/* Query intel_iommu to see if we need the workaround. Presumably that
* was loaded first.
*/
- if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB ||
+ if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG ||
gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
intel_iommu_gfx_mapped)
return 1;
}
EXPORT_SYMBOL(intel_gmch_probe);
-void intel_gtt_get(size_t *gtt_total, size_t *stolen_size,
- phys_addr_t *mappable_base, unsigned long *mappable_end)
+void intel_gtt_get(u64 *gtt_total, size_t *stolen_size,
+ phys_addr_t *mappable_base, u64 *mappable_end)
{
*gtt_total = intel_private.gtt_total_entries << PAGE_SHIFT;
*stolen_size = intel_private.stolen_size;
goto err_created;
}
- if (old_blob)
- drm_property_unreference_blob(old_blob);
-
+ drm_property_unreference_blob(old_blob);
*replace = new_blob;
return 0;
return 0;
if (edid)
- size = EDID_LENGTH + (1 + edid->extensions);
+ size = EDID_LENGTH * (1 + edid->extensions);
ret = drm_property_replace_global_blob(dev,
&connector->edid_blob_ptr,
return i915_gem_obj_to_ggtt(obj) ? "g" : " ";
}
+static u64 i915_gem_obj_total_ggtt_size(struct drm_i915_gem_object *obj)
+{
+ u64 size = 0;
+ struct i915_vma *vma;
+
+ list_for_each_entry(vma, &obj->vma_list, vma_link) {
+ if (i915_is_ggtt(vma->vm) &&
+ drm_mm_node_allocated(&vma->node))
+ size += vma->node.size;
+ }
+
+ return size;
+}
+
static void
describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
{
if (obj->fence_reg != I915_FENCE_REG_NONE)
seq_printf(m, " (fence: %d)", obj->fence_reg);
list_for_each_entry(vma, &obj->vma_list, vma_link) {
- if (!i915_is_ggtt(vma->vm))
- seq_puts(m, " (pp");
+ seq_printf(m, " (%sgtt offset: %08llx, size: %08llx",
+ i915_is_ggtt(vma->vm) ? "g" : "pp",
+ vma->node.start, vma->node.size);
+ if (i915_is_ggtt(vma->vm))
+ seq_printf(m, ", type: %u)", vma->ggtt_view.type);
else
- seq_puts(m, " (g");
- seq_printf(m, "gtt offset: %08llx, size: %08llx, type: %u)",
- vma->node.start, vma->node.size,
- vma->ggtt_view.type);
+ seq_puts(m, ")");
}
if (obj->stolen)
seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_address_space *vm = &dev_priv->gtt.base;
struct i915_vma *vma;
- size_t total_obj_size, total_gtt_size;
+ u64 total_obj_size, total_gtt_size;
int count, ret;
ret = mutex_lock_interruptible(&dev->struct_mutex);
}
mutex_unlock(&dev->struct_mutex);
- seq_printf(m, "Total %d objects, %zu bytes, %zu GTT size\n",
+ seq_printf(m, "Total %d objects, %llu bytes, %llu GTT size\n",
count, total_obj_size, total_gtt_size);
return 0;
}
struct drm_device *dev = node->minor->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj;
- size_t total_obj_size, total_gtt_size;
+ u64 total_obj_size, total_gtt_size;
LIST_HEAD(stolen);
int count, ret;
list_add(&obj->obj_exec_link, &stolen);
total_obj_size += obj->base.size;
- total_gtt_size += i915_gem_obj_ggtt_size(obj);
+ total_gtt_size += i915_gem_obj_total_ggtt_size(obj);
count++;
}
list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
}
mutex_unlock(&dev->struct_mutex);
- seq_printf(m, "Total %d objects, %zu bytes, %zu GTT size\n",
+ seq_printf(m, "Total %d objects, %llu bytes, %llu GTT size\n",
count, total_obj_size, total_gtt_size);
return 0;
}
#define count_objects(list, member) do { \
list_for_each_entry(obj, list, member) { \
- size += i915_gem_obj_ggtt_size(obj); \
+ size += i915_gem_obj_total_ggtt_size(obj); \
++count; \
if (obj->map_and_fenceable) { \
mappable_size += i915_gem_obj_ggtt_size(obj); \
struct file_stats {
struct drm_i915_file_private *file_priv;
- int count;
- size_t total, unbound;
- size_t global, shared;
- size_t active, inactive;
+ unsigned long count;
+ u64 total, unbound;
+ u64 global, shared;
+ u64 active, inactive;
};
static int per_file_stats(int id, void *ptr, void *data)
#define print_file_stats(m, name, stats) do { \
if (stats.count) \
- seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu global, %zu shared, %zu unbound)\n", \
+ seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu global, %llu shared, %llu unbound)\n", \
name, \
stats.count, \
stats.total, \
#define count_vmas(list, member) do { \
list_for_each_entry(vma, list, member) { \
- size += i915_gem_obj_ggtt_size(vma->obj); \
+ size += i915_gem_obj_total_ggtt_size(vma->obj); \
++count; \
if (vma->obj->map_and_fenceable) { \
mappable_size += i915_gem_obj_ggtt_size(vma->obj); \
struct drm_device *dev = node->minor->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
u32 count, mappable_count, purgeable_count;
- size_t size, mappable_size, purgeable_size;
+ u64 size, mappable_size, purgeable_size;
struct drm_i915_gem_object *obj;
struct i915_address_space *vm = &dev_priv->gtt.base;
struct drm_file *file;
size = count = mappable_size = mappable_count = 0;
count_objects(&dev_priv->mm.bound_list, global_list);
- seq_printf(m, "%u [%u] objects, %zu [%zu] bytes in gtt\n",
+ seq_printf(m, "%u [%u] objects, %llu [%llu] bytes in gtt\n",
count, mappable_count, size, mappable_size);
size = count = mappable_size = mappable_count = 0;
count_vmas(&vm->active_list, mm_list);
- seq_printf(m, " %u [%u] active objects, %zu [%zu] bytes\n",
+ seq_printf(m, " %u [%u] active objects, %llu [%llu] bytes\n",
count, mappable_count, size, mappable_size);
size = count = mappable_size = mappable_count = 0;
count_vmas(&vm->inactive_list, mm_list);
- seq_printf(m, " %u [%u] inactive objects, %zu [%zu] bytes\n",
+ seq_printf(m, " %u [%u] inactive objects, %llu [%llu] bytes\n",
count, mappable_count, size, mappable_size);
size = count = purgeable_size = purgeable_count = 0;
if (obj->madv == I915_MADV_DONTNEED)
purgeable_size += obj->base.size, ++purgeable_count;
}
- seq_printf(m, "%u unbound objects, %zu bytes\n", count, size);
+ seq_printf(m, "%u unbound objects, %llu bytes\n", count, size);
size = count = mappable_size = mappable_count = 0;
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
++purgeable_count;
}
}
- seq_printf(m, "%u purgeable objects, %zu bytes\n",
+ seq_printf(m, "%u purgeable objects, %llu bytes\n",
purgeable_count, purgeable_size);
- seq_printf(m, "%u pinned mappable objects, %zu bytes\n",
+ seq_printf(m, "%u pinned mappable objects, %llu bytes\n",
mappable_count, mappable_size);
- seq_printf(m, "%u fault mappable objects, %zu bytes\n",
+ seq_printf(m, "%u fault mappable objects, %llu bytes\n",
count, size);
- seq_printf(m, "%zu [%lu] gtt total\n",
+ seq_printf(m, "%llu [%llu] gtt total\n",
dev_priv->gtt.base.total,
- dev_priv->gtt.mappable_end - dev_priv->gtt.base.start);
+ (u64)dev_priv->gtt.mappable_end - dev_priv->gtt.base.start);
seq_putc(m, '\n');
print_batch_pool_stats(m, dev_priv);
uintptr_t list = (uintptr_t) node->info_ent->data;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj;
- size_t total_obj_size, total_gtt_size;
+ u64 total_obj_size, total_gtt_size;
int count, ret;
ret = mutex_lock_interruptible(&dev->struct_mutex);
describe_obj(m, obj);
seq_putc(m, '\n');
total_obj_size += obj->base.size;
- total_gtt_size += i915_gem_obj_ggtt_size(obj);
+ total_gtt_size += i915_gem_obj_total_ggtt_size(obj);
count++;
}
mutex_unlock(&dev->struct_mutex);
- seq_printf(m, "Total %d objects, %zu bytes, %zu GTT size\n",
+ seq_printf(m, "Total %d objects, %llu bytes, %llu GTT size\n",
count, total_obj_size, total_gtt_size);
return 0;
(rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT);
} else if (IS_GEN6(dev) || (IS_GEN7(dev) && !IS_VALLEYVIEW(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);
+ u32 rp_state_limits;
+ u32 gt_perf_status;
+ u32 rp_state_cap;
u32 rpmodectl, rpinclimit, rpdeclimit;
u32 rpstat, cagf, reqf;
u32 rpupei, rpcurup, rpprevup;
u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
int max_freq;
+ rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS);
+ if (IS_BROXTON(dev)) {
+ rp_state_cap = I915_READ(BXT_RP_STATE_CAP);
+ gt_perf_status = I915_READ(BXT_GT_PERF_STATUS);
+ } else {
+ rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
+ gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
+ }
+
/* RPSTAT1 is in the GT power well */
ret = mutex_lock_interruptible(&dev->struct_mutex);
if (ret)
seq_printf(m, "Down threshold: %d%%\n",
dev_priv->rps.down_threshold);
- max_freq = (rp_state_cap & 0xff0000) >> 16;
+ max_freq = (IS_BROXTON(dev) ? rp_state_cap >> 0 :
+ rp_state_cap >> 16) & 0xff;
max_freq *= (IS_SKYLAKE(dev) ? GEN9_FREQ_SCALER : 1);
seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
intel_gpu_freq(dev_priv, max_freq));
seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
intel_gpu_freq(dev_priv, max_freq));
- max_freq = rp_state_cap & 0xff;
+ max_freq = (IS_BROXTON(dev) ? rp_state_cap >> 16 :
+ rp_state_cap >> 0) & 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));
return ironlake_drpc_info(m);
}
+static int i915_frontbuffer_tracking(struct seq_file *m, void *unused)
+{
+ struct drm_info_node *node = m->private;
+ struct drm_device *dev = node->minor->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ seq_printf(m, "FB tracking busy bits: 0x%08x\n",
+ dev_priv->fb_tracking.busy_bits);
+
+ seq_printf(m, "FB tracking flip bits: 0x%08x\n",
+ dev_priv->fb_tracking.flip_bits);
+
+ return 0;
+}
+
static int i915_fbc_status(struct seq_file *m, void *unused)
{
struct drm_info_node *node = m->private;
}
intel_runtime_pm_get(dev_priv);
+ mutex_lock(&dev_priv->fbc.lock);
- if (intel_fbc_enabled(dev)) {
+ if (intel_fbc_enabled(dev_priv))
seq_puts(m, "FBC enabled\n");
- } else {
- seq_puts(m, "FBC disabled: ");
- switch (dev_priv->fbc.no_fbc_reason) {
- case FBC_OK:
- seq_puts(m, "FBC actived, but currently disabled in hardware");
- break;
- case FBC_UNSUPPORTED:
- seq_puts(m, "unsupported by this chipset");
- break;
- case FBC_NO_OUTPUT:
- seq_puts(m, "no outputs");
- break;
- case FBC_STOLEN_TOO_SMALL:
- seq_puts(m, "not enough stolen memory");
- break;
- case FBC_UNSUPPORTED_MODE:
- seq_puts(m, "mode not supported");
- break;
- case FBC_MODE_TOO_LARGE:
- seq_puts(m, "mode too large");
- break;
- case FBC_BAD_PLANE:
- seq_puts(m, "FBC unsupported on plane");
- break;
- case FBC_NOT_TILED:
- seq_puts(m, "scanout buffer not tiled");
- break;
- case FBC_MULTIPLE_PIPES:
- seq_puts(m, "multiple pipes are enabled");
- break;
- case FBC_MODULE_PARAM:
- seq_puts(m, "disabled per module param (default off)");
- break;
- case FBC_CHIP_DEFAULT:
- seq_puts(m, "disabled per chip default");
- break;
- default:
- seq_puts(m, "unknown reason");
- }
- seq_putc(m, '\n');
- }
+ else
+ seq_printf(m, "FBC disabled: %s\n",
+ intel_no_fbc_reason_str(dev_priv->fbc.no_fbc_reason));
+
+ if (INTEL_INFO(dev_priv)->gen >= 7)
+ seq_printf(m, "Compressing: %s\n",
+ yesno(I915_READ(FBC_STATUS2) &
+ FBC_COMPRESSION_MASK));
+ mutex_unlock(&dev_priv->fbc.lock);
intel_runtime_pm_put(dev_priv);
return 0;
if (INTEL_INFO(dev)->gen < 7 || !HAS_FBC(dev))
return -ENODEV;
- drm_modeset_lock_all(dev);
*val = dev_priv->fbc.false_color;
- drm_modeset_unlock_all(dev);
return 0;
}
if (INTEL_INFO(dev)->gen < 7 || !HAS_FBC(dev))
return -ENODEV;
- drm_modeset_lock_all(dev);
+ mutex_lock(&dev_priv->fbc.lock);
reg = I915_READ(ILK_DPFC_CONTROL);
dev_priv->fbc.false_color = val;
(reg | FBC_CTL_FALSE_COLOR) :
(reg & ~FBC_CTL_FALSE_COLOR));
- drm_modeset_unlock_all(dev);
+ mutex_unlock(&dev_priv->fbc.lock);
return 0;
}
if (HAS_PCH_SPLIT(dev))
sr_enabled = I915_READ(WM1_LP_ILK) & WM1_LP_SR_EN;
- else if (IS_CRESTLINE(dev) || IS_I945G(dev) || IS_I945GM(dev))
+ else if (IS_CRESTLINE(dev) || IS_G4X(dev) ||
+ IS_I945G(dev) || IS_I945GM(dev))
sr_enabled = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN;
else if (IS_I915GM(dev))
sr_enabled = I915_READ(INSTPM) & INSTPM_SELF_EN;
else if (IS_PINEVIEW(dev))
sr_enabled = I915_READ(DSPFW3) & PINEVIEW_SELF_REFRESH_EN;
+ else if (IS_VALLEYVIEW(dev))
+ sr_enabled = I915_READ(FW_BLC_SELF_VLV) & FW_CSPWRDWNEN;
intel_runtime_pm_put(dev_priv);
struct drm_i915_private *dev_priv = dev->dev_private;
int ret = 0;
int gpu_freq, ia_freq;
+ unsigned int max_gpu_freq, min_gpu_freq;
- if (!(IS_GEN6(dev) || IS_GEN7(dev))) {
+ if (!HAS_CORE_RING_FREQ(dev)) {
seq_puts(m, "unsupported on this chipset\n");
return 0;
}
if (ret)
goto out;
+ if (IS_SKYLAKE(dev)) {
+ /* Convert GT frequency to 50 HZ units */
+ min_gpu_freq =
+ dev_priv->rps.min_freq_softlimit / GEN9_FREQ_SCALER;
+ max_gpu_freq =
+ dev_priv->rps.max_freq_softlimit / GEN9_FREQ_SCALER;
+ } else {
+ min_gpu_freq = dev_priv->rps.min_freq_softlimit;
+ max_gpu_freq = dev_priv->rps.max_freq_softlimit;
+ }
+
seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
- for (gpu_freq = dev_priv->rps.min_freq_softlimit;
- gpu_freq <= dev_priv->rps.max_freq_softlimit;
- gpu_freq++) {
+ for (gpu_freq = min_gpu_freq; gpu_freq <= max_gpu_freq; gpu_freq++) {
ia_freq = gpu_freq;
sandybridge_pcode_read(dev_priv,
GEN6_PCODE_READ_MIN_FREQ_TABLE,
&ia_freq);
seq_printf(m, "%d\t\t%d\t\t\t\t%d\n",
- intel_gpu_freq(dev_priv, gpu_freq),
+ intel_gpu_freq(dev_priv, (gpu_freq *
+ (IS_SKYLAKE(dev) ? GEN9_FREQ_SCALER : 1))),
((ia_freq >> 0) & 0xff) * 100,
((ia_freq >> 8) & 0xff) * 100);
}
struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
seq_puts(m, "aliasing PPGTT:\n");
- seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.pd_offset);
+ seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.base.ggtt_offset);
ppgtt->debug_dump(ppgtt, m);
}
return 0;
}
-static int i915_pc8_status(struct seq_file *m, void *unused)
+static int i915_runtime_pm_status(struct seq_file *m, void *unused)
{
struct drm_info_node *node = m->private;
struct drm_device *dev = node->minor->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) {
+ if (!HAS_RUNTIME_PM(dev)) {
seq_puts(m, "not supported\n");
return 0;
}
seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->mm.busy));
seq_printf(m, "IRQs disabled: %s\n",
yesno(!intel_irqs_enabled(dev_priv)));
+#ifdef CONFIG_PM
+ seq_printf(m, "Usage count: %d\n",
+ atomic_read(&dev->dev->power.usage_count));
+#else
+ seq_printf(m, "Device Power Management (CONFIG_PM) disabled\n");
+#endif
return 0;
}
seq_printf(m, "---------\n");
for_each_intel_crtc(dev, crtc) {
bool active;
+ struct intel_crtc_state *pipe_config;
int x, y;
+ pipe_config = to_intel_crtc_state(crtc->base.state);
+
seq_printf(m, "CRTC %d: pipe: %c, active=%s (size=%dx%d)\n",
crtc->base.base.id, pipe_name(crtc->pipe),
- yesno(crtc->active), crtc->config->pipe_src_w,
- crtc->config->pipe_src_h);
- if (crtc->active) {
+ yesno(pipe_config->base.active),
+ pipe_config->pipe_src_w, pipe_config->pipe_src_h);
+ if (pipe_config->base.active) {
intel_crtc_info(m, crtc);
active = cursor_position(dev, crtc->pipe, &x, &y);
seq_puts(m, "\n\n");
- if (intel_crtc->config->has_drrs) {
+ if (to_intel_crtc_state(intel_crtc->base.state)->has_drrs) {
struct intel_panel *panel;
mutex_lock(&drrs->mutex);
for_each_intel_crtc(dev, intel_crtc) {
drm_modeset_lock(&intel_crtc->base.mutex, NULL);
- if (intel_crtc->active) {
+ if (intel_crtc->base.state->active) {
active_crtc_cnt++;
seq_printf(m, "\nCRTC %d: ", active_crtc_cnt);
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *crtc =
to_intel_crtc(dev_priv->pipe_to_crtc_mapping[PIPE_A]);
+ struct intel_crtc_state *pipe_config;
drm_modeset_lock_all(dev);
+ pipe_config = to_intel_crtc_state(crtc->base.state);
+
/*
* If we use the eDP transcoder we need to make sure that we don't
* bypass the pfit, since otherwise the pipe CRC source won't work. Only
* relevant on hsw with pipe A when using the always-on power well
* routing.
*/
- if (crtc->config->cpu_transcoder == TRANSCODER_EDP &&
- !crtc->config->pch_pfit.enabled) {
- crtc->config->pch_pfit.force_thru = true;
+ if (pipe_config->cpu_transcoder == TRANSCODER_EDP &&
+ !pipe_config->pch_pfit.enabled) {
+ bool active = pipe_config->base.active;
+
+ if (active) {
+ intel_crtc_control(&crtc->base, false);
+ pipe_config = to_intel_crtc_state(crtc->base.state);
+ }
+
+ pipe_config->pch_pfit.force_thru = true;
intel_display_power_get(dev_priv,
POWER_DOMAIN_PIPE_PANEL_FITTER(PIPE_A));
- intel_crtc_reset(crtc);
+ if (active)
+ intel_crtc_control(&crtc->base, true);
}
drm_modeset_unlock_all(dev);
}
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *crtc =
to_intel_crtc(dev_priv->pipe_to_crtc_mapping[PIPE_A]);
+ struct intel_crtc_state *pipe_config;
drm_modeset_lock_all(dev);
/*
* relevant on hsw with pipe A when using the always-on power well
* routing.
*/
- if (crtc->config->pch_pfit.force_thru) {
- crtc->config->pch_pfit.force_thru = false;
+ pipe_config = to_intel_crtc_state(crtc->base.state);
+ if (pipe_config->pch_pfit.force_thru) {
+ bool active = pipe_config->base.active;
+
+ if (active) {
+ intel_crtc_control(&crtc->base, false);
+ pipe_config = to_intel_crtc_state(crtc->base.state);
+ }
- intel_crtc_reset(crtc);
+ pipe_config->pch_pfit.force_thru = false;
intel_display_power_put(dev_priv,
POWER_DOMAIN_PIPE_PANEL_FITTER(PIPE_A));
+
+ if (active)
+ intel_crtc_control(&crtc->base, true);
}
drm_modeset_unlock_all(dev);
}
pipe_name(pipe));
drm_modeset_lock(&crtc->base.mutex, NULL);
- if (crtc->active)
+ if (crtc->base.state->active)
intel_wait_for_vblank(dev, pipe);
drm_modeset_unlock(&crtc->base.mutex);
static void wm_latency_show(struct seq_file *m, const uint16_t wm[8])
{
struct drm_device *dev = m->private;
- int num_levels = ilk_wm_max_level(dev) + 1;
int level;
+ int num_levels;
+
+ if (IS_CHERRYVIEW(dev))
+ num_levels = 3;
+ else if (IS_VALLEYVIEW(dev))
+ num_levels = 1;
+ else
+ num_levels = ilk_wm_max_level(dev) + 1;
drm_modeset_lock_all(dev);
/*
* - WM1+ latency values in 0.5us units
- * - latencies are in us on gen9
+ * - latencies are in us on gen9/vlv/chv
*/
- if (INTEL_INFO(dev)->gen >= 9)
+ if (INTEL_INFO(dev)->gen >= 9 || IS_VALLEYVIEW(dev))
latency *= 10;
else if (level > 0)
latency *= 5;
{
struct drm_device *dev = inode->i_private;
- if (HAS_GMCH_DISPLAY(dev))
+ if (INTEL_INFO(dev)->gen < 5)
return -ENODEV;
return single_open(file, pri_wm_latency_show, dev);
struct seq_file *m = file->private_data;
struct drm_device *dev = m->private;
uint16_t new[8] = { 0 };
- int num_levels = ilk_wm_max_level(dev) + 1;
+ int num_levels;
int level;
int ret;
char tmp[32];
+ if (IS_CHERRYVIEW(dev))
+ num_levels = 3;
+ else if (IS_VALLEYVIEW(dev))
+ num_levels = 1;
+ else
+ num_levels = ilk_wm_max_level(dev) + 1;
+
if (len >= sizeof(tmp))
return -EINVAL;
{"i915_drpc_info", i915_drpc_info, 0},
{"i915_emon_status", i915_emon_status, 0},
{"i915_ring_freq_table", i915_ring_freq_table, 0},
+ {"i915_frontbuffer_tracking", i915_frontbuffer_tracking, 0},
{"i915_fbc_status", i915_fbc_status, 0},
{"i915_ips_status", i915_ips_status, 0},
{"i915_sr_status", i915_sr_status, 0},
{"i915_edp_psr_status", i915_edp_psr_status, 0},
{"i915_sink_crc_eDP1", i915_sink_crc, 0},
{"i915_energy_uJ", i915_energy_uJ, 0},
- {"i915_pc8_status", i915_pc8_status, 0},
+ {"i915_runtime_pm_status", i915_runtime_pm_status, 0},
{"i915_power_domain_info", i915_power_domain_info, 0},
{"i915_display_info", i915_display_info, 0},
{"i915_semaphore_status", i915_semaphore_status, 0},
#define DRIVER_NAME "i915"
#define DRIVER_DESC "Intel Graphics"
-#define DRIVER_DATE "20150522"
+#define DRIVER_DATE "20150703"
#undef WARN_ON
/* Many gcc seem to no see through this and fall over :( */
HPD_NUM_PINS
};
+#define for_each_hpd_pin(__pin) \
+ for ((__pin) = (HPD_NONE + 1); (__pin) < HPD_NUM_PINS; (__pin)++)
+
+struct i915_hotplug {
+ struct work_struct hotplug_work;
+
+ struct {
+ unsigned long last_jiffies;
+ int count;
+ enum {
+ HPD_ENABLED = 0,
+ HPD_DISABLED = 1,
+ HPD_MARK_DISABLED = 2
+ } state;
+ } stats[HPD_NUM_PINS];
+ u32 event_bits;
+ struct delayed_work reenable_work;
+
+ struct intel_digital_port *irq_port[I915_MAX_PORTS];
+ u32 long_port_mask;
+ u32 short_port_mask;
+ struct work_struct dig_port_work;
+
+ /*
+ * if we get a HPD irq from DP and a HPD irq from non-DP
+ * the non-DP HPD could block the workqueue on a mode config
+ * mutex getting, that userspace may have taken. However
+ * userspace is waiting on the DP workqueue to run which is
+ * blocked behind the non-DP one.
+ */
+ struct workqueue_struct *dp_wq;
+};
+
#define I915_GEM_GPU_DOMAINS \
(I915_GEM_DOMAIN_RENDER | \
I915_GEM_DOMAIN_SAMPLER | \
&dev->mode_config.plane_list, \
base.head)
+#define for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) \
+ list_for_each_entry(intel_plane, \
+ &(dev)->mode_config.plane_list, \
+ base.head) \
+ if ((intel_plane)->pipe == (intel_crtc)->pipe)
+
#define for_each_intel_crtc(dev, intel_crtc) \
list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head)
uint32_t cfgcr1, cfgcr2;
/* bxt */
- uint32_t ebb0, pll0, pll1, pll2, pll3, pll6, pll8, pll10, pcsdw12;
+ uint32_t ebb0, ebb4, pll0, pll1, pll2, pll3, pll6, pll8, pll9, pll10,
+ pcsdw12;
};
struct intel_shared_dpll_config {
struct intel_shared_dpll {
struct intel_shared_dpll_config config;
- struct intel_shared_dpll_config *new_config;
int active; /* count of number of active CRTCs (i.e. DPMS on) */
bool on; /* is the PLL actually active? Disabled during modeset */
struct dpll;
struct drm_i915_display_funcs {
- bool (*fbc_enabled)(struct drm_device *dev);
- void (*enable_fbc)(struct drm_crtc *crtc);
- void (*disable_fbc)(struct drm_device *dev);
int (*get_display_clock_speed)(struct drm_device *dev);
int (*get_fifo_size)(struct drm_device *dev, int plane);
/**
struct drm_crtc *crtc,
uint32_t sprite_width, uint32_t sprite_height,
int pixel_size, bool enable, bool scaled);
- void (*modeset_global_resources)(struct drm_atomic_state *state);
+ int (*modeset_calc_cdclk)(struct drm_atomic_state *state);
+ void (*modeset_commit_cdclk)(struct drm_atomic_state *state);
/* Returns the active state of the crtc, and if the crtc is active,
* fills out the pipe-config with the hw state. */
bool (*get_pipe_config)(struct intel_crtc *,
struct intel_crtc_state *crtc_state);
void (*crtc_enable)(struct drm_crtc *crtc);
void (*crtc_disable)(struct drm_crtc *crtc);
- void (*off)(struct drm_crtc *crtc);
void (*audio_codec_enable)(struct drm_connector *connector,
struct intel_encoder *encoder,
struct drm_display_mode *mode);
int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags);
void (*update_primary_plane)(struct drm_crtc *crtc,
struct drm_framebuffer *fb,
/* This must match up with the value previously used for execbuf2.rsvd1. */
#define DEFAULT_CONTEXT_HANDLE 0
+
+#define CONTEXT_NO_ZEROMAP (1<<0)
/**
* struct intel_context - as the name implies, represents a context.
* @ref: reference count.
* @user_handle: userspace tracking identity for this context.
* @remap_slice: l3 row remapping information.
+ * @flags: context specific flags:
+ * CONTEXT_NO_ZEROMAP: do not allow mapping things to page 0.
* @file_priv: filp associated with this context (NULL for global default
* context).
* @hang_stats: information about the role of this context in possible GPU
struct kref ref;
int user_handle;
uint8_t remap_slice;
+ struct drm_i915_private *i915;
+ int flags;
struct drm_i915_file_private *file_priv;
struct i915_ctx_hang_stats hang_stats;
struct i915_hw_ppgtt *ppgtt;
};
struct i915_fbc {
+ /* This is always the inner lock when overlapping with struct_mutex and
+ * it's the outer lock when overlapping with stolen_lock. */
+ struct mutex lock;
unsigned long uncompressed_size;
unsigned threshold;
unsigned int fb_id;
struct intel_fbc_work {
struct delayed_work work;
- struct drm_crtc *crtc;
+ struct intel_crtc *crtc;
struct drm_framebuffer *fb;
} *fbc_work;
FBC_MULTIPLE_PIPES, /* more than one pipe active */
FBC_MODULE_PARAM,
FBC_CHIP_DEFAULT, /* disabled by default on this chip */
+ FBC_ROTATION, /* rotation is not supported */
+ FBC_IN_DBG_MASTER, /* kernel debugger is active */
} no_fbc_reason;
+
+ bool (*fbc_enabled)(struct drm_i915_private *dev_priv);
+ void (*enable_fbc)(struct intel_crtc *crtc);
+ void (*disable_fbc)(struct drm_i915_private *dev_priv);
};
/**
struct i915_gem_mm {
/** Memory allocator for GTT stolen memory */
struct drm_mm stolen;
+ /** Protects the usage of the GTT stolen memory allocator. This is
+ * always the inner lock when overlapping with struct_mutex. */
+ struct mutex stolen_lock;
+
/** List of all objects in gtt_space. Used to restore gtt
* mappings on resume */
struct list_head bound_list;
enum intel_ddb_partitioning partitioning;
};
-struct vlv_wm_values {
- struct {
- uint16_t primary;
- uint16_t sprite[2];
- uint8_t cursor;
- } pipe[3];
+struct vlv_pipe_wm {
+ uint16_t primary;
+ uint16_t sprite[2];
+ uint8_t cursor;
+};
- struct {
- uint16_t plane;
- uint8_t cursor;
- } sr;
+struct vlv_sr_wm {
+ uint16_t plane;
+ uint8_t cursor;
+};
+struct vlv_wm_values {
+ struct vlv_pipe_wm pipe[3];
+ struct vlv_sr_wm sr;
struct {
uint8_t cursor;
uint8_t sprite[2];
uint8_t primary;
} ddl[3];
+ uint8_t level;
+ bool cxsr;
};
struct skl_ddb_entry {
bool active;
};
+struct i915_execbuffer_params {
+ struct drm_device *dev;
+ struct drm_file *file;
+ uint32_t dispatch_flags;
+ uint32_t args_batch_start_offset;
+ uint32_t batch_obj_vm_offset;
+ struct intel_engine_cs *ring;
+ struct drm_i915_gem_object *batch_obj;
+ struct intel_context *ctx;
+ struct drm_i915_gem_request *request;
+};
+
struct drm_i915_private {
struct drm_device *dev;
struct kmem_cache *objects;
u32 pm_rps_events;
u32 pipestat_irq_mask[I915_MAX_PIPES];
- struct work_struct hotplug_work;
- struct {
- unsigned long hpd_last_jiffies;
- int hpd_cnt;
- enum {
- HPD_ENABLED = 0,
- HPD_DISABLED = 1,
- HPD_MARK_DISABLED = 2
- } hpd_mark;
- } hpd_stats[HPD_NUM_PINS];
- u32 hpd_event_bits;
- struct delayed_work hotplug_reenable_work;
-
+ struct i915_hotplug hotplug;
struct i915_fbc fbc;
struct i915_drrs drrs;
struct intel_opregion opregion;
unsigned int fsb_freq, mem_freq, is_ddr3;
unsigned int skl_boot_cdclk;
- unsigned int cdclk_freq;
+ unsigned int cdclk_freq, max_cdclk_freq;
unsigned int hpll_freq;
/**
/* Reclocking support */
bool render_reclock_avail;
- bool lvds_downclock_avail;
- /* indicates the reduced downclock for LVDS*/
- int lvds_downclock;
struct i915_frontbuffer_tracking fb_tracking;
struct i915_runtime_pm pm;
- struct intel_digital_port *hpd_irq_port[I915_MAX_PORTS];
- u32 long_hpd_port_mask;
- u32 short_hpd_port_mask;
- struct work_struct dig_port_work;
-
- /*
- * if we get a HPD irq from DP and a HPD irq from non-DP
- * the non-DP HPD could block the workqueue on a mode config
- * mutex getting, that userspace may have taken. However
- * userspace is waiting on the DP workqueue to run which is
- * blocked behind the non-DP one.
- */
- struct workqueue_struct *dp_wq;
-
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
- int (*execbuf_submit)(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+ int (*execbuf_submit)(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ struct list_head *vmas);
int (*init_rings)(struct drm_device *dev);
void (*cleanup_ring)(struct intel_engine_cs *ring);
void (*stop_ring)(struct intel_engine_cs *ring);
unsigned int cache_level:3;
unsigned int cache_dirty:1;
- unsigned int has_dma_mapping:1;
-
unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
unsigned int pin_display;
struct intel_context *ctx;
struct intel_ringbuffer *ringbuf;
- /** Batch buffer related to this request if any */
+ /** Batch buffer related to this request if any (used for
+ error state dump only) */
struct drm_i915_gem_object *batch_obj;
/** Time at which this request was emitted, in jiffies. */
};
int i915_gem_request_alloc(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out);
+void i915_gem_request_cancel(struct drm_i915_gem_request *req);
void i915_gem_request_free(struct kref *req_ref);
+int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
+ struct drm_file *file);
static inline uint32_t
i915_gem_request_get_seqno(struct drm_i915_gem_request *req)
((INTEL_DEVID(dev) & 0xf) == 0x6 || \
(INTEL_DEVID(dev) & 0xf) == 0xb || \
(INTEL_DEVID(dev) & 0xf) == 0xe))
+/* ULX machines are also considered ULT. */
+#define IS_BDW_ULX(dev) (IS_BROADWELL(dev) && \
+ (INTEL_DEVID(dev) & 0xf) == 0xe)
#define IS_BDW_GT3(dev) (IS_BROADWELL(dev) && \
(INTEL_DEVID(dev) & 0x00F0) == 0x0020)
#define IS_HSW_ULT(dev) (IS_HASWELL(dev) && \
/* ULX machines are also considered ULT. */
#define IS_HSW_ULX(dev) (INTEL_DEVID(dev) == 0x0A0E || \
INTEL_DEVID(dev) == 0x0A1E)
+#define IS_SKL_ULT(dev) (INTEL_DEVID(dev) == 0x1906 || \
+ INTEL_DEVID(dev) == 0x1913 || \
+ INTEL_DEVID(dev) == 0x1916 || \
+ INTEL_DEVID(dev) == 0x1921 || \
+ INTEL_DEVID(dev) == 0x1926)
+#define IS_SKL_ULX(dev) (INTEL_DEVID(dev) == 0x190E || \
+ INTEL_DEVID(dev) == 0x1915 || \
+ INTEL_DEVID(dev) == 0x191E)
#define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
#define SKL_REVID_A0 (0x0)
*/
#define HAS_128_BYTE_Y_TILING(dev) (!IS_GEN2(dev) && !(IS_I915G(dev) || \
IS_I915GM(dev)))
-#define SUPPORTS_DIGITAL_OUTPUTS(dev) (!IS_GEN2(dev) && !IS_PINEVIEW(dev))
-#define SUPPORTS_INTEGRATED_HDMI(dev) (IS_G4X(dev) || IS_GEN5(dev))
-#define SUPPORTS_INTEGRATED_DP(dev) (IS_G4X(dev) || IS_GEN5(dev))
#define SUPPORTS_TV(dev) (INTEL_INFO(dev)->supports_tv)
#define I915_HAS_HOTPLUG(dev) (INTEL_INFO(dev)->has_hotplug)
#define HAS_CSR(dev) (IS_SKYLAKE(dev))
+#define HAS_RESOURCE_STREAMER(dev) (IS_HASWELL(dev) || \
+ INTEL_INFO(dev)->gen >= 8)
+
+#define HAS_CORE_RING_FREQ(dev) (INTEL_INFO(dev)->gen >= 6 && \
+ !IS_VALLEYVIEW(dev) && !IS_BROXTON(dev))
+
#define INTEL_PCH_DEVICE_ID_MASK 0xff00
#define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00
#define INTEL_PCH_CPT_DEVICE_ID_TYPE 0x1c00
int modeset;
int panel_ignore_lid;
int semaphores;
- unsigned int lvds_downclock;
int lvds_channel_mode;
int panel_use_ssc;
int vbt_sdvo_panel_type;
int use_mmio_flip;
int mmio_debug;
bool verbose_state_checks;
- bool nuclear_pageflip;
int edp_vswing;
};
extern struct i915_params i915 __read_mostly;
unsigned long arg);
#endif
extern int intel_gpu_reset(struct drm_device *dev);
+extern bool intel_has_gpu_reset(struct drm_device *dev);
extern int i915_reset(struct drm_device *dev);
extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
extern unsigned long i915_mch_val(struct drm_i915_private *dev_priv);
extern unsigned long i915_gfx_val(struct drm_i915_private *dev_priv);
extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
-void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
void i915_firmware_load_error_print(const char *fw_path, int err);
+/* intel_hotplug.c */
+void intel_hpd_irq_handler(struct drm_device *dev, u32 pin_mask, u32 long_mask);
+void intel_hpd_init(struct drm_i915_private *dev_priv);
+void intel_hpd_init_work(struct drm_i915_private *dev_priv);
+void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
+enum port intel_hpd_pin_to_port(enum hpd_pin pin);
+
/* i915_irq.c */
void i915_queue_hangcheck(struct drm_device *dev);
__printf(3, 4)
const char *fmt, ...);
extern void intel_irq_init(struct drm_i915_private *dev_priv);
-extern void intel_hpd_init(struct drm_i915_private *dev_priv);
int intel_irq_install(struct drm_i915_private *dev_priv);
void intel_irq_uninstall(struct drm_i915_private *dev_priv);
int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
- struct intel_engine_cs *ring);
-void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct drm_i915_gem_object *obj);
-int i915_gem_ringbuffer_submission(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+ struct drm_i915_gem_request *req);
+void i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params);
+int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ struct list_head *vmas);
int i915_gem_execbuffer(struct drm_device *dev, void *data,
struct drm_file *file_priv);
int i915_gem_execbuffer2(struct drm_device *dev, void *data,
int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
int i915_gem_object_sync(struct drm_i915_gem_object *obj,
- struct intel_engine_cs *to);
+ struct intel_engine_cs *to,
+ struct drm_i915_gem_request **to_req);
void i915_vma_move_to_active(struct i915_vma *vma,
- struct intel_engine_cs *ring);
+ struct drm_i915_gem_request *req);
int i915_gem_dumb_create(struct drm_file *file_priv,
struct drm_device *dev,
struct drm_mode_create_dumb *args);
void i915_gem_retire_requests_ring(struct intel_engine_cs *ring);
int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
bool interruptible);
-int __must_check i915_gem_check_olr(struct drm_i915_gem_request *req);
static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
{
int __must_check i915_gem_init(struct drm_device *dev);
int i915_gem_init_rings(struct drm_device *dev);
int __must_check i915_gem_init_hw(struct drm_device *dev);
-int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice);
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
void i915_gem_init_swizzling(struct drm_device *dev);
void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
int __must_check i915_gpu_idle(struct drm_device *dev);
int __must_check i915_gem_suspend(struct drm_device *dev);
-int __i915_add_request(struct intel_engine_cs *ring,
- struct drm_file *file,
- struct drm_i915_gem_object *batch_obj);
-#define i915_add_request(ring) \
- __i915_add_request(ring, NULL, NULL)
+void __i915_add_request(struct drm_i915_gem_request *req,
+ struct drm_i915_gem_object *batch_obj,
+ bool flush_caches);
+#define i915_add_request(req) \
+ __i915_add_request(req, NULL, true)
+#define i915_add_request_no_flush(req) \
+ __i915_add_request(req, NULL, false)
int __i915_wait_request(struct drm_i915_gem_request *req,
unsigned reset_counter,
bool interruptible,
i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
u32 alignment,
struct intel_engine_cs *pipelined,
+ struct drm_i915_gem_request **pipelined_request,
const struct i915_ggtt_view *view);
void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
const struct i915_ggtt_view *view);
void i915_gem_context_fini(struct drm_device *dev);
void i915_gem_context_reset(struct drm_device *dev);
int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
-int i915_gem_context_enable(struct drm_i915_private *dev_priv);
+int i915_gem_context_enable(struct drm_i915_gem_request *req);
void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
-int i915_switch_context(struct intel_engine_cs *ring,
- struct intel_context *to);
+int i915_switch_context(struct drm_i915_gem_request *req);
struct intel_context *
i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
void i915_gem_context_free(struct kref *ctx_ref);
}
/* i915_gem_stolen.c */
+int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node, u64 size,
+ unsigned alignment);
+void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node);
int i915_gem_init_stolen(struct drm_device *dev);
-int i915_gem_stolen_setup_compression(struct drm_device *dev, int size, int fb_cpp);
-void i915_gem_stolen_cleanup_compression(struct drm_device *dev);
void i915_gem_cleanup_stolen(struct drm_device *dev);
struct drm_i915_gem_object *
i915_gem_object_create_stolen(struct drm_device *dev, u32 size);
int i915_debugfs_connector_add(struct drm_connector *connector);
void intel_display_crc_init(struct drm_device *dev);
#else
- static inline int i915_debugfs_connector_add(struct drm_connector *connector) {}
+ static inline int i915_debugfs_connector_add(struct drm_connector *connector)
+ { return 0; }
static inline void intel_display_crc_init(struct drm_device *dev) {}
#endif
extern void intel_modeset_cleanup(struct drm_device *dev);
extern void intel_connector_unregister(struct intel_connector *);
extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state);
-extern void intel_modeset_setup_hw_state(struct drm_device *dev,
- bool force_restore);
+extern void intel_display_resume(struct drm_device *dev);
extern void i915_redisable_vga(struct drm_device *dev);
extern void i915_redisable_vga_power_on(struct drm_device *dev);
extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_get_aperture *args = data;
- struct drm_i915_gem_object *obj;
+ struct i915_gtt *ggtt = &dev_priv->gtt;
+ struct i915_vma *vma;
size_t pinned;
pinned = 0;
mutex_lock(&dev->struct_mutex);
- list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
- if (i915_gem_obj_is_pinned(obj))
- pinned += i915_gem_obj_ggtt_size(obj);
+ list_for_each_entry(vma, &ggtt->base.active_list, mm_list)
+ if (vma->pin_count)
+ pinned += vma->node.size;
+ list_for_each_entry(vma, &ggtt->base.inactive_list, mm_list)
+ if (vma->pin_count)
+ pinned += vma->node.size;
mutex_unlock(&dev->struct_mutex);
args->aper_size = dev_priv->gtt.base.total;
sg_dma_len(sg) = obj->base.size;
obj->pages = st;
- obj->has_dma_mapping = true;
return 0;
}
sg_free_table(obj->pages);
kfree(obj->pages);
-
- obj->has_dma_mapping = false;
}
static void
if (ret)
return ret;
- intel_fb_obj_invalidate(obj, NULL, ORIGIN_CPU);
+ intel_fb_obj_invalidate(obj, ORIGIN_CPU);
if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) {
unsigned long unwritten;
i915_gem_chipset_flush(dev);
out:
- intel_fb_obj_flush(obj, false);
+ intel_fb_obj_flush(obj, false, ORIGIN_CPU);
return ret;
}
offset = i915_gem_obj_ggtt_offset(obj) + args->offset;
- intel_fb_obj_invalidate(obj, NULL, ORIGIN_GTT);
+ intel_fb_obj_invalidate(obj, ORIGIN_GTT);
while (remain > 0) {
/* Operation in this page
}
out_flush:
- intel_fb_obj_flush(obj, false);
+ intel_fb_obj_flush(obj, false, ORIGIN_GTT);
out_unpin:
i915_gem_object_ggtt_unpin(obj);
out:
if (ret)
return ret;
- intel_fb_obj_invalidate(obj, NULL, ORIGIN_CPU);
+ intel_fb_obj_invalidate(obj, ORIGIN_CPU);
i915_gem_object_pin_pages(obj);
if (needs_clflush_after)
i915_gem_chipset_flush(dev);
- intel_fb_obj_flush(obj, false);
+ intel_fb_obj_flush(obj, false, ORIGIN_CPU);
return ret;
}
return 0;
}
-/*
- * Compare arbitrary request against outstanding lazy request. Emit on match.
