diff options
| author | Dave Airlie <airlied@redhat.com> | 2015-03-24 11:12:20 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2015-03-24 11:12:20 +1000 |
| commit | 74ccbff99787b68e4eb01ef8cf29789229ab0f5d (patch) | |
| tree | d4e322105618e5b3887f7dc6b54e5d2346974675 /drivers/gpu/drm | |
| parent | ae10c2248593fb84c6951d67c98c9c934997e56a (diff) | |
| parent | 0f9e9cd61f46c07246e30871fd638ffeaca3c576 (diff) | |
| download | blackbird-obmc-linux-74ccbff99787b68e4eb01ef8cf29789229ab0f5d.tar.gz blackbird-obmc-linux-74ccbff99787b68e4eb01ef8cf29789229ab0f5d.zip | |
Merge tag 'drm-intel-next-2015-03-13-merge' of git://anongit.freedesktop.org/drm-intel into drm-next
drm-intel-next-2015-03-13-rebased:
- EU count report param for gen9+ (Jeff McGee)
- piles of pll/wm/... fixes for chv, finally out of preliminary hw support
(Ville, Vijay)
- gen9 rps support from Akash
- more work to move towards atomic from Matt, Ander and others
- runtime pm support for skl (Damien)
- edp1.4 intermediate link clock support (Sonika)
- use frontbuffer tracking for fbc (Paulo)
- remove ilk rc6 (John Harrison)
- a bunch of smaller things and fixes all over
Includes backmerge because git rerere couldn't keep up any more.
* tag 'drm-intel-next-2015-03-13-merge' of git://anongit.freedesktop.org/drm-intel: (366 commits)
drm/i915: Make sure the primary plane is enabled before reading out the fb state
drm/i915: Update DRIVER_DATE to 20150313
drm/i915: Fix vmap_batch page iterator overrun
drm/i915: Export total subslice and EU counts
drm/i915: redefine WARN_ON_ONCE to include the condition
drm/i915/skl: Implement WaDisableHBR2
drm/i915: Remove the preliminary_hw_support shackles from CHV
drm/i915: Read CHV_PLL_DW8 from the correct offset
drm/i915: Rewrite IVB FDI bifurcation conflict checks
drm/i915: Rewrite some some of the FDI lane checks
drm/i915/skl: Enable the RPS interrupts programming
drm/i915/skl: Enabling processing of Turbo interrupts
drm/i915/skl: Updated the i915_frequency_info debugfs function
drm/i915: Simplify the way BC bifurcation state consistency is kept
drm/i915/skl: Updated the act_freq_mhz_show sysfs function
drm/i915/skl: Updated the gen9_enable_rps function
drm/i915/skl: Updated the gen6_rps_limits function
drm/i915/skl: Restructured the gen6_set_rps_thresholds function
drm/i915/skl: Updated the gen6_set_rps function
drm/i915/skl: Updated the gen6_init_rps_frequencies function
...
Diffstat (limited to 'drivers/gpu/drm')
37 files changed, 1616 insertions, 1063 deletions
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 111849c4c8c2..d576a4dea64f 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -43,9 +43,10 @@ #include "drm_crtc_internal.h" #include "drm_internal.h" -static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, - struct drm_mode_fb_cmd2 *r, - struct drm_file *file_priv); +static struct drm_framebuffer * +internal_framebuffer_create(struct drm_device *dev, + struct drm_mode_fb_cmd2 *r, + struct drm_file *file_priv); /* Avoid boilerplate. I'm tired of typing. */ #define DRM_ENUM_NAME_FN(fnname, list) \ @@ -2943,13 +2944,11 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, */ if (req->flags & DRM_MODE_CURSOR_BO) { if (req->handle) { - fb = add_framebuffer_internal(dev, &fbreq, file_priv); + fb = internal_framebuffer_create(dev, &fbreq, file_priv); if (IS_ERR(fb)) { DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n"); return PTR_ERR(fb); } - - drm_framebuffer_reference(fb); } else { fb = NULL; } @@ -3308,9 +3307,10 @@ static int framebuffer_check(const struct drm_mode_fb_cmd2 *r) return 0; } -static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, - struct drm_mode_fb_cmd2 *r, - struct drm_file *file_priv) +static struct drm_framebuffer * +internal_framebuffer_create(struct drm_device *dev, + struct drm_mode_fb_cmd2 *r, + struct drm_file *file_priv) { struct drm_mode_config *config = &dev->mode_config; struct drm_framebuffer *fb; @@ -3348,12 +3348,6 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, return fb; } - mutex_lock(&file_priv->fbs_lock); - r->fb_id = fb->base.id; - list_add(&fb->filp_head, &file_priv->fbs); - DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id); - mutex_unlock(&file_priv->fbs_lock); - return fb; } @@ -3375,15 +3369,24 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, int drm_mode_addfb2(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct drm_mode_fb_cmd2 *r = data; struct drm_framebuffer *fb; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; - fb = add_framebuffer_internal(dev, data, file_priv); + fb = internal_framebuffer_create(dev, r, file_priv); if (IS_ERR(fb)) return PTR_ERR(fb); + /* Transfer ownership to the filp for reaping on close */ + + DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id); + mutex_lock(&file_priv->fbs_lock); + r->fb_id = fb->base.id; + list_add(&fb->filp_head, &file_priv->fbs); + mutex_unlock(&file_priv->fbs_lock); + return 0; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 0d15e6e30732..132581ca4ad8 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -733,10 +733,14 @@ static bool check_txmsg_state(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_sideband_msg_tx *txmsg) { bool ret; - mutex_lock(&mgr->qlock); + + /* + * All updates to txmsg->state are protected by mgr->qlock, and the two + * cases we check here are terminal states. For those the barriers + * provided by the wake_up/wait_event pair are enough. + */ ret = (txmsg->state == DRM_DP_SIDEBAND_TX_RX || txmsg->state == DRM_DP_SIDEBAND_TX_TIMEOUT); - mutex_unlock(&mgr->qlock); return ret; } @@ -1363,12 +1367,13 @@ static int process_single_tx_qlock(struct drm_dp_mst_topology_mgr *mgr, return 0; } -/* must be called holding qlock */ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) { struct drm_dp_sideband_msg_tx *txmsg; int ret; + WARN_ON(!mutex_is_locked(&mgr->qlock)); + /* construct a chunk from the first msg in the tx_msg queue */ if (list_empty(&mgr->tx_msg_downq)) { mgr->tx_down_in_progress = false; diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 7fc6f8bd4821..1134526286c8 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -403,7 +403,7 @@ static int check_free_hole(u64 start, u64 end, u64 size, unsigned alignment) unsigned rem; rem = do_div(tmp, alignment); - if (tmp) + if (rem) start += alignment - rem; } diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 9a6da3536ae5..61ae8ff4eaed 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -836,8 +836,11 @@ static u32 *vmap_batch(struct drm_i915_gem_object *obj, } i = 0; - for_each_sg_page(obj->pages->sgl, &sg_iter, npages, first_page) + for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, first_page) { pages[i++] = sg_page_iter_page(&sg_iter); + if (i == npages) + break; + } addr = vmap(pages, i, 0, PAGE_KERNEL); if (addr == NULL) { diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index e38f45374d55..1a52d6ab0f80 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1090,7 +1090,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) seq_printf(m, "Current P-state: %d\n", (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT); } else if (IS_GEN6(dev) || (IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) || - IS_BROADWELL(dev)) { + IS_BROADWELL(dev) || IS_GEN9(dev)) { 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); @@ -1109,11 +1109,15 @@ static int i915_frequency_info(struct seq_file *m, void *unused) intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); reqf = I915_READ(GEN6_RPNSWREQ); - reqf &= ~GEN6_TURBO_DISABLE; - if (IS_HASWELL(dev) || IS_BROADWELL(dev)) - reqf >>= 24; - else - reqf >>= 25; + if (IS_GEN9(dev)) + reqf >>= 23; + else { + reqf &= ~GEN6_TURBO_DISABLE; + if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + reqf >>= 24; + else + reqf >>= 25; + } reqf = intel_gpu_freq(dev_priv, reqf); rpmodectl = I915_READ(GEN6_RP_CONTROL); @@ -1127,7 +1131,9 @@ static int i915_frequency_info(struct seq_file *m, void *unused) rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI); rpcurdown = I915_READ(GEN6_RP_CUR_DOWN); rpprevdown = I915_READ(GEN6_RP_PREV_DOWN); - if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + if (IS_GEN9(dev)) + cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT; + else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT; else cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT; @@ -1153,7 +1159,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) pm_ier, pm_imr, pm_isr, pm_iir, pm_mask); seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); seq_printf(m, "Render p-state ratio: %d\n", - (gt_perf_status & 0xff00) >> 8); + (gt_perf_status & (IS_GEN9(dev) ? 0x1ff00 : 0xff00)) >> 8); seq_printf(m, "Render p-state VID: %d\n", gt_perf_status & 0xff); seq_printf(m, "Render p-state limit: %d\n", @@ -1178,14 +1184,17 @@ static int i915_frequency_info(struct seq_file *m, void *unused) GEN6_CURBSYTAVG_MASK); max_freq = (rp_state_cap & 0xff0000) >> 16; + max_freq *= (IS_SKYLAKE(dev) ? GEN9_FREQ_SCALER : 1); seq_printf(m, "Lowest (RPN) frequency: %dMHz\n", intel_gpu_freq(dev_priv, max_freq)); max_freq = (rp_state_cap & 0xff00) >> 8; + max_freq *= (IS_SKYLAKE(dev) ? GEN9_FREQ_SCALER : 1); seq_printf(m, "Nominal (RP1) frequency: %dMHz\n", intel_gpu_freq(dev_priv, max_freq)); max_freq = rp_state_cap & 0xff; + max_freq *= (IS_SKYLAKE(dev) ? GEN9_FREQ_SCALER : 1); seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n", intel_gpu_freq(dev_priv, max_freq)); @@ -1831,18 +1840,6 @@ static int i915_context_status(struct seq_file *m, void *unused) if (ret) return ret; - if (dev_priv->ips.pwrctx) { - seq_puts(m, "power context "); - describe_obj(m, dev_priv->ips.pwrctx); - seq_putc(m, '\n'); - } - - if (dev_priv->ips.renderctx) { - seq_puts(m, "render context "); - describe_obj(m, dev_priv->ips.renderctx); - seq_putc(m, '\n'); - } - list_for_each_entry(ctx, &dev_priv->context_list, link) { if (!i915.enable_execlists && ctx->legacy_hw_ctx.rcs_state == NULL) @@ -2246,6 +2243,11 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) enum pipe pipe; bool enabled = false; + if (!HAS_PSR(dev)) { + seq_puts(m, "PSR not supported\n"); + return 0; + } + intel_runtime_pm_get(dev_priv); mutex_lock(&dev_priv->psr.lock); @@ -2258,17 +2260,15 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) seq_printf(m, "Re-enable work scheduled: %s\n", yesno(work_busy(&dev_priv->psr.work.work))); - if (HAS_PSR(dev)) { - if (HAS_DDI(dev)) - enabled = I915_READ(EDP_PSR_CTL(dev)) & EDP_PSR_ENABLE; - else { - for_each_pipe(dev_priv, pipe) { - stat[pipe] = I915_READ(VLV_PSRSTAT(pipe)) & - VLV_EDP_PSR_CURR_STATE_MASK; - if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) || - (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE)) - enabled = true; - } + if (HAS_DDI(dev)) + enabled = I915_READ(EDP_PSR_CTL(dev)) & EDP_PSR_ENABLE; + else { + for_each_pipe(dev_priv, pipe) { + stat[pipe] = I915_READ(VLV_PSRSTAT(pipe)) & + VLV_EDP_PSR_CURR_STATE_MASK; + if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) || + (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE)) + enabled = true; } } seq_printf(m, "HW Enabled & Active bit: %s", yesno(enabled)); @@ -2285,7 +2285,7 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) yesno((bool)dev_priv->psr.link_standby)); /* CHV PSR has no kind of performance counter */ - if (HAS_PSR(dev) && HAS_DDI(dev)) { + if (HAS_DDI(dev)) { psrperf = I915_READ(EDP_PSR_PERF_CNT(dev)) & EDP_PSR_PERF_CNT_MASK; @@ -2308,8 +2308,7 @@ static int i915_sink_crc(struct seq_file *m, void *data) u8 crc[6]; drm_modeset_lock_all(dev); - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_encoder(dev, connector) { if (connector->base.dpms != DRM_MODE_DPMS_ON) continue; @@ -2677,7 +2676,8 @@ 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), size %dx%d, addr 0x%08x, active? %s\n", yesno(crtc->cursor_base), - x, y, crtc->cursor_width, crtc->cursor_height, + x, y, crtc->base.cursor->state->crtc_w, + crtc->base.cursor->state->crtc_h, crtc->cursor_addr, yesno(active)); } @@ -2853,7 +2853,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused) for_each_pipe(dev_priv, pipe) { seq_printf(m, "Pipe %c\n", pipe_name(pipe)); - for_each_plane(pipe, plane) { + for_each_plane(dev_priv, pipe, plane) { entry = &ddb->plane[pipe][plane]; seq_printf(m, " Plane%-8d%8u%8u%8u\n", plane + 1, entry->start, entry->end, @@ -2870,6 +2870,115 @@ static int i915_ddb_info(struct seq_file *m, void *unused) return 0; } +static void drrs_status_per_crtc(struct seq_file *m, + struct drm_device *dev, struct intel_crtc *intel_crtc) +{ + struct intel_encoder *intel_encoder; + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_drrs *drrs = &dev_priv->drrs; + int vrefresh = 0; + + for_each_encoder_on_crtc(dev, &intel_crtc->base, intel_encoder) { + /* Encoder connected on this CRTC */ + switch (intel_encoder->type) { + case INTEL_OUTPUT_EDP: + seq_puts(m, "eDP:\n"); + break; + case INTEL_OUTPUT_DSI: + seq_puts(m, "DSI:\n"); + break; + case INTEL_OUTPUT_HDMI: + seq_puts(m, "HDMI:\n"); + break; + case INTEL_OUTPUT_DISPLAYPORT: + seq_puts(m, "DP:\n"); + break; + default: + seq_printf(m, "Other encoder (id=%d).\n", + intel_encoder->type); + return; + } + } + + if (dev_priv->vbt.drrs_type == STATIC_DRRS_SUPPORT) + seq_puts(m, "\tVBT: DRRS_type: Static"); + else if (dev_priv->vbt.drrs_type == SEAMLESS_DRRS_SUPPORT) + seq_puts(m, "\tVBT: DRRS_type: Seamless"); + else if (dev_priv->vbt.drrs_type == DRRS_NOT_SUPPORTED) + seq_puts(m, "\tVBT: DRRS_type: None"); + else + seq_puts(m, "\tVBT: DRRS_type: FIXME: Unrecognized Value"); + + seq_puts(m, "\n\n"); + + if (intel_crtc->config->has_drrs) { + struct intel_panel *panel; + + mutex_lock(&drrs->mutex); + /* DRRS Supported */ + seq_puts(m, "\tDRRS Supported: Yes\n"); + + /* disable_drrs() will make drrs->dp NULL */ + if (!drrs->dp) { + seq_puts(m, "Idleness DRRS: Disabled"); + mutex_unlock(&drrs->mutex); + return; + } + + panel = &drrs->dp->attached_connector->panel; + seq_printf(m, "\t\tBusy_frontbuffer_bits: 0x%X", + drrs->busy_frontbuffer_bits); + + seq_puts(m, "\n\t\t"); + if (drrs->refresh_rate_type == DRRS_HIGH_RR) { + seq_puts(m, "DRRS_State: DRRS_HIGH_RR\n"); + vrefresh = panel->fixed_mode->vrefresh; + } else if (drrs->refresh_rate_type == DRRS_LOW_RR) { + seq_puts(m, "DRRS_State: DRRS_LOW_RR\n"); + vrefresh = panel->downclock_mode->vrefresh; + } else { + seq_printf(m, "DRRS_State: Unknown(%d)\n", + drrs->refresh_rate_type); + mutex_unlock(&drrs->mutex); + return; + } + seq_printf(m, "\t\tVrefresh: %d", vrefresh); + + seq_puts(m, "\n\t\t"); + mutex_unlock(&drrs->mutex); + } else { + /* DRRS not supported. Print the VBT parameter*/ + seq_puts(m, "\tDRRS Supported : No"); + } + seq_puts(m, "\n"); +} + +static int i915_drrs_status(struct seq_file *m, void *unused) +{ + struct drm_info_node *node = m->private; + struct drm_device *dev = node->minor->dev; + struct intel_crtc *intel_crtc; + int active_crtc_cnt = 0; + + for_each_intel_crtc(dev, intel_crtc) { + drm_modeset_lock(&intel_crtc->base.mutex, NULL); + + if (intel_crtc->active) { + active_crtc_cnt++; + seq_printf(m, "\nCRTC %d: ", active_crtc_cnt); + + drrs_status_per_crtc(m, dev, intel_crtc); + } + + drm_modeset_unlock(&intel_crtc->base.mutex); + } + + if (!active_crtc_cnt) + seq_puts(m, "No active crtc found\n"); + + return 0; +} + struct pipe_crc_info { const char *name; struct drm_device *dev; @@ -4362,7 +4471,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused) struct drm_i915_private *dev_priv = dev->dev_private; unsigned int s_tot = 0, ss_tot = 0, ss_per = 0, eu_tot = 0, eu_per = 0; - if (INTEL_INFO(dev)->gen < 9) + if ((INTEL_INFO(dev)->gen < 8) || IS_BROADWELL(dev)) return -ENODEV; seq_puts(m, "SSEU Device Info\n"); @@ -4384,7 +4493,34 @@ static int i915_sseu_status(struct seq_file *m, void *unused) yesno(INTEL_INFO(dev)->has_eu_pg)); seq_puts(m, "SSEU Device Status\n"); - if (IS_SKYLAKE(dev)) { + if (IS_CHERRYVIEW(dev)) { + const int ss_max = 2; + int ss; + u32 sig1[ss_max], sig2[ss_max]; + + sig1[0] = I915_READ(CHV_POWER_SS0_SIG1); + sig1[1] = I915_READ(CHV_POWER_SS1_SIG1); + sig2[0] = I915_READ(CHV_POWER_SS0_SIG2); + sig2[1] = I915_READ(CHV_POWER_SS1_SIG2); + + for (ss = 0; ss < ss_max; ss++) { + unsigned int eu_cnt; + + if (sig1[ss] & CHV_SS_PG_ENABLE) + /* skip disabled subslice */ + continue; + + s_tot = 1; + ss_per++; + eu_cnt = ((sig1[ss] & CHV_EU08_PG_ENABLE) ? 0 : 2) + + ((sig1[ss] & CHV_EU19_PG_ENABLE) ? 0 : 2) + + ((sig1[ss] & CHV_EU210_PG_ENABLE) ? 0 : 2) + + ((sig2[ss] & CHV_EU311_PG_ENABLE) ? 0 : 2); + eu_tot += eu_cnt; + eu_per = max(eu_per, eu_cnt); + } + ss_tot = ss_per; + } else if (IS_SKYLAKE(dev)) { const int s_max = 3, ss_max = 4; int s, ss; u32 s_reg[s_max], eu_reg[2*s_max], eu_mask[2]; @@ -4548,6 +4684,7 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_wa_registers", i915_wa_registers, 0}, {"i915_ddb_info", i915_ddb_info, 0}, {"i915_sseu_status", i915_sseu_status, 0}, + {"i915_drrs_status", i915_drrs_status, 0}, }; #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 053e1788f578..d49ed68f041e 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -68,6 +68,9 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_CHIPSET_ID: value = dev->pdev->device; break; + case I915_PARAM_REVISION: + value = dev->pdev->revision; + break; case I915_PARAM_HAS_GEM: value = 1; break; @@ -150,6 +153,16 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_MMAP_VERSION: value = 1; break; + case I915_PARAM_SUBSLICE_TOTAL: + value = INTEL_INFO(dev)->subslice_total; + if (!value) + return -ENODEV; + break; + case I915_PARAM_EU_TOTAL: + value = INTEL_INFO(dev)->eu_total; + if (!value) + return -ENODEV; + break; default: DRM_DEBUG("Unknown parameter %d\n", param->param); return -EINVAL; @@ -608,14 +621,42 @@ static void intel_device_info_runtime_init(struct drm_device *dev) /* Initialize slice/subslice/EU info */ if (IS_CHERRYVIEW(dev)) { - u32 fuse, mask_eu; + u32 fuse, eu_dis; fuse = I915_READ(CHV_FUSE_GT); - mask_eu = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK | - CHV_FGT_EU_DIS_SS0_R1_MASK | - CHV_FGT_EU_DIS_SS1_R0_MASK | - CHV_FGT_EU_DIS_SS1_R1_MASK); - info->eu_total = 16 - hweight32(mask_eu); + + info->slice_total = 1; + + if (!(fuse & CHV_FGT_DISABLE_SS0)) { + info->subslice_per_slice++; + eu_dis = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK | + CHV_FGT_EU_DIS_SS0_R1_MASK); + info->eu_total += 8 - hweight32(eu_dis); + } + + if (!