc_enabled[count++] = crtc->enabled; } @@ -10112,7 +10501,7 @@ static void intel_set_config_restore_state(struct drm_device *dev, int count; count = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { crtc->new_enabled = config->save_crtc_enabled[count++]; if (crtc->new_enabled) @@ -10236,7 +10625,7 @@ intel_modeset_stage_output_state(struct drm_device *dev, DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n", connector->base.base.id, - drm_get_connector_name(&connector->base)); + connector->base.name); } @@ -10271,7 +10660,7 @@ intel_modeset_stage_output_state(struct drm_device *dev, DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n", connector->base.base.id, - drm_get_connector_name(&connector->base), + connector->base.name, new_crtc->base.id); } @@ -10302,8 +10691,7 @@ intel_modeset_stage_output_state(struct drm_device *dev, } /* Now we've also updated encoder->new_crtc for all encoders. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { crtc->new_enabled = false; list_for_each_entry(encoder, @@ -10516,7 +10904,7 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv, struct intel_crtc *crtc; /* Make sure no transcoder isn't still depending on us. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { if (intel_crtc_to_shared_dpll(crtc) == pll) assert_pch_transcoder_disabled(dev_priv, crtc->pipe); } @@ -10573,16 +10961,6 @@ 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; @@ -10601,19 +10979,27 @@ static void intel_crtc_init(struct drm_device *dev, int pipe) intel_crtc->plane = !pipe; } + intel_crtc->cursor_base = ~0; + intel_crtc->cursor_cntl = ~0; + + init_waitqueue_head(&intel_crtc->vbl_wait); + BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) || dev_priv->plane_to_crtc_mapping[intel_crtc->plane] != NULL); dev_priv->plane_to_crtc_mapping[intel_crtc->plane] = &intel_crtc->base; dev_priv->pipe_to_crtc_mapping[intel_crtc->pipe] = &intel_crtc->base; drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs); + + WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe); } enum pipe intel_get_pipe_from_connector(struct intel_connector *connector) { struct drm_encoder *encoder = connector->base.encoder; + struct drm_device *dev = connector->base.dev; - WARN_ON(!mutex_is_locked(&connector->base.dev->mode_config.mutex)); + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); if (!encoder) return INVALID_PIPE; @@ -10709,7 +11095,7 @@ static void intel_setup_outputs(struct drm_device *dev) intel_lvds_init(dev); - if (!IS_ULT(dev)) + if (!IS_ULT(dev) && !IS_CHERRYVIEW(dev) && dev_priv->vbt.int_crt_support) intel_crt_init(dev); if (HAS_DDI(dev)) { @@ -10773,6 +11159,15 @@ static void intel_setup_outputs(struct drm_device *dev) intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C); } + if (IS_CHERRYVIEW(dev)) { + if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED) { + intel_hdmi_init(dev, VLV_DISPLAY_BASE + CHV_HDMID, + PORT_D); + if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED) + intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D); + } + } + intel_dsi_init(dev); } else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) { bool found = false; @@ -11002,6 +11397,8 @@ static void intel_init_display(struct drm_device *dev) if (HAS_PCH_SPLIT(dev) || IS_G4X(dev)) dev_priv->display.find_dpll = g4x_find_best_dpll; + else if (IS_CHERRYVIEW(dev)) + dev_priv->display.find_dpll = chv_find_best_dpll; else if (IS_VALLEYVIEW(dev)) dev_priv->display.find_dpll = vlv_find_best_dpll; else if (IS_PINEVIEW(dev)) @@ -11083,6 +11480,8 @@ 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; @@ -11211,9 +11610,6 @@ static struct intel_quirk intel_quirks[] = { /* ThinkPad T60 needs pipe A force quirk (bug #16494) */ { 0x2782, 0x17aa, 0x201a, quirk_pipea_force }, - /* 830 needs to leave pipe A & dpll A up */ - { 0x3577, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force }, - /* Lenovo U160 cannot use SSC on LVDS */ { 0x0046, 0x17aa, 0x3920, quirk_ssc_force_disable }, @@ -11287,9 +11683,7 @@ void intel_modeset_init_hw(struct drm_device *dev) intel_reset_dpio(dev); - mutex_lock(&dev->struct_mutex); intel_enable_gt_powersave(dev); - mutex_unlock(&dev->struct_mutex); } void intel_modeset_suspend_hw(struct drm_device *dev) @@ -11333,6 +11727,15 @@ 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", @@ -11362,12 +11765,11 @@ void intel_modeset_init(struct drm_device *dev) /* Just in case the BIOS is doing something questionable. */ intel_disable_fbc(dev); - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock_all(dev); intel_modeset_setup_hw_state(dev, false); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock_all(dev); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (!crtc->active) continue; @@ -11395,6 +11797,7 @@ static void intel_enable_pipe_a(struct drm_device *dev) struct intel_connector *connector; struct drm_connector *crt = NULL; struct intel_load_detect_pipe load_detect_temp; + struct drm_modeset_acquire_ctx ctx; /* We can't just switch on the pipe A, we need to set things up with a * proper mode and output configuration. As a gross hack, enable pipe A @@ -11411,8 +11814,8 @@ static void intel_enable_pipe_a(struct drm_device *dev) if (!crt) return; - if (intel_get_load_detect_pipe(crt, NULL, &load_detect_temp)) - intel_release_load_detect_pipe(crt, &load_detect_temp); + if (intel_get_load_detect_pipe(crt, NULL, &load_detect_temp, &ctx)) + intel_release_load_detect_pipe(crt, &load_detect_temp, &ctx); } @@ -11447,6 +11850,12 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) reg = PIPECONF(crtc->config.cpu_transcoder); I915_WRITE(reg, I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK); + /* restore vblank interrupts to correct state */ + if (crtc->active) + drm_vblank_on(dev, crtc->pipe); + else + drm_vblank_off(dev, crtc->pipe); + /* We need to sanitize the plane -> pipe mapping first because this will * disable the crtc (and hence change the state) if it is wrong. Note * that gen4+ has a fixed plane -> pipe mapping. */ @@ -11525,16 +11934,25 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) encoder->base.crtc = NULL; } } - if (crtc->active) { + + if (crtc->active || IS_VALLEYVIEW(dev) || INTEL_INFO(dev)->gen < 5) { /* * We start out with underrun reporting disabled to avoid races. * For correct bookkeeping mark this on active crtcs. * + * Also on gmch platforms we dont have any hardware bits to + * disable the underrun reporting. Which means we need to start + * out with underrun reporting disabled also on inactive pipes, + * since otherwise we'll complain about the garbage we read when + * e.g. coming up after runtime pm. + * * No protection against concurrent access is required - at * worst a fifo underrun happens which also sets this to false. */ crtc->cpu_fifo_underrun_disabled = true; crtc->pch_fifo_underrun_disabled = true; + + update_scanline_offset(crtc); } } @@ -11552,7 +11970,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) if (encoder->connectors_active && !has_active_crtc) { DRM_DEBUG_KMS("[ENCODER:%d:%s] has active connectors but no active pipe!\n", encoder->base.base.id, - drm_get_encoder_name(&encoder->base)); + encoder->base.name); /* Connector is active, but has no active pipe. This is * fallout from our resume register restoring. Disable @@ -11560,7 +11978,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) if (encoder->base.crtc) { DRM_DEBUG_KMS("[ENCODER:%d:%s] manually disabled\n", encoder->base.base.id, - drm_get_encoder_name(&encoder->base)); + encoder->base.name); encoder->disable(encoder); } encoder->base.crtc = NULL; @@ -11611,6 +12029,16 @@ void i915_redisable_vga(struct drm_device *dev) i915_redisable_vga_power_on(dev); } +static bool primary_get_hw_state(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + + if (!crtc->active) + return false; + + return I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE; +} + static void intel_modeset_readout_hw_state(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -11620,8 +12048,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) struct intel_connector *connector; int i; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { memset(&crtc->config, 0, sizeof(crtc->config)); crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE; @@ -11630,7 +12057,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) &crtc->config); crtc->base.enabled = crtc->active; - crtc->primary_enabled = crtc->active; + crtc->primary_enabled = primary_get_hw_state(crtc); DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n", crtc->base.base.id, @@ -11646,8 +12073,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) pll->on = pll->get_hw_state(dev_priv, pll, &pll->hw_state); pll->active = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (crtc->active && intel_crtc_to_shared_dpll(crtc) == pll) pll->active++; } @@ -11672,7 +12098,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) encoder->connectors_active = false; DRM_DEBUG_KMS("[ENCODER:%d:%s] hw state readout: %s, pipe %c\n", encoder->base.base.id, - drm_get_encoder_name(&encoder->base), + encoder->base.name, encoder->base.crtc ? "enabled" : "disabled", pipe_name(pipe)); } @@ -11689,7 +12115,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) } DRM_DEBUG_KMS("[CONNECTOR:%d:%s] hw state readout: %s\n", connector->base.base.id, - drm_get_connector_name(&connector->base), + connector->base.name, connector->base.encoder ? "enabled" : "disabled"); } } @@ -11712,8 +12138,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev, * Note that this could go away if we move to using crtc_config * checking everywhere. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (crtc->active && i915.fastboot) { intel_mode_from_pipe_config(&crtc->base.mode, &crtc->config); DRM_DEBUG_KMS("[CRTC:%d] found active mode: ", @@ -11789,7 +12214,7 @@ void intel_modeset_gem_init(struct drm_device *dev) * for this. */ mutex_lock(&dev->struct_mutex); - list_for_each_entry(c, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, c) { if (!c->primary->fb) continue; @@ -11835,7 +12260,7 @@ void intel_modeset_cleanup(struct drm_device *dev) intel_unregister_dsm_handler(); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { /* Skip inactive CRTCs */ if (!crtc->primary->fb) continue; @@ -11933,6 +12358,7 @@ struct intel_display_error_state { struct intel_pipe_error_state { bool power_domain_on; u32 source; + u32 stat; } pipe[I915_MAX_PIPES]; struct intel_plane_error_state { @@ -11990,15 +12416,9 @@ intel_display_capture_error_state(struct drm_device *dev) if (!error->pipe[i].power_domain_on) continue; - if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) { - error->cursor[i].control = I915_READ(CURCNTR(i)); - error->cursor[i].position = I915_READ(CURPOS(i)); - error->cursor[i].base = I915_READ(CURBASE(i)); - } else { - error->cursor[i].control = I915_READ(CURCNTR_IVB(i)); - error->cursor[i].position = I915_READ(CURPOS_IVB(i)); - error->cursor[i].base = I915_READ(CURBASE_IVB(i)); - } + error->cursor[i].control = I915_READ(CURCNTR(i)); + error->cursor[i].position = I915_READ(CURPOS(i)); + error->cursor[i].base = I915_READ(CURBASE(i)); error->plane[i].control = I915_READ(DSPCNTR(i)); error->plane[i].stride = I915_READ(DSPSTRIDE(i)); @@ -12014,6 +12434,9 @@ intel_display_capture_error_state(struct drm_device *dev) } error->pipe[i].source = I915_READ(PIPESRC(i)); + + if (!HAS_PCH_SPLIT(dev)) + error->pipe[i].stat = I915_READ(PIPESTAT(i)); } error->num_transcoders = INTEL_INFO(dev)->num_pipes; @@ -12064,6 +12487,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m, err_printf(m, " Power: %s\n", error->pipe[i].power_domain_on ? "on" : "off"); err_printf(m, " SRC: %08x\n", error->pipe[i].source); + err_printf(m, " STAT: %08x\n", error->pipe[i].stat); err_printf(m, "Plane [%d]:\n", i); err_printf(m, " CNTR: %08x\n", error->plane[i].control); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 2a00cb828d20..52fda950fd2a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -64,6 +64,24 @@ static const struct dp_link_dpll vlv_dpll[] = { { .p1 = 2, .p2 = 2, .n = 1, .m1 = 2, .m2 = 27 } } }; +/* + * CHV supports eDP 1.4 that have more link rates. + * Below only provides the fixed rate but exclude variable rate. + */ +static const struct dp_link_dpll chv_dpll[] = { + /* + * CHV requires to program fractional division for m2. + * m2 is stored in fixed point format using formula below + * (m2_int << 22) | m2_fraction + */ + { DP_LINK_BW_1_62, /* m2_int = 32, m2_fraction = 1677722 */ + { .p1 = 4, .p2 = 2, .n = 1, .m1 = 2, .m2 = 0x819999a } }, + { DP_LINK_BW_2_7, /* m2_int = 27, m2_fraction = 0 */ + { .p1 = 4, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } }, + { DP_LINK_BW_5_4, /* m2_int = 27, m2_fraction = 0 */ + { .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } } +}; + /** * is_edp - is the given port attached to an eDP panel (either CPU or PCH) * @intel_dp: DP struct @@ -330,8 +348,12 @@ static bool edp_have_panel_vdd(struct intel_dp *intel_dp) { struct drm_device *dev = intel_dp_to_dev(intel_dp); struct drm_i915_private *dev_priv = dev->dev_private; + 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; - return !dev_priv->pm.suspended && + power_domain = intel_display_port_power_domain(intel_encoder); + return intel_display_power_enabled(dev_priv, power_domain) && (I915_READ(_pp_ctrl_reg(intel_dp)) & EDP_FORCE_VDD) != 0; } @@ -697,9 +719,9 @@ intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector) DRM_DEBUG_KMS("registering %s bus for %s\n", name, connector->base.kdev->kobj.name); - ret = drm_dp_aux_register_i2c_bus(&intel_dp->aux); + ret = drm_dp_aux_register(&intel_dp->aux); if (ret < 0) { - DRM_ERROR("drm_dp_aux_register_i2c_bus() for %s failed (%d)\n", + DRM_ERROR("drm_dp_aux_register() for %s failed (%d)\n", name, ret); return; } @@ -709,7 +731,7 @@ intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector) intel_dp->aux.ddc.dev.kobj.name); if (ret < 0) { DRM_ERROR("sysfs_create_link() for %s failed (%d)\n", name, ret); - drm_dp_aux_unregister_i2c_bus(&intel_dp->aux); + drm_dp_aux_unregister(&intel_dp->aux); } } @@ -739,6 +761,9 @@ intel_dp_set_clock(struct intel_encoder *encoder, } else if (HAS_PCH_SPLIT(dev)) { divisor = pch_dpll; count = ARRAY_SIZE(pch_dpll); + } else if (IS_CHERRYVIEW(dev)) { + divisor = chv_dpll; + count = ARRAY_SIZE(chv_dpll); } else if (IS_VALLEYVIEW(dev)) { divisor = vlv_dpll; count = ARRAY_SIZE(vlv_dpll); @@ -755,6 +780,20 @@ intel_dp_set_clock(struct intel_encoder *encoder, } } +static void +intel_dp_set_m2_n2(struct intel_crtc *crtc, struct intel_link_m_n *m_n) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + enum transcoder transcoder = crtc->config.cpu_transcoder; + + I915_WRITE(PIPE_DATA_M2(transcoder), + TU_SIZE(m_n->tu) | m_n->gmch_m); + I915_WRITE(PIPE_DATA_N2(transcoder), m_n->gmch_n); + I915_WRITE(PIPE_LINK_M2(transcoder), m_n->link_m); + I915_WRITE(PIPE_LINK_N2(transcoder), m_n->link_n); +} + bool intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_config *pipe_config) @@ -780,6 +819,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, pipe_config->has_pch_encoder = true; pipe_config->has_dp_encoder = true; + pipe_config->has_audio = intel_dp->has_audio; if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) { intel_fixed_panel_mode(intel_connector->panel.fixed_mode, @@ -880,6 +920,14 @@ found: pipe_config->port_clock, &pipe_config->dp_m_n); + if (intel_connector->panel.downclock_mode != NULL && + intel_dp->drrs_state.type == SEAMLESS_DRRS_SUPPORT) { + intel_link_compute_m_n(bpp, lane_count, + intel_connector->panel.downclock_mode->clock, + pipe_config->port_clock, + &pipe_config->dp_m2_n2); + } + intel_dp_set_clock(encoder, pipe_config, intel_dp->link_bw); return true; @@ -915,7 +963,7 @@ static void ironlake_set_pll_cpu_edp(struct intel_dp *intel_dp) udelay(500); } -static void intel_dp_mode_set(struct intel_encoder *encoder) +static void intel_dp_prepare(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -950,7 +998,7 @@ static void intel_dp_mode_set(struct intel_encoder *encoder) intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0; intel_dp->DP |= DP_PORT_WIDTH(intel_dp->lane_count); - if (intel_dp->has_audio) { + if (crtc->config.has_audio) { DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n", pipe_name(crtc->pipe)); intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE; @@ -983,14 +1031,15 @@ static void intel_dp_mode_set(struct intel_encoder *encoder) if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) intel_dp->DP |= DP_ENHANCED_FRAMING; - if (crtc->pipe == 1) - intel_dp->DP |= DP_PIPEB_SELECT; + if (!IS_CHERRYVIEW(dev)) { + if (crtc->pipe == 1) + intel_dp->DP |= DP_PIPEB_SELECT; + } else { + intel_dp->DP |= DP_PIPE_SELECT_CHV(crtc->pipe); + } } else { intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT; } - - if (port == PORT_A && !IS_VALLEYVIEW(dev)) - ironlake_set_pll_cpu_edp(intel_dp); } #define IDLE_ON_MASK (PP_ON | PP_SEQUENCE_MASK | 0 | PP_SEQUENCE_STATE_MASK) @@ -1082,7 +1131,10 @@ 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; @@ -1095,7 +1147,8 @@ 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"); @@ -1139,9 +1192,14 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp) u32 pp; u32 pp_stat_reg, pp_ctrl_reg; - WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_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); @@ -1160,7 +1218,8 @@ 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); } } @@ -1170,9 +1229,9 @@ static void edp_panel_vdd_work(struct work_struct *__work) struct intel_dp, panel_vdd_work); struct drm_device *dev = intel_dp_to_dev(intel_dp); - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); edp_panel_vdd_off_sync(intel_dp); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock(&dev->mode_config.connection_mutex); } static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync) @@ -1244,8 +1303,11 @@ 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; @@ -1275,7 +1337,8 @@ 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) @@ -1432,6 +1495,8 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, if (port == PORT_A && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) { *pipe = PORT_TO_PIPE_CPT(tmp); + } else if (IS_CHERRYVIEW(dev)) { + *pipe = DP_PORT_TO_PIPE_CHV(tmp); } else if (!HAS_PCH_CPT(dev) || port == PORT_A) { *pipe = PORT_TO_PIPE(tmp); } else { @@ -1479,8 +1544,11 @@ static void intel_dp_get_config(struct intel_encoder *encoder, struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); int dotclock; + tmp = I915_READ(intel_dp->output_reg); + if (tmp & DP_AUDIO_OUTPUT_ENABLE) + pipe_config->has_audio = true; + if ((port == PORT_A) || !HAS_PCH_CPT(dev)) { - tmp = I915_READ(intel_dp->output_reg); if (tmp & DP_SYNC_HS_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else @@ -1816,17 +1884,59 @@ 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; + + 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 chv_post_disable_dp(struct intel_encoder *encoder) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct intel_digital_port *dport = dp_to_dig_port(intel_dp); struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + enum pipe pipe = intel_crtc->pipe; + u32 val; - if (port == PORT_A || IS_VALLEYVIEW(dev)) { - intel_dp_link_down(intel_dp); - if (!IS_VALLEYVIEW(dev)) - ironlake_edp_pll_off(intel_dp); - } + intel_dp_link_down(intel_dp); + + mutex_lock(&dev_priv->dpio_lock); + + /* Propagate soft reset to data lane reset */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + mutex_unlock(&dev_priv->dpio_lock); } static void intel_enable_dp(struct intel_encoder *encoder) @@ -1868,8 +1978,13 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder) struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); struct intel_digital_port *dport = dp_to_dig_port(intel_dp); - if (dport->port == PORT_A) + intel_dp_prepare(encoder); + + /* Only ilk+ has port A */ + if (dport->port == PORT_A) { + ironlake_set_pll_cpu_edp(intel_dp); ironlake_edp_pll_on(intel_dp); + } } static void vlv_pre_enable_dp(struct intel_encoder *encoder) @@ -1921,6 +2036,8 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder) enum dpio_channel port = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; + intel_dp_prepare(encoder); + /* Program Tx lane resets to default */ mutex_lock(&dev_priv->dpio_lock); vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port), @@ -1939,6 +2056,69 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->dpio_lock); } +static void chv_pre_enable_dp(struct intel_encoder *encoder) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct intel_digital_port *dport = dp_to_dig_port(intel_dp); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct edp_power_seq power_seq; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + int pipe = intel_crtc->pipe; + int data, i; + u32 val; + + mutex_lock(&dev_priv->dpio_lock); + + /* Deassert soft data lane reset*/ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + /* Program Tx lane latency optimal setting*/ + for (i = 0; i < 4; i++) { + /* Set the latency optimal bit */ + data = (i == 1) ? 0x0 : 0x6; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW11(ch, i), + data << DPIO_FRC_LATENCY_SHFIT); + + /* Set the upar bit */ + data = (i == 1) ? 0x0 : 0x1; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i), + data << DPIO_UPAR_SHIFT); + } + + /* Data lane stagger programming */ + /* FIXME: Fix up value only after power analysis */ + + mutex_unlock(&dev_priv->dpio_lock); + + if (is_edp(intel_dp)) { + /* init power sequencer on this pipe and port */ + intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq); + intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, + &power_seq); + } + + intel_enable_dp(encoder); + + vlv_wait_port_ready(dev_priv, dport); +} + /* * Native read with retry for link status and receiver capability reads for * cases where the sink may still be asleep. @@ -2163,6 +2343,166 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp) return 0; } +static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_digital_port *dport = dp_to_dig_port(intel_dp); + struct intel_crtc *intel_crtc = to_intel_crtc(dport->base.base.crtc); + u32 deemph_reg_value, margin_reg_value, val; + uint8_t train_set = intel_dp->train_set[0]; + enum dpio_channel ch = vlv_dport_to_channel(dport); + enum pipe pipe = intel_crtc->pipe; + int i; + + switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) { + case DP_TRAIN_PRE_EMPHASIS_0: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 128; + margin_reg_value = 52; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + deemph_reg_value = 128; + margin_reg_value = 77; + break; + case DP_TRAIN_VOLTAGE_SWING_800: + deemph_reg_value = 128; + margin_reg_value = 102; + break; + case DP_TRAIN_VOLTAGE_SWING_1200: + deemph_reg_value = 128; + margin_reg_value = 154; + /* FIXME extra to set for 1200 */ + break; + default: + return 0; + } + break; + case DP_TRAIN_PRE_EMPHASIS_3_5: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 85; + margin_reg_value = 78; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + deemph_reg_value = 85; + margin_reg_value = 116; + break; + case DP_TRAIN_VOLTAGE_SWING_800: + deemph_reg_value = 85; + margin_reg_value = 154; + break; + default: + return 0; + } + break; + case DP_TRAIN_PRE_EMPHASIS_6: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 64; + margin_reg_value = 104; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + deemph_reg_value = 64; + margin_reg_value = 154; + break; + default: + return 0; + } + break; + case DP_TRAIN_PRE_EMPHASIS_9_5: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 43; + margin_reg_value = 154; + break; + default: + return 0; + } + break; + default: + return 0; + } + + mutex_lock(&dev_priv->dpio_lock); + + /* Clear calc init */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* Program swing deemph */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i)); + val &= ~DPIO_SWING_DEEMPH9P5_MASK; + val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val); + } + + /* Program swing margin */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~DPIO_SWING_MARGIN_MASK; + val |= margin_reg_value << DPIO_SWING_MARGIN_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); + } + + /* Disable unique transition scale */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); + } + + if (((train_set & DP_TRAIN_PRE_EMPHASIS_MASK) + == DP_TRAIN_PRE_EMPHASIS_0) && + ((train_set & DP_TRAIN_VOLTAGE_SWING_MASK) + == DP_TRAIN_VOLTAGE_SWING_1200)) { + + /* + * The document said it needs to set bit 27 for ch0 and bit 26 + * for ch1. Might be a typo in the doc. + * For now, for this unique transition scale selection, set bit + * 27 for ch0 and ch1. + */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + val |= DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); + } + + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT); + val |= (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT); + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); + } + } + + /* Start swing calculation */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* LRC Bypass */ + val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); + val |= DPIO_LRC_BYPASS; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val); + + mutex_unlock(&dev_priv->dpio_lock); + + return 0; +} + static void intel_get_adjust_train(struct intel_dp *intel_dp, const uint8_t link_status[DP_LINK_STATUS_SIZE]) @@ -2377,6 +2717,9 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP) } else if (IS_HASWELL(dev)) { signal_levels = intel_hsw_signal_levels(train_set); mask = DDI_BUF_EMP_MASK; + } else if (IS_CHERRYVIEW(dev)) { + signal_levels = intel_chv_signal_levels(intel_dp); + mask = 0; } else if (IS_VALLEYVIEW(dev)) { signal_levels = intel_vlv_signal_levels(intel_dp); mask = 0; @@ -2743,22 +3086,7 @@ intel_dp_link_down(struct intel_dp *intel_dp) to_intel_crtc(intel_dig_port->base.base.crtc); uint32_t DP = intel_dp->DP; - /* - * DDI code has a strict mode set sequence and we should try to respect - * it, otherwise we might hang the machine in many different ways. So we - * really should be disabling the port only on a complete crtc_disable - * sequence. This function is just called under two conditions on DDI - * code: - * - Link train failed while doing crtc_enable, and on this case we - * really should respect the mode set sequence and wait for a - * crtc_disable. - * - Someone turned the monitor off and intel_dp_check_link_status - * called us. We don't need to disable the whole port on this case, so - * when someone turns the monitor on again, - * intel_ddi_prepare_link_retrain will take care of redoing the link - * train. - */ - if (HAS_DDI(dev)) + if (WARN_ON(HAS_DDI(dev))) return; if (WARN_ON((I915_READ(intel_dp->output_reg) & DP_PORT_EN) == 0)) @@ -2775,9 +3103,6 @@ intel_dp_link_down(struct intel_dp *intel_dp) } POSTING_READ(intel_dp->output_reg); - /* We don't really know why we're doing this */ - intel_wait_for_vblank(dev, intel_crtc->pipe); - if (HAS_PCH_IBX(dev) && I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) { struct drm_crtc *crtc = intel_dig_port->base.base.crtc; @@ -2948,6 +3273,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp) u8 sink_irq_vector; u8 link_status[DP_LINK_STATUS_SIZE]; + /* FIXME: This access isn't protected by any locks. */ if (!intel_encoder->connectors_active) return; @@ -2980,7 +3306,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp) if (!drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) { DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n", - drm_get_encoder_name(&intel_encoder->base)); + intel_encoder->base.name); intel_dp_start_link_train(intel_dp); intel_dp_complete_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); @@ -3166,7 +3492,7 @@ intel_dp_detect(struct drm_connector *connector, bool force) intel_display_power_get(dev_priv, power_domain); DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); intel_dp->has_audio = false; @@ -3374,13 +3700,13 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) struct intel_dp *intel_dp = &intel_dig_port->dp; struct drm_device *dev = intel_dp_to_dev(intel_dp); - drm_dp_aux_unregister_i2c_bus(&intel_dp->aux); + drm_dp_aux_unregister(&intel_dp->aux); drm_encoder_cleanup(encoder); if (is_edp(intel_dp)) { cancel_delayed_work_sync(&intel_dp->panel_vdd_work); - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); edp_panel_vdd_off_sync(intel_dp); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock(&dev->mode_config.connection_mutex); } kfree(intel_dig_port); } @@ -3651,6 +3977,130 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev, I915_READ(pp_div_reg)); } +void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_encoder *encoder; + struct intel_dp *intel_dp = NULL; + struct intel_crtc_config *config = NULL; + struct intel_crtc *intel_crtc = NULL; + struct intel_connector *intel_connector = dev_priv->drrs.connector; + u32 reg, val; + enum edp_drrs_refresh_rate_type index = DRRS_HIGH_RR; + + if (refresh_rate <= 0) { + DRM_DEBUG_KMS("Refresh rate should be positive non-zero.\n"); + return; + } + + if (intel_connector == NULL) { + DRM_DEBUG_KMS("DRRS supported for eDP only.\n"); + return; + } + + if (INTEL_INFO(dev)->gen < 8 && intel_edp_is_psr_enabled(dev)) { + DRM_DEBUG_KMS("DRRS is disabled as PSR is enabled\n"); + return; + } + + encoder = intel_attached_encoder(&intel_connector->base); + intel_dp = enc_to_intel_dp(&encoder->base); + intel_crtc = encoder->new_crtc; + + if (!intel_crtc) { + DRM_DEBUG_KMS("DRRS: intel_crtc not initialized\n"); + return; + } + + config = &intel_crtc->config; + + if (intel_dp->drrs_state.type < SEAMLESS_DRRS_SUPPORT) { + DRM_DEBUG_KMS("Only Seamless DRRS supported.