- */
-int
-i915_gem_check_olr(struct drm_i915_gem_request *req)
-{
- int ret;
-
- WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
-
- ret = 0;
- if (req == req->ring->outstanding_lazy_request)
- ret = i915_add_request(req->ring);
-
- return ret;
-}
-
static void fake_irq(unsigned long data)
{
wake_up_process((struct task_struct *)data);
return ret;
}
+int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
+ struct drm_file *file)
+{
+ struct drm_i915_private *dev_private;
+ struct drm_i915_file_private *file_priv;
+
+ WARN_ON(!req || !file || req->file_priv);
+
+ if (!req || !file)
+ return -EINVAL;
+
+ if (req->file_priv)
+ return -EINVAL;
+
+ dev_private = req->ring->dev->dev_private;
+ file_priv = file->driver_priv;
+
+ spin_lock(&file_priv->mm.lock);
+ req->file_priv = file_priv;
+ list_add_tail(&req->client_list, &file_priv->mm.request_list);
+ spin_unlock(&file_priv->mm.lock);
+
+ req->pid = get_pid(task_pid(current));
+
+ return 0;
+}
+
static inline void
i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
{
list_del(&request->client_list);
request->file_priv = NULL;
spin_unlock(&file_priv->mm.lock);
+
+ put_pid(request->pid);
+ request->pid = NULL;
}
static void i915_gem_request_retire(struct drm_i915_gem_request *request)
list_del_init(&request->list);
i915_gem_request_remove_from_client(request);
- put_pid(request->pid);
-
i915_gem_request_unreference(request);
}
if (ret)
return ret;
- ret = i915_gem_check_olr(req);
- if (ret)
- return ret;
-
ret = __i915_wait_request(req,
atomic_read(&dev_priv->gpu_error.reset_counter),
interruptible, NULL, NULL);
if (req == NULL)
return 0;
- ret = i915_gem_check_olr(req);
- if (ret)
- goto err;
-
requests[n++] = i915_gem_request_reference(req);
} else {
for (i = 0; i < I915_NUM_RINGS; i++) {
if (req == NULL)
continue;
- ret = i915_gem_check_olr(req);
- if (ret)
- goto err;
-
requests[n++] = i915_gem_request_reference(req);
}
}
NULL, rps);
mutex_lock(&dev->struct_mutex);
-err:
for (i = 0; i < n; i++) {
if (ret == 0)
i915_gem_object_retire_request(obj, requests[i]);
else
ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0);
+ if (write_domain != 0)
+ intel_fb_obj_invalidate(obj,
+ write_domain == I915_GEM_DOMAIN_GTT ?
+ ORIGIN_GTT : ORIGIN_CPU);
+
unref:
drm_gem_object_unreference(&obj->base);
unlock:
obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
}
+ i915_gem_gtt_finish_object(obj);
+
if (i915_gem_object_needs_bit17_swizzle(obj))
i915_gem_object_save_bit_17_swizzle(obj);
struct sg_page_iter sg_iter;
struct page *page;
unsigned long last_pfn = 0; /* suppress gcc warning */
+ int ret;
gfp_t gfp;
/* Assert that the object is not currently in any GPU domain. As it
*/
i915_gem_shrink_all(dev_priv);
page = shmem_read_mapping_page(mapping, i);
- if (IS_ERR(page))
+ if (IS_ERR(page)) {
+ ret = PTR_ERR(page);
goto err_pages;
+ }
}
#ifdef CONFIG_SWIOTLB
if (swiotlb_nr_tbl()) {
sg_mark_end(sg);
obj->pages = st;
+ ret = i915_gem_gtt_prepare_object(obj);
+ if (ret)
+ goto err_pages;
+
if (i915_gem_object_needs_bit17_swizzle(obj))
i915_gem_object_do_bit_17_swizzle(obj);
* space and so want to translate the error from shmemfs back to our
* usual understanding of ENOMEM.
*/
- if (PTR_ERR(page) == -ENOSPC)
- return -ENOMEM;
- else
- return PTR_ERR(page);
+ if (ret == -ENOSPC)
+ ret = -ENOMEM;
+
+ return ret;
}
/* Ensure that the associated pages are gathered from the backing storage
}
void i915_vma_move_to_active(struct i915_vma *vma,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
struct drm_i915_gem_object *obj = vma->obj;
+ struct intel_engine_cs *ring;
+
+ ring = i915_gem_request_get_ring(req);
/* Add a reference if we're newly entering the active list. */
if (obj->active == 0)
obj->active |= intel_ring_flag(ring);
list_move_tail(&obj->ring_list[ring->id], &ring->active_list);
- i915_gem_request_assign(&obj->last_read_req[ring->id],
- intel_ring_get_request(ring));
+ i915_gem_request_assign(&obj->last_read_req[ring->id], req);
list_move_tail(&vma->mm_list, &vma->vm->active_list);
}
RQ_BUG_ON(!(obj->active & intel_ring_flag(obj->last_write_req->ring)));
i915_gem_request_assign(&obj->last_write_req, NULL);
- intel_fb_obj_flush(obj, true);
+ intel_fb_obj_flush(obj, true, ORIGIN_CS);
}
static void
return 0;
}
-int __i915_add_request(struct intel_engine_cs *ring,
- struct drm_file *file,
- struct drm_i915_gem_object *obj)
+/*
+ * NB: This function is not allowed to fail. Doing so would mean the the
+ * request is not being tracked for completion but the work itself is
+ * going to happen on the hardware. This would be a Bad Thing(tm).
+ */
+void __i915_add_request(struct drm_i915_gem_request *request,
+ struct drm_i915_gem_object *obj,
+ bool flush_caches)
{
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
- struct drm_i915_gem_request *request;
+ struct intel_engine_cs *ring;
+ struct drm_i915_private *dev_priv;
struct intel_ringbuffer *ringbuf;
u32 request_start;
int ret;
- request = ring->outstanding_lazy_request;
if (WARN_ON(request == NULL))
- return -ENOMEM;
+ return;
- if (i915.enable_execlists) {
- ringbuf = request->ctx->engine[ring->id].ringbuf;
- } else
- ringbuf = ring->buffer;
+ ring = request->ring;
+ dev_priv = ring->dev->dev_private;
+ ringbuf = request->ringbuf;
+
+ /*
+ * To ensure that this call will not fail, space for its emissions
+ * should already have been reserved in the ring buffer. Let the ring
+ * know that it is time to use that space up.
+ */
+ intel_ring_reserved_space_use(ringbuf);
request_start = intel_ring_get_tail(ringbuf);
/*
* is that the flush _must_ happen before the next request, no matter
* what.
*/
- if (i915.enable_execlists) {
- ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
- if (ret)
- return ret;
- } else {
- ret = intel_ring_flush_all_caches(ring);
- if (ret)
- return ret;
+ if (flush_caches) {
+ if (i915.enable_execlists)
+ ret = logical_ring_flush_all_caches(request);
+ else
+ ret = intel_ring_flush_all_caches(request);
+ /* Not allowed to fail! */
+ WARN(ret, "*_ring_flush_all_caches failed: %d!\n", ret);
}
/* Record the position of the start of the request so that
*/
request->postfix = intel_ring_get_tail(ringbuf);
- if (i915.enable_execlists) {
- ret = ring->emit_request(ringbuf, request);
- if (ret)
- return ret;
- } else {
- ret = ring->add_request(ring);
- if (ret)
- return ret;
+ if (i915.enable_execlists)
+ ret = ring->emit_request(request);
+ else {
+ ret = ring->add_request(request);
request->tail = intel_ring_get_tail(ringbuf);
}
+ /* Not allowed to fail! */
+ WARN(ret, "emit|add_request failed: %d!\n", ret);
request->head = request_start;
*/
request->batch_obj = obj;
- if (!i915.enable_execlists) {
- /* Hold a reference to the current context so that we can inspect
- * it later in case a hangcheck error event fires.
- */
- request->ctx = ring->last_context;
- if (request->ctx)
- i915_gem_context_reference(request->ctx);
- }
-
request->emitted_jiffies = jiffies;
+ ring->last_submitted_seqno = request->seqno;
list_add_tail(&request->list, &ring->request_list);
- request->file_priv = NULL;
-
- if (file) {
- struct drm_i915_file_private *file_priv = file->driver_priv;
-
- spin_lock(&file_priv->mm.lock);
- request->file_priv = file_priv;
- list_add_tail(&request->client_list,
- &file_priv->mm.request_list);
- spin_unlock(&file_priv->mm.lock);
-
- request->pid = get_pid(task_pid(current));
- }
trace_i915_gem_request_add(request);
- ring->outstanding_lazy_request = NULL;
i915_queue_hangcheck(ring->dev);
round_jiffies_up_relative(HZ));
intel_mark_busy(dev_priv->dev);
- return 0;
+ /* Sanity check that the reserved size was large enough. */
+ intel_ring_reserved_space_end(ringbuf);
}
static bool i915_context_is_banned(struct drm_i915_private *dev_priv,
typeof(*req), ref);
struct intel_context *ctx = req->ctx;
+ if (req->file_priv)
+ i915_gem_request_remove_from_client(req);
+
if (ctx) {
if (i915.enable_execlists) {
- struct intel_engine_cs *ring = req->ring;
-
- if (ctx != ring->default_context)
- intel_lr_context_unpin(ring, ctx);
+ if (ctx != req->ring->default_context)
+ intel_lr_context_unpin(req);
}
i915_gem_context_unreference(ctx);
}
int i915_gem_request_alloc(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out)
{
struct drm_i915_private *dev_priv = to_i915(ring->dev);
struct drm_i915_gem_request *req;
int ret;
- if (ring->outstanding_lazy_request)
- return 0;
+ if (!req_out)
+ return -EINVAL;
+
+ *req_out = NULL;
req = kmem_cache_zalloc(dev_priv->requests, GFP_KERNEL);
if (req == NULL)
return -ENOMEM;
- kref_init(&req->ref);
- req->i915 = dev_priv;
-
ret = i915_gem_get_seqno(ring->dev, &req->seqno);
if (ret)
goto err;
+ kref_init(&req->ref);
+ req->i915 = dev_priv;
req->ring = ring;
+ req->ctx = ctx;
+ i915_gem_context_reference(req->ctx);
if (i915.enable_execlists)
- ret = intel_logical_ring_alloc_request_extras(req, ctx);
+ ret = intel_logical_ring_alloc_request_extras(req);
else
ret = intel_ring_alloc_request_extras(req);
- if (ret)
+ if (ret) {
+ i915_gem_context_unreference(req->ctx);
goto err;
+ }
+
+ /*
+ * Reserve space in the ring buffer for all the commands required to
+ * eventually emit this request. This is to guarantee that the
+ * i915_add_request() call can't fail. Note that the reserve may need
+ * to be redone if the request is not actually submitted straight
+ * away, e.g. because a GPU scheduler has deferred it.
+ */
+ if (i915.enable_execlists)
+ ret = intel_logical_ring_reserve_space(req);
+ else
+ ret = intel_ring_reserve_space(req);
+ if (ret) {
+ /*
+ * At this point, the request is fully allocated even if not
+ * fully prepared. Thus it can be cleaned up using the proper
+ * free code.
+ */
+ i915_gem_request_cancel(req);
+ return ret;
+ }
- ring->outstanding_lazy_request = req;
+ *req_out = req;
return 0;
err:
return ret;
}
+void i915_gem_request_cancel(struct drm_i915_gem_request *req)
+{
+ intel_ring_reserved_space_cancel(req->ringbuf);
+
+ i915_gem_request_unreference(req);
+}
+
struct drm_i915_gem_request *
i915_gem_find_active_request(struct intel_engine_cs *ring)
{
list_del(&submit_req->execlist_link);
if (submit_req->ctx != ring->default_context)
- intel_lr_context_unpin(ring, submit_req->ctx);
+ intel_lr_context_unpin(submit_req);
i915_gem_request_unreference(submit_req);
}
i915_gem_request_retire(request);
}
-
- /* This may not have been flushed before the reset, so clean it now */
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
}
void i915_gem_restore_fences(struct drm_device *dev)
static int
i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
{
- int ret, i;
+ int i;
if (!obj->active)
return 0;
if (list_empty(&req->list))
goto retire;
- ret = i915_gem_check_olr(req);
- if (ret)
- return ret;
-
if (i915_gem_request_completed(req, true)) {
__i915_gem_request_retire__upto(req);
retire:
static int
__i915_gem_object_sync(struct drm_i915_gem_object *obj,
struct intel_engine_cs *to,
- struct drm_i915_gem_request *req)
+ struct drm_i915_gem_request *from_req,
+ struct drm_i915_gem_request **to_req)
{
struct intel_engine_cs *from;
int ret;
- from = i915_gem_request_get_ring(req);
+ from = i915_gem_request_get_ring(from_req);
if (to == from)
return 0;
- if (i915_gem_request_completed(req, true))
+ if (i915_gem_request_completed(from_req, true))
return 0;
- ret = i915_gem_check_olr(req);
- if (ret)
- return ret;
-
if (!i915_semaphore_is_enabled(obj->base.dev)) {
struct drm_i915_private *i915 = to_i915(obj->base.dev);
- ret = __i915_wait_request(req,
+ ret = __i915_wait_request(from_req,
atomic_read(&i915->gpu_error.reset_counter),
i915->mm.interruptible,
NULL,
if (ret)
return ret;
- i915_gem_object_retire_request(obj, req);
+ i915_gem_object_retire_request(obj, from_req);
} else {
int idx = intel_ring_sync_index(from, to);
- u32 seqno = i915_gem_request_get_seqno(req);
+ u32 seqno = i915_gem_request_get_seqno(from_req);
+
+ WARN_ON(!to_req);
if (seqno <= from->semaphore.sync_seqno[idx])
return 0;
- trace_i915_gem_ring_sync_to(from, to, req);
- ret = to->semaphore.sync_to(to, from, seqno);
+ if (*to_req == NULL) {
+ ret = i915_gem_request_alloc(to, to->default_context, to_req);
+ if (ret)
+ return ret;
+ }
+
+ trace_i915_gem_ring_sync_to(*to_req, from, from_req);
+ ret = to->semaphore.sync_to(*to_req, from, seqno);
if (ret)
return ret;
*
* @obj: object which may be in use on another ring.
* @to: ring we wish to use the object on. May be NULL.
+ * @to_req: request we wish to use the object for. See below.
+ * This will be allocated and returned if a request is
+ * required but not passed in.
*
* This code is meant to abstract object synchronization with the GPU.
* Calling with NULL implies synchronizing the object with the CPU
* rather than a particular GPU ring. Conceptually we serialise writes
- * between engines inside the GPU. We only allow on engine to write
+ * between engines inside the GPU. We only allow one engine to write
* into a buffer at any time, but multiple readers. To ensure each has
* a coherent view of memory, we must:
*
* - If we are a write request (pending_write_domain is set), the new
* request must wait for outstanding read requests to complete.
*
+ * For CPU synchronisation (NULL to) no request is required. For syncing with
+ * rings to_req must be non-NULL. However, a request does not have to be
+ * pre-allocated. If *to_req is NULL and sync commands will be emitted then a
+ * request will be allocated automatically and returned through *to_req. Note
+ * that it is not guaranteed that commands will be emitted (because the system
+ * might already be idle). Hence there is no need to create a request that
+ * might never have any work submitted. Note further that if a request is
+ * returned in *to_req, it is the responsibility of the caller to submit
+ * that request (after potentially adding more work to it).
+ *
* Returns 0 if successful, else propagates up the lower layer error.
*/
int
i915_gem_object_sync(struct drm_i915_gem_object *obj,
- struct intel_engine_cs *to)
+ struct intel_engine_cs *to,
+ struct drm_i915_gem_request **to_req)
{
const bool readonly = obj->base.pending_write_domain == 0;
struct drm_i915_gem_request *req[I915_NUM_RINGS];
req[n++] = obj->last_read_req[i];
}
for (i = 0; i < n; i++) {
- ret = __i915_gem_object_sync(obj, to, req[i]);
+ ret = __i915_gem_object_sync(obj, to, req[i], to_req);
if (ret)
return ret;
}
} else if (vma->ggtt_view.pages) {
sg_free_table(vma->ggtt_view.pages);
kfree(vma->ggtt_view.pages);
- vma->ggtt_view.pages = NULL;
}
+ vma->ggtt_view.pages = NULL;
}
drm_mm_remove_node(&vma->node);
/* Since the unbound list is global, only move to that list if
* no more VMAs exist. */
- if (list_empty(&obj->vma_list)) {
- i915_gem_gtt_finish_object(obj);
+ if (list_empty(&obj->vma_list))
list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
- }
/* And finally now the object is completely decoupled from this vma,
* we can drop its hold on the backing storage and allow it to be
/* Flush everything onto the inactive list. */
for_each_ring(ring, dev_priv, i) {
if (!i915.enable_execlists) {
- ret = i915_switch_context(ring, ring->default_context);
+ struct drm_i915_gem_request *req;
+
+ ret = i915_gem_request_alloc(ring, ring->default_context, &req);
if (ret)
return ret;
+
+ ret = i915_switch_context(req);
+ if (ret) {
+ i915_gem_request_cancel(req);
+ return ret;
+ }
+
+ i915_add_request_no_flush(req);
}
ret = intel_ring_idle(ring);
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
u32 size, fence_size, fence_alignment, unfenced_alignment;
- unsigned long start =
+ u64 start =
flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
- unsigned long end =
+ u64 end =
flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total;
struct i915_vma *vma;
int ret;
* attempt to find space.
*/
if (size > end) {
- DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%lu\n",
+ DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%llu\n",
ggtt_view ? ggtt_view->type : 0,
size,
flags & PIN_MAPPABLE ? "mappable" : "total",
goto err_remove_node;
}
- ret = i915_gem_gtt_prepare_object(obj);
- if (ret)
- goto err_remove_node;
-
trace_i915_vma_bind(vma, flags);
ret = i915_vma_bind(vma, obj->cache_level, flags);
if (ret)
- goto err_finish_gtt;
+ goto err_remove_node;
list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
list_add_tail(&vma->mm_list, &vm->inactive_list);
return vma;
- err_finish_gtt:
- i915_gem_gtt_finish_object(obj);
err_remove_node:
drm_mm_remove_node(&vma->node);
err_free_vma:
old_write_domain = obj->base.write_domain;
obj->base.write_domain = 0;
- intel_fb_obj_flush(obj, false);
+ intel_fb_obj_flush(obj, false, ORIGIN_GTT);
trace_i915_gem_object_change_domain(obj,
obj->base.read_domains,
old_write_domain = obj->base.write_domain;
obj->base.write_domain = 0;
- intel_fb_obj_flush(obj, false);
+ intel_fb_obj_flush(obj, false, ORIGIN_CPU);
trace_i915_gem_object_change_domain(obj,
obj->base.read_domains,
obj->dirty = 1;
}
- if (write)
- intel_fb_obj_invalidate(obj, NULL, ORIGIN_GTT);
-
trace_i915_gem_object_change_domain(obj,
old_read_domains,
old_write_domain);
i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
u32 alignment,
struct intel_engine_cs *pipelined,
+ struct drm_i915_gem_request **pipelined_request,
const struct i915_ggtt_view *view)
{
u32 old_read_domains, old_write_domain;
int ret;
- ret = i915_gem_object_sync(obj, pipelined);
+ ret = i915_gem_object_sync(obj, pipelined, pipelined_request);
if (ret)
return ret;
obj->base.write_domain = I915_GEM_DOMAIN_CPU;
}
- if (write)
- intel_fb_obj_invalidate(obj, NULL, ORIGIN_CPU);
-
trace_i915_gem_object_change_domain(obj,
old_read_domains,
old_write_domain);
if (time_after_eq(request->emitted_jiffies, recent_enough))
break;
+ /*
+ * Note that the request might not have been submitted yet.
+ * In which case emitted_jiffies will be zero.
+ */
+ if (!request->emitted_jiffies)
+ continue;
+
target = request;
}
reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
return ret;
}
-int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
if (!HAS_L3_DPF(dev) || !remap_info)
return 0;
- ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
+ ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
if (ret)
return ret;
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring;
- int ret, i;
+ int ret, i, j;
if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
return -EIO;
*/
init_unused_rings(dev);
+ BUG_ON(!dev_priv->ring[RCS].default_context);
+
+ ret = i915_ppgtt_init_hw(dev);
+ if (ret) {
+ DRM_ERROR("PPGTT enable HW failed %d\n", ret);
+ goto out;
+ }
+
+ /* Need to do basic initialisation of all rings first: */
for_each_ring(ring, dev_priv, i) {
ret = ring->init_hw(ring);
if (ret)
goto out;
}
- for (i = 0; i < NUM_L3_SLICES(dev); i++)
- i915_gem_l3_remap(&dev_priv->ring[RCS], i);
+ /* Now it is safe to go back round and do everything else: */
+ for_each_ring(ring, dev_priv, i) {
+ struct drm_i915_gem_request *req;
- ret = i915_ppgtt_init_hw(dev);
- if (ret && ret != -EIO) {
- DRM_ERROR("PPGTT enable failed %d\n", ret);
- i915_gem_cleanup_ringbuffer(dev);
- }
+ WARN_ON(!ring->default_context);
- ret = i915_gem_context_enable(dev_priv);
- if (ret && ret != -EIO) {
- DRM_ERROR("Context enable failed %d\n", ret);
- i915_gem_cleanup_ringbuffer(dev);
+ ret = i915_gem_request_alloc(ring, ring->default_context, &req);
+ if (ret) {
+ i915_gem_cleanup_ringbuffer(dev);
+ goto out;
+ }
- goto out;
+ if (ring->id == RCS) {
+ for (j = 0; j < NUM_L3_SLICES(dev); j++)
+ i915_gem_l3_remap(req, j);
+ }
+
+ ret = i915_ppgtt_init_ring(req);
+ if (ret && ret != -EIO) {
+ DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
+ i915_gem_request_cancel(req);
+ i915_gem_cleanup_ringbuffer(dev);
+ goto out;
+ }
+
+ ret = i915_gem_context_enable(req);
+ if (ret && ret != -EIO) {
+ DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
+ i915_gem_request_cancel(req);
+ i915_gem_cleanup_ringbuffer(dev);
+ goto out;
+ }
+
+ i915_add_request_no_flush(req);
}
out:
for_each_ring(ring, dev_priv, i)
dev_priv->gt.cleanup_ring(ring);
+
+ if (i915.enable_execlists)
+ /*
+ * Neither the BIOS, ourselves or any other kernel
+ * expects the system to be in execlists mode on startup,
+ * so we need to reset the GPU back to legacy mode.
+ */
+ intel_gpu_reset(dev);
}
static void
return false;
}
-
void i915_gem_context_free(struct kref *ctx_ref)
{
- struct intel_context *ctx = container_of(ctx_ref,
- typeof(*ctx), ref);
+ struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
trace_i915_context_free(ctx);
struct drm_i915_gem_object *obj;
int ret;
- obj = i915_gem_object_create_stolen(dev, size);
- if (obj == NULL)
- obj = i915_gem_alloc_object(dev, size);
+ obj = i915_gem_alloc_object(dev, size);
if (obj == NULL)
return ERR_PTR(-ENOMEM);
kref_init(&ctx->ref);
list_add_tail(&ctx->link, &dev_priv->context_list);
+ ctx->i915 = dev_priv;
if (dev_priv->hw_context_size) {
struct drm_i915_gem_object *obj =
i915_gem_context_unreference(dctx);
}
-int i915_gem_context_enable(struct drm_i915_private *dev_priv)
+int i915_gem_context_enable(struct drm_i915_gem_request *req)
{
- struct intel_engine_cs *ring;
- int ret, i;
-
- BUG_ON(!dev_priv->ring[RCS].default_context);
+ struct intel_engine_cs *ring = req->ring;
+ int ret;
if (i915.enable_execlists) {
- for_each_ring(ring, dev_priv, i) {
- if (ring->init_context) {
- ret = ring->init_context(ring,
- ring->default_context);
- if (ret) {
- DRM_ERROR("ring init context: %d\n",
- ret);
- return ret;
- }
- }
- }
+ if (ring->init_context == NULL)
+ return 0;
+ ret = ring->init_context(req);
} else
- for_each_ring(ring, dev_priv, i) {
- ret = i915_switch_context(ring, ring->default_context);
- if (ret)
- return ret;
- }
+ ret = i915_switch_context(req);
+
+ if (ret) {
+ DRM_ERROR("ring init context: %d\n", ret);
+ return ret;
+ }
return 0;
}
}
static inline int
-mi_set_context(struct intel_engine_cs *ring,
- struct intel_context *new_context,
- u32 hw_flags)
+mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = hw_flags | MI_MM_SPACE_GTT;
const int num_rings =
/* Use an extended w/a on ivb+ if signalling from other rings */
* itlb_before_ctx_switch.
*/
if (IS_GEN6(ring->dev)) {
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, 0);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, 0);
if (ret)
return ret;
}
/* These flags are for resource streamer on HSW+ */
- if (!IS_HASWELL(ring->dev) && INTEL_INFO(ring->dev)->gen < 8)
+ if (IS_HASWELL(ring->dev) || INTEL_INFO(ring->dev)->gen >= 8)
+ flags |= (HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN);
+ else if (INTEL_INFO(ring->dev)->gen < 8)
flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
if (INTEL_INFO(ring->dev)->gen >= 7)
len += 2 + (num_rings ? 4*num_rings + 2 : 0);
- ret = intel_ring_begin(ring, len);
+ ret = intel_ring_begin(req, len);
if (ret)
return ret;
intel_ring_emit(ring, MI_NOOP);
intel_ring_emit(ring, MI_SET_CONTEXT);
- intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->legacy_hw_ctx.rcs_state) |
+ intel_ring_emit(ring, i915_gem_obj_ggtt_offset(req->ctx->legacy_hw_ctx.rcs_state) |
flags);
/*
* w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
return false;
}
-static int do_switch(struct intel_engine_cs *ring,
- struct intel_context *to)
+static int do_switch(struct drm_i915_gem_request *req)
{
+ struct intel_context *to = req->ctx;
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
struct intel_context *from = ring->last_context;
u32 hw_flags = 0;
* Register Immediate commands in Ring Buffer before submitting
* a context."*/
trace_switch_mm(ring, to);
- ret = to->ppgtt->switch_mm(to->ppgtt, ring);
+ ret = to->ppgtt->switch_mm(to->ppgtt, req);
if (ret)
goto unpin_out;
WARN_ON(needs_pd_load_pre(ring, to) &&
needs_pd_load_post(ring, to, hw_flags));
- ret = mi_set_context(ring, to, hw_flags);
+ ret = mi_set_context(req, hw_flags);
if (ret)
goto unpin_out;
*/
if (needs_pd_load_post(ring, to, hw_flags)) {
trace_switch_mm(ring, to);
- ret = to->ppgtt->switch_mm(to->ppgtt, ring);
+ ret = to->ppgtt->switch_mm(to->ppgtt, req);
/* The hardware context switch is emitted, but we haven't
* actually changed the state - so it's probably safe to bail
* here. Still, let the user know something dangerous has
if (!(to->remap_slice & (1<<i)))
continue;
- ret = i915_gem_l3_remap(ring, i);
+ ret = i915_gem_l3_remap(req, i);
/* If it failed, try again next round */
if (ret)
DRM_DEBUG_DRIVER("L3 remapping failed\n");
*/
if (from != NULL) {
from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req);
/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
* whole damn pipeline, we don't need to explicitly mark the
* object dirty. The only exception is that the context must be
if (uninitialized) {
if (ring->init_context) {
- ret = ring->init_context(ring, to);
+ ret = ring->init_context(req);
if (ret)
DRM_ERROR("ring init context: %d\n", ret);
}
/**
* i915_switch_context() - perform a GPU context switch.
- * @ring: ring for which we'll execute the context switch
- * @to: the context to switch to
+ * @req: request for which we'll execute the context switch
*
* The context life cycle is simple. The context refcount is incremented and
* decremented by 1 and create and destroy. If the context is in use by the GPU,
* switched by writing to the ELSP and requests keep a reference to their
* context.
*/
-int i915_switch_context(struct intel_engine_cs *ring,
- struct intel_context *to)
+int i915_switch_context(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
WARN_ON(i915.enable_execlists);
WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
- if (to->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
- if (to != ring->last_context) {
- i915_gem_context_reference(to);
+ if (req->ctx->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
+ if (req->ctx != ring->last_context) {
+ i915_gem_context_reference(req->ctx);
if (ring->last_context)
i915_gem_context_unreference(ring->last_context);
- ring->last_context = to;
+ ring->last_context = req->ctx;
}
return 0;
}
- return do_switch(ring, to);
+ return do_switch(req);
}
static bool contexts_enabled(struct drm_device *dev)
case I915_CONTEXT_PARAM_BAN_PERIOD:
args->value = ctx->hang_stats.ban_period_seconds;
break;
+ case I915_CONTEXT_PARAM_NO_ZEROMAP:
+ args->value = ctx->flags & CONTEXT_NO_ZEROMAP;
+ break;
default:
ret = -EINVAL;
break;
else
ctx->hang_stats.ban_period_seconds = args->value;
break;
+ case I915_CONTEXT_PARAM_NO_ZEROMAP:
+ if (args->size) {
+ ret = -EINVAL;
+ } else {
+ ctx->flags &= ~CONTEXT_NO_ZEROMAP;
+ ctx->flags |= args->value ? CONTEXT_NO_ZEROMAP : 0;
+ }
+ break;
default:
ret = -EINVAL;
break;
#include "i915_trace.h"
#include "intel_drv.h"
#include <linux/dma_remapping.h>
+ #include <linux/uaccess.h>
#define __EXEC_OBJECT_HAS_PIN (1<<31)
#define __EXEC_OBJECT_HAS_FENCE (1<<30)
}
/* We can't wait for rendering with pagefaults disabled */
- if (obj->active && in_atomic())
+ if (obj->active && pagefault_disabled())
return -EFAULT;
if (use_cpu_reloc(obj))
static int
i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
struct list_head *vmas,
+ struct intel_context *ctx,
bool *need_relocs)
{
struct drm_i915_gem_object *obj;
obj = vma->obj;
entry = vma->exec_entry;
+ if (ctx->flags & CONTEXT_NO_ZEROMAP)
+ entry->flags |= __EXEC_OBJECT_NEEDS_BIAS;
+
if (!has_fenced_gpu_access)
entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
need_fence =
struct drm_file *file,
struct intel_engine_cs *ring,
struct eb_vmas *eb,
- struct drm_i915_gem_exec_object2 *exec)
+ struct drm_i915_gem_exec_object2 *exec,
+ struct intel_context *ctx)
{
struct drm_i915_gem_relocation_entry *reloc;
struct i915_address_space *vm;
goto err;
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
- ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
+ ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, ctx, &need_relocs);
if (ret)
goto err;
}
static int
-i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
+i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
struct list_head *vmas)
{
- const unsigned other_rings = ~intel_ring_flag(ring);
+ const unsigned other_rings = ~intel_ring_flag(req->ring);
struct i915_vma *vma;
uint32_t flush_domains = 0;
bool flush_chipset = false;
struct drm_i915_gem_object *obj = vma->obj;
if (obj->active & other_rings) {
- ret = i915_gem_object_sync(obj, ring);
+ ret = i915_gem_object_sync(obj, req->ring, &req);
if (ret)
return ret;
}
}
if (flush_chipset)
- i915_gem_chipset_flush(ring->dev);
+ i915_gem_chipset_flush(req->ring->dev);
if (flush_domains & I915_GEM_DOMAIN_GTT)
wmb();
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
*/
- return intel_ring_invalidate_all_caches(ring);
+ return intel_ring_invalidate_all_caches(req);
}
static bool
if (exec[i].flags & invalid_flags)
return -EINVAL;
+ if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
+ return -EINVAL;
+
/* First check for malicious input causing overflow in
* the worst case where we need to allocate the entire
* relocation tree as a single array.
void
i915_gem_execbuffer_move_to_active(struct list_head *vmas,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
- struct drm_i915_gem_request *req = intel_ring_get_request(ring);
+ struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
struct i915_vma *vma;
list_for_each_entry(vma, vmas, exec_list) {
obj->base.pending_read_domains |= obj->base.read_domains;
obj->base.read_domains = obj->base.pending_read_domains;
- i915_vma_move_to_active(vma, ring);
+ i915_vma_move_to_active(vma, req);
if (obj->base.write_domain) {
obj->dirty = 1;
i915_gem_request_assign(&obj->last_write_req, req);
- intel_fb_obj_invalidate(obj, ring, ORIGIN_CS);
+ intel_fb_obj_invalidate(obj, ORIGIN_CS);
/* update for the implicit flush after a batch */
obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
}
void
-i915_gem_execbuffer_retire_commands(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct drm_i915_gem_object *obj)
+i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
{
/* Unconditionally force add_request to emit a full flush. */
- ring->gpu_caches_dirty = true;
+ params->ring->gpu_caches_dirty = true;
/* Add a breadcrumb for the completion of the batch buffer */
- (void)__i915_add_request(ring, file, obj);
+ __i915_add_request(params->request, params->batch_obj, true);
}
static int
i915_reset_gen7_sol_offsets(struct drm_device *dev,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
int ret, i;
return -EINVAL;
}
- ret = intel_ring_begin(ring, 4 * 3);
+ ret = intel_ring_begin(req, 4 * 3);
if (ret)
return ret;
}
static int
-i915_emit_box(struct intel_engine_cs *ring,
+i915_emit_box(struct drm_i915_gem_request *req,
struct drm_clip_rect *box,
int DR1, int DR4)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (box->y2 <= box->y1 || box->x2 <= box->x1 ||
}
if (INTEL_INFO(ring->dev)->gen >= 4) {
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
intel_ring_emit(ring, DR4);
} else {
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
}
int
-i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags)
+ struct list_head *vmas)
{
struct drm_clip_rect *cliprects = NULL;
+ struct drm_device *dev = params->dev;
+ struct intel_engine_cs *ring = params->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
- u64 exec_len;
+ u64 exec_start, exec_len;
int instp_mode;
u32 instp_mask;
int i, ret = 0;
}
}
- ret = i915_gem_execbuffer_move_to_gpu(ring, vmas);
+ ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
if (ret)
goto error;
- ret = i915_switch_context(ring, ctx);
+ ret = i915_switch_context(params->request);
if (ret)
goto error;
- WARN(ctx->ppgtt && ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
+ WARN(params->ctx->ppgtt && params->ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
"%s didn't clear reload\n", ring->name);
instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
if (ring == &dev_priv->ring[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(params->request, 4);
if (ret)
goto error;
}
if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
- ret = i915_reset_gen7_sol_offsets(dev, ring);
+ ret = i915_reset_gen7_sol_offsets(dev, params->request);
if (ret)
goto error;
}
- exec_len = args->batch_len;
+ exec_len = args->batch_len;
+ exec_start = params->batch_obj_vm_offset +
+ params->args_batch_start_offset;
+
if (cliprects) {
for (i = 0; i < args->num_cliprects; i++) {
- ret = i915_emit_box(ring, &cliprects[i],
+ ret = i915_emit_box(params->request, &cliprects[i],
args->DR1, args->DR4);
if (ret)
goto error;
- ret = ring->dispatch_execbuffer(ring,
+ ret = ring->dispatch_execbuffer(params->request,
exec_start, exec_len,
- dispatch_flags);
+ params->dispatch_flags);
if (ret)
goto error;
}
} else {
- ret = ring->dispatch_execbuffer(ring,
+ ret = ring->dispatch_execbuffer(params->request,
exec_start, exec_len,
- dispatch_flags);
+ params->dispatch_flags);
if (ret)
return ret;
}
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+ trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
- i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+ i915_gem_execbuffer_move_to_active(vmas, params->request);
+ i915_gem_execbuffer_retire_commands(params);
error:
kfree(cliprects);
struct intel_engine_cs *ring;
struct intel_context *ctx;
struct i915_address_space *vm;
+ struct i915_execbuffer_params params_master; /* XXX: will be removed later */
+ struct i915_execbuffer_params *params = ¶ms_master;
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
- u64 exec_start = args->batch_start_offset;
u32 dispatch_flags;
int ret;
bool need_relocs;
return -EINVAL;
}
+ if (args->flags & I915_EXEC_RESOURCE_STREAMER) {
+ if (!HAS_RESOURCE_STREAMER(dev)) {
+ DRM_DEBUG("RS is only allowed for Haswell, Gen8 and above\n");
+ return -EINVAL;
+ }
+ if (ring->id != RCS) {
+ DRM_DEBUG("RS is not available on %s\n",
+ ring->name);
+ return -EINVAL;
+ }
+
+ dispatch_flags |= I915_DISPATCH_RS;
+ }
+
intel_runtime_pm_get(dev_priv);
ret = i915_mutex_lock_interruptible(dev);
else
vm = &dev_priv->gtt.base;
+ memset(¶ms_master, 0x00, sizeof(params_master));
+
eb = eb_create(args);
if (eb == NULL) {
i915_gem_context_unreference(ctx);
/* Move the objects en-masse into the GTT, evicting if necessary. */
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
- ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
+ ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, ctx, &need_relocs);
if (ret)
goto err;
if (ret) {
if (ret == -EFAULT) {
ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
- eb, exec);
+ eb, exec, ctx);
BUG_ON(!mutex_is_locked(&dev->struct_mutex));
}
if (ret)
goto err;
}
+ params->args_batch_start_offset = args->batch_start_offset;
if (i915_needs_cmd_parser(ring) && args->batch_len) {
struct drm_i915_gem_object *parsed_batch_obj;
* command parser has accepted.
*/
dispatch_flags |= I915_DISPATCH_SECURE;
- exec_start = 0;
+ params->args_batch_start_offset = 0;
batch_obj = parsed_batch_obj;
}
}
if (ret)
goto err;
- exec_start += i915_gem_obj_ggtt_offset(batch_obj);
+ params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
} else
- exec_start += i915_gem_obj_offset(batch_obj, vm);
+ params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
- ret = dev_priv->gt.execbuf_submit(dev, file, ring, ctx, args,
- &eb->vmas, batch_obj, exec_start,
- dispatch_flags);
+ /* Allocate a request for this batch buffer nice and early. */
+ ret = i915_gem_request_alloc(ring, ctx, ¶ms->request);
+ if (ret)
+ goto err_batch_unpin;
+
+ ret = i915_gem_request_add_to_client(params->request, file);
+ if (ret)
+ goto err_batch_unpin;
+ /*
+ * Save assorted stuff away to pass through to *_submission().
+ * NB: This data should be 'persistent' and not local as it will
+ * kept around beyond the duration of the IOCTL once the GPU
+ * scheduler arrives.
+ */
+ params->dev = dev;
+ params->file = file;
+ params->ring = ring;
+ params->dispatch_flags = dispatch_flags;
+ params->batch_obj = batch_obj;
+ params->ctx = ctx;
+
+ ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
+
+err_batch_unpin:
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
* batch vma for correctness. For less ugly and less fragility this
*/
if (dispatch_flags & I915_DISPATCH_SECURE)
i915_gem_object_ggtt_unpin(batch_obj);
+
err:
/* the request owns the ref now */
i915_gem_context_unreference(ctx);
eb_destroy(eb);
+ /*
+ * If the request was created but not successfully submitted then it
+ * must be freed again. If it was submitted then it is being tracked
+ * on the active request list and no clean up is required here.
+ */
+ if (ret && params->request)
+ i915_gem_request_cancel(params->request);
+
mutex_unlock(&dev->struct_mutex);
pre_mutex_err:
return pte;
}
-static gen8_pde_t gen8_pde_encode(struct drm_device *dev,
- dma_addr_t addr,
- enum i915_cache_level level)
+static gen8_pde_t gen8_pde_encode(const dma_addr_t addr,
+ const enum i915_cache_level level)
{
gen8_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
pde |= addr;
return pte;
}
-#define i915_dma_unmap_single(px, dev) \
- __i915_dma_unmap_single((px)->daddr, dev)
-
-static void __i915_dma_unmap_single(dma_addr_t daddr,
- struct drm_device *dev)
+static int __setup_page_dma(struct drm_device *dev,
+ struct i915_page_dma *p, gfp_t flags)
{
struct device *device = &dev->pdev->dev;
- dma_unmap_page(device, daddr, 4096, PCI_DMA_BIDIRECTIONAL);
+ p->page = alloc_page(flags);
+ if (!p->page)
+ return -ENOMEM;
+
+ p->daddr = dma_map_page(device,
+ p->page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
+
+ if (dma_mapping_error(device, p->daddr)) {
+ __free_page(p->page);
+ return -EINVAL;
+ }
+
+ return 0;
}
-/**
- * i915_dma_map_single() - Create a dma mapping for a page table/dir/etc.
- * @px: Page table/dir/etc to get a DMA map for
- * @dev: drm device
- *
- * Page table allocations are unified across all gens. They always require a
- * single 4k allocation, as well as a DMA mapping. If we keep the structs
- * symmetric here, the simple macro covers us for every page table type.
- *
- * Return: 0 if success.
- */
-#define i915_dma_map_single(px, dev) \
- i915_dma_map_page_single((px)->page, (dev), &(px)->daddr)
+static int setup_page_dma(struct drm_device *dev, struct i915_page_dma *p)
+{
+ return __setup_page_dma(dev, p, GFP_KERNEL);
+}
-static int i915_dma_map_page_single(struct page *page,
- struct drm_device *dev,
- dma_addr_t *daddr)
+static void cleanup_page_dma(struct drm_device *dev, struct i915_page_dma *p)
{
- struct device *device = &dev->pdev->dev;
+ if (WARN_ON(!p->page))
+ return;
- *daddr = dma_map_page(device, page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
- if (dma_mapping_error(device, *daddr))
- return -ENOMEM;
+ dma_unmap_page(&dev->pdev->dev, p->daddr, 4096, PCI_DMA_BIDIRECTIONAL);
+ __free_page(p->page);
+ memset(p, 0, sizeof(*p));
+}
- return 0;
+static void *kmap_page_dma(struct i915_page_dma *p)
+{
+ return kmap_atomic(p->page);
}
-static void unmap_and_free_pt(struct i915_page_table *pt,
- struct drm_device *dev)
+/* We use the flushing unmap only with ppgtt structures:
+ * page directories, page tables and scratch pages.
+ */
+static void kunmap_page_dma(struct drm_device *dev, void *vaddr)
{
- if (WARN_ON(!pt->page))
- return;
+ /* There are only few exceptions for gen >=6. chv and bxt.
+ * And we are not sure about the latter so play safe for now.