(fuse & CHV_FGT_DISABLE_SS1)) { + info->subslice_per_slice++; + eu_dis = fuse & (CHV_FGT_EU_DIS_SS1_R0_MASK | + CHV_FGT_EU_DIS_SS1_R1_MASK); + info->eu_total += 8 - hweight32(eu_dis); + } + + info->subslice_total = info->subslice_per_slice; + /* + * CHV expected to always have a uniform distribution of EU + * across subslices. + */ + info->eu_per_subslice = info->subslice_total ? + info->eu_total / info->subslice_total : + 0; + /* + * CHV supports subslice power gating on devices with more than + * one subslice, and supports EU power gating on devices with + * more than one EU pair per subslice. + */ + info->has_slice_pg = 0; + info->has_subslice_pg = (info->subslice_total > 1); + info->has_eu_pg = (info->eu_per_subslice > 2); } else if (IS_SKYLAKE(dev)) { const int s_max = 3, ss_max = 4, eu_max = 8; int s, ss; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 0001642c38b4..82f8be4b6745 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -346,7 +346,6 @@ static const struct intel_device_info intel_broadwell_gt3m_info = { }; 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, @@ -882,12 +881,6 @@ int i915_reset(struct drm_device *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 gt irqs. Skip for ironlake per * previous concerns that it doesn't respond well to some forms diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index ee5bc43dfc0b..8ba7e1b7b733 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -56,7 +56,7 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20150227" +#define DRIVER_DATE "20150313" #undef WARN_ON /* Many gcc seem to no see through this and fall over :( */ @@ -70,6 +70,9 @@ #define WARN_ON(x) WARN((x), "WARN_ON(" #x ")") #endif +#undef WARN_ON_ONCE +#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(" #x ")") + #define MISSING_CASE(x) WARN(1, "Missing switch case (%lu) in %s\n", \ (long) (x), __func__); @@ -223,9 +226,14 @@ enum hpd_pin { #define for_each_pipe(__dev_priv, __p) \ for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++) -#define for_each_plane(pipe, p) \ - for ((p) = 0; (p) < INTEL_INFO(dev)->num_sprites[(pipe)] + 1; (p)++) -#define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++) +#define for_each_plane(__dev_priv, __pipe, __p) \ + for ((__p) = 0; \ + (__p) < INTEL_INFO(__dev_priv)->num_sprites[(__pipe)] + 1; \ + (__p)++) +#define for_each_sprite(__dev_priv, __p, __s) \ + for ((__s) = 0; \ + (__s) < INTEL_INFO(__dev_priv)->num_sprites[(__p)]; \ + (__s)++) #define for_each_crtc(dev, crtc) \ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) @@ -238,6 +246,12 @@ enum hpd_pin { &(dev)->mode_config.encoder_list, \ base.head) +#define for_each_intel_connector(dev, intel_connector) \ + list_for_each_entry(intel_connector, \ + &dev->mode_config.connector_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)) @@ -783,10 +797,19 @@ struct intel_context { struct list_head link; }; +enum fb_op_origin { + ORIGIN_GTT, + ORIGIN_CPU, + ORIGIN_CS, + ORIGIN_FLIP, +}; + struct i915_fbc { unsigned long uncompressed_size; unsigned threshold; unsigned int fb_id; + unsigned int possible_framebuffer_bits; + unsigned int busy_bits; struct intel_crtc *crtc; int y; @@ -799,14 +822,6 @@ struct i915_fbc { * possible. */ bool enabled; - /* On gen8 some rings cannont perform fbc clean operation so for now - * we are doing this on SW with mmio. - * This variable works in the opposite information direction - * of ring->fbc_dirty telling software on frontbuffer tracking - * to perform the cache clean on sw side. - */ - bool need_sw_cache_clean; - struct intel_fbc_work { struct delayed_work work; struct drm_crtc *crtc; @@ -1053,9 +1068,6 @@ struct intel_ilk_power_mgmt { int c_m; int r_t; - - struct drm_i915_gem_object *pwrctx; - struct drm_i915_gem_object *renderctx; }; struct drm_i915_private; @@ -1398,6 +1410,25 @@ struct ilk_wm_values { enum intel_ddb_partitioning partitioning; }; +struct vlv_wm_values { + struct { + uint16_t primary; + uint16_t sprite[2]; + uint8_t cursor; + } pipe[3]; + + struct { + uint16_t plane; + uint8_t cursor; + } sr; + + struct { + uint8_t cursor; + uint8_t sprite[2]; + uint8_t primary; + } ddl[3]; +}; + struct skl_ddb_entry { uint16_t start, end; /* in number of blocks, 'end' is exclusive */ }; @@ -1760,6 +1791,7 @@ struct drm_i915_private { union { struct ilk_wm_values hw; struct skl_wm_values skl_hw; + struct vlv_wm_values vlv; }; } wm; @@ -2396,6 +2428,7 @@ struct drm_i915_cmd_table { #define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev)) #define GT_FREQUENCY_MULTIPLIER 50 +#define GEN9_FREQ_SCALER 3 #include "i915_trace.h" @@ -2433,7 +2466,7 @@ struct i915_params { bool disable_display; bool disable_vtd_wa; int use_mmio_flip; - bool mmio_debug; + int mmio_debug; bool verbose_state_checks; bool nuclear_pageflip; }; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 0107c2ae77d0..0fe313d0f609 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -351,7 +351,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, struct drm_device *dev = obj->base.dev; void *vaddr = obj->phys_handle->vaddr + args->offset; char __user *user_data = to_user_ptr(args->data_ptr); - int ret; + int ret = 0; /* We manually control the domain here and pretend that it * remains coherent i.e. in the GTT domain, like shmem_pwrite. @@ -360,6 +360,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, if (ret) return ret; + intel_fb_obj_invalidate(obj, NULL, ORIGIN_CPU); if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) { unsigned long unwritten; @@ -370,13 +371,18 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, mutex_unlock(&dev->struct_mutex); unwritten = copy_from_user(vaddr, user_data, args->size); mutex_lock(&dev->struct_mutex); - if (unwritten) - return -EFAULT; + if (unwritten) { + ret = -EFAULT; + goto out; + } } drm_clflush_virt_range(vaddr, args->size); i915_gem_chipset_flush(dev); - return 0; + +out: + intel_fb_obj_flush(obj, false); + return ret; } void *i915_gem_object_alloc(struct drm_device *dev) @@ -810,6 +816,8 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, offset = i915_gem_obj_ggtt_offset(obj) + args->offset; + intel_fb_obj_invalidate(obj, NULL, ORIGIN_GTT); + while (remain > 0) { /* Operation in this page * @@ -830,7 +838,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, if (fast_user_write(dev_priv->gtt.mappable, page_base, page_offset, user_data, page_length)) { ret = -EFAULT; - goto out_unpin; + goto out_flush; } remain -= page_length; @@ -838,6 +846,8 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, offset += page_length; } +out_flush: + intel_fb_obj_flush(obj, false); out_unpin: i915_gem_object_ggtt_unpin(obj); out: @@ -952,6 +962,8 @@ i915_gem_shmem_pwrite(struct drm_device *dev, if (ret) return ret; + intel_fb_obj_invalidate(obj, NULL, ORIGIN_CPU); + i915_gem_object_pin_pages(obj); offset = args->offset; @@ -1030,6 +1042,7 @@ out: if (needs_clflush_after) i915_gem_chipset_flush(dev); + intel_fb_obj_flush(obj, false); return ret; } @@ -2929,9 +2942,9 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) req = obj->last_read_req; /* Do this after OLR check to make sure we make forward progress polling - * on this IOCTL with a timeout <=0 (like busy ioctl) + * on this IOCTL with a timeout == 0 (like busy ioctl) */ - if (args->timeout_ns <= 0) { + if (args->timeout_ns == 0) { ret = -ETIME; goto out; } @@ -2941,7 +2954,8 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) i915_gem_request_reference(req); mutex_unlock(&dev->struct_mutex); - ret = __i915_wait_request(req, reset_counter, true, &args->timeout_ns, + ret = __i915_wait_request(req, reset_counter, true, + args->timeout_ns > 0 ? &args->timeout_ns : NULL, file->driver_priv); mutex_lock(&dev->struct_mutex); i915_gem_request_unreference(req); @@ -3756,7 +3770,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) } if (write) - intel_fb_obj_invalidate(obj, NULL); + intel_fb_obj_invalidate(obj, NULL, ORIGIN_GTT); trace_i915_gem_object_change_domain(obj, old_read_domains, @@ -4071,7 +4085,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write) } if (write) - intel_fb_obj_invalidate(obj, NULL); + intel_fb_obj_invalidate(obj, NULL, ORIGIN_CPU); trace_i915_gem_object_change_domain(obj, old_read_domains, @@ -4781,6 +4795,9 @@ i915_gem_init_hw(struct drm_device *dev) if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt()) return -EIO; + /* Double layer security blanket, see i915_gem_init() */ + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + if (dev_priv->ellc_size) I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf)); @@ -4813,7 +4830,7 @@ i915_gem_init_hw(struct drm_device *dev) for_each_ring(ring, dev_priv, i) { ret = ring->init_hw(ring); if (ret) - return ret; + goto out; } for (i = 0; i < NUM_L3_SLICES(dev); i++) @@ -4830,9 +4847,11 @@ i915_gem_init_hw(struct drm_device *dev) DRM_ERROR("Context enable failed %d\n", ret); i915_gem_cleanup_ringbuffer(dev); - return ret; + goto out; } +out: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); return ret; } @@ -4866,6 +4885,14 @@ int i915_gem_init(struct drm_device *dev) dev_priv->gt.stop_ring = intel_logical_ring_stop; } + /* This is just a security blanket to placate dragons. + * On some systems, we very sporadically observe that the first TLBs + * used by the CS may be stale, despite us poking the TLB reset. If + * we hold the forcewake during initialisation these problems + * just magically go away. + */ + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + ret = i915_gem_init_userptr(dev); if (ret) goto out_unlock; @@ -4892,6 +4919,7 @@ int i915_gem_init(struct drm_device *dev) } out_unlock: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); mutex_unlock(&dev->struct_mutex); return ret; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 85a6adaba258..dc10bc43864e 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -971,7 +971,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas, obj->dirty = 1; i915_gem_request_assign(&obj->last_write_req, req); - intel_fb_obj_invalidate(obj, ring); + intel_fb_obj_invalidate(obj, ring, ORIGIN_CS); /* update for the implicit flush after a batch */ obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS; @@ -1518,7 +1518,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, * - The batch is already pinned into the relevant ppgtt, so we * already have the backing storage fully allocated. * - No other BO uses the global gtt (well contexts, but meh), - * so we don't really have issues with mutliple objects not + * so we don't really have issues with multiple objects not * fitting due to fragmentation. * So this is actually safe. */ diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 74df3d1581dd..2034f7cf238b 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -716,15 +716,19 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) if (size % (1<<30)) DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size); - /* 1. Do all our allocations for page directories and page tables. */ - ret = gen8_ppgtt_alloc(ppgtt, max_pdp); + /* 1. Do all our allocations for page directories and page tables. + * We allocate more than was asked so that we can point the unused parts + * to valid entries that point to scratch page. Dynamic page tables + * will fix this eventually. + */ + ret = gen8_ppgtt_alloc(ppgtt, GEN8_LEGACY_PDPES); if (ret) return ret; /* * 2. Create DMA mappings for the page directories and page tables. */ - for (i = 0; i < max_pdp; i++) { + for (i = 0; i < GEN8_LEGACY_PDPES; i++) { ret = gen8_ppgtt_setup_page_directories(ppgtt, i); if (ret) goto bail; @@ -744,7 +748,7 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) * plugged in correctly. So we do that now/here. For aliasing PPGTT, we * will never need to touch the PDEs again. */ - for (i = 0; i < max_pdp; i++) { + for (i = 0; i < GEN8_LEGACY_PDPES; i++) { struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i]; gen8_ppgtt_pde_t *pd_vaddr; pd_vaddr = kmap_atomic(ppgtt->pdp.page_directory[i]->page); @@ -764,9 +768,14 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) ppgtt->base.insert_entries = gen8_ppgtt_insert_entries; ppgtt->base.cleanup = gen8_ppgtt_cleanup; ppgtt->base.start = 0; - ppgtt->base.total = ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE; - ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true); + /* This is the area that we advertise as usable for the caller */ + ppgtt->base.total = max_pdp * GEN8_PDES_PER_PAGE * GEN8_PTES_PER_PAGE * PAGE_SIZE; + + /* Set all ptes to a valid scratch page. Also above requested space */ + ppgtt->base.clear_range(&ppgtt->base, 0, + ppgtt->num_pd_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE, + true); DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n", ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9baecb79de8c..49ad5fb82ace 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1696,11 +1696,6 @@ static void i9xx_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe) * the work queue. */ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir) { - /* TODO: RPS on GEN9+ is not supported yet. */ - if (WARN_ONCE(INTEL_INFO(dev_priv)->gen >= 9, - "GEN9+: unexpected RPS IRQ\n")) - return; - if (pm_iir & dev_priv->pm_rps_events) { spin_lock(&dev_priv->irq_lock); gen6_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events); @@ -3169,15 +3164,24 @@ static void gen8_irq_reset(struct drm_device *dev) ibx_irq_reset(dev); } -void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv) +void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv, + unsigned int pipe_mask) { uint32_t extra_ier = GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN; spin_lock_irq(&dev_priv->irq_lock); - GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_B, dev_priv->de_irq_mask[PIPE_B], - ~dev_priv->de_irq_mask[PIPE_B] | extra_ier); - GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_C, dev_priv->de_irq_mask[PIPE_C], - ~dev_priv->de_irq_mask[PIPE_C] | extra_ier); + if (pipe_mask & 1 << PIPE_A) + GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_A, + dev_priv->de_irq_mask[PIPE_A], + ~dev_priv->de_irq_mask[PIPE_A] | extra_ier); + if (pipe_mask & 1 << PIPE_B) + GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_B, + dev_priv->de_irq_mask[PIPE_B], + ~dev_priv->de_irq_mask[PIPE_B] | extra_ier); + if (pipe_mask & 1 << PIPE_C) + GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_C, + dev_priv->de_irq_mask[PIPE_C], + ~dev_priv->de_irq_mask[PIPE_C] | extra_ier); spin_unlock_irq(&dev_priv->irq_lock); } diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 44f2262a5553..e2d20ffe6586 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -171,10 +171,10 @@ module_param_named(use_mmio_flip, i915.use_mmio_flip, int, 0600); MODULE_PARM_DESC(use_mmio_flip, "use MMIO flips (-1=never, 0=driver discretion [default], 1=always)"); -module_param_named(mmio_debug, i915.mmio_debug, bool, 0600); +module_param_named(mmio_debug, i915.mmio_debug, int, 0600); MODULE_PARM_DESC(mmio_debug, - "Enable the MMIO debug code (default: false). This may negatively " - "affect performance."); + "Enable the MMIO debug code for the first N failures (default: off). " + "This may negatively affect performance."); module_param_named(verbose_state_checks, i915.verbose_state_checks, bool, 0600); MODULE_PARM_DESC(verbose_state_checks, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 55143cb36e74..cc8ebabc488d 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -566,6 +566,9 @@ #define DSPFREQSTAT_MASK (0x3 << DSPFREQSTAT_SHIFT) #define DSPFREQGUAR_SHIFT 14 #define DSPFREQGUAR_MASK (0x3 << DSPFREQGUAR_SHIFT) +#define DSP_MAXFIFO_PM5_STATUS (1 << 22) /* chv */ +#define DSP_AUTO_CDCLK_GATE_DISABLE (1 << 7) /* chv */ +#define DSP_MAXFIFO_PM5_ENABLE (1 << 6) /* chv */ #define _DP_SSC(val, pipe) ((val) << (2 * (pipe))) #define DP_SSC_MASK(pipe) _DP_SSC(0x3, (pipe)) #define DP_SSC_PWR_ON(pipe) _DP_SSC(0x0, (pipe)) @@ -641,6 +644,11 @@ enum skl_disp_power_wells { #define FB_GFX_FMIN_AT_VMIN_FUSE 0x137 #define FB_GFX_FMIN_AT_VMIN_FUSE_SHIFT 8 +#define PUNIT_REG_DDR_SETUP2 0x139 +#define FORCE_DDR_FREQ_REQ_ACK (1 << 8) +#define FORCE_DDR_LOW_FREQ (1 << 1) +#define FORCE_DDR_HIGH_FREQ (1 << 0) + #define PUNIT_GPU_STATUS_REG 0xdb #define PUNIT_GPU_STATUS_MAX_FREQ_SHIFT 16 #define PUNIT_GPU_STATUS_MAX_FREQ_MASK 0xff @@ -1029,6 +1037,7 @@ enum skl_disp_power_wells { #define DPIO_CHV_FIRST_MOD (0 << 8) #define DPIO_CHV_SECOND_MOD (1 << 8) #define DPIO_CHV_FEEDFWD_GAIN_SHIFT 0 +#define DPIO_CHV_FEEDFWD_GAIN_MASK (0xF << 0) #define CHV_PLL_DW3(ch) _PIPE(ch, _CHV_PLL_DW3_CH0, _CHV_PLL_DW3_CH1) #define _CHV_PLL_DW6_CH0 0x8018 @@ -1040,11 +1049,14 @@ enum skl_disp_power_wells { #define _CHV_PLL_DW8_CH0 0x8020 #define _CHV_PLL_DW8_CH1 0x81A0 +#define DPIO_CHV_TDC_TARGET_CNT_SHIFT 0 +#define DPIO_CHV_TDC_TARGET_CNT_MASK (0x3FF << 0) #define CHV_PLL_DW8(ch) _PIPE(ch, _CHV_PLL_DW8_CH0, _CHV_PLL_DW8_CH1) #define _CHV_PLL_DW9_CH0 0x8024 #define _CHV_PLL_DW9_CH1 0x81A4 #define DPIO_CHV_INT_LOCK_THRESHOLD_SHIFT 1 /* 3 bits */ +#define DPIO_CHV_INT_LOCK_THRESHOLD_MASK (7 << 1) #define DPIO_CHV_INT_LOCK_THRESHOLD_SEL_COARSE 1 /* 1: coarse & 0 : fine */ #define CHV_PLL_DW9(ch) _PIPE(ch, _CHV_PLL_DW9_CH0, _CHV_PLL_DW9_CH1) @@ -1522,6 +1534,8 @@ enum skl_disp_power_wells { /* Fuse readout registers for GT */ #define CHV_FUSE_GT (VLV_DISPLAY_BASE + 0x2168) +#define CHV_FGT_DISABLE_SS0 (1 << 10) +#define CHV_FGT_DISABLE_SS1 (1 << 11) #define CHV_FGT_EU_DIS_SS0_R0_SHIFT 16 #define CHV_FGT_EU_DIS_SS0_R0_MASK (0xf << CHV_FGT_EU_DIS_SS0_R0_SHIFT) #define CHV_FGT_EU_DIS_SS0_R1_SHIFT 20 @@ -2099,6 +2113,14 @@ enum skl_disp_power_wells { #define CDCLK_FREQ_SHIFT 4 #define CDCLK_FREQ_MASK (0x1f << CDCLK_FREQ_SHIFT) #define CZCLK_FREQ_MASK 0xf + +#define GCI_CONTROL (VLV_DISPLAY_BASE + 0x650C) +#define PFI_CREDIT_63 (9 << 28) /* chv only */ +#define PFI_CREDIT_31 (8 << 28) /* chv only */ +#define PFI_CREDIT(x) (((x) - 8) << 28) /* 8-15 */ +#define PFI_CREDIT_RESEND (1 << 27) +#define VGA_FAST_MODE_DISABLE (1 << 14) + #define GMBUSFREQ_VLV (VLV_DISPLAY_BASE + 0x6510) /* @@ -2427,6 +2449,12 @@ enum skl_disp_power_wells { #define GEN6_RP_STATE_LIMITS (MCHBAR_MIRROR_BASE_SNB + 0x5994) #define GEN6_RP_STATE_CAP (MCHBAR_MIRROR_BASE_SNB + 0x5998) +#define INTERVAL_1_28_US(us) (((us) * 100) >> 7) +#define INTERVAL_1_33_US(us) (((us) * 3) >> 2) +#define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ + INTERVAL_1_33_US(us) : \ + INTERVAL_1_28_US(us)) + /* * Logical Context regs */ @@ -3019,7 +3047,7 @@ enum skl_disp_power_wells { /* Video Data Island Packet control */ #define VIDEO_DIP_DATA 0x61178 -/* Read the description of VIDEO_DIP_DATA (before Haswel) or VIDEO_DIP_ECC +/* Read the description of VIDEO_DIP_DATA (before Haswell) or VIDEO_DIP_ECC * (Haswell and newer) to see which VIDEO_DIP_DATA byte corresponds to each byte * of the infoframe structure specified by CEA-861. */ #define VIDEO_DIP_DATA_SIZE 32 @@ -4065,7 +4093,7 @@ enum skl_disp_power_wells { #define DPINVGTT_STATUS_MASK 0xff #define DPINVGTT_STATUS_MASK_CHV 0xfff -#define DSPARB 0x70030 +#define DSPARB (dev_priv->info.display_mmio_offset + 0x70030) #define DSPARB_CSTART_MASK (0x7f << 7) #define DSPARB_CSTART_SHIFT 7 #define DSPARB_BSTART_MASK (0x7f) @@ -4073,6 +4101,9 @@ enum skl_disp_power_wells { #define DSPARB_BEND_SHIFT 9 /* on 855 */ #define DSPARB_AEND_SHIFT 0 +#define DSPARB2 (VLV_DISPLAY_BASE + 0x70060) /* vlv/chv */ +#define DSPARB3 (VLV_DISPLAY_BASE + 0x7006c) /* chv */ + /* pnv/gen4/g4x/vlv/chv */ #define DSPFW1 (dev_priv->info.display_mmio_offset + 0x70034) #define DSPFW_SR_SHIFT 23 @@ -4096,8 +4127,8 @@ enum skl_disp_power_wells { #define DSPFW_SPRITEB_MASK_VLV (0xff<<16) /* vlv/chv */ #define DSPFW_CURSORA_SHIFT 8 #define DSPFW_CURSORA_MASK (0x3f<<8) -#define DSPFW_PLANEC_SHIFT_OLD 0 -#define DSPFW_PLANEC_MASK_OLD (0x7f<<0) /* pre-gen4 sprite C */ +#define DSPFW_PLANEC_OLD_SHIFT 0 +#define DSPFW_PLANEC_OLD_MASK (0x7f<<0) /* pre-gen4 sprite C */ #define DSPFW_SPRITEA_SHIFT 0 #define DSPFW_SPRITEA_MASK (0x7f<<0) /* g4x */ #define DSPFW_SPRITEA_MASK_VLV (0xff<<0) /* vlv/chv */ @@ -4136,25 +4167,25 @@ enum skl_disp_power_wells { #define DSPFW_SPRITED_WM1_SHIFT 24 #define DSPFW_SPRITED_WM1_MASK (0xff<<24) #define DSPFW_SPRITED_SHIFT 16 -#define DSPFW_SPRITED_MASK (0xff<<16) +#define DSPFW_SPRITED_MASK_VLV (0xff<<16) #define DSPFW_SPRITEC_WM1_SHIFT 8 #define DSPFW_SPRITEC_WM1_MASK (0xff<<8) #define DSPFW_SPRITEC_SHIFT 0 -#define DSPFW_SPRITEC_MASK (0xff<<0) +#define DSPFW_SPRITEC_MASK_VLV (0xff<<0) #define DSPFW8_CHV (VLV_DISPLAY_BASE + 0x700b8) #define DSPFW_SPRITEF_WM1_SHIFT 24 #define DSPFW_SPRITEF_WM1_MASK (0xff<<24) #define DSPFW_SPRITEF_SHIFT 16 -#define DSPFW_SPRITEF_MASK (0xff<<16) +#define DSPFW_SPRITEF_MASK_VLV (0xff<<16) #define DSPFW_SPRITEE_WM1_SHIFT 8 #define DSPFW_SPRITEE_WM1_MASK (0xff<<8) #define DSPFW_SPRITEE_SHIFT 0 -#define DSPFW_SPRITEE_MASK (0xff<<0) +#define DSPFW_SPRITEE_MASK_VLV (0xff<<0) #define DSPFW9_CHV (VLV_DISPLAY_BASE + 0x7007c) /* wtf #2? */ #define DSPFW_PLANEC_WM1_SHIFT 24 #define DSPFW_PLANEC_WM1_MASK (0xff<<24) #define DSPFW_PLANEC_SHIFT 16 -#define DSPFW_PLANEC_MASK (0xff<<16) +#define DSPFW_PLANEC_MASK_VLV (0xff<<16) #define DSPFW_CURSORC_WM1_SHIFT 8 #define DSPFW_CURSORC_WM1_MASK (0x3f<<16) #define DSPFW_CURSORC_SHIFT 0 @@ -4163,7 +4194,7 @@ enum skl_disp_power_wells { /* vlv/chv high order bits */ #define DSPHOWM (VLV_DISPLAY_BASE + 0x70064) #define DSPFW_SR_HI_SHIFT 24 -#define DSPFW_SR_HI_MASK (1<<24) +#define DSPFW_SR_HI_MASK (3<<24) /* 2 bits for chv, 1 for vlv */ #define DSPFW_SPRITEF_HI_SHIFT 23 #define DSPFW_SPRITEF_HI_MASK (1<<23) #define DSPFW_SPRITEE_HI_SHIFT 22 @@ -4184,7 +4215,7 @@ enum skl_disp_power_wells { #define DSPFW_PLANEA_HI_MASK (1<<0) #define DSPHOWM1 (VLV_DISPLAY_BASE + 0x70068) #define DSPFW_SR_WM1_HI_SHIFT 24 -#define DSPFW_SR_WM1_HI_MASK (1<<24) +#define DSPFW_SR_WM1_HI_MASK (3<<24) /* 2 bits for chv, 1 for vlv */ #define DSPFW_SPRITEF_WM1_HI_SHIFT 23 #define DSPFW_SPRITEF_WM1_HI_MASK (1<<23) #define DSPFW_SPRITEE_WM1_HI_SHIFT 22 @@ -4205,21 +4236,17 @@ enum skl_disp_power_wells { #define DSPFW_PLANEA_WM1_HI_MASK (1<<0) /* drain latency register values*/ -#define DRAIN_LATENCY_PRECISION_16 16 -#define DRAIN_LATENCY_PRECISION_32 32 -#define DRAIN_LATENCY_PRECISION_64 64 #define VLV_DDL(pipe) (VLV_DISPLAY_BASE + 0x70050 + 4 * (pipe)) -#define DDL_CURSOR_PRECISION_HIGH (1<<31) -#define DDL_CURSOR_PRECISION_LOW (0<<31) #define DDL_CURSOR_SHIFT 24 -#define DDL_SPRITE_PRECISION_HIGH(sprite) (1<<(15+8*(sprite))) -#define DDL_SPRITE_PRECISION_LOW(sprite) (0<<(15+8*(sprite))) #define DDL_SPRITE_SHIFT(sprite) (8+8*(sprite)) -#define DDL_PLANE_PRECISION_HIGH (1<<7) -#define DDL_PLANE_PRECISION_LOW (0<<7) #define DDL_PLANE_SHIFT 0 +#define DDL_PRECISION_HIGH (1<<7) +#define DDL_PRECISION_LOW (0<<7) #define DRAIN_LATENCY_MASK 0x7f +#define CBR1_VLV (VLV_DISPLAY_BASE + 0x70400) +#define CBR_PND_DEADLINE_DISABLE (1<<31) + /* FIFO watermark sizes etc */ #define G4X_FIFO_LINE_SIZE 64 #define I915_FIFO_LINE_SIZE 64 @@ -6080,6 +6107,7 @@ enum skl_disp_power_wells { #define GEN6_TURBO_DISABLE (1<<31) #define GEN6_FREQUENCY(x) ((x)<<25) #define HSW_FREQUENCY(x) ((x)<<24) +#define GEN9_FREQUENCY(x) ((x)<<23) #define GEN6_OFFSET(x) ((x)<<19) #define GEN6_AGGRESSIVE_TURBO (0<<15) #define GEN6_RC_VIDEO_FREQ 0xA00C @@ -6098,8 +6126,10 @@ enum skl_disp_power_wells { #define GEN6_RPSTAT1 0xA01C #define GEN6_CAGF_SHIFT 8 #define HSW_CAGF_SHIFT 7 +#define GEN9_CAGF_SHIFT 23 #define GEN6_CAGF_MASK (0x7f << GEN6_CAGF_SHIFT) #define HSW_CAGF_MASK (0x7f << HSW_CAGF_SHIFT) +#define GEN9_CAGF_MASK (0x1ff << GEN9_CAGF_SHIFT) #define GEN6_RP_CONTROL 0xA024 #define GEN6_RP_MEDIA_TURBO (1<<11) #define GEN6_RP_MEDIA_MODE_MASK (3<<9) @@ -6225,6 +6255,17 @@ enum skl_disp_power_wells { #define GEN6_RC6 3 #define GEN6_RC7 4 +#define CHV_POWER_SS0_SIG1 0xa720 +#define CHV_POWER_SS1_SIG1 0xa728 +#define CHV_SS_PG_ENABLE (1<<1) +#define CHV_EU08_PG_ENABLE (1<<9) +#define CHV_EU19_PG_ENABLE (1<<17) +#define CHV_EU210_PG_ENABLE (1<<25) + +#define CHV_POWER_SS0_SIG2 0xa724 +#define CHV_POWER_SS1_SIG2 0xa72c +#define CHV_EU311_PG_ENABLE (1<<1) + #define GEN9_SLICE0_PGCTL_ACK 0x804c #define GEN9_SLICE1_PGCTL_ACK 0x8050 #define GEN9_SLICE2_PGCTL_ACK 0x8054 diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 67bd07edcbb0..247626885f49 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -319,7 +319,9 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev, ret = intel_gpu_freq(dev_priv, (freq >> 8) & 0xff); } else { u32 rpstat = I915_READ(GEN6_RPSTAT1); - if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) + if (IS_GEN9(dev_priv)) + ret = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT; + else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) ret = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT; else ret = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT; diff --git a/drivers/gpu/drm/i915/i915_vgpu.h b/drivers/gpu/drm/i915/i915_vgpu.h index 0db9ccf32605..97a88b5f6a26 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.h +++ b/drivers/gpu/drm/i915/i915_vgpu.h @@ -32,7 +32,7 @@ * The following structure pages are defined in GEN MMIO space * for virtualization. (One page for now) */ -#define VGT_MAGIC 0x4776544776544776 /* 'vGTvGTvG' */ +#define VGT_MAGIC 0x4776544776544776ULL /* 'vGTvGTvG' */ #define VGT_VERSION_MAJOR 1 #define VGT_VERSION_MINOR 0 diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index 011b8960fd75..3903b90fb64e 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -214,12 +214,18 @@ struct drm_crtc_state * intel_crtc_duplicate_state(struct drm_crtc *crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc_state *crtc_state; if (WARN_ON(!intel_crtc->config)) - return kzalloc(sizeof(*intel_crtc->config), GFP_KERNEL); + crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL); + else + crtc_state = kmemdup(intel_crtc->config, + sizeof(*intel_crtc->config), GFP_KERNEL); - return kmemdup(intel_crtc->config, sizeof(*intel_crtc->config), - GFP_KERNEL); + if (crtc_state) + crtc_state->base.crtc = crtc; + + return &crtc_state->base; } /** diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 985d531aaf9e..8aee7d77ce9d 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -156,16 +156,7 @@ static const struct ddi_buf_trans skl_ddi_translations_edp[] = { static const struct ddi_buf_trans skl_ddi_translations_hdmi[] = { /* Idx NT mV T mV db */ - { 0x00000018, 0x000000a0 }, /* 0: 400 400 0 */ - { 0x00004014, 0x00000098 }, /* 1: 400 600 3.5 */ - { 0x00006012, 0x00000088 }, /* 2: 400 800 6 */ - { 0x00000018, 0x0000003c }, /* 3: 450 450 0 */ - { 0x00000018, 0x00000098 }, /* 4: 600 600 0 */ - { 0x00003015, 0x00000088 }, /* 5: 600 800 2.5 */ - { 0x00005013, 0x00000080 }, /* 6: 600 1000 4.5 */ - { 0x00000018, 0x00000088 }, /* 7: 800 800 0 */ - { 0x00000096, 0x00000080 }, /* 8: 800 1000 2 */ - { 0x00000018, 0x00000080 }, /* 9: 1200 1200 0 */ + { 0x00004014, 0x00000087 }, /* 0: 800 1000 2 */ }; enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder) @@ -202,7 +193,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port) { struct drm_i915_private *dev_priv = dev->dev_private; u32 reg; - int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_800mV_0dB, + int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry, size; int hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; const struct ddi_buf_trans *ddi_translations_fdi; @@ -223,9 +214,16 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port) n_edp_entries = ARRAY_SIZE(skl_ddi_translations_dp); } + /* + * On SKL, the recommendation from the hw team is to always use + * a certain type of level shifter (and thus the corresponding + * 800mV+2dB entry). Given that's the only validated entry, we + * override what is in the VBT, at least until further notice. + */ + hdmi_level = 0; ddi_translations_hdmi = skl_ddi_translations_hdmi; n_hdmi_entries = ARRAY_SIZE(skl_ddi_translations_hdmi); - hdmi_800mV_0dB = 7; + hdmi_default_entry = 0; } else if (IS_BROADWELL(dev)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; @@ -234,7 +232,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port) n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); - hdmi_800mV_0dB = 7; + hdmi_default_entry = 7; } else if (IS_HASWELL(dev)) { ddi_translations_fdi = hsw_ddi_translations_fdi; ddi_translations_dp = hsw_ddi_translations_dp; @@ -242,7 +240,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port) ddi_translations_hdmi = hsw_ddi_translations_hdmi; n_dp_entries = n_edp_entries = ARRAY_SIZE(hsw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi); - hdmi_800mV_0dB = 6; + hdmi_default_entry = 6; } else { WARN(1, "ddi translation table missing\n"); ddi_translations_edp = bdw_ddi_translations_dp; @@ -252,7 +250,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port) n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); - hdmi_800mV_0dB = 7; + hdmi_default_entry = 7; } switch (port) { @@ -295,7 +293,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port) /* Choose a good default if VBT is badly populated */ if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN || hdmi_level >= n_hdmi_entries) - hdmi_level = hdmi_800mV_0dB; + hdmi_level = hdmi_default_entry; /* Entry 9 is for HDMI: */ I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans1); @@ -786,9 +784,18 @@ static void skl_ddi_clock_get(struct intel_encoder *encoder, case DPLL_CRTL1_LINK_RATE_810: link_clock = 81000; break; + case DPLL_CRTL1_LINK_RATE_1080: + link_clock = 108000; + break; case DPLL_CRTL1_LINK_RATE_1350: link_clock = 135000; break; + case DPLL_CRTL1_LINK_RATE_1620: + link_clock = 162000; + break; + case DPLL_CRTL1_LINK_RATE_2160: + link_clock = 216000; + break; case DPLL_CRTL1_LINK_RATE_2700: link_clock = 270000; break; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 1aa1cbd16c19..90b460cf2b57 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -37,6 +37,7 @@ #include <drm/i915_drm.h> #include "i915_drv.h" #include "i915_trace.h" +#include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_dp_helper.h> #include <drm/drm_crtc_helper.h> @@ -390,7 +391,7 @@ static const intel_limit_t intel_limits_chv = { * them would make no difference. */ .dot = { .min = 25000 * 5, .max = 540000 * 5}, - .vco = { .min = 4860000, .max = 6480000 }, + .vco = { .min = 4800000, .max = 6480000 }, .n = { .min = 1, .max = 1 }, .m1 = { .min = 2, .max = 2 }, .m2 = { .min = 24 << 22, .max = 175 << 22 }, @@ -896,8 +897,12 @@ bool intel_crtc_active(struct drm_crtc *crtc) * * We can ditch the crtc->primary->fb check as soon as we can * properly reconstruct framebuffers. + * + * FIXME: The intel_crtc->active here should be switched to + * crtc->state->active once we have proper CRTC states wired up + * for atomic. */ - return intel_crtc->active && crtc->primary->fb && + return intel_crtc->active && crtc->primary->state->fb && intel_crtc->config->base.adjusted_mode.crtc_clock; } @@ -1300,14 +1305,14 @@ static void assert_sprites_disabled(struct drm_i915_private *dev_priv, u32 val; if (INTEL_INFO(dev)->gen >= 9) { - for_each_sprite(pipe, sprite) { + for_each_sprite(dev_priv, pipe, sprite) { val = I915_READ(PLANE_CTL(pipe, sprite)); I915_STATE_WARN(val & PLANE_CTL_ENABLE, "plane %d assertion failure, should be off on pipe %c but is still active\n", sprite, pipe_name(pipe)); } } else if (IS_VALLEYVIEW(dev)) { - for_each_sprite(pipe, sprite) { + for_each_sprite(dev_priv, pipe, sprite) { reg = SPCNTR(pipe, sprite); val = I915_READ(reg); I915_STATE_WARN(val & SP_ENABLE, @@ -2533,7 +2538,6 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, break; } } - } static void i9xx_update_primary_plane(struct drm_crtc *crtc, @@ -2654,9 +2658,6 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc, I915_WRITE(reg, dspcntr); - DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n", - i915_gem_obj_ggtt_offset(obj), linear_offset, x, y, - fb->pitches[0]); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); if (INTEL_INFO(dev)->gen >= 4) { I915_WRITE(DSPSURF(plane), @@ -2758,9 +2759,6 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc, I915_WRITE(reg, dspcntr); - DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n", - i915_gem_obj_ggtt_offset(obj), linear_offset, x, y, - fb->pitches[0]); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); I915_WRITE(DSPSURF(plane), i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); @@ -2886,11 +2884,6 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, I915_WRITE(PLANE_CTL(pipe, 0), plane_ctl); - DRM_DEBUG_KMS("Writing base %08lX %d,%d,%d,%d pitch=%d\n", - i915_gem_obj_ggtt_offset(obj), - x, y, fb->width, fb->height, - fb->pitches[0]); - I915_WRITE(PLANE_POS(pipe, 0), 0); I915_WRITE(PLANE_OFFSET(pipe, 0), (y << 16) | x); I915_WRITE(PLANE_SIZE(pipe, 0), @@ -3148,38 +3141,6 @@ static void intel_fdi_normal_train(struct drm_crtc *crtc) FDI_FE_ERRC_ENABLE); } -static bool pipe_has_enabled_pch(struct intel_crtc *crtc) -{ - return crtc->base.state->enable && crtc->active && - crtc->config->has_pch_encoder; -} - -static void ivb_modeset_global_resources(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *pipe_B_crtc = - to_intel_crtc(dev_priv->pipe_to_crtc_mapping[PIPE_B]); - struct intel_crtc *pipe_C_crtc = - to_intel_crtc(dev_priv->pipe_to_crtc_mapping[PIPE_C]); - uint32_t temp; - - /* - * When everything is off disable fdi C so that we could enable fdi B - * with all lanes. Note that we don't care about enabled pipes without - * an enabled pch encoder. - */ - if (!pipe_has_enabled_pch(pipe_B_crtc) && - !pipe_has_enabled_pch(pipe_C_crtc)) { - WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE); - WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE); - - temp = I915_READ(SOUTH_CHICKEN1); - temp &= ~FDI_BC_BIFURCATION_SELECT; - DRM_DEBUG_KMS("disabling fdi C rx\n"); - I915_WRITE(SOUTH_CHICKEN1, temp); - } -} - /* The FDI link training functions for ILK/Ibexpeak. */ static void ironlake_fdi_link_train(struct drm_crtc *crtc) { @@ -3835,20 +3796,23 @@ static void ironlake_pch_transcoder_set_timings(struct intel_crtc *crtc, I915_READ(VSYNCSHIFT(cpu_transcoder))); } -static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev) +static void cpt_set_fdi_bc_bifurcation(struct drm_device *dev, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; uint32_t temp; temp = I915_READ(SOUTH_CHICKEN1); - if (temp & FDI_BC_BIFURCATION_SELECT) + if (!!(temp & FDI_BC_BIFURCATION_SELECT) == enable) return; WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE); WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE); - temp |= FDI_BC_BIFURCATION_SELECT; - DRM_DEBUG_KMS("enabling fdi C rx\n"); + temp &= ~FDI_BC_BIFURCATION_SELECT; + if (enable) + temp |= FDI_BC_BIFURCATION_SELECT; + + DRM_DEBUG_KMS("%sabling fdi C rx\n", enable ? "en" : "dis"); I915_WRITE(SOUTH_CHICKEN1, temp); POSTING_READ(SOUTH_CHICKEN1); } @@ -3856,20 +3820,19 @@ static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev) static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc) { struct drm_device *dev = intel_crtc->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; switch (intel_crtc->pipe) { case PIPE_A: break; case PIPE_B: if (intel_crtc->config->fdi_lanes > 2) - WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT); + cpt_set_fdi_bc_bifurcation(dev, false); else - cpt_enable_fdi_bc_bifurcation(dev); + cpt_set_fdi_bc_bifurcation(dev, true); break; case PIPE_C: - cpt_enable_fdi_bc_bifurcation(dev); + cpt_set_fdi_bc_bifurcation(dev, true); break; default: @@ -4204,6 +4167,24 @@ static void intel_enable_sprite_planes(struct drm_crtc *crtc) } } +/* + * Disable a plane internally without actually modifying the plane's state. + * This will allow us to easily restore the plane later by just reprogramming + * its state. + */ +static void disable_plane_internal(struct drm_plane *plane) +{ + struct intel_plane *intel_plane = to_intel_plane(plane); + struct drm_plane_state *state = + plane->funcs->atomic_duplicate_state(plane); + struct intel_plane_state *intel_state = to_intel_plane_state(state); + + intel_state->visible = false; + intel_plane->commit_plane(plane, intel_state); + + intel_plane_destroy_state(plane, state); +} + static void intel_disable_sprite_planes(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -4213,8 +4194,8 @@ static void intel_disable_sprite_planes(struct drm_crtc *crtc) drm_for_each_legacy_plane(plane, &dev->mode_config.plane_list) { intel_plane = to_intel_plane(plane); - if (intel_plane->pipe == pipe) - plane->funcs->disable_plane(plane); + if (plane->fb && intel_plane->pipe == pipe) + disable_plane_internal(plane); } } @@ -4983,24 +4964,23 @@ static void cherryview_set_cdclk(struct drm_device *dev, int cdclk) WARN_ON(dev_priv->display.get_display_clock_speed(dev) != dev_priv->vlv_cdclk_freq); switch (cdclk) { - case 400000: - cmd = 3; - break; case 333333: case 320000: - cmd = 2; - break; case 266667: - cmd = 1; - break; case 200000: - cmd = 0; break; default: MISSING_CASE(cdclk); return; } + /* + * Specs are full of misinformation, but testing on actual + * hardware has shown that we just need to write the desired + * CCK divider into the Punit register. + */ + cmd = DIV_ROUND_CLOSEST(dev_priv->hpll_freq << 1, cdclk) - 1; + mutex_lock(&dev_priv->rps.hw_lock); val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ); val &= ~DSPFREQGUAR_MASK_CHV; @@ -5020,27 +5000,25 @@ static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv, int max_pixclk) { int freq_320 = (dev_priv->hpll_freq << 1) % 320000 != 0 ? 333333 : 320000; - - /* FIXME: Punit isn't quite ready yet */ - if (IS_CHERRYVIEW(dev_priv->dev)) - return 400000; + int limit = IS_CHERRYVIEW(dev_priv) ? 95 : 90; /* * Really only a few cases to deal with, as only 4 CDclks are supported: * 200MHz * 267MHz * 320/333MHz (depends on HPLL freq) - * 400MHz - * So we check to see whether we're above 90% of the lower bin and - * adjust if needed. + * 400MHz (VLV only) + * So we check to see whether we're above 90% (VLV) or 95% (CHV) + * of the lower bin and adjust if needed. * * We seem to get an unstable or solid color picture at 200MHz. * Not sure what's wrong. For now use 200MHz only when all pipes * are off. */ - if (max_pixclk > freq_320*9/10) + if (!IS_CHERRYVIEW(dev_priv) && + max_pixclk > freq_320*limit/100) return 400000; - else if (max_pixclk > 266667*9/10) + else if (max_pixclk > 266667*limit/100) return freq_320; else if (max_pixclk > 0) return 266667; @@ -5081,6 +5059,42 @@ static void valleyview_modeset_global_pipes(struct drm_device *dev, *prepare_pipes |= (1 << intel_crtc->pipe); } +static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv) +{ + unsigned int credits, default_credits; + + if (IS_CHERRYVIEW(dev_priv)) + default_credits = PFI_CREDIT(12); + else + default_credits = PFI_CREDIT(8); + + if (DIV_ROUND_CLOSEST(dev_priv->vlv_cdclk_freq, 1000) >= dev_priv->rps.cz_freq) { + /* CHV suggested value is 31 or 63 */ + if (IS_CHERRYVIEW(dev_priv)) + credits = PFI_CREDIT_31; + else + credits = PFI_CREDIT(15); + } else { + credits = default_credits; + } + + /* + * WA - write default credits before re-programming + * FIXME: should we also set the resend bit here? + */ + I915_WRITE(GCI_CONTROL, VGA_FAST_MODE_DISABLE | + default_credits); + + I915_WRITE(GCI_CONTROL, VGA_FAST_MODE_DISABLE | + credits | PFI_CREDIT_RESEND); + + /* + * FIXME is this guaranteed to clear + * immediately or should we poll for it? + */ + WARN_ON(I915_READ(GCI_CONTROL) & PFI_CREDIT_RESEND); +} + static void valleyview_modeset_global_resources(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -5104,6 +5118,8 @@ static void valleyview_modeset_global_resources(struct drm_device *dev) else valleyview_set_cdclk(dev, req_cdclk); + vlv_program_pfi_credits(dev_priv); + intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A); } } @@ -5517,13 +5533,21 @@ bool intel_connector_get_hw_state(struct intel_connector *connector) return encoder->get_hw_state(encoder, &pipe); } +static int pipe_required_fdi_lanes(struct drm_device *dev, enum pipe pipe) +{ + struct intel_crtc *crtc = + to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe)); + + if (crtc->base.state->enable && + crtc->config->has_pch_encoder) + return crtc->config->fdi_lanes; + + return 0; +} + static bool ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, struct intel_crtc_state *pipe_config) { - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *pipe_B_crtc = - to_intel_crtc(dev_priv->pipe_to_crtc_mapping[PIPE_B]); - DRM_DEBUG_KMS("checking fdi config on pipe %c, lanes %i\n", pipe_name(pipe), pipe_config->fdi_lanes); if (pipe_config->fdi_lanes > 4) { @@ -5550,22 +5574,20 @@ static bool ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, case PIPE_A: return true; case PIPE_B: - if (dev_priv->pipe_to_crtc_mapping[PIPE_C]->enabled && - pipe_config->fdi_lanes > 2) { + if (pipe_config->fdi_lanes > 2 && + pipe_required_fdi_lanes(dev, PIPE_C) > 0) { DRM_DEBUG_KMS("invalid shared fdi lane config on pipe %c: %i lanes\n", pipe_name(pipe), pipe_config->fdi_lanes); return false; } return true; case PIPE_C: - if (!pipe_has_enabled_pch(pipe_B_crtc) || - pipe_B_crtc->config->fdi_lanes <= 2) { - if (pipe_config->fdi_lanes > 2) { - DRM_DEBUG_KMS("invalid shared fdi lane config on pipe %c: %i lanes\n", - pipe_name(pipe), pipe_config->fdi_lanes); - return false; - } - } else { + if (pipe_config->fdi_lanes > 2) { + DRM_DEBUG_KMS("only 2 lanes on pipe %c: required %i lanes\n", + pipe_name(pipe), pipe_config->fdi_lanes); + return false; + } + if (pipe_required_fdi_lanes(dev, PIPE_B) > 2) { DRM_DEBUG_KMS("fdi link B uses too many lanes to enable link C\n"); return false; } @@ -5699,10 +5721,6 @@ static int valleyview_get_display_clock_speed(struct drm_device *dev) u32 val; int divider; - /* FIXME: Punit isn't quite ready yet */ - if (IS_CHERRYVIEW(dev)) - return 400000; - if (dev_priv->hpll_freq == 0) dev_priv->hpll_freq = valleyview_get_vco(dev_priv); @@ -6144,9 +6162,10 @@ static void chv_prepare_pll(struct intel_crtc *crtc, int pipe = crtc->pipe; int dpll_reg = DPLL(crtc->pipe); enum dpio_channel port = vlv_pipe_to_channel(pipe); - u32 loopfilter, intcoeff; + u32 loopfilter, tribuf_calcntr; u32 bestn, bestm1, bestm2, bestp1, bestp2, bestm2_frac; - int refclk; + u32 dpio_val; + int vco; bestn = pipe_config->dpll.n; bestm2_frac = pipe_config->dpll.m2 & 0x3fffff; @@ -6154,6 +6173,9 @@ static void chv_prepare_pll(struct intel_crtc *crtc, bestm2 = pipe_config->dpll.m2 >> 22; bestp1 = pipe_config->dpll.p1; bestp2 = pipe_config->dpll.p2; + vco = pipe_config->dpll.vco; + dpio_val = 0; + loopfilter = 0; /* * Enable Refclk and SSC @@ -6179,26 +6201,56 @@ static void