\n"); + return; + } + + if (intel_connector->panel.downclock_mode->vrefresh == refresh_rate) + index = DRRS_LOW_RR; + + if (index == intel_dp->drrs_state.refresh_rate_type) { + DRM_DEBUG_KMS( + "DRRS requested for previously set RR...ignoring\n"); + return; + } + + if (!intel_crtc->active) { + DRM_DEBUG_KMS("eDP encoder disabled. CRTC not Active\n"); + return; + } + + if (INTEL_INFO(dev)->gen > 6 && INTEL_INFO(dev)->gen < 8) { + reg = PIPECONF(intel_crtc->config.cpu_transcoder); + val = I915_READ(reg); + if (index > DRRS_HIGH_RR) { + val |= PIPECONF_EDP_RR_MODE_SWITCH; + intel_dp_set_m2_n2(intel_crtc, &config->dp_m2_n2); + } else { + val &= ~PIPECONF_EDP_RR_MODE_SWITCH; + } + I915_WRITE(reg, val); + } + + /* + * mutex taken to ensure that there is no race between differnt + * drrs calls trying to update refresh rate. This scenario may occur + * in future when idleness detection based DRRS in kernel and + * possible calls from user space to set differnt RR are made. + */ + + mutex_lock(&intel_dp->drrs_state.mutex); + + intel_dp->drrs_state.refresh_rate_type = index; + + mutex_unlock(&intel_dp->drrs_state.mutex); + + DRM_DEBUG_KMS("eDP Refresh Rate set to : %dHz\n", refresh_rate); +} + +static struct drm_display_mode * +intel_dp_drrs_init(struct intel_digital_port *intel_dig_port, + struct intel_connector *intel_connector, + struct drm_display_mode *fixed_mode) +{ + struct drm_connector *connector = &intel_connector->base; + struct intel_dp *intel_dp = &intel_dig_port->dp; + struct drm_device *dev = intel_dig_port->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_display_mode *downclock_mode = NULL; + + if (INTEL_INFO(dev)->gen <= 6) { + DRM_DEBUG_KMS("DRRS supported for Gen7 and above\n"); + return NULL; + } + + if (dev_priv->vbt.drrs_type != SEAMLESS_DRRS_SUPPORT) { + DRM_INFO("VBT doesn't support DRRS\n"); + return NULL; + } + + downclock_mode = intel_find_panel_downclock + (dev, fixed_mode, connector); + + if (!downclock_mode) { + DRM_INFO("DRRS not supported\n"); + return NULL; + } + + dev_priv->drrs.connector = intel_connector; + + mutex_init(&intel_dp->drrs_state.mutex); + + intel_dp->drrs_state.type = dev_priv->vbt.drrs_type; + + intel_dp->drrs_state.refresh_rate_type = DRRS_HIGH_RR; + DRM_INFO("seamless DRRS supported for eDP panel.\n"); + return downclock_mode; +} + static bool intel_edp_init_connector(struct intel_dp *intel_dp, struct intel_connector *intel_connector, struct edp_power_seq *power_seq) @@ -3661,10 +4111,13 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_display_mode *fixed_mode = NULL; + struct drm_display_mode *downclock_mode = NULL; bool has_dpcd; struct drm_display_mode *scan; struct edid *edid; + intel_dp->drrs_state.type = DRRS_NOT_SUPPORTED; + if (!is_edp(intel_dp)) return true; @@ -3715,6 +4168,9 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, list_for_each_entry(scan, &connector->probed_modes, head) { if ((scan->type & DRM_MODE_TYPE_PREFERRED)) { fixed_mode = drm_mode_duplicate(dev, scan); + downclock_mode = intel_dp_drrs_init( + intel_dig_port, + intel_connector, fixed_mode); break; } } @@ -3728,7 +4184,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, } mutex_unlock(&dev->mode_config.mutex); - intel_panel_init(&intel_connector->panel, fixed_mode, NULL); + intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode); intel_panel_setup_backlight(connector); return true; @@ -3826,12 +4282,12 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, intel_dp->psr_setup_done = false; if (!intel_edp_init_connector(intel_dp, intel_connector, &power_seq)) { - drm_dp_aux_unregister_i2c_bus(&intel_dp->aux); + drm_dp_aux_unregister(&intel_dp->aux); if (is_edp(intel_dp)) { cancel_delayed_work_sync(&intel_dp->panel_vdd_work); - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); edp_panel_vdd_off_sync(intel_dp); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock(&dev->mode_config.connection_mutex); } drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); @@ -3877,25 +4333,36 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) DRM_MODE_ENCODER_TMDS); 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)) { + if (IS_CHERRYVIEW(dev)) { + intel_encoder->pre_enable = chv_pre_enable_dp; + intel_encoder->enable = vlv_enable_dp; + intel_encoder->post_disable = chv_post_disable_dp; + } else 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; intel_dig_port->dp.output_reg = output_reg; intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; - intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + if (IS_CHERRYVIEW(dev)) { + if (port == PORT_D) + intel_encoder->crtc_mask = 1 << 2; + else + intel_encoder->crtc_mask = (1 << 0) | (1 << 1); + } else { + intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + } intel_encoder->cloneable = 0; intel_encoder->hot_plug = intel_dp_hot_plug; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 328b1a70264b..bda0ae3d80cc 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 @@ -106,8 +106,8 @@ #define INTEL_DVO_CHIP_TMDS 2 #define INTEL_DVO_CHIP_TVOUT 4 -#define INTEL_DSI_COMMAND_MODE 0 -#define INTEL_DSI_VIDEO_MODE 1 +#define INTEL_DSI_VIDEO_MODE 0 +#define INTEL_DSI_COMMAND_MODE 1 struct intel_framebuffer { struct drm_framebuffer base; @@ -273,6 +273,13 @@ struct intel_crtc_config { * accordingly. */ bool has_dp_encoder; + /* Whether we should send NULL infoframes. Required for audio. */ + bool has_hdmi_sink; + + /* Audio enabled on this pipe. Only valid if either has_hdmi_sink or + * has_dp_encoder is set. */ + bool has_audio; + /* * Enable dithering, used when the selected pipe bpp doesn't match the * plane bpp. @@ -306,6 +313,9 @@ struct intel_crtc_config { int pipe_bpp; struct intel_link_m_n dp_m_n; + /* m2_n2 for eDP downclock */ + struct intel_link_m_n dp_m2_n2; + /* * Frequence the dpll for the port should run at. Differs from the * adjusted dotclock e.g. for DP or 12bpc hdmi mode. This is also @@ -343,6 +353,9 @@ struct intel_pipe_wm { struct intel_wm_level wm[5]; uint32_t linetime; bool fbc_wm_enabled; + bool pipe_enabled; + bool sprites_enabled; + bool sprites_scaled; }; struct intel_crtc { @@ -357,7 +370,6 @@ struct intel_crtc { */ bool active; unsigned long enabled_power_domains; - bool eld_vld; bool primary_enabled; /* is the primary plane (partially) visible? */ bool lowfreq_avail; struct intel_overlay *overlay; @@ -374,8 +386,8 @@ 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; + uint32_t cursor_cntl; + uint32_t cursor_base; struct intel_plane_config plane_config; struct intel_crtc_config config; @@ -396,6 +408,10 @@ struct intel_crtc { /* watermarks currently being used */ struct intel_pipe_wm active; } wm; + + wait_queue_head_t vbl_wait; + + int scanline_offset; }; struct intel_plane_wm_parameters { @@ -479,11 +495,23 @@ struct intel_hdmi { enum hdmi_infoframe_type type, const void *frame, ssize_t len); void (*set_infoframes)(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode); }; #define DP_MAX_DOWNSTREAM_PORTS 0x10 +/** + * HIGH_RR is the highest eDP panel refresh rate read from EDID + * LOW_RR is the lowest eDP panel refresh rate found from EDID + * parsing for same resolution. + */ +enum edp_drrs_refresh_rate_type { + DRRS_HIGH_RR, + DRRS_LOW_RR, + DRRS_MAX_RR, /* RR count */ +}; + struct intel_dp { uint32_t output_reg; uint32_t aux_ch_ctl_reg; @@ -522,6 +550,12 @@ struct intel_dp { bool has_aux_irq, int send_bytes, uint32_t aux_clock_divider); + struct { + enum drrs_support_type type; + enum edp_drrs_refresh_rate_type refresh_rate_type; + struct mutex mutex; + } drrs_state; + }; struct intel_digital_port { @@ -537,6 +571,7 @@ vlv_dport_to_channel(struct intel_digital_port *dport) { switch (dport->port) { case PORT_B: + case PORT_D: return DPIO_CH0; case PORT_C: return DPIO_CH1; @@ -545,6 +580,20 @@ vlv_dport_to_channel(struct intel_digital_port *dport) } } +static inline int +vlv_pipe_to_channel(enum pipe pipe) +{ + switch (pipe) { + case PIPE_A: + case PIPE_C: + return DPIO_CH0; + case PIPE_B: + return DPIO_CH1; + default: + BUG(); + } +} + static inline struct drm_crtc * intel_get_crtc_for_pipe(struct drm_device *dev, int pipe) { @@ -569,6 +618,8 @@ struct intel_unpin_work { #define INTEL_FLIP_INACTIVE 0 #define INTEL_FLIP_PENDING 1 #define INTEL_FLIP_COMPLETE 2 + u32 flip_count; + u32 gtt_offset; bool enable_stall_check; }; @@ -620,8 +671,6 @@ hdmi_to_dig_port(struct intel_hdmi *intel_hdmi) /* i915_irq.c */ bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, enum pipe pipe, bool enable); -bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, - enum pipe pipe, bool enable); bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, enum transcoder pch_transcoder, bool enable); @@ -629,8 +678,12 @@ 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 bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); +void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); +void intel_runtime_pm_disable_interrupts(struct drm_device *dev); +void intel_runtime_pm_restore_interrupts(struct drm_device *dev); +int intel_get_crtc_scanline(struct intel_crtc *crtc); +void i9xx_check_fifo_underruns(struct drm_device *dev); /* intel_crt.c */ @@ -666,9 +719,10 @@ 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); + struct intel_engine_cs *ring); void intel_mark_idle(struct drm_device *dev); void intel_crtc_restore_mode(struct drm_crtc *crtc); void intel_crtc_update_dpms(struct drm_crtc *crtc); @@ -695,12 +749,14 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv, struct intel_digital_port *dport); bool intel_get_load_detect_pipe(struct drm_connector *connector, struct drm_display_mode *mode, - struct intel_load_detect_pipe *old); + struct intel_load_detect_pipe *old, + struct drm_modeset_acquire_ctx *ctx); void intel_release_load_detect_pipe(struct drm_connector *connector, - struct intel_load_detect_pipe *old); + struct intel_load_detect_pipe *old, + struct drm_modeset_acquire_ctx *ctx); int intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_i915_gem_object *obj, - struct intel_ring_buffer *pipelined); + struct intel_engine_cs *pipelined); void intel_unpin_fb_obj(struct drm_i915_gem_object *obj); struct drm_framebuffer * __intel_framebuffer_create(struct drm_device *dev, @@ -751,6 +807,8 @@ int valleyview_get_vco(struct drm_i915_private *dev_priv); void intel_mode_from_pipe_config(struct drm_display_mode *mode, struct intel_crtc_config *pipe_config); int intel_format_to_fourcc(int format); +void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc); + /* intel_dp.c */ void intel_dp_init(struct drm_device *dev, int output_reg, enum port port); @@ -774,7 +832,7 @@ void intel_edp_panel_off(struct intel_dp *intel_dp); void intel_edp_psr_enable(struct intel_dp *intel_dp); void intel_edp_psr_disable(struct intel_dp *intel_dp); void intel_edp_psr_update(struct drm_device *dev); - +void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate); /* intel_dsi.c */ bool intel_dsi_init(struct drm_device *dev); @@ -876,6 +934,7 @@ extern struct drm_display_mode *intel_find_panel_downclock( /* intel_pm.c */ void intel_init_clock_gating(struct drm_device *dev); void intel_suspend_hw(struct drm_device *dev); +int ilk_wm_max_level(const struct drm_device *dev); void intel_update_watermarks(struct drm_crtc *crtc); void intel_update_sprite_watermarks(struct drm_plane *plane, struct drm_crtc *crtc, @@ -902,6 +961,7 @@ void intel_init_gt_powersave(struct drm_device *dev); void intel_cleanup_gt_powersave(struct drm_device *dev); void intel_enable_gt_powersave(struct drm_device *dev); void intel_disable_gt_powersave(struct drm_device *dev); +void intel_reset_gt_powersave(struct drm_device *dev); void ironlake_teardown_rc6(struct drm_device *dev); void gen6_update_ring_freq(struct drm_device *dev); void gen6_rps_idle(struct drm_i915_private *dev_priv); @@ -909,11 +969,13 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv); void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv); void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv); void intel_runtime_pm_get(struct drm_i915_private *dev_priv); +void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv); void intel_runtime_pm_put(struct drm_i915_private *dev_priv); void intel_init_runtime_pm(struct drm_i915_private *dev_priv); void intel_fini_runtime_pm(struct drm_i915_private *dev_priv); void ilk_wm_get_hw_state(struct drm_device *dev); - +void __vlv_set_power_well(struct drm_i915_private *dev_priv, + enum punit_power_well power_well_id, bool enable); /* intel_sdvo.c */ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 33656647f8bc..02f99d768d49 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -35,6 +35,11 @@ /* the sub-encoders aka panel drivers */ static const struct intel_dsi_device intel_dsi_devices[] = { + { + .panel_id = MIPI_DSI_GENERIC_PANEL_ID, + .name = "vbt-generic-dsi-vid-mode-display", + .dev_ops = &vbt_generic_dsi_display_ops, + }, }; static void band_gap_reset(struct drm_i915_private *dev_priv) @@ -59,12 +64,12 @@ static struct intel_dsi *intel_attached_dsi(struct drm_connector *connector) static inline bool is_vid_mode(struct intel_dsi *intel_dsi) { - return intel_dsi->dev.type == INTEL_DSI_VIDEO_MODE; + return intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE; } static inline bool is_cmd_mode(struct intel_dsi *intel_dsi) { - return intel_dsi->dev.type == INTEL_DSI_COMMAND_MODE; + return intel_dsi->operation_mode == INTEL_DSI_COMMAND_MODE; } static void intel_dsi_hot_plug(struct intel_encoder *encoder) @@ -94,13 +99,6 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder, return true; } -static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder) -{ - DRM_DEBUG_KMS("\n"); - - vlv_enable_dsi_pll(encoder); -} - static void intel_dsi_device_ready(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; @@ -110,6 +108,15 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder) DRM_DEBUG_KMS("\n"); + mutex_lock(&dev_priv->dpio_lock); + /* program rcomp for compliance, reduce from 50 ohms to 45 ohms + * needed everytime after power gate */ + vlv_flisdsi_write(dev_priv, 0x04, 0x0004); + mutex_unlock(&dev_priv->dpio_lock); + + /* bandgap reset is needed after everytime we do power gate */ + band_gap_reset(dev_priv); + val = I915_READ(MIPI_PORT_CTRL(pipe)); I915_WRITE(MIPI_PORT_CTRL(pipe), val | LP_OUTPUT_HOLD); usleep_range(1000, 1500); @@ -122,21 +129,6 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder) I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY); usleep_range(2000, 2500); } -static void intel_dsi_pre_enable(struct intel_encoder *encoder) -{ - struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); - - DRM_DEBUG_KMS("\n"); - - if (intel_dsi->dev.dev_ops->panel_reset) - intel_dsi->dev.dev_ops->panel_reset(&intel_dsi->dev); - - /* put device in ready state */ - intel_dsi_device_ready(encoder); - - if (intel_dsi->dev.dev_ops->send_otp_cmds) - intel_dsi->dev.dev_ops->send_otp_cmds(&intel_dsi->dev); -} static void intel_dsi_enable(struct intel_encoder *encoder) { @@ -153,18 +145,78 @@ static void intel_dsi_enable(struct intel_encoder *encoder) I915_WRITE(MIPI_MAX_RETURN_PKT_SIZE(pipe), 8 * 4); else { msleep(20); /* XXX */ - dpi_send_cmd(intel_dsi, TURN_ON); + dpi_send_cmd(intel_dsi, TURN_ON, DPI_LP_MODE_EN); msleep(100); + if (intel_dsi->dev.dev_ops->enable) + intel_dsi->dev.dev_ops->enable(&intel_dsi->dev); + /* assert ip_tg_enable signal */ temp = I915_READ(MIPI_PORT_CTRL(pipe)) & ~LANE_CONFIGURATION_MASK; temp = temp | intel_dsi->port_bits; I915_WRITE(MIPI_PORT_CTRL(pipe), temp | DPI_ENABLE); POSTING_READ(MIPI_PORT_CTRL(pipe)); } +} + +static void intel_dsi_pre_enable(struct intel_encoder *encoder) +{ + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + enum pipe pipe = intel_crtc->pipe; + u32 tmp; + + DRM_DEBUG_KMS("\n"); + + /* Disable DPOunit clock gating, can stall pipe + * and we need DPLL REFA always enabled */ + tmp = I915_READ(DPLL(pipe)); + tmp |= DPLL_REFA_CLK_ENABLE_VLV; + I915_WRITE(DPLL(pipe), tmp); + + tmp = I915_READ(DSPCLK_GATE_D); + tmp |= DPOUNIT_CLOCK_GATE_DISABLE; + I915_WRITE(DSPCLK_GATE_D, tmp); + + /* put device in ready state */ + intel_dsi_device_ready(encoder); + + msleep(intel_dsi->panel_on_delay); + + if (intel_dsi->dev.dev_ops->panel_reset) + intel_dsi->dev.dev_ops->panel_reset(&intel_dsi->dev); + + if (intel_dsi->dev.dev_ops->send_otp_cmds) + intel_dsi->dev.dev_ops->send_otp_cmds(&intel_dsi->dev); - if (intel_dsi->dev.dev_ops->enable) - intel_dsi->dev.dev_ops->enable(&intel_dsi->dev); + /* Enable port in pre-enable phase itself because as per hw team + * recommendation, port should be enabled befor plane & pipe */ + intel_dsi_enable(encoder); +} + +static void intel_dsi_enable_nop(struct intel_encoder *encoder) +{ + DRM_DEBUG_KMS("\n"); + + /* for DSI port enable has to be done before pipe + * and plane enable, so port enable is done in + * pre_enable phase itself unlike other encoders + */ +} + +static void intel_dsi_pre_disable(struct intel_encoder *encoder) +{ + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + + DRM_DEBUG_KMS("\n"); + + if (is_vid_mode(intel_dsi)) { + /* Send Shutdown command to the panel in LP mode */ + dpi_send_cmd(intel_dsi, SHUTDOWN, DPI_LP_MODE_EN); + msleep(10); + } } static void intel_dsi_disable(struct intel_encoder *encoder) @@ -179,9 +231,6 @@ static void intel_dsi_disable(struct intel_encoder *encoder) DRM_DEBUG_KMS("\n"); if (is_vid_mode(intel_dsi)) { - dpi_send_cmd(intel_dsi, SHUTDOWN); - msleep(10); - /* de-assert ip_tg_enable signal */ temp = I915_READ(MIPI_PORT_CTRL(pipe)); I915_WRITE(MIPI_PORT_CTRL(pipe), temp & ~DPI_ENABLE); @@ -190,6 +239,23 @@ static void intel_dsi_disable(struct intel_encoder *encoder) msleep(2); } + /* Panel commands can be sent when clock is in LP11 */ + I915_WRITE(MIPI_DEVICE_READY(pipe), 0x0); + + temp = I915_READ(MIPI_CTRL(pipe)); + temp &= ~ESCAPE_CLOCK_DIVIDER_MASK; + I915_WRITE(MIPI_CTRL(pipe), temp | + intel_dsi->escape_clk_div << + ESCAPE_CLOCK_DIVIDER_SHIFT); + + I915_WRITE(MIPI_EOT_DISABLE(pipe), CLOCKSTOP); + + temp = I915_READ(MIPI_DSI_FUNC_PRG(pipe)); + temp &= ~VID_MODE_FORMAT_MASK; + I915_WRITE(MIPI_DSI_FUNC_PRG(pipe), temp); + + I915_WRITE(MIPI_DEVICE_READY(pipe), 0x1); + /* if disable packets are sent before sending shutdown packet then in * some next enable sequence send turn on packet error is observed */ if (intel_dsi->dev.dev_ops->disable) @@ -227,16 +293,28 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder) vlv_disable_dsi_pll(encoder); } + static void intel_dsi_post_disable(struct intel_encoder *encoder) { + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u32 val; DRM_DEBUG_KMS("\n"); + intel_dsi_disable(encoder); + intel_dsi_clear_device_ready(encoder); + val = I915_READ(DSPCLK_GATE_D); + val &= ~DPOUNIT_CLOCK_GATE_DISABLE; + I915_WRITE(DSPCLK_GATE_D, val); + if (intel_dsi->dev.dev_ops->disable_panel_power) intel_dsi->dev.dev_ops->disable_panel_power(&intel_dsi->dev); + + msleep(intel_dsi->panel_off_delay); + msleep(intel_dsi->panel_pwr_cycle_delay); } static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, @@ -364,7 +442,7 @@ static void set_dsi_timings(struct drm_encoder *encoder, I915_WRITE(MIPI_VBP_COUNT(pipe), vbp); } -static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) +static void intel_dsi_prepare(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; struct drm_device *dev = encoder->dev; @@ -379,9 +457,6 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe)); - /* XXX: Location of the call */ - band_gap_reset(dev_priv); - /* escape clock divider, 20MHz, shared for A and C. device ready must be * off when doing this! txclkesc? */ tmp = I915_READ(MIPI_CTRL(0)); @@ -452,10 +527,20 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) /* dphy stuff */ /* in terms of low power clock */ - I915_WRITE(MIPI_INIT_COUNT(pipe), txclkesc(ESCAPE_CLOCK_DIVIDER_1, 100)); + I915_WRITE(MIPI_INIT_COUNT(pipe), txclkesc(intel_dsi->escape_clk_div, 100)); + + val = 0; + if (intel_dsi->eotp_pkt == 0) + val |= EOT_DISABLE; + + if (intel_dsi->clock_stop) + val |= CLOCKSTOP; /* recovery disables */ - I915_WRITE(MIPI_EOT_DISABLE(pipe), intel_dsi->eot_disable); + I915_WRITE(MIPI_EOT_DISABLE(pipe), val); + + /* in terms of low power clock */ + I915_WRITE(MIPI_INIT_COUNT(pipe), intel_dsi->init_count); /* in terms of txbyteclkhs. actual high to low switch + * MIPI_STOP_STATE_STALL * MIPI_LP_BYTECLK. @@ -484,9 +569,23 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) intel_dsi->clk_hs_to_lp_count << HS_LP_PWR_SW_CNT_SHIFT); if (is_vid_mode(intel_dsi)) + /* Some panels might have resolution which is not a multiple of + * 64 like 1366 x 768. Enable RANDOM resolution support for such + * panels by default */ I915_WRITE(MIPI_VIDEO_MODE_FORMAT(pipe), intel_dsi->video_frmt_cfg_bits | - intel_dsi->video_mode_format); + intel_dsi->video_mode_format | + IP_TG_CONFIG | + RANDOM_DPI_DISPLAY_RESOLUTION); +} + +static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder) +{ + DRM_DEBUG_KMS("\n"); + + intel_dsi_prepare(encoder); + + vlv_enable_dsi_pll(encoder); } static enum drm_connector_status @@ -566,11 +665,16 @@ bool intel_dsi_init(struct drm_device *dev) struct intel_connector *intel_connector; struct drm_connector *connector; struct drm_display_mode *fixed_mode = NULL; + struct drm_i915_private *dev_priv = dev->dev_private; const struct intel_dsi_device *dsi; unsigned int i; DRM_DEBUG_KMS("\n"); + /* There is no detection method for MIPI so rely on VBT */ + if (!dev_priv->vbt.has_mipi) + return false; + intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL); if (!intel_dsi) return false; @@ -585,6 +689,13 @@ bool intel_dsi_init(struct drm_device *dev) encoder = &intel_encoder->base; intel_dsi->attached_connector = intel_connector; + if (IS_VALLEYVIEW(dev)) { + dev_priv->mipi_mmio_base = VLV_MIPI_BASE; + } else { + DRM_ERROR("Unsupported Mipi device to reg base"); + return false; + } + connector = &intel_connector->base; drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI); @@ -594,9 +705,8 @@ bool intel_dsi_init(struct drm_device *dev) intel_encoder->compute_config = intel_dsi_compute_config; intel_encoder->pre_pll_enable = intel_dsi_pre_pll_enable; intel_encoder->pre_enable = intel_dsi_pre_enable; - intel_encoder->enable = intel_dsi_enable; - intel_encoder->mode_set = intel_dsi_mode_set; - intel_encoder->disable = intel_dsi_disable; + intel_encoder->enable = intel_dsi_enable_nop; + intel_encoder->disable = intel_dsi_pre_disable; intel_encoder->post_disable = intel_dsi_post_disable; intel_encoder->get_hw_state = intel_dsi_get_hw_state; intel_encoder->get_config = intel_dsi_get_config; diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h index b4a27cec882f..31db33d3e5cc 100644 --- a/drivers/gpu/drm/i915/intel_dsi.h +++ b/drivers/gpu/drm/i915/intel_dsi.h @@ -31,7 +31,6 @@ struct intel_dsi_device { unsigned int panel_id; const char *name; - int type; const struct intel_dsi_dev_ops *dev_ops; void *dev_priv; }; @@ -85,6 +84,9 @@ struct intel_dsi { /* virtual channel */ int channel; + /* Video mode or command mode */ + u16 operation_mode; + /* number of DSI lanes */ unsigned int lane_count; @@ -95,8 +97,10 @@ struct intel_dsi { u32 video_mode_format; /* eot for MIPI_EOT_DISABLE register */ - u32 eot_disable; + u8 eotp_pkt; + u8 clock_stop; + u8 escape_clk_div; u32 port_bits; u32 bw_timer; u32 dphy_reg; @@ -110,6 +114,15 @@ struct intel_dsi { u16 hs_to_lp_count; u16 clk_lp_to_hs_count; u16 clk_hs_to_lp_count; + + u16 init_count; + + /* all delays in ms */ + u16 backlight_off_delay; + u16 backlight_on_delay; + u16 panel_on_delay; + u16 panel_off_delay; + u16 panel_pwr_cycle_delay; }; static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder) @@ -120,4 +133,6 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder) extern void vlv_enable_dsi_pll(struct intel_encoder *encoder); extern void vlv_disable_dsi_pll(struct intel_encoder *encoder); +extern struct intel_dsi_dev_ops vbt_generic_dsi_display_ops; + #endif /* _INTEL_DSI_H */ diff --git a/drivers/gpu/drm/i915/intel_dsi_cmd.c b/drivers/gpu/drm/i915/intel_dsi_cmd.c index 7c40f981d2c7..3eeb21b9fddf 100644 --- a/drivers/gpu/drm/i915/intel_dsi_cmd.c +++ b/drivers/gpu/drm/i915/intel_dsi_cmd.c @@ -389,7 +389,7 @@ int dsi_vc_generic_read(struct intel_dsi *intel_dsi, int channel, * * XXX: commands with data in MIPI_DPI_DATA? */ -int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd) +int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs) { struct drm_encoder *encoder = &intel_dsi->base.base; struct drm_device *dev = encoder->dev; @@ -399,7 +399,7 @@ int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd) u32 mask; /* XXX: pipe, hs */ - if (intel_dsi->hs) + if (hs) cmd &= ~DPI_LP_MODE; else cmd |= DPI_LP_MODE; diff --git a/drivers/gpu/drm/i915/intel_dsi_cmd.h b/drivers/gpu/drm/i915/intel_dsi_cmd.h index 54c8a234a2e0..9a18cbfa5460 100644 --- a/drivers/gpu/drm/i915/intel_dsi_cmd.h +++ b/drivers/gpu/drm/i915/intel_dsi_cmd.h @@ -33,6 +33,9 @@ #include "intel_drv.h" #include "intel_dsi.h" +#define DPI_LP_MODE_EN false +#define DPI_HS_MODE_EN true + void dsi_hs_mode_enable(struct intel_dsi *intel_dsi, bool enable); int dsi_vc_dcs_write(struct intel_dsi *intel_dsi, int channel, @@ -47,7 +50,7 @@ int dsi_vc_dcs_read(struct intel_dsi *intel_dsi, int channel, u8 dcs_cmd, int dsi_vc_generic_read(struct intel_dsi *intel_dsi, int channel, u8 *reqdata, int reqlen, u8 *buf, int buflen); -int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd); +int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs); /* XXX: questionable write helpers */ static inline int dsi_vc_dcs_write_0(struct intel_dsi *intel_dsi, diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c new file mode 100644 index 000000000000..21a0d348cedc --- /dev/null +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -0,0 +1,589 @@ +/* + * 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. + * + * Author: Shobhit Kumar <shobhit.kumar@intel.com> + * + */ + +#include <drm/drmP.h> +#include <drm/drm_crtc.h> +#include <drm/drm_edid.h> +#include <drm/i915_drm.h> +#include <linux/slab.h> +#include <video/mipi_display.h> +#include <asm/intel-mid.h> +#include <video/mipi_display.h> +#include "i915_drv.h" +#include "intel_drv.h" +#include "intel_dsi.h" +#include "intel_dsi_cmd.h" + +#define MIPI_TRANSFER_MODE_SHIFT 0 +#define MIPI_VIRTUAL_CHANNEL_SHIFT 1 +#define MIPI_PORT_SHIFT 3 + +#define PREPARE_CNT_MAX 0x3F +#define EXIT_ZERO_CNT_MAX 0x3F +#define CLK_ZERO_CNT_MAX 0xFF +#define TRAIL_CNT_MAX 0x1F + +#define NS_KHZ_RATIO 1000000 + +#define GPI0_NC_0_HV_DDI0_HPD 0x4130 +#define GPIO_NC_0_HV_DDI0_PAD 0x4138 +#define GPIO_NC_1_HV_DDI0_DDC_SDA 0x4120 +#define GPIO_NC_1_HV_DDI0_DDC_SDA_PAD 0x4128 +#define GPIO_NC_2_HV_DDI0_DDC_SCL 0x4110 +#define GPIO_NC_2_HV_DDI0_DDC_SCL_PAD 0x4118 +#define GPIO_NC_3_PANEL0_VDDEN 0x4140 +#define GPIO_NC_3_PANEL0_VDDEN_PAD 0x4148 +#define GPIO_NC_4_PANEL0_BLKEN 0x4150 +#define GPIO_NC_4_PANEL0_BLKEN_PAD 0x4158 +#define GPIO_NC_5_PANEL0_BLKCTL 0x4160 +#define GPIO_NC_5_PANEL0_BLKCTL_PAD 0x4168 +#define GPIO_NC_6_PCONF0 0x4180 +#define GPIO_NC_6_PAD 0x4188 +#define GPIO_NC_7_PCONF0 0x4190 +#define GPIO_NC_7_PAD 0x4198 +#define GPIO_NC_8_PCONF0 0x4170 +#define GPIO_NC_8_PAD 0x4178 +#define GPIO_NC_9_PCONF0 0x4100 +#define GPIO_NC_9_PAD 0x4108 +#define GPIO_NC_10_PCONF0 0x40E0 +#define GPIO_NC_10_PAD 0x40E8 +#define GPIO_NC_11_PCONF0 0x40F0 +#define GPIO_NC_11_PAD 0x40F8 + +struct gpio_table { + u16 function_reg; + u16 pad_reg; + u8 init; +}; + +static struct gpio_table gtable[] = { + { GPI0_NC_0_HV_DDI0_HPD, GPIO_NC_0_HV_DDI0_PAD, 0 }, + { GPIO_NC_1_HV_DDI0_DDC_SDA, GPIO_NC_1_HV_DDI0_DDC_SDA_PAD, 0 }, + { GPIO_NC_2_HV_DDI0_DDC_SCL, GPIO_NC_2_HV_DDI0_DDC_SCL_PAD, 0 }, + { GPIO_NC_3_PANEL0_VDDEN, GPIO_NC_3_PANEL0_VDDEN_PAD, 0 }, + { GPIO_NC_4_PANEL0_BLKEN, GPIO_NC_4_PANEL0_BLKEN_PAD, 0 }, + { GPIO_NC_5_PANEL0_BLKCTL, GPIO_NC_5_PANEL0_BLKCTL_PAD, 0 }, + { GPIO_NC_6_PCONF0, GPIO_NC_6_PAD, 0 }, + { GPIO_NC_7_PCONF0, GPIO_NC_7_PAD, 0 }, + { GPIO_NC_8_PCONF0, GPIO_NC_8_PAD, 0 }, + { GPIO_NC_9_PCONF0, GPIO_NC_9_PAD, 0 }, + { GPIO_NC_10_PCONF0, GPIO_NC_10_PAD, 0}, + { GPIO_NC_11_PCONF0, GPIO_NC_11_PAD, 0} +}; + +static u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi, u8 *data) +{ + u8 type, byte, mode, vc, port; + u16 len; + + byte = *data++; + mode = (byte >> MIPI_TRANSFER_MODE_SHIFT) & 0x1; + vc = (byte >> MIPI_VIRTUAL_CHANNEL_SHIFT) & 0x3; + port = (byte >> MIPI_PORT_SHIFT) & 0x3; + + /* LP or HS mode */ + intel_dsi->hs = mode; + + /* get packet type and increment the pointer */ + type = *data++; + + len = *((u16 *) data); + data += 2; + + switch (type) { + case MIPI_DSI_GENERIC_SHORT_WRITE_0_PARAM: + dsi_vc_generic_write_0(intel_dsi, vc); + break; + case MIPI_DSI_GENERIC_SHORT_WRITE_1_PARAM: + dsi_vc_generic_write_1(intel_dsi, vc, *data); + break; + case MIPI_DSI_GENERIC_SHORT_WRITE_2_PARAM: + dsi_vc_generic_write_2(intel_dsi, vc, *data, *(data + 1)); + break; + case MIPI_DSI_GENERIC_READ_REQUEST_0_PARAM: + case MIPI_DSI_GENERIC_READ_REQUEST_1_PARAM: + case MIPI_DSI_GENERIC_READ_REQUEST_2_PARAM: + DRM_DEBUG_DRIVER("Generic Read not yet implemented or used\n"); + break; + case MIPI_DSI_GENERIC_LONG_WRITE: + dsi_vc_generic_write(intel_dsi, vc, data, len); + break; + case MIPI_DSI_DCS_SHORT_WRITE: + dsi_vc_dcs_write_0(intel_dsi, vc, *data); + break; + case MIPI_DSI_DCS_SHORT_WRITE_PARAM: + dsi_vc_dcs_write_1(intel_dsi, vc, *data, *(data + 1)); + break; + case MIPI_DSI_DCS_READ: + DRM_DEBUG_DRIVER("DCS Read not yet implemented or used\n"); + break; + case MIPI_DSI_DCS_LONG_WRITE: + dsi_vc_dcs_write(intel_dsi, vc, data, len); + break; + }; + + data += len; + + return data; +} + +static u8 *mipi_exec_delay(struct intel_dsi *intel_dsi, u8 *data) +{ + u32 delay = *((u32 *) data); + + usleep_range(delay, delay + 10); + data += 4; + + return data; +} + +static u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, u8 *data) +{ + u8 gpio, action; + u16 function, pad; + u32 val; + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + gpio = *data++; + + /* pull up/down */ + action = *data++; + + function = gtable[gpio].function_reg; + pad = gtable[gpio].pad_reg; + + mutex_lock(&dev_priv->dpio_lock); + if (!gtable[gpio].init) { + /* program the function */ + /* FIXME: remove constant below */ + vlv_gpio_nc_write(dev_priv, function, 0x2000CC00); + gtable[gpio].init = 1; + } + + val = 0x4 | action; + + /* pull up/down */ + vlv_gpio_nc_write(dev_priv, pad, val); + mutex_unlock(&dev_priv->dpio_lock); + + return data; +} + +typedef u8 * (*fn_mipi_elem_exec)(struct intel_dsi *intel_dsi, u8 *data); +static const fn_mipi_elem_exec exec_elem[] = { + NULL, /* reserved */ + mipi_exec_send_packet, + mipi_exec_delay, + mipi_exec_gpio, + NULL, /* status read; later */ +}; + +/* + * MIPI Sequence from VBT #53 parsing logic + * We have already separated each seqence during bios parsing + * Following is generic execution function for any sequence + */ + +static const char * const seq_name[] = { + "UNDEFINED", + "MIPI_SEQ_ASSERT_RESET", + "MIPI_SEQ_INIT_OTP", + "MIPI_SEQ_DISPLAY_ON", + "MIPI_SEQ_DISPLAY_OFF", + "MIPI_SEQ_DEASSERT_RESET" +}; + +static void generic_exec_sequence(struct intel_dsi *intel_dsi, char *sequence) +{ + u8 *data = sequence; + fn_mipi_elem_exec mipi_elem_exec; + int index; + + if (!sequence) + return; + + DRM_DEBUG_DRIVER("Starting MIPI sequence - %s\n", seq_name[*data]); + + /* go to the first element of the sequence */ + data++; + + /* parse each byte till we reach end of sequence byte - 0x00 */ + while (1) { + index = *data; + mipi_elem_exec = exec_elem[index]; + if (!mipi_elem_exec) { + DRM_ERROR("Unsupported MIPI element, skipping sequence execution\n"); + return; + } + + /* goto element payload */ + data++; + + /* execute the element specific rotines */ + data = mipi_elem_exec(intel_dsi, data); + + /* + * After processing the element, data should point to + * next element or end of sequence + * check if have we reached end of sequence + */ + if (*data == 0x00) + break; + } +} + +static bool generic_init(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct mipi_config *mipi_config = dev_priv->vbt.dsi.config; + struct mipi_pps_data *pps = dev_priv->vbt.dsi.pps; + struct drm_display_mode *mode = dev_priv->vbt.lfp_lvds_vbt_mode; + u32 bits_per_pixel = 24; + u32 tlpx_ns, extra_byte_count, bitrate, tlpx_ui; + u32 ui_num, ui_den; + u32 prepare_cnt, exit_zero_cnt, clk_zero_cnt, trail_cnt; + u32 ths_prepare_ns, tclk_trail_ns; + u32 tclk_prepare_clkzero, ths_prepare_hszero; + u32 lp_to_hs_switch, hs_to_lp_switch; + + DRM_DEBUG_KMS("\n"); + + intel_dsi->eotp_pkt = mipi_config->eot_pkt_disabled ? 