+ */
+ if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
- i915_dma_unmap_single(pt, dev);
- __free_page(pt->page);
- kfree(pt->used_ptes);
- kfree(pt);
+ kunmap_atomic(vaddr);
}
-static void gen8_initialize_pt(struct i915_address_space *vm,
- struct i915_page_table *pt)
+#define kmap_px(px) kmap_page_dma(px_base(px))
+#define kunmap_px(ppgtt, vaddr) kunmap_page_dma((ppgtt)->base.dev, (vaddr))
+
+#define setup_px(dev, px) setup_page_dma((dev), px_base(px))
+#define cleanup_px(dev, px) cleanup_page_dma((dev), px_base(px))
+#define fill_px(dev, px, v) fill_page_dma((dev), px_base(px), (v))
+#define fill32_px(dev, px, v) fill_page_dma_32((dev), px_base(px), (v))
+
+static void fill_page_dma(struct drm_device *dev, struct i915_page_dma *p,
+ const uint64_t val)
{
- gen8_pte_t *pt_vaddr, scratch_pte;
int i;
+ uint64_t * const vaddr = kmap_page_dma(p);
- pt_vaddr = kmap_atomic(pt->page);
- scratch_pte = gen8_pte_encode(vm->scratch.addr,
- I915_CACHE_LLC, true);
+ for (i = 0; i < 512; i++)
+ vaddr[i] = val;
+
+ kunmap_page_dma(dev, vaddr);
+}
+
+static void fill_page_dma_32(struct drm_device *dev, struct i915_page_dma *p,
+ const uint32_t val32)
+{
+ uint64_t v = val32;
- for (i = 0; i < GEN8_PTES; i++)
- pt_vaddr[i] = scratch_pte;
+ v = v << 32 | val32;
- if (!HAS_LLC(vm->dev))
- drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
- kunmap_atomic(pt_vaddr);
+ fill_page_dma(dev, p, v);
}
-static struct i915_page_table *alloc_pt_single(struct drm_device *dev)
+static struct i915_page_scratch *alloc_scratch_page(struct drm_device *dev)
+{
+ struct i915_page_scratch *sp;
+ int ret;
+
+ sp = kzalloc(sizeof(*sp), GFP_KERNEL);
+ if (sp == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ ret = __setup_page_dma(dev, px_base(sp), GFP_DMA32 | __GFP_ZERO);
+ if (ret) {
+ kfree(sp);
+ return ERR_PTR(ret);
+ }
+
+ set_pages_uc(px_page(sp), 1);
+
+ return sp;
+}
+
+static void free_scratch_page(struct drm_device *dev,
+ struct i915_page_scratch *sp)
+{
+ set_pages_wb(px_page(sp), 1);
+
+ cleanup_px(dev, sp);
+ kfree(sp);
+}
+
+static struct i915_page_table *alloc_pt(struct drm_device *dev)
{
struct i915_page_table *pt;
const size_t count = INTEL_INFO(dev)->gen >= 8 ?
if (!pt->used_ptes)
goto fail_bitmap;
- pt->page = alloc_page(GFP_KERNEL);
- if (!pt->page)
- goto fail_page;
-
- ret = i915_dma_map_single(pt, dev);
+ ret = setup_px(dev, pt);
if (ret)
- goto fail_dma;
+ goto fail_page_m;
return pt;
-fail_dma:
- __free_page(pt->page);
-fail_page:
+fail_page_m:
kfree(pt->used_ptes);
fail_bitmap:
kfree(pt);
return ERR_PTR(ret);
}
-static void unmap_and_free_pd(struct i915_page_directory *pd,
- struct drm_device *dev)
+static void free_pt(struct drm_device *dev, struct i915_page_table *pt)
{
- if (pd->page) {
- i915_dma_unmap_single(pd, dev);
- __free_page(pd->page);
- kfree(pd->used_pdes);
- kfree(pd);
- }
+ cleanup_px(dev, pt);
+ kfree(pt->used_ptes);
+ kfree(pt);
}
-static struct i915_page_directory *alloc_pd_single(struct drm_device *dev)
+static void gen8_initialize_pt(struct i915_address_space *vm,
+ struct i915_page_table *pt)
+{
+ gen8_pte_t scratch_pte;
+
+ scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, true);
+
+ fill_px(vm->dev, pt, scratch_pte);
+}
+
+static void gen6_initialize_pt(struct i915_address_space *vm,
+ struct i915_page_table *pt)
+{
+ gen6_pte_t scratch_pte;
+
+ WARN_ON(px_dma(vm->scratch_page) == 0);
+
+ scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, true, 0);
+
+ fill32_px(vm->dev, pt, scratch_pte);
+}
+
+static struct i915_page_directory *alloc_pd(struct drm_device *dev)
{
struct i915_page_directory *pd;
int ret = -ENOMEM;
pd->used_pdes = kcalloc(BITS_TO_LONGS(I915_PDES),
sizeof(*pd->used_pdes), GFP_KERNEL);
if (!pd->used_pdes)
- goto free_pd;
-
- pd->page = alloc_page(GFP_KERNEL);
- if (!pd->page)
- goto free_bitmap;
+ goto fail_bitmap;
- ret = i915_dma_map_single(pd, dev);
+ ret = setup_px(dev, pd);
if (ret)
- goto free_page;
+ goto fail_page_m;
return pd;
-free_page:
- __free_page(pd->page);
-free_bitmap:
+fail_page_m:
kfree(pd->used_pdes);
-free_pd:
+fail_bitmap:
kfree(pd);
return ERR_PTR(ret);
}
+static void free_pd(struct drm_device *dev, struct i915_page_directory *pd)
+{
+ if (px_page(pd)) {
+ cleanup_px(dev, pd);
+ kfree(pd->used_pdes);
+ kfree(pd);
+ }
+}
+
+static void gen8_initialize_pd(struct i915_address_space *vm,
+ struct i915_page_directory *pd)
+{
+ gen8_pde_t scratch_pde;
+
+ scratch_pde = gen8_pde_encode(px_dma(vm->scratch_pt), I915_CACHE_LLC);
+
+ fill_px(vm->dev, pd, scratch_pde);
+}
+
/* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct intel_engine_cs *ring,
+static int gen8_write_pdp(struct drm_i915_gem_request *req,
unsigned entry,
dma_addr_t addr)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
BUG_ON(entry >= 4);
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
}
static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
int i, ret;
for (i = GEN8_LEGACY_PDPES - 1; i >= 0; i--) {
- struct i915_page_directory *pd = ppgtt->pdp.page_directory[i];
- dma_addr_t pd_daddr = pd ? pd->daddr : ppgtt->scratch_pd->daddr;
- /* The page directory might be NULL, but we need to clear out
- * whatever the previous context might have used. */
- ret = gen8_write_pdp(ring, i, pd_daddr);
+ const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
+
+ ret = gen8_write_pdp(req, i, pd_daddr);
if (ret)
return ret;
}
unsigned num_entries = length >> PAGE_SHIFT;
unsigned last_pte, i;
- scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr,
+ scratch_pte = gen8_pte_encode(px_dma(ppgtt->base.scratch_page),
I915_CACHE_LLC, use_scratch);
while (num_entries) {
struct i915_page_directory *pd;
struct i915_page_table *pt;
- struct page *page_table;
if (WARN_ON(!ppgtt->pdp.page_directory[pdpe]))
- continue;
+ break;
pd = ppgtt->pdp.page_directory[pdpe];
if (WARN_ON(!pd->page_table[pde]))
- continue;
+ break;
pt = pd->page_table[pde];
- if (WARN_ON(!pt->page))
+ if (WARN_ON(!px_page(pt)))
- continue;
+ break;
- page_table = pt->page;
-
last_pte = pte + num_entries;
if (last_pte > GEN8_PTES)
last_pte = GEN8_PTES;
- pt_vaddr = kmap_atomic(page_table);
+ pt_vaddr = kmap_px(pt);
for (i = pte; i < last_pte; i++) {
pt_vaddr[i] = scratch_pte;
num_entries--;
}
- if (!HAS_LLC(ppgtt->base.dev))
- drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
- kunmap_atomic(pt_vaddr);
+ kunmap_px(ppgtt, pt);
pte = 0;
if (++pde == I915_PDES) {
if (pt_vaddr == NULL) {
struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe];
struct i915_page_table *pt = pd->page_table[pde];
- struct page *page_table = pt->page;
-
- pt_vaddr = kmap_atomic(page_table);
+ pt_vaddr = kmap_px(pt);
}
pt_vaddr[pte] =
gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
cache_level, true);
if (++pte == GEN8_PTES) {
- if (!HAS_LLC(ppgtt->base.dev))
- drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
- kunmap_atomic(pt_vaddr);
+ kunmap_px(ppgtt, pt_vaddr);
pt_vaddr = NULL;
if (++pde == I915_PDES) {
pdpe++;
pte = 0;
}
}
- if (pt_vaddr) {
- if (!HAS_LLC(ppgtt->base.dev))
- drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
- kunmap_atomic(pt_vaddr);
- }
-}
-
-static void __gen8_do_map_pt(gen8_pde_t * const pde,
- struct i915_page_table *pt,
- struct drm_device *dev)
-{
- gen8_pde_t entry =
- gen8_pde_encode(dev, pt->daddr, I915_CACHE_LLC);
- *pde = entry;
-}
-static void gen8_initialize_pd(struct i915_address_space *vm,
- struct i915_page_directory *pd)
-{
- struct i915_hw_ppgtt *ppgtt =
- container_of(vm, struct i915_hw_ppgtt, base);
- gen8_pde_t *page_directory;
- struct i915_page_table *pt;
- int i;
-
- page_directory = kmap_atomic(pd->page);
- pt = ppgtt->scratch_pt;
- for (i = 0; i < I915_PDES; i++)
- /* Map the PDE to the page table */
- __gen8_do_map_pt(page_directory + i, pt, vm->dev);
-
- if (!HAS_LLC(vm->dev))
- drm_clflush_virt_range(page_directory, PAGE_SIZE);
- kunmap_atomic(page_directory);
+ if (pt_vaddr)
+ kunmap_px(ppgtt, pt_vaddr);
}
-static void gen8_free_page_tables(struct i915_page_directory *pd, struct drm_device *dev)
+static void gen8_free_page_tables(struct drm_device *dev,
+ struct i915_page_directory *pd)
{
int i;
- if (!pd->page)
+ if (!px_page(pd))
return;
for_each_set_bit(i, pd->used_pdes, I915_PDES) {
if (WARN_ON(!pd->page_table[i]))
continue;
- unmap_and_free_pt(pd->page_table[i], dev);
+ free_pt(dev, pd->page_table[i]);
pd->page_table[i] = NULL;
}
}
+static int gen8_init_scratch(struct i915_address_space *vm)
+{
+ struct drm_device *dev = vm->dev;
+
+ vm->scratch_page = alloc_scratch_page(dev);
+ if (IS_ERR(vm->scratch_page))
+ return PTR_ERR(vm->scratch_page);
+
+ vm->scratch_pt = alloc_pt(dev);
+ if (IS_ERR(vm->scratch_pt)) {
+ free_scratch_page(dev, vm->scratch_page);
+ return PTR_ERR(vm->scratch_pt);
+ }
+
+ vm->scratch_pd = alloc_pd(dev);
+ if (IS_ERR(vm->scratch_pd)) {
+ free_pt(dev, vm->scratch_pt);
+ free_scratch_page(dev, vm->scratch_page);
+ return PTR_ERR(vm->scratch_pd);
+ }
+
+ gen8_initialize_pt(vm, vm->scratch_pt);
+ gen8_initialize_pd(vm, vm->scratch_pd);
+
+ return 0;
+}
+
+static void gen8_free_scratch(struct i915_address_space *vm)
+{
+ struct drm_device *dev = vm->dev;
+
+ free_pd(dev, vm->scratch_pd);
+ free_pt(dev, vm->scratch_pt);
+ free_scratch_page(dev, vm->scratch_page);
+}
+
static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
{
struct i915_hw_ppgtt *ppgtt =
if (WARN_ON(!ppgtt->pdp.page_directory[i]))
continue;
- gen8_free_page_tables(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
- unmap_and_free_pd(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
+ gen8_free_page_tables(ppgtt->base.dev,
+ ppgtt->pdp.page_directory[i]);
+ free_pd(ppgtt->base.dev, ppgtt->pdp.page_directory[i]);
}
- unmap_and_free_pd(ppgtt->scratch_pd, ppgtt->base.dev);
- unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
+ gen8_free_scratch(vm);
}
/**
/* Don't reallocate page tables */
if (pt) {
/* Scratch is never allocated this way */
- WARN_ON(pt == ppgtt->scratch_pt);
+ WARN_ON(pt == ppgtt->base.scratch_pt);
continue;
}
- pt = alloc_pt_single(dev);
+ pt = alloc_pt(dev);
if (IS_ERR(pt))
goto unwind_out;
gen8_initialize_pt(&ppgtt->base, pt);
pd->page_table[pde] = pt;
- set_bit(pde, new_pts);
+ __set_bit(pde, new_pts);
}
return 0;
unwind_out:
for_each_set_bit(pde, new_pts, I915_PDES)
- unmap_and_free_pt(pd->page_table[pde], dev);
+ free_pt(dev, pd->page_table[pde]);
return -ENOMEM;
}
WARN_ON(!bitmap_empty(new_pds, GEN8_LEGACY_PDPES));
- /* FIXME: upper bound must not overflow 32 bits */
- WARN_ON((start + length) > (1ULL << 32));
-
gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
if (pd)
continue;
- pd = alloc_pd_single(dev);
+ pd = alloc_pd(dev);
if (IS_ERR(pd))
goto unwind_out;
gen8_initialize_pd(&ppgtt->base, pd);
pdp->page_directory[pdpe] = pd;
- set_bit(pdpe, new_pds);
+ __set_bit(pdpe, new_pds);
}
return 0;
unwind_out:
for_each_set_bit(pdpe, new_pds, GEN8_LEGACY_PDPES)
- unmap_and_free_pd(pdp->page_directory[pdpe], dev);
+ free_pd(dev, pdp->page_directory[pdpe]);
return -ENOMEM;
}
return -ENOMEM;
}
+/* PDE TLBs are a pain to invalidate on GEN8+. When we modify
+ * the page table structures, we mark them dirty so that
+ * context switching/execlist queuing code takes extra steps
+ * to ensure that tlbs are flushed.
+ */
+static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt)
+{
+ ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.dev)->ring_mask;
+}
+
static int gen8_alloc_va_range(struct i915_address_space *vm,
uint64_t start,
uint64_t length)
* actually use the other side of the canonical address space.
*/
if (WARN_ON(start + length < start))
- return -ERANGE;
+ return -ENODEV;
+
+ if (WARN_ON(start + length > ppgtt->base.total))
+ return -ENODEV;
ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables);
if (ret)
/* Allocations have completed successfully, so set the bitmaps, and do
* the mappings. */
gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
- gen8_pde_t *const page_directory = kmap_atomic(pd->page);
+ gen8_pde_t *const page_directory = kmap_px(pd);
struct i915_page_table *pt;
uint64_t pd_len = gen8_clamp_pd(start, length);
uint64_t pd_start = start;
gen8_pte_count(pd_start, pd_len));
/* Our pde is now pointing to the pagetable, pt */
- set_bit(pde, pd->used_pdes);
+ __set_bit(pde, pd->used_pdes);
/* Map the PDE to the page table */
- __gen8_do_map_pt(page_directory + pde, pt, vm->dev);
+ page_directory[pde] = gen8_pde_encode(px_dma(pt),
+ I915_CACHE_LLC);
/* NB: We haven't yet mapped ptes to pages. At this
* point we're still relying on insert_entries() */
}
- if (!HAS_LLC(vm->dev))
- drm_clflush_virt_range(page_directory, PAGE_SIZE);
+ kunmap_px(ppgtt, page_directory);
- kunmap_atomic(page_directory);
-
- set_bit(pdpe, ppgtt->pdp.used_pdpes);
+ __set_bit(pdpe, ppgtt->pdp.used_pdpes);
}
free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
+ mark_tlbs_dirty(ppgtt);
return 0;
err_out:
while (pdpe--) {
for_each_set_bit(temp, new_page_tables[pdpe], I915_PDES)
- unmap_and_free_pt(ppgtt->pdp.page_directory[pdpe]->page_table[temp], vm->dev);
+ free_pt(vm->dev, ppgtt->pdp.page_directory[pdpe]->page_table[temp]);
}
for_each_set_bit(pdpe, new_page_dirs, GEN8_LEGACY_PDPES)
- unmap_and_free_pd(ppgtt->pdp.page_directory[pdpe], vm->dev);
+ free_pd(vm->dev, ppgtt->pdp.page_directory[pdpe]);
free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
+ mark_tlbs_dirty(ppgtt);
return ret;
}
*/
static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
{
- ppgtt->scratch_pt = alloc_pt_single(ppgtt->base.dev);
- if (IS_ERR(ppgtt->scratch_pt))
- return PTR_ERR(ppgtt->scratch_pt);
-
- ppgtt->scratch_pd = alloc_pd_single(ppgtt->base.dev);
- if (IS_ERR(ppgtt->scratch_pd))
- return PTR_ERR(ppgtt->scratch_pd);
+ int ret;
- gen8_initialize_pt(&ppgtt->base, ppgtt->scratch_pt);
- gen8_initialize_pd(&ppgtt->base, ppgtt->scratch_pd);
+ ret = gen8_init_scratch(&ppgtt->base);
+ if (ret)
+ return ret;
ppgtt->base.start = 0;
ppgtt->base.total = 1ULL << 32;
uint32_t pte, pde, temp;
uint32_t start = ppgtt->base.start, length = ppgtt->base.total;
- scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
+ scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, true, 0);
gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde) {
u32 expected;
gen6_pte_t *pt_vaddr;
- dma_addr_t pt_addr = ppgtt->pd.page_table[pde]->daddr;
+ const dma_addr_t pt_addr = px_dma(ppgtt->pd.page_table[pde]);
pd_entry = readl(ppgtt->pd_addr + pde);
expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
expected);
seq_printf(m, "\tPDE: %x\n", pd_entry);
- pt_vaddr = kmap_atomic(ppgtt->pd.page_table[pde]->page);
+ pt_vaddr = kmap_px(ppgtt->pd.page_table[pde]);
+
for (pte = 0; pte < GEN6_PTES; pte+=4) {
unsigned long va =
(pde * PAGE_SIZE * GEN6_PTES) +
}
seq_puts(m, "\n");
}
- kunmap_atomic(pt_vaddr);
+ kunmap_px(ppgtt, pt_vaddr);
}
}
container_of(pd, struct i915_hw_ppgtt, pd);
u32 pd_entry;
- pd_entry = GEN6_PDE_ADDR_ENCODE(pt->daddr);
+ pd_entry = GEN6_PDE_ADDR_ENCODE(px_dma(pt));
pd_entry |= GEN6_PDE_VALID;
writel(pd_entry, ppgtt->pd_addr + pde);
static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
{
- BUG_ON(ppgtt->pd.pd_offset & 0x3f);
+ BUG_ON(ppgtt->pd.base.ggtt_offset & 0x3f);
- return (ppgtt->pd.pd_offset / 64) << 16;
+ return (ppgtt->pd.base.ggtt_offset / 64) << 16;
}
static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
/* NB: TLBs must be flushed and invalidated before a switch */
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
}
static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = to_i915(ppgtt->base.dev);
I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
}
static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
/* NB: TLBs must be flushed and invalidated before a switch */
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
/* XXX: RCS is the only one to auto invalidate the TLBs? */
if (ring->id != RCS) {
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
}
}
static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ppgtt->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned first_pte = first_entry % GEN6_PTES;
unsigned last_pte, i;
- scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
+ scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, true, 0);
while (num_entries) {
last_pte = first_pte + num_entries;
if (last_pte > GEN6_PTES)
last_pte = GEN6_PTES;
- pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->page);
+ pt_vaddr = kmap_px(ppgtt->pd.page_table[act_pt]);
for (i = first_pte; i < last_pte; i++)
pt_vaddr[i] = scratch_pte;
- kunmap_atomic(pt_vaddr);
+ kunmap_px(ppgtt, pt_vaddr);
num_entries -= last_pte - first_pte;
first_pte = 0;
pt_vaddr = NULL;
for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
if (pt_vaddr == NULL)
- pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->page);
+ pt_vaddr = kmap_px(ppgtt->pd.page_table[act_pt]);
pt_vaddr[act_pte] =
vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
cache_level, true, flags);
if (++act_pte == GEN6_PTES) {
- kunmap_atomic(pt_vaddr);
+ kunmap_px(ppgtt, pt_vaddr);
pt_vaddr = NULL;
act_pt++;
act_pte = 0;
}
}
if (pt_vaddr)
- kunmap_atomic(pt_vaddr);
-}
-
-/* PDE TLBs are a pain invalidate pre GEN8. It requires a context reload. If we
- * are switching between contexts with the same LRCA, we also must do a force
- * restore.
- */
-static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt)
-{
- /* If current vm != vm, */
- ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.dev)->ring_mask;
-}
-
-static void gen6_initialize_pt(struct i915_address_space *vm,
- struct i915_page_table *pt)
-{
- gen6_pte_t *pt_vaddr, scratch_pte;
- int i;
-
- WARN_ON(vm->scratch.addr == 0);
-
- scratch_pte = vm->pte_encode(vm->scratch.addr,
- I915_CACHE_LLC, true, 0);
-
- pt_vaddr = kmap_atomic(pt->page);
-
- for (i = 0; i < GEN6_PTES; i++)
- pt_vaddr[i] = scratch_pte;
-
- kunmap_atomic(pt_vaddr);
+ kunmap_px(ppgtt, pt_vaddr);
}
static int gen6_alloc_va_range(struct i915_address_space *vm,
- uint64_t start, uint64_t length)
+ uint64_t start_in, uint64_t length_in)
{
DECLARE_BITMAP(new_page_tables, I915_PDES);
struct drm_device *dev = vm->dev;
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
struct i915_page_table *pt;
- const uint32_t start_save = start, length_save = length;
+ uint32_t start, length, start_save, length_save;
uint32_t pde, temp;
int ret;
- WARN_ON(upper_32_bits(start));
+ if (WARN_ON(start_in + length_in > ppgtt->base.total))
+ return -ENODEV;
+
+ start = start_save = start_in;
+ length = length_save = length_in;
bitmap_zero(new_page_tables, I915_PDES);
* tables.
*/
gen6_for_each_pde(pt, &ppgtt->pd, start, length, temp, pde) {
- if (pt != ppgtt->scratch_pt) {
+ if (pt != vm->scratch_pt) {
WARN_ON(bitmap_empty(pt->used_ptes, GEN6_PTES));
continue;
}
/* We've already allocated a page table */
WARN_ON(!bitmap_empty(pt->used_ptes, GEN6_PTES));
- pt = alloc_pt_single(dev);
+ pt = alloc_pt(dev);
if (IS_ERR(pt)) {
ret = PTR_ERR(pt);
goto unwind_out;
gen6_initialize_pt(vm, pt);
ppgtt->pd.page_table[pde] = pt;
- set_bit(pde, new_page_tables);
+ __set_bit(pde, new_page_tables);
trace_i915_page_table_entry_alloc(vm, pde, start, GEN6_PDE_SHIFT);
}
bitmap_set(tmp_bitmap, gen6_pte_index(start),
gen6_pte_count(start, length));
- if (test_and_clear_bit(pde, new_page_tables))
+ if (__test_and_clear_bit(pde, new_page_tables))
gen6_write_pde(&ppgtt->pd, pde, pt);
trace_i915_page_table_entry_map(vm, pde, pt,
for_each_set_bit(pde, new_page_tables, I915_PDES) {
struct i915_page_table *pt = ppgtt->pd.page_table[pde];
- ppgtt->pd.page_table[pde] = ppgtt->scratch_pt;
- unmap_and_free_pt(pt, vm->dev);
+ ppgtt->pd.page_table[pde] = vm->scratch_pt;
+ free_pt(vm->dev, pt);
}
mark_tlbs_dirty(ppgtt);
return ret;
}
+static int gen6_init_scratch(struct i915_address_space *vm)
+{
+ struct drm_device *dev = vm->dev;
+
+ vm->scratch_page = alloc_scratch_page(dev);
+ if (IS_ERR(vm->scratch_page))
+ return PTR_ERR(vm->scratch_page);
+
+ vm->scratch_pt = alloc_pt(dev);
+ if (IS_ERR(vm->scratch_pt)) {
+ free_scratch_page(dev, vm->scratch_page);
+ return PTR_ERR(vm->scratch_pt);
+ }
+
+ gen6_initialize_pt(vm, vm->scratch_pt);
+
+ return 0;
+}
+
+static void gen6_free_scratch(struct i915_address_space *vm)
+{
+ struct drm_device *dev = vm->dev;
+
+ free_pt(dev, vm->scratch_pt);
+ free_scratch_page(dev, vm->scratch_page);
+}
+
static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
{
struct i915_hw_ppgtt *ppgtt =
struct i915_page_table *pt;
uint32_t pde;
-
drm_mm_remove_node(&ppgtt->node);
gen6_for_all_pdes(pt, ppgtt, pde) {
- if (pt != ppgtt->scratch_pt)
- unmap_and_free_pt(pt, ppgtt->base.dev);
+ if (pt != vm->scratch_pt)
+ free_pt(ppgtt->base.dev, pt);
}
- unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
- unmap_and_free_pd(&ppgtt->pd, ppgtt->base.dev);
+ gen6_free_scratch(vm);
}
static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
{
+ struct i915_address_space *vm = &ppgtt->base;
struct drm_device *dev = ppgtt->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
bool retried = false;
* size. We allocate at the top of the GTT to avoid fragmentation.
*/
BUG_ON(!drm_mm_initialized(&dev_priv->gtt.base.mm));
- ppgtt->scratch_pt = alloc_pt_single(ppgtt->base.dev);
- if (IS_ERR(ppgtt->scratch_pt))
- return PTR_ERR(ppgtt->scratch_pt);
- gen6_initialize_pt(&ppgtt->base, ppgtt->scratch_pt);
+ ret = gen6_init_scratch(vm);
+ if (ret)
+ return ret;
alloc:
ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm,
return 0;
err_out:
- unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
+ gen6_free_scratch(vm);
return ret;
}
uint32_t pde, temp;
gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde)
- ppgtt->pd.page_table[pde] = ppgtt->scratch_pt;
+ ppgtt->pd.page_table[pde] = ppgtt->base.scratch_pt;
}
static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
ppgtt->debug_dump = gen6_dump_ppgtt;
- ppgtt->pd.pd_offset =
+ ppgtt->pd.base.ggtt_offset =
ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
ppgtt->pd_addr = (gen6_pte_t __iomem *)dev_priv->gtt.gsm +
- ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
+ ppgtt->pd.base.ggtt_offset / sizeof(gen6_pte_t);
gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total);
ppgtt->node.start / PAGE_SIZE);
DRM_DEBUG("Adding PPGTT at offset %x\n",
- ppgtt->pd.pd_offset << 10);
+ ppgtt->pd.base.ggtt_offset << 10);
return 0;
}
static int __hw_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
ppgtt->base.dev = dev;
- ppgtt->base.scratch = dev_priv->gtt.base.scratch;
if (INTEL_INFO(dev)->gen < 8)
return gen6_ppgtt_init(ppgtt);
else
return gen8_ppgtt_init(ppgtt);
}
+
int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
{
struct drm_i915_private *dev_priv = dev->dev_private;
int i915_ppgtt_init_hw(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_engine_cs *ring;
- struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
- int i, ret = 0;
-
/* In the case of execlists, PPGTT is enabled by the context descriptor
* and the PDPs are contained within the context itself. We don't
* need to do anything here. */
else
MISSING_CASE(INTEL_INFO(dev)->gen);
- if (ppgtt) {
- for_each_ring(ring, dev_priv, i) {
- ret = ppgtt->switch_mm(ppgtt, ring);
- if (ret != 0)
- return ret;
- }
- }
+ return 0;
+}
- return ret;
+int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
+{
+ struct drm_i915_private *dev_priv = req->ring->dev->dev_private;
+ struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+
+ if (i915.enable_execlists)
+ return 0;
+
+ if (!ppgtt)
+ return 0;
+
+ return ppgtt->switch_mm(ppgtt, req);
}
+
struct i915_hw_ppgtt *
i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
{
int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
{
- if (obj->has_dma_mapping)
- return 0;
-
if (!dma_map_sg(&obj->base.dev->pdev->dev,
obj->pages->sgl, obj->pages->nents,
PCI_DMA_BIDIRECTIONAL))
first_entry, num_entries, max_entries))
num_entries = max_entries;
- scratch_pte = gen8_pte_encode(vm->scratch.addr,
+ scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
I915_CACHE_LLC,
use_scratch);
for (i = 0; i < num_entries; i++)
first_entry, num_entries, max_entries))
num_entries = max_entries;
- scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch, 0);
+ scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, use_scratch, 0);
for (i = 0; i < num_entries; i++)
iowrite32(scratch_pte, >t_base[i]);
interruptible = do_idling(dev_priv);
- if (!obj->has_dma_mapping)
- dma_unmap_sg(&dev->pdev->dev,
- obj->pages->sgl, obj->pages->nents,
- PCI_DMA_BIDIRECTIONAL);
+ dma_unmap_sg(&dev->pdev->dev, obj->pages->sgl, obj->pages->nents,
+ PCI_DMA_BIDIRECTIONAL);
undo_idling(dev_priv, interruptible);
}
void i915_gem_init_global_gtt(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- unsigned long gtt_size, mappable_size;
+ u64 gtt_size, mappable_size;
gtt_size = dev_priv->gtt.base.total;
mappable_size = dev_priv->gtt.mappable_end;
vm->cleanup(vm);
}
-static int setup_scratch_page(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct page *page;
- dma_addr_t dma_addr;
-
- page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
- if (page == NULL)
- return -ENOMEM;
- set_pages_uc(page, 1);
-
-#ifdef CONFIG_INTEL_IOMMU
- dma_addr = pci_map_page(dev->pdev, page, 0, PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
- if (pci_dma_mapping_error(dev->pdev, dma_addr))
- return -EINVAL;
-#else
- dma_addr = page_to_phys(page);
-#endif
- dev_priv->gtt.base.scratch.page = page;
- dev_priv->gtt.base.scratch.addr = dma_addr;
-
- return 0;
-}
-
-static void teardown_scratch_page(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct page *page = dev_priv->gtt.base.scratch.page;
-
- set_pages_wb(page, 1);
- pci_unmap_page(dev->pdev, dev_priv->gtt.base.scratch.addr,
- PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
- __free_page(page);
-}
-
static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
{
snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
size_t gtt_size)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_page_scratch *scratch_page;
phys_addr_t gtt_phys_addr;
- int ret;
/* For Modern GENs the PTEs and register space are split in the BAR */
gtt_phys_addr = pci_resource_start(dev->pdev, 0) +
return -ENOMEM;
}
- ret = setup_scratch_page(dev);
- if (ret) {
+ scratch_page = alloc_scratch_page(dev);
+ if (IS_ERR(scratch_page)) {
DRM_ERROR("Scratch setup failed\n");
/* iounmap will also get called at remove, but meh */
iounmap(dev_priv->gtt.gsm);
+ return PTR_ERR(scratch_page);
}
- return ret;
+ dev_priv->gtt.base.scratch_page = scratch_page;
+
+ return 0;
}
/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
}
static int gen8_gmch_probe(struct drm_device *dev,
- size_t *gtt_total,
+ u64 *gtt_total,
size_t *stolen,
phys_addr_t *mappable_base,
- unsigned long *mappable_end)
+ u64 *mappable_end)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- unsigned int gtt_size;
+ u64 gtt_size;
u16 snb_gmch_ctl;
int ret;
}
static int gen6_gmch_probe(struct drm_device *dev,
- size_t *gtt_total,
+ u64 *gtt_total,
size_t *stolen,
phys_addr_t *mappable_base,
- unsigned long *mappable_end)
+ u64 *mappable_end)
{
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned int gtt_size;
* a coarse sanity check.
*/
if ((*mappable_end < (64<<20) || (*mappable_end > (512<<20)))) {
- DRM_ERROR("Unknown GMADR size (%lx)\n",
+ DRM_ERROR("Unknown GMADR size (%llx)\n",
dev_priv->gtt.mappable_end);
return -ENXIO;
}
struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
iounmap(gtt->gsm);
- teardown_scratch_page(vm->dev);
+ free_scratch_page(vm->dev, vm->scratch_page);
}
static int i915_gmch_probe(struct drm_device *dev,
- size_t *gtt_total,
+ u64 *gtt_total,
size_t *stolen,
phys_addr_t *mappable_base,
- unsigned long *mappable_end)
+ u64 *mappable_end)
{
struct drm_i915_private *dev_priv = dev->dev_private;
int ret;
dev_priv->gtt.base.cleanup = gen6_gmch_remove;
}
+ gtt->base.dev = dev;
+
ret = gtt->gtt_probe(dev, >t->base.total, >t->stolen_size,
>t->mappable_base, >t->mappable_end);
if (ret)
return ret;
- gtt->base.dev = dev;
-
/* GMADR is the PCI mmio aperture into the global GTT. */
- DRM_INFO("Memory usable by graphics device = %zdM\n",
+ DRM_INFO("Memory usable by graphics device = %lluM\n",
gtt->base.total >> 20);
- DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20);
+ DRM_DEBUG_DRIVER("GMADR size = %lldM\n", gtt->mappable_end >> 20);
DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20);
#ifdef CONFIG_INTEL_IOMMU
if (intel_iommu_gfx_mapped)
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj;
struct i915_address_space *vm;
+ struct i915_vma *vma;
+ bool flush;
i915_check_and_clear_faults(dev);
dev_priv->gtt.base.total,
true);
+ /* Cache flush objects bound into GGTT and rebind them. */
+ vm = &dev_priv->gtt.base;
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
- struct i915_vma *vma = i915_gem_obj_to_vma(obj,
- &dev_priv->gtt.base);
- if (!vma)
- continue;
+ flush = false;
+ list_for_each_entry(vma, &obj->vma_list, vma_link) {
+ if (vma->vm != vm)
+ continue;
- i915_gem_clflush_object(obj, obj->pin_display);
- WARN_ON(i915_vma_bind(vma, obj->cache_level, PIN_UPDATE));
- }
+ WARN_ON(i915_vma_bind(vma, obj->cache_level,
+ PIN_UPDATE));
+ flush = true;
+ }
+
+ if (flush)
+ i915_gem_clflush_object(obj, obj->pin_display);
+ }
if (INTEL_INFO(dev)->gen >= 8) {
if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view,
struct drm_i915_gem_object *obj)
{
- struct drm_device *dev = obj->base.dev;
struct intel_rotation_info *rot_info = &ggtt_view->rotation_info;
- unsigned long size, pages, rot_pages;
+ unsigned int size_pages = rot_info->size >> PAGE_SHIFT;
struct sg_page_iter sg_iter;
unsigned long i;
dma_addr_t *page_addr_list;
struct sg_table *st;
- unsigned int tile_pitch, tile_height;
- unsigned int width_pages, height_pages;
int ret = -ENOMEM;
- pages = obj->base.size / PAGE_SIZE;
-
- /* Calculate tiling geometry. */
- tile_height = intel_tile_height(dev, rot_info->pixel_format,
- rot_info->fb_modifier);
- tile_pitch = PAGE_SIZE / tile_height;
- width_pages = DIV_ROUND_UP(rot_info->pitch, tile_pitch);
- height_pages = DIV_ROUND_UP(rot_info->height, tile_height);
- rot_pages = width_pages * height_pages;
- size = rot_pages * PAGE_SIZE;
-
/* Allocate a temporary list of source pages for random access. */
- page_addr_list = drm_malloc_ab(pages, sizeof(dma_addr_t));
+ page_addr_list = drm_malloc_ab(obj->base.size / PAGE_SIZE,
+ sizeof(dma_addr_t));
if (!page_addr_list)
return ERR_PTR(ret);
if (!st)
goto err_st_alloc;
- ret = sg_alloc_table(st, rot_pages, GFP_KERNEL);
+ ret = sg_alloc_table(st, size_pages, GFP_KERNEL);
if (ret)
goto err_sg_alloc;
}
/* Rotate the pages. */
- rotate_pages(page_addr_list, width_pages, height_pages, st);
+ rotate_pages(page_addr_list,
+ rot_info->width_pages, rot_info->height_pages,
+ st);
DRM_DEBUG_KMS(
- "Created rotated page mapping for object size %lu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %lu pages).\n",
- size, rot_info->pitch, rot_info->height,
- rot_info->pixel_format, width_pages, height_pages,
- rot_pages);
+ "Created rotated page mapping for object size %zu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages).\n",
+ obj->base.size, rot_info->pitch, rot_info->height,
+ rot_info->pixel_format, rot_info->width_pages,
+ rot_info->height_pages, size_pages);
drm_free_large(page_addr_list);
drm_free_large(page_addr_list);
DRM_DEBUG_KMS(
- "Failed to create rotated mapping for object size %lu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %lu pages)\n",
- size, ret, rot_info->pitch, rot_info->height,
- rot_info->pixel_format, width_pages, height_pages,
- rot_pages);
+ "Failed to create rotated mapping for object size %zu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages)\n",
+ obj->base.size, ret, rot_info->pitch, rot_info->height,
+ rot_info->pixel_format, rot_info->width_pages,
+ rot_info->height_pages, size_pages);
return ERR_PTR(ret);
}
vma->node.size,
VM_TO_TRACE_NAME(vma->vm));
+ /* XXX: i915_vma_pin() will fix this +- hack */
+ vma->pin_count++;
ret = vma->vm->allocate_va_range(vma->vm,
vma->node.start,
vma->node.size);
+ vma->pin_count--;
if (ret)
return ret;
}
i915_ggtt_view_size(struct drm_i915_gem_object *obj,
const struct i915_ggtt_view *view)
{
- if (view->type == I915_GGTT_VIEW_NORMAL ||
- view->type == I915_GGTT_VIEW_ROTATED) {
+ if (view->type == I915_GGTT_VIEW_NORMAL) {
return obj->base.size;
+ } else if (view->type == I915_GGTT_VIEW_ROTATED) {
+ return view->rotation_info.size;
} else if (view->type == I915_GGTT_VIEW_PARTIAL) {
return view->params.partial.size << PAGE_SHIFT;
} else {
* for is a boon.
*/
+int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node, u64 size,
+ unsigned alignment)
+{
+ int ret;
+
+ if (!drm_mm_initialized(&dev_priv->mm.stolen))
+ return -ENODEV;
+
+ mutex_lock(&dev_priv->mm.stolen_lock);
+ ret = drm_mm_insert_node(&dev_priv->mm.stolen, node, size, alignment,
+ DRM_MM_SEARCH_DEFAULT);
+ mutex_unlock(&dev_priv->mm.stolen_lock);
+
+ return ret;
+}
+
+void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node)
+{
+ mutex_lock(&dev_priv->mm.stolen_lock);
+ drm_mm_remove_node(node);
+ mutex_unlock(&dev_priv->mm.stolen_lock);
+}
+
static unsigned long i915_stolen_to_physical(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
return base;
}
-static int find_compression_threshold(struct drm_device *dev,
- struct drm_mm_node *node,
- int size,
- int fb_cpp)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- int compression_threshold = 1;
- int ret;
-
- /* HACK: This code depends on what we will do in *_enable_fbc. If that
- * code changes, this code needs to change as well.
- *
- * The enable_fbc code will attempt to use one of our 2 compression
- * thresholds, therefore, in that case, we only have 1 resort.
- */
-
- /* Try to over-allocate to reduce reallocations and fragmentation. */
- ret = drm_mm_insert_node(&dev_priv->mm.stolen, node,
- size <<= 1, 4096, DRM_MM_SEARCH_DEFAULT);
- if (ret == 0)
- return compression_threshold;
-
-again:
- /* HW's ability to limit the CFB is 1:4 */
- if (compression_threshold > 4 ||
- (fb_cpp == 2 && compression_threshold == 2))
- return 0;
-
- ret = drm_mm_insert_node(&dev_priv->mm.stolen, node,
- size >>= 1, 4096,
- DRM_MM_SEARCH_DEFAULT);
- if (ret && INTEL_INFO(dev)->gen <= 4) {
- return 0;
- } else if (ret) {
- compression_threshold <<= 1;
- goto again;
- } else {
- return compression_threshold;
- }
-}
-
-static int i915_setup_compression(struct drm_device *dev, int size, int fb_cpp)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct drm_mm_node *uninitialized_var(compressed_llb);
- int ret;
-
- ret = find_compression_threshold(dev, &dev_priv->fbc.compressed_fb,
- size, fb_cpp);
- if (!ret)
- goto err_llb;
- else if (ret > 1) {
- DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
-
- }
-
- dev_priv->fbc.threshold = ret;
-
- if (INTEL_INFO(dev_priv)->gen >= 5)
- I915_WRITE(ILK_DPFC_CB_BASE, dev_priv->fbc.compressed_fb.start);
- else if (IS_GM45(dev)) {
- I915_WRITE(DPFC_CB_BASE, dev_priv->fbc.compressed_fb.start);
- } else {
- compressed_llb = kzalloc(sizeof(*compressed_llb), GFP_KERNEL);
- if (!compressed_llb)
- goto err_fb;
-
- ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_llb,
- 4096, 4096, DRM_MM_SEARCH_DEFAULT);
- if (ret)
- goto err_fb;
-
- dev_priv->fbc.compressed_llb = compressed_llb;
-
- I915_WRITE(FBC_CFB_BASE,
- dev_priv->mm.stolen_base + dev_priv->fbc.compressed_fb.start);
- I915_WRITE(FBC_LL_BASE,
- dev_priv->mm.stolen_base + compressed_llb->start);
- }
-
- dev_priv->fbc.uncompressed_size = size;
-
- DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n",
- size);
-
- return 0;
-
-err_fb:
- kfree(compressed_llb);
- drm_mm_remove_node(&dev_priv->fbc.compressed_fb);
-err_llb:
- pr_info_once("drm: not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
- return -ENOSPC;
-}
-
-int i915_gem_stolen_setup_compression(struct drm_device *dev, int size, int fb_cpp)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (!drm_mm_initialized(&dev_priv->mm.stolen))
- return -ENODEV;
-
- if (size <= dev_priv->fbc.uncompressed_size)
- return 0;
-
- /* Release any current block */
- i915_gem_stolen_cleanup_compression(dev);
-
- return i915_setup_compression(dev, size, fb_cpp);
-}
-
-void i915_gem_stolen_cleanup_compression(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (dev_priv->fbc.uncompressed_size == 0)
- return;
-
- drm_mm_remove_node(&dev_priv->fbc.compressed_fb);
-
- if (dev_priv->fbc.compressed_llb) {
- drm_mm_remove_node(dev_priv->fbc.compressed_llb);
- kfree(dev_priv->fbc.compressed_llb);
- }
-
- dev_priv->fbc.uncompressed_size = 0;
-}
-
void i915_gem_cleanup_stolen(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
if (!drm_mm_initialized(&dev_priv->mm.stolen))
return;
- i915_gem_stolen_cleanup_compression(dev);
drm_mm_takedown(&dev_priv->mm.stolen);
}
u32 tmp;
int bios_reserved = 0;
+ mutex_init(&dev_priv->mm.stolen_lock);
+
#ifdef CONFIG_INTEL_IOMMU
if (intel_iommu_gfx_mapped && INTEL_INFO(dev)->gen < 8) {
DRM_INFO("DMAR active, disabling use of stolen memory\n");
static void
i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
{
+ struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+
if (obj->stolen) {
- drm_mm_remove_node(obj->stolen);
+ i915_gem_stolen_remove_node(dev_priv, obj->stolen);
kfree(obj->stolen);
obj->stolen = NULL;
}
if (obj->pages == NULL)
goto cleanup;
- obj->has_dma_mapping = true;
i915_gem_object_pin_pages(obj);
obj->stolen = stolen;
if (!stolen)
return NULL;
- ret = drm_mm_insert_node(&dev_priv->mm.stolen, stolen, size,
- 4096, DRM_MM_SEARCH_DEFAULT);
+ ret = i915_gem_stolen_insert_node(dev_priv, stolen, size, 4096);
if (ret) {
kfree(stolen);
return NULL;
if (obj)
return obj;
- drm_mm_remove_node(stolen);
+ i915_gem_stolen_remove_node(dev_priv, stolen);
kfree(stolen);
return NULL;
}
stolen->start = stolen_offset;
stolen->size = size;
+ mutex_lock(&dev_priv->mm.stolen_lock);
ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
+ mutex_unlock(&dev_priv->mm.stolen_lock);
if (ret) {
DRM_DEBUG_KMS("failed to allocate stolen space\n");
kfree(stolen);
obj = _i915_gem_object_create_stolen(dev, stolen);
if (obj == NULL) {
DRM_DEBUG_KMS("failed to allocate stolen object\n");
- drm_mm_remove_node(stolen);
+ i915_gem_stolen_remove_node(dev_priv, stolen);
kfree(stolen);
return NULL;
}
err_vma:
i915_gem_vma_destroy(vma);
err_out:
- drm_mm_remove_node(stolen);
+ i915_gem_stolen_remove_node(dev_priv, stolen);
kfree(stolen);
drm_gem_object_unreference(&obj->base);
return NULL;
#include <drm/i915_drm.h>
#include "i915_drv.h"
-typedef struct _drm_i915_batchbuffer32 {
- int start; /* agp offset */
- int used; /* nr bytes in use */
- int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */
- int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */
- int num_cliprects; /* mulitpass with multiple cliprects? */
- u32 cliprects; /* pointer to userspace cliprects */
-} drm_i915_batchbuffer32_t;
-
-static int compat_i915_batchbuffer(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- drm_i915_batchbuffer32_t batchbuffer32;
- drm_i915_batchbuffer_t __user *batchbuffer;
-
- if (copy_from_user
- (&batchbuffer32, (void __user *)arg, sizeof(batchbuffer32)))
- return -EFAULT;
-
- batchbuffer = compat_alloc_user_space(sizeof(*batchbuffer));
- if (!access_ok(VERIFY_WRITE, batchbuffer, sizeof(*batchbuffer))
- || __put_user(batchbuffer32.start, &batchbuffer->start)
- || __put_user(batchbuffer32.used, &batchbuffer->used)
- || __put_user(batchbuffer32.DR1, &batchbuffer->DR1)
- || __put_user(batchbuffer32.DR4, &batchbuffer->DR4)
- || __put_user(batchbuffer32.num_cliprects,
- &batchbuffer->num_cliprects)
- || __put_user((int __user *)(unsigned long)batchbuffer32.cliprects,
- &batchbuffer->cliprects))
- return -EFAULT;
-
- return drm_ioctl(file, DRM_IOCTL_I915_BATCHBUFFER,
- (unsigned long)batchbuffer);
-}
-
-typedef struct _drm_i915_cmdbuffer32 {
- u32 buf; /* pointer to userspace command buffer */
- int sz; /* nr bytes in buf */
- int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */
- int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */
- int num_cliprects; /* mulitpass with multiple cliprects? */
- u32 cliprects; /* pointer to userspace cliprects */
-} drm_i915_cmdbuffer32_t;
-
-static int compat_i915_cmdbuffer(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- drm_i915_cmdbuffer32_t cmdbuffer32;
- drm_i915_cmdbuffer_t __user *cmdbuffer;
-
- if (copy_from_user
- (&cmdbuffer32, (void __user *)arg, sizeof(cmdbuffer32)))
- return -EFAULT;
-
- cmdbuffer = compat_alloc_user_space(sizeof(*cmdbuffer));
- if (!access_ok(VERIFY_WRITE, cmdbuffer, sizeof(*cmdbuffer))
- || __put_user((int __user *)(unsigned long)cmdbuffer32.buf,
- &cmdbuffer->buf)
- || __put_user(cmdbuffer32.sz, &cmdbuffer->sz)
- || __put_user(cmdbuffer32.DR1, &cmdbuffer->DR1)
- || __put_user(cmdbuffer32.DR4, &cmdbuffer->DR4)
- || __put_user(cmdbuffer32.num_cliprects, &cmdbuffer->num_cliprects)
- || __put_user((int __user *)(unsigned long)cmdbuffer32.cliprects,
- &cmdbuffer->cliprects))
- return -EFAULT;
-
- return drm_ioctl(file, DRM_IOCTL_I915_CMDBUFFER,
- (unsigned long)cmdbuffer);
-}
-
-typedef struct drm_i915_irq_emit32 {
- u32 irq_seq;
-} drm_i915_irq_emit32_t;
-
-static int compat_i915_irq_emit(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- drm_i915_irq_emit32_t req32;
- drm_i915_irq_emit_t __user *request;
-
- if (copy_from_user(&req32, (void __user *)arg, sizeof(req32)))
- return -EFAULT;
-
- request = compat_alloc_user_space(sizeof(*request));
- if (!access_ok(VERIFY_WRITE, request, sizeof(*request))
- || __put_user((int __user *)(unsigned long)req32.irq_seq,
- &request->irq_seq))
- return -EFAULT;
-
- return drm_ioctl(file, DRM_IOCTL_I915_IRQ_EMIT,
- (unsigned long)request);
-}
-typedef struct drm_i915_getparam32 {
- int param;
+struct drm_i915_getparam32 {
+ s32 param;
+ /*
+ * We screwed up the generic ioctl struct here and used a variable-sized
+ * pointer. Use u32 in the compat struct to match the 32bit pointer
+ * userspace expects.