chv_prepare_pll(struct intel_crtc *crtc, 1 << DPIO_CHV_N_DIV_SHIFT); /* M2 fraction division */ - vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac); + if (bestm2_frac) + 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)); + dpio_val = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW3(port)); + dpio_val &= ~(DPIO_CHV_FEEDFWD_GAIN_MASK | DPIO_CHV_FRAC_DIV_EN); + dpio_val |= (2 << DPIO_CHV_FEEDFWD_GAIN_SHIFT); + if (bestm2_frac) + dpio_val |= DPIO_CHV_FRAC_DIV_EN; + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW3(port), dpio_val); + + /* Program digital lock detect threshold */ + dpio_val = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW9(port)); + dpio_val &= ~(DPIO_CHV_INT_LOCK_THRESHOLD_MASK | + DPIO_CHV_INT_LOCK_THRESHOLD_SEL_COARSE); + dpio_val |= (0x5 << DPIO_CHV_INT_LOCK_THRESHOLD_SHIFT); + if (!bestm2_frac) + dpio_val |= DPIO_CHV_INT_LOCK_THRESHOLD_SEL_COARSE; + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW9(port), dpio_val); /* Loop filter */ - refclk = i9xx_get_refclk(crtc, 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; + if (vco == 5400000) { + loopfilter |= (0x3 << DPIO_CHV_PROP_COEFF_SHIFT); + loopfilter |= (0x8 << DPIO_CHV_INT_COEFF_SHIFT); + loopfilter |= (0x1 << DPIO_CHV_GAIN_CTRL_SHIFT); + tribuf_calcntr = 0x9; + } else if (vco <= 6200000) { + loopfilter |= (0x5 << DPIO_CHV_PROP_COEFF_SHIFT); + loopfilter |= (0xB << DPIO_CHV_INT_COEFF_SHIFT); + loopfilter |= (0x3 << DPIO_CHV_GAIN_CTRL_SHIFT); + tribuf_calcntr = 0x9; + } else if (vco <= 6480000) { + loopfilter |= (0x4 << DPIO_CHV_PROP_COEFF_SHIFT); + loopfilter |= (0x9 << DPIO_CHV_INT_COEFF_SHIFT); + loopfilter |= (0x3 << DPIO_CHV_GAIN_CTRL_SHIFT); + tribuf_calcntr = 0x8; + } else { + /* Not supported. Apply the same limits as in the max case */ + loopfilter |= (0x4 << DPIO_CHV_PROP_COEFF_SHIFT); + loopfilter |= (0x9 << DPIO_CHV_INT_COEFF_SHIFT); + loopfilter |= (0x3 << DPIO_CHV_GAIN_CTRL_SHIFT); + tribuf_calcntr = 0; + } vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW6(port), loopfilter); + dpio_val = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW8(port)); + dpio_val &= ~DPIO_CHV_TDC_TARGET_CNT_MASK; + dpio_val |= (tribuf_calcntr << DPIO_CHV_TDC_TARGET_CNT_SHIFT); + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW8(port), dpio_val); + /* AFC Recal */ vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)) | @@ -8409,8 +8461,8 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base) uint32_t cntl = 0, size = 0; if (base) { - unsigned int width = intel_crtc->cursor_width; - unsigned int height = intel_crtc->cursor_height; + unsigned int width = intel_crtc->base.cursor->state->crtc_w; + unsigned int height = intel_crtc->base.cursor->state->crtc_h; unsigned int stride = roundup_pow_of_two(width) * 4; switch (stride) { @@ -8474,7 +8526,7 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) cntl = 0; if (base) { cntl = MCURSOR_GAMMA_ENABLE; - switch (intel_crtc->cursor_width) { + switch (intel_crtc->base.cursor->state->crtc_w) { case 64: cntl |= CURSOR_MODE_64_ARGB_AX; break; @@ -8485,7 +8537,7 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) cntl |= CURSOR_MODE_256_ARGB_AX; break; default: - MISSING_CASE(intel_crtc->cursor_width); + MISSING_CASE(intel_crtc->base.cursor->state->crtc_w); return; } cntl |= pipe << 28; /* Connect to correct pipe */ @@ -8532,7 +8584,7 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, base = 0; if (x < 0) { - if (x + intel_crtc->cursor_width <= 0) + if (x + intel_crtc->base.cursor->state->crtc_w <= 0) base = 0; pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; @@ -8541,7 +8593,7 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, pos |= x << CURSOR_X_SHIFT; if (y < 0) { - if (y + intel_crtc->cursor_height <= 0) + if (y + intel_crtc->base.cursor->state->crtc_h <= 0) base = 0; pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; @@ -8557,8 +8609,8 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, /* ILK+ do this automagically */ if (HAS_GMCH_DISPLAY(dev) && crtc->cursor->state->rotation == BIT(DRM_ROTATE_180)) { - base += (intel_crtc->cursor_height * - intel_crtc->cursor_width - 1) * 4; + base += (intel_crtc->base.cursor->state->crtc_h * + intel_crtc->base.cursor->state->crtc_w - 1) * 4; } if (IS_845G(dev) || IS_I865G(dev)) @@ -9219,7 +9271,6 @@ static void intel_unpin_work_fn(struct work_struct *__work) mutex_lock(&dev->struct_mutex); intel_unpin_fb_obj(intel_fb_obj(work->old_fb)); drm_gem_object_unreference(&work->pending_flip_obj->base); - drm_framebuffer_unreference(work->old_fb); intel_fbc_update(dev); @@ -9228,6 +9279,7 @@ static void intel_unpin_work_fn(struct work_struct *__work) mutex_unlock(&dev->struct_mutex); intel_frontbuffer_flip_complete(dev, INTEL_FRONTBUFFER_PRIMARY(pipe)); + drm_framebuffer_unreference(work->old_fb); BUG_ON(atomic_read(&to_intel_crtc(work->crtc)->unpin_work_count) == 0); atomic_dec(&to_intel_crtc(work->crtc)->unpin_work_count); @@ -9799,7 +9851,7 @@ void intel_check_page_flip(struct drm_device *dev, int pipe) struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - WARN_ON(!in_irq()); + WARN_ON(!in_interrupt()); if (crtc == NULL) return; @@ -9891,10 +9943,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, if (atomic_read(&intel_crtc->unpin_work_count) >= 2) flush_workqueue(dev_priv->wq); - ret = i915_mutex_lock_interruptible(dev); - if (ret) - goto cleanup; - /* Reference the objects for the scheduled work. */ drm_framebuffer_reference(work->old_fb); drm_gem_object_reference(&obj->base); @@ -9904,6 +9952,10 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, work->pending_flip_obj = obj; + ret = i915_mutex_lock_interruptible(dev); + if (ret) + goto cleanup; + atomic_inc(&intel_crtc->unpin_work_count); intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); @@ -9968,13 +10020,14 @@ cleanup_unpin: intel_unpin_fb_obj(obj); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); + mutex_unlock(&dev->struct_mutex); +cleanup: crtc->primary->fb = old_fb; update_state_fb(crtc->primary); + + drm_gem_object_unreference_unlocked(&obj->base); drm_framebuffer_unreference(work->old_fb); - drm_gem_object_unreference(&obj->base); - mutex_unlock(&dev->struct_mutex); -cleanup: spin_lock_irq(&dev->event_lock); intel_crtc->unpin_work = NULL; spin_unlock_irq(&dev->event_lock); @@ -10014,8 +10067,7 @@ static void intel_modeset_update_staged_output_state(struct drm_device *dev) struct intel_encoder *encoder; struct intel_connector *connector; - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { connector->new_encoder = to_intel_encoder(connector->base.encoder); } @@ -10046,8 +10098,7 @@ static void intel_modeset_commit_output_state(struct drm_device *dev) struct intel_encoder *encoder; struct intel_connector *connector; - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { connector->base.encoder = &connector->new_encoder->base; } @@ -10135,8 +10186,7 @@ compute_baseline_pipe_bpp(struct intel_crtc *crtc, pipe_config->pipe_bpp = bpp; /* Clamp display bpp to EDID value */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (!connector->new_encoder || connector->new_encoder->new_crtc != crtc) continue; @@ -10263,8 +10313,7 @@ static bool check_digital_port_conflicts(struct drm_device *dev) * list to detect the problem on ddi platforms * where there's just one encoder per digital port. */ - list_for_each_entry(connector, - &dev->mode_config.connector_list, base.head) { + for_each_intel_connector(dev, connector) { struct intel_encoder *encoder = connector->new_encoder; if (!encoder) @@ -10437,8 +10486,7 @@ intel_modeset_affected_pipes(struct drm_crtc *crtc, unsigned *modeset_pipes, * to be part of the prepare_pipes mask. We don't (yet) support global * modeset across multiple crtcs, so modeset_pipes will only have one * bit set at most. */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->base.encoder == &connector->new_encoder->base) continue; @@ -10807,7 +10855,7 @@ static void check_wm_state(struct drm_device *dev) continue; /* planes */ - for_each_plane(pipe, plane) { + for_each_plane(dev_priv, pipe, plane) { hw_entry = &hw_ddb.plane[pipe][plane]; sw_entry = &sw_ddb->plane[pipe][plane]; @@ -10841,8 +10889,7 @@ check_connector_state(struct drm_device *dev) { struct intel_connector *connector; - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { /* This also checks the encoder/connector hw state with the * ->get_hw_state callbacks. */ intel_connector_check_state(connector); @@ -10872,8 +10919,7 @@ check_encoder_state(struct drm_device *dev) I915_STATE_WARN(encoder->connectors_active && !encoder->base.crtc, "encoder's active_connectors set, but no crtc\n"); - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->base.encoder != &encoder->base) continue; enabled = true; @@ -11394,7 +11440,7 @@ static void intel_set_config_restore_state(struct drm_device *dev, } count = 0; - list_for_each_entry(connector, &dev->mode_config.connector_list, base.head) { + for_each_intel_connector(dev, connector) { connector->new_encoder = to_intel_encoder(config->save_connector_encoders[count++]); } @@ -11486,8 +11532,7 @@ intel_modeset_stage_output_state(struct drm_device *dev, WARN_ON(!set->fb && (set->num_connectors != 0)); WARN_ON(set->fb && (set->num_connectors == 0)); - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { /* Otherwise traverse passed in connector list and get encoders * for them. */ for (ro = 0; ro < set->num_connectors; ro++) { @@ -11512,15 +11557,16 @@ intel_modeset_stage_output_state(struct drm_device *dev, if (&connector->new_encoder->base != connector->base.encoder) { - DRM_DEBUG_KMS("encoder changed, full mode switch\n"); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] encoder changed, full mode switch\n", + connector->base.base.id, + connector->base.name); config->mode_changed = true; } } /* connector->new_encoder is now updated for all connectors. */ /* Update crtc of enabled connectors. */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { struct drm_crtc *new_crtc; if (!connector->new_encoder) @@ -11549,9 +11595,7 @@ intel_modeset_stage_output_state(struct drm_device *dev, /* Check for any encoders that needs to be disabled. */ for_each_intel_encoder(dev, encoder) { int num_connectors = 0; - list_for_each_entry(connector, - &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->new_encoder == encoder) { WARN_ON(!connector->new_encoder->new_crtc); num_connectors++; @@ -11566,13 +11610,14 @@ intel_modeset_stage_output_state(struct drm_device *dev, /* Only now check for crtc changes so we don't miss encoders * that will be disabled. */ if (&encoder->new_crtc->base != encoder->base.crtc) { - DRM_DEBUG_KMS("crtc changed, full mode switch\n"); + DRM_DEBUG_KMS("[ENCODER:%d:%s] crtc changed, full mode switch\n", + encoder->base.base.id, + encoder->base.name); config->mode_changed = true; } } /* Now we've also updated encoder->new_crtc for all encoders. */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->new_encoder) if (connector->new_encoder != connector->encoder) connector->encoder = connector->new_encoder; @@ -11588,7 +11633,8 @@ intel_modeset_stage_output_state(struct drm_device *dev, } if (crtc->new_enabled != crtc->base.state->enable) { - DRM_DEBUG_KMS("crtc %sabled, full mode switch\n", + DRM_DEBUG_KMS("[CRTC:%d] %sabled, full mode switch\n", + crtc->base.base.id, crtc->new_enabled ? "en" : "dis"); config->mode_changed = true; } @@ -11611,7 +11657,7 @@ static void disable_crtc_nofb(struct intel_crtc *crtc) DRM_DEBUG_KMS("Trying to restore without FB -> disabling pipe %c\n", pipe_name(crtc->pipe)); - list_for_each_entry(connector, &dev->mode_config.connector_list, base.head) { + for_each_intel_connector(dev, connector) { if (connector->new_encoder && connector->new_encoder->new_crtc == crtc) connector->new_encoder = NULL; @@ -12182,8 +12228,8 @@ void intel_plane_destroy(struct drm_plane *plane) } const struct drm_plane_funcs intel_plane_funcs = { - .update_plane = drm_atomic_helper_update_plane, - .disable_plane = drm_atomic_helper_disable_plane, + .update_plane = drm_plane_helper_update, + .disable_plane = drm_plane_helper_disable, .destroy = intel_plane_destroy, .set_property = drm_atomic_helper_plane_set_property, .atomic_get_property = intel_plane_atomic_get_property, @@ -12302,7 +12348,7 @@ intel_check_cursor_plane(struct drm_plane *plane, finish: if (intel_crtc->active) { - if (intel_crtc->cursor_width != state->base.crtc_w) + if (plane->state->crtc_w != state->base.crtc_w) intel_crtc->atomic.update_wm = true; intel_crtc->atomic.fb_bits |= @@ -12345,8 +12391,6 @@ intel_commit_cursor_plane(struct drm_plane *plane, intel_crtc->cursor_addr = addr; intel_crtc->cursor_bo = obj; update: - intel_crtc->cursor_width = state->base.crtc_w; - intel_crtc->cursor_height = state->base.crtc_h; if (intel_crtc->active) intel_crtc_update_cursor(crtc, state->visible); @@ -12574,10 +12618,15 @@ static void intel_setup_outputs(struct drm_device *dev) if (HAS_DDI(dev)) { int found; - /* Haswell uses DDI functions to detect digital outputs */ + /* + * Haswell uses DDI functions to detect digital outputs. + * On SKL pre-D0 the strap isn't connected, so we assume + * it's there. + */ found = I915_READ(DDI_BUF_CTL_A) & DDI_INIT_DISPLAY_DETECTED; - /* DDI A only supports eDP */ - if (found) + /* WaIgnoreDDIAStrap: skl */ + if (found || + (IS_SKYLAKE(dev) && INTEL_REVID(dev) < SKL_REVID_D0)) intel_ddi_init(dev, PORT_A); /* DDI B, C and D detection is indicated by the SFUSE_STRAP @@ -13068,8 +13117,6 @@ static void intel_init_display(struct drm_device *dev) } else if (IS_IVYBRIDGE(dev)) { /* FIXME: detect B0+ stepping and use auto training */ dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train; - dev_priv->display.modeset_global_resources = - ivb_modeset_global_resources; } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { dev_priv->display.fdi_link_train = hsw_fdi_link_train; } else if (IS_VALLEYVIEW(dev)) { @@ -13365,7 +13412,7 @@ void intel_modeset_init(struct drm_device *dev) for_each_pipe(dev_priv, pipe) { intel_crtc_init(dev, pipe); - for_each_sprite(pipe, sprite) { + for_each_sprite(dev_priv, pipe, sprite) { ret = intel_plane_init(dev, pipe, sprite); if (ret) DRM_DEBUG_KMS("pipe %c sprite %c init failed: %d\n", @@ -13421,9 +13468,7 @@ static void intel_enable_pipe_a(struct drm_device *dev) /* 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 * by enabling the load detect pipe once. */ - list_for_each_entry(connector, - &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->encoder->type == INTEL_OUTPUT_ANALOG) { crt = &connector->base; break; @@ -13494,8 +13539,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) crtc->plane = plane; /* ... and break all links. */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->encoder->base.crtc != &crtc->base) continue; @@ -13504,8 +13548,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) } /* multiple connectors may have the same encoder: * handle them and break crtc link separately */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) + for_each_intel_connector(dev, connector) if (connector->encoder->base.crtc == &crtc->base) { connector->encoder->base.crtc = NULL; connector->encoder->connectors_active = false; @@ -13609,9 +13652,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) * a bug in one of the get_hw_state functions. Or someplace else * in our code, like the register restore mess on resume. Clamp * things to off as a safer default. */ - list_for_each_entry(connector, - &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->encoder != encoder) continue; connector->base.dpms = DRM_MODE_DPMS_OFF; @@ -13726,8 +13767,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) pipe_name(pipe)); } - list_for_each_entry(connector, &dev->mode_config.connector_list, - base.head) { + for_each_intel_connector(dev, connector) { if (connector->get_hw_state(connector)) { connector->base.dpms = DRM_MODE_DPMS_ON; connector->encoder->connectors_active = true; @@ -13907,8 +13947,6 @@ void intel_modeset_cleanup(struct drm_device *dev) intel_fbc_disable(dev); - ironlake_teardown_rc6(dev); - mutex_unlock(&dev->struct_mutex); /* flush any delayed tasks or pending work */ diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index d1141d37e205..ca60060710d2 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -84,6 +84,11 @@ static const struct dp_link_dpll chv_dpll[] = { { DP_LINK_BW_5_4, /* m2_int = 27, m2_fraction = 0 */ { .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } } }; +/* Skylake supports following rates */ +static const uint32_t gen9_rates[] = { 162000, 216000, 270000, 324000, + 432000, 540000 }; + +static const uint32_t default_rates[] = { 162000, 270000, 540000 }; /** * is_edp - is the given port attached to an eDP panel (either CPU or PCH) @@ -129,7 +134,10 @@ intel_dp_max_link_bw(struct intel_dp *intel_dp) case DP_LINK_BW_2_7: break; case DP_LINK_BW_5_4: /* 1.2 capable displays may advertise higher bw */ - if (((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) || + if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) + /* WaDisableHBR2:skl */ + max_link_bw = DP_LINK_BW_2_7; + else if (((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) || INTEL_INFO(dev)->gen >= 8) && intel_dp->dpcd[DP_DPCD_REV] >= 0x12) max_link_bw = DP_LINK_BW_5_4; @@ -1075,7 +1083,7 @@ intel_dp_connector_unregister(struct intel_connector *intel_connector) } static void -skl_edp_set_pll_config(struct intel_crtc_state *pipe_config, int link_bw) +skl_edp_set_pll_config(struct intel_crtc_state *pipe_config, int link_clock) { u32 ctrl1; @@ -1084,19 +1092,35 @@ skl_edp_set_pll_config(struct intel_crtc_state *pipe_config, int link_bw) pipe_config->dpll_hw_state.cfgcr2 = 0; ctrl1 = DPLL_CTRL1_OVERRIDE(SKL_DPLL0); - switch (link_bw) { - case DP_LINK_BW_1_62: + switch (link_clock / 2) { + case 81000: ctrl1 |= DPLL_CRTL1_LINK_RATE(DPLL_CRTL1_LINK_RATE_810, SKL_DPLL0); break; - case DP_LINK_BW_2_7: + case 135000: ctrl1 |= DPLL_CRTL1_LINK_RATE(DPLL_CRTL1_LINK_RATE_1350, SKL_DPLL0); break; - case DP_LINK_BW_5_4: + case 270000: ctrl1 |= DPLL_CRTL1_LINK_RATE(DPLL_CRTL1_LINK_RATE_2700, SKL_DPLL0); break; + case 162000: + ctrl1 |= DPLL_CRTL1_LINK_RATE(DPLL_CRTL1_LINK_RATE_1620, + SKL_DPLL0); + break; + /* TBD: For DP link rates 2.16 GHz and 4.32 GHz, VCO is 8640 which + results in CDCLK change. Need to handle the change of CDCLK by + disabling pipes and re-enabling them */ + case 108000: + ctrl1 |= DPLL_CRTL1_LINK_RATE(DPLL_CRTL1_LINK_RATE_1080, + SKL_DPLL0); + break; + case 216000: + ctrl1 |= DPLL_CRTL1_LINK_RATE(DPLL_CRTL1_LINK_RATE_2160, + SKL_DPLL0); + break; + } pipe_config->dpll_hw_state.ctrl1 = ctrl1; } @@ -1117,6 +1141,52 @@ hsw_dp_set_ddi_pll_sel(struct intel_crtc_state *pipe_config, int link_bw) } } +static int +intel_read_sink_rates(struct intel_dp *intel_dp, uint32_t *sink_rates) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + int i = 0; + uint16_t val; + + if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) { + /* + * Receiver supports only main-link rate selection by + * link rate table method, so read link rates from + * supported_link_rates + */ + for (i = 0; i < DP_MAX_SUPPORTED_RATES; ++i) { + val = le16_to_cpu(intel_dp->supported_rates[i]); + if (val == 0) + break; + + sink_rates[i] = val * 200; + } + + if (i <= 0) + DRM_ERROR("No rates in SUPPORTED_LINK_RATES"); + } + return i; +} + +static int +intel_read_source_rates(struct intel_dp *intel_dp, uint32_t *source_rates) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + int i; + int max_default_rate; + + if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) { + for (i = 0; i < ARRAY_SIZE(gen9_rates); ++i) + source_rates[i] = gen9_rates[i]; + } else { + /* Index of the max_link_bw supported + 1 */ + max_default_rate = (intel_dp_max_link_bw(intel_dp) >> 3) + 1; + for (i = 0; i < max_default_rate; ++i) + source_rates[i] = default_rates[i]; + } + return i; +} + static void intel_dp_set_clock(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, int link_bw) @@ -1150,6 +1220,45 @@ intel_dp_set_clock(struct intel_encoder *encoder, } } +static int intel_supported_rates(const uint32_t *source_rates, int source_len, +const uint32_t *sink_rates, int sink_len, uint32_t *supported_rates) +{ + int i = 0, j = 0, k = 0; + + /* For panels with edp version less than 1.4 */ + if (sink_len == 0) { + for (i = 0; i < source_len; ++i) + supported_rates[i] = source_rates[i]; + return source_len; + } + + /* For edp1.4 panels, find the common rates between source and sink */ + while (i < source_len && j < sink_len) { + if (source_rates[i] == sink_rates[j]) { + supported_rates[k] = source_rates[i]; + ++k; + ++i; + ++j; + } else if (source_rates[i] < sink_rates[j]) { + ++i; + } else { + ++j; + } + } + return k; +} + +static int rate_to_index(uint32_t find, const uint32_t *rates) +{ + int i = 0; + + for (i = 0; i < DP_MAX_SUPPORTED_RATES; ++i) + if (find == rates[i]) + break; + + return i; +} + bool intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) @@ -1166,10 +1275,25 @@ intel_dp_compute_config(struct intel_encoder *encoder, int max_lane_count = intel_dp_max_lane_count(intel_dp); /* Conveniently, the link BW constants become indices with a shift...