0 : 1; + intel_dsi->clock_stop = mipi_config->enable_clk_stop ? 1 : 0; + intel_dsi->lane_count = mipi_config->lane_cnt + 1; + intel_dsi->pixel_format = mipi_config->videomode_color_format << 7; + + if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB666) + bits_per_pixel = 18; + else if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB565) + bits_per_pixel = 16; + + bitrate = (mode->clock * bits_per_pixel) / intel_dsi->lane_count; + + intel_dsi->operation_mode = mipi_config->is_cmd_mode; + intel_dsi->video_mode_format = mipi_config->video_transfer_mode; + intel_dsi->escape_clk_div = mipi_config->byte_clk_sel; + intel_dsi->lp_rx_timeout = mipi_config->lp_rx_timeout; + intel_dsi->turn_arnd_val = mipi_config->turn_around_timeout; + intel_dsi->rst_timer_val = mipi_config->device_reset_timer; + intel_dsi->init_count = mipi_config->master_init_timer; + intel_dsi->bw_timer = mipi_config->dbi_bw_timer; + intel_dsi->video_frmt_cfg_bits = mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0; + + switch (intel_dsi->escape_clk_div) { + case 0: + tlpx_ns = 50; + break; + case 1: + tlpx_ns = 100; + break; + + case 2: + tlpx_ns = 200; + break; + default: + tlpx_ns = 50; + break; + } + + switch (intel_dsi->lane_count) { + case 1: + case 2: + extra_byte_count = 2; + break; + case 3: + extra_byte_count = 4; + break; + case 4: + default: + extra_byte_count = 3; + break; + } + + /* + * ui(s) = 1/f [f in hz] + * ui(ns) = 10^9 / (f*10^6) [f in Mhz] -> 10^3/f(Mhz) + */ + + /* in Kbps */ + ui_num = NS_KHZ_RATIO; + ui_den = bitrate; + + tclk_prepare_clkzero = mipi_config->tclk_prepare_clkzero; + ths_prepare_hszero = mipi_config->ths_prepare_hszero; + + /* + * B060 + * LP byte clock = TLPX/ (8UI) + */ + intel_dsi->lp_byte_clk = DIV_ROUND_UP(tlpx_ns * ui_den, 8 * ui_num); + + /* count values in UI = (ns value) * (bitrate / (2 * 10^6)) + * + * Since txddrclkhs_i is 2xUI, all the count values programmed in + * DPHY param register are divided by 2 + * + * prepare count + */ + ths_prepare_ns = max(mipi_config->ths_prepare, mipi_config->tclk_prepare); + prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * ui_den, ui_num * 2); + + /* exit zero count */ + exit_zero_cnt = DIV_ROUND_UP( + (ths_prepare_hszero - ths_prepare_ns) * ui_den, + ui_num * 2 + ); + + /* + * Exit zero is unified val ths_zero and ths_exit + * minimum value for ths_exit = 110ns + * min (exit_zero_cnt * 2) = 110/UI + * exit_zero_cnt = 55/UI + */ + if (exit_zero_cnt < (55 * ui_den / ui_num)) + if ((55 * ui_den) % ui_num) + exit_zero_cnt += 1; + + /* clk zero count */ + clk_zero_cnt = DIV_ROUND_UP( + (tclk_prepare_clkzero - ths_prepare_ns) + * ui_den, 2 * ui_num); + + /* trail count */ + tclk_trail_ns = max(mipi_config->tclk_trail, mipi_config->ths_trail); + trail_cnt = DIV_ROUND_UP(tclk_trail_ns * ui_den, 2 * ui_num); + + if (prepare_cnt > PREPARE_CNT_MAX || + exit_zero_cnt > EXIT_ZERO_CNT_MAX || + clk_zero_cnt > CLK_ZERO_CNT_MAX || + trail_cnt > TRAIL_CNT_MAX) + DRM_DEBUG_DRIVER("Values crossing maximum limits, restricting to max values\n"); + + if (prepare_cnt > PREPARE_CNT_MAX) + prepare_cnt = PREPARE_CNT_MAX; + + if (exit_zero_cnt > EXIT_ZERO_CNT_MAX) + exit_zero_cnt = EXIT_ZERO_CNT_MAX; + + if (clk_zero_cnt > CLK_ZERO_CNT_MAX) + clk_zero_cnt = CLK_ZERO_CNT_MAX; + + if (trail_cnt > TRAIL_CNT_MAX) + trail_cnt = TRAIL_CNT_MAX; + + /* B080 */ + intel_dsi->dphy_reg = exit_zero_cnt << 24 | trail_cnt << 16 | + clk_zero_cnt << 8 | prepare_cnt; + + /* + * LP to HS switch count = 4TLPX + PREP_COUNT * 2 + EXIT_ZERO_COUNT * 2 + * + 10UI + Extra Byte Count + * + * HS to LP switch count = THS-TRAIL + 2TLPX + Extra Byte Count + * Extra Byte Count is calculated according to number of lanes. + * High Low Switch Count is the Max of LP to HS and + * HS to LP switch count + * + */ + tlpx_ui = DIV_ROUND_UP(tlpx_ns * ui_den, ui_num); + + /* B044 */ + /* FIXME: + * The comment above does not match with the code */ + lp_to_hs_switch = DIV_ROUND_UP(4 * tlpx_ui + prepare_cnt * 2 + + exit_zero_cnt * 2 + 10, 8); + + hs_to_lp_switch = DIV_ROUND_UP(mipi_config->ths_trail + 2 * tlpx_ui, 8); + + intel_dsi->hs_to_lp_count = max(lp_to_hs_switch, hs_to_lp_switch); + intel_dsi->hs_to_lp_count += extra_byte_count; + + /* B088 */ + /* LP -> HS for clock lanes + * LP clk sync + LP11 + LP01 + tclk_prepare + tclk_zero + + * extra byte count + * 2TPLX + 1TLPX + 1 TPLX(in ns) + prepare_cnt * 2 + clk_zero_cnt * + * 2(in UI) + extra byte count + * In byteclks = (4TLPX + prepare_cnt * 2 + clk_zero_cnt *2 (in UI)) / + * 8 + extra byte count + */ + intel_dsi->clk_lp_to_hs_count = + DIV_ROUND_UP( + 4 * tlpx_ui + prepare_cnt * 2 + + clk_zero_cnt * 2, + 8); + + intel_dsi->clk_lp_to_hs_count += extra_byte_count; + + /* HS->LP for Clock Lanes + * Low Power clock synchronisations + 1Tx byteclk + tclk_trail + + * Extra byte count + * 2TLPX + 8UI + (trail_count*2)(in UI) + Extra byte count + * In byteclks = (2*TLpx(in UI) + trail_count*2 +8)(in UI)/8 + + * Extra byte count + */ + intel_dsi->clk_hs_to_lp_count = + DIV_ROUND_UP(2 * tlpx_ui + trail_cnt * 2 + 8, + 8); + intel_dsi->clk_hs_to_lp_count += extra_byte_count; + + DRM_DEBUG_KMS("Eot %s\n", intel_dsi->eotp_pkt ? "enabled" : "disabled"); + DRM_DEBUG_KMS("Clockstop %s\n", intel_dsi->clock_stop ? + "disabled" : "enabled"); + DRM_DEBUG_KMS("Mode %s\n", intel_dsi->operation_mode ? "command" : "video"); + DRM_DEBUG_KMS("Pixel Format %d\n", intel_dsi->pixel_format); + DRM_DEBUG_KMS("TLPX %d\n", intel_dsi->escape_clk_div); + DRM_DEBUG_KMS("LP RX Timeout 0x%x\n", intel_dsi->lp_rx_timeout); + DRM_DEBUG_KMS("Turnaround Timeout 0x%x\n", intel_dsi->turn_arnd_val); + DRM_DEBUG_KMS("Init Count 0x%x\n", intel_dsi->init_count); + DRM_DEBUG_KMS("HS to LP Count 0x%x\n", intel_dsi->hs_to_lp_count); + DRM_DEBUG_KMS("LP Byte Clock %d\n", intel_dsi->lp_byte_clk); + DRM_DEBUG_KMS("DBI BW Timer 0x%x\n", intel_dsi->bw_timer); + DRM_DEBUG_KMS("LP to HS Clock Count 0x%x\n", intel_dsi->clk_lp_to_hs_count); + DRM_DEBUG_KMS("HS to LP Clock Count 0x%x\n", intel_dsi->clk_hs_to_lp_count); + DRM_DEBUG_KMS("BTA %s\n", + intel_dsi->video_frmt_cfg_bits & DISABLE_VIDEO_BTA ? + "disabled" : "enabled"); + + /* delays in VBT are in unit of 100us, so need to convert + * here in ms + * Delay (100us) * 100 /1000 = Delay / 10 (ms) */ + intel_dsi->backlight_off_delay = pps->bl_disable_delay / 10; + intel_dsi->backlight_on_delay = pps->bl_enable_delay / 10; + intel_dsi->panel_on_delay = pps->panel_on_delay / 10; + intel_dsi->panel_off_delay = pps->panel_off_delay / 10; + intel_dsi->panel_pwr_cycle_delay = pps->panel_power_cycle_delay / 10; + + return true; +} + +static int generic_mode_valid(struct intel_dsi_device *dsi, + struct drm_display_mode *mode) +{ + return MODE_OK; +} + +static bool generic_mode_fixup(struct intel_dsi_device *dsi, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) { + return true; +} + +static void generic_panel_reset(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET]; + + generic_exec_sequence(intel_dsi, sequence); +} + +static void generic_disable_panel_power(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]; + + generic_exec_sequence(intel_dsi, sequence); +} + +static void generic_send_otp_cmds(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP]; + + generic_exec_sequence(intel_dsi, sequence); +} + +static void generic_enable(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]; + + generic_exec_sequence(intel_dsi, sequence); +} + +static void generic_disable(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_OFF]; + + generic_exec_sequence(intel_dsi, sequence); +} + +static enum drm_connector_status generic_detect(struct intel_dsi_device *dsi) +{ + return connector_status_connected; +} + +static bool generic_get_hw_state(struct intel_dsi_device *dev) +{ + return true; +} + +static struct drm_display_mode *generic_get_modes(struct intel_dsi_device *dsi) +{ + struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev); + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + dev_priv->vbt.lfp_lvds_vbt_mode->type |= DRM_MODE_TYPE_PREFERRED; + return dev_priv->vbt.lfp_lvds_vbt_mode; +} + +static void generic_destroy(struct intel_dsi_device *dsi) { } + +/* Callbacks. We might not need them all. */ +struct intel_dsi_dev_ops vbt_generic_dsi_display_ops = { + .init = generic_init, + .mode_valid = generic_mode_valid, + .mode_fixup = generic_mode_fixup, + .panel_reset = generic_panel_reset, + .disable_panel_power = generic_disable_panel_power, + .send_otp_cmds = generic_send_otp_cmds, + .enable = generic_enable, + .disable = generic_disable, + .detect = generic_detect, + .get_hw_state = generic_get_hw_state, + .get_modes = generic_get_modes, + .destroy = generic_destroy, +}; diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 7fe3feedfe03..a3631c0a5c28 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -285,7 +285,7 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder, return true; } -static void intel_dvo_mode_set(struct intel_encoder *encoder) +static void intel_dvo_pre_enable(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -343,7 +343,7 @@ intel_dvo_detect(struct drm_connector *connector, bool force) { struct intel_dvo *intel_dvo = intel_attached_dvo(connector); DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev); } @@ -475,7 +475,7 @@ void intel_dvo_init(struct drm_device *dev) intel_encoder->get_hw_state = intel_dvo_get_hw_state; intel_encoder->get_config = intel_dvo_get_config; intel_encoder->compute_config = intel_dvo_compute_config; - intel_encoder->mode_set = intel_dvo_mode_set; + intel_encoder->pre_enable = intel_dvo_pre_enable; intel_connector->get_hw_state = intel_dvo_connector_get_hw_state; intel_connector->unregister = intel_connector_unregister; diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index f73ba5e6b7a8..088fe9378a4c 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -343,15 +343,15 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, num_connectors_detected++; if (!enabled[i]) { - DRM_DEBUG_KMS("connector %d not enabled, skipping\n", - connector->base.id); + DRM_DEBUG_KMS("connector %s not enabled, skipping\n", + connector->name); continue; } encoder = connector->encoder; if (!encoder || WARN_ON(!encoder->crtc)) { - DRM_DEBUG_KMS("connector %d has no encoder or crtc, skipping\n", - connector->base.id); + DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n", + connector->name); enabled[i] = false; continue; } @@ -373,16 +373,16 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, } } - DRM_DEBUG_KMS("looking for cmdline mode on connector %d\n", - fb_conn->connector->base.id); + DRM_DEBUG_KMS("looking for cmdline mode on connector %s\n", + connector->name); /* go for command line mode first */ modes[i] = drm_pick_cmdline_mode(fb_conn, width, height); /* try for preferred next */ if (!modes[i]) { - DRM_DEBUG_KMS("looking for preferred mode on connector %d\n", - fb_conn->connector->base.id); + DRM_DEBUG_KMS("looking for preferred mode on connector %s\n", + connector->name); modes[i] = drm_has_preferred_mode(fb_conn, width, height); } @@ -390,7 +390,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, /* No preferred mode marked by the EDID? Are there any modes? */ if (!modes[i] && !list_empty(&connector->modes)) { DRM_DEBUG_KMS("using first mode listed on connector %s\n", - drm_get_connector_name(connector)); + connector->name); modes[i] = list_first_entry(&connector->modes, struct drm_display_mode, head); @@ -409,16 +409,20 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, * since the fb helper layer wants a pointer to * something we own. */ + DRM_DEBUG_KMS("looking for current mode on connector %s\n", + connector->name); intel_mode_from_pipe_config(&encoder->crtc->hwmode, &to_intel_crtc(encoder->crtc)->config); modes[i] = &encoder->crtc->hwmode; } crtcs[i] = new_crtc; - DRM_DEBUG_KMS("connector %s on crtc %d: %s\n", - drm_get_connector_name(connector), + DRM_DEBUG_KMS("connector %s on pipe %d [CRTC:%d]: %dx%d%s\n", + connector->name, + pipe_name(to_intel_crtc(encoder->crtc)->pipe), encoder->crtc->base.id, - modes[i]->name); + modes[i]->hdisplay, modes[i]->vdisplay, + modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :""); fallback = false; } @@ -497,7 +501,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, return false; /* Find the largest fb */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { intel_crtc = to_intel_crtc(crtc); if (!intel_crtc->active || !crtc->primary->fb) { @@ -521,7 +525,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, } /* Now make sure all the pipes will fit into it */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { unsigned int cur_size; intel_crtc = to_intel_crtc(crtc); @@ -586,7 +590,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, drm_framebuffer_reference(&ifbdev->fb->base); /* Final pass to check if any active pipes don't have fbs */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { intel_crtc = to_intel_crtc(crtc); if (!intel_crtc->active) @@ -692,11 +696,7 @@ void intel_fbdev_restore_mode(struct drm_device *dev) if (!dev_priv->fbdev) return; - drm_modeset_lock_all(dev); - - ret = drm_fb_helper_restore_fbdev_mode(&dev_priv->fbdev->helper); + ret = drm_fb_helper_restore_fbdev_mode_unlocked(&dev_priv->fbdev->helper); if (ret) DRM_DEBUG("failed to restore crtc mode\n"); - - drm_modeset_unlock_all(dev); } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 157267aa3561..eee2bbec2958 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -418,6 +418,7 @@ intel_hdmi_set_hdmi_infoframe(struct drm_encoder *encoder, } static void g4x_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -440,7 +441,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder, * either. */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~VIDEO_DIP_ENABLE; @@ -471,6 +472,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder, } static void ibx_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -486,7 +488,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, /* See the big comment in g4x_set_infoframes() */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~VIDEO_DIP_ENABLE; @@ -518,6 +520,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, } static void cpt_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -531,7 +534,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder, /* See the big comment in g4x_set_infoframes() */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~(VIDEO_DIP_ENABLE | VIDEO_DIP_ENABLE_AVI); @@ -554,20 +557,23 @@ static void cpt_set_infoframes(struct drm_encoder *encoder, } static void vlv_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; + struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); u32 reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe); u32 val = I915_READ(reg); + u32 port = VIDEO_DIP_PORT(intel_dig_port->port); assert_hdmi_port_disabled(intel_hdmi); /* See the big comment in g4x_set_infoframes() */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~VIDEO_DIP_ENABLE; @@ -576,9 +582,19 @@ static void vlv_set_infoframes(struct drm_encoder *encoder, return; } + if (port != (val & VIDEO_DIP_PORT_MASK)) { + if (val & VIDEO_DIP_ENABLE) { + val &= ~VIDEO_DIP_ENABLE; + I915_WRITE(reg, val); + POSTING_READ(reg); + } + val &= ~VIDEO_DIP_PORT_MASK; + val |= port; + } + val |= VIDEO_DIP_ENABLE; - val &= ~(VIDEO_DIP_ENABLE_VENDOR | VIDEO_DIP_ENABLE_GAMUT | - VIDEO_DIP_ENABLE_GCP); + val &= ~(VIDEO_DIP_ENABLE_AVI | VIDEO_DIP_ENABLE_VENDOR | + VIDEO_DIP_ENABLE_GAMUT | VIDEO_DIP_ENABLE_GCP); I915_WRITE(reg, val); POSTING_READ(reg); @@ -589,6 +605,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder, } static void hsw_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -599,7 +616,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder, assert_hdmi_port_disabled(intel_hdmi); - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { I915_WRITE(reg, 0); POSTING_READ(reg); return; @@ -616,7 +633,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder, intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode); } -static void intel_hdmi_mode_set(struct intel_encoder *encoder) +static void intel_hdmi_prepare(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -638,27 +655,26 @@ static void intel_hdmi_mode_set(struct intel_encoder *encoder) else hdmi_val |= SDVO_COLOR_FORMAT_8bpc; - /* Required on CPT */ - if (intel_hdmi->has_hdmi_sink && HAS_PCH_CPT(dev)) + if (crtc->config.has_hdmi_sink) hdmi_val |= HDMI_MODE_SELECT_HDMI; - if (intel_hdmi->has_audio) { + if (crtc->config.has_audio) { + WARN_ON(!crtc->config.has_hdmi_sink); DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n", pipe_name(crtc->pipe)); hdmi_val |= SDVO_AUDIO_ENABLE; - hdmi_val |= HDMI_MODE_SELECT_HDMI; intel_write_eld(&encoder->base, adjusted_mode); } if (HAS_PCH_CPT(dev)) hdmi_val |= SDVO_PIPE_SEL_CPT(crtc->pipe); + else if (IS_CHERRYVIEW(dev)) + hdmi_val |= SDVO_PIPE_SEL_CHV(crtc->pipe); else hdmi_val |= SDVO_PIPE_SEL(crtc->pipe); I915_WRITE(intel_hdmi->hdmi_reg, hdmi_val); POSTING_READ(intel_hdmi->hdmi_reg); - - intel_hdmi->set_infoframes(&encoder->base, adjusted_mode); } static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, @@ -681,6 +697,8 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); + else if (IS_CHERRYVIEW(dev)) + *pipe = SDVO_PORT_TO_PIPE_CHV(tmp); else *pipe = PORT_TO_PIPE(tmp); @@ -707,6 +725,12 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder, else flags |= DRM_MODE_FLAG_NVSYNC; + if (tmp & HDMI_MODE_SELECT_HDMI) + pipe_config->has_hdmi_sink = true; + + if (tmp & HDMI_MODE_SELECT_HDMI) + pipe_config->has_audio = true; + pipe_config->adjusted_mode.flags |= flags; if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc) @@ -729,7 +753,7 @@ static void intel_enable_hdmi(struct intel_encoder *encoder) u32 temp; u32 enable_bits = SDVO_ENABLE; - if (intel_hdmi->has_audio) + if (intel_crtc->config.has_audio) enable_bits |= SDVO_AUDIO_ENABLE; temp = I915_READ(intel_hdmi->hdmi_reg); @@ -883,9 +907,11 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, int portclock_limit = hdmi_portclock_limit(intel_hdmi, false); int desired_bpp; + pipe_config->has_hdmi_sink = intel_hdmi->has_hdmi_sink; + if (intel_hdmi->color_range_auto) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ - if (intel_hdmi->has_hdmi_sink && + if (pipe_config->has_hdmi_sink && drm_match_cea_mode(adjusted_mode) > 1) intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235; else @@ -898,13 +924,16 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev)) pipe_config->has_pch_encoder = true; + if (pipe_config->has_hdmi_sink && intel_hdmi->has_audio) + pipe_config->has_audio = true; + /* * HDMI is either 12 or 8, so if the display lets 10bpc sneak * through, clamp it down. Note that g4x/vlv don't support 12bpc hdmi * outputs. We also need to check that the higher clock still fits * within limits. */ - if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink && + if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink && clock_12bpc <= portclock_limit && hdmi_12bpc_possible(encoder->new_crtc)) { DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n"); @@ -944,7 +973,7 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) enum drm_connector_status status = connector_status_disconnected; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); power_domain = intel_display_port_power_domain(intel_encoder); intel_display_power_get(dev_priv, power_domain); @@ -1104,20 +1133,34 @@ done: return 0; } +static void intel_hdmi_pre_enable(struct intel_encoder *encoder) +{ + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); + struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + struct drm_display_mode *adjusted_mode = + &intel_crtc->config.adjusted_mode; + + intel_hdmi_prepare(encoder); + + intel_hdmi->set_infoframes(&encoder->base, + intel_crtc->config.has_hdmi_sink, + adjusted_mode); +} + static void vlv_hdmi_pre_enable(struct intel_encoder *encoder) { struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct intel_hdmi *intel_hdmi = &dport->hdmi; struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + struct drm_display_mode *adjusted_mode = + &intel_crtc->config.adjusted_mode; enum dpio_channel port = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; u32 val; - if (!IS_VALLEYVIEW(dev)) - return; - /* Enable clock channels for this port */ mutex_lock(&dev_priv->dpio_lock); val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port)); @@ -1144,6 +1187,10 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder) vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888); mutex_unlock(&dev_priv->dpio_lock); + intel_hdmi->set_infoframes(&encoder->base, + intel_crtc->config.has_hdmi_sink, + adjusted_mode); + intel_enable_hdmi(encoder); vlv_wait_port_ready(dev_priv, dport); @@ -1159,8 +1206,7 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder) enum dpio_channel port = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; - if (!IS_VALLEYVIEW(dev)) - return; + intel_hdmi_prepare(encoder); /* Program Tx lane resets to default */ mutex_lock(&dev_priv->dpio_lock); @@ -1199,6 +1245,152 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->dpio_lock); } +static void chv_hdmi_post_disable(struct intel_encoder *encoder) +{ + struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + enum pipe pipe = intel_crtc->pipe; + u32 val; + + mutex_lock(&dev_priv->dpio_lock); + + /* Propagate soft reset to data lane reset */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + mutex_unlock(&dev_priv->dpio_lock); +} + +static void chv_hdmi_pre_enable(struct intel_encoder *encoder) +{ + struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + int pipe = intel_crtc->pipe; + int data, i; + u32 val; + + mutex_lock(&dev_priv->dpio_lock); + + /* Deassert soft data lane reset*/ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + /* Program Tx latency optimal setting */ + for (i = 0; i < 4; i++) { + /* Set the latency optimal bit */ + data = (i == 1) ? 0x0 : 0x6; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW11(ch, i), + data << DPIO_FRC_LATENCY_SHFIT); + + /* Set the upar bit */ + data = (i == 1) ? 0x0 : 0x1; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i), + data << DPIO_UPAR_SHIFT); + } + + /* Data lane stagger programming */ + /* FIXME: Fix up value only after power analysis */ + + /* Clear calc init */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* FIXME: Program the support xxx V-dB */ + /* Use 800mV-0dB */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i)); + val &= ~DPIO_SWING_DEEMPH9P5_MASK; + val |= 128 << DPIO_SWING_DEEMPH9P5_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val); + } + + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~DPIO_SWING_MARGIN_MASK; + val |= 102 << DPIO_SWING_MARGIN_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); + } + + /* Disable unique transition scale */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); + } + + /* Additional steps for 1200mV-0dB */ +#if 0 + val = vlv_dpio_read(dev_priv, pipe, VLV_TX_DW3(ch)); + if (ch) + val |= DPIO_TX_UNIQ_TRANS_SCALE_CH1; + else + val |= DPIO_TX_UNIQ_TRANS_SCALE_CH0; + vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(ch), val); + + vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(ch), + vlv_dpio_read(dev_priv, pipe, VLV_TX_DW2(ch)) | + (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT)); +#endif + /* Start swing calculation */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* LRC Bypass */ + val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); + val |= DPIO_LRC_BYPASS; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val); + + mutex_unlock(&dev_priv->dpio_lock); + + intel_enable_hdmi(encoder); + + vlv_wait_port_ready(dev_priv, dport); +} + static void intel_hdmi_destroy(struct drm_connector *connector) { drm_connector_cleanup(connector); @@ -1259,7 +1451,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, intel_encoder->hpd_pin = HPD_PORT_C; break; case PORT_D: - intel_hdmi->ddc_bus = GMBUS_PORT_DPD; + if (IS_CHERRYVIEW(dev)) + intel_hdmi->ddc_bus = GMBUS_PORT_DPD_CHV; + else + intel_hdmi->ddc_bus = GMBUS_PORT_DPD; intel_encoder->hpd_pin = HPD_PORT_D; break; case PORT_A: @@ -1329,21 +1524,32 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port) DRM_MODE_ENCODER_TMDS); intel_encoder->compute_config = intel_hdmi_compute_config; - intel_encoder->mode_set = intel_hdmi_mode_set; intel_encoder->disable = intel_disable_hdmi; intel_encoder->get_hw_state = intel_hdmi_get_hw_state; intel_encoder->get_config = intel_hdmi_get_config; - if (IS_VALLEYVIEW(dev)) { + if (IS_CHERRYVIEW(dev)) { + intel_encoder->pre_enable = chv_hdmi_pre_enable; + intel_encoder->enable = vlv_enable_hdmi; + intel_encoder->post_disable = chv_hdmi_post_disable; + } else if (IS_VALLEYVIEW(dev)) { intel_encoder->pre_pll_enable = vlv_hdmi_pre_pll_enable; intel_encoder->pre_enable = vlv_hdmi_pre_enable; intel_encoder->enable = vlv_enable_hdmi; intel_encoder->post_disable = vlv_hdmi_post_disable; } else { + intel_encoder->pre_enable = intel_hdmi_pre_enable; intel_encoder->enable = intel_enable_hdmi; } intel_encoder->type = INTEL_OUTPUT_HDMI; - intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + if (IS_CHERRYVIEW(dev)) { + if (port == PORT_D) + intel_encoder->crtc_mask = 1 << 2; + else + intel_encoder->crtc_mask = (1 << 0) | (1 << 1); + } else { + intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + } intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG; /* * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index f1ecf916474a..23126023aeba 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -111,13 +111,6 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, pipe_config->adjusted_mode.flags |= flags; - /* gen2/3 store dither state in pfit control, needs to match */ - if (INTEL_INFO(dev)->gen < 4) { - tmp = I915_READ(PFIT_CONTROL); - - pipe_config->gmch_pfit.control |= tmp & PANEL_8TO6_DITHER_ENABLE; - } - dotclock = pipe_config->port_clock; if (HAS_PCH_SPLIT(dev_priv->dev)) @@ -126,10 +119,6 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, pipe_config->adjusted_mode.crtc_clock = dotclock; } -/* The LVDS pin pair needs to be on before the DPLLs are enabled. - * This is an exception to the general rule that mode_set doesn't turn - * things on. - */ static void intel_pre_enable_lvds(struct intel_encoder *encoder) { struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); @@ -331,15 +320,6 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder, return true; } -static void intel_lvds_mode_set(struct intel_encoder *encoder) -{ - /* - * We don't do anything here, the LVDS port is fully set up in the pre - * enable hook - the ordering constraints for enabling the lvds port vs. - * enabling the display pll are too strict. - */ -} - /** * Detect the LVDS connection. * @@ -354,7 +334,7 @@ intel_lvds_detect(struct drm_connector *connector, bool force) enum drm_connector_status status; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); status = intel_panel_detect(dev); if (status != connector_status_unknown) @@ -953,7 +933,6 @@ void intel_lvds_init(struct drm_device *dev) intel_encoder->enable = intel_enable_lvds; intel_encoder->pre_enable = intel_pre_enable_lvds; intel_encoder->compute_config = intel_lvds_compute_config; - intel_encoder->mode_set = intel_lvds_mode_set; intel_encoder->disable = intel_disable_lvds; intel_encoder->get_hw_state = intel_lvds_get_hw_state; intel_encoder->get_config = intel_lvds_get_config; diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index acde2945eb8a..2e2c71fcc9ed 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -410,7 +410,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp) if (bclp > 255) return ASLC_BACKLIGHT_FAILED; - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); /* * Update backlight on all connectors that support backlight (usually @@ -421,7 +421,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp) intel_panel_set_backlight(intel_connector, bclp, 