+ */
u32 value;
-} drm_i915_getparam32_t;
+};
static int compat_i915_getparam(struct file *file, unsigned int cmd,
unsigned long arg)
{
- drm_i915_getparam32_t req32;
+ struct drm_i915_getparam32 req32;
drm_i915_getparam_t __user *request;
if (copy_from_user(&req32, (void __user *)arg, sizeof(req32)))
(unsigned long)request);
}
-typedef struct drm_i915_mem_alloc32 {
- int region;
- int alignment;
- int size;
- u32 region_offset; /* offset from start of fb or agp */
-} drm_i915_mem_alloc32_t;
-
-static int compat_i915_alloc(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- drm_i915_mem_alloc32_t req32;
- drm_i915_mem_alloc_t __user *request;
-
- if (copy_from_user(&req32, (void __user *)arg, sizeof(req32)))
- return -EFAULT;
-
- request = compat_alloc_user_space(sizeof(*request));
- if (!access_ok(VERIFY_WRITE, request, sizeof(*request))
- || __put_user(req32.region, &request->region)
- || __put_user(req32.alignment, &request->alignment)
- || __put_user(req32.size, &request->size)
- || __put_user((void __user *)(unsigned long)req32.region_offset,
- &request->region_offset))
- return -EFAULT;
-
- return drm_ioctl(file, DRM_IOCTL_I915_ALLOC,
- (unsigned long)request);
-}
-
static drm_ioctl_compat_t *i915_compat_ioctls[] = {
- [DRM_I915_BATCHBUFFER] = compat_i915_batchbuffer,
- [DRM_I915_CMDBUFFER] = compat_i915_cmdbuffer,
[DRM_I915_GETPARAM] = compat_i915_getparam,
- [DRM_I915_IRQ_EMIT] = compat_i915_irq_emit,
- [DRM_I915_ALLOC] = compat_i915_alloc
};
/**
drm_ioctl_compat_t *fn = NULL;
int ret;
- if (nr < DRM_COMMAND_BASE)
+ if (nr < DRM_COMMAND_BASE || nr >= DRM_COMMAND_END)
return drm_compat_ioctl(filp, cmd, arg);
if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(i915_compat_ioctls))
u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal;
struct intel_crtc *intel_crtc =
to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
- const struct drm_display_mode *mode =
- &intel_crtc->config->base.adjusted_mode;
+ const struct drm_display_mode *mode = &intel_crtc->base.hwmode;
htotal = mode->crtc_htotal;
hsync_start = mode->crtc_hsync_start;
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- const struct drm_display_mode *mode = &crtc->config->base.adjusted_mode;
+ const struct drm_display_mode *mode = &crtc->base.hwmode;
enum pipe pipe = crtc->pipe;
int position, vtotal;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- const struct drm_display_mode *mode = &intel_crtc->config->base.adjusted_mode;
+ const struct drm_display_mode *mode = &intel_crtc->base.hwmode;
int position;
int vbl_start, vbl_end, hsync_start, htotal, vtotal;
bool in_vbl = true;
int ret = 0;
unsigned long irqflags;
- if (!intel_crtc->active) {
+ if (WARN_ON(!mode->crtc_clock)) {
DRM_DEBUG_DRIVER("trying to get scanoutpos for disabled "
"pipe %c\n", pipe_name(pipe));
return 0;
return -EINVAL;
}
- if (!crtc->state->enable) {
+ if (!crtc->hwmode.crtc_clock) {
DRM_DEBUG_KMS("crtc %d is disabled\n", pipe);
return -EBUSY;
}
return drm_calc_vbltimestamp_from_scanoutpos(dev, pipe, max_error,
vblank_time, flags,
crtc,
- &to_intel_crtc(crtc)->config->base.adjusted_mode);
-}
-
-static bool intel_hpd_irq_event(struct drm_device *dev,
- struct drm_connector *connector)
-{
- enum drm_connector_status old_status;
-
- WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
- old_status = connector->status;
-
- connector->status = connector->funcs->detect(connector, false);
- if (old_status == connector->status)
- return false;
-
- DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n",
- connector->base.id,
- connector->name,
- drm_get_connector_status_name(old_status),
- drm_get_connector_status_name(connector->status));
-
- return true;
-}
-
-static void i915_digport_work_func(struct work_struct *work)
-{
- struct drm_i915_private *dev_priv =
- container_of(work, struct drm_i915_private, dig_port_work);
- u32 long_port_mask, short_port_mask;
- struct intel_digital_port *intel_dig_port;
- int i;
- u32 old_bits = 0;
-
- spin_lock_irq(&dev_priv->irq_lock);
- long_port_mask = dev_priv->long_hpd_port_mask;
- dev_priv->long_hpd_port_mask = 0;
- short_port_mask = dev_priv->short_hpd_port_mask;
- dev_priv->short_hpd_port_mask = 0;
- spin_unlock_irq(&dev_priv->irq_lock);
-
- for (i = 0; i < I915_MAX_PORTS; i++) {
- bool valid = false;
- bool long_hpd = false;
- intel_dig_port = dev_priv->hpd_irq_port[i];
- if (!intel_dig_port || !intel_dig_port->hpd_pulse)
- continue;
-
- if (long_port_mask & (1 << i)) {
- valid = true;
- long_hpd = true;
- } else if (short_port_mask & (1 << i))
- valid = true;
-
- if (valid) {
- enum irqreturn ret;
-
- ret = intel_dig_port->hpd_pulse(intel_dig_port, long_hpd);
- if (ret == IRQ_NONE) {
- /* fall back to old school hpd */
- old_bits |= (1 << intel_dig_port->base.hpd_pin);
- }
- }
- }
-
- if (old_bits) {
- spin_lock_irq(&dev_priv->irq_lock);
- dev_priv->hpd_event_bits |= old_bits;
- spin_unlock_irq(&dev_priv->irq_lock);
- schedule_work(&dev_priv->hotplug_work);
- }
-}
-
-/*
- * Handle hotplug events outside the interrupt handler proper.
- */
-#define I915_REENABLE_HOTPLUG_DELAY (2*60*1000)
-
-static void i915_hotplug_work_func(struct work_struct *work)
-{
- struct drm_i915_private *dev_priv =
- container_of(work, struct drm_i915_private, hotplug_work);
- struct drm_device *dev = dev_priv->dev;
- struct drm_mode_config *mode_config = &dev->mode_config;
- struct intel_connector *intel_connector;
- struct intel_encoder *intel_encoder;
- struct drm_connector *connector;
- bool hpd_disabled = false;
- bool changed = false;
- u32 hpd_event_bits;
-
- mutex_lock(&mode_config->mutex);
- DRM_DEBUG_KMS("running encoder hotplug functions\n");
-
- spin_lock_irq(&dev_priv->irq_lock);
-
- hpd_event_bits = dev_priv->hpd_event_bits;
- dev_priv->hpd_event_bits = 0;
- list_for_each_entry(connector, &mode_config->connector_list, head) {
- intel_connector = to_intel_connector(connector);
- if (!intel_connector->encoder)
- continue;
- intel_encoder = intel_connector->encoder;
- if (intel_encoder->hpd_pin > HPD_NONE &&
- dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_MARK_DISABLED &&
- connector->polled == DRM_CONNECTOR_POLL_HPD) {
- DRM_INFO("HPD interrupt storm detected on connector %s: "
- "switching from hotplug detection to polling\n",
- connector->name);
- dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark = HPD_DISABLED;
- connector->polled = DRM_CONNECTOR_POLL_CONNECT
- | DRM_CONNECTOR_POLL_DISCONNECT;
- hpd_disabled = true;
- }
- if (hpd_event_bits & (1 << intel_encoder->hpd_pin)) {
- DRM_DEBUG_KMS("Connector %s (pin %i) received hotplug event.\n",
- connector->name, intel_encoder->hpd_pin);
- }
- }
- /* if there were no outputs to poll, poll was disabled,
- * therefore make sure it's enabled when disabling HPD on
- * some connectors */
- if (hpd_disabled) {
- drm_kms_helper_poll_enable(dev);
- mod_delayed_work(system_wq, &dev_priv->hotplug_reenable_work,
- msecs_to_jiffies(I915_REENABLE_HOTPLUG_DELAY));
- }
-
- spin_unlock_irq(&dev_priv->irq_lock);
-
- list_for_each_entry(connector, &mode_config->connector_list, head) {
- intel_connector = to_intel_connector(connector);
- if (!intel_connector->encoder)
- continue;
- intel_encoder = intel_connector->encoder;
- if (hpd_event_bits & (1 << intel_encoder->hpd_pin)) {
- if (intel_encoder->hot_plug)
- intel_encoder->hot_plug(intel_encoder);
- if (intel_hpd_irq_event(dev, connector))
- changed = true;
- }
- }
- mutex_unlock(&mode_config->mutex);
-
- if (changed)
- drm_kms_helper_hotplug_event(dev);
+ &crtc->hwmode);
}
static void ironlake_rps_change_irq_handler(struct drm_device *dev)
return ret;
}
-#define HPD_STORM_DETECT_PERIOD 1000
-#define HPD_STORM_THRESHOLD 5
-
-static int pch_port_to_hotplug_shift(enum port port)
+static bool pch_port_hotplug_long_detect(enum port port, u32 val)
{
switch (port) {
- case PORT_A:
- case PORT_E:
- default:
- return -1;
case PORT_B:
- return 0;
+ return val & PORTB_HOTPLUG_LONG_DETECT;
case PORT_C:
- return 8;
+ return val & PORTC_HOTPLUG_LONG_DETECT;
case PORT_D:
- return 16;
+ return val & PORTD_HOTPLUG_LONG_DETECT;
+ default:
+ return false;
}
}
-static int i915_port_to_hotplug_shift(enum port port)
+static bool i9xx_port_hotplug_long_detect(enum port port, u32 val)
{
switch (port) {
- case PORT_A:
- case PORT_E:
- default:
- return -1;
case PORT_B:
- return 17;
+ return val & PORTB_HOTPLUG_INT_LONG_PULSE;
case PORT_C:
- return 19;
+ return val & PORTC_HOTPLUG_INT_LONG_PULSE;
case PORT_D:
- return 21;
- }
-}
-
-static enum port get_port_from_pin(enum hpd_pin pin)
-{
- switch (pin) {
- case HPD_PORT_B:
- return PORT_B;
- case HPD_PORT_C:
- return PORT_C;
- case HPD_PORT_D:
- return PORT_D;
+ return val & PORTD_HOTPLUG_INT_LONG_PULSE;
default:
- return PORT_A; /* no hpd */
+ return false;
}
}
-static void intel_hpd_irq_handler(struct drm_device *dev,
- u32 hotplug_trigger,
- u32 dig_hotplug_reg,
- const u32 hpd[HPD_NUM_PINS])
+/* Get a bit mask of pins that have triggered, and which ones may be long. */
+static void pch_get_hpd_pins(u32 *pin_mask, u32 *long_mask,
+ u32 hotplug_trigger, u32 dig_hotplug_reg,
+ const u32 hpd[HPD_NUM_PINS])
{
- struct drm_i915_private *dev_priv = dev->dev_private;
- int i;
enum port port;
- bool storm_detected = false;
- bool queue_dig = false, queue_hp = false;
- u32 dig_shift;
- u32 dig_port_mask = 0;
-
- if (!hotplug_trigger)
- return;
+ int i;
- DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x\n",
- hotplug_trigger, dig_hotplug_reg);
+ *pin_mask = 0;
+ *long_mask = 0;
- spin_lock(&dev_priv->irq_lock);
- for (i = 1; i < HPD_NUM_PINS; i++) {
- if (!(hpd[i] & hotplug_trigger))
+ for_each_hpd_pin(i) {
+ if ((hpd[i] & hotplug_trigger) == 0)
continue;
- port = get_port_from_pin(i);
- if (port && dev_priv->hpd_irq_port[port]) {
- bool long_hpd;
+ *pin_mask |= BIT(i);
- if (!HAS_GMCH_DISPLAY(dev_priv)) {
- dig_shift = pch_port_to_hotplug_shift(port);
- long_hpd = (dig_hotplug_reg >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
- } else {
- dig_shift = i915_port_to_hotplug_shift(port);
- long_hpd = (hotplug_trigger >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
- }
-
- DRM_DEBUG_DRIVER("digital hpd port %c - %s\n",
- port_name(port),
- long_hpd ? "long" : "short");
- /* for long HPD pulses we want to have the digital queue happen,
- but we still want HPD storm detection to function. */
- if (long_hpd) {
- dev_priv->long_hpd_port_mask |= (1 << port);
- dig_port_mask |= hpd[i];
- } else {
- /* for short HPD just trigger the digital queue */
- dev_priv->short_hpd_port_mask |= (1 << port);
- hotplug_trigger &= ~hpd[i];
- }
- queue_dig = true;
- }
+ port = intel_hpd_pin_to_port(i);
+ if (pch_port_hotplug_long_detect(port, dig_hotplug_reg))
+ *long_mask |= BIT(i);
}
- for (i = 1; i < HPD_NUM_PINS; i++) {
- if (hpd[i] & hotplug_trigger &&
- dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED) {
- /*
- * On GMCH platforms the interrupt mask bits only
- * prevent irq generation, not the setting of the
- * hotplug bits itself. So only WARN about unexpected
- * interrupts on saner platforms.
- */
- WARN_ONCE(INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev),
- "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n",
- hotplug_trigger, i, hpd[i]);
+ DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x\n",
+ hotplug_trigger, dig_hotplug_reg, *pin_mask);
- continue;
- }
+}
+
+/* Get a bit mask of pins that have triggered, and which ones may be long. */
+static void i9xx_get_hpd_pins(u32 *pin_mask, u32 *long_mask,
+ u32 hotplug_trigger, const u32 hpd[HPD_NUM_PINS])
+{
+ enum port port;
+ int i;
+
+ *pin_mask = 0;
+ *long_mask = 0;
+
+ if (!hotplug_trigger)
+ return;
- if (!(hpd[i] & hotplug_trigger) ||
- dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED)
+ for_each_hpd_pin(i) {
+ if ((hpd[i] & hotplug_trigger) == 0)
continue;
- if (!(dig_port_mask & hpd[i])) {
- dev_priv->hpd_event_bits |= (1 << i);
- queue_hp = true;
- }
+ *pin_mask |= BIT(i);
- if (!time_in_range(jiffies, dev_priv->hpd_stats[i].hpd_last_jiffies,
- dev_priv->hpd_stats[i].hpd_last_jiffies
- + msecs_to_jiffies(HPD_STORM_DETECT_PERIOD))) {
- dev_priv->hpd_stats[i].hpd_last_jiffies = jiffies;
- dev_priv->hpd_stats[i].hpd_cnt = 0;
- DRM_DEBUG_KMS("Received HPD interrupt on PIN %d - cnt: 0\n", i);
- } else if (dev_priv->hpd_stats[i].hpd_cnt > HPD_STORM_THRESHOLD) {
- dev_priv->hpd_stats[i].hpd_mark = HPD_MARK_DISABLED;
- dev_priv->hpd_event_bits &= ~(1 << i);
- DRM_DEBUG_KMS("HPD interrupt storm detected on PIN %d\n", i);
- storm_detected = true;
- } else {
- dev_priv->hpd_stats[i].hpd_cnt++;
- DRM_DEBUG_KMS("Received HPD interrupt on PIN %d - cnt: %d\n", i,
- dev_priv->hpd_stats[i].hpd_cnt);
- }
+ port = intel_hpd_pin_to_port(i);
+ if (i9xx_port_hotplug_long_detect(port, hotplug_trigger))
+ *long_mask |= BIT(i);
}
- if (storm_detected)
- dev_priv->display.hpd_irq_setup(dev);
- spin_unlock(&dev_priv->irq_lock);
-
- /*
- * Our hotplug handler can grab modeset locks (by calling down into the
- * fb helpers). Hence it must not be run on our own dev-priv->wq work
- * queue for otherwise the flush_work in the pageflip code will
- * deadlock.
- */
- if (queue_dig)
- queue_work(dev_priv->dp_wq, &dev_priv->dig_port_work);
- if (queue_hp)
- schedule_work(&dev_priv->hotplug_work);
+ DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, pins 0x%08x\n",
+ hotplug_trigger, *pin_mask);
}
static void gmbus_irq_handler(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+ u32 pin_mask, long_mask;
- if (hotplug_status) {
- I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
- /*
- * Make sure hotplug status is cleared before we clear IIR, or else we
- * may miss hotplug events.
- */
- POSTING_READ(PORT_HOTPLUG_STAT);
+ if (!hotplug_status)
+ return;
- if (IS_G4X(dev) || IS_VALLEYVIEW(dev)) {
- u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
+ I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+ /*
+ * Make sure hotplug status is cleared before we clear IIR, or else we
+ * may miss hotplug events.
+ */
+ POSTING_READ(PORT_HOTPLUG_STAT);
- intel_hpd_irq_handler(dev, hotplug_trigger, 0, hpd_status_g4x);
- } else {
- u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
+ if (IS_G4X(dev) || IS_VALLEYVIEW(dev)) {
+ u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
- intel_hpd_irq_handler(dev, hotplug_trigger, 0, hpd_status_i915);
- }
+ i9xx_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, hpd_status_g4x);
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
- if ((IS_G4X(dev) || IS_VALLEYVIEW(dev)) &&
- hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
+ if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
dp_aux_irq_handler(dev);
+ } else {
+ u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
+
+ i9xx_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, hpd_status_i915);
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
}
}
struct drm_i915_private *dev_priv = dev->dev_private;
int pipe;
u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK;
- u32 dig_hotplug_reg;
- dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
- I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
+ if (hotplug_trigger) {
+ u32 dig_hotplug_reg, pin_mask, long_mask;
+
+ dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
+ I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
- intel_hpd_irq_handler(dev, hotplug_trigger, dig_hotplug_reg, hpd_ibx);
+ pch_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ dig_hotplug_reg, hpd_ibx);
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+ }
if (pch_iir & SDE_AUDIO_POWER_MASK) {
int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK) >>
struct drm_i915_private *dev_priv = dev->dev_private;
int pipe;
u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT;
- u32 dig_hotplug_reg;
- dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
- I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
+ if (hotplug_trigger) {
+ u32 dig_hotplug_reg, pin_mask, long_mask;
- intel_hpd_irq_handler(dev, hotplug_trigger, dig_hotplug_reg, hpd_cpt);
+ dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
+ I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
+ pch_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ dig_hotplug_reg, hpd_cpt);
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+ }
if (pch_iir & SDE_AUDIO_POWER_MASK_CPT) {
int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK_CPT) >>
static void bxt_hpd_handler(struct drm_device *dev, uint32_t iir_status)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- uint32_t hp_control;
- uint32_t hp_trigger;
+ u32 hp_control, hp_trigger;
+ u32 pin_mask, long_mask;
/* Get the status */
hp_trigger = iir_status & BXT_DE_PORT_HOTPLUG_MASK;
return;
}
- DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x\n",
- hp_control & BXT_HOTPLUG_CTL_MASK);
-
- /* Check for HPD storm and schedule bottom half */
- intel_hpd_irq_handler(dev, hp_trigger, hp_control, hpd_bxt);
-
- /*
- * FIXME: Save the hot plug status for bottom half before
- * clearing the sticky status bits, else the status will be
- * lost.
- */
-
/* Clear sticky bits in hpd status */
I915_WRITE(BXT_HOTPLUG_CTL, hp_control);
+
+ pch_get_hpd_pins(&pin_mask, &long_mask, hp_trigger, hp_control, hpd_bxt);
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
}
static irqreturn_t gen8_irq_handler(int irq, void *arg)
spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
}
- static struct drm_i915_gem_request *
- ring_last_request(struct intel_engine_cs *ring)
- {
- return list_entry(ring->request_list.prev,
- struct drm_i915_gem_request, list);
- }
-
static bool
- ring_idle(struct intel_engine_cs *ring)
+ ring_idle(struct intel_engine_cs *ring, u32 seqno)
{
return (list_empty(&ring->request_list) ||
- i915_gem_request_completed(ring_last_request(ring), false));
+ i915_seqno_passed(seqno, ring->last_submitted_seqno));
}
static bool
acthd = intel_ring_get_active_head(ring);
if (ring->hangcheck.seqno == seqno) {
- if (ring_idle(ring)) {
+ if (ring_idle(ring, seqno)) {
ring->hangcheck.action = HANGCHECK_IDLE;
if (waitqueue_active(&ring->irq_queue)) {
if (HAS_PCH_IBX(dev)) {
hotplug_irqs = SDE_HOTPLUG_MASK;
for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
+ if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
enabled_irqs |= hpd_ibx[intel_encoder->hpd_pin];
} else {
hotplug_irqs = SDE_HOTPLUG_MASK_CPT;
for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
+ if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
enabled_irqs |= hpd_cpt[intel_encoder->hpd_pin];
}
/* Now, enable HPD */
for_each_intel_encoder(dev, intel_encoder) {
- if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark
+ if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state
== HPD_ENABLED)
hotplug_port |= hpd_bxt[intel_encoder->hpd_pin];
}
/* Note HDMI and DP share hotplug bits */
/* enable bits are the same for all generations */
for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
+ if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
hotplug_en |= hpd_mask_i915[intel_encoder->hpd_pin];
/* Programming the CRT detection parameters tends
to generate a spurious hotplug event about three
I915_WRITE(IIR, I915_READ(IIR));
}
-static void intel_hpd_irq_reenable_work(struct work_struct *work)
-{
- struct drm_i915_private *dev_priv =
- container_of(work, typeof(*dev_priv),
- hotplug_reenable_work.work);
- struct drm_device *dev = dev_priv->dev;
- struct drm_mode_config *mode_config = &dev->mode_config;
- int i;
-
- intel_runtime_pm_get(dev_priv);
-
- spin_lock_irq(&dev_priv->irq_lock);
- for (i = (HPD_NONE + 1); i < HPD_NUM_PINS; i++) {
- struct drm_connector *connector;
-
- if (dev_priv->hpd_stats[i].hpd_mark != HPD_DISABLED)
- continue;
-
- dev_priv->hpd_stats[i].hpd_mark = HPD_ENABLED;
-
- list_for_each_entry(connector, &mode_config->connector_list, head) {
- struct intel_connector *intel_connector = to_intel_connector(connector);
-
- if (intel_connector->encoder->hpd_pin == i) {
- if (connector->polled != intel_connector->polled)
- DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n",
- connector->name);
- connector->polled = intel_connector->polled;
- if (!connector->polled)
- connector->polled = DRM_CONNECTOR_POLL_HPD;
- }
- }
- }
- if (dev_priv->display.hpd_irq_setup)
- dev_priv->display.hpd_irq_setup(dev);
- spin_unlock_irq(&dev_priv->irq_lock);
-
- intel_runtime_pm_put(dev_priv);
-}
-
/**
* intel_irq_init - initializes irq support
* @dev_priv: i915 device instance
{
struct drm_device *dev = dev_priv->dev;
- INIT_WORK(&dev_priv->hotplug_work, i915_hotplug_work_func);
- INIT_WORK(&dev_priv->dig_port_work, i915_digport_work_func);
+ intel_hpd_init_work(dev_priv);
+
INIT_WORK(&dev_priv->rps.work, gen6_pm_rps_work);
INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work);
INIT_DELAYED_WORK(&dev_priv->gpu_error.hangcheck_work,
i915_hangcheck_elapsed);
- INIT_DELAYED_WORK(&dev_priv->hotplug_reenable_work,
- intel_hpd_irq_reenable_work);
pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE);
}
}
-/**
- * intel_hpd_init - initializes and enables hpd support
- * @dev_priv: i915 device instance
- *
- * This function enables the hotplug support. It requires that interrupts have
- * already been enabled with intel_irq_init_hw(). From this point on hotplug and
- * poll request can run concurrently to other code, so locking rules must be
- * obeyed.
- *
- * This is a separate step from interrupt enabling to simplify the locking rules
- * in the driver load and resume code.
- */
-void intel_hpd_init(struct drm_i915_private *dev_priv)
-{
- struct drm_device *dev = dev_priv->dev;
- struct drm_mode_config *mode_config = &dev->mode_config;
- struct drm_connector *connector;
- int i;
-
- for (i = 1; i < HPD_NUM_PINS; i++) {
- dev_priv->hpd_stats[i].hpd_cnt = 0;
- dev_priv->hpd_stats[i].hpd_mark = HPD_ENABLED;
- }
- list_for_each_entry(connector, &mode_config->connector_list, head) {
- struct intel_connector *intel_connector = to_intel_connector(connector);
- connector->polled = intel_connector->polled;
- if (connector->encoder && !connector->polled && I915_HAS_HOTPLUG(dev) && intel_connector->encoder->hpd_pin > HPD_NONE)
- connector->polled = DRM_CONNECTOR_POLL_HPD;
- if (intel_connector->mst_port)
- connector->polled = DRM_CONNECTOR_POLL_HPD;
- }
-
- /* Interrupt setup is already guaranteed to be single-threaded, this is
- * just to make the assert_spin_locked checks happy. */
- spin_lock_irq(&dev_priv->irq_lock);
- if (dev_priv->display.hpd_irq_setup)
- dev_priv->display.hpd_irq_setup(dev);
- spin_unlock_irq(&dev_priv->irq_lock);
-}
-
/**
* intel_irq_install - enables the hardware interrupt
* @dev_priv: i915 device instance
/* PCI config space */
-#define HPLLCC 0xc0 /* 855 only */
-#define GC_CLOCK_CONTROL_MASK (0xf << 0)
+#define HPLLCC 0xc0 /* 85x only */
+#define GC_CLOCK_CONTROL_MASK (0x7 << 0)
#define GC_CLOCK_133_200 (0 << 0)
#define GC_CLOCK_100_200 (1 << 0)
#define GC_CLOCK_100_133 (2 << 0)
-#define GC_CLOCK_166_250 (3 << 0)
+#define GC_CLOCK_133_266 (3 << 0)
+#define GC_CLOCK_133_200_2 (4 << 0)
+#define GC_CLOCK_133_266_2 (5 << 0)
+#define GC_CLOCK_166_266 (6 << 0)
+#define GC_CLOCK_166_250 (7 << 0)
+
#define GCFGC2 0xda
#define GCFGC 0xf0 /* 915+ only */
#define GC_LOW_FREQUENCY_ENABLE (1 << 7)
#define GAM_ECOCHK 0x4090
#define BDW_DISABLE_HDC_INVALIDATION (1<<25)
#define ECOCHK_SNB_BIT (1<<10)
+#define ECOCHK_DIS_TLB (1<<8)
#define HSW_ECOCHK_ARB_PRIO_SOL (1<<6)
#define ECOCHK_PPGTT_CACHE64B (0x3<<3)
#define ECOCHK_PPGTT_CACHE4B (0x0<<3)
#define MI_RESTORE_EXT_STATE_EN (1<<2)
#define MI_FORCE_RESTORE (1<<1)
#define MI_RESTORE_INHIBIT (1<<0)
+#define HSW_MI_RS_SAVE_STATE_EN (1<<3)
+#define HSW_MI_RS_RESTORE_STATE_EN (1<<2)
#define MI_SEMAPHORE_SIGNAL MI_INSTR(0x1b, 0) /* GEN8+ */
#define MI_SEMAPHORE_TARGET(engine) ((engine)<<15)
#define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */
#define MI_INVALIDATE_BSD (1<<7)
#define MI_FLUSH_DW_USE_GTT (1<<2)
#define MI_FLUSH_DW_USE_PPGTT (0<<2)
+#define MI_LOAD_REGISTER_MEM(x) MI_INSTR(0x29, 2*(x)-1)
+#define MI_LOAD_REGISTER_MEM_GEN8(x) MI_INSTR(0x29, 3*(x)-1)
#define MI_BATCH_BUFFER MI_INSTR(0x30, 1)
#define MI_BATCH_NON_SECURE (1)
/* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
#define MI_BATCH_BUFFER_START MI_INSTR(0x31, 0)
#define MI_BATCH_GTT (2<<6) /* aliased with (1<<7) on gen4 */
#define MI_BATCH_BUFFER_START_GEN8 MI_INSTR(0x31, 1)
+#define MI_BATCH_RESOURCE_STREAMER (1<<10)
#define MI_PREDICATE_SRC0 (0x2400)
#define MI_PREDICATE_SRC1 (0x2408)
#define DISPLAY_PLANE_A (0<<20)
#define DISPLAY_PLANE_B (1<<20)
#define GFX_OP_PIPE_CONTROL(len) ((0x3<<29)|(0x3<<27)|(0x2<<24)|(len-2))
+#define PIPE_CONTROL_FLUSH_L3 (1<<27)
#define PIPE_CONTROL_GLOBAL_GTT_IVB (1<<24) /* gen7+ */
#define PIPE_CONTROL_MMIO_WRITE (1<<23)
#define PIPE_CONTROL_STORE_DATA_INDEX (1<<21)
#define PIPE_CONTROL_INDIRECT_STATE_DISABLE (1<<9)
#define PIPE_CONTROL_NOTIFY (1<<8)
#define PIPE_CONTROL_FLUSH_ENABLE (1<<7) /* gen7+ */
+#define PIPE_CONTROL_DC_FLUSH_ENABLE (1<<5)
#define PIPE_CONTROL_VF_CACHE_INVALIDATE (1<<4)
#define PIPE_CONTROL_CONST_CACHE_INVALIDATE (1<<3)
#define PIPE_CONTROL_STATE_CACHE_INVALIDATE (1<<2)
#define MI_CLFLUSH MI_INSTR(0x27, 0)
#define MI_REPORT_PERF_COUNT MI_INSTR(0x28, 0)
#define MI_REPORT_PERF_COUNT_GGTT (1<<0)
-#define MI_LOAD_REGISTER_MEM MI_INSTR(0x29, 0)
#define MI_LOAD_REGISTER_REG MI_INSTR(0x2A, 0)
#define MI_RS_STORE_DATA_IMM MI_INSTR(0x2B, 0)
#define MI_LOAD_URB_MEM MI_INSTR(0x2C, 0)
#define _PORT_PLL_EBB_0_A 0x162034
#define _PORT_PLL_EBB_0_B 0x6C034
#define _PORT_PLL_EBB_0_C 0x6C340
-#define PORT_PLL_P1_MASK (0x07 << 13)
-#define PORT_PLL_P1(x) ((x) << 13)
-#define PORT_PLL_P2_MASK (0x1f << 8)
-#define PORT_PLL_P2(x) ((x) << 8)
+#define PORT_PLL_P1_SHIFT 13
+#define PORT_PLL_P1_MASK (0x07 << PORT_PLL_P1_SHIFT)
+#define PORT_PLL_P1(x) ((x) << PORT_PLL_P1_SHIFT)
+#define PORT_PLL_P2_SHIFT 8
+#define PORT_PLL_P2_MASK (0x1f << PORT_PLL_P2_SHIFT)
+#define PORT_PLL_P2(x) ((x) << PORT_PLL_P2_SHIFT)
#define BXT_PORT_PLL_EBB_0(port) _PORT3(port, _PORT_PLL_EBB_0_A, \
_PORT_PLL_EBB_0_B, \
_PORT_PLL_EBB_0_C)
/* PORT_PLL_0_A */
#define PORT_PLL_M2_MASK 0xFF
/* PORT_PLL_1_A */
-#define PORT_PLL_N_MASK (0x0F << 8)
-#define PORT_PLL_N(x) ((x) << 8)
+#define PORT_PLL_N_SHIFT 8
+#define PORT_PLL_N_MASK (0x0F << PORT_PLL_N_SHIFT)
+#define PORT_PLL_N(x) ((x) << PORT_PLL_N_SHIFT)
/* PORT_PLL_2_A */
#define PORT_PLL_M2_FRAC_MASK 0x3FFFFF
/* PORT_PLL_3_A */
/* PORT_PLL_8_A */
#define PORT_PLL_TARGET_CNT_MASK 0x3FF
/* PORT_PLL_9_A */
-#define PORT_PLL_LOCK_THRESHOLD_MASK 0xe
+#define PORT_PLL_LOCK_THRESHOLD_SHIFT 1
+#define PORT_PLL_LOCK_THRESHOLD_MASK (0x7 << PORT_PLL_LOCK_THRESHOLD_SHIFT)
/* PORT_PLL_10_A */
#define PORT_PLL_DCO_AMP_OVR_EN_H (1<<27)
+#define PORT_PLL_DCO_AMP_DEFAULT 15
#define PORT_PLL_DCO_AMP_MASK 0x3c00
#define PORT_PLL_DCO_AMP(x) (x<<10)
#define _PORT_PLL_BASE(port) _PORT3(port, _PORT_PLL_0_A, \
_PORT_TX_DW14_LN0_C) + \
_BXT_LANE_OFFSET(lane))
+/* UAIMI scratch pad register 1 */
+#define UAIMI_SPR1 0x4F074
+/* SKL VccIO mask */
+#define SKL_VCCIO_MASK 0x1
+/* SKL balance leg register */
+#define DISPIO_CR_TX_BMU_CR0 0x6C00C
+/* I_boost values */
+#define BALANCE_LEG_SHIFT(port) (8+3*(port))
+#define BALANCE_LEG_MASK(port) (7<<(8+3*(port)))
+/* Balance leg disable bits */
+#define BALANCE_LEG_DISABLE_SHIFT 23
+
/*
* Fence registers
*/
#define RING_MAX_IDLE(base) ((base)+0x54)
#define RING_HWS_PGA(base) ((base)+0x80)
#define RING_HWS_PGA_GEN6(base) ((base)+0x2080)
+#define RING_RESET_CTL(base) ((base)+0xd0)
+#define RESET_CTL_REQUEST_RESET (1 << 0)
+#define RESET_CTL_READY_TO_RESET (1 << 1)
#define HSW_GTT_CACHE_EN 0x4024
#define GTT_CACHE_EN_ALL 0xF0007FFF
#define FBC_FENCE_OFF 0x03218 /* BSpec typo has 321Bh */
#define FBC_TAG 0x03300
+#define FBC_STATUS2 0x43214
+#define FBC_COMPRESSION_MASK 0x7ff
+
#define FBC_LL_SIZE (1536)
/* Framebuffer compression for GM45+ */
#define DPLL_DVO_2X_MODE (1 << 30)
#define DPLL_EXT_BUFFER_ENABLE_VLV (1 << 30)
#define DPLL_SYNCLOCK_ENABLE (1 << 29)
-#define DPLL_REFA_CLK_ENABLE_VLV (1 << 29)
+#define DPLL_REF_CLK_ENABLE_VLV (1 << 29)
#define DPLL_VGA_MODE_DIS (1 << 28)
#define DPLLB_MODE_DAC_SERIAL (1 << 26) /* i915 */
#define DPLLB_MODE_LVDS (2 << 26) /* i915 */
#define DPLL_FPA01_P1_POST_DIV_MASK_PINEVIEW 0x00ff8000 /* Pineview */
#define DPLL_LOCK_VLV (1<<15)
#define DPLL_INTEGRATED_CRI_CLK_VLV (1<<14)
-#define DPLL_INTEGRATED_CLOCK_VLV (1<<13)
-#define DPLL_SSC_REF_CLOCK_CHV (1<<13)
+#define DPLL_INTEGRATED_REF_CLK_VLV (1<<13)
+#define DPLL_SSC_REF_CLK_CHV (1<<13)
#define DPLL_PORTC_READY_MASK (0xf << 4)
#define DPLL_PORTB_READY_MASK (0xf)
#define CLKCFG_MEM_800 (3 << 4)
#define CLKCFG_MEM_MASK (7 << 4)
+#define HPLLVCO (MCHBAR_MIRROR_BASE + 0xc38)
+#define HPLLVCO_MOBILE (MCHBAR_MIRROR_BASE + 0xc0f)
+
#define TSC1 0x11001
#define TSE (1<<0)
#define TR1 0x11006
#define GEN6_GT_THREAD_STATUS_CORE_MASK 0x7
#define GEN6_GT_PERF_STATUS (MCHBAR_MIRROR_BASE_SNB + 0x5948)
+#define BXT_GT_PERF_STATUS (MCHBAR_MIRROR_BASE_SNB + 0x7070)
#define GEN6_RP_STATE_LIMITS (MCHBAR_MIRROR_BASE_SNB + 0x5994)
#define GEN6_RP_STATE_CAP (MCHBAR_MIRROR_BASE_SNB + 0x5998)
+#define BXT_RP_STATE_CAP 0x138170
#define INTERVAL_1_28_US(us) (((us) * 100) >> 7)
#define INTERVAL_1_33_US(us) (((us) * 3) >> 2)
* valid. Now, docs explain in dwords what is in the context object. The full
* size is 70720 bytes, however, the power context and execlist context will
* never be saved (power context is stored elsewhere, and execlists don't work
- * on HSW) - so the final size is 66944 bytes, which rounds to 17 pages.
+ * on HSW) - so the final size, including the extra state required for the
+ * Resource Streamer, is 66944 bytes, which rounds to 17 pages.
*/
#define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE)
/* Same as Haswell, but 72064 bytes now. */
#define BLM_POLARITY_PNV (1 << 0) /* pnv only */
#define BLC_HIST_CTL (dev_priv->info.display_mmio_offset + 0x61260)
+ #define BLM_HISTOGRAM_ENABLE (1 << 31)
/* New registers for PCH-split platforms. Safe where new bits show up, the
* register layout machtes with gen4 BLC_PWM_CTL[12]. */
#define DSPARB_BSTART_SHIFT 0
#define DSPARB_BEND_SHIFT 9 /* on 855 */
#define DSPARB_AEND_SHIFT 0
-
+#define DSPARB_SPRITEA_SHIFT_VLV 0
+#define DSPARB_SPRITEA_MASK_VLV (0xff << 0)
+#define DSPARB_SPRITEB_SHIFT_VLV 8
+#define DSPARB_SPRITEB_MASK_VLV (0xff << 8)
+#define DSPARB_SPRITEC_SHIFT_VLV 16
+#define DSPARB_SPRITEC_MASK_VLV (0xff << 16)
+#define DSPARB_SPRITED_SHIFT_VLV 24
+#define DSPARB_SPRITED_MASK_VLV (0xff << 24)
#define DSPARB2 (VLV_DISPLAY_BASE + 0x70060) /* vlv/chv */
+#define DSPARB_SPRITEA_HI_SHIFT_VLV 0
+#define DSPARB_SPRITEA_HI_MASK_VLV (0x1 << 0)
+#define DSPARB_SPRITEB_HI_SHIFT_VLV 4
+#define DSPARB_SPRITEB_HI_MASK_VLV (0x1 << 4)
+#define DSPARB_SPRITEC_HI_SHIFT_VLV 8
+#define DSPARB_SPRITEC_HI_MASK_VLV (0x1 << 8)
+#define DSPARB_SPRITED_HI_SHIFT_VLV 12
+#define DSPARB_SPRITED_HI_MASK_VLV (0x1 << 12)
+#define DSPARB_SPRITEE_HI_SHIFT_VLV 16
+#define DSPARB_SPRITEE_HI_MASK_VLV (0x1 << 16)
+#define DSPARB_SPRITEF_HI_SHIFT_VLV 20
+#define DSPARB_SPRITEF_HI_MASK_VLV (0x1 << 20)
#define DSPARB3 (VLV_DISPLAY_BASE + 0x7006c) /* chv */
+#define DSPARB_SPRITEE_SHIFT_VLV 0
+#define DSPARB_SPRITEE_MASK_VLV (0xff << 0)
+#define DSPARB_SPRITEF_SHIFT_VLV 8
+#define DSPARB_SPRITEF_MASK_VLV (0xff << 8)
/* pnv/gen4/g4x/vlv/chv */
#define DSPFW1 (dev_priv->info.display_mmio_offset + 0x70034)
#define HSW_NDE_RSTWRN_OPT 0x46408
#define RESET_PCH_HANDSHAKE_ENABLE (1<<4)
+#define SKL_DFSM 0x51000
+#define SKL_DFSM_CDCLK_LIMIT_MASK (3 << 23)
+#define SKL_DFSM_CDCLK_LIMIT_675 (0 << 23)
+#define SKL_DFSM_CDCLK_LIMIT_540 (1 << 23)
+#define SKL_DFSM_CDCLK_LIMIT_450 (2 << 23)
+#define SKL_DFSM_CDCLK_LIMIT_337_5 (3 << 23)
+
#define FF_SLICE_CS_CHICKEN2 0x20e4
#define GEN9_TSG_BARRIER_ACK_DISABLE (1<<8)
#define GEN8_L3SQCREG4 0xb118
#define GEN8_LQSC_RO_PERF_DIS (1<<27)
+#define GEN8_LQSC_FLUSH_COHERENT_LINES (1<<21)
/* GEN8 chicken */
#define HDC_CHICKEN0 0x7300
#define _VIDEO_DIP_CTL_A 0xe0200
#define _VIDEO_DIP_DATA_A 0xe0208
#define _VIDEO_DIP_GCP_A 0xe0210
+#define GCP_COLOR_INDICATION (1 << 2)
+#define GCP_DEFAULT_PHASE_ENABLE (1 << 1)
+#define GCP_AV_MUTE (1 << 0)
#define _VIDEO_DIP_CTL_B 0xe1200
#define _VIDEO_DIP_DATA_B 0xe1208
#define _TRANSA_CHICKEN1 0xf0060
#define _TRANSB_CHICKEN1 0xf1060
#define TRANS_CHICKEN1(pipe) _PIPE(pipe, _TRANSA_CHICKEN1, _TRANSB_CHICKEN1)
+#define TRANS_CHICKEN1_HDMIUNIT_GC_DISABLE (1<<10)
#define TRANS_CHICKEN1_DP0UNIT_GC_DISABLE (1<<4)
#define _TRANSA_CHICKEN2 0xf0064
#define _TRANSB_CHICKEN2 0xf1064
#define PCH_PP_CONTROL 0xc7204
#define PANEL_UNLOCK_REGS (0xabcd << 16)
#define PANEL_UNLOCK_MASK (0xffff << 16)
+#define BXT_POWER_CYCLE_DELAY_MASK (0x1f0)
+#define BXT_POWER_CYCLE_DELAY_SHIFT 4
#define EDP_FORCE_VDD (1 << 3)
#define EDP_BLC_ENABLE (1 << 2)
#define PANEL_POWER_RESET (1 << 1)
#define PANEL_POWER_CYCLE_DELAY_MASK (0x1f)
#define PANEL_POWER_CYCLE_DELAY_SHIFT 0
+/* BXT PPS changes - 2nd set of PPS registers */
+#define _BXT_PP_STATUS2 0xc7300
+#define _BXT_PP_CONTROL2 0xc7304
+#define _BXT_PP_ON_DELAYS2 0xc7308
+#define _BXT_PP_OFF_DELAYS2 0xc730c
+
+#define BXT_PP_STATUS(n) ((!n) ? PCH_PP_STATUS : _BXT_PP_STATUS2)
+#define BXT_PP_CONTROL(n) ((!n) ? PCH_PP_CONTROL : _BXT_PP_CONTROL2)
+#define BXT_PP_ON_DELAYS(n) ((!n) ? PCH_PP_ON_DELAYS : _BXT_PP_ON_DELAYS2)
+#define BXT_PP_OFF_DELAYS(n) ((!n) ? PCH_PP_OFF_DELAYS : _BXT_PP_OFF_DELAYS2)
+
#define PCH_DP_B 0xe4100
#define PCH_DPB_AUX_CH_CTL 0xe4110
#define PCH_DPB_AUX_CH_DATA1 0xe4114
#define GEN6_PCODE_READ_RC6VIDS 0x5
#define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5)
#define GEN6_DECODE_RC6_VID(vids) (((vids) * 5) + 245)
+#define BDW_PCODE_DISPLAY_FREQ_CHANGE_REQ 0x18
#define GEN9_PCODE_READ_MEM_LATENCY 0x6
#define GEN9_MEM_LATENCY_LEVEL_MASK 0xFF
#define GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT 8
#define AUDIO_CP_READY(trans) ((1 << 1) << ((trans) * 4))
#define AUDIO_ELD_VALID(trans) ((1 << 0) << ((trans) * 4))
+ #define HSW_AUD_CHICKENBIT 0x65f10
+ #define SKL_AUD_CODEC_WAKE_SIGNAL (1 << 15)
+
/* HSW Power Wells */
#define HSW_PWR_WELL_BIOS 0x45400 /* CTL1 */
#define HSW_PWR_WELL_DRIVER 0x45404 /* CTL2 */
#define LCPLL_CLK_FREQ_337_5_BDW (2<<26)
#define LCPLL_CLK_FREQ_675_BDW (3<<26)
#define LCPLL_CD_CLOCK_DISABLE (1<<25)
+#define LCPLL_ROOT_CD_CLOCK_DISABLE (1<<24)
#define LCPLL_CD2X_CLOCK_DISABLE (1<<23)
#define LCPLL_POWER_DOWN_ALLOW (1<<22)
#define LCPLL_CD_SOURCE_FCLK (1<<21)
#define DC_STATE_EN 0x45504
#define DC_STATE_EN_UPTO_DC5 (1<<0)
#define DC_STATE_EN_DC9 (1<<3)
-
-/*
-* SKL DC
-*/
-#define DC_STATE_EN 0x45504
-#define DC_STATE_EN_UPTO_DC5 (1<<0)
#define DC_STATE_EN_UPTO_DC6 (2<<0)
#define DC_STATE_EN_UPTO_DC5_DC6_MASK 0x3
#define _PALETTE_A (dev_priv->info.display_mmio_offset + 0xa000)
#define _PALETTE_B (dev_priv->info.display_mmio_offset + 0xa800)
+/* MOCS (Memory Object Control State) registers */
+#define GEN9_LNCFCMOCS0 0xb020 /* L3 Cache Control base */
+
+#define GEN9_GFX_MOCS_0 0xc800 /* Graphics MOCS base register*/
+#define GEN9_MFX0_MOCS_0 0xc900 /* Media 0 MOCS base register*/
+#define GEN9_MFX1_MOCS_0 0xca00 /* Media 1 MOCS base register*/
+#define GEN9_VEBOX_MOCS_0 0xcb00 /* Video MOCS base register*/
+#define GEN9_BLT_MOCS_0 0xcc00 /* Blitter MOCS base register*/
+
#endif /* _I915_REG_H_ */
);
TRACE_EVENT(i915_gem_ring_sync_to,
- TP_PROTO(struct intel_engine_cs *from,
- struct intel_engine_cs *to,
+ TP_PROTO(struct drm_i915_gem_request *to_req,
+ struct intel_engine_cs *from,
struct drm_i915_gem_request *req),
- TP_ARGS(from, to, req),
+ TP_ARGS(to_req, from, req),
TP_STRUCT__entry(
__field(u32, dev)
TP_fast_assign(
__entry->dev = from->dev->primary->index;
__entry->sync_from = from->id;
- __entry->sync_to = to->id;
+ __entry->sync_to = to_req->ring->id;
__entry->seqno = i915_gem_request_get_seqno(req);
),
);
TRACE_EVENT(i915_gem_ring_flush,
- TP_PROTO(struct intel_engine_cs *ring, u32 invalidate, u32 flush),
- TP_ARGS(ring, invalidate, flush),
+ TP_PROTO(struct drm_i915_gem_request *req, u32 invalidate, u32 flush),
+ TP_ARGS(req, invalidate, flush),
TP_STRUCT__entry(
__field(u32, dev)
),
TP_fast_assign(
- __entry->dev = ring->dev->primary->index;
- __entry->ring = ring->id;
+ __entry->dev = req->ring->dev->primary->index;
+ __entry->ring = req->ring->id;
__entry->invalidate = invalidate;
__entry->flush = flush;
),
TP_fast_assign(
__entry->ctx = ctx;
__entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL;
- __entry->dev = ctx->file_priv->dev_priv->dev->primary->index;
+ __entry->dev = ctx->i915->dev->primary->index;
),
TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
*
* The disable sequences must be performed before disabling the transcoder or
* port. The enable sequences may only be performed after enabling the
- * transcoder and port, and after completed link training.