*/ int min_clock = 0; - int max_clock = intel_dp_max_link_bw(intel_dp) >> 3; + int max_clock; int bpp, mode_rate; - static int bws[] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7, DP_LINK_BW_5_4 }; int link_avail, link_clock; + uint32_t sink_rates[8]; + uint32_t supported_rates[8] = {0}; + uint32_t source_rates[8]; + int source_len, sink_len, supported_len; + + sink_len = intel_read_sink_rates(intel_dp, sink_rates); + + source_len = intel_read_source_rates(intel_dp, source_rates); + + supported_len = intel_supported_rates(source_rates, source_len, + sink_rates, sink_len, supported_rates); + + /* No common link rates between source and sink */ + WARN_ON(supported_len <= 0); + + max_clock = supported_len - 1; if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev) && port != PORT_A) pipe_config->has_pch_encoder = true; @@ -1193,8 +1317,8 @@ intel_dp_compute_config(struct intel_encoder *encoder, return false; DRM_DEBUG_KMS("DP link computation with max lane count %i " - "max bw %02x pixel clock %iKHz\n", - max_lane_count, bws[max_clock], + "max bw %d pixel clock %iKHz\n", + max_lane_count, supported_rates[max_clock], adjusted_mode->crtc_clock); /* Walk through all bpp values. Luckily they're all nicely spaced with 2 @@ -1223,8 +1347,11 @@ intel_dp_compute_config(struct intel_encoder *encoder, bpp); for (clock = min_clock; clock <= max_clock; clock++) { - for (lane_count = min_lane_count; lane_count <= max_lane_count; lane_count <<= 1) { - link_clock = drm_dp_bw_code_to_link_rate(bws[clock]); + for (lane_count = min_lane_count; + lane_count <= max_lane_count; + lane_count <<= 1) { + + link_clock = supported_rates[clock]; link_avail = intel_dp_max_data_rate(link_clock, lane_count); @@ -1253,10 +1380,19 @@ found: if (intel_dp->color_range) pipe_config->limited_color_range = true; - intel_dp->link_bw = bws[clock]; intel_dp->lane_count = lane_count; + + intel_dp->link_bw = + drm_dp_link_rate_to_bw_code(supported_rates[clock]); + + if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) { + intel_dp->rate_select = + rate_to_index(supported_rates[clock], sink_rates); + intel_dp->link_bw = 0; + } + pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw); + pipe_config->port_clock = supported_rates[clock]; DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n", intel_dp->link_bw, intel_dp->lane_count, @@ -1279,7 +1415,7 @@ found: } if (IS_SKYLAKE(dev) && is_edp(intel_dp)) - skl_edp_set_pll_config(pipe_config, intel_dp->link_bw); + skl_edp_set_pll_config(pipe_config, supported_rates[clock]); else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hsw_dp_set_ddi_pll_sel(pipe_config, intel_dp->link_bw); else @@ -3366,6 +3502,9 @@ intel_dp_start_link_train(struct intel_dp *intel_dp) if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); + if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) + drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, + &intel_dp->rate_select, 1); link_config[0] = 0; link_config[1] = DP_SET_ANSI_8B10B; @@ -3578,6 +3717,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_device *dev = dig_port->base.base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + uint8_t rev; if (intel_dp_dpcd_read_wake(&intel_dp->aux, 0x000, intel_dp->dpcd, sizeof(intel_dp->dpcd)) < 0) @@ -3609,6 +3749,16 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) } else intel_dp->use_tps3 = false; + /* Intermediate frequency support */ + if (is_edp(intel_dp) && + (intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] & DP_DPCD_DISPLAY_CONTROL_CAPABLE) && + (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_EDP_DPCD_REV, &rev, 1) == 1) && + (rev >= 0x03)) { /* eDp v1.4 or higher */ + intel_dp_dpcd_read_wake(&intel_dp->aux, + DP_SUPPORTED_LINK_RATES, + intel_dp->supported_rates, + sizeof(intel_dp->supported_rates)); + } if (!(intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT)) return true; /* native DP sink */ @@ -4966,12 +5116,13 @@ void intel_edp_drrs_invalidate(struct drm_device *dev, if (!dev_priv->drrs.dp) return; + cancel_delayed_work_sync(&dev_priv->drrs.work); + mutex_lock(&dev_priv->drrs.mutex); crtc = dp_to_dig_port(dev_priv->drrs.dp)->base.base.crtc; pipe = to_intel_crtc(crtc)->pipe; if (dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR) { - cancel_delayed_work_sync(&dev_priv->drrs.work); intel_dp_set_drrs_state(dev_priv->dev, dev_priv->drrs.dp->attached_connector->panel. fixed_mode->vrefresh); @@ -5004,13 +5155,13 @@ void intel_edp_drrs_flush(struct drm_device *dev, if (!dev_priv->drrs.dp) return; + cancel_delayed_work_sync(&dev_priv->drrs.work); + mutex_lock(&dev_priv->drrs.mutex); crtc = dp_to_dig_port(dev_priv->drrs.dp)->base.base.crtc; pipe = to_intel_crtc(crtc)->pipe; dev_priv->drrs.busy_frontbuffer_bits &= ~frontbuffer_bits; - cancel_delayed_work_sync(&dev_priv->drrs.work); - if (dev_priv->drrs.refresh_rate_type != DRRS_LOW_RR && !dev_priv->drrs.busy_frontbuffer_bits) schedule_delayed_work(&dev_priv->drrs.work, diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 9f67a379a9a5..be124928ca14 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -58,7 +58,7 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, pipe_config->pipe_bpp = 24; pipe_config->port_clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw); - list_for_each_entry(intel_connector, &dev->mode_config.connector_list, base.head) { + for_each_intel_connector(dev, intel_connector) { if (intel_connector->new_encoder == encoder) { found = intel_connector; break; @@ -140,7 +140,7 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder) struct drm_crtc *crtc = encoder->base.crtc; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - list_for_each_entry(intel_connector, &dev->mode_config.connector_list, base.head) { + for_each_intel_connector(dev, intel_connector) { if (intel_connector->new_encoder == encoder) { found = intel_connector; break; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index f4aa849b243e..c77128c67cf8 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -464,7 +464,6 @@ struct intel_crtc { struct drm_i915_gem_object *cursor_bo; uint32_t cursor_addr; - int16_t cursor_width, cursor_height; uint32_t cursor_cntl; uint32_t cursor_size; uint32_t cursor_base; @@ -623,10 +622,12 @@ struct intel_dp { uint32_t color_range; bool color_range_auto; uint8_t link_bw; + uint8_t rate_select; uint8_t lane_count; uint8_t dpcd[DP_RECEIVER_CAP_SIZE]; uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE]; uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS]; + __le16 supported_rates[DP_MAX_SUPPORTED_RATES]; struct drm_dp_aux aux; uint8_t train_set[4]; int panel_power_up_delay; @@ -839,7 +840,8 @@ static inline bool intel_irqs_enabled(struct drm_i915_private *dev_priv) } int intel_get_crtc_scanline(struct intel_crtc *crtc); -void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv); +void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv, + unsigned int pipe_mask); /* intel_crt.c */ void intel_crt_init(struct drm_device *dev); @@ -874,7 +876,8 @@ void intel_ddi_set_vc_payload_alloc(struct drm_crtc *crtc, bool state); /* intel_frontbuffer.c */ void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj, - struct intel_engine_cs *ring); + struct intel_engine_cs *ring, + enum fb_op_origin origin); void intel_frontbuffer_flip_prepare(struct drm_device *dev, unsigned frontbuffer_bits); void intel_frontbuffer_flip_complete(struct drm_device *dev, @@ -1115,7 +1118,11 @@ bool intel_fbc_enabled(struct drm_device *dev); void intel_fbc_update(struct drm_device *dev); void intel_fbc_init(struct drm_i915_private *dev_priv); void intel_fbc_disable(struct drm_device *dev); -void bdw_fbc_sw_flush(struct drm_device *dev, u32 value); +void intel_fbc_invalidate(struct drm_i915_private *dev_priv, + unsigned int frontbuffer_bits, + enum fb_op_origin origin); +void intel_fbc_flush(struct drm_i915_private *dev_priv, + unsigned int frontbuffer_bits); /* intel_hdmi.c */ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port); @@ -1231,7 +1238,6 @@ void intel_enable_gt_powersave(struct drm_device *dev); void intel_disable_gt_powersave(struct drm_device *dev); void intel_suspend_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); void gen6_rps_boost(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 618f7bdab0ba..9fcf446e95f5 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -174,29 +174,10 @@ static bool g4x_fbc_enabled(struct drm_device *dev) return I915_READ(DPFC_CONTROL) & DPFC_CTL_EN; } -static void snb_fbc_blit_update(struct drm_device *dev) +static void intel_fbc_nuke(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; - u32 blt_ecoskpd; - - /* Make sure blitter notifies FBC of writes */ - - /* Blitter is part of Media powerwell on VLV. No impact of - * his param in other platforms for now */ - intel_uncore_forcewake_get(dev_priv, FORCEWAKE_MEDIA); - - blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD); - blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY << - GEN6_BLITTER_LOCK_SHIFT; - I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd); - blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY; - I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd); - blt_ecoskpd &= ~(GEN6_BLITTER_FBC_NOTIFY << - GEN6_BLITTER_LOCK_SHIFT); - I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd); - POSTING_READ(GEN6_BLITTER_ECOSKPD); - - intel_uncore_forcewake_put(dev_priv, FORCEWAKE_MEDIA); + I915_WRITE(MSG_FBC_REND_STATE, FBC_REND_NUKE); + POSTING_READ(MSG_FBC_REND_STATE); } static void ilk_fbc_enable(struct drm_crtc *crtc) @@ -239,9 +220,10 @@ static void ilk_fbc_enable(struct drm_crtc *crtc) I915_WRITE(SNB_DPFC_CTL_SA, SNB_CPU_FENCE_ENABLE | obj->fence_reg); I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->y); - snb_fbc_blit_update(dev); } + intel_fbc_nuke(dev_priv); + DRM_DEBUG_KMS("enabled fbc on plane %c\n", plane_name(intel_crtc->plane)); } @@ -320,7 +302,7 @@ static void gen7_fbc_enable(struct drm_crtc *crtc) SNB_CPU_FENCE_ENABLE | obj->fence_reg); I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->y); - snb_fbc_blit_update(dev); + intel_fbc_nuke(dev_priv); DRM_DEBUG_KMS("enabled fbc on plane %c\n", plane_name(intel_crtc->plane)); } @@ -340,19 +322,6 @@ bool intel_fbc_enabled(struct drm_device *dev) return dev_priv->fbc.enabled; } -void bdw_fbc_sw_flush(struct drm_device *dev, u32 value) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - if (!IS_GEN8(dev)) - return; - - if (!intel_fbc_enabled(dev)) - return; - - I915_WRITE(MSG_FBC_REND_STATE, value); -} - static void intel_fbc_work_fn(struct work_struct *__work) { struct intel_fbc_work *work = @@ -685,6 +654,44 @@ out_disable: i915_gem_stolen_cleanup_compression(dev); } +void intel_fbc_invalidate(struct drm_i915_private *dev_priv, + unsigned int frontbuffer_bits, + enum fb_op_origin origin) +{ + struct drm_device *dev = dev_priv->dev; + unsigned int fbc_bits; + + if (origin == ORIGIN_GTT) + return; + + if (dev_priv->fbc.enabled) + fbc_bits = INTEL_FRONTBUFFER_PRIMARY(dev_priv->fbc.crtc->pipe); + else if (dev_priv->fbc.fbc_work) + fbc_bits = INTEL_FRONTBUFFER_PRIMARY( + to_intel_crtc(dev_priv->fbc.fbc_work->crtc)->pipe); + else + fbc_bits = dev_priv->fbc.possible_framebuffer_bits; + + dev_priv->fbc.busy_bits |= (fbc_bits & frontbuffer_bits); + + if (dev_priv->fbc.busy_bits) + intel_fbc_disable(dev); +} + +void intel_fbc_flush(struct drm_i915_private *dev_priv, + unsigned int frontbuffer_bits) +{ + struct drm_device *dev = dev_priv->dev; + + if (!dev_priv->fbc.busy_bits) + return; + + dev_priv->fbc.busy_bits &= ~frontbuffer_bits; + + if (!dev_priv->fbc.busy_bits) + intel_fbc_update(dev); +} + /** * intel_fbc_init - Initialize FBC * @dev_priv: the i915 device @@ -693,12 +700,22 @@ out_disable: */ void intel_fbc_init(struct drm_i915_private *dev_priv) { + enum pipe pipe; + if (!HAS_FBC(dev_priv)) { dev_priv->fbc.enabled = false; dev_priv->fbc.no_fbc_reason = FBC_UNSUPPORTED; return; } + for_each_pipe(dev_priv, pipe) { + dev_priv->fbc.possible_framebuffer_bits |= + INTEL_FRONTBUFFER_PRIMARY(pipe); + + if (IS_HASWELL(dev_priv) || INTEL_INFO(dev_priv)->gen >= 8) + break; + } + if (INTEL_INFO(dev_priv)->gen >= 7) { dev_priv->display.fbc_enabled = ilk_fbc_enabled; dev_priv->display.enable_fbc = gen7_fbc_enable; diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 234a699b8219..757c0d216f80 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -71,6 +71,31 @@ static int intel_fbdev_set_par(struct fb_info *info) return ret; } +static int intel_fbdev_blank(int blank, struct fb_info *info) +{ + struct drm_fb_helper *fb_helper = info->par; + struct intel_fbdev *ifbdev = + container_of(fb_helper, struct intel_fbdev, helper); + int ret; + + ret = drm_fb_helper_blank(blank, info); + + if (ret == 0) { + /* + * FIXME: fbdev presumes that all callbacks also work from + * atomic contexts and relies on that for emergency oops + * printing. KMS totally doesn't do that and the locking here is + * by far not the only place this goes wrong. Ignore this for + * now until we solve this for real. + */ + mutex_lock(&fb_helper->dev->struct_mutex); + intel_fb_obj_invalidate(ifbdev->fb->obj, NULL, ORIGIN_GTT); + mutex_unlock(&fb_helper->dev->struct_mutex); + } + + return ret; +} + static struct fb_ops intelfb_ops = { .owner = THIS_MODULE, .fb_check_var = drm_fb_helper_check_var, @@ -79,7 +104,7 @@ static struct fb_ops intelfb_ops = { .fb_copyarea = cfb_copyarea, .fb_imageblit = cfb_imageblit, .fb_pan_display = drm_fb_helper_pan_display, - .fb_blank = drm_fb_helper_blank, + .fb_blank = intel_fbdev_blank, .fb_setcmap = drm_fb_helper_setcmap, .fb_debug_enter = drm_fb_helper_debug_enter, .fb_debug_leave = drm_fb_helper_debug_leave, diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c index 73cb6e036445..0a1bac8ac72b 100644 --- a/drivers/gpu/drm/i915/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/intel_frontbuffer.c @@ -118,8 +118,6 @@ static void intel_mark_fb_busy(struct drm_device *dev, continue; intel_increase_pllclock(dev, pipe); - if (ring && intel_fbc_enabled(dev)) - ring->fbc_dirty = true; } } @@ -127,6 +125,7 @@ static void intel_mark_fb_busy(struct drm_device *dev, * intel_fb_obj_invalidate - invalidate frontbuffer object * @obj: GEM object to invalidate * @ring: set for asynchronous rendering + * @origin: which operation caused the invalidation * * This function gets called every time rendering on the given object starts and * frontbuffer caching (fbc, low refresh rate for DRRS, panel self refresh) must @@ -135,7 +134,8 @@ static void intel_mark_fb_busy(struct drm_device *dev, * scheduled. */ void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj, - struct intel_engine_cs *ring) + struct intel_engine_cs *ring, + enum fb_op_origin origin) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -158,6 +158,7 @@ void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj, intel_psr_invalidate(dev, obj->frontbuffer_bits); intel_edp_drrs_invalidate(dev, obj->frontbuffer_bits); + intel_fbc_invalidate(dev_priv, obj->frontbuffer_bits, origin); } /** @@ -185,16 +186,7 @@ void intel_frontbuffer_flush(struct drm_device *dev, intel_edp_drrs_flush(dev, frontbuffer_bits); intel_psr_flush(dev, frontbuffer_bits); - - /* - * FIXME: Unconditional fbc flushing here is a rather gross hack and - * needs to be reworked into a proper frontbuffer tracking scheme like - * psr employs. - */ - if (dev_priv->fbc.need_sw_cache_clean) { - dev_priv->fbc.need_sw_cache_clean = false; - bdw_fbc_sw_flush(dev, FBC_REND_CACHE_CLEAN); - } + intel_fbc_flush(dev_priv, frontbuffer_bits); } /** diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 542cf6844dc3..288c9d24098e 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -263,6 +263,47 @@ static const struct cxsr_latency *intel_get_cxsr_latency(int is_desktop, return NULL; } +static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable) +{ + u32 val; + + mutex_lock(&dev_priv->rps.hw_lock); + + val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2); + if (enable) + val &= ~FORCE_DDR_HIGH_FREQ; + else + val |= FORCE_DDR_HIGH_FREQ; + val &= ~FORCE_DDR_LOW_FREQ; + val |= FORCE_DDR_FREQ_REQ_ACK; + vlv_punit_write(dev_priv, PUNIT_REG_DDR_SETUP2, val); + + if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) & + FORCE_DDR_FREQ_REQ_ACK) == 0, 3)) + DRM_ERROR("timed out waiting for Punit DDR DVFS request\n"); + + mutex_unlock(&dev_priv->rps.hw_lock); +} + +static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable) +{ + u32 val; + + mutex_lock(&dev_priv->rps.hw_lock); + + val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ); + if (enable) + val |= DSP_MAXFIFO_PM5_ENABLE; + else + val &= ~DSP_MAXFIFO_PM5_ENABLE; + vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, val); + + mutex_unlock(&dev_priv->rps.hw_lock); +} + +#define FW_WM(value, plane) \ + (((value) << DSPFW_ ## plane ## _SHIFT) & DSPFW_ ## plane ## _MASK) + void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable) { struct drm_device *dev = dev_priv->dev; @@ -270,6 +311,8 @@ void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable) if (IS_VALLEYVIEW(dev)) { I915_WRITE(FW_BLC_SELF_VLV, enable ? FW_CSPWRDWNEN : 0); + if (IS_CHERRYVIEW(dev)) + chv_set_memory_pm5(dev_priv, enable); } else if (IS_G4X(dev) || IS_CRESTLINE(dev)) { I915_WRITE(FW_BLC_SELF, enable ? FW_BLC_SELF_EN : 0); } else if (IS_PINEVIEW(dev)) { @@ -292,6 +335,7 @@ void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable) enable ? "enabled" : "disabled"); } + /* * Latency for FIFO fetches is dependent on several factors: * - memory configuration (speed, channels) @@ -308,6 +352,61 @@ void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable) */ static const int pessimal_latency_ns = 5000; +#define VLV_FIFO_START(dsparb, dsparb2, lo_shift, hi_shift) \ + ((((dsparb) >> (lo_shift)) & 0xff) | ((((dsparb2) >> (hi_shift)) & 0x1) << 8)) + +static int vlv_get_fifo_size(struct drm_device *dev, + enum pipe pipe, int plane) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int sprite0_start, sprite1_start, size; + + switch (pipe) { + uint32_t dsparb, dsparb2, dsparb3; + case PIPE_A: + dsparb = I915_READ(DSPARB); + dsparb2 = I915_READ(DSPARB2); + sprite0_start = VLV_FIFO_START(dsparb, dsparb2, 0, 0); + sprite1_start = VLV_FIFO_START(dsparb, dsparb2, 8, 4); + break; + case PIPE_B: + dsparb = I915_READ(DSPARB); + dsparb2 = I915_READ(DSPARB2); + sprite0_start = VLV_FIFO_START(dsparb, dsparb2, 16, 8); + sprite1_start = VLV_FIFO_START(dsparb, dsparb2, 24, 12); + break; + case PIPE_C: + dsparb2 = I915_READ(DSPARB2); + dsparb3 = I915_READ(DSPARB3); + sprite0_start = VLV_FIFO_START(dsparb3, dsparb2, 0, 16); + sprite1_start = VLV_FIFO_START(dsparb3, dsparb2, 8, 20); + break; + default: + return 0; + } + + switch (plane) { + case 0: + size = sprite0_start; + break; + case 1: + size = sprite1_start - sprite0_start; + break; + case 2: + size = 512 - 1 - sprite1_start; + break; + default: + return 0; + } + + DRM_DEBUG_KMS("Pipe %c %s %c FIFO size: %d\n", + pipe_name(pipe), plane == 0 ? "primary" : "sprite", + plane == 0 ? plane_name(pipe) : sprite_name(pipe, plane - 1), + size); + + return size; +} + static int i9xx_get_fifo_size(struct drm_device *dev, int plane) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -553,7 +652,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) crtc = single_enabled_crtc(dev); if (crtc) { const struct drm_display_mode *adjusted_mode; - int pixel_size = crtc->primary->fb->bits_per_pixel / 8; + int pixel_size = crtc->primary->state->fb->bits_per_pixel / 8; int