255); iowrite32(DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID, &asle->cblv); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock(&dev->mode_config.connection_mutex); return 0; diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 129db0c7d835..daa118978eec 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -213,7 +213,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay, { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; BUG_ON(overlay->last_flip_req); @@ -236,7 +236,7 @@ static int intel_overlay_on(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; BUG_ON(overlay->active); @@ -263,7 +263,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay, { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; u32 flip_addr = overlay->flip_addr; u32 tmp; int ret; @@ -320,7 +320,7 @@ static int intel_overlay_off(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; u32 flip_addr = overlay->flip_addr; int ret; @@ -363,7 +363,7 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; if (overlay->last_flip_req == 0) @@ -389,7 +389,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; /* Only wait if there is actually an old frame to release to @@ -688,7 +688,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, u32 swidth, swidthsw, sheight, ostride; BUG_ON(!mutex_is_locked(&dev->struct_mutex)); - BUG_ON(!mutex_is_locked(&dev->mode_config.mutex)); + BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); BUG_ON(!overlay); ret = intel_overlay_release_old_vid(overlay); @@ -793,7 +793,7 @@ int intel_overlay_switch_off(struct intel_overlay *overlay) int ret; BUG_ON(!mutex_is_locked(&dev->struct_mutex)); - BUG_ON(!mutex_is_locked(&dev->mode_config.mutex)); + BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); ret = intel_overlay_recover_from_interrupt(overlay); if (ret != 0) diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index cb8cfb7e0974..5e6c888b4928 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -42,6 +42,59 @@ intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode, drm_mode_set_crtcinfo(adjusted_mode, 0); } +/** + * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID + * @dev: drm device + * @fixed_mode : panel native mode + * @connector: LVDS/eDP connector + * + * Return downclock_avail + * Find the reduced downclock for LVDS/eDP in EDID. + */ +struct drm_display_mode * +intel_find_panel_downclock(struct drm_device *dev, + struct drm_display_mode *fixed_mode, + struct drm_connector *connector) +{ + struct drm_display_mode *scan, *tmp_mode; + int temp_downclock; + + temp_downclock = fixed_mode->clock; + tmp_mode = NULL; + + list_for_each_entry(scan, &connector->probed_modes, head) { + /* + * If one mode has the same resolution with the fixed_panel + * mode while they have the different refresh rate, it means + * that the reduced downclock is found. In such + * case we can set the different FPx0/1 to dynamically select + * between low and high frequency. + */ + if (scan->hdisplay == fixed_mode->hdisplay && + scan->hsync_start == fixed_mode->hsync_start && + scan->hsync_end == fixed_mode->hsync_end && + scan->htotal == fixed_mode->htotal && + scan->vdisplay == fixed_mode->vdisplay && + scan->vsync_start == fixed_mode->vsync_start && + scan->vsync_end == fixed_mode->vsync_end && + scan->vtotal == fixed_mode->vtotal) { + if (scan->clock < temp_downclock) { + /* + * The downclock is already found. But we + * expect to find the lower downclock. + */ + temp_downclock = scan->clock; + tmp_mode = scan; + } + } + } + + if (temp_downclock < fixed_mode->clock) + return drm_mode_duplicate(dev, tmp_mode); + else + return NULL; +} + /* adjusted_mode has been preset to be the panel's fixed mode */ void intel_pch_panel_fitting(struct intel_crtc *intel_crtc, @@ -308,21 +361,43 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc, pfit_control |= ((intel_crtc->pipe << PFIT_PIPE_SHIFT) | PFIT_FILTER_FUZZY); + /* Make sure pre-965 set dither correctly for 18bpp panels. */ + if (INTEL_INFO(dev)->gen < 4 && pipe_config->pipe_bpp == 18) + pfit_control |= PANEL_8TO6_DITHER_ENABLE; + out: if ((pfit_control & PFIT_ENABLE) == 0) { pfit_control = 0; pfit_pgm_ratios = 0; } - /* Make sure pre-965 set dither correctly for 18bpp panels. */ - if (INTEL_INFO(dev)->gen < 4 && pipe_config->pipe_bpp == 18) - pfit_control |= PANEL_8TO6_DITHER_ENABLE; - pipe_config->gmch_pfit.control = pfit_control; pipe_config->gmch_pfit.pgm_ratios = pfit_pgm_ratios; pipe_config->gmch_pfit.lvds_border_bits = border; } +enum drm_connector_status +intel_panel_detect(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Assume that the BIOS does not lie through the OpRegion... */ + if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) { + return ioread32(dev_priv->opregion.lid_state) & 0x1 ? + connector_status_connected : + connector_status_disconnected; + } + + switch (i915.panel_ignore_lid) { + case -2: + return connector_status_connected; + case -1: + return connector_status_disconnected; + default: + return connector_status_unknown; + } +} + static u32 intel_panel_compute_brightness(struct intel_connector *connector, u32 val) { @@ -795,40 +870,18 @@ void intel_panel_enable_backlight(struct intel_connector *connector) spin_unlock_irqrestore(&dev_priv->backlight_lock, flags); } -enum drm_connector_status -intel_panel_detect(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - /* Assume that the BIOS does not lie through the OpRegion... */ - if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) { - return ioread32(dev_priv->opregion.lid_state) & 0x1 ? - connector_status_connected : - connector_status_disconnected; - } - - switch (i915.panel_ignore_lid) { - case -2: - return connector_status_connected; - case -1: - return connector_status_disconnected; - default: - return connector_status_unknown; - } -} - #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) static int intel_backlight_device_update_status(struct backlight_device *bd) { struct intel_connector *connector = bl_get_data(bd); struct drm_device *dev = connector->base.dev; - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); DRM_DEBUG_KMS("updating intel_backlight, brightness=%d/%d\n", bd->props.brightness, bd->props.max_brightness); intel_panel_set_backlight(connector, bd->props.brightness, bd->props.max_brightness); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock(&dev->mode_config.connection_mutex); return 0; } @@ -840,9 +893,9 @@ static int intel_backlight_device_get_brightness(struct backlight_device *bd) int ret; intel_runtime_pm_get(dev_priv); - mutex_lock(&dev->mode_config.mutex); + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); ret = intel_panel_get_backlight(connector); - mutex_unlock(&dev->mode_config.mutex); + drm_modeset_unlock(&dev->mode_config.connection_mutex); intel_runtime_pm_put(dev_priv); return ret; @@ -1077,7 +1130,7 @@ int intel_panel_setup_backlight(struct drm_connector *connector) if (ret) { DRM_DEBUG_KMS("failed to setup backlight for connector %s\n", - drm_get_connector_name(connector)); + connector->name); return ret; } @@ -1103,59 +1156,6 @@ void intel_panel_destroy_backlight(struct drm_connector *connector) intel_backlight_device_unregister(intel_connector); } -/** - * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID - * @dev: drm device - * @fixed_mode : panel native mode - * @connector: LVDS/eDP connector - * - * Return downclock_avail - * Find the reduced downclock for LVDS/eDP in EDID. - */ -struct drm_display_mode * -intel_find_panel_downclock(struct drm_device *dev, - struct drm_display_mode *fixed_mode, - struct drm_connector *connector) -{ - struct drm_display_mode *scan, *tmp_mode; - int temp_downclock; - - temp_downclock = fixed_mode->clock; - tmp_mode = NULL; - - list_for_each_entry(scan, &connector->probed_modes, head) { - /* - * If one mode has the same resolution with the fixed_panel - * mode while they have the different refresh rate, it means - * that the reduced downclock is found. In such - * case we can set the different FPx0/1 to dynamically select - * between low and high frequency. - */ - if (scan->hdisplay == fixed_mode->hdisplay && - scan->hsync_start == fixed_mode->hsync_start && - scan->hsync_end == fixed_mode->hsync_end && - scan->htotal == fixed_mode->htotal && - scan->vdisplay == fixed_mode->vdisplay && - scan->vsync_start == fixed_mode->vsync_start && - scan->vsync_end == fixed_mode->vsync_end && - scan->vtotal == fixed_mode->vtotal) { - if (scan->clock < temp_downclock) { - /* - * The downclock is already found. But we - * expect to find the lower downclock. - */ - temp_downclock = scan->clock; - tmp_mode = scan; - } - } - } - - if (temp_downclock < fixed_mode->clock) - return drm_mode_duplicate(dev, tmp_mode); - else - return NULL; -} - /* Set up chip specific backlight functions */ void intel_panel_init_backlight_funcs(struct drm_device *dev) { diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index d93dcf683e8c..d1e53abec1b5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -487,7 +487,7 @@ void intel_update_fbc(struct drm_device *dev) * - new fb is too large to fit in compressed buffer * - going to an unsupported config (interlace, pixel multiply, etc.) */ - list_for_each_entry(tmp_crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, tmp_crtc) { if (intel_crtc_active(tmp_crtc) && to_intel_crtc(tmp_crtc)->primary_enabled) { if (crtc) { @@ -1010,7 +1010,7 @@ static struct drm_crtc *single_enabled_crtc(struct drm_device *dev) { struct drm_crtc *crtc, *enabled = NULL; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (intel_crtc_active(crtc)) { if (enabled) return NULL; @@ -1831,6 +1831,40 @@ static unsigned int ilk_display_fifo_size(const struct drm_device *dev) return 512; } +static unsigned int ilk_plane_wm_reg_max(const struct drm_device *dev, + int level, bool is_sprite) +{ + if (INTEL_INFO(dev)->gen >= 8) + /* BDW primary/sprite plane watermarks */ + return level == 0 ? 255 : 2047; + else if (INTEL_INFO(dev)->gen >= 7) + /* IVB/HSW primary/sprite plane watermarks */ + return level == 0 ? 127 : 1023; + else if (!is_sprite) + /* ILK/SNB primary plane watermarks */ + return level == 0 ? 127 : 511; + else + /* ILK/SNB sprite plane watermarks */ + return level == 0 ? 63 : 255; +} + +static unsigned int ilk_cursor_wm_reg_max(const struct drm_device *dev, + int level) +{ + if (INTEL_INFO(dev)->gen >= 7) + return level == 0 ? 63 : 255; + else + return level == 0 ? 31 : 63; +} + +static unsigned int ilk_fbc_wm_reg_max(const struct drm_device *dev) +{ + if (INTEL_INFO(dev)->gen >= 8) + return 31; + else + return 15; +} + /* Calculate the maximum primary/sprite plane watermark */ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, int level, @@ -1839,7 +1873,6 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, bool is_sprite) { unsigned int fifo_size = ilk_display_fifo_size(dev); - unsigned int max; /* if sprites aren't enabled, sprites get nothing */ if (is_sprite && !config->sprites_enabled) @@ -1870,19 +1903,7 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, } /* clamp to max that the registers can hold */ - if (INTEL_INFO(dev)->gen >= 8) - max = level == 0 ? 255 : 2047; - else if (INTEL_INFO(dev)->gen >= 7) - /* IVB/HSW primary/sprite plane watermarks */ - max = level == 0 ? 127 : 1023; - else if (!is_sprite) - /* ILK/SNB primary plane watermarks */ - max = level == 0 ? 127 : 511; - else - /* ILK/SNB sprite plane watermarks */ - max = level == 0 ? 63 : 255; - - return min(fifo_size, max); + return min(fifo_size, ilk_plane_wm_reg_max(dev, level, is_sprite)); } /* Calculate the maximum cursor plane watermark */ @@ -1895,20 +1916,7 @@ static unsigned int ilk_cursor_wm_max(const struct drm_device *dev, return 64; /* otherwise just report max that registers can hold */ - if (INTEL_INFO(dev)->gen >= 7) - return level == 0 ? 63 : 255; - else - return level == 0 ? 31 : 63; -} - -/* Calculate the maximum FBC watermark */ -static unsigned int ilk_fbc_wm_max(const struct drm_device *dev) -{ - /* max that registers can hold */ - if (INTEL_INFO(dev)->gen >= 8) - return 31; - else - return 15; + return ilk_cursor_wm_reg_max(dev, level); } static void ilk_compute_wm_maximums(const struct drm_device *dev, @@ -1920,7 +1928,17 @@ static void ilk_compute_wm_maximums(const struct drm_device *dev, max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false); max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true); max->cur = ilk_cursor_wm_max(dev, level, config); - max->fbc = ilk_fbc_wm_max(dev); + max->fbc = ilk_fbc_wm_reg_max(dev); +} + +static void ilk_compute_wm_reg_maximums(struct drm_device *dev, + int level, + struct ilk_wm_maximums *max) +{ + max->pri = ilk_plane_wm_reg_max(dev, level, false); + max->spr = ilk_plane_wm_reg_max(dev, level, true); + max->cur = ilk_cursor_wm_reg_max(dev, level); + max->fbc = ilk_fbc_wm_reg_max(dev); } static bool ilk_validate_wm_level(int level, @@ -2059,7 +2077,7 @@ static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5]) wm[3] *= 2; } -static int ilk_wm_max_level(const struct drm_device *dev) +int ilk_wm_max_level(const struct drm_device *dev) { /* how many WM levels are we expecting */ if (IS_HASWELL(dev) || IS_BROADWELL(dev)) @@ -2155,38 +2173,52 @@ static void ilk_setup_wm_latency(struct drm_device *dev) } static void ilk_compute_wm_parameters(struct drm_crtc *crtc, - struct ilk_pipe_wm_parameters *p, - struct intel_wm_config *config) + struct ilk_pipe_wm_parameters *p) { struct drm_device *dev = crtc->dev; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum pipe pipe = intel_crtc->pipe; struct drm_plane *plane; - p->active = intel_crtc_active(crtc); - if (p->active) { - p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal; - p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc); - p->pri.bytes_per_pixel = crtc->primary->fb->bits_per_pixel / 8; - p->cur.bytes_per_pixel = 4; - p->pri.horiz_pixels = intel_crtc->config.pipe_src_w; - p->cur.horiz_pixels = intel_crtc->cursor_width; - /* TODO: for now, assume primary and cursor planes are always enabled. */ - p->pri.enabled = true; - p->cur.enabled = true; - } + if (!intel_crtc_active(crtc)) + return; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - config->num_pipes_active += intel_crtc_active(crtc); + p->active = true; + p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal; + p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc); + p->pri.bytes_per_pixel = crtc->primary->fb->bits_per_pixel / 8; + p->cur.bytes_per_pixel = 4; + p->pri.horiz_pixels = intel_crtc->config.pipe_src_w; + p->cur.horiz_pixels = intel_crtc->cursor_width; + /* TODO: for now, assume primary and cursor planes are always enabled. */ + p->pri.enabled = true; + p->cur.enabled = true; drm_for_each_legacy_plane(plane, &dev->mode_config.plane_list) { struct intel_plane *intel_plane = to_intel_plane(plane); - if (intel_plane->pipe == pipe) + if (intel_plane->pipe == pipe) { p->spr = intel_plane->wm; + break; + } + } +} + +static void ilk_compute_wm_config(struct drm_device *dev, + struct intel_wm_config *config) +{ + struct intel_crtc *intel_crtc; - config->sprites_enabled |= intel_plane->wm.enabled; - config->sprites_scaled |= intel_plane->wm.scaled; + /* Compute the currently _active_ config */ + for_each_intel_crtc(dev, intel_crtc) { + const struct intel_pipe_wm *wm = &intel_crtc->wm.active; + + if (!wm->pipe_enabled) + continue; + + config->sprites_enabled |= wm->sprites_enabled; + config->sprites_scaled |= wm->sprites_scaled; + config->num_pipes_active++; } } @@ -2206,8 +2238,9 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc, }; struct ilk_wm_maximums max; - /* LP0 watermarks always use 1/2 DDB partitioning */ - ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); + pipe_wm->pipe_enabled = params->active; + pipe_wm->sprites_enabled = params->spr.enabled; + pipe_wm->sprites_scaled = params->spr.scaled; /* ILK/SNB: LP2+ watermarks only w/o sprites */ if (INTEL_INFO(dev)->gen <= 6 && params->spr.enabled) @@ -2217,15 +2250,37 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc, if (params->spr.scaled) max_level = 0; - for (level = 0; level <= max_level; level++) - ilk_compute_wm_level(dev_priv, level, params, - &pipe_wm->wm[level]); + ilk_compute_wm_level(dev_priv, 0, params, &pipe_wm->wm[0]); if (IS_HASWELL(dev) || IS_BROADWELL(dev)) pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc); + /* LP0 watermarks always use 1/2 DDB partitioning */ + ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); + /* At least LP0 must be valid */ - return ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]); + if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) + return false; + + ilk_compute_wm_reg_maximums(dev, 1, &max); + + for (level = 1; level <= max_level; level++) { + struct intel_wm_level wm = {}; + + ilk_compute_wm_level(dev_priv, level, params, &wm); + + /* + * Disable any watermark level that exceeds the + * register maximums since such watermarks are + * always invalid. + */ + if (!ilk_validate_wm_level(level, &max, &wm)) + break; + + pipe_wm->wm[level] = wm; + } + + return true; } /* @@ -2237,20 +2292,28 @@ static void ilk_merge_wm_level(struct drm_device *dev, { const struct intel_crtc *intel_crtc; - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { - const struct intel_wm_level *wm = - &intel_crtc->wm.active.wm[level]; + ret_wm->enable = true; + + for_each_intel_crtc(dev, intel_crtc) { + const struct intel_pipe_wm *active = &intel_crtc->wm.active; + const struct intel_wm_level *wm = &active->wm[level]; + + if (!active->pipe_enabled) + continue; + /* + * The watermark values may have been used in the past, + * so we must maintain them in the registers for some + * time even if the level is now disabled. + */ if (!wm->enable) - return; + ret_wm->enable = false; ret_wm->pri_val = max(ret_wm->pri_val, wm->pri_val); ret_wm->spr_val = max(ret_wm->spr_val, wm->spr_val); ret_wm->cur_val = max(ret_wm->cur_val, wm->cur_val); ret_wm->fbc_val = max(ret_wm->fbc_val, wm->fbc_val); } - - ret_wm->enable = true; } /* @@ -2262,6 +2325,7 @@ static void ilk_wm_merge(struct drm_device *dev, struct intel_pipe_wm *merged) { int level, max_level = ilk_wm_max_level(dev); + int last_enabled_level = max_level; /* ILK/SNB/IVB: LP1+ watermarks only w/ single pipe */ if ((INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev)) && @@ -2277,15 +2341,19 @@ static void ilk_wm_merge(struct drm_device *dev, ilk_merge_wm_level(dev, level, wm); - if (!ilk_validate_wm_level(level, max, wm)) - break; + if (level > last_enabled_level) + wm->enable = false; + else if (!ilk_validate_wm_level(level, max, wm)) + /* make sure all following levels get disabled */ + last_enabled_level = level - 1; /* * The spec says it is preferred to disable * FBC WMs instead of disabling a WM level. */ if (wm->fbc_val > max->fbc) { - merged->fbc_wm_enabled = false; + if (wm->enable) + merged->fbc_wm_enabled = false; wm->fbc_val = 0; } } @@ -2340,14 +2408,19 @@ static void ilk_compute_wm_results(struct drm_device *dev, level = ilk_wm_lp_to_level(wm_lp, merged); r = &merged->wm[level]; - if (!r->enable) - break; - results->wm_lp[wm_lp - 1] = WM3_LP_EN | + /* + * Maintain the watermark values even if the level is + * disabled. Doing otherwise could cause underruns. + */ + results->wm_lp[wm_lp - 1] = (ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) | (r->pri_val << WM1_LP_SR_SHIFT) | r->cur_val; + if (r->enable) + results->wm_lp[wm_lp - 1] |= WM1_LP_SR_EN; + if (INTEL_INFO(dev)->gen >= 8) results->wm_lp[wm_lp - 1] |= r->fbc_val << WM1_LP_FBC_SHIFT_BDW; @@ -2355,6 +2428,10 @@ static void ilk_compute_wm_results(struct drm_device *dev, results->wm_lp[wm_lp - 1] |= r->fbc_val << WM1_LP_FBC_SHIFT; + /* + * Always set WM1S_LP_EN when spr_val != 0, even if the + * level is disabled. Doing otherwise could cause underruns. + */ if (INTEL_INFO(dev)->gen <= 6 && r->spr_val) { WARN_ON(wm_lp != 1); results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val; @@ -2363,7 +2440,7 @@ static void ilk_compute_wm_results(struct drm_device *dev, } /* LP0 register values */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, intel_crtc) { enum pipe pipe = intel_crtc->pipe; const struct intel_wm_level *r = &intel_crtc->wm.active.wm[0]; @@ -2598,7 +2675,7 @@ static void ilk_update_wm(struct drm_crtc *crtc) struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct intel_wm_config config = {}; - ilk_compute_wm_parameters(crtc, ¶ms, &config); + ilk_compute_wm_parameters(crtc, ¶ms); intel_compute_pipe_wm(crtc, ¶ms, &pipe_wm); @@ -2607,6 +2684,8 @@ static void ilk_update_wm(struct drm_crtc *crtc) intel_crtc->wm.active = pipe_wm; + ilk_compute_wm_config(dev, &config); + ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max); ilk_wm_merge(dev, &config, &max, &lp_wm_1_2); @@ -2673,7 +2752,9 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe)); - if (intel_crtc_active(crtc)) { + active->pipe_enabled = intel_crtc_active(crtc); + + if (active->pipe_enabled) { u32 tmp = hw->wm_pipe[pipe]; /* @@ -2706,7 +2787,7 @@ void ilk_wm_get_hw_state(struct drm_device *dev) struct ilk_wm_values *hw = &dev_priv->wm.hw; struct drm_crtc *crtc; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + for_each_crtc(dev, crtc) ilk_pipe_wm_get_hw_state(crtc); hw->wm_lp[0] = I915_READ(WM1_LP_ILK); @@ -2714,8 +2795,10 @@ void ilk_wm_get_hw_state(struct drm_device *dev) hw->wm_lp[2] = I915_READ(WM3_LP_ILK); hw->wm_lp_spr[0] = I915_READ(WM1S_LP_ILK); - hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB); - hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB); + if (INTEL_INFO(dev)->gen >= 7) { + hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB); + hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB); + } if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hw->partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ? @@ -3071,6 +3154,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev)) mask |= GEN6_PM_RP_UP_EI_EXPIRED; + if (IS_GEN8(dev_priv->dev)) + mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP; + return ~mask; } @@ -3091,7 +3177,7 @@ 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 @@ -3134,16 +3220,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) /* Mask turbo interrupt so that they will not come in between */ I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); - /* Bring up the Gfx clock */ - I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, - I915_READ(VLV_GTLC_SURVIVABILITY_REG) | - VLV_GFX_CLK_FORCE_ON_BIT); - - if (wait_for(((VLV_GFX_CLK_STATUS_BIT & - I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 5)) { - DRM_ERROR("GFX_CLK_ON request timed out\n"); - return; - } + vlv_force_gfx_clock(dev_priv, true); dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit; @@ -3154,10 +3231,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) & GENFREQSTATUS) == 0, 5)) DRM_ERROR("timed out waiting for Punit\n"); - /* Release the Gfx clock */ - I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, - I915_READ(VLV_GTLC_SURVIVABILITY_REG) & - ~VLV_GFX_CLK_FORCE_ON_BIT); + vlv_force_gfx_clock(dev_priv, false); I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq)); @@ -3215,6 +3289,26 @@ void valleyview_set_rps(struct drm_device *dev, u8 val) trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val)); } +static void gen8_disable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP); + I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) & + ~dev_priv->pm_rps_events); + /* Complete PM interrupt masking here doesn't race with the rps work + * item again unmasking PM interrupts because that is using a different + * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in + * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which + * gen8_enable_rps will clean up. */ + + spin_lock_irq(&dev_priv->irq_lock); + dev_priv->rps.pm_iir = 0; + spin_unlock_irq(&dev_priv->irq_lock); + + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events); +} + static void gen6_disable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3241,7 +3335,10 @@ static void gen6_disable_rps(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); I915_WRITE(GEN6_RPNSWREQ, 1 << 31); - gen6_disable_rps_interrupts(dev); + if (IS_BROADWELL(dev)) + gen8_disable_rps_interrupts(dev); + else + gen6_disable_rps_interrupts(dev); } static void valleyview_disable_rps(struct drm_device *dev) @@ -3255,21 +3352,44 @@ static void valleyview_disable_rps(struct drm_device *dev) static void intel_print_rc6_info(struct drm_device *dev, u32 mode) { + if (IS_VALLEYVIEW(dev)) { + if (mode & (GEN7_RC_CTL_TO_MODE | GEN6_RC_CTL_EI_MODE(1))) + mode = GEN6_RC_CTL_RC6_ENABLE; + else + mode = 0; + } DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n", (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off", (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off", (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off"); } -int intel_enable_rc6(const struct drm_device *dev) +static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) { /* No RC6 before Ironlake */ if (INTEL_INFO(dev)->gen < 5) return 0; + /* RC6 is only on Ironlake mobile not on desktop */ + if (INTEL_INFO(dev)->gen == 5 && !IS_IRONLAKE_M(dev)) + return 0; + /* Respect the kernel parameter if it is set */ - if (i915.enable_rc6 >= 0) - return i915.enable_rc6; + if (enable_rc6 >= 0) { + int mask; + + if (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev)) + mask = INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE | + INTEL_RC6pp_ENABLE; + else + mask = INTEL_RC6_ENABLE; + + if ((enable_rc6 & mask) != enable_rc6) + DRM_INFO("Adjusting RC6 mask to %d (requested %d, valid %d)\n", + enable_rc6 & mask, enable_rc6, mask); + + return enable_rc6 & mask; + } /* Disable RC6 on Ironlake */ if (INTEL_INFO(dev)->gen == 5) @@ -3281,6 +3401,22 @@ int intel_enable_rc6(const struct drm_device *dev) return INTEL_RC6_ENABLE; } +int intel_enable_rc6(const struct drm_device *dev) +{ + return i915.enable_rc6; +} + +static void gen8_enable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + spin_lock_irq(&dev_priv->irq_lock); + WARN_ON(dev_priv->rps.pm_iir); + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events); + spin_unlock_irq(&dev_priv->irq_lock); +} + static void gen6_enable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3292,10 +3428,31 @@ 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; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t rc6_mask = 0, rp_state_cap; int unused; @@ -3310,6 +3467,7 @@ 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); @@ -3329,8 +3487,10 @@ 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 */ @@ -3346,11 +3506,15 @@ static void gen8_enable_rps(struct drm_device *dev) I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10); + /* WaDisablePwrmtrEvent:chv (pre-production hw) */ + I915_WRITE(0xA80C, I915_READ(0xA80C) & 0x00ffffff); + I915_WRITE(0xA810, I915_READ(0xA810) & 0xffffff00); + /* 5: Enable RPS */ I915_WRITE(GEN6_RP_CONTROL, GEN6_RP_MEDIA_TURBO | GEN6_RP_MEDIA_HW_NORMAL_MODE | - GEN6_RP_MEDIA_IS_GFX | + GEN6_RP_MEDIA_IS_GFX | /* WaSetMaskForGfxBusyness:chv (pre-production hw ?) */ GEN6_RP_ENABLE | GEN6_RP_UP_BUSY_AVG | GEN6_RP_DOWN_IDLE_AVG); @@ -3359,7 +3523,7 @@ static void gen8_enable_rps(struct drm_device *dev) gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8); - gen6_enable_rps_interrupts(dev); + gen8_enable_rps_interrupts(dev); gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); } @@ -3367,7 +3531,7 @@ static void gen8_enable_rps(struct drm_device *dev) static void gen6_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; u32 rp_state_cap; u32 gt_perf_status; u32 rc6vids, pcu_mbox = 0, rc6_mask = 0; @@ -3396,23 +3560,7 @@ 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); @@ -3494,7 +3642,7 @@ static void gen6_enable_rps(struct drm_device *dev) gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); } -void gen6_update_ring_freq(struct drm_device *dev) +static void __gen6_update_ring_freq(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; int min_freq = 15; @@ -3564,6 +3712,18 @@ void gen6_update_ring_freq(struct drm_device *dev) } } +void gen6_update_ring_freq(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen < 6 || IS_VALLEYVIEW(dev)) + return; + + mutex_lock(&dev_priv->rps.hw_lock); + __gen6_update_ring_freq(dev); + mutex_unlock(&dev_priv->rps.hw_lock); +} + int valleyview_rps_max_freq(struct drm_i915_private *dev_priv) { u32 val, rp0; @@ -3658,10 +3818,49 @@ static void valleyview_cleanup_pctx(struct drm_device *dev) dev_priv->vlv_pctx = NULL; } +static void valleyview_init_gt_powersave(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + valleyview_setup_pctx(dev); + + mutex_lock(&dev_priv->rps.hw_lock); + + dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv); + dev_priv->rps.rp0_freq = dev_priv->rps.max_freq; + DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n", + vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq), + dev_priv->rps.max_freq); + + dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv); + DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n", + vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq), + dev_priv->rps.efficient_freq); + + dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv); + DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n", + vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq), + dev_priv->rps.min_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; + + mutex_unlock(&dev_priv->rps.hw_lock); +} + +static void valleyview_cleanup_gt_powersave(struct drm_device *dev) +{ + valleyview_cleanup_pctx(dev); +} + static void valleyview_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; u32 gtfifodbg, val, rc6_mode = 0; int i; @@ -3724,29 +3923,6 @@ static void valleyview_enable_rps(struct drm_device *dev) vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq), dev_priv->rps.cur_freq); - dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv); - dev_priv->rps.rp0_freq = dev_priv->rps.max_freq; - DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n", - vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq), - dev_priv->rps.max_freq); - - dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv); - DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n", - vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq), - dev_priv->rps.efficient_freq); - - dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv); - DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n", - vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq), - dev_priv->rps.min_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; - DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n", vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq), dev_priv->rps.efficient_freq); @@ -3815,7 +3991,7 @@ static int ironlake_setup_rc6(struct drm_device *dev) static void ironlake_enable_rc6(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; bool was_interruptible; int ret; @@ -3873,7 +4049,7 @@ static void ironlake_enable_rc6(struct drm_device *dev) I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN); I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); - intel_print_rc6_info(dev, INTEL_RC6_ENABLE); + intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE); } static unsigned long intel_pxfreq(u32 vidfreq) @@ -4327,7 +4503,7 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower); bool i915_gpu_busy(void) { struct drm_i915_private *dev_priv; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; bool ret = false; int i; @@ -4487,14 +4663,16 @@ static void intel_init_emon(struct drm_device *dev) void intel_init_gt_powersave(struct drm_device *dev) { + i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6); + if (IS_VALLEYVIEW(dev)) - valleyview_setup_pctx(dev); + valleyview_init_gt_powersave(dev); } void intel_cleanup_gt_powersave(struct drm_device *dev) { if (IS_VALLEYVIEW(dev)) - valleyview_cleanup_pctx(dev); + valleyview_cleanup_gt_powersave(dev); } void intel_disable_gt_powersave(struct drm_device *dev) @@ -4507,8 +4685,10 @@ void intel_disable_gt_powersave(struct drm_device *dev) if (IS_IRONLAKE_M(dev)) { ironlake_disable_drps(dev); ironlake_disable_rc6(dev); - } else if (INTEL_INFO(dev)->gen >= 6) { - cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work); + } else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) { + if (cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work)) + intel_runtime_pm_put(dev_priv); + cancel_work_sync(&dev_priv->rps.work); mutex_lock(&dev_priv->rps.hw_lock); if (IS_VALLEYVIEW(dev)) @@ -4533,13 +4713,15 @@ static void intel_gen6_powersave_work(struct work_struct *work) valleyview_enable_rps(dev); } else if (IS_BROADWELL(dev)) { gen8_enable_rps(dev); - gen6_update_ring_freq(dev); + __gen6_update_ring_freq(dev); } else { gen6_enable_rps(dev); - gen6_update_ring_freq(dev); + __gen6_update_ring_freq(dev); } dev_priv->rps.enabled = true; mutex_unlock(&dev_priv->rps.hw_lock); + + intel_runtime_pm_put(dev_priv); } void intel_enable_gt_powersave(struct drm_device *dev) @@ -4547,20 +4729,38 @@ void intel_enable_gt_powersave(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; if (IS_IRONLAKE_M(dev)) { + mutex_lock(&dev->struct_mutex); ironlake_enable_drps(dev); ironlake_enable_rc6(dev); intel_init_emon(dev); - } else if (IS_GEN6(dev) || IS_GEN7(dev)) { + mutex_unlock(&dev->struct_mutex); + } else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) { /* * PCU communication is slow and this doesn't need to be * done at any specific time, so do this out of our fast path * to make resume and init faster. + * + * We depend on the HW RC6 power context save/restore + * mechanism when entering D3 through runtime PM suspend. So + * disable RPM until RPS/RC6 is properly setup. We can only + * get here via the driver load/system resume/runtime resume + * paths, so the _noresume version is enough (and in case of + * runtime resume it's necessary). */ - schedule_delayed_work(&dev_priv->rps.delayed_resume_work, - round_jiffies_up_relative(HZ)); + if (schedule_delayed_work(&dev_priv->rps.delayed_resume_work, + round_jiffies_up_relative(HZ))) + intel_runtime_pm_get_noresume(dev_priv); } } +void intel_reset_gt_powersave(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + dev_priv->rps.enabled = false; + intel_enable_gt_powersave(dev); +} + static void ibx_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -4666,6 +4866,9 @@ static void ironlake_init_clock_gating(struct drm_device *dev) I915_WRITE(CACHE_MODE_0, _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE)); + /* WaDisable_RenderCache_OperationalFlush:ilk */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + g4x_disable_trickle_feed(dev); ibx_init_clock_gating(dev); @@ -4741,6 +4944,9 @@ static void gen6_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE)); + /* WaDisable_RenderCache_OperationalFlush:snb */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* * BSpec recoomends 8x4 when MSAA is used, * however in practice 16x4 seems fastest. @@ -4909,6 +5115,10 @@ static void gen8_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN7_HALF_SLICE_CHICKEN1, _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE)); + /* WaDisableDopClockGating:bdw May not be needed for production */ + I915_WRITE(GEN7_ROW_CHICKEN2, + _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); + /* WaSwitchSolVfFArbitrationPriority:bdw */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL); @@ -4980,6 +5190,9 @@ static void haswell_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN7_FF_THREAD_MODE, I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME); + /* WaDisable_RenderCache_OperationalFlush:hsw */ + I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* enable HiZ Raw Stall Optimization */ I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE)); @@ -5032,6 +5245,9 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN7_HALF_SLICE_CHICKEN1, _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE)); + /* WaDisable_RenderCache_OperationalFlush:ivb */ + I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */ I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1, GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC); @@ -5126,6 +5342,10 @@ 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 */ @@ -5143,6 +5363,9 @@ static void valleyview_init_clock_gating(struct drm_device *dev) _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP | GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE)); + /* WaDisable_RenderCache_OperationalFlush:vlv */ + I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* WaForceL3Serialization:vlv */ I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) & ~L3SQ_URB_READ_CAM_MATCH_DISABLE); @@ -5165,8 +5388,11 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN6_UCGCTL2, GEN6_RCZUNIT_CLOCK_GATE_DISABLE); - /* WaDisableL3Bank2xClockGate:vlv */ - I915_WRITE(GEN7_UCGCTL4, GEN7_L3BANK2X_CLOCK_GATE_DISABLE); + /* WaDisableL3Bank2xClockGate:vlv + * Disabling L3 clock gating- MMIO 940c[25] = 1 + * Set bit 25, to disable L3_BANK_2x_CLK_GATING */ + I915_WRITE(GEN7_UCGCTL4, + I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE); I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE); @@ -5191,6 +5417,59 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_WRITE(VLV_GUNIT_CLOCK_GATE, GCFG_DIS); } +static void cherryview_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE); + + I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE); + + /* WaDisablePartialInstShootdown:chv */ + I915_WRITE(GEN8_ROW_CHICKEN, + _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE)); + + /* WaDisableThreadStallDopClockGating:chv */ + I915_WRITE(GEN8_ROW_CHICKEN, + _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE)); + + /* WaVSRefCountFullforceMissDisable:chv */ + /* WaDSRefCountFullforceMissDisable:chv */ + I915_WRITE(GEN7_FF_THREAD_MODE, + I915_READ(GEN7_FF_THREAD_MODE) & + ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME)); + + /* WaDisableSemaphoreAndSyncFlipWait:chv */ + I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL, + _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE)); + + /* WaDisableCSUnitClockGating:chv */ + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_CSUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSDEUnitClockGating:chv */ + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSamplerPowerBypass:chv (pre-production hw) */ + I915_WRITE(HALF_SLICE_CHICKEN3, + _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS)); + + /* WaDisableGunitClockGating:chv (pre-production hw) */ + I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) | + GINT_DIS); + + /* WaDisableFfDopClockGating:chv (pre-production hw) */ + I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL, + _MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE)); + + /* WaDisableDopClockGating:chv (pre-production hw) */ + I915_WRITE(GEN7_ROW_CHICKEN2, + _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE); +} + static void g4x_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -5212,6 +5491,9 @@ static void g4x_init_clock_gating(struct drm_device *dev) I915_WRITE(CACHE_MODE_0, _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE)); + /* WaDisable_RenderCache_OperationalFlush:g4x */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + g4x_disable_trickle_feed(dev); } @@ -5226,6 +5508,9 @@ static void crestline_init_clock_gating(struct drm_device *dev) I915_WRITE16(DEUC, 0); I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE)); + + /* WaDisable_RenderCache_OperationalFlush:gen4 */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); } static void broadwater_init_clock_gating(struct drm_device *dev) @@ -5240,6 +5525,9 @@ static void broadwater_init_clock_gating(struct drm_device *dev) I915_WRITE(RENCLK_GATE_D2, 0); I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE)); + + /* WaDisable_RenderCache_OperationalFlush:gen4 */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); } static void gen3_init_clock_gating(struct drm_device *dev) @@ -5256,6 +5544,12 @@ static void gen3_init_clock_gating(struct drm_device *dev) /* IIR "flip pending" means done if this bit is set */ I915_WRITE(ECOSKPD, _MASKED_BIT_DISABLE(ECO_FLIP_DONE)); + + /* interrupts should cause a wake up from C3 */ + I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_AGPBUSY_INT_EN)); + + /* On GEN3 we really need to make sure the ARB C3 LP bit is set */ + I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE)); } static void i85x_init_clock_gating(struct drm_device *dev) @@ -5263,6 +5557,10 @@ static void i85x_init_clock_gating(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; I915_WRITE(RENCLK_GATE_D1, SV_CLOCK_GATE_DISABLE); + + /* interrupts should cause a wake up from C3 */ + I915_WRITE(MI_STATE, _MASKED_BIT_ENABLE(MI_AGPBUSY_INT_EN) | + _MASKED_BIT_DISABLE(MI_AGPBUSY_830_MODE)); } static void i830_init_clock_gating(struct drm_device *dev) @@ -5314,10 +5612,25 @@ bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { struct i915_power_domains *power_domains; + struct i915_power_well *power_well; + bool is_enabled; + int i; + + if (dev_priv->pm.suspended) + return false; power_domains = &dev_priv->power_domains; + is_enabled = true; + for_each_power_well_rev(i, power_well, BIT(domain), power_domains) { + if (power_well->always_on) + continue; - return power_domains->domain_use_count[domain]; + if (!power_well->count) { + is_enabled = false; + break; + } + } + return is_enabled; } bool intel_display_power_enabled(struct drm_i915_private *dev_priv, @@ -5392,33 +5705,6 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv) } } -static void reset_vblank_counter(struct drm_device *dev, enum pipe pipe) -{ - assert_spin_locked(&dev->vbl_lock); - - dev->vblank[pipe].last = 0; -} - -static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv) -{ - struct drm_device *dev = dev_priv->dev; - enum pipe pipe; - unsigned long irqflags; - - /* - * After this, the registers on the pipes that are part of the power - * well will become zero, so we have to adjust our counters according to - * that. - * - * FIXME: Should we do this in general in drm_vblank_post_modeset? - */ - spin_lock_irqsave(&dev->vbl_lock, irqflags); - for_each_pipe(pipe) - if (pipe != PIPE_A) - reset_vblank_counter(dev, pipe); - spin_unlock_irqrestore(&dev->vbl_lock, irqflags); -} - static void hsw_set_power_well(struct drm_i915_private *dev_priv, struct i915_power_well *power_well, bool enable) { @@ -5447,8 +5733,6 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv, I915_WRITE(HSW_PWR_WELL_DRIVER, 0); POSTING_READ(HSW_PWR_WELL_DRIVER); DRM_DEBUG_KMS("Requesting to disable the power well\n"); - - hsw_power_well_post_disable(dev_priv); } } } @@ -5489,13 +5773,34 @@ static bool i9xx_always_on_power_well_enabled(struct drm_i915_private *dev_priv, return true; } -static void vlv_set_power_well(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well, bool enable) +void __vlv_set_power_well(struct drm_i915_private *dev_priv, + enum punit_power_well power_well_id, bool enable) { - enum punit_power_well power_well_id = power_well->data; + struct drm_device *dev = dev_priv->dev; u32 mask; u32 state; u32 ctrl; + enum pipe pipe; + + if (power_well_id == PUNIT_POWER_WELL_DPIO_CMN_BC) { + if (enable) { + /* + * Enable the CRI clock source so we can get at the + * display and the reference clock for VGA + * hotplug / manual detection. + */ + I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | + DPLL_REFA_CLK_ENABLE_VLV | + DPLL_INTEGRATED_CRI_CLK_VLV); + udelay(1); /* >10ns for cmnreset, >0ns for sidereset */ + } else { + for_each_pipe(pipe) + assert_pll_disabled(dev_priv, pipe); + /* Assert common reset */ + I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) & + ~DPIO_CMNRST); + } + } mask = PUNIT_PWRGT_MASK(power_well_id); state = enable ? PUNIT_PWRGT_PWR_ON(power_well_id) : @@ -5523,6 +5828,28 @@ static void vlv_set_power_well(struct drm_i915_private *dev_priv, out: mutex_unlock(&dev_priv->rps.hw_lock); + + /* + * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx - + * 6. De-assert cmn_reset/side_reset. Same as VLV X0. + * a. GUnit 0x2110 bit[0] set to 1 (def 0) + * b. The other bits such as sfr settings / modesel may all + * be set to 0. + * + * This should only be done on init and resume from S3 with + * both PLLs disabled, or we risk losing DPIO and PLL + * synchronization. + */ + if (power_well_id == PUNIT_POWER_WELL_DPIO_CMN_BC && enable) + I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST); +} + +static void vlv_set_power_well(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well, bool enable) +{ + enum punit_power_well power_well_id = power_well->data; + + __vlv_set_power_well(dev_priv, power_well_id, enable); } static void vlv_power_well_sync_hw(struct drm_i915_private *dev_priv, @@ -5591,11 +5918,13 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv, spin_unlock_irq(&dev_priv->irq_lock); /* - * During driver initialization we need to defer enabling hotplug - * processing until fbdev is set up. + * During driver initialization/resume we can avoid restoring the + * part of the HW/SW state that will be inited anyway explicitly. */ - if (dev_priv->enable_hotplug_processing) - intel_hpd_init(dev_priv->dev); + if (dev_priv->power_domains.initializing) + return; + + intel_hpd_init(dev_priv->dev); i915_redisable_vga_power_on(dev_priv->dev); } @@ -5603,23 +5932,12 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv, static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - struct drm_device *dev = dev_priv->dev; - enum pipe pipe; - WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D); spin_lock_irq(&dev_priv->irq_lock); - for_each_pipe(pipe) - __intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); - valleyview_disable_display_irqs(dev_priv); spin_unlock_irq(&dev_priv->irq_lock); - spin_lock_irq(&dev->vbl_lock); - for_each_pipe(pipe) - reset_vblank_counter(dev, pipe); - spin_unlock_irq(&dev->vbl_lock); - vlv_set_power_well(dev_priv, power_well, false); } @@ -5867,12 +6185,6 @@ static struct i915_power_well vlv_power_wells[] = { .ops = &vlv_display_power_well_ops, }, { - .name = "dpio-common", - .domains = VLV_DPIO_CMN_BC_POWER_DOMAINS, - .data = PUNIT_POWER_WELL_DPIO_CMN_BC, - .ops = &vlv_dpio_power_well_ops, - }, - { .name = "dpio-tx-b-01", .domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS | VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS | @@ -5908,6 +6220,12 @@ static struct i915_power_well vlv_power_wells[] = { .ops = &vlv_dpio_power_well_ops, .data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_23, }, + { + .name = "dpio-common", + .domains = VLV_DPIO_CMN_BC_POWER_DOMAINS, + .data = PUNIT_POWER_WELL_DPIO_CMN_BC, + .ops = &vlv_dpio_power_well_ops, + }, }; #define set_power_wells(power_domains, __power_wells) ({ \ @@ -5959,9 +6277,13 @@ static void intel_power_domains_resume(struct drm_i915_private *dev_priv) void intel_power_domains_init_hw(struct drm_i915_private *dev_priv) { + struct i915_power_domains *power_domains = &dev_priv->power_domains; + + power_domains->initializing = true; /* For now, we need the power well to be always enabled. */ intel_display_set_init_power(dev_priv, true); intel_power_domains_resume(dev_priv); + power_domains->initializing = false; } void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv) @@ -5986,6 +6308,18 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv) WARN(dev_priv->pm.suspended, "Device still suspended.\n"); } +void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct device *device = &dev->pdev->dev; + + if (!HAS_RUNTIME_PM(dev)) + return; + + WARN(dev_priv->pm.suspended, "Getting nosync-ref while suspended.\n"); + pm_runtime_get_noresume(device); +} + void intel_runtime_pm_put(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -6008,6 +6342,15 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv) pm_runtime_set_active(device); + /* + * RPM depends on RC6 to save restore the GT HW context, so make RC6 a + * requirement. + */ + if (!intel_enable_rc6(dev)) { + DRM_INFO("RC6 disabled, disabling runtime PM support\n"); + return; + } + pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */ pm_runtime_mark_last_busy(device); pm_runtime_use_autosuspend(device); @@ -6023,6 +6366,9 @@ void intel_fini_runtime_pm(struct drm_i915_private *dev_priv) if (!HAS_RUNTIME_PM(dev)) return; + if (!intel_enable_rc6(dev)) + return; + /* Make sure we're not suspended first. */ pm_runtime_get_sync(device); pm_runtime_disable(device); @@ -6087,6 +6433,10 @@ void intel_init_pm(struct drm_device *dev) dev_priv->display.init_clock_gating = haswell_init_clock_gating; else if (INTEL_INFO(dev)->gen == 8) dev_priv->display.init_clock_gating = gen8_init_clock_gating; + } else if (IS_CHERRYVIEW(dev)) { + dev_priv->display.update_wm = valleyview_update_wm; + dev_priv->display.init_clock_gating = + cherryview_init_clock_gating; } else if (IS_VALLEYVIEW(dev)) { dev_priv->display.update_wm = valleyview_update_wm; dev_priv->display.init_clock_gating = diff --git a/drivers/gpu/drm/i915/intel_renderstate.h b/drivers/gpu/drm/i915/intel_renderstate.h new file mode 100644 index 000000000000..a5e783a9928a --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate.h @@ -0,0 +1,48 @@ +/* + * 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. + */ + +#ifndef _INTEL_RENDERSTATE_H +#define _INTEL_RENDERSTATE_H + +#include <linux/types.h> + +struct intel_renderstate_rodata { + const u32 *reloc; + const u32 reloc_items; + const u32 *batch; + const u32 batch_items; +}; + +extern const struct intel_renderstate_rodata gen6_null_state; +extern const struct intel_renderstate_rodata gen7_null_state; +extern const struct intel_renderstate_rodata gen8_null_state; + +#define RO_RENDERSTATE(_g) \ + const struct intel_renderstate_rodata gen ## _g ## _null_state = { \ + .reloc = gen ## _g ## _null_state_relocs, \ + .reloc_items = sizeof(gen ## _g ## _null_state_relocs)/4, \ + .batch = gen ## _g ## _null_state_batch, \ + .batch_items = sizeof(gen ## _g ## _null_state_batch)/4, \ + } + +#endif /* INTEL_RENDERSTATE_H */ diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen6.c b/drivers/gpu/drm/i915/intel_renderstate_gen6.c new file mode 100644 index 000000000000..740538ad0977 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate_gen6.c @@ -0,0 +1,289 @@ +#include "intel_renderstate.h" + +static const u32 gen6_null_state_relocs[] = { + 0x00000020, + 0x00000024, + 0x0000002c, + 0x000001e0, + 0x000001e4, +}; + +static const u32 gen6_null_state_batch[] = { + 0x69040000, + 0x790d0001, + 0x00000000, + 0x00000000, + 0x78180000, + 0x00000001, + 0x61010008, + 0x00000000, + 0x00000001, /* reloc */ + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000001, + 0x61020000, + 0x00000000, + 0x78050001, + 0x00000018, + 0x00000000, + 0x780d1002, + 0x00000000, + 0x00000000, + 0x00000420, + 0x78150003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78100004, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78160003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78110005, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78120002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78170003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x79050005, + 0xe0040000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x79100000, + 0x00000000, + 0x79000002, + 0xffffffff, + 0x00000000, + 0x00000000, + 0x780e0002, + 0x00000441, + 0x00000401, + 0x00000401, + 0x78021002, + 0x00000000, + 0x00000000, + 0x00000400, + 0x78130012, + 0x00400810, + 0x00000000, + 0x20000000, + 0x04000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78140007, + 0x00000280, + 0x08080000, + 0x00000000, + 0x00060000, + 0x4e080002, + 0x00100400, + 0x00000000, + 0x00000000, + 0x78090005, + 0x02000000, + 0x22220000, + 0x02f60000, + 0x11330000, + 0x02850004, + 0x11220000, + 0x78011002, + 0x00000000, + 0x00000000, + 0x00000200, + 0x78080003, + 0x00002000, + 0x00000448, /* reloc */ + 0x00000448, /* reloc */ + 0x00000000, + 0x05000000, /* cmds end */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000220, /* state start */ + 0x00000240, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0060005a, + 0x204077be, + 0x000000c0, + 0x008d0040, + 0x0060005a, + 0x206077be, + 0x000000c0, + 0x008d0080, + 0x0060005a, + 0x208077be, + 0x000000d0, + 0x008d0040, + 0x0060005a, + 0x20a077be, + 0x000000d0, + 0x008d0080, + 0x00000201, + 0x20080061, + 0x00000000, + 0x00000000, + 0x00600001, + 0x20200022, + 0x008d0000, + 0x00000000, + 0x02800031, + 0x21c01cc9, + 0x00000020, + 0x0a8a0001, + 0x00600001, + 0x204003be, + 0x008d01c0, + 0x00000000, + 0x00600001, + 0x206003be, + 0x008d01e0, + 0x00000000, + 0x00600001, + 0x208003be, + 0x008d0200, + 0x00000000, + 0x00600001, + 0x20a003be, + 0x008d0220, + 0x00000000, + 0x00600001, + 0x20c003be, + 0x008d0240, + 0x00000000, + 0x00600001, + 0x20e003be, + 0x008d0260, + 0x00000000, + 0x00600001, + 0x210003be, + 0x008d0280, + 0x00000000, + 0x00600001, + 0x212003be, + 0x008d02a0, + 0x00000000, + 0x05800031, + 0x24001cc8, + 0x00000040, + 0x90019000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x30000000, + 0x00000124, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0xf99a130c, + 0x799a130c, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x80000031, + 0x00000003, + 0x00000000, /* state end */ +}; + +RO_RENDERSTATE(6); diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen7.c b/drivers/gpu/drm/i915/intel_renderstate_gen7.c new file mode 100644 index 000000000000..6fa7ff2a1298 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate_gen7.c @@ -0,0 +1,253 @@ +#include "intel_renderstate.h" + +static const u32 gen7_null_state_relocs[] = { + 0x0000000c, + 0x00000010, + 0x00000018, + 0x000001ec, +}; + +static const u32 gen7_null_state_batch[] = { + 0x69040000, + 0x61010008, + 0x00000000, + 0x00000001, /* reloc */ + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000001, + 0x790d0002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78180000, + 0x00000001, + 0x79160000, + 0x00000008, + 0x78300000, + 0x02010040, + 0x78310000, + 0x04000000, + 0x78320000, + 0x04000000, + 0x78330000, + 0x02000000, + 0x78100004, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781b0005, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781c0002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781d0004, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78110005, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78120002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78210000, + 0x00000000, + 0x78130005, + 0x00000000, + 0x20000000, + 0x04000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78140001, + 0x20000800, + 0x00000000, + 0x781e0001, + 0x00000000, + 0x00000000, + 0x78050005, + 0xe0040000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78040001, + 0x00000000, + 0x00000000, + 0x78240000, + 0x00000240, + 0x78230000, + 0x00000260, + 0x782f0000, + 0x00000280, + 0x781f000c, + 0x00400810, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78200006, + 0x000002c0, + 0x08080000, + 0x00000000, + 0x28000402, + 0x00060000, + 0x00000000, + 0x00000000, + 0x78090005, + 0x02000000, + 0x22220000, + 0x02f60000, + 0x11230000, + 0x02f60004, + 0x11230000, + 0x78080003, + 0x00006008, + 0x00000340, /* reloc */ + 0xffffffff, + 0x00000000, + 0x782a0000, + 0x00000360, + 0x79000002, + 0xffffffff, + 0x00000000, + 0x00000000, + 0x7b000005, + 0x0000000f, + 0x00000003, + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000000, + 0x05000000, /* cmds end */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000031, /* state start */ + 0x00000003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0xf99a130c, + 0x799a130c, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000492, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0080005a, + 0x2e2077bd, + 0x000000c0, + 0x008d0040, + 0x0080005a, + 0x2e6077bd, + 0x000000d0, + 0x008d0040, + 0x02800031, + 0x21801fa9, + 0x008d0e20, + 0x08840001, + 0x00800001, + 0x2e2003bd, + 0x008d0180, + 0x00000000, + 0x00800001, + 0x2e6003bd, + 0x008d01c0, + 0x00000000, + 0x00800001, + 0x2ea003bd, + 0x008d0200, + 0x00000000, + 0x00800001, + 0x2ee003bd, + 0x008d0240, + 0x00000000, + 0x05800031, + 0x20001fa8, + 0x008d0e20, + 0x90031000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000380, + 0x000003a0, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, /* state end */ +}; + +RO_RENDERSTATE(7); diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen8.c b/drivers/gpu/drm/i915/intel_renderstate_gen8.c new file mode 100644 index 000000000000..5c875615d42a --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate_gen8.c @@ -0,0 +1,479 @@ +#include "intel_renderstate.h" + +static const u32 gen8_null_state_relocs[] = { + 0x00000048, + 0x00000050, + 0x00000060, + 0x000003ec, +}; + +static const u32 gen8_null_state_batch[] = { + 0x69040000, + 0x61020001, + 0x00000000, + 0x00000000, + 0x79120000, + 0x00000000, + 0x79130000, + 0x00000000, + 0x79140000, + 0x00000000, + 0x79150000, + 0x00000000, + 0x79160000, + 0x00000000, + 0x6101000e, + 0x00000001, + 0x00000000, + 0x00000001, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0xfffff001, + 0x00001001, + 0xfffff001, + 0x00001001, + 0x78230000, + 0x000006e0, + 0x78210000, + 0x00000700, + 0x78300000, + 0x08010040, + 0x78330000, + 0x08000000, + 0x78310000, + 0x08000000, + 0x78320000, + 0x08000000, + 0x78240000, + 0x00000641, + 0x780e0000, + 0x00000601, + 0x780d0000, + 0x00000000, + 0x78180000, + 0x00000001, + 0x78520003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78190009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781b0007, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78270000, + 0x00000000, + 0x782c0000, + 0x00000000, + 0x781c0002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78160009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78110008, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78290000, + 0x00000000, + 0x782e0000, + 0x00000000, + 0x781a0009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781d0007, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78280000, + 0x00000000, + 0x782d0000, + 0x00000000, + 0x78260000, + 0x00000000, + 0x782b0000, + 0x00000000, + 0x78150009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78100007, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781e0003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78120002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781f0002, + 0x30400820, + 0x00000000, + 0x00000000, + 0x78510009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78500003, + 0x00210000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78130002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x782a0000, + 0x00000480, + 0x782f0000, + 0x00000540, + 0x78140000, + 0x00000800, + 0x78170009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x7820000a, + 0x00000580, + 0x00000000, + 0x08080000, + 0x00000000, + 0x00000000, + 0x1f000002, + 0x00060000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x784d0000, + 0x40000000, + 0x784f0000, + 0x80000100, + 0x780f0000, + 0x00000740, + 0x78050006, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78070003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78060003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78040001, + 0x00000000, + 0x00000001, + 0x79000002, + 0xffffffff, + 0x00000000, + 0x00000000, + 0x78080003, + 0x00006000, + 0x000005e0, /* reloc */ + 0x00000000, + 0x00000000, + 0x78090005, + 0x02000000, + 0x22220000, + 0x02f60000, + 0x11230000, + 0x02850004, + 0x11230000, + 0x784b0000, + 0x0000000f, + 0x78490001, + 0x00000000, + 0x00000000, + 0x7b000005, + 0x00000000, + 0x00000003, + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000000, + 0x05000000, /* cmds end */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x000004c0, /* state start */ + 0x00000500, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000092, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0060005a, + 0x21403ae8, + 0x3a0000c0, + 0x008d0040, + 0x0060005a, + 0x21603ae8, + 0x3a0000c0, + 0x008d0080, + 0x0060005a, + 0x21803ae8, + 0x3a0000d0, + 0x008d0040, + 0x0060005a, + 0x21a03ae8, + 0x3a0000d0, + 0x008d0080, + 0x02800031, + 0x2e0022e8, + 0x0e000140, + 0x08840001, + 0x05800031, + 0x200022e0, + 0x0e000e00, + 