+ * transcoder and port, and after completed link training. Therefore the audio
+ * enable/disable sequences are part of the modeset sequence.
*
* The codec and controller sequences could be done either parallel or serial,
* but generally the ELDV/PD change in the codec sequence indicates to the audio
intel_display_power_put(dev_to_i915(dev), POWER_DOMAIN_AUDIO);
}
+ static void i915_audio_component_codec_wake_override(struct device *dev,
+ bool enable)
+ {
+ struct drm_i915_private *dev_priv = dev_to_i915(dev);
+ u32 tmp;
+
+ if (!IS_SKYLAKE(dev_priv))
+ return;
+
+ /*
+ * Enable/disable generating the codec wake signal, overriding the
+ * internal logic to generate the codec wake to controller.
+ */
+ tmp = I915_READ(HSW_AUD_CHICKENBIT);
+ tmp &= ~SKL_AUD_CODEC_WAKE_SIGNAL;
+ I915_WRITE(HSW_AUD_CHICKENBIT, tmp);
+ usleep_range(1000, 1500);
+
+ if (enable) {
+ tmp = I915_READ(HSW_AUD_CHICKENBIT);
+ tmp |= SKL_AUD_CODEC_WAKE_SIGNAL;
+ I915_WRITE(HSW_AUD_CHICKENBIT, tmp);
+ usleep_range(1000, 1500);
+ }
+ }
+
/* Get CDCLK in kHz */
static int i915_audio_component_get_cdclk_freq(struct device *dev)
{
.owner = THIS_MODULE,
.get_power = i915_audio_component_get_power,
.put_power = i915_audio_component_put_power,
+ .codec_wake_override = i915_audio_component_codec_wake_override,
.get_cdclk_freq = i915_audio_component_get_cdclk_freq,
};
static void ironlake_pch_clock_get(struct intel_crtc *crtc,
struct intel_crtc_state *pipe_config);
-static int intel_set_mode(struct drm_crtc *crtc,
- struct drm_atomic_state *state,
- bool force_restore);
static int intel_framebuffer_init(struct drm_device *dev,
struct intel_framebuffer *ifb,
struct drm_mode_fb_cmd2 *mode_cmd,
struct intel_crtc_state *crtc_state);
static int i9xx_get_refclk(const struct intel_crtc_state *crtc_state,
int num_connectors);
-static void intel_crtc_enable_planes(struct drm_crtc *crtc);
-static void intel_crtc_disable_planes(struct drm_crtc *crtc);
-
-static struct intel_encoder *intel_find_encoder(struct intel_connector *connector, int pipe)
-{
- if (!connector->mst_port)
- return connector->encoder;
- else
- return &connector->mst_port->mst_encoders[pipe]->base;
-}
+static void intel_modeset_setup_hw_state(struct drm_device *dev);
typedef struct {
int min, max;
static const intel_limit_t intel_limits_bxt = {
/* FIXME: find real dot limits */
.dot = { .min = 0, .max = INT_MAX },
- .vco = { .min = 4800000, .max = 6480000 },
+ .vco = { .min = 4800000, .max = 6700000 },
.n = { .min = 1, .max = 1 },
.m1 = { .min = 2, .max = 2 },
/* FIXME: find real m2 limits */
.p2 = { .p2_slow = 1, .p2_fast = 20 },
};
-static void vlv_clock(int refclk, intel_clock_t *clock)
+static bool
+needs_modeset(struct drm_crtc_state *state)
{
- clock->m = clock->m1 * clock->m2;
- clock->p = clock->p1 * clock->p2;
- if (WARN_ON(clock->n == 0 || clock->p == 0))
- return;
- clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n);
- clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
+ return state->mode_changed || state->active_changed;
}
/**
return limit;
}
+/*
+ * Platform specific helpers to calculate the port PLL loopback- (clock.m),
+ * and post-divider (clock.p) values, pre- (clock.vco) and post-divided fast
+ * (clock.dot) clock rates. This fast dot clock is fed to the port's IO logic.
+ * The helpers' return value is the rate of the clock that is fed to the
+ * display engine's pipe which can be the above fast dot clock rate or a
+ * divided-down version of it.
+ */
/* m1 is reserved as 0 in Pineview, n is a ring counter */
-static void pineview_clock(int refclk, intel_clock_t *clock)
+static int pnv_calc_dpll_params(int refclk, intel_clock_t *clock)
{
clock->m = clock->m2 + 2;
clock->p = clock->p1 * clock->p2;
if (WARN_ON(clock->n == 0 || clock->p == 0))
- return;
+ return 0;
clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n);
clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
+
+ return clock->dot;
}
static uint32_t i9xx_dpll_compute_m(struct dpll *dpll)
return 5 * (dpll->m1 + 2) + (dpll->m2 + 2);
}
-static void i9xx_clock(int refclk, intel_clock_t *clock)
+static int i9xx_calc_dpll_params(int refclk, intel_clock_t *clock)
{
clock->m = i9xx_dpll_compute_m(clock);
clock->p = clock->p1 * clock->p2;
if (WARN_ON(clock->n + 2 == 0 || clock->p == 0))
- return;
+ return 0;
clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n + 2);
clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
+
+ return clock->dot;
}
-static void chv_clock(int refclk, intel_clock_t *clock)
+static int vlv_calc_dpll_params(int refclk, intel_clock_t *clock)
{
clock->m = clock->m1 * clock->m2;
clock->p = clock->p1 * clock->p2;
if (WARN_ON(clock->n == 0 || clock->p == 0))
- return;
+ return 0;
+ clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n);
+ clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
+
+ return clock->dot / 5;
+}
+
+int chv_calc_dpll_params(int refclk, intel_clock_t *clock)
+{
+ clock->m = clock->m1 * clock->m2;
+ clock->p = clock->p1 * clock->p2;
+ if (WARN_ON(clock->n == 0 || clock->p == 0))
+ return 0;
clock->vco = DIV_ROUND_CLOSEST_ULL((uint64_t)refclk * clock->m,
clock->n << 22);
clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
+
+ return clock->dot / 5;
}
#define INTELPllInvalid(s) do { /* DRM_DEBUG(s); */ return false; } while (0)
return true;
}
-static bool
-i9xx_find_best_dpll(const intel_limit_t *limit,
- struct intel_crtc_state *crtc_state,
- int target, int refclk, intel_clock_t *match_clock,
- intel_clock_t *best_clock)
+static int
+i9xx_select_p2_div(const intel_limit_t *limit,
+ const struct intel_crtc_state *crtc_state,
+ int target)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
- struct drm_device *dev = crtc->base.dev;
- intel_clock_t clock;
- int err = target;
+ struct drm_device *dev = crtc_state->base.crtc->dev;
if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
/*
* single/dual channel state, if we even can.
*/
if (intel_is_dual_link_lvds(dev))
- clock.p2 = limit->p2.p2_fast;
+ return limit->p2.p2_fast;
else
- clock.p2 = limit->p2.p2_slow;
+ return limit->p2.p2_slow;
} else {
if (target < limit->p2.dot_limit)
- clock.p2 = limit->p2.p2_slow;
+ return limit->p2.p2_slow;
else
- clock.p2 = limit->p2.p2_fast;
+ return limit->p2.p2_fast;
}
+}
+
+static bool
+i9xx_find_best_dpll(const intel_limit_t *limit,
+ struct intel_crtc_state *crtc_state,
+ int target, int refclk, intel_clock_t *match_clock,
+ intel_clock_t *best_clock)
+{
+ struct drm_device *dev = crtc_state->base.crtc->dev;
+ intel_clock_t clock;
+ int err = target;
memset(best_clock, 0, sizeof(*best_clock));
+ clock.p2 = i9xx_select_p2_div(limit, crtc_state, target);
+
for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max;
clock.m1++) {
for (clock.m2 = limit->m2.min;
clock.p1 <= limit->p1.max; clock.p1++) {
int this_err;
- i9xx_clock(refclk, &clock);
+ i9xx_calc_dpll_params(refclk, &clock);
if (!intel_PLL_is_valid(dev, limit,
&clock))
continue;
int target, int refclk, intel_clock_t *match_clock,
intel_clock_t *best_clock)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
- struct drm_device *dev = crtc->base.dev;
+ struct drm_device *dev = crtc_state->base.crtc->dev;
intel_clock_t clock;
int err = target;
- if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
- /*
- * For LVDS just rely on its current settings for dual-channel.
- * We haven't figured out how to reliably set up different
- * single/dual channel state, if we even can.
- */
- if (intel_is_dual_link_lvds(dev))
- clock.p2 = limit->p2.p2_fast;
- else
- clock.p2 = limit->p2.p2_slow;
- } else {
- if (target < limit->p2.dot_limit)
- clock.p2 = limit->p2.p2_slow;
- else
- clock.p2 = limit->p2.p2_fast;
- }
-
memset(best_clock, 0, sizeof(*best_clock));
+ clock.p2 = i9xx_select_p2_div(limit, crtc_state, target);
+
for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max;
clock.m1++) {
for (clock.m2 = limit->m2.min;
clock.p1 <= limit->p1.max; clock.p1++) {
int this_err;
- pineview_clock(refclk, &clock);
+ pnv_calc_dpll_params(refclk, &clock);
if (!intel_PLL_is_valid(dev, limit,
&clock))
continue;
int target, int refclk, intel_clock_t *match_clock,
intel_clock_t *best_clock)
{
- struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
- struct drm_device *dev = crtc->base.dev;
+ struct drm_device *dev = crtc_state->base.crtc->dev;
intel_clock_t clock;
int max_n;
- bool found;
+ bool found = false;
/* approximately equals target * 0.00585 */
int err_most = (target >> 8) + (target >> 9);
- found = false;
-
- if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
- if (intel_is_dual_link_lvds(dev))
- clock.p2 = limit->p2.p2_fast;
- else
- clock.p2 = limit->p2.p2_slow;
- } else {
- if (target < limit->p2.dot_limit)
- clock.p2 = limit->p2.p2_slow;
- else
- clock.p2 = limit->p2.p2_fast;
- }
memset(best_clock, 0, sizeof(*best_clock));
+
+ clock.p2 = i9xx_select_p2_div(limit, crtc_state, target);
+
max_n = limit->n.max;
/* based on hardware requirement, prefer smaller n to precision */
for (clock.n = limit->n.min; clock.n <= max_n; clock.n++) {
clock.p1 >= limit->p1.min; clock.p1--) {
int this_err;
- i9xx_clock(refclk, &clock);
+ i9xx_calc_dpll_params(refclk, &clock);
if (!intel_PLL_is_valid(dev, limit,
&clock))
continue;
clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
refclk * clock.m1);
- vlv_clock(refclk, &clock);
+ vlv_calc_dpll_params(refclk, &clock);
if (!intel_PLL_is_valid(dev, limit,
&clock))
clock.m2 = m2;
- chv_clock(refclk, &clock);
+ chv_calc_dpll_params(refclk, &clock);
if (!intel_PLL_is_valid(dev, limit, &clock))
continue;
line_mask = DSL_LINEMASK_GEN3;
line1 = I915_READ(reg) & line_mask;
- mdelay(5);
+ msleep(5);
line2 = I915_READ(reg) & line_mask;
return line1 == line2;
int count = 0;
for_each_intel_crtc(dev, crtc)
- count += crtc->active &&
+ count += crtc->base.state->active &&
intel_pipe_has_type(crtc, INTEL_OUTPUT_DVO);
return count;
/* Disable DVO 2x clock on both PLLs if necessary */
if (IS_I830(dev) &&
intel_pipe_has_type(crtc, INTEL_OUTPUT_DVO) &&
- intel_num_dvo_pipes(dev) == 1) {
+ !intel_num_dvo_pipes(dev)) {
I915_WRITE(DPLL(PIPE_B),
I915_READ(DPLL(PIPE_B)) & ~DPLL_DVO_2X_MODE);
I915_WRITE(DPLL(PIPE_A),
/* Make sure the pipe isn't still relying on us */
assert_pipe_disabled(dev_priv, pipe);
- I915_WRITE(DPLL(pipe), 0);
+ I915_WRITE(DPLL(pipe), DPLL_VGA_MODE_DIS);
POSTING_READ(DPLL(pipe));
}
static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
{
- u32 val = 0;
+ u32 val;
/* Make sure the pipe isn't still relying on us */
assert_pipe_disabled(dev_priv, pipe);
* Leave integrated clock source and reference clock enabled for pipe B.
* The latter is needed for VGA hotplug / manual detection.
*/
+ val = DPLL_VGA_MODE_DIS;
if (pipe == PIPE_B)
- val = DPLL_INTEGRATED_CRI_CLK_VLV | DPLL_REFA_CLK_ENABLE_VLV;
+ val = DPLL_INTEGRATED_CRI_CLK_VLV | DPLL_REF_CLK_ENABLE_VLV;
I915_WRITE(DPLL(pipe), val);
POSTING_READ(DPLL(pipe));
assert_pipe_disabled(dev_priv, pipe);
/* Set PLL en = 0 */
- val = DPLL_SSC_REF_CLOCK_CHV | DPLL_REFA_CLK_ENABLE_VLV;
+ val = DPLL_SSC_REF_CLK_CHV |
+ DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
if (pipe != PIPE_A)
val |= DPLL_INTEGRATED_CRI_CLK_VLV;
I915_WRITE(DPLL(pipe), val);
/* PCH only available on ILK+ */
BUG_ON(INTEL_INFO(dev)->gen < 5);
- if (WARN_ON(pll == NULL))
- return;
+ if (pll == NULL)
+ return;
- if (WARN_ON(pll->config.crtc_mask == 0))
+ if (WARN_ON(!(pll->config.crtc_mask & (1 << drm_crtc_index(&crtc->base)))))
return;
DRM_DEBUG_KMS("disable %s (active %d, on? %d) for crtc %d\n",
if (HAS_PCH_IBX(dev_priv->dev)) {
/*
- * make the BPC in transcoder be consistent with
- * that in pipeconf reg.
+ * Make the BPC in transcoder be consistent with
+ * that in pipeconf reg. For HDMI we must use 8bpc
+ * here for both 8bpc and 12bpc.
*/
val &= ~PIPECONF_BPC_MASK;
- val |= pipeconf_val & PIPECONF_BPC_MASK;
+ if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_HDMI))
+ val |= PIPECONF_8BPC;
+ else
+ val |= pipeconf_val & PIPECONF_BPC_MASK;
}
val &= ~TRANS_INTERLACE_MASK;
int reg;
u32 val;
+ DRM_DEBUG_KMS("enabling pipe %c\n", pipe_name(pipe));
+
assert_planes_disabled(dev_priv, pipe);
assert_cursor_disabled(dev_priv, pipe);
assert_sprites_disabled(dev_priv, pipe);
int reg;
u32 val;
+ DRM_DEBUG_KMS("disabling pipe %c\n", pipe_name(pipe));
+
/*
* Make sure planes won't keep trying to pump pixels to us,
* or we might hang the display.
intel_wait_for_pipe_off(crtc);
}
-/**
- * intel_enable_primary_hw_plane - enable the primary plane on a given pipe
- * @plane: plane to be enabled
- * @crtc: crtc for the plane
- *
- * Enable @plane on @crtc, making sure that the pipe is running first.
- */
-static void intel_enable_primary_hw_plane(struct drm_plane *plane,
- struct drm_crtc *crtc)
-{
- struct drm_device *dev = plane->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
- /* If the pipe isn't enabled, we can't pump pixels and may hang */
- assert_pipe_enabled(dev_priv, intel_crtc->pipe);
- to_intel_plane_state(plane->state)->visible = true;
-
- dev_priv->display.update_primary_plane(crtc, plane->fb,
- crtc->x, crtc->y);
-}
-
static bool need_vtd_wa(struct drm_device *dev)
{
#ifdef CONFIG_INTEL_IOMMU
const struct drm_plane_state *plane_state)
{
struct intel_rotation_info *info = &view->rotation_info;
+ unsigned int tile_height, tile_pitch;
*view = i915_ggtt_view_normal;
info->pitch = fb->pitches[0];
info->fb_modifier = fb->modifier[0];
+ tile_height = intel_tile_height(fb->dev, fb->pixel_format,
+ fb->modifier[0]);
+ tile_pitch = PAGE_SIZE / tile_height;
+ info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_pitch);
+ info->height_pages = DIV_ROUND_UP(fb->height, tile_height);
+ info->size = info->width_pages * info->height_pages * PAGE_SIZE;
+
return 0;
}
+static unsigned int intel_linear_alignment(struct drm_i915_private *dev_priv)
+{
+ if (INTEL_INFO(dev_priv)->gen >= 9)
+ return 256 * 1024;
+ else if (IS_BROADWATER(dev_priv) || IS_CRESTLINE(dev_priv) ||
+ IS_VALLEYVIEW(dev_priv))
+ return 128 * 1024;
+ else if (INTEL_INFO(dev_priv)->gen >= 4)
+ return 4 * 1024;
+ else
+ return 0;
+}
+
int
intel_pin_and_fence_fb_obj(struct drm_plane *plane,
struct drm_framebuffer *fb,
const struct drm_plane_state *plane_state,
- struct intel_engine_cs *pipelined)
+ struct intel_engine_cs *pipelined,
+ struct drm_i915_gem_request **pipelined_request)
{
struct drm_device *dev = fb->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
switch (fb->modifier[0]) {
case DRM_FORMAT_MOD_NONE:
- if (INTEL_INFO(dev)->gen >= 9)
- alignment = 256 * 1024;
- else if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
- alignment = 128 * 1024;
- else if (INTEL_INFO(dev)->gen >= 4)
- alignment = 4 * 1024;
- else
- alignment = 64 * 1024;
+ alignment = intel_linear_alignment(dev_priv);
break;
case I915_FORMAT_MOD_X_TILED:
if (INTEL_INFO(dev)->gen >= 9)
dev_priv->mm.interruptible = false;
ret = i915_gem_object_pin_to_display_plane(obj, alignment, pipelined,
- &view);
+ pipelined_request, &view);
if (ret)
goto err_interruptible;
/* Computes the linear offset to the base tile and adjusts x, y. bytes per pixel
* is assumed to be a power-of-two. */
-unsigned long intel_gen4_compute_page_offset(int *x, int *y,
+unsigned long intel_gen4_compute_page_offset(struct drm_i915_private *dev_priv,
+ int *x, int *y,
unsigned int tiling_mode,
unsigned int cpp,
unsigned int pitch)
return tile_rows * pitch * 8 + tiles * 4096;
} else {
+ unsigned int alignment = intel_linear_alignment(dev_priv) - 1;
unsigned int offset;
offset = *y * pitch + *x * cpp;
- *y = 0;
- *x = (offset & 4095) / cpp;
- return offset & -4096;
+ *y = (offset & alignment) / pitch;
+ *x = ((offset & alignment) - *y * pitch) / cpp;
+ return offset & ~alignment;
}
}
struct intel_crtc *i;
struct drm_i915_gem_object *obj;
struct drm_plane *primary = intel_crtc->base.primary;
+ struct drm_plane_state *plane_state = primary->state;
struct drm_framebuffer *fb;
if (!plane_config->fb)
return;
valid_fb:
+ plane_state->src_x = plane_state->src_y = 0;
+ plane_state->src_w = fb->width << 16;
+ plane_state->src_h = fb->height << 16;
+
+ plane_state->crtc_x = plane_state->src_y = 0;
+ plane_state->crtc_w = fb->width;
+ plane_state->crtc_h = fb->height;
+
obj = intel_fb_obj(fb);
if (obj->tiling_mode != I915_TILING_NONE)
dev_priv->preserve_bios_swizzle = true;
- primary->fb = fb;
- primary->state->crtc = &intel_crtc->base;
- primary->crtc = &intel_crtc->base;
- update_state_fb(primary);
- obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
+ drm_framebuffer_reference(fb);
+ primary->fb = primary->state->fb = fb;
+ primary->crtc = primary->state->crtc = &intel_crtc->base;
+ intel_crtc->base.state->plane_mask |= (1 << drm_plane_index(primary));
+ obj->frontbuffer_bits |= to_intel_plane(primary)->frontbuffer_bit;
}
static void i9xx_update_primary_plane(struct drm_crtc *crtc,
if (INTEL_INFO(dev)->gen >= 4) {
intel_crtc->dspaddr_offset =
- intel_gen4_compute_page_offset(&x, &y, obj->tiling_mode,
+ intel_gen4_compute_page_offset(dev_priv,
+ &x, &y, obj->tiling_mode,
pixel_size,
fb->pitches[0]);
linear_offset -= intel_crtc->dspaddr_offset;
linear_offset = y * fb->pitches[0] + x * pixel_size;
intel_crtc->dspaddr_offset =
- intel_gen4_compute_page_offset(&x, &y, obj->tiling_mode,
+ intel_gen4_compute_page_offset(dev_priv,
+ &x, &y, obj->tiling_mode,
pixel_size,
fb->pitches[0]);
linear_offset -= intel_crtc->dspaddr_offset;
return i915_gem_obj_ggtt_offset_view(obj, view);
}
+static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
+{
+ struct drm_device *dev = intel_crtc->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(SKL_PS_CTRL(intel_crtc->pipe, id), 0);
+ I915_WRITE(SKL_PS_WIN_POS(intel_crtc->pipe, id), 0);
+ I915_WRITE(SKL_PS_WIN_SZ(intel_crtc->pipe, id), 0);
+ DRM_DEBUG_KMS("CRTC:%d Disabled scaler id %u.%u\n",
+ intel_crtc->base.base.id, intel_crtc->pipe, id);
+}
+
/*
* This function detaches (aka. unbinds) unused scalers in hardware
*/
-void skl_detach_scalers(struct intel_crtc *intel_crtc)
+static void skl_detach_scalers(struct intel_crtc *intel_crtc)
{
- struct drm_device *dev;
- struct drm_i915_private *dev_priv;
struct intel_crtc_scaler_state *scaler_state;
int i;
- if (!intel_crtc || !intel_crtc->config)
- return;
-
- dev = intel_crtc->base.dev;
- dev_priv = dev->dev_private;
scaler_state = &intel_crtc->config->scaler_state;
/* loop through and disable scalers that aren't in use */
for (i = 0; i < intel_crtc->num_scalers; i++) {
- if (!scaler_state->scalers[i].in_use) {
- I915_WRITE(SKL_PS_CTRL(intel_crtc->pipe, i), 0);
- I915_WRITE(SKL_PS_WIN_POS(intel_crtc->pipe, i), 0);
- I915_WRITE(SKL_PS_WIN_SZ(intel_crtc->pipe, i), 0);
- DRM_DEBUG_KMS("CRTC:%d Disabled scaler id %u.%u\n",
- intel_crtc->base.base.id, intel_crtc->pipe, i);
- }
+ if (!scaler_state->scalers[i].in_use)
+ skl_detach_scaler(intel_crtc, i);
}
}
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- if (dev_priv->display.disable_fbc)
- dev_priv->display.disable_fbc(dev);
+ if (dev_priv->fbc.disable_fbc)
+ dev_priv->fbc.disable_fbc(dev_priv);
dev_priv->display.update_primary_plane(crtc, fb, x, y);
}
}
-void intel_crtc_reset(struct intel_crtc *crtc)
-{
- struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
- if (!crtc->active)
- return;
-
- intel_crtc_disable_planes(&crtc->base);
- dev_priv->display.crtc_disable(&crtc->base);
- dev_priv->display.crtc_enable(&crtc->base);
- intel_crtc_enable_planes(&crtc->base);
-}
-
void intel_prepare_reset(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct intel_crtc *crtc;
-
/* no reset support for gen2 */
if (IS_GEN2(dev))
return;
return;
drm_modeset_lock_all(dev);
-
/*
* Disabling the crtcs gracefully seems nicer. Also the
* g33 docs say we should at least disable all the planes.
*/
- for_each_intel_crtc(dev, crtc) {
- if (!crtc->active)
- continue;
-
- intel_crtc_disable_planes(&crtc->base);
- dev_priv->display.crtc_disable(&crtc->base);
- }
+ intel_display_suspend(dev);
}
void intel_finish_reset(struct drm_device *dev)
dev_priv->display.hpd_irq_setup(dev);
spin_unlock_irq(&dev_priv->irq_lock);
- intel_modeset_setup_hw_state(dev, true);
+ intel_display_resume(dev);
intel_hpd_init(dev_priv);
lpt_enable_pch_transcoder(dev_priv, cpu_transcoder);
}
-void intel_put_shared_dpll(struct intel_crtc *crtc)
-{
- struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
-
- if (pll == NULL)
- return;
-
- if (!(pll->config.crtc_mask & (1 << crtc->pipe))) {
- WARN(1, "bad %s crtc mask\n", pll->name);
- return;
- }
-
- pll->config.crtc_mask &= ~(1 << crtc->pipe);
- if (pll->config.crtc_mask == 0) {
- WARN_ON(pll->on);
- WARN_ON(pll->active);
- }
-
- crtc->config->shared_dpll = DPLL_ID_PRIVATE;
-}
-
struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc,
struct intel_crtc_state *crtc_state)
{
struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
struct intel_shared_dpll *pll;
+ struct intel_shared_dpll_config *shared_dpll;
enum intel_dpll_id i;
+ shared_dpll = intel_atomic_get_shared_dpll_state(crtc_state->base.state);
+
if (HAS_PCH_IBX(dev_priv->dev)) {
/* Ironlake PCH has a fixed PLL->PCH pipe mapping. */
i = (enum intel_dpll_id) crtc->pipe;
DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n",
crtc->base.base.id, pll->name);
- WARN_ON(pll->new_config->crtc_mask);
+ WARN_ON(shared_dpll[i].crtc_mask);
goto found;
}
pll = &dev_priv->shared_dplls[i];
DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n",
crtc->base.base.id, pll->name);
- WARN_ON(pll->new_config->crtc_mask);
+ WARN_ON(shared_dpll[i].crtc_mask);
goto found;
}
pll = &dev_priv->shared_dplls[i];
/* Only want to check enabled timings first */
- if (pll->new_config->crtc_mask == 0)
+ if (shared_dpll[i].crtc_mask == 0)
continue;
if (memcmp(&crtc_state->dpll_hw_state,
- &pll->new_config->hw_state,
- sizeof(pll->new_config->hw_state)) == 0) {
+ &shared_dpll[i].hw_state,
+ sizeof(crtc_state->dpll_hw_state)) == 0) {
DRM_DEBUG_KMS("CRTC:%d sharing existing %s (crtc mask 0x%08x, ative %d)\n",
crtc->base.base.id, pll->name,
- pll->new_config->crtc_mask,
+ shared_dpll[i].crtc_mask,
pll->active);
goto found;
}
/* Ok no matching timings, maybe there's a free one? */
for (i = 0; i < dev_priv->num_shared_dpll; i++) {
pll = &dev_priv->shared_dplls[i];
- if (pll->new_config->crtc_mask == 0) {
+ if (shared_dpll[i].crtc_mask == 0) {
DRM_DEBUG_KMS("CRTC:%d allocated %s\n",
crtc->base.base.id, pll->name);
goto found;
return NULL;
found:
- if (pll->new_config->crtc_mask == 0)
- pll->new_config->hw_state = crtc_state->dpll_hw_state;
+ if (shared_dpll[i].crtc_mask == 0)
+ shared_dpll[i].hw_state =
+ crtc_state->dpll_hw_state;
crtc_state->shared_dpll = i;
DRM_DEBUG_DRIVER("using %s for pipe %c\n", pll->name,
pipe_name(crtc->pipe));
- pll->new_config->crtc_mask |= 1 << crtc->pipe;
+ shared_dpll[i].crtc_mask |= 1 << crtc->pipe;
return pll;
}
-/**
- * intel_shared_dpll_start_config - start a new PLL staged config
- * @dev_priv: DRM device
- * @clear_pipes: mask of pipes that will have their PLLs freed
- *
- * Starts a new PLL staged config, copying the current config but
- * releasing the references of pipes specified in clear_pipes.
- */
-static int intel_shared_dpll_start_config(struct drm_i915_private *dev_priv,
- unsigned clear_pipes)
-{
- struct intel_shared_dpll *pll;
- enum intel_dpll_id i;
-
- for (i = 0; i < dev_priv->num_shared_dpll; i++) {
- pll = &dev_priv->shared_dplls[i];
-
- pll->new_config = kmemdup(&pll->config, sizeof pll->config,
- GFP_KERNEL);
- if (!pll->new_config)
- goto cleanup;
-
- pll->new_config->crtc_mask &= ~clear_pipes;
- }
-
- return 0;
-
-cleanup:
- while (--i >= 0) {
- pll = &dev_priv->shared_dplls[i];
- kfree(pll->new_config);
- pll->new_config = NULL;
- }
-
- return -ENOMEM;
-}
-
-static void intel_shared_dpll_commit(struct drm_i915_private *dev_priv)
+static void intel_shared_dpll_commit(struct drm_atomic_state *state)
{
+ struct drm_i915_private *dev_priv = to_i915(state->dev);
+ struct intel_shared_dpll_config *shared_dpll;
struct intel_shared_dpll *pll;
enum intel_dpll_id i;
- for (i = 0; i < dev_priv->num_shared_dpll; i++) {
- pll = &dev_priv->shared_dplls[i];
-
- WARN_ON(pll->new_config == &pll->config);
-
- pll->config = *pll->new_config;
- kfree(pll->new_config);
- pll->new_config = NULL;
- }
-}
-
-static void intel_shared_dpll_abort_config(struct drm_i915_private *dev_priv)
-{
- struct intel_shared_dpll *pll;
- enum intel_dpll_id i;
+ if (!to_intel_atomic_state(state)->dpll_set)
+ return;
+ shared_dpll = to_intel_atomic_state(state)->shared_dpll;
for (i = 0; i < dev_priv->num_shared_dpll; i++) {
pll = &dev_priv->shared_dplls[i];
-
- WARN_ON(pll->new_config == &pll->config);
-
- kfree(pll->new_config);
- pll->new_config = NULL;
+ pll->config = shared_dpll[i];
}
}
}
}
-/**
- * skl_update_scaler_users - Stages update to crtc's scaler state
- * @intel_crtc: crtc
- * @crtc_state: crtc_state
- * @plane: plane (NULL indicates crtc is requesting update)
- * @plane_state: plane's state
- * @force_detach: request unconditional detachment of scaler
- *
- * This function updates scaler state for requested plane or crtc.
- * To request scaler usage update for a plane, caller shall pass plane pointer.
- * To request scaler usage update for crtc, caller shall pass plane pointer
- * as NULL.
- *
- * Return
- * 0 - scaler_usage updated successfully
- * error - requested scaling cannot be supported or other error condition
- */
-int
-skl_update_scaler_users(
- struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state,
- struct intel_plane *intel_plane, struct intel_plane_state *plane_state,
- int force_detach)
+static int
+skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
+ unsigned scaler_user, int *scaler_id, unsigned int rotation,
+ int src_w, int src_h, int dst_w, int dst_h)
{
+ struct intel_crtc_scaler_state *scaler_state =
+ &crtc_state->scaler_state;
+ struct intel_crtc *intel_crtc =
+ to_intel_crtc(crtc_state->base.crtc);
int need_scaling;
- int idx;
- int src_w, src_h, dst_w, dst_h;
- int *scaler_id;
- struct drm_framebuffer *fb;
- struct intel_crtc_scaler_state *scaler_state;
- unsigned int rotation;
-
- if (!intel_crtc || !crtc_state)
- return 0;
-
- scaler_state = &crtc_state->scaler_state;
-
- idx = intel_plane ? drm_plane_index(&intel_plane->base) : SKL_CRTC_INDEX;
- fb = intel_plane ? plane_state->base.fb : NULL;
-
- if (intel_plane) {
- src_w = drm_rect_width(&plane_state->src) >> 16;
- src_h = drm_rect_height(&plane_state->src) >> 16;
- dst_w = drm_rect_width(&plane_state->dst);
- dst_h = drm_rect_height(&plane_state->dst);
- scaler_id = &plane_state->scaler_id;
- rotation = plane_state->base.rotation;
- } else {
- struct drm_display_mode *adjusted_mode =
- &crtc_state->base.adjusted_mode;
- src_w = crtc_state->pipe_src_w;
- src_h = crtc_state->pipe_src_h;
- dst_w = adjusted_mode->hdisplay;
- dst_h = adjusted_mode->vdisplay;
- scaler_id = &scaler_state->scaler_id;
- rotation = DRM_ROTATE_0;
- }
need_scaling = intel_rotation_90_or_270(rotation) ?
(src_h != dst_w || src_w != dst_h):
* update to free the scaler is done in plane/panel-fit programming.
* For this purpose crtc/plane_state->scaler_id isn't reset here.
*/
- if (force_detach || !need_scaling || (intel_plane &&
- (!fb || !plane_state->visible))) {
+ if (force_detach || !need_scaling) {
if (*scaler_id >= 0) {
- scaler_state->scaler_users &= ~(1 << idx);
+ scaler_state->scaler_users &= ~(1 << scaler_user);
scaler_state->scalers[*scaler_id].in_use = 0;
- DRM_DEBUG_KMS("Staged freeing scaler id %d.%d from %s:%d "
- "crtc_state = %p scaler_users = 0x%x\n",
- intel_crtc->pipe, *scaler_id, intel_plane ? "PLANE" : "CRTC",
- intel_plane ? intel_plane->base.base.id :
- intel_crtc->base.base.id, crtc_state,
+ DRM_DEBUG_KMS("scaler_user index %u.%u: "
+ "Staged freeing scaler id %d scaler_users = 0x%x\n",
+ intel_crtc->pipe, scaler_user, *scaler_id,
scaler_state->scaler_users);
*scaler_id = -1;
}
src_w > SKL_MAX_SRC_W || src_h > SKL_MAX_SRC_H ||
dst_w > SKL_MAX_DST_W || dst_h > SKL_MAX_DST_H) {
- DRM_DEBUG_KMS("%s:%d scaler_user index %u.%u: src %ux%u dst %ux%u "
+ DRM_DEBUG_KMS("scaler_user index %u.%u: src %ux%u dst %ux%u "
"size is out of scaler range\n",
- intel_plane ? "PLANE" : "CRTC",
- intel_plane ? intel_plane->base.base.id : intel_crtc->base.base.id,
- intel_crtc->pipe, idx, src_w, src_h, dst_w, dst_h);
- return -EINVAL;
- }
-
- /* check colorkey */
- if (WARN_ON(intel_plane &&
- intel_plane->ckey.flags != I915_SET_COLORKEY_NONE)) {
- DRM_DEBUG_KMS("PLANE:%d scaling %ux%u->%ux%u not allowed with colorkey",
- intel_plane->base.base.id, src_w, src_h, dst_w, dst_h);
+ intel_crtc->pipe, scaler_user, src_w, src_h, dst_w, dst_h);
return -EINVAL;
}
- /* Check src format */
- if (intel_plane) {
- switch (fb->pixel_format) {
- case DRM_FORMAT_RGB565:
- case DRM_FORMAT_XBGR8888:
- case DRM_FORMAT_XRGB8888:
- case DRM_FORMAT_ABGR8888:
- case DRM_FORMAT_ARGB8888:
- case DRM_FORMAT_XRGB2101010:
- case DRM_FORMAT_XBGR2101010:
- case DRM_FORMAT_YUYV:
- case DRM_FORMAT_YVYU:
- case DRM_FORMAT_UYVY:
- case DRM_FORMAT_VYUY:
- break;
- default:
- DRM_DEBUG_KMS("PLANE:%d FB:%d unsupported scaling format 0x%x\n",
- intel_plane->base.base.id, fb->base.id, fb->pixel_format);
- return -EINVAL;
- }
- }
-
/* mark this plane as a scaler user in crtc_state */
- scaler_state->scaler_users |= (1 << idx);
- DRM_DEBUG_KMS("%s:%d staged scaling request for %ux%u->%ux%u "
- "crtc_state = %p scaler_users = 0x%x\n",
- intel_plane ? "PLANE" : "CRTC",
- intel_plane ? intel_plane->base.base.id : intel_crtc->base.base.id,
- src_w, src_h, dst_w, dst_h, crtc_state, scaler_state->scaler_users);
+ scaler_state->scaler_users |= (1 << scaler_user);
+ DRM_DEBUG_KMS("scaler_user index %u.%u: "
+ "staged scaling request for %ux%u->%ux%u scaler_users = 0x%x\n",
+ intel_crtc->pipe, scaler_user, src_w, src_h, dst_w, dst_h,
+ scaler_state->scaler_users);
+
return 0;
}
-static void skylake_pfit_update(struct intel_crtc *crtc, int enable)
+/**
+ * skl_update_scaler_crtc - Stages update to scaler state for a given crtc.
+ *
+ * @state: crtc's scaler state
+ *
+ * Return
+ * 0 - scaler_usage updated successfully
+ * error - requested scaling cannot be supported or other error condition
+ */
+int skl_update_scaler_crtc(struct intel_crtc_state *state)
{
- struct drm_device *dev = crtc->base.dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- int pipe = crtc->pipe;
- struct intel_crtc_scaler_state *scaler_state =
- &crtc->config->scaler_state;
-
- DRM_DEBUG_KMS("for crtc_state = %p\n", crtc->config);
+ struct intel_crtc *intel_crtc = to_intel_crtc(state->base.crtc);
+ struct drm_display_mode *adjusted_mode =
+ &state->base.adjusted_mode;
- /* To update pfit, first update scaler state */
- skl_update_scaler_users(crtc, crtc->config, NULL, NULL, !enable);
- intel_atomic_setup_scalers(crtc->base.dev, crtc, crtc->config);
- skl_detach_scalers(crtc);
- if (!enable)
- return;
+ DRM_DEBUG_KMS("Updating scaler for [CRTC:%i] scaler_user index %u.%u\n",
+ intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX);
- if (crtc->config->pch_pfit.enabled) {
- int id;
+ return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX,
+ &state->scaler_state.scaler_id, DRM_ROTATE_0,
+ state->pipe_src_w, state->pipe_src_h,
+ adjusted_mode->hdisplay, adjusted_mode->vdisplay);
+}
- if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) {
+/**
+ * skl_update_scaler_plane - Stages update to scaler state for a given plane.
+ *
+ * @state: crtc's scaler state
+ * @plane_state: atomic plane state to update
+ *
+ * Return
+ * 0 - scaler_usage updated successfully
+ * error - requested scaling cannot be supported or other error condition
+ */
+static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
+ struct intel_plane_state *plane_state)
+{
+
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+ struct intel_plane *intel_plane =
+ to_intel_plane(plane_state->base.plane);
+ struct drm_framebuffer *fb = plane_state->base.fb;
+ int ret;
+
+ bool force_detach = !fb || !plane_state->visible;
+
+ DRM_DEBUG_KMS("Updating scaler for [PLANE:%d] scaler_user index %u.%u\n",
+ intel_plane->base.base.id, intel_crtc->pipe,
+ drm_plane_index(&intel_plane->base));
+
+ ret = skl_update_scaler(crtc_state, force_detach,
+ drm_plane_index(&intel_plane->base),
+ &plane_state->scaler_id,
+ plane_state->base.rotation,
+ drm_rect_width(&plane_state->src) >> 16,
+ drm_rect_height(&plane_state->src) >> 16,
+ drm_rect_width(&plane_state->dst),
+ drm_rect_height(&plane_state->dst));
+
+ if (ret || plane_state->scaler_id < 0)
+ return ret;
+
+ /* check colorkey */
+ if (plane_state->ckey.flags != I915_SET_COLORKEY_NONE) {
+ DRM_DEBUG_KMS("[PLANE:%d] scaling with color key not allowed",
+ intel_plane->base.base.id);
+ return -EINVAL;
+ }
+
+ /* Check src format */
+ switch (fb->pixel_format) {
+ case DRM_FORMAT_RGB565:
+ case DRM_FORMAT_XBGR8888:
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_ABGR8888:
+ case DRM_FORMAT_ARGB8888:
+ case DRM_FORMAT_XRGB2101010:
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_YUYV:
+ case DRM_FORMAT_YVYU:
+ case DRM_FORMAT_UYVY:
+ case DRM_FORMAT_VYUY:
+ break;
+ default:
+ DRM_DEBUG_KMS("[PLANE:%d] FB:%d unsupported scaling format 0x%x\n",
+ intel_plane->base.base.id, fb->base.id, fb->pixel_format);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void skylake_scaler_disable(struct intel_crtc *crtc)
+{
+ int i;
+
+ for (i = 0; i < crtc->num_scalers; i++)
+ skl_detach_scaler(crtc, i);
+}
+
+static void skylake_pfit_enable(struct intel_crtc *crtc)
+{
+ struct drm_device *dev = crtc->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int pipe = crtc->pipe;
+ struct intel_crtc_scaler_state *scaler_state =
+ &crtc->config->scaler_state;
+
+ DRM_DEBUG_KMS("for crtc_state = %p\n", crtc->config);
+
+ if (crtc->config->pch_pfit.enabled) {
+ int id;
+
+ if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) {
DRM_ERROR("Requesting pfit without getting a scaler first\n");
return;
}
}
}
-static void intel_enable_sprite_planes(struct drm_crtc *crtc)
-{
- struct drm_device *dev = crtc->dev;
- enum pipe pipe = to_intel_crtc(crtc)->pipe;
- struct drm_plane *plane;
- struct intel_plane *intel_plane;
-
- drm_for_each_legacy_plane(plane, &dev->mode_config.plane_list) {
- intel_plane = to_intel_plane(plane);
- if (intel_plane->pipe == pipe)
- intel_plane_restore(&intel_plane->base);
- }
-}
-
void hsw_enable_ips(struct intel_crtc *crtc)
{
struct drm_device *dev = crtc->base.dev;
bool reenable_ips = false;
/* The clocks have to be on to load the palette. */
- if (!crtc->state->enable || !intel_crtc->active)
+ if (!crtc->state->active)
return;
if (HAS_GMCH_DISPLAY(dev_priv->dev)) {
*/
hsw_enable_ips(intel_crtc);
- mutex_lock(&dev->struct_mutex);
- intel_fbc_update(dev);
- mutex_unlock(&dev->struct_mutex);
-
/*
* Gen2 reports pipe underruns whenever all planes are disabled.
* So don't enable underrun reporting before at least some planes
* event which is after the vblank start event, so we need to have a
* wait-for-vblank between disabling the plane and the pipe.