clock; adjusted_mode = &to_intel_crtc(crtc)->config->base.adjusted_mode; @@ -565,7 +664,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) pixel_size, latency->display_sr); reg = I915_READ(DSPFW1); reg &= ~DSPFW_SR_MASK; - reg |= wm << DSPFW_SR_SHIFT; + reg |= FW_WM(wm, SR); I915_WRITE(DSPFW1, reg); DRM_DEBUG_KMS("DSPFW1 register is %x\n", reg); @@ -575,7 +674,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) pixel_size, latency->cursor_sr); reg = I915_READ(DSPFW3); reg &= ~DSPFW_CURSOR_SR_MASK; - reg |= (wm & 0x3f) << DSPFW_CURSOR_SR_SHIFT; + reg |= FW_WM(wm, CURSOR_SR); I915_WRITE(DSPFW3, reg); /* Display HPLL off SR */ @@ -584,7 +683,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) pixel_size, latency->display_hpll_disable); reg = I915_READ(DSPFW3); reg &= ~DSPFW_HPLL_SR_MASK; - reg |= wm & DSPFW_HPLL_SR_MASK; + reg |= FW_WM(wm, HPLL_SR); I915_WRITE(DSPFW3, reg); /* cursor HPLL off SR */ @@ -593,7 +692,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) pixel_size, latency->cursor_hpll_disable); reg = I915_READ(DSPFW3); reg &= ~DSPFW_HPLL_CURSOR_MASK; - reg |= (wm & 0x3f) << DSPFW_HPLL_CURSOR_SHIFT; + reg |= FW_WM(wm, HPLL_CURSOR); I915_WRITE(DSPFW3, reg); DRM_DEBUG_KMS("DSPFW3 register is %x\n", reg); @@ -629,7 +728,7 @@ static bool g4x_compute_wm0(struct drm_device *dev, clock = adjusted_mode->crtc_clock; htotal = adjusted_mode->crtc_htotal; hdisplay = to_intel_crtc(crtc)->config->pipe_src_w; - pixel_size = crtc->primary->fb->bits_per_pixel / 8; + pixel_size = crtc->primary->state->fb->bits_per_pixel / 8; /* Use the small buffer method to calculate plane watermark */ entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000; @@ -644,7 +743,7 @@ static bool g4x_compute_wm0(struct drm_device *dev, /* Use the large buffer method to calculate cursor watermark */ line_time_us = max(htotal * 1000 / clock, 1); line_count = (cursor_latency_ns / line_time_us + 1000) / 1000; - entries = line_count * to_intel_crtc(crtc)->cursor_width * pixel_size; + entries = line_count * crtc->cursor->state->crtc_w * pixel_size; tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8; if (tlb_miss > 0) entries += tlb_miss; @@ -716,7 +815,7 @@ static bool g4x_compute_srwm(struct drm_device *dev, clock = adjusted_mode->crtc_clock; htotal = adjusted_mode->crtc_htotal; hdisplay = to_intel_crtc(crtc)->config->pipe_src_w; - pixel_size = crtc->primary->fb->bits_per_pixel / 8; + pixel_size = crtc->primary->state->fb->bits_per_pixel / 8; line_time_us = max(htotal * 1000 / clock, 1); line_count = (latency_ns / line_time_us + 1000) / 1000; @@ -730,7 +829,7 @@ static bool g4x_compute_srwm(struct drm_device *dev, *display_wm = entries + display->guard_size; /* calculate the self-refresh watermark for display cursor */ - entries = line_count * pixel_size * to_intel_crtc(crtc)->cursor_width; + entries = line_count * pixel_size * crtc->cursor->state->crtc_w; entries = DIV_ROUND_UP(entries, cursor->cacheline_size); *cursor_wm = entries + cursor->guard_size; @@ -739,232 +838,234 @@ static bool g4x_compute_srwm(struct drm_device *dev, display, cursor); } -static bool vlv_compute_drain_latency(struct drm_crtc *crtc, - int pixel_size, - int *prec_mult, - int *drain_latency) -{ - struct drm_device *dev = crtc->dev; - int entries; - int clock = to_intel_crtc(crtc)->config->base.adjusted_mode.crtc_clock; +#define FW_WM_VLV(value, plane) \ + (((value) << DSPFW_ ## plane ## _SHIFT) & DSPFW_ ## plane ## _MASK_VLV) - if (WARN(clock == 0, "Pixel clock is zero!\n")) - return false; +static void vlv_write_wm_values(struct intel_crtc *crtc, + const struct vlv_wm_values *wm) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; - if (WARN(pixel_size == 0, "Pixel size is zero!\n")) - return false; + I915_WRITE(VLV_DDL(pipe), + (wm->ddl[pipe].cursor << DDL_CURSOR_SHIFT) | + (wm->ddl[pipe].sprite[1] << DDL_SPRITE_SHIFT(1)) | + (wm->ddl[pipe].sprite[0] << DDL_SPRITE_SHIFT(0)) | + (wm->ddl[pipe].primary << DDL_PLANE_SHIFT)); - entries = DIV_ROUND_UP(clock, 1000) * pixel_size; - if (IS_CHERRYVIEW(dev)) - *prec_mult = (entries > 128) ? DRAIN_LATENCY_PRECISION_32 : - DRAIN_LATENCY_PRECISION_16; - else - *prec_mult = (entries > 128) ? DRAIN_LATENCY_PRECISION_64 : - DRAIN_LATENCY_PRECISION_32; - *drain_latency = (64 * (*prec_mult) * 4) / entries; + I915_WRITE(DSPFW1, + FW_WM(wm->sr.plane, SR) | + FW_WM(wm->pipe[PIPE_B].cursor, CURSORB) | + FW_WM_VLV(wm->pipe[PIPE_B].primary, PLANEB) | + FW_WM_VLV(wm->pipe[PIPE_A].primary, PLANEA)); + I915_WRITE(DSPFW2, + FW_WM_VLV(wm->pipe[PIPE_A].sprite[1], SPRITEB) | + FW_WM(wm->pipe[PIPE_A].cursor, CURSORA) | + FW_WM_VLV(wm->pipe[PIPE_A].sprite[0], SPRITEA)); + I915_WRITE(DSPFW3, + FW_WM(wm->sr.cursor, CURSOR_SR)); + + if (IS_CHERRYVIEW(dev_priv)) { + I915_WRITE(DSPFW7_CHV, + FW_WM_VLV(wm->pipe[PIPE_B].sprite[1], SPRITED) | + FW_WM_VLV(wm->pipe[PIPE_B].sprite[0], SPRITEC)); + I915_WRITE(DSPFW8_CHV, + FW_WM_VLV(wm->pipe[PIPE_C].sprite[1], SPRITEF) | + FW_WM_VLV(wm->pipe[PIPE_C].sprite[0], SPRITEE)); + I915_WRITE(DSPFW9_CHV, + FW_WM_VLV(wm->pipe[PIPE_C].primary, PLANEC) | + FW_WM(wm->pipe[PIPE_C].cursor, CURSORC)); + I915_WRITE(DSPHOWM, + FW_WM(wm->sr.plane >> 9, SR_HI) | + FW_WM(wm->pipe[PIPE_C].sprite[1] >> 8, SPRITEF_HI) | + FW_WM(wm->pipe[PIPE_C].sprite[0] >> 8, SPRITEE_HI) | + FW_WM(wm->pipe[PIPE_C].primary >> 8, PLANEC_HI) | + FW_WM(wm->pipe[PIPE_B].sprite[1] >> 8, SPRITED_HI) | + FW_WM(wm->pipe[PIPE_B].sprite[0] >> 8, SPRITEC_HI) | + FW_WM(wm->pipe[PIPE_B].primary >> 8, PLANEB_HI) | + FW_WM(wm->pipe[PIPE_A].sprite[1] >> 8, SPRITEB_HI) | + FW_WM(wm->pipe[PIPE_A].sprite[0] >> 8, SPRITEA_HI) | + FW_WM(wm->pipe[PIPE_A].primary >> 8, PLANEA_HI)); + } else { + I915_WRITE(DSPFW7, + FW_WM_VLV(wm->pipe[PIPE_B].sprite[1], SPRITED) | + FW_WM_VLV(wm->pipe[PIPE_B].sprite[0], SPRITEC)); + I915_WRITE(DSPHOWM, + FW_WM(wm->sr.plane >> 9, SR_HI) | + FW_WM(wm->pipe[PIPE_B].sprite[1] >> 8, SPRITED_HI) | + FW_WM(wm->pipe[PIPE_B].sprite[0] >> 8, SPRITEC_HI) | + FW_WM(wm->pipe[PIPE_B].primary >> 8, PLANEB_HI) | + FW_WM(wm->pipe[PIPE_A].sprite[1] >> 8, SPRITEB_HI) | + FW_WM(wm->pipe[PIPE_A].sprite[0] >> 8, SPRITEA_HI) | + FW_WM(wm->pipe[PIPE_A].primary >> 8, PLANEA_HI)); + } - if (*drain_latency > DRAIN_LATENCY_MASK) - *drain_latency = DRAIN_LATENCY_MASK; + POSTING_READ(DSPFW1); - return true; + dev_priv->wm.vlv = *wm; } -/* - * Update drain latency registers of memory arbiter - * - * Valleyview SoC has a new memory arbiter and needs drain latency registers - * to be programmed. Each plane has a drain latency multiplier and a drain - * latency value. - */ +#undef FW_WM_VLV -static void vlv_update_drain_latency(struct drm_crtc *crtc) +static uint8_t vlv_compute_drain_latency(struct drm_crtc *crtc, + struct drm_plane *plane) { 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 pixel_size; - int drain_latency; - enum pipe pipe = intel_crtc->pipe; - int plane_prec, prec_mult, plane_dl; - const int high_precision = IS_CHERRYVIEW(dev) ? - DRAIN_LATENCY_PRECISION_32 : DRAIN_LATENCY_PRECISION_64; + int entries, prec_mult, drain_latency, pixel_size; + int clock = intel_crtc->config->base.adjusted_mode.crtc_clock; + const int high_precision = IS_CHERRYVIEW(dev) ? 16 : 64; - plane_dl = I915_READ(VLV_DDL(pipe)) & ~(DDL_PLANE_PRECISION_HIGH | - DRAIN_LATENCY_MASK | DDL_CURSOR_PRECISION_HIGH | - (DRAIN_LATENCY_MASK << DDL_CURSOR_SHIFT)); + /* + * FIXME the plane might have an fb + * but be invisible (eg. due to clipping) + */ + if (!intel_crtc->active || !plane->state->fb) + return 0; - if (!intel_crtc_active(crtc)) { - I915_WRITE(VLV_DDL(pipe), plane_dl); - return; - } + if (WARN(clock == 0, "Pixel clock is zero!\n")) + return 0; - /* Primary plane Drain Latency */ - pixel_size = crtc->primary->fb->bits_per_pixel / 8; /* BPP */ - if (vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, &drain_latency)) { - plane_prec = (prec_mult == high_precision) ? - DDL_PLANE_PRECISION_HIGH : - DDL_PLANE_PRECISION_LOW; - plane_dl |= plane_prec | drain_latency; - } + pixel_size = drm_format_plane_cpp(plane->state->fb->pixel_format, 0); - /* Cursor Drain Latency - * BPP is always 4 for cursor - */ - pixel_size = 4; + if (WARN(pixel_size == 0, "Pixel size is zero!\n")) + return 0; + + entries = DIV_ROUND_UP(clock, 1000) * pixel_size; + + prec_mult = high_precision; + drain_latency = 64 * prec_mult * 4 / entries; - /* Program cursor DL only if it is enabled */ - if (intel_crtc->cursor_base && - vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, &drain_latency)) { - plane_prec = (prec_mult == high_precision) ? - DDL_CURSOR_PRECISION_HIGH : - DDL_CURSOR_PRECISION_LOW; - plane_dl |= plane_prec | (drain_latency << DDL_CURSOR_SHIFT); + if (drain_latency > DRAIN_LATENCY_MASK) { + prec_mult /= 2; + drain_latency = 64 * prec_mult * 4 / entries; } - I915_WRITE(VLV_DDL(pipe), plane_dl); -} + if (drain_latency > DRAIN_LATENCY_MASK) + drain_latency = DRAIN_LATENCY_MASK; -#define single_plane_enabled(mask) is_power_of_2(mask) + return drain_latency | (prec_mult == high_precision ? + DDL_PRECISION_HIGH : DDL_PRECISION_LOW); +} -static void valleyview_update_wm(struct drm_crtc *crtc) +static int vlv_compute_wm(struct intel_crtc *crtc, + struct intel_plane *plane, + int fifo_size) { - struct drm_device *dev = crtc->dev; - static const int sr_latency_ns = 12000; - struct drm_i915_private *dev_priv = dev->dev_private; - int planea_wm, planeb_wm, cursora_wm, cursorb_wm; - int plane_sr, cursor_sr; - int ignore_plane_sr, ignore_cursor_sr; - unsigned int enabled = 0; - bool cxsr_enabled; + int clock, entries, pixel_size; - vlv_update_drain_latency(crtc); + /* + * FIXME the plane might have an fb + * but be invisible (eg. due to clipping) + */ + if (!crtc->active || !plane->base.state->fb) + return 0; - if (g4x_compute_wm0(dev, PIPE_A, - &valleyview_wm_info, pessimal_latency_ns, - &valleyview_cursor_wm_info, pessimal_latency_ns, - &planea_wm, &cursora_wm)) - enabled |= 1 << PIPE_A; + pixel_size = drm_format_plane_cpp(plane->base.state->fb->pixel_format, 0); + clock = crtc->config->base.adjusted_mode.crtc_clock; - if (g4x_compute_wm0(dev, PIPE_B, - &valleyview_wm_info, pessimal_latency_ns, - &valleyview_cursor_wm_info, pessimal_latency_ns, - &planeb_wm, &cursorb_wm)) - enabled |= 1 << PIPE_B; + entries = DIV_ROUND_UP(clock, 1000) * pixel_size; - if (single_plane_enabled(enabled) && - g4x_compute_srwm(dev, ffs(enabled) - 1, - sr_latency_ns, - &valleyview_wm_info, - &valleyview_cursor_wm_info, - &plane_sr, &ignore_cursor_sr) && - g4x_compute_srwm(dev, ffs(enabled) - 1, - 2*sr_latency_ns, - &valleyview_wm_info, - &valleyview_cursor_wm_info, - &ignore_plane_sr, &cursor_sr)) { - cxsr_enabled = true; - } else { - cxsr_enabled = false; - intel_set_memory_cxsr(dev_priv, false); - plane_sr = cursor_sr = 0; + /* + * Set up the watermark such that we don't start issuing memory + * requests until we are within PND's max deadline value (256us). + * Idea being to be idle as long as possible while still taking + * advatange of PND's deadline scheduling. The limit of 8 + * cachelines (used when the FIFO will anyway drain in less time + * than 256us) should match what we would be done if trickle + * feed were enabled. + */ + return fifo_size - clamp(DIV_ROUND_UP(256 * entries, 64), 0, fifo_size - 8); +} + +static bool vlv_compute_sr_wm(struct drm_device *dev, + struct vlv_wm_values *wm) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_crtc *crtc; + enum pipe pipe = INVALID_PIPE; + int num_planes = 0; + int fifo_size = 0; + struct intel_plane *plane; + + wm->sr.cursor = wm->sr.plane = 0; + + crtc = single_enabled_crtc(dev); + /* maxfifo not supported on pipe C */ + if (crtc && to_intel_crtc(crtc)->pipe != PIPE_C) { + pipe = to_intel_crtc(crtc)->pipe; + num_planes = !!wm->pipe[pipe].primary + + !!wm->pipe[pipe].sprite[0] + + !!wm->pipe[pipe].sprite[1]; + fifo_size = INTEL_INFO(dev_priv)->num_pipes * 512 - 1; } - DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, " - "B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n", - planea_wm, cursora_wm, - planeb_wm, cursorb_wm, - plane_sr, cursor_sr); + if (fifo_size == 0 || num_planes > 1) + return false; - I915_WRITE(DSPFW1, - (plane_sr << DSPFW_SR_SHIFT) | - (cursorb_wm << DSPFW_CURSORB_SHIFT) | - (planeb_wm << DSPFW_PLANEB_SHIFT) | - (planea_wm << DSPFW_PLANEA_SHIFT)); - I915_WRITE(DSPFW2, - (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) | - (cursora_wm << DSPFW_CURSORA_SHIFT)); - I915_WRITE(DSPFW3, - (I915_READ(DSPFW3) & ~DSPFW_CURSOR_SR_MASK) | - (cursor_sr << DSPFW_CURSOR_SR_SHIFT)); + wm->sr.cursor = vlv_compute_wm(to_intel_crtc(crtc), + to_intel_plane(crtc->cursor), 0x3f); - if (cxsr_enabled) - intel_set_memory_cxsr(dev_priv, true); + list_for_each_entry(plane, &dev->mode_config.plane_list, base.head) { + if (plane->base.type == DRM_PLANE_TYPE_CURSOR) + continue; + + if (plane->pipe != pipe) + continue; + + wm->sr.plane = vlv_compute_wm(to_intel_crtc(crtc), + plane, fifo_size); + if (wm->sr.plane != 0) + break; + } + + return true; } -static void cherryview_update_wm(struct drm_crtc *crtc) +static void valleyview_update_wm(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; - static const int sr_latency_ns = 12000; struct drm_i915_private *dev_priv = dev->dev_private; - int planea_wm, planeb_wm, planec_wm; - int cursora_wm, cursorb_wm, cursorc_wm; - int plane_sr, cursor_sr; - int ignore_plane_sr, ignore_cursor_sr; - unsigned int enabled = 0; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + enum pipe pipe = intel_crtc->pipe; bool cxsr_enabled; + struct vlv_wm_values wm = dev_priv->wm.vlv; - vlv_update_drain_latency(crtc); + wm.ddl[pipe].primary = vlv_compute_drain_latency(crtc, crtc->primary); + wm.pipe[pipe].primary = vlv_compute_wm(intel_crtc, + to_intel_plane(crtc->primary), + vlv_get_fifo_size(dev, pipe, 0)); - if (g4x_compute_wm0(dev, PIPE_A, - &valleyview_wm_info, pessimal_latency_ns, - &valleyview_cursor_wm_info, pessimal_latency_ns, - &planea_wm, &cursora_wm)) - enabled |= 1 << PIPE_A; + wm.ddl[pipe].cursor = vlv_compute_drain_latency(crtc, crtc->cursor); + wm.pipe[pipe].cursor = vlv_compute_wm(intel_crtc, + to_intel_plane(crtc->cursor), + 0x3f); - if (g4x_compute_wm0(dev, PIPE_B, - &valleyview_wm_info, pessimal_latency_ns, - &valleyview_cursor_wm_info, pessimal_latency_ns, - &planeb_wm, &cursorb_wm)) - enabled |= 1 << PIPE_B; + cxsr_enabled = vlv_compute_sr_wm(dev, &wm); - if (g4x_compute_wm0(dev, PIPE_C, - &valleyview_wm_info, pessimal_latency_ns, - &valleyview_cursor_wm_info, pessimal_latency_ns, - &planec_wm, &cursorc_wm)) - enabled |= 1 << PIPE_C; + if (memcmp(&wm, &dev_priv->wm.vlv, sizeof(wm)) == 0) + return; - if (single_plane_enabled(enabled) && - g4x_compute_srwm(dev, ffs(enabled) - 1, - sr_latency_ns, - &valleyview_wm_info, - &valleyview_cursor_wm_info, - &plane_sr, &ignore_cursor_sr) && - g4x_compute_srwm(dev, ffs(enabled) - 1, - 2*sr_latency_ns, - &valleyview_wm_info, - &valleyview_cursor_wm_info, - &ignore_plane_sr, &cursor_sr)) { - cxsr_enabled = true; - } else { - cxsr_enabled = false; - intel_set_memory_cxsr(dev_priv, false); - plane_sr = cursor_sr = 0; - } + DRM_DEBUG_KMS("Setting FIFO watermarks - %c: plane=%d, cursor=%d, " + "SR: plane=%d, cursor=%d\n", pipe_name(pipe), + wm.pipe[pipe].primary, wm.pipe[pipe].cursor, + wm.sr.plane, wm.sr.cursor); - DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, " - "B: plane=%d, cursor=%d, C: plane=%d, cursor=%d, " - "SR: plane=%d, cursor=%d\n", - planea_wm, cursora_wm, - planeb_wm, cursorb_wm, - planec_wm, cursorc_wm, - plane_sr, cursor_sr); + /* + * FIXME DDR DVFS introduces massive memory latencies which + * are not known to system agent so any deadline specified + * by the display may not be respected. To support DDR DVFS + * the watermark code needs to be rewritten to essentially + * bypass deadline mechanism and rely solely on the + * watermarks. For now disable DDR DVFS. + */ + if (IS_CHERRYVIEW(dev_priv)) + chv_set_memory_dvfs(dev_priv, false); - I915_WRITE(DSPFW1, - (plane_sr << DSPFW_SR_SHIFT) | - (cursorb_wm << DSPFW_CURSORB_SHIFT) | - (planeb_wm << DSPFW_PLANEB_SHIFT) | - (planea_wm << DSPFW_PLANEA_SHIFT)); - I915_WRITE(DSPFW2, - (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) | - (cursora_wm << DSPFW_CURSORA_SHIFT)); - I915_WRITE(DSPFW3, - (I915_READ(DSPFW3) & ~DSPFW_CURSOR_SR_MASK) | - (cursor_sr << DSPFW_CURSOR_SR_SHIFT)); - I915_WRITE(DSPFW9_CHV, - (I915_READ(DSPFW9_CHV) & ~(DSPFW_PLANEC_MASK | - DSPFW_CURSORC_MASK)) | - (planec_wm << DSPFW_PLANEC_SHIFT) | - (cursorc_wm << DSPFW_CURSORC_SHIFT)); + if (!cxsr_enabled) + intel_set_memory_cxsr(dev_priv, false); + + vlv_write_wm_values(intel_crtc, &wm); if (cxsr_enabled) intel_set_memory_cxsr(dev_priv, true); @@ -979,30 +1080,47 @@ static void valleyview_update_sprite_wm(struct drm_plane *plane, { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; - int pipe = to_intel_plane(plane)->pipe; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + enum pipe pipe = intel_crtc->pipe; int sprite = to_intel_plane(plane)->plane; - int drain_latency; - int plane_prec; - int sprite_dl; - int prec_mult; - const int high_precision = IS_CHERRYVIEW(dev) ? - DRAIN_LATENCY_PRECISION_32 : DRAIN_LATENCY_PRECISION_64; + bool cxsr_enabled; + struct vlv_wm_values wm = dev_priv->wm.vlv; - sprite_dl = I915_READ(VLV_DDL(pipe)) & ~(DDL_SPRITE_PRECISION_HIGH(sprite) | - (DRAIN_LATENCY_MASK << DDL_SPRITE_SHIFT(sprite))); + if (enabled) { + wm.ddl[pipe].sprite[sprite] = + vlv_compute_drain_latency(crtc, plane); - if (enabled && vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, - &drain_latency)) { - plane_prec = (prec_mult == high_precision) ? - DDL_SPRITE_PRECISION_HIGH(sprite) : - DDL_SPRITE_PRECISION_LOW(sprite); - sprite_dl |= plane_prec | - (drain_latency << DDL_SPRITE_SHIFT(sprite)); + wm.pipe[pipe].sprite[sprite] = + vlv_compute_wm(intel_crtc, + to_intel_plane(plane), + vlv_get_fifo_size(dev, pipe, sprite+1)); + } else { + wm.ddl[pipe].sprite[sprite] = 0; + wm.pipe[pipe].sprite[sprite] = 0; } - I915_WRITE(VLV_DDL(pipe), sprite_dl); + cxsr_enabled = vlv_compute_sr_wm(dev, &wm); + + if (memcmp(&wm, &dev_priv->wm.vlv, sizeof(wm)) == 0) + return; + + DRM_DEBUG_KMS("Setting FIFO watermarks - %c: sprite %c=%d, " + "SR: plane=%d, cursor=%d\n", pipe_name(pipe), + sprite_name(pipe, sprite), + wm.pipe[pipe].sprite[sprite], + wm.sr.plane, wm.sr.cursor); + + if (!cxsr_enabled) + intel_set_memory_cxsr(dev_priv, false); + + vlv_write_wm_values(intel_crtc, &wm); + + if (cxsr_enabled) + intel_set_memory_cxsr(dev_priv, true); } +#define single_plane_enabled(mask) is_power_of_2(mask) + static void g4x_update_wm(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -1045,17 +1163,17 @@ static void g4x_update_wm(struct drm_crtc *crtc) plane_sr, cursor_sr); I915_WRITE(DSPFW1, - (plane_sr << DSPFW_SR_SHIFT) | - (cursorb_wm << DSPFW_CURSORB_SHIFT) | - (planeb_wm << DSPFW_PLANEB_SHIFT) | - (planea_wm << DSPFW_PLANEA_SHIFT)); + FW_WM(plane_sr, SR) | + FW_WM(cursorb_wm, CURSORB) | + FW_WM(planeb_wm, PLANEB) | + FW_WM(planea_wm, PLANEA)); I915_WRITE(DSPFW2, (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) | - (cursora_wm << DSPFW_CURSORA_SHIFT)); + FW_WM(cursora_wm, CURSORA)); /* HPLL off in SR has some issues on G4x... disable it */ I915_WRITE(DSPFW3, (I915_READ(DSPFW3) & ~(DSPFW_HPLL_SR_EN | DSPFW_CURSOR_SR_MASK)) | - (cursor_sr << DSPFW_CURSOR_SR_SHIFT)); + FW_WM(cursor_sr, CURSOR_SR)); if (cxsr_enabled) intel_set_memory_cxsr(dev_priv, true); @@ -1080,7 +1198,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) int clock = adjusted_mode->crtc_clock; int htotal = adjusted_mode->crtc_htotal; int hdisplay = to_intel_crtc(crtc)->config->pipe_src_w; - int pixel_size = crtc->primary->fb->bits_per_pixel / 8; + int pixel_size = crtc->primary->state->fb->bits_per_pixel / 8; unsigned long line_time_us; int entries; @@ -1098,7 +1216,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) entries, srwm); entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - pixel_size * to_intel_crtc(crtc)->cursor_width; + pixel_size * crtc->cursor->state->crtc_w; entries = DIV_ROUND_UP(entries, i965_cursor_wm_info.cacheline_size); cursor_sr = i965_cursor_wm_info.fifo_size - @@ -1121,19 +1239,21 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) srwm); /* 965 has limitations... */ - I915_WRITE(DSPFW1, (srwm << DSPFW_SR_SHIFT) | - (8 << DSPFW_CURSORB_SHIFT) | - (8 << DSPFW_PLANEB_SHIFT) | - (8 << DSPFW_PLANEA_SHIFT)); - I915_WRITE(DSPFW2, (8 << DSPFW_CURSORA_SHIFT) | - (8 << DSPFW_PLANEC_SHIFT_OLD)); + I915_WRITE(DSPFW1, FW_WM(srwm, SR) | + FW_WM(8, CURSORB) | + FW_WM(8, PLANEB) | + FW_WM(8, PLANEA)); + I915_WRITE(DSPFW2, FW_WM(8, CURSORA) | + FW_WM(8, PLANEC_OLD)); /* update cursor SR watermark */ - I915_WRITE(DSPFW3, (cursor_sr << DSPFW_CURSOR_SR_SHIFT)); + I915_WRITE(DSPFW3, FW_WM(cursor_sr, CURSOR_SR)); if (cxsr_enabled) intel_set_memory_cxsr(dev_priv, true); } +#undef FW_WM + static void i9xx_update_wm(struct drm_crtc *unused_crtc) { struct drm_device *dev = unused_crtc->dev; @@ -1157,7 +1277,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) crtc = intel_get_crtc_for_plane(dev, 0); if (intel_crtc_active(crtc)) { const struct drm_display_mode *adjusted_mode; - int cpp = crtc->primary->fb->bits_per_pixel / 8; + int cpp = crtc->primary->state->fb->bits_per_pixel / 8; if (IS_GEN2(dev)) cpp = 4; @@ -1179,7 +1299,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) crtc = intel_get_crtc_for_plane(dev, 1); if (intel_crtc_active(crtc)) { const struct drm_display_mode *adjusted_mode; - int cpp = crtc->primary->fb->bits_per_pixel / 8; + int cpp = crtc->primary->state->fb->bits_per_pixel / 8; if (IS_GEN2(dev)) cpp = 4; @@ -1202,7 +1322,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) if (IS_I915GM(dev) && enabled) { struct drm_i915_gem_object *obj; - obj = intel_fb_obj(enabled->primary->fb); + obj = intel_fb_obj(enabled->primary->state->fb); /* self-refresh seems busted with untiled */ if (obj->tiling_mode == I915_TILING_NONE) @@ -1226,7 +1346,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) int clock = adjusted_mode->crtc_clock; int htotal = adjusted_mode->crtc_htotal; int hdisplay = to_intel_crtc(enabled)->config->pipe_src_w; - int pixel_size = enabled->primary->fb->bits_per_pixel / 8; + int pixel_size = enabled->primary->state->fb->bits_per_pixel / 8; unsigned long line_time_us; int entries; @@ -1663,7 +1783,7 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc) struct drm_display_mode *mode = &intel_crtc->config->base.adjusted_mode; u32 linetime, ips_linetime; - if (!intel_crtc_active(crtc)) + if (!intel_crtc->active) return 0; /* The WM are computed with base on how long it takes to fill a single @@ -1918,19 +2038,31 @@ static void ilk_compute_wm_parameters(struct drm_crtc *crtc, enum pipe pipe = intel_crtc->pipe; struct drm_plane *plane; - if (!intel_crtc_active(crtc)) + if (!intel_crtc->active) return; p->active = true; p->pipe_htotal = intel_crtc->config->base.