0x90031000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0xf99a130c, + 0x799a130c, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x3f800000, + 0x00000000, + 0x3f800000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, /* state end */ +}; + +RO_RENDERSTATE(8); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 79fb4cc2137c..279488addf3f 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -33,26 +33,44 @@ #include "i915_trace.h" #include "intel_drv.h" -static inline int ring_space(struct intel_ring_buffer *ring) +/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill, + * but keeps the logic simple. Indeed, the whole purpose of this macro is just + * to give some inclination as to some of the magic values used in the various + * workarounds! + */ +#define CACHELINE_BYTES 64 + +static inline int __ring_space(int head, int tail, int size) { - int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE); + int space = head - (tail + I915_RING_FREE_SPACE); if (space < 0) - space += ring->size; + space += size; return space; } -void __intel_ring_advance(struct intel_ring_buffer *ring) +static inline int ring_space(struct intel_engine_cs *ring) +{ + struct intel_ringbuffer *ringbuf = ring->buffer; + return __ring_space(ringbuf->head & HEAD_ADDR, ringbuf->tail, ringbuf->size); +} + +static bool intel_ring_stopped(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; + return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring); +} - ring->tail &= ring->size - 1; - if (dev_priv->gpu_error.stop_rings & intel_ring_flag(ring)) +void __intel_ring_advance(struct intel_engine_cs *ring) +{ + struct intel_ringbuffer *ringbuf = ring->buffer; + ringbuf->tail &= ringbuf->size - 1; + if (intel_ring_stopped(ring)) return; - ring->write_tail(ring, ring->tail); + ring->write_tail(ring, ringbuf->tail); } static int -gen2_render_ring_flush(struct intel_ring_buffer *ring, +gen2_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { @@ -78,7 +96,7 @@ gen2_render_ring_flush(struct intel_ring_buffer *ring, } static int -gen4_render_ring_flush(struct intel_ring_buffer *ring, +gen4_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { @@ -173,9 +191,9 @@ gen4_render_ring_flush(struct intel_ring_buffer *ring, * really our business. That leaves only stall at scoreboard. */ static int -intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring) +intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring) { - u32 scratch_addr = ring->scratch.gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; @@ -208,11 +226,11 @@ intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring) } static int -gen6_render_ring_flush(struct intel_ring_buffer *ring, +gen6_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; - u32 scratch_addr = ring->scratch.gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; /* Force SNB workarounds for PIPE_CONTROL flushes */ @@ -260,7 +278,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring, } static int -gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring) +gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring) { int ret; @@ -278,7 +296,7 @@ gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring) return 0; } -static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value) +static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value) { int ret; @@ -302,11 +320,11 @@ static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value) } static int -gen7_render_ring_flush(struct intel_ring_buffer *ring, +gen7_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; - u32 scratch_addr = ring->scratch.gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; /* @@ -363,11 +381,11 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring, } static int -gen8_render_ring_flush(struct intel_ring_buffer *ring, +gen8_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; - u32 scratch_addr = ring->scratch.gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; flags |= PIPE_CONTROL_CS_STALL; @@ -403,14 +421,14 @@ gen8_render_ring_flush(struct intel_ring_buffer *ring, } -static void ring_write_tail(struct intel_ring_buffer *ring, +static void ring_write_tail(struct intel_engine_cs *ring, u32 value) { struct drm_i915_private *dev_priv = ring->dev->dev_private; I915_WRITE_TAIL(ring, value); } -u64 intel_ring_get_active_head(struct intel_ring_buffer *ring) +u64 intel_ring_get_active_head(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; u64 acthd; @@ -426,7 +444,7 @@ u64 intel_ring_get_active_head(struct intel_ring_buffer *ring) return acthd; } -static void ring_setup_phys_status_page(struct intel_ring_buffer *ring) +static void ring_setup_phys_status_page(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; u32 addr; @@ -437,7 +455,7 @@ static void ring_setup_phys_status_page(struct intel_ring_buffer *ring) I915_WRITE(HWS_PGA, addr); } -static bool stop_ring(struct intel_ring_buffer *ring) +static bool stop_ring(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = to_i915(ring->dev); @@ -461,11 +479,12 @@ static bool stop_ring(struct intel_ring_buffer *ring) return (I915_READ_HEAD(ring) & HEAD_ADDR) == 0; } -static int init_ring_common(struct intel_ring_buffer *ring) +static int init_ring_common(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_i915_gem_object *obj = ring->obj; + struct intel_ringbuffer *ringbuf = ring->buffer; + struct drm_i915_gem_object *obj = ringbuf->obj; int ret = 0; gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); @@ -504,7 +523,7 @@ static int init_ring_common(struct intel_ring_buffer *ring) * register values. */ I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj)); I915_WRITE_CTL(ring, - ((ring->size - PAGE_SIZE) & RING_NR_PAGES) + ((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID); /* If the head is still not zero, the ring is dead */ @@ -512,12 +531,11 @@ static int init_ring_common(struct intel_ring_buffer *ring) I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) && (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) { DRM_ERROR("%s initialization failed " - "ctl %08x head %08x tail %08x start %08x\n", - ring->name, - I915_READ_CTL(ring), - I915_READ_HEAD(ring), - I915_READ_TAIL(ring), - I915_READ_START(ring)); + "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08lx]\n", + ring->name, + I915_READ_CTL(ring), I915_READ_CTL(ring) & RING_VALID, + I915_READ_HEAD(ring), I915_READ_TAIL(ring), + I915_READ_START(ring), (unsigned long)i915_gem_obj_ggtt_offset(obj)); ret = -EIO; goto out; } @@ -525,10 +543,10 @@ static int init_ring_common(struct intel_ring_buffer *ring) if (!drm_core_check_feature(ring->dev, DRIVER_MODESET)) i915_kernel_lost_context(ring->dev); else { - ring->head = I915_READ_HEAD(ring); - ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR; - ring->space = ring_space(ring); - ring->last_retired_head = -1; + ringbuf->head = I915_READ_HEAD(ring); + ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR; + ringbuf->space = ring_space(ring); + ringbuf->last_retired_head = -1; } memset(&ring->hangcheck, 0, sizeof(ring->hangcheck)); @@ -540,7 +558,7 @@ out: } static int -init_pipe_control(struct intel_ring_buffer *ring) +init_pipe_control(struct intel_engine_cs *ring) { int ret; @@ -581,7 +599,7 @@ err: return ret; } -static int init_render_ring(struct intel_ring_buffer *ring) +static int init_render_ring(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -595,19 +613,21 @@ static int init_render_ring(struct intel_ring_buffer *ring) * to use MI_WAIT_FOR_EVENT within the CS. It should already be * programmed to '1' on all products. * - * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw + * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv */ if (INTEL_INFO(dev)->gen >= 6) 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) { @@ -624,13 +644,6 @@ 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) @@ -642,7 +655,7 @@ static int init_render_ring(struct intel_ring_buffer *ring) return ret; } -static void render_ring_cleanup(struct intel_ring_buffer *ring) +static void render_ring_cleanup(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; @@ -658,20 +671,46 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring) ring->scratch.obj = NULL; } -static void -update_mboxes(struct intel_ring_buffer *ring, - u32 mmio_offset) +static int gen6_signal(struct intel_engine_cs *signaller, + unsigned int num_dwords) { -/* NB: In order to be able to do semaphore MBOX updates for varying number - * of rings, it's easiest if we round up each individual update to a - * multiple of 2 (since ring updates must always be a multiple of 2) - * even though the actual update only requires 3 dwords. - */ + struct drm_device *dev = signaller->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_engine_cs *useless; + int i, ret; + + /* NB: In order to be able to do semaphore MBOX updates for varying + * number of rings, it's easiest if we round up each individual update + * to a multiple of 2 (since ring updates must always be a multiple of + * 2) even though the actual update only requires 3 dwords. + */ #define MBOX_UPDATE_DWORDS 4 - intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1)); - intel_ring_emit(ring, mmio_offset); - intel_ring_emit(ring, ring->outstanding_lazy_seqno); - intel_ring_emit(ring, MI_NOOP); + if (i915_semaphore_is_enabled(dev)) + num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS); + else + return intel_ring_begin(signaller, num_dwords); + + ret = intel_ring_begin(signaller, num_dwords); + if (ret) + return ret; +#undef MBOX_UPDATE_DWORDS + + for_each_ring(useless, dev_priv, i) { + u32 mbox_reg = signaller->semaphore.mbox.signal[i]; + if (mbox_reg != GEN6_NOSYNC) { + intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1)); + intel_ring_emit(signaller, mbox_reg); + intel_ring_emit(signaller, signaller->outstanding_lazy_seqno); + intel_ring_emit(signaller, MI_NOOP); + } else { + intel_ring_emit(signaller, MI_NOOP); + intel_ring_emit(signaller, MI_NOOP); + intel_ring_emit(signaller, MI_NOOP); + intel_ring_emit(signaller, MI_NOOP); + } + } + + return 0; } /** @@ -684,29 +723,14 @@ update_mboxes(struct intel_ring_buffer *ring, * This acts like a signal in the canonical semaphore. */ static int -gen6_add_request(struct intel_ring_buffer *ring) +gen6_add_request(struct intel_engine_cs *ring) { - struct drm_device *dev = ring->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *useless; - int i, ret, num_dwords = 4; - - if (i915_semaphore_is_enabled(dev)) - num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS); -#undef MBOX_UPDATE_DWORDS + int ret; - ret = intel_ring_begin(ring, num_dwords); + ret = ring->semaphore.signal(ring, 4); if (ret) return ret; - if (i915_semaphore_is_enabled(dev)) { - for_each_ring(useless, dev_priv, i) { - u32 mbox_reg = ring->signal_mbox[i]; - if (mbox_reg != GEN6_NOSYNC) - update_mboxes(ring, mbox_reg); - } - } - intel_ring_emit(ring, MI_STORE_DWORD_INDEX); intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT); intel_ring_emit(ring, ring->outstanding_lazy_seqno); @@ -731,14 +755,15 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev, * @seqno - seqno which the waiter will block on */ static int -gen6_ring_sync(struct intel_ring_buffer *waiter, - struct intel_ring_buffer *signaller, +gen6_ring_sync(struct intel_engine_cs *waiter, + struct intel_engine_cs *signaller, u32 seqno) { - int ret; u32 dw1 = MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE | MI_SEMAPHORE_REGISTER; + u32 wait_mbox = signaller->semaphore.mbox.wait[waiter->id]; + int ret; /* Throughout all of the GEM code, seqno passed implies our current * seqno is >= the last seqno executed. However for hardware the @@ -746,8 +771,7 @@ gen6_ring_sync(struct intel_ring_buffer *waiter, */ seqno -= 1; - WARN_ON(signaller->semaphore_register[waiter->id] == - MI_SEMAPHORE_SYNC_INVALID); + WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID); ret = intel_ring_begin(waiter, 4); if (ret) @@ -755,9 +779,7 @@ gen6_ring_sync(struct intel_ring_buffer *waiter, /* If seqno wrap happened, omit the wait with no-ops */ if (likely(!i915_gem_has_seqno_wrapped(waiter->dev, seqno))) { - intel_ring_emit(waiter, - dw1 | - signaller->semaphore_register[waiter->id]); + intel_ring_emit(waiter, dw1 | wait_mbox); intel_ring_emit(waiter, seqno); intel_ring_emit(waiter, 0); intel_ring_emit(waiter, MI_NOOP); @@ -782,9 +804,9 @@ do { \ } while (0) static int -pc_render_add_request(struct intel_ring_buffer *ring) +pc_render_add_request(struct intel_engine_cs *ring) { - u32 scratch_addr = ring->scratch.gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; /* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently @@ -806,15 +828,15 @@ pc_render_add_request(struct intel_ring_buffer *ring) intel_ring_emit(ring, ring->outstanding_lazy_seqno); intel_ring_emit(ring, 0); PIPE_CONTROL_FLUSH(ring, scratch_addr); - scratch_addr += 128; /* write to separate cachelines */ + scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */ PIPE_CONTROL_FLUSH(ring, scratch_addr); - scratch_addr += 128; + scratch_addr += 2 * CACHELINE_BYTES; PIPE_CONTROL_FLUSH(ring, scratch_addr); - scratch_addr += 128; + scratch_addr += 2 * CACHELINE_BYTES; PIPE_CONTROL_FLUSH(ring, scratch_addr); - scratch_addr += 128; + scratch_addr += 2 * CACHELINE_BYTES; PIPE_CONTROL_FLUSH(ring, scratch_addr); - scratch_addr += 128; + scratch_addr += 2 * CACHELINE_BYTES; PIPE_CONTROL_FLUSH(ring, scratch_addr); intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE | @@ -830,7 +852,7 @@ pc_render_add_request(struct intel_ring_buffer *ring) } static u32 -gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) +gen6_ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) { /* Workaround to force correct ordering between irq and seqno writes on * ivb (and maybe also on snb) by reading from a CS register (like @@ -844,31 +866,31 @@ gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) } static u32 -ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) +ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) { return intel_read_status_page(ring, I915_GEM_HWS_INDEX); } static void -ring_set_seqno(struct intel_ring_buffer *ring, u32 seqno) +ring_set_seqno(struct intel_engine_cs *ring, u32 seqno) { intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno); } static u32 -pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) +pc_render_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) { return ring->scratch.cpu_page[0]; } static void -pc_render_set_seqno(struct intel_ring_buffer *ring, u32 seqno) +pc_render_set_seqno(struct intel_engine_cs *ring, u32 seqno) { ring->scratch.cpu_page[0] = seqno; } static bool -gen5_ring_get_irq(struct intel_ring_buffer *ring) +gen5_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -886,7 +908,7 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring) } static void -gen5_ring_put_irq(struct intel_ring_buffer *ring) +gen5_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -899,7 +921,7 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring) } static bool -i9xx_ring_get_irq(struct intel_ring_buffer *ring) +i9xx_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -920,7 +942,7 @@ i9xx_ring_get_irq(struct intel_ring_buffer *ring) } static void -i9xx_ring_put_irq(struct intel_ring_buffer *ring) +i9xx_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -936,7 +958,7 @@ i9xx_ring_put_irq(struct intel_ring_buffer *ring) } static bool -i8xx_ring_get_irq(struct intel_ring_buffer *ring) +i8xx_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -957,7 +979,7 @@ i8xx_ring_get_irq(struct intel_ring_buffer *ring) } static void -i8xx_ring_put_irq(struct intel_ring_buffer *ring) +i8xx_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -972,7 +994,7 @@ i8xx_ring_put_irq(struct intel_ring_buffer *ring) spin_unlock_irqrestore(&dev_priv->irq_lock, flags); } -void intel_ring_setup_status_page(struct intel_ring_buffer *ring) +void intel_ring_setup_status_page(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -989,6 +1011,11 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring) case BCS: mmio = BLT_HWS_PGA_GEN7; break; + /* + * VCS2 actually doesn't exist on Gen7. Only shut up + * gcc switch check warning + */ + case VCS2: case VCS: mmio = BSD_HWS_PGA_GEN7; break; @@ -1030,7 +1057,7 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring) } static int -bsd_ring_flush(struct intel_ring_buffer *ring, +bsd_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { @@ -1047,7 +1074,7 @@ bsd_ring_flush(struct intel_ring_buffer *ring, } static int -i9xx_add_request(struct intel_ring_buffer *ring) +i9xx_add_request(struct intel_engine_cs *ring) { int ret; @@ -1065,7 +1092,7 @@ i9xx_add_request(struct intel_ring_buffer *ring) } static bool -gen6_ring_get_irq(struct intel_ring_buffer *ring) +gen6_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1090,7 +1117,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring) } static void -gen6_ring_put_irq(struct intel_ring_buffer *ring) +gen6_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1108,7 +1135,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring) } static bool -hsw_vebox_get_irq(struct intel_ring_buffer *ring) +hsw_vebox_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1128,7 +1155,7 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring) } static void -hsw_vebox_put_irq(struct intel_ring_buffer *ring) +hsw_vebox_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1146,7 +1173,7 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring) } static bool -gen8_ring_get_irq(struct intel_ring_buffer *ring) +gen8_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1172,7 +1199,7 @@ gen8_ring_get_irq(struct intel_ring_buffer *ring) } static void -gen8_ring_put_irq(struct intel_ring_buffer *ring) +gen8_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1192,8 +1219,8 @@ gen8_ring_put_irq(struct intel_ring_buffer *ring) } static int -i965_dispatch_execbuffer(struct intel_ring_buffer *ring, - u32 offset, u32 length, +i965_dispatch_execbuffer(struct intel_engine_cs *ring, + u64 offset, u32 length, unsigned flags) { int ret; @@ -1215,8 +1242,8 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring, /* Just userspace ABI convention to limit the wa batch bo to a resonable size */ #define I830_BATCH_LIMIT (256*1024) static int -i830_dispatch_execbuffer(struct intel_ring_buffer *ring, - u32 offset, u32 len, +i830_dispatch_execbuffer(struct intel_engine_cs *ring, + u64 offset, u32 len, unsigned flags) { int ret; @@ -1266,8 +1293,8 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring, } static int -i915_dispatch_execbuffer(struct intel_ring_buffer *ring, - u32 offset, u32 len, +i915_dispatch_execbuffer(struct intel_engine_cs *ring, + u64 offset, u32 len, unsigned flags) { int ret; @@ -1283,7 +1310,7 @@ i915_dispatch_execbuffer(struct intel_ring_buffer *ring, return 0; } -static void cleanup_status_page(struct intel_ring_buffer *ring) +static void cleanup_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1297,50 +1324,44 @@ static void cleanup_status_page(struct intel_ring_buffer *ring) ring->status_page.obj = NULL; } -static int init_status_page(struct intel_ring_buffer *ring) +static int init_status_page(struct intel_engine_cs *ring) { - struct drm_device *dev = ring->dev; struct drm_i915_gem_object *obj; - int ret; - obj = i915_gem_alloc_object(dev, 4096); - if (obj == NULL) { - DRM_ERROR("Failed to allocate status page\n"); - ret = -ENOMEM; - goto err; - } + if ((obj = ring->status_page.obj) == NULL) { + int ret; - ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); - if (ret) - goto err_unref; + obj = i915_gem_alloc_object(ring->dev, 4096); + if (obj == NULL) { + DRM_ERROR("Failed to allocate status page\n"); + return -ENOMEM; + } - ret = i915_gem_obj_ggtt_pin(obj, 4096, 0); - if (ret) - goto err_unref; + ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); + if (ret) + goto err_unref; + + ret = i915_gem_obj_ggtt_pin(obj, 4096, 0); + if (ret) { +err_unref: + drm_gem_object_unreference(&obj->base); + return ret; + } + + ring->status_page.obj = obj; + } ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj); ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl)); - if (ring->status_page.page_addr == NULL) { - ret = -ENOMEM; - goto err_unpin; - } - ring->status_page.obj = obj; memset(ring->status_page.page_addr, 0, PAGE_SIZE); DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n", ring->name, ring->status_page.gfx_addr); return 0; - -err_unpin: - i915_gem_object_ggtt_unpin(obj); -err_unref: - drm_gem_object_unreference(&obj->base); -err: - return ret; } -static int init_phys_status_page(struct intel_ring_buffer *ring) +static int init_phys_status_page(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1357,44 +1378,24 @@ static int init_phys_status_page(struct intel_ring_buffer *ring) return 0; } -static int intel_init_ring_buffer(struct drm_device *dev, - struct intel_ring_buffer *ring) +static int allocate_ring_buffer(struct intel_engine_cs *ring) { + struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_ringbuffer *ringbuf = ring->buffer; struct drm_i915_gem_object *obj; - struct drm_i915_private *dev_priv = dev->dev_private; int ret; - ring->dev = dev; - INIT_LIST_HEAD(&ring->active_list); - INIT_LIST_HEAD(&ring->request_list); - ring->size = 32 * PAGE_SIZE; - memset(ring->sync_seqno, 0, sizeof(ring->sync_seqno)); - - init_waitqueue_head(&ring->irq_queue); - - if (I915_NEED_GFX_HWS(dev)) { - ret = init_status_page(ring); - if (ret) - return ret; - } else { - BUG_ON(ring->id != RCS); - ret = init_phys_status_page(ring); - if (ret) - return ret; - } + if (intel_ring_initialized(ring)) + return 0; obj = NULL; if (!HAS_LLC(dev)) - obj = i915_gem_object_create_stolen(dev, ring->size); + obj = i915_gem_object_create_stolen(dev, ringbuf->size); if (obj == NULL) - obj = i915_gem_alloc_object(dev, ring->size); - if (obj == NULL) { - DRM_ERROR("Failed to allocate ringbuffer\n"); - ret = -ENOMEM; - goto err_hws; - } - - ring->obj = obj; + obj = i915_gem_alloc_object(dev, ringbuf->size); + if (obj == NULL) + return -ENOMEM; ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE); if (ret) @@ -1404,65 +1405,102 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (ret) goto err_unpin; - ring->virtual_start = + ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj), - ring->size); - if (ring->virtual_start == NULL) { - DRM_ERROR("Failed to map ringbuffer.\n"); + ringbuf->size); + if (ringbuf->virtual_start == NULL) { ret = -EINVAL; goto err_unpin; } - ret = ring->init(ring); - if (ret) - goto err_unmap; + ringbuf->obj = obj; + return 0; + +err_unpin: + i915_gem_object_ggtt_unpin(obj); +err_unref: + drm_gem_object_unreference(&obj->base); + return ret; +} + +static int intel_init_ring_buffer(struct drm_device *dev, + struct intel_engine_cs *ring) +{ + struct intel_ringbuffer *ringbuf = ring->buffer; + int ret; + + if (ringbuf == NULL) { + ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL); + if (!ringbuf) + return -ENOMEM; + ring->buffer = ringbuf; + } + + ring->dev = dev; + INIT_LIST_HEAD(&ring->active_list); + INIT_LIST_HEAD(&ring->request_list); + ringbuf->size = 32 * PAGE_SIZE; + memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno)); + + init_waitqueue_head(&ring->irq_queue); + + if (I915_NEED_GFX_HWS(dev)) { + ret = init_status_page(ring); + if (ret) + goto error; + } else { + BUG_ON(ring->id != RCS); + ret = init_phys_status_page(ring); + if (ret) + goto error; + } + + ret = allocate_ring_buffer(ring); + if (ret) { + DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret); + goto error; + } /* Workaround an erratum on the i830 which causes a hang if * the TAIL pointer points to within the last 2 cachelines * of the buffer. */ - ring->effective_size = ring->size; - if (IS_I830(ring->dev) || IS_845G(ring->dev)) - ring->effective_size -= 128; + ringbuf->effective_size = ringbuf->size; + if (IS_I830(dev) || IS_845G(dev)) + ringbuf->effective_size -= 2 * CACHELINE_BYTES; - i915_cmd_parser_init_ring(ring); + ret = i915_cmd_parser_init_ring(ring); + if (ret) + goto error; + + ret = ring->init(ring); + if (ret) + goto error; return 0; -err_unmap: - iounmap(ring->virtual_start); -err_unpin: - i915_gem_object_ggtt_unpin(obj); -err_unref: - drm_gem_object_unreference(&obj->base); - ring->obj = NULL; -err_hws: - cleanup_status_page(ring); +error: + kfree(ringbuf); + ring->buffer = NULL; return ret; } -void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring) +void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) { - struct drm_i915_private *dev_priv; - int ret; + struct drm_i915_private *dev_priv = to_i915(ring->dev); + struct intel_ringbuffer *ringbuf = ring->buffer; - if (ring->obj == NULL) + if (!intel_ring_initialized(ring)) return; - /* Disable the ring buffer. The ring must be idle at this point */ - dev_priv = ring->dev->dev_private; - ret = intel_ring_idle(ring); - if (ret && !i915_reset_in_progress(&dev_priv->gpu_error)) - DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n", - ring->name, ret); - - I915_WRITE_CTL(ring, 0); + intel_stop_ring_buffer(ring); + WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0); - iounmap(ring->virtual_start); + iounmap(ringbuf->virtual_start); - i915_gem_object_ggtt_unpin(ring->obj); - drm_gem_object_unreference(&ring->obj->base); - ring->obj = NULL; + i915_gem_object_ggtt_unpin(ringbuf->obj); + drm_gem_object_unreference(&ringbuf->obj->base); + ringbuf->obj = NULL; ring->preallocated_lazy_request = NULL; ring->outstanding_lazy_seqno = 0; @@ -1470,44 +1508,34 @@ void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring) ring->cleanup(ring); cleanup_status_page(ring); + + i915_cmd_parser_fini_ring(ring); + + kfree(ringbuf); + ring->buffer = NULL; } -static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n) +static int intel_ring_wait_request(struct intel_engine_cs *ring, int n) { + struct intel_ringbuffer *ringbuf = ring->buffer; struct drm_i915_gem_request *request; - u32 seqno = 0, tail; + u32 seqno = 0; int ret; - if (ring->last_retired_head != -1) { - ring->head = ring->last_retired_head; - ring->last_retired_head = -1; + if (ringbuf->last_retired_head != -1) { + ringbuf->head = ringbuf->last_retired_head; + ringbuf->last_retired_head = -1; - ring->space = ring_space(ring); - if (ring->space >= n) + ringbuf->space = ring_space(ring); + if (ringbuf->space >= n) return 0; } list_for_each_entry(request, &ring->request_list, list) { - int space; - - if (request->tail == -1) - continue; - - space = request->tail - (ring->tail + I915_RING_FREE_SPACE); - if (space < 0) - space += ring->size; - if (space >= n) { + if (__ring_space(request->tail, ringbuf->tail, ringbuf->size) >= n) { seqno = request->seqno; - tail = request->tail; break; } - - /* Consume this request in case we need more space than - * is available and so need to prevent a race between - * updating last_retired_head and direct reads of - * I915_RING_HEAD. It also provides a nice sanity check. - */ - request->tail = -1; } if (seqno == 0) @@ -1517,18 +1545,19 @@ static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n) if (ret) return ret; - ring->head = tail; - ring->space = ring_space(ring); - if (WARN_ON(ring->space < n)) - return -ENOSPC; + i915_gem_retire_requests_ring(ring); + ringbuf->head = ringbuf->last_retired_head; + ringbuf->last_retired_head = -1; + ringbuf->space = ring_space(ring); return 0; } -static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) +static int ring_wait_for_space(struct intel_engine_cs *ring, int n) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ringbuffer *ringbuf = ring->buffer; unsigned long end; int ret; @@ -1539,7 +1568,6 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) /* force the tail write in case we have been skipping them */ __intel_ring_advance(ring); - trace_i915_ring_wait_begin(ring); /* With GEM the hangcheck timer should kick us out of the loop, * leaving it early runs the risk of corrupting GEM state (due * to running on almost untested codepaths). But on resume @@ -1547,12 +1575,13 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) * case by choosing an insanely large timeout. */ end = jiffies + 60 * HZ; + trace_i915_ring_wait_begin(ring); do { - ring->head = I915_READ_HEAD(ring); - ring->space = ring_space(ring); - if (ring->space >= n) { - trace_i915_ring_wait_end(ring); - return 0; + ringbuf->head = I915_READ_HEAD(ring); + ringbuf->space = ring_space(ring); + if (ringbuf->space >= n) { + ret = 0; + break; } if (!drm_core_check_feature(dev, DRIVER_MODESET) && @@ -1564,38 +1593,49 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) msleep(1); + if (dev_priv->mm.interruptible && signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + ret = i915_gem_check_wedge(&dev_priv->gpu_error, dev_priv->mm.interruptible); if (ret) - return ret; - } while (!time_after(jiffies, end)); + break; + + if (time_after(jiffies, end)) { + ret = -EBUSY; + break; + } + } while (1); trace_i915_ring_wait_end(ring); - return -EBUSY; + return ret; } -static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring) +static int intel_wrap_ring_buffer(struct intel_engine_cs *ring) { uint32_t __iomem *virt; - int rem = ring->size - ring->tail; + struct intel_ringbuffer *ringbuf = ring->buffer; + int rem = ringbuf->size - ringbuf->tail; - if (ring->space < rem) { + if (ringbuf->space < rem) { int ret = ring_wait_for_space(ring, rem); if (ret) return ret; } - virt = ring->virtual_start + ring->tail; + virt = ringbuf->virtual_start + ringbuf->tail; rem /= 4; while (rem--) iowrite32(MI_NOOP, virt++); - ring->tail = 0; - ring->space = ring_space(ring); + ringbuf->tail = 0; + ringbuf->space = ring_space(ring); return 0; } -int intel_ring_idle(struct intel_ring_buffer *ring) +int intel_ring_idle(struct intel_engine_cs *ring) { u32 seqno; int ret; @@ -1619,7 +1659,7 @@ int intel_ring_idle(struct intel_ring_buffer *ring) } static int -intel_ring_alloc_seqno(struct intel_ring_buffer *ring) +intel_ring_alloc_seqno(struct intel_engine_cs *ring) { if (ring->outstanding_lazy_seqno) return 0; @@ -1637,18 +1677,19 