*/
- if (HAS_GMCH_DISPLAY(dev))
+ if (HAS_GMCH_DISPLAY(dev)) {
intel_set_memory_cxsr(dev_priv, false);
-
- mutex_lock(&dev->struct_mutex);
- if (dev_priv->fbc.crtc == intel_crtc)
- intel_fbc_disable(dev);
- mutex_unlock(&dev->struct_mutex);
+ dev_priv->wm.vlv.cxsr = false;
+ intel_wait_for_vblank(dev, pipe);
+ }
/*
* FIXME IPS should be fine as long as one plane is
hsw_disable_ips(intel_crtc);
}
-static void intel_crtc_enable_planes(struct drm_crtc *crtc)
+static void intel_post_plane_update(struct intel_crtc *crtc)
{
- struct drm_device *dev = crtc->dev;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- int pipe = intel_crtc->pipe;
+ struct intel_crtc_atomic_commit *atomic = &crtc->atomic;
+ struct drm_device *dev = crtc->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_plane *plane;
- intel_enable_primary_hw_plane(crtc->primary, crtc);
- intel_enable_sprite_planes(crtc);
- intel_crtc_update_cursor(crtc, true);
+ if (atomic->wait_vblank)
+ intel_wait_for_vblank(dev, crtc->pipe);
- intel_post_enable_primary(crtc);
+ intel_frontbuffer_flip(dev, atomic->fb_bits);
- /*
- * FIXME: Once we grow proper nuclear flip support out of this we need
- * to compute the mask of flip planes precisely. For the time being
- * consider this a flip to a NULL plane.
- */
- intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_ALL_MASK(pipe));
+ if (atomic->disable_cxsr)
+ crtc->wm.cxsr_allowed = true;
+
+ if (crtc->atomic.update_wm_post)
+ intel_update_watermarks(&crtc->base);
+
+ if (atomic->update_fbc)
+ intel_fbc_update(dev_priv);
+
+ if (atomic->post_enable_primary)
+ intel_post_enable_primary(&crtc->base);
+
+ drm_for_each_plane_mask(plane, dev, atomic->update_sprite_watermarks)
+ intel_update_sprite_watermarks(plane, &crtc->base,
+ 0, 0, 0, false, false);
+
+ memset(atomic, 0, sizeof(*atomic));
}
-static void intel_crtc_disable_planes(struct drm_crtc *crtc)
+static void intel_pre_plane_update(struct intel_crtc *crtc)
{
- struct drm_device *dev = crtc->dev;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- struct intel_plane *intel_plane;
- int pipe = intel_crtc->pipe;
+ struct drm_device *dev = crtc->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_crtc_atomic_commit *atomic = &crtc->atomic;
+ struct drm_plane *p;
- if (!intel_crtc->active)
- return;
+ /* Track fb's for any planes being disabled */
+ drm_for_each_plane_mask(p, dev, atomic->disabled_planes) {
+ struct intel_plane *plane = to_intel_plane(p);
- intel_crtc_wait_for_pending_flips(crtc);
+ mutex_lock(&dev->struct_mutex);
+ i915_gem_track_fb(intel_fb_obj(plane->base.fb), NULL,
+ plane->frontbuffer_bit);
+ mutex_unlock(&dev->struct_mutex);
+ }
- intel_pre_disable_primary(crtc);
+ if (atomic->wait_for_flips)
+ intel_crtc_wait_for_pending_flips(&crtc->base);
- intel_crtc_dpms_overlay_disable(intel_crtc);
- for_each_intel_plane(dev, intel_plane) {
- if (intel_plane->pipe == pipe) {
- struct drm_crtc *from = intel_plane->base.crtc;
+ if (atomic->disable_fbc)
+ intel_fbc_disable_crtc(crtc);
- intel_plane->disable_plane(&intel_plane->base,
- from ?: crtc, true);
- }
+ if (crtc->atomic.disable_ips)
+ hsw_disable_ips(crtc);
+
+ if (atomic->pre_disable_primary)
+ intel_pre_disable_primary(&crtc->base);
+
+ if (atomic->disable_cxsr) {
+ crtc->wm.cxsr_allowed = false;
+ intel_set_memory_cxsr(dev_priv, false);
}
+}
+
+static void intel_crtc_disable_planes(struct drm_crtc *crtc, unsigned plane_mask)
+{
+ struct drm_device *dev = crtc->dev;
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ struct drm_plane *p;
+ int pipe = intel_crtc->pipe;
+
+ intel_crtc_dpms_overlay_disable(intel_crtc);
+
+ drm_for_each_plane_mask(p, dev, plane_mask)
+ to_intel_plane(p)->disable_plane(p, crtc);
/*
* FIXME: Once we grow proper nuclear flip support out of this we need
struct intel_encoder *encoder;
int pipe = intel_crtc->pipe;
- WARN_ON(!crtc->state->enable);
-
- if (intel_crtc->active)
+ if (WARN_ON(intel_crtc->active))
return;
if (intel_crtc->config->has_pch_encoder)
return HAS_IPS(crtc->base.dev) && crtc->pipe == PIPE_A;
}
-/*
- * This implements the workaround described in the "notes" section of the mode
- * set sequence documentation. When going from no pipes or single pipe to
- * multiple pipes, and planes are enabled after the pipe, we need to wait at
- * least 2 vblanks on the first pipe before enabling planes on the second pipe.
- */
-static void haswell_mode_set_planes_workaround(struct intel_crtc *crtc)
-{
- struct drm_device *dev = crtc->base.dev;
- struct intel_crtc *crtc_it, *other_active_crtc = NULL;
-
- /* We want to get the other_active_crtc only if there's only 1 other
- * active crtc. */
- for_each_intel_crtc(dev, crtc_it) {
- if (!crtc_it->active || crtc_it == crtc)
- continue;
-
- if (other_active_crtc)
- return;
-
- other_active_crtc = crtc_it;
- }
- if (!other_active_crtc)
- return;
-
- intel_wait_for_vblank(dev, other_active_crtc->pipe);
- intel_wait_for_vblank(dev, other_active_crtc->pipe);
-}
-
static void haswell_crtc_enable(struct drm_crtc *crtc)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
struct intel_encoder *encoder;
- int pipe = intel_crtc->pipe;
+ int pipe = intel_crtc->pipe, hsw_workaround_pipe;
+ struct intel_crtc_state *pipe_config =
+ to_intel_crtc_state(crtc->state);
- WARN_ON(!crtc->state->enable);
-
- if (intel_crtc->active)
+ if (WARN_ON(intel_crtc->active))
return;
if (intel_crtc_to_shared_dpll(intel_crtc))
intel_ddi_enable_pipe_clock(intel_crtc);
if (INTEL_INFO(dev)->gen == 9)
- skylake_pfit_update(intel_crtc, 1);
+ skylake_pfit_enable(intel_crtc);
else if (INTEL_INFO(dev)->gen < 9)
ironlake_pfit_enable(intel_crtc);
else
/* If we change the relative order between pipe/planes enabling, we need
* to change the workaround. */
- haswell_mode_set_planes_workaround(intel_crtc);
+ hsw_workaround_pipe = pipe_config->hsw_workaround_pipe;
+ if (IS_HASWELL(dev) && hsw_workaround_pipe != INVALID_PIPE) {
+ intel_wait_for_vblank(dev, hsw_workaround_pipe);
+ intel_wait_for_vblank(dev, hsw_workaround_pipe);
+ }
}
static void ironlake_pfit_disable(struct intel_crtc *crtc)
int pipe = intel_crtc->pipe;
u32 reg, temp;
- if (!intel_crtc->active)
- return;
-
for_each_encoder_on_crtc(dev, crtc, encoder)
encoder->disable(encoder);
I915_WRITE(PCH_DPLL_SEL, temp);
}
- /* disable PCH DPLL */
- intel_disable_shared_dpll(intel_crtc);
-
ironlake_fdi_pll_disable(intel_crtc);
}
intel_crtc->active = false;
intel_update_watermarks(crtc);
-
- mutex_lock(&dev->struct_mutex);
- intel_fbc_update(dev);
- mutex_unlock(&dev->struct_mutex);
}
static void haswell_crtc_disable(struct drm_crtc *crtc)
struct intel_encoder *encoder;
enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
- if (!intel_crtc->active)
- return;
-
for_each_encoder_on_crtc(dev, crtc, encoder) {
intel_opregion_notify_encoder(encoder, false);
encoder->disable(encoder);
intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
if (INTEL_INFO(dev)->gen == 9)
- skylake_pfit_update(intel_crtc, 0);
+ skylake_scaler_disable(intel_crtc);
else if (INTEL_INFO(dev)->gen < 9)
ironlake_pfit_disable(intel_crtc);
else
intel_crtc->active = false;
intel_update_watermarks(crtc);
-
- mutex_lock(&dev->struct_mutex);
- intel_fbc_update(dev);
- mutex_unlock(&dev->struct_mutex);
-
- if (intel_crtc_to_shared_dpll(intel_crtc))
- intel_disable_shared_dpll(intel_crtc);
-}
-
-static void ironlake_crtc_off(struct drm_crtc *crtc)
-{
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- intel_put_shared_dpll(intel_crtc);
}
-
static void i9xx_pfit_enable(struct intel_crtc *crtc)
{
struct drm_device *dev = crtc->base.dev;
unsigned long mask;
enum transcoder transcoder;
+ if (!crtc->state->active)
+ return 0;
+
transcoder = intel_pipe_to_cpu_transcoder(dev->dev_private, pipe);
mask = BIT(POWER_DOMAIN_PIPE(pipe));
return mask;
}
+static unsigned long modeset_get_crtc_power_domains(struct drm_crtc *crtc)
+{
+ struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ enum intel_display_power_domain domain;
+ unsigned long domains, new_domains, old_domains;
+
+ old_domains = intel_crtc->enabled_power_domains;
+ intel_crtc->enabled_power_domains = new_domains = get_crtc_power_domains(crtc);
+
+ domains = new_domains & ~old_domains;
+
+ for_each_power_domain(domain, domains)
+ intel_display_power_get(dev_priv, domain);
+
+ return old_domains & ~new_domains;
+}
+
+static void modeset_put_power_domains(struct drm_i915_private *dev_priv,
+ unsigned long domains)
+{
+ enum intel_display_power_domain domain;
+
+ for_each_power_domain(domain, domains)
+ intel_display_power_put(dev_priv, domain);
+}
+
static void modeset_update_crtc_power_domains(struct drm_atomic_state *state)
{
struct drm_device *dev = state->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- unsigned long pipe_domains[I915_MAX_PIPES] = { 0, };
- struct intel_crtc *crtc;
+ unsigned long put_domains[I915_MAX_PIPES] = {};
+ struct drm_crtc_state *crtc_state;
+ struct drm_crtc *crtc;
+ int i;
- /*
- * First get all needed power domains, then put all unneeded, to avoid
- * any unnecessary toggling of the power wells.
- */
- for_each_intel_crtc(dev, crtc) {
- enum intel_display_power_domain domain;
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ if (needs_modeset(crtc->state))
+ put_domains[to_intel_crtc(crtc)->pipe] =
+ modeset_get_crtc_power_domains(crtc);
+ }
- if (!crtc->base.state->enable)
- continue;
+ if (dev_priv->display.modeset_commit_cdclk) {
+ unsigned int cdclk = to_intel_atomic_state(state)->cdclk;
+
+ if (cdclk != dev_priv->cdclk_freq &&
+ !WARN_ON(!state->allow_modeset))
+ dev_priv->display.modeset_commit_cdclk(state);
+ }
+
+ for (i = 0; i < I915_MAX_PIPES; i++)
+ if (put_domains[i])
+ modeset_put_power_domains(dev_priv, put_domains[i]);
+}
+
+static void intel_update_max_cdclk(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
- pipe_domains[crtc->pipe] = get_crtc_power_domains(&crtc->base);
+ if (IS_SKYLAKE(dev)) {
+ u32 limit = I915_READ(SKL_DFSM) & SKL_DFSM_CDCLK_LIMIT_MASK;
- for_each_power_domain(domain, pipe_domains[crtc->pipe])
- intel_display_power_get(dev_priv, domain);
+ if (limit == SKL_DFSM_CDCLK_LIMIT_675)
+ dev_priv->max_cdclk_freq = 675000;
+ else if (limit == SKL_DFSM_CDCLK_LIMIT_540)
+ dev_priv->max_cdclk_freq = 540000;
+ else if (limit == SKL_DFSM_CDCLK_LIMIT_450)
+ dev_priv->max_cdclk_freq = 450000;
+ else
+ dev_priv->max_cdclk_freq = 337500;
+ } else if (IS_BROADWELL(dev)) {
+ /*
+ * FIXME with extra cooling we can allow
+ * 540 MHz for ULX and 675 Mhz for ULT.
+ * How can we know if extra cooling is
+ * available? PCI ID, VTB, something else?
+ */
+ if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
+ dev_priv->max_cdclk_freq = 450000;
+ else if (IS_BDW_ULX(dev))
+ dev_priv->max_cdclk_freq = 450000;
+ else if (IS_BDW_ULT(dev))
+ dev_priv->max_cdclk_freq = 540000;
+ else
+ dev_priv->max_cdclk_freq = 675000;
+ } else if (IS_CHERRYVIEW(dev)) {
+ dev_priv->max_cdclk_freq = 320000;
+ } else if (IS_VALLEYVIEW(dev)) {
+ dev_priv->max_cdclk_freq = 400000;
+ } else {
+ /* otherwise assume cdclk is fixed */
+ dev_priv->max_cdclk_freq = dev_priv->cdclk_freq;
}
- if (dev_priv->display.modeset_global_resources)
- dev_priv->display.modeset_global_resources(state);
+ DRM_DEBUG_DRIVER("Max CD clock rate: %d kHz\n",
+ dev_priv->max_cdclk_freq);
+}
- for_each_intel_crtc(dev, crtc) {
- enum intel_display_power_domain domain;
+static void intel_update_cdclk(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
- for_each_power_domain(domain, crtc->enabled_power_domains)
- intel_display_power_put(dev_priv, domain);
+ dev_priv->cdclk_freq = dev_priv->display.get_display_clock_speed(dev);
+ DRM_DEBUG_DRIVER("Current CD clock rate: %d kHz\n",
+ dev_priv->cdclk_freq);
- crtc->enabled_power_domains = pipe_domains[crtc->pipe];
+ /*
+ * Program the gmbus_freq based on the cdclk frequency.
+ * BSpec erroneously claims we should aim for 4MHz, but
+ * in fact 1MHz is the correct frequency.
+ */
+ if (IS_VALLEYVIEW(dev)) {
+ /*
+ * Program the gmbus_freq based on the cdclk frequency.
+ * BSpec erroneously claims we should aim for 4MHz, but
+ * in fact 1MHz is the correct frequency.
+ */
+ I915_WRITE(GMBUSFREQ_VLV, DIV_ROUND_UP(dev_priv->cdclk_freq, 1000));
}
- intel_display_set_init_power(dev_priv, false);
+ if (dev_priv->max_cdclk_freq == 0)
+ intel_update_max_cdclk(dev);
}
-void broxton_set_cdclk(struct drm_device *dev, int frequency)
+static void broxton_set_cdclk(struct drm_device *dev, int frequency)
{
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t divider;
return;
}
- dev_priv->cdclk_freq = frequency;
+ intel_update_cdclk(dev);
}
void broxton_init_cdclk(struct drm_device *dev)
static void skl_set_cdclk(struct drm_i915_private *dev_priv, unsigned int freq)
{
+ struct drm_device *dev = dev_priv->dev;
u32 freq_select, pcu_ack;
DRM_DEBUG_DRIVER("Changing CDCLK to %dKHz\n", freq);
mutex_lock(&dev_priv->rps.hw_lock);
sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL, pcu_ack);
mutex_unlock(&dev_priv->rps.hw_lock);
+
+ intel_update_cdclk(dev);
}
void skl_uninit_cdclk(struct drm_i915_private *dev_priv)
return vco_freq[hpll_freq] * 1000;
}
-static void vlv_update_cdclk(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- dev_priv->cdclk_freq = dev_priv->display.get_display_clock_speed(dev);
- DRM_DEBUG_DRIVER("Current CD clock rate: %d kHz\n",
- dev_priv->cdclk_freq);
-
- /*
- * Program the gmbus_freq based on the cdclk frequency.
- * BSpec erroneously claims we should aim for 4MHz, but
- * in fact 1MHz is the correct frequency.
- */
- I915_WRITE(GMBUSFREQ_VLV, DIV_ROUND_UP(dev_priv->cdclk_freq, 1000));
-}
-
/* Adjust CDclk dividers to allow high res or save power if possible */
static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
{
mutex_unlock(&dev_priv->sb_lock);
- vlv_update_cdclk(dev);
+ intel_update_cdclk(dev);
}
static void cherryview_set_cdclk(struct drm_device *dev, int cdclk)
}
mutex_unlock(&dev_priv->rps.hw_lock);
- vlv_update_cdclk(dev);
+ intel_update_cdclk(dev);
}
static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv,
int max_pixclk = 0;
for_each_intel_crtc(dev, intel_crtc) {
- if (state)
- crtc_state =
- intel_atomic_get_crtc_state(state, intel_crtc);
- else
- crtc_state = intel_crtc->config;
+ crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
if (IS_ERR(crtc_state))
return PTR_ERR(crtc_state);
return max_pixclk;
}
-static int valleyview_modeset_global_pipes(struct drm_atomic_state *state)
+static int valleyview_modeset_calc_cdclk(struct drm_atomic_state *state)
{
- struct drm_i915_private *dev_priv = to_i915(state->dev);
- struct drm_crtc *crtc;
- struct drm_crtc_state *crtc_state;
- int max_pixclk = intel_mode_max_pixclk(state->dev, state);
- int cdclk, i;
+ struct drm_device *dev = state->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int max_pixclk = intel_mode_max_pixclk(dev, state);
if (max_pixclk < 0)
return max_pixclk;
- if (IS_VALLEYVIEW(dev_priv))
- cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
- else
- cdclk = broxton_calc_cdclk(dev_priv, max_pixclk);
+ to_intel_atomic_state(state)->cdclk =
+ valleyview_calc_cdclk(dev_priv, max_pixclk);
- if (cdclk == dev_priv->cdclk_freq)
- return 0;
+ return 0;
+}
- /* add all active pipes to the state */
- for_each_crtc(state->dev, crtc) {
- if (!crtc->state->enable)
- continue;
+static int broxton_modeset_calc_cdclk(struct drm_atomic_state *state)
+{
+ struct drm_device *dev = state->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int max_pixclk = intel_mode_max_pixclk(dev, state);
- crtc_state = drm_atomic_get_crtc_state(state, crtc);
- if (IS_ERR(crtc_state))
- return PTR_ERR(crtc_state);
- }
+ if (max_pixclk < 0)
+ return max_pixclk;
- /* disable/enable all currently active pipes while we change cdclk */
- for_each_crtc_in_state(state, crtc, crtc_state, i)
- if (crtc_state->enable)
- crtc_state->mode_changed = true;
+ to_intel_atomic_state(state)->cdclk =
+ broxton_calc_cdclk(dev_priv, max_pixclk);
return 0;
}
if (DIV_ROUND_CLOSEST(dev_priv->cdclk_freq, 1000) >= dev_priv->rps.cz_freq) {
/* CHV suggested value is 31 or 63 */
if (IS_CHERRYVIEW(dev_priv))
- credits = PFI_CREDIT_31;
+ credits = PFI_CREDIT_63;
else
credits = PFI_CREDIT(15);
} else {
WARN_ON(I915_READ(GCI_CONTROL) & PFI_CREDIT_RESEND);
}
-static void valleyview_modeset_global_resources(struct drm_atomic_state *old_state)
+static void valleyview_modeset_commit_cdclk(struct drm_atomic_state *old_state)
{
struct drm_device *dev = old_state->dev;
+ unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk;
struct drm_i915_private *dev_priv = dev->dev_private;
- int max_pixclk = intel_mode_max_pixclk(dev, NULL);
- int req_cdclk;
- /* The path in intel_mode_max_pixclk() with a NULL atomic state should
- * never fail. */
- if (WARN_ON(max_pixclk < 0))
- return;
-
- req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
-
- if (req_cdclk != dev_priv->cdclk_freq) {
- /*
- * FIXME: We can end up here with all power domains off, yet
- * with a CDCLK frequency other than the minimum. To account
- * for this take the PIPE-A power domain, which covers the HW
- * blocks needed for the following programming. This can be
- * removed once it's guaranteed that we get here either with
- * the minimum CDCLK set, or the required power domains
- * enabled.
- */
- intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
+ /*
+ * FIXME: We can end up here with all power domains off, yet
+ * with a CDCLK frequency other than the minimum. To account
+ * for this take the PIPE-A power domain, which covers the HW
+ * blocks needed for the following programming. This can be
+ * removed once it's guaranteed that we get here either with
+ * the minimum CDCLK set, or the required power domains
+ * enabled.
+ */
+ intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
- if (IS_CHERRYVIEW(dev))
- cherryview_set_cdclk(dev, req_cdclk);
- else
- valleyview_set_cdclk(dev, req_cdclk);
+ if (IS_CHERRYVIEW(dev))
+ cherryview_set_cdclk(dev, req_cdclk);
+ else
+ valleyview_set_cdclk(dev, req_cdclk);
- vlv_program_pfi_credits(dev_priv);
+ vlv_program_pfi_credits(dev_priv);
- intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A);
- }
+ intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A);
}
static void valleyview_crtc_enable(struct drm_crtc *crtc)
int pipe = intel_crtc->pipe;
bool is_dsi;
- WARN_ON(!crtc->state->enable);
-
- if (intel_crtc->active)
+ if (WARN_ON(intel_crtc->active))
return;
is_dsi = intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DSI);
intel_crtc_load_lut(crtc);
- intel_update_watermarks(crtc);
intel_enable_pipe(intel_crtc);
assert_vblank_disabled(crtc);
struct intel_encoder *encoder;
int pipe = intel_crtc->pipe;
- WARN_ON(!crtc->state->enable);
-
- if (intel_crtc->active)
+ if (WARN_ON(intel_crtc->active))
return;
i9xx_set_pll_dividers(intel_crtc);
struct intel_encoder *encoder;
int pipe = intel_crtc->pipe;
- if (!intel_crtc->active)
- return;
-
/*
* On gen2 planes are double buffered but the pipe isn't, so we must
* wait for planes to fully turn off before disabling the pipe.
intel_crtc->active = false;
intel_update_watermarks(crtc);
+}
- mutex_lock(&dev->struct_mutex);
- intel_fbc_update(dev);
- mutex_unlock(&dev->struct_mutex);
+static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
+{
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+ enum intel_display_power_domain domain;
+ unsigned long domains;
+
+ if (!intel_crtc->active)
+ return;
+
+ if (to_intel_plane_state(crtc->primary->state)->visible) {
+ intel_crtc_wait_for_pending_flips(crtc);
+ intel_pre_disable_primary(crtc);
+ }
+
+ intel_crtc_disable_planes(crtc, crtc->state->plane_mask);
+ dev_priv->display.crtc_disable(crtc);
+ intel_disable_shared_dpll(intel_crtc);
+
+ domains = intel_crtc->enabled_power_domains;
+ for_each_power_domain(domain, domains)
+ intel_display_power_put(dev_priv, domain);
+ intel_crtc->enabled_power_domains = 0;
}
-static void i9xx_crtc_off(struct drm_crtc *crtc)
+/*
+ * turn all crtc's off, but do not adjust state
+ * This has to be paired with a call to intel_modeset_setup_hw_state.
+ */
+int intel_display_suspend(struct drm_device *dev)
{
+ struct drm_mode_config *config = &dev->mode_config;
+ struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
+ struct drm_atomic_state *state;
+ struct drm_crtc *crtc;
+ unsigned crtc_mask = 0;
+ int ret = 0;
+
+ if (WARN_ON(!ctx))
+ return 0;
+
+ lockdep_assert_held(&ctx->ww_ctx);
+ state = drm_atomic_state_alloc(dev);
+ if (WARN_ON(!state))
+ return -ENOMEM;
+
+ state->acquire_ctx = ctx;
+ state->allow_modeset = true;
+
+ for_each_crtc(dev, crtc) {
+ struct drm_crtc_state *crtc_state =
+ drm_atomic_get_crtc_state(state, crtc);
+
+ ret = PTR_ERR_OR_ZERO(crtc_state);
+ if (ret)
+ goto free;
+
+ if (!crtc_state->active)
+ continue;
+
+ crtc_state->active = false;
+ crtc_mask |= 1 << drm_crtc_index(crtc);
+ }
+
+ if (crtc_mask) {
+ ret = drm_atomic_commit(state);
+
+ if (!ret) {
+ for_each_crtc(dev, crtc)
+ if (crtc_mask & (1 << drm_crtc_index(crtc)))
+ crtc->state->active = true;
+
+ return ret;
+ }
+ }
+
+free:
+ if (ret)
+ DRM_ERROR("Suspending crtc's failed with %i\n", ret);
+ drm_atomic_state_free(state);
+ return ret;
}
/* Master function to enable/disable CRTC and corresponding power wells */
-void intel_crtc_control(struct drm_crtc *crtc, bool enable)
+int intel_crtc_control(struct drm_crtc *crtc, bool enable)
{
struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_mode_config *config = &dev->mode_config;
+ struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- enum intel_display_power_domain domain;
- unsigned long domains;
+ struct intel_crtc_state *pipe_config;
+ struct drm_atomic_state *state;
+ int ret;
- if (enable) {
- if (!intel_crtc->active) {
- domains = get_crtc_power_domains(crtc);
- for_each_power_domain(domain, domains)
- intel_display_power_get(dev_priv, domain);
- intel_crtc->enabled_power_domains = domains;
+ if (enable == intel_crtc->active)
+ return 0;
- dev_priv->display.crtc_enable(crtc);
- intel_crtc_enable_planes(crtc);
- }
- } else {
- if (intel_crtc->active) {
- intel_crtc_disable_planes(crtc);
- dev_priv->display.crtc_disable(crtc);
+ if (enable && !crtc->state->enable)
+ return 0;
- domains = intel_crtc->enabled_power_domains;
- for_each_power_domain(domain, domains)
- intel_display_power_put(dev_priv, domain);
- intel_crtc->enabled_power_domains = 0;
- }
+ /* this function should be called with drm_modeset_lock_all for now */
+ if (WARN_ON(!ctx))
+ return -EIO;
+ lockdep_assert_held(&ctx->ww_ctx);
+
+ state = drm_atomic_state_alloc(dev);
+ if (WARN_ON(!state))
+ return -ENOMEM;
+
+ state->acquire_ctx = ctx;
+ state->allow_modeset = true;
+
+ pipe_config = intel_atomic_get_crtc_state(state, intel_crtc);
+ if (IS_ERR(pipe_config)) {
+ ret = PTR_ERR(pipe_config);
+ goto err;
}
+ pipe_config->base.active = enable;
+
+ ret = drm_atomic_commit(state);
+ if (!ret)
+ return ret;
+
+err:
+ DRM_ERROR("Updating crtc active failed with %i\n", ret);
+ drm_atomic_state_free(state);
+ return ret;
}
/**
enable |= intel_encoder->connectors_active;
intel_crtc_control(crtc, enable);
-
- crtc->state->active = enable;
-}
-
-static void intel_crtc_disable(struct drm_crtc *crtc)
-{
- struct drm_device *dev = crtc->dev;
- struct drm_connector *connector;
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- intel_crtc_disable_planes(crtc);
- dev_priv->display.crtc_disable(crtc);
- dev_priv->display.off(crtc);
-
- drm_plane_helper_disable(crtc->primary);
-
- /* Update computed state. */
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
- if (!connector->encoder || !connector->encoder->crtc)
- continue;
-
- if (connector->encoder->crtc != crtc)
- continue;
-
- connector->dpms = DRM_MODE_DPMS_OFF;
- to_intel_encoder(connector->encoder)->connectors_active = false;
- }
}
void intel_encoder_destroy(struct drm_encoder *encoder)
return ret;
}
+static bool pipe_config_supports_ips(struct drm_i915_private *dev_priv,
+ struct intel_crtc_state *pipe_config)
+{
+ if (pipe_config->pipe_bpp > 24)
+ return false;
+
+ /* HSW can handle pixel rate up to cdclk? */
+ if (IS_HASWELL(dev_priv->dev))
+ return true;
+
+ /*
+ * We compare against max which means we must take
+ * the increased cdclk requirement into account when
+ * calculating the new cdclk.
+ *
+ * Should measure whether using a lower cdclk w/o IPS
+ */
+ return ilk_pipe_pixel_rate(pipe_config) <=
+ dev_priv->max_cdclk_freq * 95 / 100;
+}
+
static void hsw_compute_ips_config(struct intel_crtc *crtc,
struct intel_crtc_state *pipe_config)
{
+ struct drm_device *dev = crtc->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
pipe_config->ips_enabled = i915.enable_ips &&
- hsw_crtc_supports_ips(crtc) &&
- pipe_config->pipe_bpp <= 24;
+ hsw_crtc_supports_ips(crtc) &&
+ pipe_config_supports_ips(dev_priv, pipe_config);
}
static int intel_crtc_compute_config(struct intel_crtc *crtc,
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
- int ret;
/* FIXME should check pixel clock limits on all platforms */
if (INTEL_INFO(dev)->gen < 4) {
- int clock_limit =
- dev_priv->display.get_display_clock_speed(dev);
+ int clock_limit = dev_priv->max_cdclk_freq;
/*
* Enable pixel doubling when the dot clock
if (pipe_config->has_pch_encoder)
return ironlake_fdi_compute_config(crtc, pipe_config);
- /* FIXME: remove below call once atomic mode set is place and all crtc
- * related checks called from atomic_crtc_check function */
- ret = 0;
- DRM_DEBUG_KMS("intel_crtc = %p drm_state (pipe_config->base.state) = %p\n",
- crtc, pipe_config->base.state);
- ret = intel_atomic_setup_scalers(dev, crtc, pipe_config);
-
- return ret;
+ return 0;
}
static int skylake_get_display_clock_speed(struct drm_device *dev)
uint32_t cdctl = I915_READ(CDCLK_CTL);
uint32_t linkrate;
- if (!(lcpll1 & LCPLL_PLL_ENABLE)) {
- WARN(1, "LCPLL1 not enabled\n");
+ if (!(lcpll1 & LCPLL_PLL_ENABLE))
return 24000; /* 24MHz is the cd freq with NSSC ref */
- }
if ((cdctl & CDCLK_FREQ_SEL_MASK) == CDCLK_FREQ_540)
return 540000;
return 24000;
}
+static int broxton_get_display_clock_speed(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ uint32_t cdctl = I915_READ(CDCLK_CTL);
+ uint32_t pll_ratio = I915_READ(BXT_DE_PLL_CTL) & BXT_DE_PLL_RATIO_MASK;
+ uint32_t pll_enab = I915_READ(BXT_DE_PLL_ENABLE);
+ int cdclk;
+
+ if (!(pll_enab & BXT_DE_PLL_PLL_ENABLE))
+ return 19200;
+
+ cdclk = 19200 * pll_ratio / 2;
+
+ switch (cdctl & BXT_CDCLK_CD2X_DIV_SEL_MASK) {
+ case BXT_CDCLK_CD2X_DIV_SEL_1:
+ return cdclk; /* 576MHz or 624MHz */
+ case BXT_CDCLK_CD2X_DIV_SEL_1_5:
+ return cdclk * 2 / 3; /* 384MHz */
+ case BXT_CDCLK_CD2X_DIV_SEL_2:
+ return cdclk / 2; /* 288MHz */
+ case BXT_CDCLK_CD2X_DIV_SEL_4:
+ return cdclk / 4; /* 144MHz */
+ }
+
+ /* error case, do as if DE PLL isn't enabled */
+ return 19200;
+}
+
static int broadwell_get_display_clock_speed(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
return 266667;
}
-static int i855_get_display_clock_speed(struct drm_device *dev)
+static int i85x_get_display_clock_speed(struct drm_device *dev)
{
u16 hpllcc = 0;
+
+ /*
+ * 852GM/852GMV only supports 133 MHz and the HPLLCC
+ * encoding is different :(
+ * FIXME is this the right way to detect 852GM/852GMV?
+ */
+ if (dev->pdev->revision == 0x1)
+ return 133333;
+
+ pci_bus_read_config_word(dev->pdev->bus,
+ PCI_DEVFN(0, 3), HPLLCC, &hpllcc);
+
/* Assume that the hardware is in the high speed state. This
* should be the default.
*/
switch (hpllcc & GC_CLOCK_CONTROL_MASK) {
case GC_CLOCK_133_200:
+ case GC_CLOCK_133_200_2:
case GC_CLOCK_100_200:
return 200000;
case GC_CLOCK_166_250:
return 250000;
case GC_CLOCK_100_133:
return 133333;
+ case GC_CLOCK_133_266:
+ case GC_CLOCK_133_266_2:
+ case GC_CLOCK_166_266:
+ return 266667;
}
/* Shouldn't happen */
return 133333;
}
+static unsigned int intel_hpll_vco(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ static const unsigned int blb_vco[8] = {
+ [0] = 3200000,
+ [1] = 4000000,
+ [2] = 5333333,
+ [3] = 4800000,
+ [4] = 6400000,
+ };
+ static const unsigned int pnv_vco[8] = {
+ [0] = 3200000,
+ [1] = 4000000,
+ [2] = 5333333,
+ [3] = 4800000,
+ [4] = 2666667,
+ };
+ static const unsigned int cl_vco[8] = {
+ [0] = 3200000,
+ [1] = 4000000,
+ [2] = 5333333,
+ [3] = 6400000,
+ [4] = 3333333,
+ [5] = 3566667,
+ [6] = 4266667,
+ };
+ static const unsigned int elk_vco[8] = {
+ [0] = 3200000,
+ [1] = 4000000,
+ [2] = 5333333,
+ [3] = 4800000,
+ };
+ static const unsigned int ctg_vco[8] = {
+ [0] = 3200000,
+ [1] = 4000000,
+ [2] = 5333333,
+ [3] = 6400000,
+ [4] = 2666667,
+ [5] = 4266667,
+ };
+ const unsigned int *vco_table;
+ unsigned int vco;
+ uint8_t tmp = 0;
+
+ /* FIXME other chipsets? */
+ if (IS_GM45(dev))
+ vco_table = ctg_vco;
+ else if (IS_G4X(dev))
+ vco_table = elk_vco;
+ else if (IS_CRESTLINE(dev))
+ vco_table = cl_vco;
+ else if (IS_PINEVIEW(dev))
+ vco_table = pnv_vco;
+ else if (IS_G33(dev))
+ vco_table = blb_vco;
+ else
+ return 0;
+
+ tmp = I915_READ(IS_MOBILE(dev) ? HPLLVCO_MOBILE : HPLLVCO);
+
+ vco = vco_table[tmp & 0x7];
+ if (vco == 0)
+ DRM_ERROR("Bad HPLL VCO (HPLLVCO=0x%02x)\n", tmp);
+ else
+ DRM_DEBUG_KMS("HPLL VCO %u kHz\n", vco);
+
+ return vco;
+}
+
+static int gm45_get_display_clock_speed(struct drm_device *dev)
+{
+ unsigned int cdclk_sel, vco = intel_hpll_vco(dev);
+ uint16_t tmp = 0;
+
+ pci_read_config_word(dev->pdev, GCFGC, &tmp);
+
+ cdclk_sel = (tmp >> 12) & 0x1;
+
+ switch (vco) {
+ case 2666667:
+ case 4000000:
+ case 5333333:
+ return cdclk_sel ? 333333 : 222222;
+ case 3200000:
+ return cdclk_sel ? 320000 : 228571;
+ default:
+ DRM_ERROR("Unable to determine CDCLK. HPLL VCO=%u, CFGC=0x%04x\n", vco, tmp);
+ return 222222;
+ }
+}
+
+static int i965gm_get_display_clock_speed(struct drm_device *dev)
+{
+ static const uint8_t div_3200[] = { 16, 10, 8 };
+ static const uint8_t div_4000[] = { 20, 12, 10 };
+ static const uint8_t div_5333[] = { 24, 16, 14 };
+ const uint8_t *div_table;
+ unsigned int cdclk_sel, vco = intel_hpll_vco(dev);
+ uint16_t tmp = 0;
+
+ pci_read_config_word(dev->pdev, GCFGC, &tmp);
+
+ cdclk_sel = ((tmp >> 8) & 0x1f) - 1;
+
+ if (cdclk_sel >= ARRAY_SIZE(div_3200))
+ goto fail;
+
+ switch (vco) {
+ case 3200000:
+ div_table = div_3200;
+ break;
+ case 4000000:
+ div_table = div_4000;
+ break;
+ case 5333333:
+ div_table = div_5333;
+ break;
+ default:
+ goto fail;
+ }
+
+ return DIV_ROUND_CLOSEST(vco, div_table[cdclk_sel]);
+
+fail:
+ DRM_ERROR("Unable to determine CDCLK. HPLL VCO=%u kHz, CFGC=0x%04x\n", vco, tmp);
+ return 200000;
+}
+
+static int g33_get_display_clock_speed(struct drm_device *dev)
+{
+ static const uint8_t div_3200[] = { 12, 10, 8, 7, 5, 16 };
+ static const uint8_t div_4000[] = { 14, 12, 10, 8, 6, 20 };
+ static const uint8_t div_4800[] = { 20, 14, 12, 10, 8, 24 };
+ static const uint8_t div_5333[] = { 20, 16, 12, 12, 8, 28 };
+ const uint8_t *div_table;
+ unsigned int cdclk_sel, vco = intel_hpll_vco(dev);
+ uint16_t tmp = 0;
+
+ pci_read_config_word(dev->pdev, GCFGC, &tmp);
+
+ cdclk_sel = (tmp >> 4) & 0x7;
+
+ if (cdclk_sel >= ARRAY_SIZE(div_3200))
+ goto fail;
+
+ switch (vco) {
+ case 3200000:
+ div_table = div_3200;
+ break;
+ case 4000000:
+ div_table = div_4000;
+ break;
+ case 4800000:
+ div_table = div_4800;
+ break;
+ case 5333333:
+ div_table = div_5333;
+ break;
+ default:
+ goto fail;
+ }
+
+ return DIV_ROUND_CLOSEST(vco, div_table[cdclk_sel]);
+
+fail:
+ DRM_ERROR("Unable to determine CDCLK. HPLL VCO=%u kHz, CFGC=0x%08x\n", vco, tmp);
+ return 190476;
+}
+
static void
intel_reduce_m_n_ratio(uint32_t *num, uint32_t *den)
{
intel_cpu_transcoder_set_m_n(crtc, dp_m_n, dp_m2_n2);
}
-static void vlv_update_pll(struct intel_crtc *crtc,
- struct intel_crtc_state *pipe_config)
+static void vlv_compute_dpll(struct intel_crtc *crtc,
+ struct intel_crtc_state *pipe_config)
{
u32 dpll, dpll_md;
* clock for pipe B, since VGA hotplug / manual detection depends
* on it.
*/
- dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV |
- DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV;
+ dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REF_CLK_ENABLE_VLV |
+ DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_REF_CLK_VLV;
/* We should never disable this, set it here for state tracking */
if (crtc->pipe == PIPE_B)
dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
mutex_unlock(&dev_priv->sb_lock);
}
-static void chv_update_pll(struct intel_crtc *crtc,
- struct intel_crtc_state *pipe_config)
+static void chv_compute_dpll(struct intel_crtc *crtc,
+ struct intel_crtc_state *pipe_config)
{
- pipe_config->dpll_hw_state.dpll = DPLL_SSC_REF_CLOCK_CHV |
- DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS |
+ pipe_config->dpll_hw_state.dpll = DPLL_SSC_REF_CLK_CHV |
+ DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS |
DPLL_VCO_ENABLE;
if (crtc->pipe != PIPE_A)
pipe_config->dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
};
if (IS_CHERRYVIEW(dev)) {
- chv_update_pll(crtc, &pipe_config);
+ chv_compute_dpll(crtc, &pipe_config);
chv_prepare_pll(crtc, &pipe_config);
chv_enable_pll(crtc, &pipe_config);
} else {
- vlv_update_pll(crtc, &pipe_config);
+ vlv_compute_dpll(crtc, &pipe_config);
vlv_prepare_pll(crtc, &pipe_config);
vlv_enable_pll(crtc, &pipe_config);
}
vlv_disable_pll(to_i915(dev), pipe);
}
-static void i9xx_update_pll(struct intel_crtc *crtc,
- struct intel_crtc_state *crtc_state,
- intel_clock_t *reduced_clock,
- int num_connectors)
+static void i9xx_compute_dpll(struct intel_crtc *crtc,
+ struct intel_crtc_state *crtc_state,
+ intel_clock_t *reduced_clock,
+ int num_connectors)
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
}
}
-static void i8xx_update_pll(struct intel_crtc *crtc,
- struct intel_crtc_state *crtc_state,
- intel_clock_t *reduced_clock,
- int num_connectors)
+static void i8xx_compute_dpll(struct intel_crtc *crtc,
+ struct intel_crtc_state *crtc_state,
+ intel_clock_t *reduced_clock,
+ int num_connectors)
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
mode->vsync_end = pipe_config->base.adjusted_mode.crtc_vsync_end;
mode->flags = pipe_config->base.adjusted_mode.flags;
+ mode->type = DRM_MODE_TYPE_DRIVER;
mode->clock = pipe_config->base.adjusted_mode.crtc_clock;
mode->flags |= pipe_config->base.adjusted_mode.flags;
+
+ mode->hsync = drm_mode_hsync(mode);
+ mode->vrefresh = drm_mode_vrefresh(mode);
+ drm_mode_set_name(mode);
}
static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
int refclk, num_connectors = 0;
- intel_clock_t clock, reduced_clock;
- bool ok, has_reduced_clock = false;
- bool is_lvds = false, is_dsi = false;
+ intel_clock_t clock;
+ bool ok;
+ bool is_dsi = false;
struct intel_encoder *encoder;
const intel_limit_t *limit;
struct drm_atomic_state *state = crtc_state->base.state;
encoder = to_intel_encoder(connector_state->best_encoder);
switch (encoder->type) {
- case INTEL_OUTPUT_LVDS:
- is_lvds = true;
- break;
case INTEL_OUTPUT_DSI:
is_dsi = true;
break;
return -EINVAL;
}
- if (is_lvds && dev_priv->lvds_downclock_avail) {
- /*
- * Ensure we match the reduced clock's P to the target
- * clock. If the clocks don't match, we can't switch
- * the display clock by using the FP0/FP1. In such case
- * we will disable the LVDS downclock feature.
- */
- has_reduced_clock =
- dev_priv->display.find_dpll(limit, crtc_state,
- dev_priv->lvds_downclock,
- refclk, &clock,
- &reduced_clock);
- }
/* Compat-code for transition, will disappear. */
crtc_state->dpll.n = clock.n;
crtc_state->dpll.m1 = clock.m1;
}
if (IS_GEN2(dev)) {
- i8xx_update_pll(crtc, crtc_state,
- has_reduced_clock ? &reduced_clock : NULL,
- num_connectors);
+ i8xx_compute_dpll(crtc, crtc_state, NULL,
+ num_connectors);
} else if (IS_CHERRYVIEW(dev)) {
- chv_update_pll(crtc, crtc_state);
+ chv_compute_dpll(crtc, crtc_state);
} else if (IS_VALLEYVIEW(dev)) {
- vlv_update_pll(crtc, crtc_state);
+ vlv_compute_dpll(crtc, crtc_state);
} else {
- i9xx_update_pll(crtc, crtc_state,
- has_reduced_clock ? &reduced_clock : NULL,
- num_connectors);
+ i9xx_compute_dpll(crtc, crtc_state, NULL,
+ num_connectors);
}
return 0;
clock.p1 = (mdiv >> DPIO_P1_SHIFT) & 7;
clock.p2 = (mdiv >> DPIO_P2_SHIFT) & 0x1f;
- vlv_clock(refclk, &clock);
-
- /* clock.dot is the fast clock */
- pipe_config->port_clock = clock.dot / 5;
+ pipe_config->port_clock = vlv_calc_dpll_params(refclk, &clock);
}
static void
int pipe = pipe_config->cpu_transcoder;
enum dpio_channel port = vlv_pipe_to_channel(pipe);
intel_clock_t clock;
- u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2;
+ u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2, pll_dw3;
int refclk = 100000;
mutex_lock(&dev_priv->sb_lock);
pll_dw0 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW0(port));
pll_dw1 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW1(port));
pll_dw2 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW2(port));
+ pll_dw3 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW3(port));
mutex_unlock(&dev_priv->sb_lock);
clock.m1 = (pll_dw1 & 0x7) == DPIO_CHV_M1_DIV_BY_2 ? 2 : 0;
- clock.m2 = ((pll_dw0 & 0xff) << 22) | (pll_dw2 & 0x3fffff);
+ clock.m2 = (pll_dw0 & 0xff) << 22;
+ if (pll_dw3 & DPIO_CHV_FRAC_DIV_EN)
+ clock.m2 |= pll_dw2 & 0x3fffff;
clock.n = (pll_dw1 >> DPIO_CHV_N_DIV_SHIFT) & 0xf;
clock.p1 = (cmn_dw13 >> DPIO_CHV_P1_DIV_SHIFT) & 0x7;
clock.p2 = (cmn_dw13 >> DPIO_CHV_P2_DIV_SHIFT) & 0x1f;
- chv_clock(refclk, &clock);
-
- /* clock.dot is the fast clock */
- pipe_config->port_clock = clock.dot / 5;
+ pipe_config->port_clock = chv_calc_dpll_params(refclk, &clock);
}
static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
struct drm_i915_private *dev_priv = dev->dev_private;
int refclk;
const intel_limit_t *limit;
- bool ret, is_lvds = false;
-
- is_lvds = intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS);
+ bool ret;
refclk = ironlake_get_refclk(crtc_state);
if (!ret)
return false;
- if (is_lvds && dev_priv->lvds_downclock_avail) {
- /*
- * Ensure we match the reduced clock's P to the target clock.