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; + + if (crtc->primary->state->fb) { + p->pri.enabled = true; + p->pri.bytes_per_pixel = + crtc->primary->state->fb->bits_per_pixel / 8; + } else { + p->pri.enabled = false; + p->pri.bytes_per_pixel = 0; + } + + if (crtc->cursor->state->fb) { + p->cur.enabled = true; + p->cur.bytes_per_pixel = 4; + } else { + p->cur.enabled = false; + p->cur.bytes_per_pixel = 0; + } 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; + p->cur.horiz_pixels = intel_crtc->base.cursor->state->crtc_w; drm_for_each_legacy_plane(plane, &dev->mode_config.plane_list) { struct intel_plane *intel_plane = to_intel_plane(plane); @@ -2430,7 +2562,7 @@ skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, nth_active_pipe = 0; for_each_crtc(dev, crtc) { - if (!intel_crtc_active(crtc)) + if (!to_intel_crtc(crtc)->active) continue; if (crtc == for_crtc) @@ -2463,13 +2595,12 @@ static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg) void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */) { - struct drm_device *dev = dev_priv->dev; enum pipe pipe; int plane; u32 val; for_each_pipe(dev_priv, pipe) { - for_each_plane(pipe, plane) { + for_each_plane(dev_priv, pipe, plane) { val = I915_READ(PLANE_BUF_CFG(pipe, plane)); skl_ddb_entry_init_from_hw(&ddb->plane[pipe][plane], val); @@ -2518,6 +2649,7 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc, struct skl_ddb_allocation *ddb /* out */) { struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum pipe pipe = intel_crtc->pipe; struct skl_ddb_entry *alloc = &ddb->pipe[pipe]; @@ -2542,7 +2674,7 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc, alloc->end -= cursor_blocks; /* 1. Allocate the mininum required blocks for each active plane */ - for_each_plane(pipe, plane) { + for_each_plane(dev_priv, pipe, plane) { const struct intel_plane_wm_parameters *p; p = ¶ms->plane[plane]; @@ -2670,7 +2802,7 @@ static void skl_compute_wm_global_parameters(struct drm_device *dev, struct drm_plane *plane; list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - config->num_pipes_active += intel_crtc_active(crtc); + config->num_pipes_active += to_intel_crtc(crtc)->active; /* FIXME: I don't think we need those two global parameters on SKL */ list_for_each_entry(plane, &dev->mode_config.plane_list, head) { @@ -2691,32 +2823,36 @@ static void skl_compute_wm_pipe_parameters(struct drm_crtc *crtc, struct drm_framebuffer *fb; int i = 1; /* Index for sprite planes start */ - p->active = intel_crtc_active(crtc); + p->active = intel_crtc->active; if (p->active) { p->pipe_htotal = intel_crtc->config->base.adjusted_mode.crtc_htotal; p->pixel_rate = skl_pipe_pixel_rate(intel_crtc->config); - /* - * For now, assume primary and cursor planes are always enabled. - */ - p->plane[0].enabled = true; - p->plane[0].bytes_per_pixel = - crtc->primary->fb->bits_per_pixel / 8; - p->plane[0].horiz_pixels = intel_crtc->config->pipe_src_w; - p->plane[0].vert_pixels = intel_crtc->config->pipe_src_h; - p->plane[0].tiling = DRM_FORMAT_MOD_NONE; fb = crtc->primary->state->fb; - /* - * Framebuffer can be NULL on plane disable, but it does not - * matter for watermarks if we assume no tiling in that case. - */ - if (fb) + if (fb) { + p->plane[0].enabled = true; + p->plane[0].bytes_per_pixel = fb->bits_per_pixel / 8; p->plane[0].tiling = fb->modifier[0]; + } else { + p->plane[0].enabled = false; + p->plane[0].bytes_per_pixel = 0; + p->plane[0].tiling = DRM_FORMAT_MOD_NONE; + } + p->plane[0].horiz_pixels = intel_crtc->config->pipe_src_w; + p->plane[0].vert_pixels = intel_crtc->config->pipe_src_h; - p->cursor.enabled = true; - p->cursor.bytes_per_pixel = 4; - p->cursor.horiz_pixels = intel_crtc->cursor_width ? - intel_crtc->cursor_width : 64; + fb = crtc->cursor->state->fb; + if (fb) { + p->cursor.enabled = true; + p->cursor.bytes_per_pixel = fb->bits_per_pixel / 8; + p->cursor.horiz_pixels = crtc->cursor->state->crtc_w; + p->cursor.vert_pixels = crtc->cursor->state->crtc_h; + } else { + p->cursor.enabled = false; + p->cursor.bytes_per_pixel = 0; + p->cursor.horiz_pixels = 64; + p->cursor.vert_pixels = 64; + } } list_for_each_entry(plane, &dev->mode_config.plane_list, head) { @@ -2822,7 +2958,7 @@ static void skl_compute_wm_level(const struct drm_i915_private *dev_priv, static uint32_t skl_compute_linetime_wm(struct drm_crtc *crtc, struct skl_pipe_wm_parameters *p) { - if (!intel_crtc_active(crtc)) + if (!to_intel_crtc(crtc)->active) return 0; return DIV_ROUND_UP(8 * p->pipe_htotal * 1000, p->pixel_rate); @@ -2996,12 +3132,11 @@ static void skl_write_wm_values(struct drm_i915_private *dev_priv, static void skl_wm_flush_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, int pass) { - struct drm_device *dev = dev_priv->dev; int plane; DRM_DEBUG_KMS("flush pipe %c (pass %d)\n", pipe_name(pipe), pass); - for_each_plane(pipe, plane) { + for_each_plane(dev_priv, pipe, plane) { I915_WRITE(PLANE_SURF(pipe, plane), I915_READ(PLANE_SURF(pipe, plane))); } @@ -3370,7 +3505,7 @@ static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc) hw->plane_trans[pipe][i] = I915_READ(PLANE_WM_TRANS(pipe, i)); hw->cursor_trans[pipe] = I915_READ(CUR_WM_TRANS(pipe)); - if (!intel_crtc_active(crtc)) + if (!intel_crtc->active) return; hw->dirty[pipe] = true; @@ -3425,7 +3560,7 @@ 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)); - active->pipe_enabled = intel_crtc_active(crtc); + active->pipe_enabled = intel_crtc->active; if (active->pipe_enabled) { u32 tmp = hw->wm_pipe[pipe]; @@ -3539,41 +3674,6 @@ void intel_update_sprite_watermarks(struct drm_plane *plane, pixel_size, enabled, scaled); } -static struct drm_i915_gem_object * -intel_alloc_context_page(struct drm_device *dev) -{ - struct drm_i915_gem_object *ctx; - int ret; - - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - - ctx = i915_gem_alloc_object(dev, 4096); - if (!ctx) { - DRM_DEBUG("failed to alloc power context, RC6 disabled\n"); - return NULL; - } - - ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0); - if (ret) { - DRM_ERROR("failed to pin power context: %d\n", ret); - goto err_unref; - } - - ret = i915_gem_object_set_to_gtt_domain(ctx, 1); - if (ret) { - DRM_ERROR("failed to set-domain on power context: %d\n", ret); - goto err_unpin; - } - - return ctx; - -err_unpin: - i915_gem_object_ggtt_unpin(ctx); -err_unref: - drm_gem_object_unreference(&ctx->base); - return NULL; -} - /** * Lock protecting IPS related data structures */ @@ -3706,7 +3806,7 @@ static void ironlake_disable_drps(struct drm_device *dev) * ourselves, instead of doing a rmw cycle (which might result in us clearing * all limits and the gpu stuck at whatever frequency it is at atm). */ -static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val) +static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val) { u32 limits; @@ -3716,9 +3816,15 @@ static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val) * the hw runs at the minimal clock before selecting the desired * frequency, if the down threshold expires in that window we will not * receive a down interrupt. */ - limits = dev_priv->rps.max_freq_softlimit << 24; - if (val <= dev_priv->rps.min_freq_softlimit) - limits |= dev_priv->rps.min_freq_softlimit << 16; + if (IS_GEN9(dev_priv->dev)) { + limits = (dev_priv->rps.max_freq_softlimit) << 23; + if (val <= dev_priv->rps.min_freq_softlimit) + limits |= (dev_priv->rps.min_freq_softlimit) << 14; + } else { + limits = dev_priv->rps.max_freq_softlimit << 24; + if (val <= dev_priv->rps.min_freq_softlimit) + limits |= dev_priv->rps.min_freq_softlimit << 16; + } return limits; } @@ -3726,6 +3832,8 @@ static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val) static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) { int new_power; + u32 threshold_up = 0, threshold_down = 0; /* in % */ + u32 ei_up = 0, ei_down = 0; new_power = dev_priv->rps.power; switch (dev_priv->rps.power) { @@ -3758,59 +3866,53 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) switch (new_power) { case LOW_POWER: /* Upclock if more than 95% busy over 16ms */ - I915_WRITE(GEN6_RP_UP_EI, 12500); - I915_WRITE(GEN6_RP_UP_THRESHOLD, 11800); + ei_up = 16000; + threshold_up = 95; /* Downclock if less than 85% busy over 32ms */ - I915_WRITE(GEN6_RP_DOWN_EI, 25000); - I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 21250); - - I915_WRITE(GEN6_RP_CONTROL, - GEN6_RP_MEDIA_TURBO | - GEN6_RP_MEDIA_HW_NORMAL_MODE | - GEN6_RP_MEDIA_IS_GFX | - GEN6_RP_ENABLE | - GEN6_RP_UP_BUSY_AVG | - GEN6_RP_DOWN_IDLE_AVG); + ei_down = 32000; + threshold_down = 85; break; case BETWEEN: /* Upclock if more than 90% busy over 13ms */ - I915_WRITE(GEN6_RP_UP_EI, 10250); - I915_WRITE(GEN6_RP_UP_THRESHOLD, 9225); + ei_up = 13000; + threshold_up = 90; /* Downclock if less than 75% busy over 32ms */ - I915_WRITE(GEN6_RP_DOWN_EI, 25000); - I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 18750); - - I915_WRITE(GEN6_RP_CONTROL, - GEN6_RP_MEDIA_TURBO | - GEN6_RP_MEDIA_HW_NORMAL_MODE | - GEN6_RP_MEDIA_IS_GFX | - GEN6_RP_ENABLE | - GEN6_RP_UP_BUSY_AVG | - GEN6_RP_DOWN_IDLE_AVG); + ei_down = 32000; + threshold_down = 75; break; case HIGH_POWER: /* Upclock if more than 85% busy over 10ms */ - I915_WRITE(GEN6_RP_UP_EI, 8000); - I915_WRITE(GEN6_RP_UP_THRESHOLD, 6800); + ei_up = 10000; + threshold_up = 85; /* Downclock if less than 60% busy over 32ms */ - I915_WRITE(GEN6_RP_DOWN_EI, 25000); - I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 15000); - - I915_WRITE(GEN6_RP_CONTROL, - GEN6_RP_MEDIA_TURBO | - GEN6_RP_MEDIA_HW_NORMAL_MODE | - GEN6_RP_MEDIA_IS_GFX | - GEN6_RP_ENABLE | - GEN6_RP_UP_BUSY_AVG | - GEN6_RP_DOWN_IDLE_AVG); + ei_down = 32000; + threshold_down = 60; break; } + I915_WRITE(GEN6_RP_UP_EI, + GT_INTERVAL_FROM_US(dev_priv, ei_up)); + I915_WRITE(GEN6_RP_UP_THRESHOLD, + GT_INTERVAL_FROM_US(dev_priv, (ei_up * threshold_up / 100))); + + I915_WRITE(GEN6_RP_DOWN_EI, + GT_INTERVAL_FROM_US(dev_priv, ei_down)); + I915_WRITE(GEN6_RP_DOWN_THRESHOLD, + GT_INTERVAL_FROM_US(dev_priv, (ei_down * threshold_down / 100))); + + I915_WRITE(GEN6_RP_CONTROL, + GEN6_RP_MEDIA_TURBO | + GEN6_RP_MEDIA_HW_NORMAL_MODE | + GEN6_RP_MEDIA_IS_GFX | + GEN6_RP_ENABLE | + GEN6_RP_UP_BUSY_AVG | + GEN6_RP_DOWN_IDLE_AVG); + dev_priv->rps.power = new_power; dev_priv->rps.last_adj = 0; } @@ -3847,7 +3949,10 @@ static 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) || IS_BROADWELL(dev)) + if (IS_GEN9(dev)) + I915_WRITE(GEN6_RPNSWREQ, + GEN9_FREQUENCY(val)); + else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(val)); else @@ -3860,7 +3965,7 @@ static void gen6_set_rps(struct drm_device *dev, u8 val) /* Make sure we continue to get interrupts * until we hit the minimum or maximum frequencies. */ - I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, gen6_rps_limits(dev_priv, val)); + I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, intel_rps_limits(dev_priv, val)); I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val)); POSTING_READ(GEN6_RPNSWREQ); @@ -4081,6 +4186,13 @@ static void gen6_init_rps_frequencies(struct drm_device *dev) dev_priv->rps.rp0_freq = (rp_state_cap >> 0) & 0xff; dev_priv->rps.rp1_freq = (rp_state_cap >> 8) & 0xff; dev_priv->rps.min_freq = (rp_state_cap >> 16) & 0xff; + if (IS_SKYLAKE(dev)) { + /* Store the frequency values in 16.66 MHZ units, which is + the natural hardware unit for SKL */ + dev_priv->rps.rp0_freq *= GEN9_FREQ_SCALER; + dev_priv->rps.rp1_freq *= GEN9_FREQ_SCALER; + dev_priv->rps.min_freq *= GEN9_FREQ_SCALER; + } /* hw_max = RP0 until we check for overclocking */ dev_priv->rps.max_freq = dev_priv->rps.rp0_freq; @@ -4121,23 +4233,21 @@ static void gen9_enable_rps(struct drm_device *dev) gen6_init_rps_frequencies(dev); - I915_WRITE(GEN6_RPNSWREQ, 0xc800000); - I915_WRITE(GEN6_RC_VIDEO_FREQ, 0xc800000); + /* Program defaults and thresholds for RPS*/ + I915_WRITE(GEN6_RC_VIDEO_FREQ, + GEN9_FREQUENCY(dev_priv->rps.rp1_freq)); + + /* 1 second timeout*/ + I915_WRITE(GEN6_RP_DOWN_TIMEOUT, + GT_INTERVAL_FROM_US(dev_priv, 1000000)); - I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 0xf4240); - I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, 0x12060000); - I915_WRITE(GEN6_RP_UP_THRESHOLD, 0xe808); - I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 0x3bd08); - I915_WRITE(GEN6_RP_UP_EI, 0x101d0); - I915_WRITE(GEN6_RP_DOWN_EI, 0x55730); I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 0xa); - I915_WRITE(GEN6_PMINTRMSK, 0x6); - I915_WRITE(GEN6_RP_CONTROL, GEN6_RP_MEDIA_TURBO | - GEN6_RP_MEDIA_HW_MODE | GEN6_RP_MEDIA_IS_GFX | - GEN6_RP_ENABLE | GEN6_RP_UP_BUSY_AVG | - GEN6_RP_DOWN_IDLE_AVG); - gen6_enable_rps_interrupts(dev); + /* Leaning on the below call to gen6_set_rps to program/setup the + * Up/Down EI & threshold registers, as well as the RP_CONTROL, + * RP_INTERRUPT_LIMITS & RPNSWREQ registers */ + dev_priv->rps.power = HIGH_POWER; /* force a reset */ + gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); } @@ -4990,124 +5100,6 @@ static void valleyview_enable_rps(struct drm_device *dev) intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); } -void ironlake_teardown_rc6(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - if (dev_priv->ips.renderctx) { - i915_gem_object_ggtt_unpin(dev_priv->ips.renderctx); - drm_gem_object_unreference(&dev_priv->ips.renderctx->base); - dev_priv->ips.renderctx = NULL; - } - - if (dev_priv->ips.pwrctx) { - i915_gem_object_ggtt_unpin(dev_priv->ips.pwrctx); - drm_gem_object_unreference(&dev_priv->ips.pwrctx->base); - dev_priv->ips.pwrctx = NULL; - } -} - -static void ironlake_disable_rc6(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - if (I915_READ(PWRCTXA)) { - /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */ - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT); - wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON), - 50); - - I915_WRITE(PWRCTXA, 0); - POSTING_READ(PWRCTXA); - - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); - POSTING_READ(RSTDBYCTL); - } -} - -static int ironlake_setup_rc6(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - if (dev_priv->ips.renderctx == NULL) - dev_priv->ips.renderctx = intel_alloc_context_page(dev); - if (!dev_priv->ips.renderctx) - return -ENOMEM; - - if (dev_priv->ips.pwrctx == NULL) - dev_priv->ips.pwrctx = intel_alloc_context_page(dev); - if (!dev_priv->ips.pwrctx) { - ironlake_teardown_rc6(dev); - return -ENOMEM; - } - - return 0; -} - -static void ironlake_enable_rc6(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_engine_cs *ring = &dev_priv->ring[RCS]; - bool was_interruptible; - int ret; - - /* rc6 disabled by default due to repeated reports of hanging during - * boot and resume. - */ - if (!intel_enable_rc6(dev)) - return; - - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - - ret = ironlake_setup_rc6(dev); - if (ret) - return; - - was_interruptible = dev_priv->mm.interruptible; - dev_priv->mm.interruptible = false; - - /* - * GPU can automatically power down the render unit if given a page - * to save state. - */ - ret = intel_ring_begin(ring, 6); - if (ret) { - ironlake_teardown_rc6(dev); - dev_priv->mm.interruptible = was_interruptible; - return; - } - - intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN); - intel_ring_emit(ring, MI_SET_CONTEXT); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) | - MI_MM_SPACE_GTT | - MI_SAVE_EXT_STATE_EN | - MI_RESTORE_EXT_STATE_EN | - MI_RESTORE_INHIBIT); - intel_ring_emit(ring, MI_SUSPEND_FLUSH); - intel_ring_emit(ring, MI_NOOP); - intel_ring_emit(ring, MI_FLUSH); - intel_ring_advance(ring); - - /* - * Wait for the command parser to advance past MI_SET_CONTEXT. The HW - * does an implicit flush, combined with MI_FLUSH above, it should be - * safe to assume that renderctx is valid - */ - ret = intel_ring_idle(ring); - dev_priv->mm.interruptible = was_interruptible; - if (ret) { - DRM_ERROR("failed to enable ironlake power savings\n"); - ironlake_teardown_rc6(dev); - return; - } - - 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, GEN6_RC_CTL_RC6_ENABLE); -} - static unsigned long intel_pxfreq(u32 vidfreq) { unsigned long freq; @@ -5620,12 +5612,7 @@ static void gen6_suspend_rps(struct drm_device *dev) flush_delayed_work(&dev_priv->rps.delayed_resume_work); - /* - * TODO: disable RPS interrupts on GEN9+ too once RPS support - * is added for it. - */ - if (INTEL_INFO(dev)->gen < 9) - gen6_disable_rps_interrupts(dev); + gen6_disable_rps_interrupts(dev); } /** @@ -5655,7 +5642,6 @@ 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) { intel_suspend_gt_powersave(dev); @@ -5683,12 +5669,7 @@ static void intel_gen6_powersave_work(struct work_struct *work) mutex_lock(&dev_priv->rps.hw_lock); - /* - * TODO: reset/enable RPS interrupts on GEN9+ too, once RPS support is - * added for it. - */ - if (INTEL_INFO(dev)->gen < 9) - gen6_reset_rps_interrupts(dev); + gen6_reset_rps_interrupts(dev); if (IS_CHERRYVIEW(dev)) { cherryview_enable_rps(dev); @@ -5707,8 +5688,7 @@ static void intel_gen6_powersave_work(struct work_struct *work) } dev_priv->rps.enabled = true; - if (INTEL_INFO(dev)->gen < 9) - gen6_enable_rps_interrupts(dev); + gen6_enable_rps_interrupts(dev); mutex_unlock(&dev_priv->rps.hw_lock); @@ -5726,7 +5706,6 @@ void intel_enable_gt_powersave(struct drm_device *dev) if (IS_IRONLAKE_M(dev)) { mutex_lock(&dev->struct_mutex); ironlake_enable_drps(dev); - ironlake_enable_rc6(dev); intel_init_emon(dev); mutex_unlock(&dev->struct_mutex); } else if (INTEL_INFO(dev)->gen >= 6) { @@ -6259,11 +6238,22 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) gen6_check_mch_setup(dev); } +static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv) +{ + I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE); + + /* + * Disable trickle feed and enable pnd deadline calculation + */ + I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE); + I915_WRITE(CBR1_VLV, 0); +} + static void valleyview_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); + vlv_init_display_clock_gating(dev_priv); /* WaDisableEarlyCull:vlv */ I915_WRITE(_3D_CHICKEN3, @@ -6311,8 +6301,6 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN7_UCGCTL4, I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE); - I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE); - /* * BSpec says this must be set, even though * WaDisable4x2SubspanOptimization isn't listed for VLV. @@ -6349,9 +6337,7 @@ 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); + vlv_init_display_clock_gating(dev_priv); /* WaVSRefCountFullforceMissDisable:chv */ /* WaDSRefCountFullforceMissDisable:chv */ @@ -6541,7 +6527,7 @@ void intel_init_pm(struct drm_device *dev) else if (INTEL_INFO(dev)->gen == 8) dev_priv->display.init_clock_gating = broadwell_init_clock_gating; } else if (IS_CHERRYVIEW(dev)) { - dev_priv->display.update_wm = cherryview_update_wm; + dev_priv->display.update_wm = valleyview_update_wm; dev_priv->display.update_sprite_wm = valleyview_update_sprite_wm; dev_priv->display.init_clock_gating = cherryview_init_clock_gating; @@ -6709,7 +6695,9 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val) int intel_gpu_freq(struct drm_i915_private *dev_priv, int val) { - if (IS_CHERRYVIEW(dev_priv->dev)) + if (IS_GEN9(dev_priv->dev)) + return (val * GT_FREQUENCY_MULTIPLIER) / GEN9_FREQ_SCALER; + else if (IS_CHERRYVIEW(dev_priv->dev)) return chv_gpu_freq(dev_priv, val); else if (IS_VALLEYVIEW(dev_priv->dev)) return byt_gpu_freq(dev_priv, val); @@ -6719,7 +6707,9 @@ int intel_gpu_freq(struct drm_i915_private *dev_priv, int val) int intel_freq_opcode(struct drm_i915_private *dev_priv, int val) { - if (IS_CHERRYVIEW(dev_priv->dev)) + if (IS_GEN9(dev_priv->dev)) + return (val * GEN9_FREQ_SCALER) / GT_FREQUENCY_MULTIPLIER; + else if (IS_CHERRYVIEW(dev_priv->dev)) return chv_freq_opcode(dev_priv, val); else if (IS_VALLEYVIEW(dev_priv->dev)) return byt_freq_opcode(dev_priv, val); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index cd79c3843452..441e2502b889 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -317,29 +317,6 @@ gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring) return 0; } -static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value) -{ - int ret; - - if (!ring->fbc_dirty) - return 0; - - ret = intel_ring_begin(ring, 6); - if (ret) - return ret; - /* WaFbcNukeOn3DBlt:ivb/hsw */ - intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1)); - intel_ring_emit(ring, MSG_FBC_REND_STATE); - intel_ring_emit(ring, value); - intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) | MI_SRM_LRM_GLOBAL_GTT); - intel_ring_emit(ring, MSG_FBC_REND_STATE); - intel_ring_emit(ring, ring->scratch.gtt_offset + 256); - intel_ring_advance(ring); - - ring->fbc_dirty = false; - return 0; -} - static int gen7_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) @@ -398,9 +375,6 @@ gen7_render_ring_flush(struct intel_engine_cs *ring, intel_ring_emit(ring, 0); intel_ring_advance(ring); - if (!invalidate_domains && flush_domains) - return gen7_ring_fbc_flush(ring, FBC_REND_NUKE); - return 0; } @@ -458,14 +432,7 @@ gen8_render_ring_flush(struct intel_engine_cs *ring, return ret; } - ret = gen8_emit_pipe_control(ring, flags, scratch_addr); - if (ret) - return ret; - - if (!invalidate_domains && flush_domains) - return gen7_ring_fbc_flush(ring, FBC_REND_NUKE); - - return 0; + return gen8_emit_pipe_control(ring, flags, scratch_addr); } static void ring_write_tail(struct intel_engine_cs *ring, @@ -2477,7 +2444,6 @@ static int gen6_ring_flush(struct intel_engine_cs *ring, u32 invalidate, u32 flush) { struct drm_device *dev = ring->dev; - struct drm_i915_private *dev_priv = dev->dev_private; uint32_t cmd; int ret; @@ -2486,7 +2452,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring, return ret; cmd = MI_FLUSH_DW; - if (INTEL_INFO(ring->dev)->gen >= 8) + if (INTEL_INFO(dev)->gen >= 8) cmd += 1; /* We always require a command barrier so that subsequent @@ -2506,7 +2472,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring, cmd |= MI_INVALIDATE_TLB; intel_ring_emit(ring, cmd); intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT); - if (INTEL_INFO(ring->dev)->gen >= 8) { + if (INTEL_INFO(dev)->gen >= 8) { intel_ring_emit(ring, 0); /* upper addr */ intel_ring_emit(ring, 0); /* value */ } else { @@ -2515,13 +2481,6 @@ static int gen6_ring_flush(struct intel_engine_cs *ring, } intel_ring_advance(ring); - if (!invalidate && flush) { - if (IS_GEN7(dev)) - return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN); - else if (IS_BROADWELL(dev)) - dev_priv->fbc.need_sw_cache_clean = true; - } - return 0; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 8f3b49a23ccf..c761fe05ad6f 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -267,7 +267,6 @@ struct intel_engine_cs { */ struct drm_i915_gem_request *outstanding_lazy_request; bool gpu_caches_dirty; - bool fbc_dirty; wait_queue_head_t irq_queue; diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 6d8e29abbc33..ce00e6994eeb 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -194,8 +194,39 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv) outb(inb(VGA_MSR_READ), VGA_MSR_WRITE); vga_put(dev->pdev, VGA_RSRC_LEGACY_IO); - if (IS_BROADWELL(dev) || (INTEL_INFO(dev)->gen >= 9)) - gen8_irq_power_well_post_enable(dev_priv); + if (IS_BROADWELL(dev)) + gen8_irq_power_well_post_enable(dev_priv, + 1 << PIPE_C | 1 << PIPE_B); +} + +static void skl_power_well_post_enable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + struct drm_device *dev = dev_priv->dev; + + /* + * After we re-enable the power well, if we touch VGA register 0x3d5 + * we'll get unclaimed register interrupts. This stops after we write + * anything to the VGA MSR register. The vgacon module uses this + * register all the time, so if we unbind our driver and, as a + * consequence, bind vgacon, we'll get stuck in an infinite loop at + * console_unlock(). So make here we touch the VGA MSR register, making + * sure vgacon can keep working normally without triggering interrupts + * and error messages. + */ + if (power_well->data == SKL_DISP_PW_2) { + vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO); + outb(inb(VGA_MSR_READ), VGA_MSR_WRITE); + vga_put(dev->pdev, VGA_RSRC_LEGACY_IO); + + gen8_irq_power_well_post_enable(dev_priv, + 1 << PIPE_C | 1 << PIPE_B); + } + + if (power_well->data == SKL_DISP_PW_1) { + intel_prepare_ddi(dev); + gen8_irq_power_well_post_enable(dev_priv, 1 << PIPE_A); + } } static void hsw_set_power_well(struct drm_i915_private *dev_priv, @@ -293,7 +324,7 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, { uint32_t tmp, fuse_status; uint32_t req_mask, state_mask; - bool check_fuse_status = false; + bool is_enabled, enable_requested, check_fuse_status = false; tmp = I915_READ(HSW_PWR_WELL_DRIVER); fuse_status = I915_READ(SKL_FUSE_STATUS); @@ -324,15 +355,17 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, } req_mask = SKL_POWER_WELL_REQ(power_well->data); + enable_requested = tmp & req_mask; state_mask = SKL_POWER_WELL_STATE(power_well->data); + is_enabled = tmp & state_mask; if (enable) { - if (!(tmp & req_mask)) { + if (!enable_requested) { I915_WRITE(HSW_PWR_WELL_DRIVER, tmp | req_mask); - DRM_DEBUG_KMS("Enabling %s\n", power_well->name); } - if (!(tmp & state_mask)) { + if (!is_enabled) { + DRM_DEBUG_KMS("Enabling %s\n", power_well->name); if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) & state_mask), 1)) DRM_ERROR("%s enable timeout\n", @@ -340,7 +373,7 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, check_fuse_status = true; } } else { - if (tmp & req_mask) { + if (enable_requested) { I915_WRITE(HSW_PWR_WELL_DRIVER, tmp & ~req_mask); POSTING_READ(HSW_PWR_WELL_DRIVER); DRM_DEBUG_KMS("Disabling %s\n", power_well->name); @@ -358,6 +391,9 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, DRM_ERROR("PG2 distributing status timeout\n"); } } + + if (enable && !is_enabled) + skl_power_well_post_enable(dev_priv, power_well); } static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv, @@ -1420,7 +1456,7 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv) } /** - * intel_aux_display_runtime_get - grab an auxilliary power domain reference + * intel_aux_display_runtime_get - grab an auxiliary power domain reference * @dev_priv: i915 device instance * * This function grabs a power domain reference for the auxiliary power domain @@ -1437,10 +1473,10 @@ void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv) } /** - * intel_aux_display_runtime_put - release an auxilliary power domain reference + * intel_aux_display_runtime_put - release an auxiliary power domain reference * @dev_priv: i915 device instance * - * This function drops the auxilliary power domain reference obtained by + * This function drops the auxiliary power domain reference obtained by * intel_aux_display_runtime_get() and might power down the corresponding * hardware block right away if this is the last reference. */ diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 64ad2b40179f..9e554c2cfbb4 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1247,7 +1247,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder) switch (crtc->config->pixel_multiplier) { default: - WARN(1, "unknown pixel mutlipler specified\n"); + WARN(1, "unknown pixel multiplier specified\n"); case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break; case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break; case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break; diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 7051da7015d3..a82873631851 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -1361,10 +1361,10 @@ out_unlock: int intel_plane_restore(struct drm_plane *plane) { - if (!plane->crtc || !plane->fb) + if (!plane->crtc || !plane->state->fb) return 0; - return plane->funcs->update_plane(plane, plane->crtc, plane->fb, + return plane->funcs->update_plane(plane, plane->crtc, plane->state->fb, plane->state->crtc_x, plane->state->crtc_y, plane->state->crtc_w, plane->state->crtc_h, plane->state->src_x, plane->state->src_y, diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 8879f17770aa..ab5cc94588e1 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -557,18 +557,24 @@ hsw_unclaimed_reg_debug(struct drm_i915_private *dev_priv, u32 reg, bool read, WARN(1, "Unclaimed register detected %s %s register 0x%x\n", when, op, reg); __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); + i915.mmio_debug--; /* Only report the first N failures */ } } static void hsw_unclaimed_reg_detect(struct drm_i915_private *dev_priv) { - if (i915.mmio_debug) + static bool mmio_debug_once = true; + + if (i915.mmio_debug || !mmio_debug_once) return; if (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM) { - DRM_ERROR("Unclaimed register detected. Please use the i915.mmio_debug=1 to debug this problem."); + DRM_DEBUG("Unclaimed register detected, " + "enabling oneshot unclaimed register reporting. " + "Please use i915.mmio_debug=N for more information.\n"); __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); + i915.mmio_debug = mmio_debug_once--; } } @@ -1082,8 +1088,14 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev) /* We need to init first for ECOBUS access and then * determine later if we want to reinit, in case of MT access is - * not working + * not working. In this stage we don't know which flavour this + * ivb is, so it is better to reset also the gen6 fw registers + * before the ecobus check. */ + + __raw_i915_write32(dev_priv, FORCEWAKE, 0); + __raw_posting_read(dev_priv, ECOBUS); + fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_MT_ACK); diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index d13d1b5a859f..df09ca7c4889 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -1030,37 +1030,59 @@ static inline bool radeon_test_signaled(struct radeon_fence *fence) return test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags); } +struct radeon_wait_cb { + struct fence_cb base; + struct task_struct *task; +}; + +static void +radeon_fence_wait_cb(struct fence *fence, struct fence_cb *cb) +{ + struct radeon_wait_cb *wait = + container_of(cb, struct radeon_wait_cb, base); + + wake_up_process(wait->task); +} + static signed long radeon_fence_default_wait(struct fence *f, bool intr, signed long t) { struct radeon_fence *fence = to_radeon_fence(f); struct radeon_device *rdev = fence->rdev; - bool signaled; + struct radeon_wait_cb cb; - fence_enable_sw_signaling(&fence->base); + cb.task = current; - /* - * This function has to return -EDEADLK, but cannot hold - * exclusive_lock during the wait because some callers - * may already hold it. This means checking needs_reset without - * lock, and not fiddling with any gpu internals. - * - * The callback installed with fence_enable_sw_signaling will - * run before our wait_event_*timeout call, so we will see - * both the signaled fence and the changes to needs_reset. - */ + if (fence_add_callback(f, &cb.base, radeon_fence_wait_cb)) + return t; + + while (t > 0) { + if (intr) + set_current_state(TASK_INTERRUPTIBLE); + else + set_current_state(TASK_UNINTERRUPTIBLE); + + /* + * radeon_test_signaled must be called after + * set_current_state to prevent a race with wake_up_process + */ + if (radeon_test_signaled(fence)) + break; + + if (rdev->needs_reset) { + t = -EDEADLK; + break; + } + + t = schedule_timeout(t); + + if (t > 0 && intr && signal_pending(current)) + t = -ERESTARTSYS; + } + + __set_current_state(TASK_RUNNING); + fence_remove_callback(f, &cb.base); - if (intr) - t = wait_event_interruptible_timeout(rdev->fence_queue, - ((signaled = radeon_test_signaled(fence)) || - rdev->needs_reset), t); - else - t = wait_event_timeout(rdev->fence_queue, - ((signaled = radeon_test_signaled(fence)) || - rdev->needs_reset), t); - - if (t > 0 && !signaled) - return -EDEADLK; return t; } diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 86e75798320f..b1d74bc375d8 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -7236,8 +7236,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK); if (!vclk || !dclk) { - /* keep the Bypass mode, put PLL to sleep */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* keep the Bypass mode */ return 0; } @@ -7253,8 +7252,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) /* set VCO_MODE to 1 */ WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK); - /* toggle UPLL_SLEEP to 1 then back to 0 */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* disable sleep mode */ WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK); /* deassert UPLL_RESET */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 6c6b655defcf..e13b9cbc304e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -725,32 +725,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err1; } - ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, - (dev_priv->vram_size >> PAGE_SHIFT)); - if (unlikely(ret != 0)) { - DRM_ERROR("Failed initializing memory manager for VRAM.\n"); - goto out_err2; - } - - dev_priv->has_gmr = true; - if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || - refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, - VMW_PL_GMR) != 0) { - DRM_INFO("No GMR memory available. " - "Graphics memory resources are very limited.\n"); - dev_priv->has_gmr = false; - } - - if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { - dev_priv->has_mob = true; - if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, - VMW_PL_MOB) != 0) { - DRM_INFO("No MOB memory available. " - "3D will be disabled.\n"); - dev_priv->has_mob = false; - } - } - dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start, dev_priv->mmio_size); @@ -813,6 +787,33 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_no_fman; } + + ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, + (dev_priv->vram_size >> PAGE_SHIFT)); + if (unlikely(ret != 0)) { + DRM_ERROR("Failed initializing memory manager for VRAM.\n"); + goto out_no_vram; + } + + dev_priv->has_gmr = true; + if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || + refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, + VMW_PL_GMR) != 0) { + DRM_INFO("No GMR memory available. " + "Graphics memory resources are very limited.\n"); + dev_priv->has_gmr = false; + } + + if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { + dev_priv->has_mob = true; + if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, + VMW_PL_MOB) != 0) { + DRM_INFO("No MOB memory available. " + "3D will be disabled.\n"); + dev_priv->has_mob = false; + } + } + vmw_kms_save_vga(dev_priv); /* Start kms and overlay systems, needs fifo. */ @@ -838,6 +839,12 @@ out_no_fifo: vmw_kms_close(dev_priv); out_no_kms: vmw_kms_restore_vga(dev_priv); + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); +out_no_vram: vmw_fence_manager_takedown(dev_priv->fman); out_no_fman: if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -853,12 +860,6 @@ out_err4: iounmap(dev_priv->mmio_virt); out_err3: arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); -out_err2: (void)ttm_bo_device_release(&dev_priv->bdev); out_err1: vmw_ttm_global_release(dev_priv); @@ -887,6 +888,13 @@ static int vmw_driver_unload(struct drm_device *dev) } vmw_kms_close(dev_priv); vmw_overlay_close(dev_priv); + + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); + vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) drm_irq_uninstall(dev_priv->dev); @@ -898,11 +906,6 @@ static int vmw_driver_unload(struct drm_device *dev) ttm_object_device_release(&dev_priv->tdev); iounmap(dev_priv->mmio_virt); arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); (void)ttm_bo_device_release(&dev_priv->bdev); vmw_ttm_global_release(dev_priv); @@ -1235,6 +1238,7 @@ static void vmw_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + pci_disable_device(pdev); drm_put_dev(dev); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 33176d05db35..654c8daeb5ab 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -890,7 +890,8 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo); if (unlikely(ret != 0)) { DRM_ERROR("Could not find or use MOB buffer.\n"); - return -EINVAL; + ret = -EINVAL; + goto out_no_reloc; } bo = &vmw_bo->base; @@ -914,7 +915,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, out_no_reloc: vmw_dmabuf_unreference(&vmw_bo); - vmw_bo_p = NULL; + *vmw_bo_p = NULL; return ret; } @@ -951,7 +952,8 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo); if (unlikely(ret != 0)) { DRM_ERROR("Could not find or use GMR region.\n"); - return -EINVAL; + ret = -EINVAL; + goto out_no_reloc; } bo = &vmw_bo->base; @@ -974,7 +976,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, out_no_reloc: vmw_dmabuf_unreference(&vmw_bo); - vmw_bo_p = NULL; + *vmw_bo_p = NULL; return ret; } @@ -2780,13 +2782,11 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data, NULL, arg->command_size, arg->throttle_us, (void __user *)(unsigned long)arg->fence_rep, NULL); - + ttm_read_unlock(&dev_priv->reservation_sem); if (unlikely(ret != 0)) - goto out_unlock; + return ret; vmw_kms_cursor_post_execbuf(dev_priv); -out_unlock: - ttm_read_unlock(&dev_priv->reservation_sem); - return ret; + return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 8725b79e7847..07cda8cbbddb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2033,23 +2033,17 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, int i; struct drm_mode_config *mode_config = &dev->mode_config; - ret = ttm_read_lock(&dev_priv->reservation_sem, true); - if (unlikely(ret != 0)) - return ret; - if (!arg->num_outputs) { struct drm_vmw_rect def_rect = {0, 0, 800, 600}; vmw_du_update_layout(dev_priv, 1, &def_rect); - goto out_unlock; + return 0; } rects_size = arg->num_outputs * sizeof(struct drm_vmw_rect); rects = kcalloc(arg->num_outputs, sizeof(struct drm_vmw_rect), GFP_KERNEL); - if (unlikely(!rects)) { - ret = -ENOMEM; - goto out_unlock; - } + if (unlikely(!rects)) + return -ENOMEM; user_rects = (void __user *)(unsigned long)arg->rects; ret = copy_from_user(rects, user_rects, rects_size); @@ -2074,7 +2068,5 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, out_free: kfree(rects); -out_unlock: - ttm_read_unlock(&dev_priv->reservation_sem); return ret; } |