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring) return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno); } -static int __intel_ring_prepare(struct intel_ring_buffer *ring, +static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes) { + struct intel_ringbuffer *ringbuf = ring->buffer; int ret; - if (unlikely(ring->tail + bytes > ring->effective_size)) { + if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) { ret = intel_wrap_ring_buffer(ring); if (unlikely(ret)) return ret; } - if (unlikely(ring->space < bytes)) { + if (unlikely(ringbuf->space < bytes)) { ret = ring_wait_for_space(ring, bytes); if (unlikely(ret)) return ret; @@ -1657,7 +1698,7 @@ static int __intel_ring_prepare(struct intel_ring_buffer *ring, return 0; } -int intel_ring_begin(struct intel_ring_buffer *ring, +int intel_ring_begin(struct intel_engine_cs *ring, int num_dwords) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1677,19 +1718,20 @@ int intel_ring_begin(struct intel_ring_buffer *ring, if (ret) return ret; - ring->space -= num_dwords * sizeof(uint32_t); + ring->buffer->space -= num_dwords * sizeof(uint32_t); return 0; } /* Align the ring tail to a cacheline boundary */ -int intel_ring_cacheline_align(struct intel_ring_buffer *ring) +int intel_ring_cacheline_align(struct intel_engine_cs *ring) { - int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t); + int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); int ret; if (num_dwords == 0) return 0; + num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords; ret = intel_ring_begin(ring, num_dwords); if (ret) return ret; @@ -1702,7 +1744,7 @@ int intel_ring_cacheline_align(struct intel_ring_buffer *ring) return 0; } -void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno) +void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1719,7 +1761,7 @@ void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno) ring->hangcheck.seqno = seqno; } -static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring, +static void gen6_bsd_ring_write_tail(struct intel_engine_cs *ring, u32 value) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1752,7 +1794,7 @@ static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring, _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE)); } -static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring, +static int gen6_bsd_ring_flush(struct intel_engine_cs *ring, u32 invalidate, u32 flush) { uint32_t cmd; @@ -1788,8 +1830,8 @@ static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring, } static int -gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, - u32 offset, u32 len, +gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring, + u64 offset, u32 len, unsigned flags) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1803,8 +1845,8 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, /* FIXME(BDW): Address space and security selectors. */ intel_ring_emit(ring, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8)); - intel_ring_emit(ring, offset); - intel_ring_emit(ring, 0); + intel_ring_emit(ring, lower_32_bits(offset)); + intel_ring_emit(ring, upper_32_bits(offset)); intel_ring_emit(ring, MI_NOOP); intel_ring_advance(ring); @@ -1812,8 +1854,8 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, } static int -hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, - u32 offset, u32 len, +hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring, + u64 offset, u32 len, unsigned flags) { int ret; @@ -1833,8 +1875,8 @@ hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, } static int -gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, - u32 offset, u32 len, +gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring, + u64 offset, u32 len, unsigned flags) { int ret; @@ -1855,7 +1897,7 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, /* Blitter support (SandyBridge+) */ -static int gen6_ring_flush(struct intel_ring_buffer *ring, +static int gen6_ring_flush(struct intel_engine_cs *ring, u32 invalidate, u32 flush) { struct drm_device *dev = ring->dev; @@ -1898,7 +1940,7 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring, int intel_init_render_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; ring->name = "render ring"; ring->id = RCS; @@ -1920,15 +1962,24 @@ int intel_init_render_ring_buffer(struct drm_device *dev) ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT; ring->get_seqno = gen6_ring_get_seqno; ring->set_seqno = ring_set_seqno; - ring->sync_to = gen6_ring_sync; - ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV; - ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB; - ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_RVE; - ring->signal_mbox[RCS] = GEN6_NOSYNC; - ring->signal_mbox[VCS] = GEN6_VRSYNC; - ring->signal_mbox[BCS] = GEN6_BRSYNC; - ring->signal_mbox[VECS] = GEN6_VERSYNC; + ring->semaphore.sync_to = gen6_ring_sync; + ring->semaphore.signal = gen6_signal; + /* + * The current semaphore is only applied on pre-gen8 platform. + * And there is no VCS2 ring on the pre-gen8 platform. So the + * semaphore between RCS and VCS2 is initialized as INVALID. + * Gen8 will initialize the sema between VCS2 and RCS later. + */ + ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_RV; + ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_RB; + ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_RVE; + ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.signal[RCS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[VCS] = GEN6_VRSYNC; + ring->semaphore.mbox.signal[BCS] = GEN6_BRSYNC; + ring->semaphore.mbox.signal[VECS] = GEN6_VERSYNC; + ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC; } else if (IS_GEN5(dev)) { ring->add_request = pc_render_add_request; ring->flush = gen4_render_ring_flush; @@ -1999,16 +2050,25 @@ int intel_init_render_ring_buffer(struct drm_device *dev) int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; + struct intel_ringbuffer *ringbuf = ring->buffer; int ret; + if (ringbuf == NULL) { + ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL); + if (!ringbuf) + return -ENOMEM; + ring->buffer = ringbuf; + } + ring->name = "render ring"; ring->id = RCS; ring->mmio_base = RENDER_RING_BASE; if (INTEL_INFO(dev)->gen >= 6) { /* non-kms not supported on gen6+ */ - return -ENODEV; + ret = -ENODEV; + goto err_ringbuf; } /* Note: gem is not supported on gen5/ilk without kms (the corresponding @@ -2043,31 +2103,39 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size) INIT_LIST_HEAD(&ring->active_list); INIT_LIST_HEAD(&ring->request_list); - ring->size = size; - ring->effective_size = ring->size; + ringbuf->size = size; + ringbuf->effective_size = ringbuf->size; if (IS_I830(ring->dev) || IS_845G(ring->dev)) - ring->effective_size -= 128; + ringbuf->effective_size -= 2 * CACHELINE_BYTES; - ring->virtual_start = ioremap_wc(start, size); - if (ring->virtual_start == NULL) { + ringbuf->virtual_start = ioremap_wc(start, size); + if (ringbuf->virtual_start == NULL) { DRM_ERROR("can not ioremap virtual address for" " ring buffer\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err_ringbuf; } if (!I915_NEED_GFX_HWS(dev)) { ret = init_phys_status_page(ring); if (ret) - return ret; + goto err_vstart; } return 0; + +err_vstart: + iounmap(ringbuf->virtual_start); +err_ringbuf: + kfree(ringbuf); + ring->buffer = NULL; + return ret; } int intel_init_bsd_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[VCS]; + struct intel_engine_cs *ring = &dev_priv->ring[VCS]; ring->name = "bsd ring"; ring->id = VCS; @@ -2096,15 +2164,24 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev) ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer; } - ring->sync_to = gen6_ring_sync; - ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR; - ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB; - ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_VVE; - ring->signal_mbox[RCS] = GEN6_RVSYNC; - ring->signal_mbox[VCS] = GEN6_NOSYNC; - ring->signal_mbox[BCS] = GEN6_BVSYNC; - ring->signal_mbox[VECS] = GEN6_VEVSYNC; + ring->semaphore.sync_to = gen6_ring_sync; + ring->semaphore.signal = gen6_signal; + /* + * The current semaphore is only applied on pre-gen8 platform. + * And there is no VCS2 ring on the pre-gen8 platform. So the + * semaphore between VCS and VCS2 is initialized as INVALID. + * Gen8 will initialize the sema between VCS2 and VCS later. + */ + ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VR; + ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VB; + ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_VVE; + ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.signal[RCS] = GEN6_RVSYNC; + ring->semaphore.mbox.signal[VCS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[BCS] = GEN6_BVSYNC; + ring->semaphore.mbox.signal[VECS] = GEN6_VEVSYNC; + ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC; } else { ring->mmio_base = BSD_RING_BASE; ring->flush = bsd_ring_flush; @@ -2127,10 +2204,63 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev) return intel_init_ring_buffer(dev, ring); } +/** + * Initialize the second BSD ring for Broadwell GT3. + * It is noted that this only exists on Broadwell GT3. + */ +int intel_init_bsd2_ring_buffer(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_engine_cs *ring = &dev_priv->ring[VCS2]; + + if ((INTEL_INFO(dev)->gen != 8)) { + DRM_ERROR("No dual-BSD ring on non-BDW machine\n"); + return -EINVAL; + } + + ring->name = "bds2_ring"; + ring->id = VCS2; + + ring->write_tail = ring_write_tail; + ring->mmio_base = GEN8_BSD2_RING_BASE; + ring->flush = gen6_bsd_ring_flush; + ring->add_request = gen6_add_request; + ring->get_seqno = gen6_ring_get_seqno; + ring->set_seqno = ring_set_seqno; + ring->irq_enable_mask = + GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT; + ring->irq_get = gen8_ring_get_irq; + ring->irq_put = gen8_ring_put_irq; + ring->dispatch_execbuffer = + gen8_ring_dispatch_execbuffer; + ring->semaphore.sync_to = gen6_ring_sync; + ring->semaphore.signal = gen6_signal; + /* + * The current semaphore is only applied on the pre-gen8. And there + * is no bsd2 ring on the pre-gen8. So now the semaphore_register + * between VCS2 and other ring is initialized as invalid. + * Gen8 will initialize the sema between VCS2 and other ring later. + */ + ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.signal[RCS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[VCS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[BCS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[VECS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC; + + ring->init = init_ring_common; + + return intel_init_ring_buffer(dev, ring); +} + int intel_init_blt_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[BCS]; + struct intel_engine_cs *ring = &dev_priv->ring[BCS]; ring->name = "blitter ring"; ring->id = BCS; @@ -2153,15 +2283,24 @@ int intel_init_blt_ring_buffer(struct drm_device *dev) ring->irq_put = gen6_ring_put_irq; ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer; } - ring->sync_to = gen6_ring_sync; - ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR; - ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV; - ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_BVE; - ring->signal_mbox[RCS] = GEN6_RBSYNC; - ring->signal_mbox[VCS] = GEN6_VBSYNC; - ring->signal_mbox[BCS] = GEN6_NOSYNC; - ring->signal_mbox[VECS] = GEN6_VEBSYNC; + ring->semaphore.sync_to = gen6_ring_sync; + ring->semaphore.signal = gen6_signal; + /* + * The current semaphore is only applied on pre-gen8 platform. And + * there is no VCS2 ring on the pre-gen8 platform. So the semaphore + * between BCS and VCS2 is initialized as INVALID. + * Gen8 will initialize the sema between BCS and VCS2 later. + */ + ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_BR; + ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_BV; + ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_BVE; + ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.signal[RCS] = GEN6_RBSYNC; + ring->semaphore.mbox.signal[VCS] = GEN6_VBSYNC; + ring->semaphore.mbox.signal[BCS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[VECS] = GEN6_VEBSYNC; + ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC; ring->init = init_ring_common; return intel_init_ring_buffer(dev, ring); @@ -2170,7 +2309,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev) int intel_init_vebox_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[VECS]; + struct intel_engine_cs *ring = &dev_priv->ring[VECS]; ring->name = "video enhancement ring"; ring->id = VECS; @@ -2194,22 +2333,25 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev) ring->irq_put = hsw_vebox_put_irq; ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer; } - ring->sync_to = gen6_ring_sync; - ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VER; - ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_VEV; - ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VEB; - ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_INVALID; - ring->signal_mbox[RCS] = GEN6_RVESYNC; - ring->signal_mbox[VCS] = GEN6_VVESYNC; - ring->signal_mbox[BCS] = GEN6_BVESYNC; - ring->signal_mbox[VECS] = GEN6_NOSYNC; + ring->semaphore.sync_to = gen6_ring_sync; + ring->semaphore.signal = gen6_signal; + ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VER; + ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_VEV; + ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VEB; + ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID; + ring->semaphore.mbox.signal[RCS] = GEN6_RVESYNC; + ring->semaphore.mbox.signal[VCS] = GEN6_VVESYNC; + ring->semaphore.mbox.signal[BCS] = GEN6_BVESYNC; + ring->semaphore.mbox.signal[VECS] = GEN6_NOSYNC; + ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC; ring->init = init_ring_common; return intel_init_ring_buffer(dev, ring); } int -intel_ring_flush_all_caches(struct intel_ring_buffer *ring) +intel_ring_flush_all_caches(struct intel_engine_cs *ring) { int ret; @@ -2227,7 +2369,7 @@ intel_ring_flush_all_caches(struct intel_ring_buffer *ring) } int -intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring) +intel_ring_invalidate_all_caches(struct intel_engine_cs *ring) { uint32_t flush_domains; int ret; @@ -2245,3 +2387,19 @@ intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring) ring->gpu_caches_dirty = false; return 0; } + +void +intel_stop_ring_buffer(struct intel_engine_cs *ring) +{ + int ret; + + if (!intel_ring_initialized(ring)) + return; + + ret = intel_ring_idle(ring); + if (ret && !i915_reset_in_progress(&to_i915(ring->dev)->gpu_error)) + DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n", + ring->name, ret); + + stop_ring(ring); +} diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 2b91c4b4d34b..910c83cf7d44 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -1,6 +1,10 @@ #ifndef _INTEL_RINGBUFFER_H_ #define _INTEL_RINGBUFFER_H_ +#include <linux/hashtable.h> + +#define I915_CMD_HASH_ORDER 9 + /* * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use" * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use" @@ -54,76 +58,93 @@ struct intel_ring_hangcheck { bool deadlock; }; -struct intel_ring_buffer { +struct intel_ringbuffer { + struct drm_i915_gem_object *obj; + void __iomem *virtual_start; + + u32 head; + u32 tail; + int space; + int size; + int effective_size; + + /** We track the position of the requests in the ring buffer, and + * when each is retired we increment last_retired_head as the GPU + * must have finished processing the request and so we know we + * can advance the ringbuffer up to that position. + * + * last_retired_head is set to -1 after the value is consumed so + * we can detect new retirements. + */ + u32 last_retired_head; +}; + +struct intel_engine_cs { const char *name; enum intel_ring_id { RCS = 0x0, VCS, BCS, VECS, + VCS2 } id; -#define I915_NUM_RINGS 4 +#define I915_NUM_RINGS 5 +#define LAST_USER_RING (VECS + 1) u32 mmio_base; - void __iomem *virtual_start; struct drm_device *dev; - struct drm_i915_gem_object *obj; + struct intel_ringbuffer *buffer; - u32 head; - u32 tail; - int space; - int size; - int effective_size; struct intel_hw_status_page status_page; - /** We track the position of the requests in the ring buffer, and - * when each is retired we increment last_retired_head as the GPU - * must have finished processing the request and so we know we - * can advance the ringbuffer up to that position. - * - * last_retired_head is set to -1 after the value is consumed so - * we can detect new retirements. - */ - u32 last_retired_head; - unsigned irq_refcount; /* protected by dev_priv->irq_lock */ u32 irq_enable_mask; /* bitmask to enable ring interrupt */ u32 trace_irq_seqno; - u32 sync_seqno[I915_NUM_RINGS-1]; - bool __must_check (*irq_get)(struct intel_ring_buffer *ring); - void (*irq_put)(struct intel_ring_buffer *ring); + bool __must_check (*irq_get)(struct intel_engine_cs *ring); + void (*irq_put)(struct intel_engine_cs *ring); - int (*init)(struct intel_ring_buffer *ring); + int (*init)(struct intel_engine_cs *ring); - void (*write_tail)(struct intel_ring_buffer *ring, + void (*write_tail)(struct intel_engine_cs *ring, u32 value); - int __must_check (*flush)(struct intel_ring_buffer *ring, + int __must_check (*flush)(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains); - int (*add_request)(struct intel_ring_buffer *ring); + int (*add_request)(struct intel_engine_cs *ring); /* Some chipsets are not quite as coherent as advertised and need * an expensive kick to force a true read of the up-to-date seqno. * However, the up-to-date seqno is not always required and the last * seen value is good enough. Note that the seqno will always be * monotonic, even if not coherent. */ - u32 (*get_seqno)(struct intel_ring_buffer *ring, + u32 (*get_seqno)(struct intel_engine_cs *ring, bool lazy_coherency); - void (*set_seqno)(struct intel_ring_buffer *ring, + void (*set_seqno)(struct intel_engine_cs *ring, u32 seqno); - int (*dispatch_execbuffer)(struct intel_ring_buffer *ring, - u32 offset, u32 length, + int (*dispatch_execbuffer)(struct intel_engine_cs *ring, + u64 offset, u32 length, unsigned flags); #define I915_DISPATCH_SECURE 0x1 #define I915_DISPATCH_PINNED 0x2 - void (*cleanup)(struct intel_ring_buffer *ring); - int (*sync_to)(struct intel_ring_buffer *ring, - struct intel_ring_buffer *to, - u32 seqno); + void (*cleanup)(struct intel_engine_cs *ring); - /* our mbox written by others */ - u32 semaphore_register[I915_NUM_RINGS]; - /* mboxes this ring signals to */ - u32 signal_mbox[I915_NUM_RINGS]; + struct { + u32 sync_seqno[I915_NUM_RINGS-1]; + + struct { + /* our mbox written by others */ + u32 wait[I915_NUM_RINGS]; + /* mboxes this ring signals to */ + u32 signal[I915_NUM_RINGS]; + } mbox; + + /* AKA wait() */ + int (*sync_to)(struct intel_engine_cs *ring, + struct intel_engine_cs *to, + u32 seqno); + int (*signal)(struct intel_engine_cs *signaller, + /* num_dwords needed by caller */ + unsigned int num_dwords); + } semaphore; /** * List of objects currently involved in rendering from the @@ -153,12 +174,8 @@ 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; + struct intel_context *default_context; + struct intel_context *last_context; struct intel_ring_hangcheck hangcheck; @@ -168,12 +185,13 @@ struct intel_ring_buffer { volatile u32 *cpu_page; } scratch; + bool needs_cmd_parser; + /* - * Tables of commands the command parser needs to know about + * Table of commands the command parser needs to know about * for this ring. */ - const struct drm_i915_cmd_table *cmd_tables; - int cmd_table_count; + DECLARE_HASHTABLE(cmd_hash, I915_CMD_HASH_ORDER); /* * Table of registers allowed in commands that read/write registers. @@ -202,20 +220,20 @@ struct intel_ring_buffer { }; static inline bool -intel_ring_initialized(struct intel_ring_buffer *ring) +intel_ring_initialized(struct intel_engine_cs *ring) { - return ring->obj != NULL; + return ring->buffer && ring->buffer->obj; } static inline unsigned -intel_ring_flag(struct intel_ring_buffer *ring) +intel_ring_flag(struct intel_engine_cs *ring) { return 1 << ring->id; } static inline u32 -intel_ring_sync_index(struct intel_ring_buffer *ring, - struct intel_ring_buffer *other) +intel_ring_sync_index(struct intel_engine_cs *ring, + struct intel_engine_cs *other) { int idx; @@ -233,7 +251,7 @@ intel_ring_sync_index(struct intel_ring_buffer *ring, } static inline u32 -intel_read_status_page(struct intel_ring_buffer *ring, +intel_read_status_page(struct intel_engine_cs *ring, int reg) { /* Ensure that the compiler doesn't optimize away the load. */ @@ -242,7 +260,7 @@ intel_read_status_page(struct intel_ring_buffer *ring, } static inline void -intel_write_status_page(struct intel_ring_buffer *ring, +intel_write_status_page(struct intel_engine_cs *ring, int reg, u32 value) { ring->status_page.page_addr[reg] = value; @@ -267,47 +285,51 @@ intel_write_status_page(struct intel_ring_buffer *ring, #define I915_GEM_HWS_SCRATCH_INDEX 0x30 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT) -void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring); +void intel_stop_ring_buffer(struct intel_engine_cs *ring); +void intel_cleanup_ring_buffer(struct intel_engine_cs *ring); -int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n); -int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring); -static inline void intel_ring_emit(struct intel_ring_buffer *ring, +int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n); +int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring); +static inline void intel_ring_emit(struct intel_engine_cs *ring, u32 data) { - iowrite32(data, ring->virtual_start + ring->tail); - ring->tail += 4; + struct intel_ringbuffer *ringbuf = ring->buffer; + iowrite32(data, ringbuf->virtual_start + ringbuf->tail); + ringbuf->tail += 4; } -static inline void intel_ring_advance(struct intel_ring_buffer *ring) +static inline void intel_ring_advance(struct intel_engine_cs *ring) { - ring->tail &= ring->size - 1; + struct intel_ringbuffer *ringbuf = ring->buffer; + ringbuf->tail &= ringbuf->size - 1; } -void __intel_ring_advance(struct intel_ring_buffer *ring); +void __intel_ring_advance(struct intel_engine_cs *ring); -int __must_check intel_ring_idle(struct intel_ring_buffer *ring); -void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno); -int intel_ring_flush_all_caches(struct intel_ring_buffer *ring); -int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring); +int __must_check intel_ring_idle(struct intel_engine_cs *ring); +void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno); +int intel_ring_flush_all_caches(struct intel_engine_cs *ring); +int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring); int intel_init_render_ring_buffer(struct drm_device *dev); int intel_init_bsd_ring_buffer(struct drm_device *dev); +int intel_init_bsd2_ring_buffer(struct drm_device *dev); int intel_init_blt_ring_buffer(struct drm_device *dev); int intel_init_vebox_ring_buffer(struct drm_device *dev); -u64 intel_ring_get_active_head(struct intel_ring_buffer *ring); -void intel_ring_setup_status_page(struct intel_ring_buffer *ring); +u64 intel_ring_get_active_head(struct intel_engine_cs *ring); +void intel_ring_setup_status_page(struct intel_engine_cs *ring); -static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring) +static inline u32 intel_ring_get_tail(struct intel_engine_cs *ring) { - return ring->tail; + return ring->buffer->tail; } -static inline u32 intel_ring_get_seqno(struct intel_ring_buffer *ring) +static inline u32 intel_ring_get_seqno(struct intel_engine_cs *ring) { BUG_ON(ring->outstanding_lazy_seqno == 0); return ring->outstanding_lazy_seqno; } -static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno) +static inline void i915_trace_irq_get(struct intel_engine_cs *ring, u32 seqno) { if (ring->trace_irq_seqno == 0 && ring->irq_get(ring)) ring->trace_irq_seqno = seqno; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 46be00d66df3..6a4d5bc17697 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1153,20 +1153,21 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, pipe_config->pixel_multiplier = intel_sdvo_get_pixel_multiplier(adjusted_mode); + pipe_config->has_hdmi_sink = intel_sdvo->has_hdmi_monitor; + if (intel_sdvo->color_range_auto) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ /* FIXME: This bit is only valid when using TMDS encoding and 8 * bit per color mode. */ - if (intel_sdvo->has_hdmi_monitor && + if (pipe_config->has_hdmi_sink && drm_match_cea_mode(adjusted_mode) > 1) - intel_sdvo->color_range = HDMI_COLOR_RANGE_16_235; - else - intel_sdvo->color_range = 0; + pipe_config->limited_color_range = true; + } else { + if (pipe_config->has_hdmi_sink && + intel_sdvo->color_range == HDMI_COLOR_RANGE_16_235) + pipe_config->limited_color_range = true; } - if (intel_sdvo->color_range) - pipe_config->limited_color_range = true; - /* Clock computation needs to happen after pixel multiplier. */ if (intel_sdvo->is_tv) i9xx_adjust_sdvo_tv_clock(pipe_config); @@ -1174,7 +1175,7 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, return true; } -static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) +static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder) { struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1223,7 +1224,7 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) if (!intel_sdvo_set_target_input(intel_sdvo)) return; - if (intel_sdvo->has_hdmi_monitor) { + if (crtc->config.has_hdmi_sink) { intel_sdvo_set_encode(intel_sdvo, SDVO_ENCODE_HDMI); intel_sdvo_set_colorimetry(intel_sdvo, SDVO_COLORIMETRY_RGB256); @@ -1258,8 +1259,8 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) /* The real mode polarity is set by the SDVO commands, using * struct intel_sdvo_dtd. */ sdvox = SDVO_VSYNC_ACTIVE_HIGH | SDVO_HSYNC_ACTIVE_HIGH; - if (!HAS_PCH_SPLIT(dev) && intel_sdvo->is_hdmi) - sdvox |= intel_sdvo->color_range; + if (!HAS_PCH_SPLIT(dev) && crtc->config.limited_color_range) + sdvox |= HDMI_COLOR_RANGE_16_235; if (INTEL_INFO(dev)->gen < 5) sdvox |= SDVO_BORDER_ENABLE; } else { @@ -1349,6 +1350,8 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, u8 val; bool ret; + sdvox = I915_READ(intel_sdvo->sdvo_reg); + ret = intel_sdvo_get_input_timing(intel_sdvo, &dtd); if (!ret) { /* Some sdvo encoders are not spec compliant and don't @@ -1377,7 +1380,6 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, * other platfroms. */ if (IS_I915G(dev) || IS_I915GM(dev)) { - sdvox = I915_READ(intel_sdvo->sdvo_reg); pipe_config->pixel_multiplier = ((sdvox & SDVO_PORT_MULTIPLY_MASK) >> SDVO_PORT_MULTIPLY_SHIFT) + 1; @@ -1406,6 +1408,15 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, } } + if (sdvox & HDMI_COLOR_RANGE_16_235) + pipe_config->limited_color_range = true; + + if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ENCODE, + &val, 1)) { + if (val == SDVO_ENCODE_HDMI) + pipe_config->has_hdmi_sink = true; + } + WARN(encoder_pixel_multiplier != pipe_config->pixel_multiplier, "SDVO pixel multiplier mismatch, port: %i, encoder: %i\n", pipe_config->pixel_multiplier, encoder_pixel_multiplier); @@ -1732,7 +1743,7 @@ intel_sdvo_detect(struct drm_connector *connector, bool force) enum drm_connector_status ret; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); if (!intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ATTACHED_DISPLAYS, @@ -1794,7 +1805,7 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector) struct edid *edid; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); /* set the bus switch and get the modes */ edid = intel_sdvo_get_edid(connector); @@ -1892,7 +1903,7 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector) int i; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); /* Read the list of supported input resolutions for the selected TV * format. @@ -1929,7 +1940,7 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector) struct drm_display_mode *newmode; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, drm_get_connector_name(connector)); + connector->base.id, connector->name); /* * Fetch modes from VBT. For SDVO prefer the VBT mode since some @@ -2999,7 +3010,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob) intel_encoder->compute_config = intel_sdvo_compute_config; intel_encoder->disable = intel_disable_sdvo; - intel_encoder->mode_set = intel_sdvo_mode_set; + intel_encoder->pre_enable = intel_sdvo_pre_enable; intel_encoder->enable = intel_enable_sdvo; intel_encoder->get_hw_state = intel_sdvo_get_hw_state; intel_encoder->get_config = intel_sdvo_get_config; diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 0954f132726e..01d841ea3140 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -29,12 +29,21 @@ * IOSF sideband, see VLV2_SidebandMsg_HAS.docx and * VLV_VLV2_PUNIT_HAS_0.8.docx */ + +/* Standard MMIO read, non-posted */ +#define SB_MRD_NP 0x00 +/* Standard MMIO write, non-posted */ +#define SB_MWR_NP 0x01 +/* Private register read, double-word addressing, non-posted */ +#define SB_CRRDDA_NP 0x06 +/* Private register write, double-word addressing, non-posted */ +#define SB_CRWRDA_NP 0x07 + static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn, u32 port, u32 opcode, u32 addr, u32 *val) { u32 cmd, be = 0xf, bar = 0; - bool is_read = (opcode == PUNIT_OPCODE_REG_READ || - opcode == DPIO_OPCODE_REG_READ); + bool is_read = (opcode == SB_MRD_NP || opcode == SB_CRRDDA_NP); cmd = (devfn << IOSF_DEVFN_SHIFT) | (opcode << IOSF_OPCODE_SHIFT) | (port << IOSF_PORT_SHIFT) | (be << IOSF_BYTE_ENABLES_SHIFT) | @@ -74,7 +83,7 @@ u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr) mutex_lock(&dev_priv->dpio_lock); vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT, - PUNIT_OPCODE_REG_READ, addr, &val); + SB_CRRDDA_NP, addr, &val); mutex_unlock(&dev_priv->dpio_lock); return val; @@ -86,7 +95,7 @@ void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val) mutex_lock(&dev_priv->dpio_lock); vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT, - PUNIT_OPCODE_REG_WRITE, addr, &val); + SB_CRWRDA_NP, addr, &val); mutex_unlock(&dev_priv->dpio_lock); } @@ -95,7 +104,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg) u32 val = 0; vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT, - PUNIT_OPCODE_REG_READ, reg, &val); + SB_CRRDDA_NP, reg, &val); return val; } @@ -103,7 +112,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg) void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT, - PUNIT_OPCODE_REG_WRITE, reg, &val); + SB_CRWRDA_NP, reg, &val); } u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr) @@ -114,7 +123,7 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr) mutex_lock(&dev_priv->dpio_lock); vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC, - PUNIT_OPCODE_REG_READ, addr, &val); + SB_CRRDDA_NP, addr, &val); mutex_unlock(&dev_priv->dpio_lock); return val; @@ -124,56 +133,56 @@ u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val = 0; vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC, - PUNIT_OPCODE_REG_READ, reg, &val); + SB_CRRDDA_NP, reg, &val); return val; } void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC, - PUNIT_OPCODE_REG_WRITE, reg, &val); + SB_CRWRDA_NP, reg, &val); } u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val = 0; vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK, - PUNIT_OPCODE_REG_READ, reg, &val); + SB_CRRDDA_NP, reg, &val); return val; } void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK, - PUNIT_OPCODE_REG_WRITE, reg, &val); + SB_CRWRDA_NP, reg, &val); } u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val = 0; vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU, - PUNIT_OPCODE_REG_READ, reg, &val); + SB_CRRDDA_NP, reg, &val); return val; } void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU, - PUNIT_OPCODE_REG_WRITE, reg, &val); + SB_CRWRDA_NP, reg, &val); } u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val = 0; vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE, - PUNIT_OPCODE_REG_READ, reg, &val); + SB_CRRDDA_NP, reg, &val); return val; } void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE, - PUNIT_OPCODE_REG_WRITE, reg, &val); + SB_CRWRDA_NP, reg, &val); } u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) @@ -181,14 +190,22 @@ u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) u32 val = 0; vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)), - DPIO_OPCODE_REG_READ, reg, &val); + SB_MRD_NP, 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; } void vlv_dpio_write(struct drm_i915_private *dev_priv, enum pipe pipe, int reg, u32 val) { vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)), - DPIO_OPCODE_REG_WRITE, reg, &val); + SB_MWR_NP, reg, &val); } /* SBI access */ @@ -253,13 +270,13 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value, u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val = 0; - vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, - DPIO_OPCODE_REG_READ, reg, &val); + vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRRDDA_NP, + reg, &val); return val; } void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { - vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, - DPIO_OPCODE_REG_WRITE, reg, &val); + vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRWRDA_NP, + reg, &val); } diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 336ae6c602f2..1b66ddcdfb33 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -37,6 +37,106 @@ #include <drm/i915_drm.h> #include "i915_drv.h" +static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs) +{ + /* paranoia */ + if (!mode->crtc_htotal) + return 1; + + return DIV_ROUND_UP(usecs * mode->crtc_clock, 1000 * mode->crtc_htotal); +} + +static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count) +{ + struct drm_device *dev = crtc->base.dev; + const struct drm_display_mode *mode = &crtc->config.adjusted_mode; + enum pipe pipe = crtc->pipe; + long timeout = msecs_to_jiffies_timeout(1); + int scanline, min, max, vblank_start; + DEFINE_WAIT(wait); + + WARN_ON(!drm_modeset_is_locked(&crtc->base.mutex)); + + vblank_start = mode->crtc_vblank_start; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vblank_start = DIV_ROUND_UP(vblank_start, 2); + + /* FIXME needs to be calibrated sensibly */ + min = vblank_start - usecs_to_scanlines(mode, 100); + max = vblank_start - 1; + + if (min <= 0 || max <= 0) + return false; + + if (WARN_ON(drm_vblank_get(dev, pipe))) + return false; + + local_irq_disable(); + + trace_i915_pipe_update_start(crtc, min, max); + + for (;;) { + /* + * prepare_to_wait() has a memory barrier, which guarantees + * other CPUs can see the task state update by the time we + * read the scanline. + */ + prepare_to_wait(&crtc->vbl_wait, &wait, TASK_UNINTERRUPTIBLE); + + scanline = intel_get_crtc_scanline(crtc); + if (scanline < min || scanline > max) + break; + + if (timeout <= 0) { + DRM_ERROR("Potential atomic update failure on pipe %c\n", + pipe_name(crtc->pipe)); + break; + } + + local_irq_enable(); + + timeout = schedule_timeout(timeout); + + local_irq_disable(); + } + + finish_wait(&crtc->vbl_wait, &wait); + + drm_vblank_put(dev, pipe); + + *start_vbl_count = dev->driver->get_vblank_counter(dev, pipe); + + trace_i915_pipe_update_vblank_evaded(crtc, min, max, *start_vbl_count); + + return true; +} + +static void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count) +{ + struct drm_device *dev = crtc->base.dev; + enum pipe pipe = crtc->pipe; + u32 end_vbl_count = dev->driver->get_vblank_counter(dev, pipe); + + trace_i915_pipe_update_end(crtc, end_vbl_count); + + local_irq_enable(); + + if (start_vbl_count != end_vbl_count) + DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n", + pipe_name(pipe), start_vbl_count, end_vbl_count); +} + +static void intel_update_primary_plane(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + int reg = DSPCNTR(crtc->plane); + + if (crtc->primary_enabled) + I915_WRITE(reg, I915_READ(reg) | DISPLAY_PLANE_ENABLE); + else + I915_WRITE(reg, I915_READ(reg) & ~DISPLAY_PLANE_ENABLE); +} + static void vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc, struct drm_framebuffer *fb, @@ -48,11 +148,14 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc, struct drm_device *dev = dplane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(dplane); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_plane->pipe; int plane = intel_plane->plane; u32 sprctl; unsigned long sprsurf_offset, linear_offset; int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + u32 start_vbl_count; + bool atomic_update; sprctl = I915_READ(SPCNTR(pipe, plane)); @@ -131,6 +234,10 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc, fb->pitches[0]); linear_offset -= sprsurf_offset; + atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count); + + intel_update_primary_plane(intel_crtc); + I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]); I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x); @@ -143,7 +250,11 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc, I915_WRITE(SPCNTR(pipe, plane), sprctl); I915_WRITE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) + sprsurf_offset); - POSTING_READ(SPSURF(pipe, plane)); + + intel_flush_primary_plane(dev_priv, intel_crtc->plane); + + if (atomic_update) + intel_pipe_update_end(intel_crtc, start_vbl_count); } static void @@ -152,14 +263,25 @@ vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc) struct drm_device *dev = dplane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(dplane); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_plane->pipe; int plane = intel_plane->plane; + u32 start_vbl_count; + bool atomic_update; + + atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count); + + intel_update_primary_plane(intel_crtc); I915_WRITE(SPCNTR(pipe, plane), I915_READ(SPCNTR(pipe, plane)) & ~SP_ENABLE); /* Activate double buffered register update */ I915_WRITE(SPSURF(pipe, plane), 0); - POSTING_READ(SPSURF(pipe, plane)); + + intel_flush_primary_plane(dev_priv, intel_crtc->plane); + + if (atomic_update) + intel_pipe_update_end(intel_crtc, start_vbl_count); intel_update_sprite_watermarks(dplane, crtc, 0, 0, false, false); } @@ -226,10 +348,13 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(plane); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_plane->pipe; u32 sprctl, sprscale = 0; unsigned long sprsurf_offset, linear_offset; int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + u32 start_vbl_count; + bool atomic_update; sprctl = I915_READ(SPRCTL(pipe)); @@ -299,6 +424,10 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, pixel_size, fb->pitches[0]); linear_offset -= sprsurf_offset; + atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count); + + intel_update_primary_plane(intel_crtc); + I915_WRITE(SPRSTRIDE(pipe), fb->pitches[0]); I915_WRITE(SPRPOS(pipe), (crtc_y << 16) | crtc_x); @@ -317,7 +446,11 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, I915_WRITE(SPRCTL(pipe), sprctl); I915_WRITE(SPRSURF(pipe), i915_gem_obj_ggtt_offset(obj) + sprsurf_offset); - POSTING_READ(SPRSURF(pipe)); + + intel_flush_primary_plane(dev_priv, intel_crtc->plane); + + if (atomic_update) + intel_pipe_update_end(intel_crtc, start_vbl_count); } static void @@ -326,7 +459,14 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(plane); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_plane->pipe; + u32 start_vbl_count; + bool atomic_update; + + atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count); + + intel_update_primary_plane(intel_crtc); I915_WRITE(SPRCTL(pipe), I915_READ(SPRCTL(pipe)) & ~SPRITE_ENABLE); /* Can't leave the scaler enabled... */ @@ -334,7 +474,11 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) I915_WRITE(SPRSCALE(pipe), 0); /* Activate double buffered register update */ I915_WRITE(SPRSURF(pipe), 0); - POSTING_READ(SPRSURF(pipe)); + + intel_flush_primary_plane(dev_priv, intel_crtc->plane); + + if (atomic_update) + intel_pipe_update_end(intel_crtc, start_vbl_count); /* * Avoid underruns when disabling the sprite. @@ -410,10 +554,13 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(plane); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_plane->pipe; unsigned long dvssurf_offset, linear_offset; u32 dvscntr, dvsscale; int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + u32 start_vbl_count; + bool atomic_update; dvscntr = I915_READ(DVSCNTR(pipe)); @@ -478,6 +625,10 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, pixel_size, fb->pitches[0]); linear_offset -= dvssurf_offset; + atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count); + + intel_update_primary_plane(intel_crtc); + I915_WRITE(DVSSTRIDE(pipe), fb->pitches[0]); I915_WRITE(DVSPOS(pipe), (crtc_y << 16) | crtc_x); @@ -491,7 +642,11 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, I915_WRITE(DVSCNTR(pipe), dvscntr); I915_WRITE(DVSSURF(pipe), i915_gem_obj_ggtt_offset(obj) + dvssurf_offset); - POSTING_READ(DVSSURF(pipe)); + + intel_flush_primary_plane(dev_priv, intel_crtc->plane); + + if (atomic_update) + intel_pipe_update_end(intel_crtc, start_vbl_count); } static void @@ -500,14 +655,25 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(plane); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_plane->pipe; + u32 start_vbl_count; + bool atomic_update; + + atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count); + + intel_update_primary_plane(intel_crtc); I915_WRITE(DVSCNTR(pipe), I915_READ(DVSCNTR(pipe)) & ~DVS_ENABLE); /* Disable the scaler */ I915_WRITE(DVSSCALE(pipe), 0); /* Flush double buffered register updates */ I915_WRITE(DVSSURF(pipe), 0); - POSTING_READ(DVSSURF(pipe)); + + intel_flush_primary_plane(dev_priv, intel_crtc->plane); + + if (atomic_update) + intel_pipe_update_end(intel_crtc, start_vbl_count); /* * Avoid underruns when disabling the sprite. @@ -519,20 +685,10 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) } static void -intel_enable_primary(struct drm_crtc *crtc) +intel_post_enable_primary(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int reg = DSPCNTR(intel_crtc->plane); - - if (intel_crtc->primary_enabled) - return; - - intel_crtc->primary_enabled = true; - - I915_WRITE(reg, I915_READ(reg) | DISPLAY_PLANE_ENABLE); - intel_flush_primary_plane(dev_priv, intel_crtc->plane); /* * FIXME IPS should be fine as long as one plane is @@ -540,10 +696,7 @@ intel_enable_primary(struct drm_crtc *crtc) * when going from primary only to sprite only and vice * versa. */ - if (intel_crtc->config.ips_enabled) { - intel_wait_for_vblank(dev, intel_crtc->pipe); - hsw_enable_ips(intel_crtc); - } + hsw_enable_ips(intel_crtc); mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); @@ -551,17 +704,11 @@ intel_enable_primary(struct drm_crtc *crtc) } static void -intel_disable_primary(struct drm_crtc *crtc) +intel_pre_disable_primary(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int reg = DSPCNTR(intel_crtc->plane); - - if (!intel_crtc->primary_enabled) - return; - - intel_crtc->primary_enabled = false; mutex_lock(&dev->struct_mutex); if (dev_priv->fbc.plane == intel_crtc->plane) @@ -575,9 +722,6 @@ intel_disable_primary(struct drm_crtc *crtc) * versa. */ hsw_disable_ips(intel_crtc); - - I915_WRITE(reg, I915_READ(reg) & ~DISPLAY_PLANE_ENABLE); - intel_flush_primary_plane(dev_priv, intel_crtc->plane); } static int @@ -671,7 +815,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, struct drm_i915_gem_object *obj = intel_fb->obj; struct drm_i915_gem_object *old_obj = intel_plane->obj; int ret; - bool disable_primary = false; + bool primary_enabled; bool visible; int hscale, vscale; int max_scale, min_scale; @@ -842,8 +986,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, * If the sprite is completely covering the primary plane, * we can disable the primary and save power. */ - disable_primary = drm_rect_equals(&dst, &clip) && !colorkey_enabled(intel_plane); - WARN_ON(disable_primary && !visible && intel_crtc->active); + primary_enabled = !drm_rect_equals(&dst, &clip) || colorkey_enabled(intel_plane); + WARN_ON(!primary_enabled && !visible && intel_crtc->active); mutex_lock(&dev->struct_mutex); @@ -870,12 +1014,15 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, intel_plane->obj = obj; if (intel_crtc->active) { - /* - * Be sure to re-enable the primary before the sprite is no longer - * covering it fully. - */ - if (!disable_primary) - intel_enable_primary(crtc); + bool primary_was_enabled = intel_crtc->primary_enabled; + + intel_crtc->primary_enabled = primary_enabled; + + if (primary_was_enabled != primary_enabled) + intel_crtc_wait_for_pending_flips(crtc); + + if (primary_was_enabled && !primary_enabled) + intel_pre_disable_primary(crtc); if (visible) intel_plane->update_plane(plane, crtc, fb, obj, @@ -884,8 +1031,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, else intel_plane->disable_plane(plane, crtc); - if (disable_primary) - intel_disable_primary(crtc); + if (!primary_was_enabled && primary_enabled) + intel_post_enable_primary(crtc); } /* Unpin old obj after new one is active to avoid ugliness */ @@ -923,8 +1070,14 @@ intel_disable_plane(struct drm_plane *plane) intel_crtc = to_intel_crtc(plane->crtc); if (intel_crtc->active) { - intel_enable_primary(plane->crtc); + bool primary_was_enabled = intel_crtc->primary_enabled; + + intel_crtc->primary_enabled = true; + intel_plane->disable_plane(plane, plane->crtc); + + if (!primary_was_enabled && intel_crtc->primary_enabled) + intel_post_enable_primary(plane->crtc); } if (intel_plane->obj) { diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index bafe92e317d5..67c6c9a2eb1c 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -934,7 +934,86 @@ intel_tv_compute_config(struct intel_encoder *encoder, return true; } -static void intel_tv_mode_set(struct intel_encoder *encoder) +static void +set_tv_mode_timings(struct drm_i915_private *dev_priv, + const struct tv_mode *tv_mode, + bool burst_ena) +{ + u32 hctl1, hctl2, hctl3; + u32 vctl1, vctl2, vctl3, vctl4, vctl5, vctl6, vctl7; + + hctl1 = (tv_mode->hsync_end << TV_HSYNC_END_SHIFT) | + (tv_mode->htotal << TV_HTOTAL_SHIFT); + + hctl2 = (tv_mode->hburst_start << 16) | + (tv_mode->hburst_len << TV_HBURST_LEN_SHIFT); + + if (burst_ena) + hctl2 |= TV_BURST_ENA; + + hctl3 = (tv_mode->hblank_start << TV_HBLANK_START_SHIFT) | + (tv_mode->hblank_end << TV_HBLANK_END_SHIFT); + + vctl1 = (tv_mode->nbr_end << TV_NBR_END_SHIFT) | + (tv_mode->vi_end_f1 << TV_VI_END_F1_SHIFT) | + (tv_mode->vi_end_f2 << TV_VI_END_F2_SHIFT); + + vctl2 = (tv_mode->vsync_len << TV_VSYNC_LEN_SHIFT) | + (tv_mode->vsync_start_f1 << TV_VSYNC_START_F1_SHIFT) | + (tv_mode->vsync_start_f2 << TV_VSYNC_START_F2_SHIFT); + + vctl3 = (tv_mode->veq_len << TV_VEQ_LEN_SHIFT) | + (tv_mode->veq_start_f1 << TV_VEQ_START_F1_SHIFT) | + (tv_mode->veq_start_f2 << TV_VEQ_START_F2_SHIFT); + + if (tv_mode->veq_ena) + vctl3 |= TV_EQUAL_ENA; + + vctl4 = (tv_mode->vburst_start_f1 << TV_VBURST_START_F1_SHIFT) | + (tv_mode->vburst_end_f1 << TV_VBURST_END_F1_SHIFT); + + vctl5 = (tv_mode->vburst_start_f2 << TV_VBURST_START_F2_SHIFT) | + (tv_mode->vburst_end_f2 << TV_VBURST_END_F2_SHIFT); + + vctl6 = (tv_mode->vburst_start_f3 << TV_VBURST_START_F3_SHIFT) | + (tv_mode->vburst_end_f3 << TV_VBURST_END_F3_SHIFT); + + vctl7 = (tv_mode->vburst_start_f4 << TV_VBURST_START_F4_SHIFT) | + (tv_mode->vburst_end_f4 << TV_VBURST_END_F4_SHIFT); + + I915_WRITE(TV_H_CTL_1, hctl1); + I915_WRITE(TV_H_CTL_2, hctl2); + I915_WRITE(TV_H_CTL_3, hctl3); + I915_WRITE(TV_V_CTL_1, vctl1); + I915_WRITE(TV_V_CTL_2, vctl2); + I915_WRITE(TV_V_CTL_3, vctl3); + I915_WRITE(TV_V_CTL_4, vctl4); + I915_WRITE(TV_V_CTL_5, vctl5); + I915_WRITE(TV_V_CTL_6, vctl6); + I915_WRITE(TV_V_CTL_7, vctl7); +} + +static void set_color_conversion(struct drm_i915_private *dev_priv, + const struct color_conversion *color_conversion) +{ + if (!color_conversion) + return; + + I915_WRITE(TV_CSC_Y, (color_conversion->ry << 16) | + color_conversion->gy); + I915_WRITE(TV_CSC_Y2, (color_conversion->by << 16) | + color_conversion->ay); + I915_WRITE(TV_CSC_U, (color_conversion->ru << 16) | + color_conversion->gu); + I915_WRITE(TV_CSC_U2, (color_conversion->bu << 16) | + color_conversion->au); + I915_WRITE(TV_CSC_V, (color_conversion->rv << 16) | + color_conversion->gv); + I915_WRITE(TV_CSC_V2, (color_conversion->bv << 16) | + color_conversion->av); +} + +static void intel_tv_pre_enable(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -942,14 +1021,13 @@ static void intel_tv_mode_set(struct intel_encoder *encoder) struct intel_tv *intel_tv = enc_to_tv(encoder); const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); u32 tv_ctl; - u32 hctl1, hctl2, hctl3; - u32 vctl1, vctl2, vctl3, vctl4, vctl5, vctl6, vctl7; u32 scctl1, scctl2, scctl3; int i, j; const struct video_levels *video_levels; const struct color_conversion *color_conversion; bool burst_ena; - int pipe = intel_crtc->pipe; + int xpos = 0x0, ypos = 0x0; + unsigned int xsize, ysize; if (!tv_mode) return; /* can't happen (mode_prepare prevents this) */ @@ -982,44 +1060,6 @@ static void intel_tv_mode_set(struct intel_encoder *encoder) burst_ena = tv_mode->burst_ena; break; } - hctl1 = (tv_mode->hsync_end << TV_HSYNC_END_SHIFT) | - (tv_mode->htotal << TV_HTOTAL_SHIFT); - - hctl2 = (tv_mode->hburst_start << 16) | - (tv_mode->hburst_len << TV_HBURST_LEN_SHIFT); - - if (burst_ena) - hctl2 |= TV_BURST_ENA; - - hctl3 = (tv_mode->hblank_start << TV_HBLANK_START_SHIFT) | - (tv_mode->hblank_end << TV_HBLANK_END_SHIFT); - - vctl1 = (tv_mode->nbr_end << TV_NBR_END_SHIFT) | - (tv_mode->vi_end_f1 << TV_VI_END_F1_SHIFT) | - (tv_mode->vi_end_f2 << TV_VI_END_F2_SHIFT); - - vctl2 = (tv_mode->vsync_len << TV_VSYNC_LEN_SHIFT) | - (tv_mode->vsync_start_f1 << TV_VSYNC_START_F1_SHIFT) | - (tv_mode->vsync_start_f2 << TV_VSYNC_START_F2_SHIFT); - - vctl3 = (tv_mode->veq_len << TV_VEQ_LEN_SHIFT) | - (tv_mode->veq_start_f1 << TV_VEQ_START_F1_SHIFT) | - (tv_mode->veq_start_f2 << TV_VEQ_START_F2_SHIFT); - - if (tv_mode->veq_ena) - vctl3 |= TV_EQUAL_ENA; - - vctl4 = (tv_mode->vburst_start_f1 << TV_VBURST_START_F1_SHIFT) | - (tv_mode->vburst_end_f1 << TV_VBURST_END_F1_SHIFT); - - vctl5 = (tv_mode->vburst_start_f2 << TV_VBURST_START_F2_SHIFT) | - (tv_mode->vburst_end_f2 << TV_VBURST_END_F2_SHIFT); - - vctl6 = (tv_mode->vburst_start_f3 << TV_VBURST_START_F3_SHIFT) | - (tv_mode->vburst_end_f3 << TV_VBURST_END_F3_SHIFT); - - vctl7 = (tv_mode->vburst_start_f4 << TV_VBURST_START_F4_SHIFT) | - (tv_mode->vburst_end_f4 << TV_VBURST_END_F4_SHIFT); if (intel_crtc->pipe == 1) tv_ctl |= TV_ENC_PIPEB_SELECT; @@ -1051,37 +1091,16 @@ static void intel_tv_mode_set(struct intel_encoder *encoder) tv_mode->dda3_inc << TV_SCDDA3_INC_SHIFT; /* Enable two fixes for the chips that need them. */ - if (dev->pdev->device < 0x2772) + if (IS_I915GM(dev)) tv_ctl |= TV_ENC_C0_FIX | TV_ENC_SDP_FIX; - I915_WRITE(TV_H_CTL_1, hctl1); - I915_WRITE(TV_H_CTL_2, hctl2); - I915_WRITE(TV_H_CTL_3, hctl3); - I915_WRITE(TV_V_CTL_1, vctl1); - I915_WRITE(TV_V_CTL_2, vctl2); - I915_WRITE(TV_V_CTL_3, vctl3); - I915_WRITE(TV_V_CTL_4, vctl4); - I915_WRITE(TV_V_CTL_5, vctl5); - I915_WRITE(TV_V_CTL_6, vctl6); - I915_WRITE(TV_V_CTL_7, vctl7); + set_tv_mode_timings(dev_priv, tv_mode, burst_ena); + I915_WRITE(TV_SC_CTL_1, scctl1); I915_WRITE(TV_SC_CTL_2, scctl2); I915_WRITE(TV_SC_CTL_3, scctl3); - if (color_conversion) { - I915_WRITE(TV_CSC_Y, (color_conversion->ry << 16) | - color_conversion->gy); - I915_WRITE(TV_CSC_Y2, (color_conversion->by << 16) | - color_conversion->ay); - I915_WRITE(TV_CSC_U, (color_conversion->ru << 16) | - color_conversion->gu); - I915_WRITE(TV_CSC_U2, (color_conversion->bu << 16) | - color_conversion->au); - I915_WRITE(TV_CSC_V, (color_conversion->rv << 16) | - color_conversion->gv); - I915_WRITE(TV_CSC_V2, (color_conversion->bv << 16) | - color_conversion->av); - } + set_color_conversion(dev_priv, color_conversion); if (INTEL_INFO(dev)->gen >= 4) I915_WRITE(TV_CLR_KNOBS, 0x00404000); @@ -1092,46 +1111,25 @@ static void intel_tv_mode_set(struct intel_encoder *encoder) I915_WRITE(TV_CLR_LEVEL, ((video_levels->black << TV_BLACK_LEVEL_SHIFT) | (video_levels->blank << TV_BLANK_LEVEL_SHIFT))); - { - int pipeconf_reg = PIPECONF(pipe); - int dspcntr_reg = DSPCNTR(intel_crtc->plane); - int pipeconf = I915_READ(pipeconf_reg); - int dspcntr = I915_READ(dspcntr_reg); - int xpos = 0x0, ypos = 0x0; - unsigned int xsize, ysize; - /* Pipe must be off here */ - I915_WRITE(dspcntr_reg, dspcntr & ~DISPLAY_PLANE_ENABLE); - intel_flush_primary_plane(dev_priv, intel_crtc->plane); - - /* Wait for vblank for the disable to take effect */ - if (IS_GEN2(dev)) - intel_wait_for_vblank(dev, intel_crtc->pipe); - - I915_WRITE(pipeconf_reg, pipeconf & ~PIPECONF_ENABLE); - /* Wait for vblank for the disable to take effect. */ - intel_wait_for_pipe_off(dev, intel_crtc->pipe); - - /* Filter ctl must be set before TV_WIN_SIZE */ - I915_WRITE(TV_FILTER_CTL_1, TV_AUTO_SCALE); - xsize = tv_mode->hblank_start - tv_mode->hblank_end; - if (tv_mode->progressive) - ysize = tv_mode->nbr_end + 1; - else - ysize = 2*tv_mode->nbr_end + 1; - - xpos += intel_tv->margin[TV_MARGIN_LEFT]; - ypos += intel_tv->margin[TV_MARGIN_TOP]; - xsize -= (intel_tv->margin[TV_MARGIN_LEFT] + - intel_tv->margin[TV_MARGIN_RIGHT]); - ysize -= (intel_tv->margin[TV_MARGIN_TOP] + - intel_tv->margin[TV_MARGIN_BOTTOM]); - I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos); - I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize); - - I915_WRITE(pipeconf_reg, pipeconf); - I915_WRITE(dspcntr_reg, dspcntr); - intel_flush_primary_plane(dev_priv, intel_crtc->plane); - } + + assert_pipe_disabled(dev_priv, intel_crtc->pipe); + + /* Filter ctl must be set before TV_WIN_SIZE */ + I915_WRITE(TV_FILTER_CTL_1, TV_AUTO_SCALE); + xsize = tv_mode->hblank_start - tv_mode->hblank_end; + if (tv_mode->progressive) + ysize = tv_mode->nbr_end + 1; + else + ysize = 2*tv_mode->nbr_end + 1; + + xpos += intel_tv->margin[TV_MARGIN_LEFT]; + ypos += intel_tv->margin[TV_MARGIN_TOP]; + xsize -= (intel_tv->margin[TV_MARGIN_LEFT] + + intel_tv->margin[TV_MARGIN_RIGHT]); + ysize -= (intel_tv->margin[TV_MARGIN_TOP] + + intel_tv->margin[TV_MARGIN_BOTTOM]); + I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos); + I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize); j = 0; for (i = 0; i < 60; i++) @@ -1316,17 +1314,18 @@ intel_tv_detect(struct drm_connector *connector, bool force) int type; DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n", - connector->base.id, drm_get_connector_name(connector), + connector->base.id, connector->name, force); mode = reported_modes[0]; if (force) { struct intel_load_detect_pipe tmp; + struct drm_modeset_acquire_ctx ctx; - if (intel_get_load_detect_pipe(connector, &mode, &tmp)) { + if (intel_get_load_detect_pipe(connector, &mode, &tmp, &ctx)) { type = intel_tv_detect_type(intel_tv, connector); - intel_release_load_detect_pipe(connector, &tmp); + intel_release_load_detect_pipe(connector, &tmp, &ctx); } else return connector_status_unknown; } else @@ -1634,7 +1633,7 @@ intel_tv_init(struct drm_device *dev) intel_encoder->compute_config = intel_tv_compute_config; intel_encoder->get_config = intel_tv_get_config; - intel_encoder->mode_set = intel_tv_mode_set; + intel_encoder->pre_enable = intel_tv_pre_enable; intel_encoder->enable = intel_enable_tv; intel_encoder->disable = intel_disable_tv; intel_encoder->get_hw_state = intel_tv_get_hw_state; diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index d0c75779d3f6..79cba593df0d 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -255,8 +255,7 @@ 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; @@ -275,8 +274,7 @@ 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; @@ -374,7 +372,7 @@ void intel_uncore_early_sanitize(struct drm_device *dev) if (HAS_FPGA_DBG_UNCLAIMED(dev)) __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); - if (IS_HASWELL(dev) && + if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) && (__raw_i915_read32(dev_priv, HSW_EDRAM_PRESENT) == 1)) { /* The docs do not explain exactly how the calculation can be * made. It is somewhat guessable, but for now, it's always @@ -395,26 +393,8 @@ void intel_uncore_early_sanitize(struct drm_device *dev) void intel_uncore_sanitize(struct drm_device *dev) { - struct drm_i915_private *dev_priv = dev->dev_private; - u32 reg_val; - /* BIOS often leaves RC6 enabled, but disable it for hw init */ intel_disable_gt_powersave(dev); - - /* Turn off power gate, require especially for the BIOS less system */ - if (IS_VALLEYVIEW(dev)) { - - mutex_lock(&dev_priv->rps.hw_lock); - reg_val = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS); - - if (reg_val & (PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_RENDER) | - PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_MEDIA) | - PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_DISP2D))) - vlv_punit_write(dev_priv, PUNIT_REG_PWRGT_CTRL, 0x0); - - mutex_unlock(&dev_priv->rps.hw_lock); - - } } /* @@ -488,6 +468,17 @@ 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) { @@ -854,12 +845,15 @@ 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, @@ -911,7 +905,7 @@ int i915_get_reset_stats_ioctl(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_reset_stats *args = data; struct i915_ctx_hang_stats *hs; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; if (args->flags || args->pad) @@ -955,6 +949,9 @@ static int i965_do_reset(struct drm_device *dev) { int ret; + /* FIXME: i965g/gm need a display save/restore for gpu reset. */ + return -ENODEV; + /* * Set the domains we want to reset (GRDOM/bits 2 and 3) as * well as the reset bit (GR/bit 0). Setting the GR bit @@ -966,7 +963,6 @@ static int i965_do_reset(struct drm_device *dev) if (ret) return ret; - /* We can't reset render&media without also resetting display ... */ pci_write_config_byte(dev->pdev, I965_GDRST, GRDOM_MEDIA | GRDOM_RESET_ENABLE); @@ -979,26 +975,58 @@ static int i965_do_reset(struct drm_device *dev) return 0; } +static int g4x_do_reset(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int ret; + + pci_write_config_byte(dev->pdev, I965_GDRST, + GRDOM_RENDER | GRDOM_RESET_ENABLE); + ret = wait_for(i965_reset_complete(dev), 500); + if (ret) + return ret; + + /* WaVcpClkGateDisableForMediaReset:ctg,elk */ + I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE); + POSTING_READ(VDECCLK_GATE_D); + + pci_write_config_byte(dev->pdev, I965_GDRST, + GRDOM_MEDIA | GRDOM_RESET_ENABLE); + ret = wait_for(i965_reset_complete(dev), 500); + if (ret) + return ret; + + /* WaVcpClkGateDisableForMediaReset:ctg,elk */ + I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE); + POSTING_READ(VDECCLK_GATE_D); + + pci_write_config_byte(dev->pdev, I965_GDRST, 0); + + return 0; +} + static int ironlake_do_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - u32 gdrst; int ret; - gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR); - gdrst &= ~GRDOM_MASK; I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, - gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE); - ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500); + ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE); + ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & + ILK_GRDOM_RESET_ENABLE) == 0, 500); if (ret) return ret; - /* We can't reset render&media without also resetting display ... */ - gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR); - gdrst &= ~GRDOM_MASK; I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, - gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE); - return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500); + ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE); + ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & + ILK_GRDOM_RESET_ENABLE) == 0, 500); + if (ret) + return ret; + + I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, 0); + + return 0; } static int gen6_do_reset(struct drm_device *dev) @@ -1029,7 +1057,11 @@ int intel_gpu_reset(struct drm_device *dev) case 7: case 6: return gen6_do_reset(dev); case 5: return ironlake_do_reset(dev); - case 4: return i965_do_reset(dev); + case 4: + if (IS_G4X(dev)) + return g4x_do_reset(dev); + else + return i965_do_reset(dev); default: return -ENODEV; } } |