- * If the clocks don't match, we can't switch the display clock
- * by using the FP0/FP1. In such case we will disable the LVDS
- * downclock feature.
- */
- *has_reduced_clock =
- dev_priv->display.find_dpll(limit, crtc_state,
- dev_priv->lvds_downclock,
- refclk, clock,
- reduced_clock);
- }
-
return true;
}
}
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+ intel_update_cdclk(dev_priv->dev);
}
/*
intel_prepare_ddi(dev);
}
-static void broxton_modeset_global_resources(struct drm_atomic_state *old_state)
+static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state)
{
struct drm_device *dev = old_state->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- int max_pixclk = intel_mode_max_pixclk(dev, NULL);
- int req_cdclk;
+ unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk;
- /* see the comment in valleyview_modeset_global_resources */
- if (WARN_ON(max_pixclk < 0))
- return;
-
- req_cdclk = broxton_calc_cdclk(dev_priv, max_pixclk);
-
- if (req_cdclk != dev_priv->cdclk_freq)
- broxton_set_cdclk(dev, req_cdclk);
+ broxton_set_cdclk(dev, req_cdclk);
}
-static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
- struct intel_crtc_state *crtc_state)
+/* compute the max rate for new configuration */
+static int ilk_max_pixel_rate(struct drm_atomic_state *state)
{
- if (!intel_ddi_pll_select(crtc, crtc_state))
- return -EINVAL;
+ struct intel_crtc *intel_crtc;
+ struct intel_crtc_state *crtc_state;
+ int max_pixel_rate = 0;
- crtc->lowfreq_avail = false;
+ for_each_intel_crtc(state->dev, intel_crtc) {
+ int pixel_rate;
- return 0;
-}
+ crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
+ if (IS_ERR(crtc_state))
+ return PTR_ERR(crtc_state);
-static void bxt_get_ddi_pll(struct drm_i915_private *dev_priv,
- enum port port,
- struct intel_crtc_state *pipe_config)
-{
- switch (port) {
+ if (!crtc_state->base.enable)
+ continue;
+
+ pixel_rate = ilk_pipe_pixel_rate(crtc_state);
+
+ /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
+ if (IS_BROADWELL(state->dev) && crtc_state->ips_enabled)
+ pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95);
+
+ max_pixel_rate = max(max_pixel_rate, pixel_rate);
+ }
+
+ return max_pixel_rate;
+}
+
+static void broadwell_set_cdclk(struct drm_device *dev, int cdclk)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t val, data;
+ int ret;
+
+ if (WARN((I915_READ(LCPLL_CTL) &
+ (LCPLL_PLL_DISABLE | LCPLL_PLL_LOCK |
+ LCPLL_CD_CLOCK_DISABLE | LCPLL_ROOT_CD_CLOCK_DISABLE |
+ LCPLL_CD2X_CLOCK_DISABLE | LCPLL_POWER_DOWN_ALLOW |
+ LCPLL_CD_SOURCE_FCLK)) != LCPLL_PLL_LOCK,
+ "trying to change cdclk frequency with cdclk not enabled\n"))
+ return;
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+ ret = sandybridge_pcode_write(dev_priv,
+ BDW_PCODE_DISPLAY_FREQ_CHANGE_REQ, 0x0);
+ mutex_unlock(&dev_priv->rps.hw_lock);
+ if (ret) {
+ DRM_ERROR("failed to inform pcode about cdclk change\n");
+ return;
+ }
+
+ val = I915_READ(LCPLL_CTL);
+ val |= LCPLL_CD_SOURCE_FCLK;
+ I915_WRITE(LCPLL_CTL, val);
+
+ if (wait_for_atomic_us(I915_READ(LCPLL_CTL) &
+ LCPLL_CD_SOURCE_FCLK_DONE, 1))
+ DRM_ERROR("Switching to FCLK failed\n");
+
+ val = I915_READ(LCPLL_CTL);
+ val &= ~LCPLL_CLK_FREQ_MASK;
+
+ switch (cdclk) {
+ case 450000:
+ val |= LCPLL_CLK_FREQ_450;
+ data = 0;
+ break;
+ case 540000:
+ val |= LCPLL_CLK_FREQ_54O_BDW;
+ data = 1;
+ break;
+ case 337500:
+ val |= LCPLL_CLK_FREQ_337_5_BDW;
+ data = 2;
+ break;
+ case 675000:
+ val |= LCPLL_CLK_FREQ_675_BDW;
+ data = 3;
+ break;
+ default:
+ WARN(1, "invalid cdclk frequency\n");
+ return;
+ }
+
+ I915_WRITE(LCPLL_CTL, val);
+
+ val = I915_READ(LCPLL_CTL);
+ val &= ~LCPLL_CD_SOURCE_FCLK;
+ I915_WRITE(LCPLL_CTL, val);
+
+ if (wait_for_atomic_us((I915_READ(LCPLL_CTL) &
+ LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+ DRM_ERROR("Switching back to LCPLL failed\n");
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+ sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, data);
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+ intel_update_cdclk(dev);
+
+ WARN(cdclk != dev_priv->cdclk_freq,
+ "cdclk requested %d kHz but got %d kHz\n",
+ cdclk, dev_priv->cdclk_freq);
+}
+
+static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
+{
+ struct drm_i915_private *dev_priv = to_i915(state->dev);
+ int max_pixclk = ilk_max_pixel_rate(state);
+ int cdclk;
+
+ /*
+ * FIXME should also account for plane ratio
+ * once 64bpp pixel formats are supported.
+ */
+ if (max_pixclk > 540000)
+ cdclk = 675000;
+ else if (max_pixclk > 450000)
+ cdclk = 540000;
+ else if (max_pixclk > 337500)
+ cdclk = 450000;
+ else
+ cdclk = 337500;
+
+ /*
+ * FIXME move the cdclk caclulation to
+ * compute_config() so we can fail gracegully.
+ */
+ if (cdclk > dev_priv->max_cdclk_freq) {
+ DRM_ERROR("requested cdclk (%d kHz) exceeds max (%d kHz)\n",
+ cdclk, dev_priv->max_cdclk_freq);
+ cdclk = dev_priv->max_cdclk_freq;
+ }
+
+ to_intel_atomic_state(state)->cdclk = cdclk;
+
+ return 0;
+}
+
+static void broadwell_modeset_commit_cdclk(struct drm_atomic_state *old_state)
+{
+ struct drm_device *dev = old_state->dev;
+ unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk;
+
+ broadwell_set_cdclk(dev, req_cdclk);
+}
+
+static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
+ struct intel_crtc_state *crtc_state)
+{
+ if (!intel_ddi_pll_select(crtc, crtc_state))
+ return -EINVAL;
+
+ crtc->lowfreq_avail = false;
+
+ return 0;
+}
+
+static void bxt_get_ddi_pll(struct drm_i915_private *dev_priv,
+ enum port port,
+ struct intel_crtc_state *pipe_config)
+{
+ switch (port) {
case PORT_A:
pipe_config->ddi_pll_sel = SKL_DPLL0;
pipe_config->shared_dpll = DPLL_ID_SKL_DPLL1;
retry:
ret = drm_modeset_lock(&config->connection_mutex, ctx);
if (ret)
- goto fail_unlock;
+ goto fail;
/*
* Algorithm gets a little messy:
ret = drm_modeset_lock(&crtc->mutex, ctx);
if (ret)
- goto fail_unlock;
+ goto fail;
ret = drm_modeset_lock(&crtc->primary->mutex, ctx);
if (ret)
- goto fail_unlock;
+ goto fail;
old->dpms_mode = connector->dpms;
old->load_detect_temp = false;
continue;
if (possible_crtc->state->enable)
continue;
- /* This can occur when applying the pipe A quirk on resume. */
- if (to_intel_crtc(possible_crtc)->new_enabled)
- continue;
crtc = possible_crtc;
break;
*/
if (!crtc) {
DRM_DEBUG_KMS("no pipe available for load-detect\n");
- goto fail_unlock;
+ goto fail;
}
ret = drm_modeset_lock(&crtc->mutex, ctx);
if (ret)
- goto fail_unlock;
+ goto fail;
ret = drm_modeset_lock(&crtc->primary->mutex, ctx);
if (ret)
- goto fail_unlock;
- intel_encoder->new_crtc = to_intel_crtc(crtc);
- to_intel_connector(connector)->new_encoder = intel_encoder;
+ goto fail;
intel_crtc = to_intel_crtc(crtc);
- intel_crtc->new_enabled = true;
old->dpms_mode = connector->dpms;
old->load_detect_temp = true;
old->release_fb = NULL;
drm_mode_copy(&crtc_state->base.mode, mode);
- if (intel_set_mode(crtc, state, true)) {
+ if (drm_atomic_commit(state)) {
DRM_DEBUG_KMS("failed to set mode on load-detect pipe\n");
if (old->release_fb)
old->release_fb->funcs->destroy(old->release_fb);
intel_wait_for_vblank(dev, intel_crtc->pipe);
return true;
- fail:
- intel_crtc->new_enabled = crtc->state->enable;
-fail_unlock:
+fail:
drm_atomic_state_free(state);
state = NULL;
if (IS_ERR(crtc_state))
goto fail;
- to_intel_connector(connector)->new_encoder = NULL;
- intel_encoder->new_crtc = NULL;
- intel_crtc->new_enabled = false;
-
connector_state->best_encoder = NULL;
connector_state->crtc = NULL;
if (ret)
goto fail;
- ret = intel_set_mode(crtc, state, true);
+ ret = drm_atomic_commit(state);
if (ret)
goto fail;
u32 dpll = pipe_config->dpll_hw_state.dpll;
u32 fp;
intel_clock_t clock;
+ int port_clock;
int refclk = i9xx_pll_refclk(dev, pipe_config);
if ((dpll & DISPLAY_RATE_SELECT_FPA1) == 0)
}
if (IS_PINEVIEW(dev))
- pineview_clock(refclk, &clock);
+ port_clock = pnv_calc_dpll_params(refclk, &clock);
else
- i9xx_clock(refclk, &clock);
+ port_clock = i9xx_calc_dpll_params(refclk, &clock);
} else {
u32 lvds = IS_I830(dev) ? 0 : I915_READ(LVDS);
bool is_lvds = (pipe == 1) && (lvds & LVDS_PORT_EN);
clock.p2 = 2;
}
- i9xx_clock(refclk, &clock);
+ port_clock = i9xx_calc_dpll_params(refclk, &clock);
}
/*
* port_clock to compute adjusted_mode.crtc_clock in the
* encoder's get_config() function.
*/
- pipe_config->port_clock = clock.dot;
+ pipe_config->port_clock = port_clock;
}
int intel_dotclock_calculate(int link_freq,
return mode;
}
-static void intel_decrease_pllclock(struct drm_crtc *crtc)
-{
- struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
- if (!HAS_GMCH_DISPLAY(dev))
- return;
-
- if (!dev_priv->lvds_downclock_avail)
- return;
-
- /*
- * Since this is called by a timer, we should never get here in
- * the manual case.
- */
- if (!HAS_PIPE_CXSR(dev) && intel_crtc->lowfreq_avail) {
- int pipe = intel_crtc->pipe;
- int dpll_reg = DPLL(pipe);
- int dpll;
-
- DRM_DEBUG_DRIVER("downclocking LVDS\n");
-
- assert_panel_unlocked(dev_priv, pipe);
-
- dpll = I915_READ(dpll_reg);
- dpll |= DISPLAY_RATE_SELECT_FPA1;
- I915_WRITE(dpll_reg, dpll);
- intel_wait_for_vblank(dev, pipe);
- dpll = I915_READ(dpll_reg);
- if (!(dpll & DISPLAY_RATE_SELECT_FPA1))
- DRM_DEBUG_DRIVER("failed to downclock LVDS!\n");
- }
-
-}
-
void intel_mark_busy(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
void intel_mark_idle(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct drm_crtc *crtc;
if (!dev_priv->mm.busy)
return;
dev_priv->mm.busy = false;
- for_each_crtc(dev, crtc) {
- if (!crtc->primary->fb)
- continue;
-
- intel_decrease_pllclock(crtc);
- }
-
if (INTEL_INFO(dev)->gen >= 6)
gen6_rps_idle(dev->dev_private);
{
struct intel_unpin_work *work =
container_of(__work, struct intel_unpin_work, work);
- struct drm_device *dev = work->crtc->dev;
- enum pipe pipe = to_intel_crtc(work->crtc)->pipe;
+ struct intel_crtc *crtc = to_intel_crtc(work->crtc);
+ struct drm_device *dev = crtc->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_plane *primary = crtc->base.primary;
mutex_lock(&dev->struct_mutex);
- intel_unpin_fb_obj(work->old_fb, work->crtc->primary->state);
+ intel_unpin_fb_obj(work->old_fb, primary->state);
drm_gem_object_unreference(&work->pending_flip_obj->base);
- intel_fbc_update(dev);
+ intel_fbc_update(dev_priv);
if (work->flip_queued_req)
i915_gem_request_assign(&work->flip_queued_req, NULL);
mutex_unlock(&dev->struct_mutex);
- intel_frontbuffer_flip_complete(dev, INTEL_FRONTBUFFER_PRIMARY(pipe));
+ intel_frontbuffer_flip_complete(dev, to_intel_plane(primary)->frontbuffer_bit);
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);
+ BUG_ON(atomic_read(&crtc->unpin_work_count) == 0);
+ atomic_dec(&crtc->unpin_work_count);
kfree(work);
}
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
u32 flip_mask;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
intel_ring_emit(ring, 0); /* aux display base address, unused */
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
u32 flip_mask;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
intel_ring_emit(ring, MI_NOOP);
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
uint32_t pf, pipesrc;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
intel_ring_emit(ring, pf | pipesrc);
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
uint32_t pf, pipesrc;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
intel_ring_emit(ring, pf | pipesrc);
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
uint32_t plane_bit = 0;
int len, ret;
* then do the cacheline alignment, and finally emit the
* MI_DISPLAY_FLIP.
*/
- ret = intel_ring_cacheline_align(ring);
+ ret = intel_ring_cacheline_align(req);
if (ret)
return ret;
- ret = intel_ring_begin(ring, len);
+ ret = intel_ring_begin(req, len);
if (ret)
return ret;
intel_ring_emit(ring, (MI_NOOP));
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
static void intel_do_mmio_flip(struct intel_crtc *intel_crtc)
{
struct drm_device *dev = intel_crtc->base.dev;
- bool atomic_update;
u32 start_vbl_count;
intel_mark_page_flip_active(intel_crtc);
- atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+ intel_pipe_update_start(intel_crtc, &start_vbl_count);
if (INTEL_INFO(dev)->gen >= 9)
skl_do_mmio_flip(intel_crtc);
/* use_mmio_flip() retricts MMIO flips to ilk+ */
ilk_do_mmio_flip(intel_crtc);
- if (atomic_update)
- intel_pipe_update_end(intel_crtc, start_vbl_count);
+ intel_pipe_update_end(intel_crtc, start_vbl_count);
}
static void intel_mmio_flip_work_func(struct work_struct *work)
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
return -ENODEV;
struct intel_unpin_work *work;
struct intel_engine_cs *ring;
bool mmio_flip;
+ struct drm_i915_gem_request *request = NULL;
int ret;
/*
*/
ret = intel_pin_and_fence_fb_obj(crtc->primary, fb,
crtc->primary->state,
- mmio_flip ? i915_gem_request_get_ring(obj->last_write_req) : ring);
+ mmio_flip ? i915_gem_request_get_ring(obj->last_write_req) : ring, &request);
if (ret)
goto cleanup_pending;
i915_gem_request_assign(&work->flip_queued_req,
obj->last_write_req);
} else {
- if (obj->last_write_req) {
- ret = i915_gem_check_olr(obj->last_write_req);
+ if (!request) {
+ ret = i915_gem_request_alloc(ring, ring->default_context, &request);
if (ret)
goto cleanup_unpin;
}
- ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
+ ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request,
page_flip_flags);
if (ret)
goto cleanup_unpin;
- i915_gem_request_assign(&work->flip_queued_req,
- intel_ring_get_request(ring));
+ i915_gem_request_assign(&work->flip_queued_req, request);
}
+ if (request)
+ i915_add_request_no_flush(request);
+
work->flip_queued_vblank = drm_crtc_vblank_count(crtc);
work->enable_stall_check = true;
i915_gem_track_fb(intel_fb_obj(work->old_fb), obj,
- INTEL_FRONTBUFFER_PRIMARY(pipe));
-
- intel_fbc_disable(dev);
- intel_frontbuffer_flip_prepare(dev, INTEL_FRONTBUFFER_PRIMARY(pipe));
+ to_intel_plane(primary)->frontbuffer_bit);
mutex_unlock(&dev->struct_mutex);
+ intel_fbc_disable(dev_priv);
+ intel_frontbuffer_flip_prepare(dev,
+ to_intel_plane(primary)->frontbuffer_bit);
+
trace_i915_flip_request(intel_crtc->plane, obj);
return 0;
cleanup_unpin:
intel_unpin_fb_obj(fb, crtc->primary->state);
cleanup_pending:
+ if (request)
+ i915_gem_request_cancel(request);
atomic_dec(&intel_crtc->unpin_work_count);
mutex_unlock(&dev->struct_mutex);
cleanup:
kfree(work);
if (ret == -EIO) {
+ struct drm_atomic_state *state;
+ struct drm_plane_state *plane_state;
+
out_hang:
- ret = intel_plane_restore(primary);
+ state = drm_atomic_state_alloc(dev);
+ if (!state)
+ return -ENOMEM;
+ state->acquire_ctx = drm_modeset_legacy_acquire_ctx(crtc);
+
+retry:
+ plane_state = drm_atomic_get_plane_state(state, primary);
+ ret = PTR_ERR_OR_ZERO(plane_state);
+ if (!ret) {
+ drm_atomic_set_fb_for_plane(plane_state, fb);
+
+ ret = drm_atomic_set_crtc_for_plane(plane_state, crtc);
+ if (!ret)
+ ret = drm_atomic_commit(state);
+ }
+
+ if (ret == -EDEADLK) {
+ drm_modeset_backoff(state->acquire_ctx);
+ drm_atomic_state_clear(state);
+ goto retry;
+ }
+
+ if (ret)
+ drm_atomic_state_free(state);
+
if (ret == 0 && event) {
spin_lock_irq(&dev->event_lock);
drm_send_vblank_event(dev, pipe, event);
return ret;
}
-static const struct drm_crtc_helper_funcs intel_helper_funcs = {
- .mode_set_base_atomic = intel_pipe_set_base_atomic,
- .load_lut = intel_crtc_load_lut,
- .atomic_begin = intel_begin_crtc_commit,
- .atomic_flush = intel_finish_crtc_commit,
-};
/**
- * intel_modeset_update_staged_output_state
+ * intel_wm_need_update - Check whether watermarks need updating
+ * @plane: drm plane
+ * @state: new plane state
*
- * Updates the staged output configuration state, e.g. after we've read out the
- * current hw state.
+ * Check current plane state versus the new one to determine whether
+ * watermarks need to be recalculated.
+ *
+ * Returns true or false.
*/
-static void intel_modeset_update_staged_output_state(struct drm_device *dev)
+static bool intel_wm_need_update(struct drm_plane *plane,
+ struct drm_plane_state *state)
{
- struct intel_crtc *crtc;
- struct intel_encoder *encoder;
- struct intel_connector *connector;
-
- for_each_intel_connector(dev, connector) {
- connector->new_encoder =
- to_intel_encoder(connector->base.encoder);
- }
+ /* Update watermarks on tiling changes. */
+ if (!plane->state->fb || !state->fb ||
+ plane->state->fb->modifier[0] != state->fb->modifier[0] ||
+ plane->state->rotation != state->rotation)
+ return true;
- for_each_intel_encoder(dev, encoder) {
- encoder->new_crtc =
- to_intel_crtc(encoder->base.crtc);
- }
+ if (plane->state->crtc_w != state->crtc_w)
+ return true;
- for_each_intel_crtc(dev, crtc) {
- crtc->new_enabled = crtc->base.state->enable;
- }
+ return false;
}
-/* Transitional helper to copy current connector/encoder state to
- * connector->state. This is needed so that code that is partially
- * converted to atomic does the right thing.
- */
-static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
+int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
+ struct drm_plane_state *plane_state)
{
- struct intel_connector *connector;
+ struct drm_crtc *crtc = crtc_state->crtc;
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ struct drm_plane *plane = plane_state->plane;
+ struct drm_device *dev = crtc->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_plane_state *old_plane_state =
+ to_intel_plane_state(plane->state);
+ int idx = intel_crtc->base.base.id, ret;
+ int i = drm_plane_index(plane);
+ bool mode_changed = needs_modeset(crtc_state);
+ bool was_crtc_enabled = crtc->state->active;
+ bool is_crtc_enabled = crtc_state->active;
+
+ bool turn_off, turn_on, visible, was_visible;
+ struct drm_framebuffer *fb = plane_state->fb;
+
+ if (crtc_state && INTEL_INFO(dev)->gen >= 9 &&
+ plane->type != DRM_PLANE_TYPE_CURSOR) {
+ ret = skl_update_scaler_plane(
+ to_intel_crtc_state(crtc_state),
+ to_intel_plane_state(plane_state));
+ if (ret)
+ return ret;
+ }
- for_each_intel_connector(dev, connector) {
- if (connector->base.encoder) {
- connector->base.state->best_encoder =
- connector->base.encoder;
- connector->base.state->crtc =
- connector->base.encoder->crtc;
- } else {
- connector->base.state->best_encoder = NULL;
- connector->base.state->crtc = NULL;
+ /*
+ * Disabling a plane is always okay; we just need to update
+ * fb tracking in a special way since cleanup_fb() won't
+ * get called by the plane helpers.
+ */
+ if (old_plane_state->base.fb && !fb)
+ intel_crtc->atomic.disabled_planes |= 1 << i;
+
+ was_visible = old_plane_state->visible;
+ visible = to_intel_plane_state(plane_state)->visible;
+
+ if (!was_crtc_enabled && WARN_ON(was_visible))
+ was_visible = false;
+
+ if (!is_crtc_enabled && WARN_ON(visible))
+ visible = false;
+
+ if (!was_visible && !visible)
+ return 0;
+
+ turn_off = was_visible && (!visible || mode_changed);
+ turn_on = visible && (!was_visible || mode_changed);
+
+ DRM_DEBUG_ATOMIC("[CRTC:%i] has [PLANE:%i] with fb %i\n", idx,
+ plane->base.id, fb ? fb->base.id : -1);
+
+ DRM_DEBUG_ATOMIC("[PLANE:%i] visible %i -> %i, off %i, on %i, ms %i\n",
+ plane->base.id, was_visible, visible,
+ turn_off, turn_on, mode_changed);
+
+ if (turn_on) {
+ intel_crtc->atomic.update_wm_pre = true;
+ /* must disable cxsr around plane enable/disable */
+ if (plane->type != DRM_PLANE_TYPE_CURSOR) {
+ intel_crtc->atomic.disable_cxsr = true;
+ /* to potentially re-enable cxsr */
+ intel_crtc->atomic.wait_vblank = true;
+ intel_crtc->atomic.update_wm_post = true;
+ }
+ } else if (turn_off) {
+ intel_crtc->atomic.update_wm_post = true;
+ /* must disable cxsr around plane enable/disable */
+ if (plane->type != DRM_PLANE_TYPE_CURSOR) {
+ if (is_crtc_enabled)
+ intel_crtc->atomic.wait_vblank = true;
+ intel_crtc->atomic.disable_cxsr = true;
}
+ } else if (intel_wm_need_update(plane, plane_state)) {
+ intel_crtc->atomic.update_wm_pre = true;
}
-}
-/* Fixup legacy state after an atomic state swap.
- */
-static void intel_modeset_fixup_state(struct drm_atomic_state *state)
-{
- struct intel_crtc *crtc;
- struct intel_encoder *encoder;
- struct intel_connector *connector;
+ if (visible)
+ intel_crtc->atomic.fb_bits |=
+ to_intel_plane(plane)->frontbuffer_bit;
- for_each_intel_connector(state->dev, connector) {
- connector->base.encoder = connector->base.state->best_encoder;
- if (connector->base.encoder)
- connector->base.encoder->crtc =
- connector->base.state->crtc;
- }
+ switch (plane->type) {
+ case DRM_PLANE_TYPE_PRIMARY:
+ intel_crtc->atomic.wait_for_flips = true;
+ intel_crtc->atomic.pre_disable_primary = turn_off;
+ intel_crtc->atomic.post_enable_primary = turn_on;
- /* Update crtc of disabled encoders */
- for_each_intel_encoder(state->dev, encoder) {
- int num_connectors = 0;
+ if (turn_off) {
+ /*
+ * FIXME: Actually if we will still have any other
+ * plane enabled on the pipe we could let IPS enabled
+ * still, but for now lets consider that when we make
+ * primary invisible by setting DSPCNTR to 0 on
+ * update_primary_plane function IPS needs to be
+ * disable.
+ */
+ intel_crtc->atomic.disable_ips = true;
- for_each_intel_connector(state->dev, connector)
- if (connector->base.encoder == &encoder->base)
- num_connectors++;
+ intel_crtc->atomic.disable_fbc = true;
+ }
- if (num_connectors == 0)
- encoder->base.crtc = NULL;
- }
+ /*
+ * FBC does not work on some platforms for rotated
+ * planes, so disable it when rotation is not 0 and
+ * update it when rotation is set back to 0.
+ *
+ * FIXME: This is redundant with the fbc update done in
+ * the primary plane enable function except that that
+ * one is done too late. We eventually need to unify
+ * this.
+ */
- for_each_intel_crtc(state->dev, crtc) {
- crtc->base.enabled = crtc->base.state->enable;
- crtc->config = to_intel_crtc_state(crtc->base.state);
+ if (visible &&
+ INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
+ dev_priv->fbc.crtc == intel_crtc &&
+ plane_state->rotation != BIT(DRM_ROTATE_0))
+ intel_crtc->atomic.disable_fbc = true;
+
+ /*
+ * BDW signals flip done immediately if the plane
+ * is disabled, even if the plane enable is already
+ * armed to occur at the next vblank :(
+ */
+ if (turn_on && IS_BROADWELL(dev))
+ intel_crtc->atomic.wait_vblank = true;
+
+ intel_crtc->atomic.update_fbc |= visible || mode_changed;
+ break;
+ case DRM_PLANE_TYPE_CURSOR:
+ break;
+ case DRM_PLANE_TYPE_OVERLAY:
+ if (turn_off && !mode_changed) {
+ intel_crtc->atomic.wait_vblank = true;
+ intel_crtc->atomic.update_sprite_watermarks |=
+ 1 << i;
+ }
}
+ return 0;
}
-static void
-connected_sink_compute_bpp(struct intel_connector *connector,
- struct intel_crtc_state *pipe_config)
+static bool encoders_cloneable(const struct intel_encoder *a,
+ const struct intel_encoder *b)
{
- int bpp = pipe_config->pipe_bpp;
+ /* masks could be asymmetric, so check both ways */
+ return a == b || (a->cloneable & (1 << b->type) &&
+ b->cloneable & (1 << a->type));
+}
- DRM_DEBUG_KMS("[CONNECTOR:%d:%s] checking for sink bpp constrains\n",
+static bool check_single_encoder_cloning(struct drm_atomic_state *state,
+ struct intel_crtc *crtc,
+ struct intel_encoder *encoder)
+{
+ struct intel_encoder *source_encoder;
+ struct drm_connector *connector;
+ struct drm_connector_state *connector_state;
+ int i;
+
+ for_each_connector_in_state(state, connector, connector_state, i) {
+ if (connector_state->crtc != &crtc->base)
+ continue;
+
+ source_encoder =
+ to_intel_encoder(connector_state->best_encoder);
+ if (!encoders_cloneable(encoder, source_encoder))
+ return false;
+ }
+
+ return true;
+}
+
+static bool check_encoder_cloning(struct drm_atomic_state *state,
+ struct intel_crtc *crtc)
+{
+ struct intel_encoder *encoder;
+ struct drm_connector *connector;
+ struct drm_connector_state *connector_state;
+ int i;
+
+ for_each_connector_in_state(state, connector, connector_state, i) {
+ if (connector_state->crtc != &crtc->base)
+ continue;
+
+ encoder = to_intel_encoder(connector_state->best_encoder);
+ if (!check_single_encoder_cloning(state, crtc, encoder))
+ return false;
+ }
+
+ return true;
+}
+
+static int intel_crtc_atomic_check(struct drm_crtc *crtc,
+ struct drm_crtc_state *crtc_state)
+{
+ struct drm_device *dev = crtc->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ struct intel_crtc_state *pipe_config =
+ to_intel_crtc_state(crtc_state);
+ struct drm_atomic_state *state = crtc_state->state;
+ int ret, idx = crtc->base.id;
+ bool mode_changed = needs_modeset(crtc_state);
+
+ if (mode_changed && !check_encoder_cloning(state, intel_crtc)) {
+ DRM_DEBUG_KMS("rejecting invalid cloning configuration\n");
+ return -EINVAL;
+ }
+
+ I915_STATE_WARN(crtc->state->active != intel_crtc->active,
+ "[CRTC:%i] mismatch between state->active(%i) and crtc->active(%i)\n",
+ idx, crtc->state->active, intel_crtc->active);
+
+ if (mode_changed && !crtc_state->active)
+ intel_crtc->atomic.update_wm_post = true;
+
+ if (mode_changed && crtc_state->enable &&
+ dev_priv->display.crtc_compute_clock &&
+ !WARN_ON(pipe_config->shared_dpll != DPLL_ID_PRIVATE)) {
+ ret = dev_priv->display.crtc_compute_clock(intel_crtc,
+ pipe_config);
+ if (ret)
+ return ret;
+ }
+
+ ret = 0;
+ if (INTEL_INFO(dev)->gen >= 9) {
+ if (mode_changed)
+ ret = skl_update_scaler_crtc(pipe_config);
+
+ if (!ret)
+ ret = intel_atomic_setup_scalers(dev, intel_crtc,
+ pipe_config);
+ }
+
+ return ret;
+}
+
+static const struct drm_crtc_helper_funcs intel_helper_funcs = {
+ .mode_set_base_atomic = intel_pipe_set_base_atomic,
+ .load_lut = intel_crtc_load_lut,
+ .atomic_begin = intel_begin_crtc_commit,
+ .atomic_flush = intel_finish_crtc_commit,
+ .atomic_check = intel_crtc_atomic_check,
+};
+
+static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
+{
+ struct intel_connector *connector;
+
+ for_each_intel_connector(dev, connector) {
+ if (connector->base.encoder) {
+ connector->base.state->best_encoder =
+ connector->base.encoder;
+ connector->base.state->crtc =
+ connector->base.encoder->crtc;
+ } else {
+ connector->base.state->best_encoder = NULL;
+ connector->base.state->crtc = NULL;
+ }
+ }
+}
+
+static void
+connected_sink_compute_bpp(struct intel_connector *connector,
+ struct intel_crtc_state *pipe_config)
+{
+ int bpp = pipe_config->pipe_bpp;
+
+ DRM_DEBUG_KMS("[CONNECTOR:%d:%s] checking for sink bpp constrains\n",
connector->base.base.id,
connector->base.name);
DRM_DEBUG_KMS("double wide: %i\n", pipe_config->double_wide);
if (IS_BROXTON(dev)) {
- DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: ebb0: 0x%x, "
+ DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: ebb0: 0x%x, ebb4: 0x%x,"
"pll0: 0x%x, pll1: 0x%x, pll2: 0x%x, pll3: 0x%x, "
- "pll6: 0x%x, pll8: 0x%x, pcsdw12: 0x%x\n",
+ "pll6: 0x%x, pll8: 0x%x, pll9: 0x%x, pll10: 0x%x, pcsdw12: 0x%x\n",
pipe_config->ddi_pll_sel,
pipe_config->dpll_hw_state.ebb0,
+ pipe_config->dpll_hw_state.ebb4,
pipe_config->dpll_hw_state.pll0,
pipe_config->dpll_hw_state.pll1,
pipe_config->dpll_hw_state.pll2,
pipe_config->dpll_hw_state.pll3,
pipe_config->dpll_hw_state.pll6,
pipe_config->dpll_hw_state.pll8,
+ pipe_config->dpll_hw_state.pll9,
+ pipe_config->dpll_hw_state.pll10,
pipe_config->dpll_hw_state.pcsdw12);
} else if (IS_SKYLAKE(dev)) {
DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: "
}
}
-static bool encoders_cloneable(const struct intel_encoder *a,
- const struct intel_encoder *b)
-{
- /* masks could be asymmetric, so check both ways */
- return a == b || (a->cloneable & (1 << b->type) &&
- b->cloneable & (1 << a->type));
-}
-
-static bool check_single_encoder_cloning(struct drm_atomic_state *state,
- struct intel_crtc *crtc,
- struct intel_encoder *encoder)
-{
- struct intel_encoder *source_encoder;
- struct drm_connector *connector;
- struct drm_connector_state *connector_state;
- int i;
-
- for_each_connector_in_state(state, connector, connector_state, i) {
- if (connector_state->crtc != &crtc->base)
- continue;
-
- source_encoder =
- to_intel_encoder(connector_state->best_encoder);
- if (!encoders_cloneable(encoder, source_encoder))
- return false;
- }
-
- return true;
-}
-
-static bool check_encoder_cloning(struct drm_atomic_state *state,
- struct intel_crtc *crtc)
-{
- struct intel_encoder *encoder;
- struct drm_connector *connector;
- struct drm_connector_state *connector_state;
- int i;
-
- for_each_connector_in_state(state, connector, connector_state, i) {
- if (connector_state->crtc != &crtc->base)
- continue;
-
- encoder = to_intel_encoder(connector_state->best_encoder);
- if (!check_single_encoder_cloning(state, crtc, encoder))
- return false;
- }
-
- return true;
-}
-
static bool check_digital_port_conflicts(struct drm_atomic_state *state)
{
struct drm_device *dev = state->dev;
static int
intel_modeset_pipe_config(struct drm_crtc *crtc,
- struct drm_atomic_state *state,
struct intel_crtc_state *pipe_config)
{
+ struct drm_atomic_state *state = pipe_config->base.state;
struct intel_encoder *encoder;
struct drm_connector *connector;
struct drm_connector_state *connector_state;
int i;
bool retry = true;
- if (!check_encoder_cloning(state, to_intel_crtc(crtc))) {
- DRM_DEBUG_KMS("rejecting invalid cloning configuration\n");
- return -EINVAL;
- }
-
- if (!check_digital_port_conflicts(state)) {
- DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
- return -EINVAL;
- }
-
clear_intel_crtc_state(pipe_config);
pipe_config->cpu_transcoder =
DRM_DEBUG_KMS("plane bpp: %i, pipe bpp: %i, dithering: %i\n",
base_bpp, pipe_config->pipe_bpp, pipe_config->dither);
- return 0;
fail:
return ret;
}
return false;
}
-static bool
-needs_modeset(struct drm_crtc_state *state)
-{
- return state->mode_changed || state->active_changed;
-}
-
static void
intel_modeset_update_state(struct drm_atomic_state *state)
{
struct drm_device *dev = state->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_encoder *intel_encoder;
struct drm_crtc *crtc;
struct drm_crtc_state *crtc_state;
struct drm_connector *connector;
int i;
- intel_shared_dpll_commit(dev_priv);
+ intel_shared_dpll_commit(state);
for_each_intel_encoder(dev, intel_encoder) {
if (!intel_encoder->base.crtc)
continue;
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- if (crtc != intel_encoder->base.crtc)
- continue;
-
- if (crtc_state->enable && needs_modeset(crtc_state))
- intel_encoder->connectors_active = false;
+ crtc = intel_encoder->base.crtc;
+ crtc_state = drm_atomic_get_existing_crtc_state(state, crtc);
+ if (!crtc_state || !needs_modeset(crtc->state))
+ continue;
- break;
- }
+ intel_encoder->connectors_active = false;
}
- drm_atomic_helper_swap_state(state->dev, state);
- intel_modeset_fixup_state(state);
+ drm_atomic_helper_update_legacy_modeset_state(state->dev, state);
/* Double check state. */
- for_each_crtc(dev, crtc) {
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
WARN_ON(crtc->state->enable != intel_crtc_in_use(crtc));
+
+ to_intel_crtc(crtc)->config = to_intel_crtc_state(crtc->state);
+
+ /* Update hwmode for vblank functions */
+ if (crtc->state->active)
+ crtc->hwmode = crtc->state->adjusted_mode;
+ else
+ crtc->hwmode.crtc_clock = 0;
}
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
if (!connector->encoder || !connector->encoder->crtc)
continue;
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- if (crtc != connector->encoder->crtc)
- continue;
-
- if (crtc->state->enable && needs_modeset(crtc->state)) {
- struct drm_property *dpms_property =
- dev->mode_config.dpms_property;
+ crtc = connector->encoder->crtc;
+ crtc_state = drm_atomic_get_existing_crtc_state(state, crtc);
+ if (!crtc_state || !needs_modeset(crtc->state))
+ continue;
- connector->dpms = DRM_MODE_DPMS_ON;
- drm_object_property_set_value(&connector->base,
- dpms_property,
- DRM_MODE_DPMS_ON);
+ if (crtc->state->active) {
+ struct drm_property *dpms_property =
+ dev->mode_config.dpms_property;
- intel_encoder = to_intel_encoder(connector->encoder);
- intel_encoder->connectors_active = true;
- }
+ connector->dpms = DRM_MODE_DPMS_ON;
+ drm_object_property_set_value(&connector->base, dpms_property, DRM_MODE_DPMS_ON);
- break;
- }
+ intel_encoder = to_intel_encoder(connector->encoder);
+ intel_encoder->connectors_active = true;
+ } else
+ connector->dpms = DRM_MODE_DPMS_OFF;
}
-
}
static bool intel_fuzzy_clock_check(int clock1, int clock2)
base.head) \
if (mask & (1 <<(intel_crtc)->pipe))
+
+static bool
+intel_compare_m_n(unsigned int m, unsigned int n,
+ unsigned int m2, unsigned int n2,
+ bool exact)
+{
+ if (m == m2 && n == n2)
+ return true;
+
+ if (exact || !m || !n || !m2 || !n2)
+ return false;
+
+ BUILD_BUG_ON(DATA_LINK_M_N_MASK > INT_MAX);
+
+ if (m > m2) {
+ while (m > m2) {
+ m2 <<= 1;
+ n2 <<= 1;
+ }
+ } else if (m < m2) {
+ while (m < m2) {
+ m <<= 1;
+ n <<= 1;
+ }
+ }
+
+ return m == m2 && n == n2;
+}
+
+static bool
+intel_compare_link_m_n(const struct intel_link_m_n *m_n,
+ struct intel_link_m_n *m2_n2,
+ bool adjust)
+{
+ if (m_n->tu == m2_n2->tu &&
+ intel_compare_m_n(m_n->gmch_m, m_n->gmch_n,
+ m2_n2->gmch_m, m2_n2->gmch_n, !adjust) &&
+ intel_compare_m_n(m_n->link_m, m_n->link_n,
+ m2_n2->link_m, m2_n2->link_n, !adjust)) {
+ if (adjust)
+ *m2_n2 = *m_n;
+
+ return true;
+ }
+
+ return false;
+}
+
static bool
intel_pipe_config_compare(struct drm_device *dev,
struct intel_crtc_state *current_config,
- struct intel_crtc_state *pipe_config)
+ struct intel_crtc_state *pipe_config,
+ bool adjust)
{
+ bool ret = true;
+
+#define INTEL_ERR_OR_DBG_KMS(fmt, ...) \
+ do { \
+ if (!adjust) \
+ DRM_ERROR(fmt, ##__VA_ARGS__); \
+ else \
+ DRM_DEBUG_KMS(fmt, ##__VA_ARGS__); \
+ } while (0)
+
#define PIPE_CONF_CHECK_X(name) \
if (current_config->name != pipe_config->name) { \
- DRM_ERROR("mismatch in " #name " " \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name " " \
"(expected 0x%08x, found 0x%08x)\n", \
current_config->name, \
pipe_config->name); \
- return false; \
+ ret = false; \
}
#define PIPE_CONF_CHECK_I(name) \
if (current_config->name != pipe_config->name) { \
- DRM_ERROR("mismatch in " #name " " \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name " " \
"(expected %i, found %i)\n", \
current_config->name, \
pipe_config->name); \
- return false; \
+ ret = false; \
+ }
+
+#define PIPE_CONF_CHECK_M_N(name) \
+ if (!intel_compare_link_m_n(¤t_config->name, \
+ &pipe_config->name,\
+ adjust)) { \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name " " \
+ "(expected tu %i gmch %i/%i link %i/%i, " \
+ "found tu %i, gmch %i/%i link %i/%i)\n", \
+ current_config->name.tu, \
+ current_config->name.gmch_m, \
+ current_config->name.gmch_n, \
+ current_config->name.link_m, \
+ current_config->name.link_n, \
+ pipe_config->name.tu, \
+ pipe_config->name.gmch_m, \
+ pipe_config->name.gmch_n, \
+ pipe_config->name.link_m, \
+ pipe_config->name.link_n); \
+ ret = false; \
+ }
+
+#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) \
+ if (!intel_compare_link_m_n(¤t_config->name, \
+ &pipe_config->name, adjust) && \
+ !intel_compare_link_m_n(¤t_config->alt_name, \
+ &pipe_config->name, adjust)) { \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name " " \
+ "(expected tu %i gmch %i/%i link %i/%i, " \
+ "or tu %i gmch %i/%i link %i/%i, " \
+ "found tu %i, gmch %i/%i link %i/%i)\n", \
+ current_config->name.tu, \
+ current_config->name.gmch_m, \
+ current_config->name.gmch_n, \
+ current_config->name.link_m, \
+ current_config->name.link_n, \
+ current_config->alt_name.tu, \
+ current_config->alt_name.gmch_m, \
+ current_config->alt_name.gmch_n, \
+ current_config->alt_name.link_m, \
+ current_config->alt_name.link_n, \
+ pipe_config->name.tu, \
+ pipe_config->name.gmch_m, \
+ pipe_config->name.gmch_n, \
+ pipe_config->name.link_m, \
+ pipe_config->name.link_n); \
+ ret = false; \
}
/* This is required for BDW+ where there is only one set of registers for
#define PIPE_CONF_CHECK_I_ALT(name, alt_name) \
if ((current_config->name != pipe_config->name) && \
(current_config->alt_name != pipe_config->name)) { \
- DRM_ERROR("mismatch in " #name " " \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name " " \
"(expected %i or %i, found %i)\n", \
current_config->name, \
current_config->alt_name, \
pipe_config->name); \
- return false; \
+ ret = false; \
}
#define PIPE_CONF_CHECK_FLAGS(name, mask) \
if ((current_config->name ^ pipe_config->name) & (mask)) { \
- DRM_ERROR("mismatch in " #name "(" #mask ") " \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name "(" #mask ") " \
"(expected %i, found %i)\n", \
current_config->name & (mask), \
pipe_config->name & (mask)); \
- return false; \
+ ret = false; \
}
#define PIPE_CONF_CHECK_CLOCK_FUZZY(name) \
if (!intel_fuzzy_clock_check(current_config->name, pipe_config->name)) { \
- DRM_ERROR("mismatch in " #name " " \
+ INTEL_ERR_OR_DBG_KMS("mismatch in " #name " " \
"(expected %i, found %i)\n", \
current_config->name, \
pipe_config->name); \
- return false; \
+ ret = false; \
}
#define PIPE_CONF_QUIRK(quirk) \
PIPE_CONF_CHECK_I(has_pch_encoder);
PIPE_CONF_CHECK_I(fdi_lanes);
- PIPE_CONF_CHECK_I(fdi_m_n.gmch_m);
- PIPE_CONF_CHECK_I(fdi_m_n.gmch_n);
- PIPE_CONF_CHECK_I(fdi_m_n.link_m);
- PIPE_CONF_CHECK_I(fdi_m_n.link_n);
- PIPE_CONF_CHECK_I(fdi_m_n.tu);
+ PIPE_CONF_CHECK_M_N(fdi_m_n);
PIPE_CONF_CHECK_I(has_dp_encoder);
if (INTEL_INFO(dev)->gen < 8) {
- PIPE_CONF_CHECK_I(dp_m_n.gmch_m);
- PIPE_CONF_CHECK_I(dp_m_n.gmch_n);
- PIPE_CONF_CHECK_I(dp_m_n.link_m);
- PIPE_CONF_CHECK_I(dp_m_n.link_n);
- PIPE_CONF_CHECK_I(dp_m_n.tu);
-
- if (current_config->has_drrs) {
- PIPE_CONF_CHECK_I(dp_m2_n2.gmch_m);
- PIPE_CONF_CHECK_I(dp_m2_n2.gmch_n);
- PIPE_CONF_CHECK_I(dp_m2_n2.link_m);
- PIPE_CONF_CHECK_I(dp_m2_n2.link_n);
- PIPE_CONF_CHECK_I(dp_m2_n2.tu);
- }
- } else {
- PIPE_CONF_CHECK_I_ALT(dp_m_n.gmch_m, dp_m2_n2.gmch_m);
- PIPE_CONF_CHECK_I_ALT(dp_m_n.gmch_n, dp_m2_n2.gmch_n);
- PIPE_CONF_CHECK_I_ALT(dp_m_n.link_m, dp_m2_n2.link_m);
- PIPE_CONF_CHECK_I_ALT(dp_m_n.link_n, dp_m2_n2.link_n);
- PIPE_CONF_CHECK_I_ALT(dp_m_n.tu, dp_m2_n2.tu);
- }
+ PIPE_CONF_CHECK_M_N(dp_m_n);
+
+ PIPE_CONF_CHECK_I(has_drrs);
+ if (current_config->has_drrs)
+ PIPE_CONF_CHECK_M_N(dp_m2_n2);
+ } else
+ PIPE_CONF_CHECK_M_N_ALT(dp_m_n, dp_m2_n2);
PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hdisplay);
PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_htotal);
#undef PIPE_CONF_CHECK_FLAGS
#undef PIPE_CONF_CHECK_CLOCK_FUZZY
#undef PIPE_CONF_QUIRK
+#undef INTEL_ERR_OR_DBG_KMS
- return true;
+ return ret;
}
static void check_wm_state(struct drm_device *dev)
struct intel_connector *connector;
for_each_intel_connector(dev, connector) {
+ struct drm_encoder *encoder = connector->base.encoder;
+ struct drm_connector_state *state = connector->base.state;
+
/* This also checks the encoder/connector hw state with the
* ->get_hw_state callbacks. */
intel_connector_check_state(connector);
- I915_STATE_WARN(&connector->new_encoder->base != connector->base.encoder,
+ I915_STATE_WARN(state->best_encoder != encoder,
"connector's staged encoder doesn't match current encoder\n");
}
}
encoder->base.base.id,
encoder->base.name);
- I915_STATE_WARN(&encoder->new_crtc->base != encoder->base.crtc,
- "encoder's stage crtc doesn't match current crtc\n");
I915_STATE_WARN(encoder->connectors_active && !encoder->base.crtc,
"encoder's active_connectors set, but no crtc\n");
enabled = true;
if (connector->base.dpms != DRM_MODE_DPMS_OFF)
active = true;
+
+ I915_STATE_WARN(connector->base.state->crtc !=
+ encoder->base.crtc,
+ "connector's crtc doesn't match encoder crtc\n");
}
/*
* for MST connectors if we unplug the connector is gone
"crtc active state doesn't match with hw state "
"(expected %i, found %i)\n", crtc->active, active);
- if (active &&
- !intel_pipe_config_compare(dev, crtc->config, &pipe_config)) {
+ I915_STATE_WARN(crtc->active != crtc->base.state->active,
+ "transitional active state does not match atomic hw state "
+ "(expected %i, found %i)\n", crtc->base.state->active, crtc->active);
+
+ if (!active)
+ continue;
+
+ if (!intel_pipe_config_compare(dev, crtc->config,
+ &pipe_config, false)) {
I915_STATE_WARN(1, "pipe state doesn't match!\n");
intel_dump_pipe_config(crtc, &pipe_config,
"[hw state]");
crtc->scanline_offset = 1;
}
-static struct intel_crtc_state *
-intel_modeset_compute_config(struct drm_crtc *crtc,
- struct drm_atomic_state *state)
-{
- struct intel_crtc_state *pipe_config;
- int ret = 0;
-
- ret = drm_atomic_add_affected_connectors(state, crtc);
- if (ret)
- return ERR_PTR(ret);
-
- ret = drm_atomic_helper_check_modeset(state->dev, state);
- if (ret)
- return ERR_PTR(ret);
-
- /*
- * Note this needs changes when we start tracking multiple modes
- * and crtcs. At that point we'll need to compute the whole config
- * (i.e. one pipe_config for each crtc) rather than just the one
- * for this crtc.
- */
- pipe_config = intel_atomic_get_crtc_state(state, to_intel_crtc(crtc));
- if (IS_ERR(pipe_config))
- return pipe_config;
-
- if (!pipe_config->base.enable)
- return pipe_config;
-
- ret = intel_modeset_pipe_config(crtc, state, pipe_config);
- if (ret)
- return ERR_PTR(ret);
-
- /* Check things that can only be changed through modeset */
- if (pipe_config->has_audio !=
- to_intel_crtc(crtc)->config->has_audio)
- pipe_config->base.mode_changed = true;
-
- /*
- * Note we have an issue here with infoframes: current code
- * only updates them on the full mode set path per hw
- * requirements. So here we should be checking for any
- * required changes and forcing a mode set.
- */
-
- intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config,"[modeset]");
-
- ret = drm_atomic_helper_check_planes(state->dev, state);
- if (ret)
- return ERR_PTR(ret);
-
- return pipe_config;
-}
-
-static int __intel_set_mode_setup_plls(struct drm_atomic_state *state)
+static void intel_modeset_clear_plls(struct drm_atomic_state *state)
{
struct drm_device *dev = state->dev;
struct drm_i915_private *dev_priv = to_i915(dev);
- unsigned clear_pipes = 0;
+ struct intel_shared_dpll_config *shared_dpll = NULL;
struct intel_crtc *intel_crtc;
struct intel_crtc_state *intel_crtc_state;
struct drm_crtc *crtc;
struct drm_crtc_state *crtc_state;
- int ret = 0;
int i;
if (!dev_priv->display.crtc_compute_clock)
- return 0;
+ return;
for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ int dpll;
+
intel_crtc = to_intel_crtc(crtc);
intel_crtc_state = to_intel_crtc_state(crtc_state);
+ dpll = intel_crtc_state->shared_dpll;
- if (needs_modeset(crtc_state)) {
- clear_pipes |= 1 << intel_crtc->pipe;
- intel_crtc_state->shared_dpll = DPLL_ID_PRIVATE;
- }
- }
+ if (!needs_modeset(crtc_state) || dpll == DPLL_ID_PRIVATE)
+ continue;
- ret = intel_shared_dpll_start_config(dev_priv, clear_pipes);
- if (ret)
- goto done;
+ intel_crtc_state->shared_dpll = DPLL_ID_PRIVATE;
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- if (!needs_modeset(crtc_state) || !crtc_state->enable)
- continue;
-
- intel_crtc = to_intel_crtc(crtc);
- intel_crtc_state = to_intel_crtc_state(crtc_state);
-
- ret = dev_priv->display.crtc_compute_clock(intel_crtc,
- intel_crtc_state);
- if (ret) {
- intel_shared_dpll_abort_config(dev_priv);
- goto done;
- }
- }
+ if (!shared_dpll)
+ shared_dpll = intel_atomic_get_shared_dpll_state(state);
-done:
- return ret;
-}
-
-/* Code that should eventually be part of atomic_check() */
-static int __intel_set_mode_checks(struct drm_atomic_state *state)
-{
- struct drm_device *dev = state->dev;
- int ret;
-
- /*
- * See if the config requires any additional preparation, e.g.
- * to adjust global state with pipes off. We need to do this
- * here so we can get the modeset_pipe updated config for the new
- * mode set on this crtc. For other crtcs we need to use the
- * adjusted_mode bits in the crtc directly.
- */
- if (IS_VALLEYVIEW(dev) || IS_BROXTON(dev)) {
- ret = valleyview_modeset_global_pipes(state);
- if (ret)
- return ret;
+ shared_dpll[dpll].crtc_mask &= ~(1 << intel_crtc->pipe);
}
-
- ret = __intel_set_mode_setup_plls(state);
- if (ret)
- return ret;
-
- return 0;
}
-static int __intel_set_mode(struct drm_crtc *modeset_crtc,
- struct intel_crtc_state *pipe_config)
+/*
+ * This implements the workaround described in the "notes" section of the mode
+ * set sequence documentation. When going from no pipes or single pipe to
+ * multiple pipes, and planes are enabled after the pipe, we need to wait at
+ * least 2 vblanks on the first pipe before enabling planes on the second pipe.
+ */
+static int haswell_mode_set_planes_workaround(struct drm_atomic_state *state)
{
- struct drm_device *dev = modeset_crtc->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct drm_atomic_state *state = pipe_config->base.state;
- struct drm_crtc *crtc;
struct drm_crtc_state *crtc_state;
- int ret = 0;
+ struct intel_crtc *intel_crtc;
+ struct drm_crtc *crtc;
+ struct intel_crtc_state *first_crtc_state = NULL;
+ struct intel_crtc_state *other_crtc_state = NULL;
+ enum pipe first_pipe = INVALID_PIPE, enabled_pipe = INVALID_PIPE;
int i;
- ret = __intel_set_mode_checks(state);
- if (ret < 0)
- return ret;
-
- ret = drm_atomic_helper_prepare_planes(dev, state);
- if (ret)
- return ret;
-
+ /* look at all crtc's that are going to be enabled in during modeset */
for_each_crtc_in_state(state, crtc, crtc_state, i) {
- if (!needs_modeset(crtc_state))
+ intel_crtc = to_intel_crtc(crtc);
+
+ if (!crtc_state->active || !needs_modeset(crtc_state))
continue;
- if (!crtc_state->enable) {
- if (crtc->state->enable)
- intel_crtc_disable(crtc);
- } else if (crtc->state->enable) {
- intel_crtc_disable_planes(crtc);
- dev_priv->display.crtc_disable(crtc);
+ if (first_crtc_state) {
+ other_crtc_state = to_intel_crtc_state(crtc_state);
+ break;
+ } else {
+ first_crtc_state = to_intel_crtc_state(crtc_state);
+ first_pipe = intel_crtc->pipe;
}
}
- /* crtc->mode is already used by the ->mode_set callbacks, hence we need
- * to set it here already despite that we pass it down the callchain.
- *
- * Note we'll need to fix this up when we start tracking multiple
- * pipes; here we assume a single modeset_pipe and only track the
- * single crtc and mode.
- */
- if (pipe_config->base.enable && needs_modeset(&pipe_config->base)) {
- modeset_crtc->mode = pipe_config->base.mode;
-
- /*
- * Calculate and store various constants which
- * are later needed by vblank and swap-completion
- * timestamping. They are derived from true hwmode.
- */
- drm_calc_timestamping_constants(modeset_crtc,
- &pipe_config->base.adjusted_mode);
- }
-
- /* Only after disabling all output pipelines that will be changed can we
- * update the the output configuration. */
- intel_modeset_update_state(state);
+ /* No workaround needed? */
+ if (!first_crtc_state)
+ return 0;
- /* The state has been swaped above, so state actually contains the
- * old state now. */
+ /* w/a possibly needed, check how many crtc's are already enabled. */
+ for_each_intel_crtc(state->dev, intel_crtc) {
+ struct intel_crtc_state *pipe_config;
- modeset_update_crtc_power_domains(state);
+ pipe_config = intel_atomic_get_crtc_state(state, intel_crtc);
+ if (IS_ERR(pipe_config))
+ return PTR_ERR(pipe_config);
- drm_atomic_helper_commit_planes(dev, state);
+ pipe_config->hsw_workaround_pipe = INVALID_PIPE;
- /* Now enable the clocks, plane, pipe, and connectors that we set up. */
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- if (!needs_modeset(crtc->state) || !crtc->state->enable)
+ if (!pipe_config->base.active ||
+ needs_modeset(&pipe_config->base))
continue;
- update_scanline_offset(to_intel_crtc(crtc));
+ /* 2 or more enabled crtcs means no need for w/a */
+ if (enabled_pipe != INVALID_PIPE)
+ return 0;
- dev_priv->display.crtc_enable(crtc);
- intel_crtc_enable_planes(crtc);
+ enabled_pipe = intel_crtc->pipe;
}
- /* FIXME: add subpixel order */
-
- drm_atomic_helper_cleanup_planes(dev, state);
-
- drm_atomic_state_free(state);
+ if (enabled_pipe != INVALID_PIPE)
+ first_crtc_state->hsw_workaround_pipe = enabled_pipe;
+ else if (other_crtc_state)
+ other_crtc_state->hsw_workaround_pipe = first_pipe;
return 0;
}
-static int intel_set_mode_with_config(struct drm_crtc *crtc,
- struct intel_crtc_state *pipe_config,
- bool force_restore)
+static int intel_modeset_all_pipes(struct drm_atomic_state *state)
{
- int ret;
+ struct drm_crtc *crtc;
+ struct drm_crtc_state *crtc_state;
+ int ret = 0;
- ret = __intel_set_mode(crtc, pipe_config);
+ /* add all active pipes to the state */
+ for_each_crtc(state->dev, crtc) {
+ crtc_state = drm_atomic_get_crtc_state(state, crtc);
+ if (IS_ERR(crtc_state))
+ return PTR_ERR(crtc_state);
- if (ret == 0 && force_restore) {
- intel_modeset_update_staged_output_state(crtc->dev);
- intel_modeset_check_state(crtc->dev);
- }
+ if (!crtc_state->active || needs_modeset(crtc_state))
+ continue;
- return ret;
-}
+ crtc_state->mode_changed = true;
-static int intel_set_mode(struct drm_crtc *crtc,
- struct drm_atomic_state *state,
- bool force_restore)
-{
- struct intel_crtc_state *pipe_config;
- int ret = 0;
+ ret = drm_atomic_add_affected_connectors(state, crtc);
+ if (ret)
+ break;
- pipe_config = intel_modeset_compute_config(crtc, state);
- if (IS_ERR(pipe_config)) {
- ret = PTR_ERR(pipe_config);
- goto out;
+ ret = drm_atomic_add_affected_planes(state, crtc);
+ if (ret)
+ break;
}
- ret = intel_set_mode_with_config(crtc, pipe_config, force_restore);
- if (ret)
- goto out;
-
-out:
return ret;
}
-void intel_crtc_restore_mode(struct drm_crtc *crtc)
+
+static int intel_modeset_checks(struct drm_atomic_state *state)
{
- struct drm_device *dev = crtc->dev;
- struct drm_atomic_state *state;
- struct intel_encoder *encoder;
- struct intel_connector *connector;
- struct drm_connector_state *connector_state;
- struct intel_crtc_state *crtc_state;
+ struct drm_device *dev = state->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
int ret;
- state = drm_atomic_state_alloc(dev);
- if (!state) {
- DRM_DEBUG_KMS("[CRTC:%d] mode restore failed, out of memory",
- crtc->base.id);
- return;
- }
-
- state->acquire_ctx = dev->mode_config.acquire_ctx;
-
- /* The force restore path in the HW readout code relies on the staged
- * config still keeping the user requested config while the actual
- * state has been overwritten by the configuration read from HW. We
- * need to copy the staged config to the atomic state, otherwise the
- * mode set will just reapply the state the HW is already in. */
- for_each_intel_encoder(dev, encoder) {
- if (&encoder->new_crtc->base != crtc)
- continue;
-
- for_each_intel_connector(dev, connector) {
- if (connector->new_encoder != encoder)
- continue;
-
- connector_state = drm_atomic_get_connector_state(state, &connector->base);
- if (IS_ERR(connector_state)) {
- DRM_DEBUG_KMS("Failed to add [CONNECTOR:%d:%s] to state: %ld\n",
- connector->base.base.id,
- connector->base.name,
- PTR_ERR(connector_state));
- continue;
- }
-
- connector_state->crtc = crtc;
- connector_state->best_encoder = &encoder->base;
- }
- }
-
- crtc_state = intel_atomic_get_crtc_state(state, to_intel_crtc(crtc));
- if (IS_ERR(crtc_state)) {
- DRM_DEBUG_KMS("Failed to add [CRTC:%d] to state: %ld\n",
- crtc->base.id, PTR_ERR(crtc_state));
- drm_atomic_state_free(state);
- return;
+ if (!check_digital_port_conflicts(state)) {
+ DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
+ return -EINVAL;
}
- crtc_state->base.active = crtc_state->base.enable =
- to_intel_crtc(crtc)->new_enabled;
+ /*
+ * See if the config requires any additional preparation, e.g.
+ * to adjust global state with pipes off. We need to do this
+ * here so we can get the modeset_pipe updated config for the new
+ * mode set on this crtc. For other crtcs we need to use the
+ * adjusted_mode bits in the crtc directly.
+ */
+ if (dev_priv->display.modeset_calc_cdclk) {
+ unsigned int cdclk;
- drm_mode_copy(&crtc_state->base.mode, &crtc->mode);
+ ret = dev_priv->display.modeset_calc_cdclk(state);
- intel_modeset_setup_plane_state(state, crtc, &crtc->mode,
- crtc->primary->fb, crtc->x, crtc->y);
+ cdclk = to_intel_atomic_state(state)->cdclk;
+ if (!ret && cdclk != dev_priv->cdclk_freq)
+ ret = intel_modeset_all_pipes(state);
- ret = intel_set_mode(crtc, state, false);
- if (ret)
- drm_atomic_state_free(state);
-}
-
-#undef for_each_intel_crtc_masked
+ if (ret < 0)
+ return ret;
+ } else
+ to_intel_atomic_state(state)->cdclk = dev_priv->cdclk_freq;
-static bool intel_connector_in_mode_set(struct intel_connector *connector,
- struct drm_mode_set *set)
-{
- int ro;
+ intel_modeset_clear_plls(state);
- for (ro = 0; ro < set->num_connectors; ro++)
- if (set->connectors[ro] == &connector->base)
- return true;
+ if (IS_HASWELL(dev))
+ return haswell_mode_set_planes_workaround(state);
- return false;
+ return 0;
}
-static int
-intel_modeset_stage_output_state(struct drm_device *dev,
- struct drm_mode_set *set,
- struct drm_atomic_state *state)
+/**
+ * intel_atomic_check - validate state object
+ * @dev: drm device
+ * @state: state to validate
+ */
+static int intel_atomic_check(struct drm_device *dev,
+ struct drm_atomic_state *state)
{
- struct intel_connector *connector;
- struct drm_connector *drm_connector;
- struct drm_connector_state *connector_state;
struct drm_crtc *crtc;
struct drm_crtc_state *crtc_state;
- int i, ret;
+ int ret, i;
+ bool any_ms = false;
- /* The upper layers ensure that we either disable a crtc or have a list
- * of connectors. For paranoia, double-check this. */
- WARN_ON(!set->fb && (set->num_connectors != 0));
- WARN_ON(set->fb && (set->num_connectors == 0));
+ ret = drm_atomic_helper_check_modeset(dev, state);
+ if (ret)
+ return ret;
- for_each_intel_connector(dev, connector) {
- bool in_mode_set = intel_connector_in_mode_set(connector, set);
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ struct intel_crtc_state *pipe_config =
+ to_intel_crtc_state(crtc_state);
+ bool modeset, recalc = false;
- if (!in_mode_set && connector->base.state->crtc != set->crtc)
+ if (!crtc_state->enable) {
+ if (needs_modeset(crtc_state))
+ any_ms = true;
continue;
-
- connector_state =
- drm_atomic_get_connector_state(state, &connector->base);
- if (IS_ERR(connector_state))
- return PTR_ERR(connector_state);
-
- if (in_mode_set) {
- int pipe = to_intel_crtc(set->crtc)->pipe;
- connector_state->best_encoder =
- &intel_find_encoder(connector, pipe)->base;
}
- if (connector->base.state->crtc != set->crtc)
- continue;
-
- /* If we disable the crtc, disable all its connectors. Also, if
- * the connector is on the changing crtc but not on the new
- * connector list, disable it. */
- if (!set->fb || !in_mode_set) {
- connector_state->best_encoder = NULL;
-
- DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n",
- connector->base.base.id,
- connector->base.name);
- }
- }
- /* connector->new_encoder is now updated for all connectors. */
+ modeset = needs_modeset(crtc_state);
+ /* see comment in intel_modeset_readout_hw_state */
+ if (!modeset && crtc_state->mode_blob != crtc->state->mode_blob &&
+ pipe_config->quirks & PIPE_CONFIG_QUIRK_INHERITED_MODE)
+ recalc = true;
- for_each_connector_in_state(state, drm_connector, connector_state, i) {
- connector = to_intel_connector(drm_connector);
+ if (!modeset && !recalc)
+ continue;
- if (!connector_state->best_encoder) {
- ret = drm_atomic_set_crtc_for_connector(connector_state,
- NULL);
+ if (recalc) {
+ ret = drm_atomic_add_affected_connectors(state, crtc);
if (ret)
return ret;
-
- continue;
}
- if (intel_connector_in_mode_set(connector, set)) {
- struct drm_crtc *crtc = connector->base.state->crtc;
+ ret = intel_modeset_pipe_config(crtc, pipe_config);
+ if (ret)
+ return ret;
- /* If this connector was in a previous crtc, add it
- * to the state. We might need to disable it. */
- if (crtc) {
- crtc_state =
- drm_atomic_get_crtc_state(state, crtc);
- if (IS_ERR(crtc_state))
- return PTR_ERR(crtc_state);
- }
+ if (recalc && (!i915.fastboot ||
+ !intel_pipe_config_compare(state->dev,
+ to_intel_crtc_state(crtc->state),
+ pipe_config, true))) {
+ modeset = crtc_state->mode_changed = true;
- ret = drm_atomic_set_crtc_for_connector(connector_state,
- set->crtc);
+ ret = drm_atomic_add_affected_planes(state, crtc);
if (ret)
return ret;
}
- /* Make sure the new CRTC will work with the encoder */
- if (!drm_encoder_crtc_ok(connector_state->best_encoder,
- connector_state->crtc)) {
- return -EINVAL;
- }
-
- DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n",
- connector->base.base.id,
- connector->base.name,
- connector_state->crtc->base.id);
-
- if (connector_state->best_encoder != &connector->encoder->base)
- connector->encoder =
- to_intel_encoder(connector_state->best_encoder);
+ any_ms = modeset;
+ intel_dump_pipe_config(to_intel_crtc(crtc),
+ pipe_config,
+ modeset ? "[modeset]" : "[fastboot]");
}
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- bool has_connectors;
+ if (any_ms) {
+ ret = intel_modeset_checks(state);
- ret = drm_atomic_add_affected_connectors(state, crtc);
if (ret)
return ret;
+ } else
+ to_intel_atomic_state(state)->cdclk =
+ to_i915(state->dev)->cdclk_freq;
+
+ return drm_atomic_helper_check_planes(state->dev, state);
+}
+
+/**
+ * intel_atomic_commit - commit validated state object
+ * @dev: DRM device
+ * @state: the top-level driver state object
+ * @async: asynchronous commit
+ *
+ * This function commits a top-level state object that has been validated
+ * with drm_atomic_helper_check().
+ *
+ * FIXME: Atomic modeset support for i915 is not yet complete. At the moment
+ * we can only handle plane-related operations and do not yet support
+ * asynchronous commit.
+ *
+ * RETURNS
+ * Zero for success or -errno.
+ */
+static int intel_atomic_commit(struct drm_device *dev,
+ struct drm_atomic_state *state,
+ bool async)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_crtc *crtc;
+ struct drm_crtc_state *crtc_state;
+ int ret = 0;
+ int i;
+ bool any_ms = false;
- has_connectors = !!drm_atomic_connectors_for_crtc(state, crtc);
- if (has_connectors != crtc_state->enable)
- crtc_state->enable =
- crtc_state->active = has_connectors;
+ if (async) {
+ DRM_DEBUG_KMS("i915 does not yet support async commit\n");
+ return -EINVAL;
}
- ret = intel_modeset_setup_plane_state(state, set->crtc, set->mode,
- set->fb, set->x, set->y);
+ ret = drm_atomic_helper_prepare_planes(dev, state);
if (ret)
return ret;
- crtc_state = drm_atomic_get_crtc_state(state, set->crtc);
- if (IS_ERR(crtc_state))
- return PTR_ERR(crtc_state);
-
- if (set->mode)
- drm_mode_copy(&crtc_state->mode, set->mode);
+ drm_atomic_helper_swap_state(dev, state);
- if (set->num_connectors)
- crtc_state->active = true;
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- return 0;
-}
+ if (!needs_modeset(crtc->state))
+ continue;
-static bool primary_plane_visible(struct drm_crtc *crtc)
-{
- struct intel_plane_state *plane_state =
- to_intel_plane_state(crtc->primary->state);
+ any_ms = true;
+ intel_pre_plane_update(intel_crtc);
- return plane_state->visible;
-}
+ if (crtc_state->active) {
+ intel_crtc_disable_planes(crtc, crtc_state->plane_mask);
+ dev_priv->display.crtc_disable(crtc);
+ intel_crtc->active = false;
+ intel_disable_shared_dpll(intel_crtc);
+ }
+ }
-static int intel_crtc_set_config(struct drm_mode_set *set)
-{
- struct drm_device *dev;
- struct drm_atomic_state *state = NULL;
- struct intel_crtc_state *pipe_config;
- bool primary_plane_was_visible;
- int ret;
+ /* Only after disabling all output pipelines that will be changed can we
+ * update the the output configuration. */
+ intel_modeset_update_state(state);
- BUG_ON(!set);
- BUG_ON(!set->crtc);
- BUG_ON(!set->crtc->helper_private);
+ /* The state has been swaped above, so state actually contains the
+ * old state now. */
+ if (any_ms)
+ modeset_update_crtc_power_domains(state);
- /* Enforce sane interface api - has been abused by the fb helper. */
- BUG_ON(!set->mode && set->fb);
- BUG_ON(set->fb && set->num_connectors == 0);
+ /* Now enable the clocks, plane, pipe, and connectors that we set up. */
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ bool modeset = needs_modeset(crtc->state);
- if (set->fb) {
- DRM_DEBUG_KMS("[CRTC:%d] [FB:%d] #connectors=%d (x y) (%i %i)\n",
- set->crtc->base.id, set->fb->base.id,
- (int)set->num_connectors, set->x, set->y);
- } else {
- DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id);
- }
+ if (modeset && crtc->state->active) {
+ update_scanline_offset(to_intel_crtc(crtc));
+ dev_priv->display.crtc_enable(crtc);
+ }
- dev = set->crtc->dev;
+ if (!modeset)
+ intel_pre_plane_update(intel_crtc);
- state = drm_atomic_state_alloc(dev);
- if (!state)
- return -ENOMEM;
+ drm_atomic_helper_commit_planes_on_crtc(crtc_state);
+ intel_post_plane_update(intel_crtc);
+ }
- state->acquire_ctx = dev->mode_config.acquire_ctx;
+ /* FIXME: add subpixel order */
- ret = intel_modeset_stage_output_state(dev, set, state);
- if (ret)
- goto out;
+ drm_atomic_helper_wait_for_vblanks(dev, state);
+ drm_atomic_helper_cleanup_planes(dev, state);
+ drm_atomic_state_free(state);
- pipe_config = intel_modeset_compute_config(set->crtc, state);
- if (IS_ERR(pipe_config)) {
- ret = PTR_ERR(pipe_config);
- goto out;
- }
+ if (any_ms)
+ intel_modeset_check_state(dev);
- intel_update_pipe_size(to_intel_crtc(set->crtc));
+ return 0;
+}
- primary_plane_was_visible = primary_plane_visible(set->crtc);
+void intel_crtc_restore_mode(struct drm_crtc *crtc)
+{
+ struct drm_device *dev = crtc->dev;
+ struct drm_atomic_state *state;
+ struct drm_crtc_state *crtc_state;
+ int ret;
- ret = intel_set_mode_with_config(set->crtc, pipe_config, true);
+ state = drm_atomic_state_alloc(dev);
+ if (!state) {
+ DRM_DEBUG_KMS("[CRTC:%d] crtc restore failed, out of memory",
+ crtc->base.id);
+ return;
+ }
- if (ret == 0 &&
- pipe_config->base.enable &&
- pipe_config->base.planes_changed &&
- !needs_modeset(&pipe_config->base)) {
- struct intel_crtc *intel_crtc = to_intel_crtc(set->crtc);
+ state->acquire_ctx = drm_modeset_legacy_acquire_ctx(crtc);
- /*
- * We need to make sure the primary plane is re-enabled if it
- * has previously been turned off.
- */
- if (ret == 0 && !primary_plane_was_visible &&
- primary_plane_visible(set->crtc)) {
- WARN_ON(!intel_crtc->active);
- intel_post_enable_primary(set->crtc);
- }
+retry:
+ crtc_state = drm_atomic_get_crtc_state(state, crtc);
+ ret = PTR_ERR_OR_ZERO(crtc_state);
+ if (!ret) {
+ if (!crtc_state->active)
+ goto out;
- /*
- * In the fastboot case this may be our only check of the
- * state after boot. It would be better to only do it on
- * the first update, but we don't have a nice way of doing that
- * (and really, set_config isn't used much for high freq page
- * flipping, so increasing its cost here shouldn't be a big
- * deal).
- */
- if (i915.fastboot && ret == 0)
- intel_modeset_check_state(set->crtc->dev);
+ crtc_state->mode_changed = true;
+ ret = drm_atomic_commit(state);
}
- if (ret) {
- DRM_DEBUG_KMS("failed to set mode on [CRTC:%d], err = %d\n",
- set->crtc->base.id, ret);
+ if (ret == -EDEADLK) {
+ drm_atomic_state_clear(state);
+ drm_modeset_backoff(state->acquire_ctx);
+ goto retry;
}
-out:
if (ret)
+out:
drm_atomic_state_free(state);
- return ret;
}
+#undef for_each_intel_crtc_masked
+
static const struct drm_crtc_funcs intel_crtc_funcs = {
.gamma_set = intel_crtc_gamma_set,
- .set_config = intel_crtc_set_config,
+ .set_config = drm_atomic_helper_set_config,
.destroy = intel_crtc_destroy,
.page_flip = intel_crtc_page_flip,
.atomic_duplicate_state = intel_crtc_duplicate_state,
static void intel_shared_dpll_init(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (HAS_DDI(dev))
- intel_ddi_pll_init(dev);
- else if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev))
- ibx_pch_dpll_init(dev);
- else
- dev_priv->num_shared_dpll = 0;
-
- BUG_ON(dev_priv->num_shared_dpll > I915_NUM_PLLS);
-}
-
-/**
- * intel_wm_need_update - Check whether watermarks need updating
- * @plane: drm plane
- * @state: new plane state
- *
- * Check current plane state versus the new one to determine whether
- * watermarks need to be recalculated.
- *
- * Returns true or false.
- */
-bool intel_wm_need_update(struct drm_plane *plane,
- struct drm_plane_state *state)
-{
- /* Update watermarks on tiling changes. */
- if (!plane->state->fb || !state->fb ||
- plane->state->fb->modifier[0] != state->fb->modifier[0] ||
- plane->state->rotation != state->rotation)
- return true;
+ struct drm_i915_private *dev_priv = dev->dev_private;
- return false;
+ intel_update_cdclk(dev);
+
+ if (HAS_DDI(dev))
+ intel_ddi_pll_init(dev);
+ else if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev))
+ ibx_pch_dpll_init(dev);
+ else
+ dev_priv->num_shared_dpll = 0;
+
+ BUG_ON(dev_priv->num_shared_dpll > I915_NUM_PLLS);
}
/**
{
struct drm_device *dev = plane->dev;
struct intel_plane *intel_plane = to_intel_plane(plane);
- enum pipe pipe = intel_plane->pipe;
struct drm_i915_gem_object *obj = intel_fb_obj(fb);
struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->fb);
- unsigned frontbuffer_bits = 0;
int ret = 0;
if (!obj)
return 0;
- switch (plane->type) {
- case DRM_PLANE_TYPE_PRIMARY:
- frontbuffer_bits = INTEL_FRONTBUFFER_PRIMARY(pipe);
- break;
- case DRM_PLANE_TYPE_CURSOR:
- frontbuffer_bits = INTEL_FRONTBUFFER_CURSOR(pipe);
- break;
- case DRM_PLANE_TYPE_OVERLAY:
- frontbuffer_bits = INTEL_FRONTBUFFER_SPRITE(pipe);
- break;
- }
-
mutex_lock(&dev->struct_mutex);
if (plane->type == DRM_PLANE_TYPE_CURSOR &&
if (ret)
DRM_DEBUG_KMS("failed to attach phys object\n");
} else {
- ret = intel_pin_and_fence_fb_obj(plane, fb, new_state, NULL);
+ ret = intel_pin_and_fence_fb_obj(plane, fb, new_state, NULL, NULL);
}
if (ret == 0)
- i915_gem_track_fb(old_obj, obj, frontbuffer_bits);
+ i915_gem_track_fb(old_obj, obj, intel_plane->frontbuffer_bit);
mutex_unlock(&dev->struct_mutex);
dev = intel_crtc->base.dev;
dev_priv = dev->dev_private;
crtc_clock = crtc_state->base.adjusted_mode.crtc_clock;
- cdclk = dev_priv->display.get_display_clock_speed(dev);
+ cdclk = to_intel_atomic_state(crtc_state->base.state)->cdclk;
if (!crtc_clock || !cdclk)
return DRM_PLANE_HELPER_NO_SCALING;
static int
intel_check_primary_plane(struct drm_plane *plane,
+ struct intel_crtc_state *crtc_state,
struct intel_plane_state *state)
{
- struct drm_device *dev = plane->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc = state->base.crtc;
- struct intel_crtc *intel_crtc;
- struct intel_crtc_state *crtc_state;
struct drm_framebuffer *fb = state->base.fb;
- struct drm_rect *dest = &state->dst;
- struct drm_rect *src = &state->src;
- const struct drm_rect *clip = &state->clip;
- bool can_position = false;
- int max_scale = DRM_PLANE_HELPER_NO_SCALING;
int min_scale = DRM_PLANE_HELPER_NO_SCALING;
- int ret;
-
- crtc = crtc ? crtc : plane->crtc;
- intel_crtc = to_intel_crtc(crtc);
- crtc_state = state->base.state ?
- intel_atomic_get_crtc_state(state->base.state, intel_crtc) : NULL;
+ int max_scale = DRM_PLANE_HELPER_NO_SCALING;
+ bool can_position = false;
- if (INTEL_INFO(dev)->gen >= 9) {
- /* use scaler when colorkey is not required */
- if (to_intel_plane(plane)->ckey.flags == I915_SET_COLORKEY_NONE) {
- min_scale = 1;
- max_scale = skl_max_scale(intel_crtc, crtc_state);
- }
+ /* use scaler when colorkey is not required */
+ if (INTEL_INFO(plane->dev)->gen >= 9 &&
+ state->ckey.flags == I915_SET_COLORKEY_NONE) {
+ min_scale = 1;
+ max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state);
can_position = true;
}
- ret = drm_plane_helper_check_update(plane, crtc, fb,
- src, dest, clip,
- min_scale,
- max_scale,
- can_position, true,
- &state->visible);
- if (ret)
- return ret;
-
- if (crtc_state ? crtc_state->base.active : intel_crtc->active) {
- struct intel_plane_state *old_state =
- to_intel_plane_state(plane->state);
-
- intel_crtc->atomic.wait_for_flips = true;
-
- /*
- * FBC does not work on some platforms for rotated
- * planes, so disable it when rotation is not 0 and
- * update it when rotation is set back to 0.
- *
- * FIXME: This is redundant with the fbc update done in
- * the primary plane enable function except that that
- * one is done too late. We eventually need to unify
- * this.
- */
- if (state->visible &&
- INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
- dev_priv->fbc.crtc == intel_crtc &&
- state->base.rotation != BIT(DRM_ROTATE_0)) {
- intel_crtc->atomic.disable_fbc = true;
- }
-
- if (state->visible && !old_state->visible) {
- /*
- * BDW signals flip done immediately if the plane
- * is disabled, even if the plane enable is already
- * armed to occur at the next vblank :(
- */
- if (IS_BROADWELL(dev))
- intel_crtc->atomic.wait_vblank = true;
- }
-
- /*
- * FIXME: Actually if we will still have any other plane enabled
- * on the pipe we could let IPS enabled still, but for
- * now lets consider that when we make primary invisible
- * by setting DSPCNTR to 0 on update_primary_plane function
- * IPS needs to be disable.
- */
- if (!state->visible || !fb)
- intel_crtc->atomic.disable_ips = true;
-
- intel_crtc->atomic.fb_bits |=
- INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
-
- intel_crtc->atomic.update_fbc = true;
-
- if (intel_wm_need_update(plane, &state->base))
- intel_crtc->atomic.update_wm = true;
- }
-
- if (INTEL_INFO(dev)->gen >= 9) {
- ret = skl_update_scaler_users(intel_crtc, crtc_state,
- to_intel_plane(plane), state, 0);
- if (ret)
- return ret;
- }
-
- return 0;
+ return drm_plane_helper_check_update(plane, crtc, fb, &state->src,
+ &state->dst, &state->clip,
+ min_scale, max_scale,
+ can_position, true,
+ &state->visible);
}
static void
crtc->x = src->x1 >> 16;
crtc->y = src->y1 >> 16;
- if (intel_crtc->active) {
- if (state->visible)
- /* FIXME: kill this fastboot hack */
- intel_update_pipe_size(intel_crtc);
+ if (!crtc->state->active)
+ return;
+
+ if (state->visible)
+ /* FIXME: kill this fastboot hack */
+ intel_update_pipe_size(intel_crtc);
- dev_priv->display.update_primary_plane(crtc, plane->fb,
- crtc->x, crtc->y);
- }
+ dev_priv->display.update_primary_plane(crtc, fb, crtc->x, crtc->y);
}
static void
intel_disable_primary_plane(struct drm_plane *plane,
- struct drm_crtc *crtc,
- bool force)
+ struct drm_crtc *crtc)
{
struct drm_device *dev = plane->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
static void intel_begin_crtc_commit(struct drm_crtc *crtc)
{
struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- struct intel_plane *intel_plane;
- struct drm_plane *p;
- unsigned fb_bits = 0;
-
- /* Track fb's for any planes being disabled */
- list_for_each_entry(p, &dev->mode_config.plane_list, head) {
- intel_plane = to_intel_plane(p);
-
- if (intel_crtc->atomic.disabled_planes &
- (1 << drm_plane_index(p))) {
- switch (p->type) {
- case DRM_PLANE_TYPE_PRIMARY:
- fb_bits = INTEL_FRONTBUFFER_PRIMARY(intel_plane->pipe);
- break;
- case DRM_PLANE_TYPE_CURSOR:
- fb_bits = INTEL_FRONTBUFFER_CURSOR(intel_plane->pipe);
- break;
- case DRM_PLANE_TYPE_OVERLAY:
- fb_bits = INTEL_FRONTBUFFER_SPRITE(intel_plane->pipe);
- break;
- }
-
- mutex_lock(&dev->struct_mutex);
- i915_gem_track_fb(intel_fb_obj(p->fb), NULL, fb_bits);
- mutex_unlock(&dev->struct_mutex);
- }
- }
- if (intel_crtc->atomic.wait_for_flips)
- intel_crtc_wait_for_pending_flips(crtc);
-
- if (intel_crtc->atomic.disable_fbc)
- intel_fbc_disable(dev);
-
- if (intel_crtc->atomic.disable_ips)
- hsw_disable_ips(intel_crtc);
-
- if (intel_crtc->atomic.pre_disable_primary)
- intel_pre_disable_primary(crtc);
-
- if (intel_crtc->atomic.update_wm)
+ if (intel_crtc->atomic.update_wm_pre)
intel_update_watermarks(crtc);
- intel_runtime_pm_get(dev_priv);
-
/* Perform vblank evasion around commit operation */
- if (intel_crtc->active)
- intel_crtc->atomic.evade =
- intel_pipe_update_start(intel_crtc,
- &intel_crtc->atomic.start_vbl_count);
+ if (crtc->state->active)
+ intel_pipe_update_start(intel_crtc, &intel_crtc->start_vbl_count);
+
+ if (!needs_modeset(crtc->state) && INTEL_INFO(dev)->gen >= 9)
+ skl_detach_scalers(intel_crtc);
}
static void intel_finish_crtc_commit(struct drm_crtc *crtc)
{
- struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- struct drm_plane *p;
-
- if (intel_crtc->atomic.evade)
- intel_pipe_update_end(intel_crtc,
- intel_crtc->atomic.start_vbl_count);
-
- intel_runtime_pm_put(dev_priv);
- if (intel_crtc->atomic.wait_vblank)
- intel_wait_for_vblank(dev, intel_crtc->pipe);
-
- intel_frontbuffer_flip(dev, intel_crtc->atomic.fb_bits);
-
- if (intel_crtc->atomic.update_fbc) {
- mutex_lock(&dev->struct_mutex);
- intel_fbc_update(dev);
- mutex_unlock(&dev->struct_mutex);
- }
-
- if (intel_crtc->atomic.post_enable_primary)
- intel_post_enable_primary(crtc);
-
- drm_for_each_legacy_plane(p, &dev->mode_config.plane_list)
- if (intel_crtc->atomic.update_sprite_watermarks & drm_plane_index(p))
- intel_update_sprite_watermarks(p, crtc, 0, 0, 0,
- false, false);
-
- memset(&intel_crtc->atomic, 0, sizeof(intel_crtc->atomic));
+ if (crtc->state->active)
+ intel_pipe_update_end(intel_crtc, intel_crtc->start_vbl_count);
}
/**
}
primary->pipe = pipe;
primary->plane = pipe;
+ primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe);
primary->check_plane = intel_check_primary_plane;
primary->commit_plane = intel_commit_primary_plane;
primary->disable_plane = intel_disable_primary_plane;
- primary->ckey.flags = I915_SET_COLORKEY_NONE;
if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4)
primary->plane = !pipe;
static int
intel_check_cursor_plane(struct drm_plane *plane,
+ struct intel_crtc_state *crtc_state,
struct intel_plane_state *state)
{
- struct drm_crtc *crtc = state->base.crtc;
- struct drm_device *dev = plane->dev;
+ struct drm_crtc *crtc = crtc_state->base.crtc;
struct drm_framebuffer *fb = state->base.fb;
- struct drm_rect *dest = &state->dst;
- struct drm_rect *src = &state->src;
- const struct drm_rect *clip = &state->clip;
struct drm_i915_gem_object *obj = intel_fb_obj(fb);
- struct intel_crtc *intel_crtc;
unsigned stride;
int ret;
- crtc = crtc ? crtc : plane->crtc;
- intel_crtc = to_intel_crtc(crtc);
-
- ret = drm_plane_helper_check_update(plane, crtc, fb,
- src, dest, clip,
+ ret = drm_plane_helper_check_update(plane, crtc, fb, &state->src,
+ &state->dst, &state->clip,
DRM_PLANE_HELPER_NO_SCALING,
DRM_PLANE_HELPER_NO_SCALING,
true, true, &state->visible);
if (ret)
return ret;
-
/* if we want to turn off the cursor ignore width and height */
if (!obj)
- goto finish;
+ return 0;
/* Check for which cursor types we support */
- if (!cursor_size_ok(dev, state->base.crtc_w, state->base.crtc_h)) {
+ if (!cursor_size_ok(plane->dev, state->base.crtc_w, state->base.crtc_h)) {
DRM_DEBUG("Cursor dimension %dx%d not supported\n",
state->base.crtc_w, state->base.crtc_h);
return -EINVAL;
if (fb->modifier[0] != DRM_FORMAT_MOD_NONE) {
DRM_DEBUG_KMS("cursor cannot be tiled\n");
- ret = -EINVAL;
- }
-
-finish:
- if (intel_crtc->active) {
- if (plane->state->crtc_w != state->base.crtc_w)
- intel_crtc->atomic.update_wm = true;
-
- intel_crtc->atomic.fb_bits |=
- INTEL_FRONTBUFFER_CURSOR(intel_crtc->pipe);
+ return -EINVAL;
}
- return ret;
+ return 0;
}
static void
intel_disable_cursor_plane(struct drm_plane *plane,
- struct drm_crtc *crtc,
- bool force)
+ struct drm_crtc *crtc)
{
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
- if (!force) {
- plane->fb = NULL;
- intel_crtc->cursor_bo = NULL;
- intel_crtc->cursor_addr = 0;
- }
-
intel_crtc_update_cursor(crtc, false);
}
intel_crtc->cursor_addr = addr;
intel_crtc->cursor_bo = obj;
-update:
- if (intel_crtc->active)
+update:
+ if (crtc->state->active)
intel_crtc_update_cursor(crtc, state->visible);
}
cursor->max_downscale = 1;
cursor->pipe = pipe;
cursor->plane = pipe;
+ cursor->frontbuffer_bit = INTEL_FRONTBUFFER_CURSOR(pipe);
cursor->check_plane = intel_check_cursor_plane;
cursor->commit_plane = intel_commit_cursor_plane;
cursor->disable_plane = intel_disable_cursor_plane;
for (i = 0; i < intel_crtc->num_scalers; i++) {
intel_scaler = &scaler_state->scalers[i];
intel_scaler->in_use = 0;
- intel_scaler->id = i;
-
intel_scaler->mode = PS_SCALER_MODE_DYN;
}
intel_crtc->cursor_cntl = ~0;
intel_crtc->cursor_size = ~0;
+ intel_crtc->wm.cxsr_allowed = true;
+
BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
dev_priv->plane_to_crtc_mapping[intel_crtc->plane] != NULL);
dev_priv->plane_to_crtc_mapping[intel_crtc->plane] = &intel_crtc->base;
}
intel_dsi_init(dev);
- } else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) {
+ } else if (!IS_GEN2(dev) && !IS_PINEVIEW(dev)) {
bool found = false;
if (I915_READ(GEN3_SDVOB) & SDVO_DETECTED) {
DRM_DEBUG_KMS("probing SDVOB\n");
found = intel_sdvo_init(dev, GEN3_SDVOB, true);
- if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) {
+ if (!found && IS_G4X(dev)) {
DRM_DEBUG_KMS("probing HDMI on SDVOB\n");
intel_hdmi_init(dev, GEN4_HDMIB, PORT_B);
}
- if (!found && SUPPORTS_INTEGRATED_DP(dev))
+ if (!found && IS_G4X(dev))
intel_dp_init(dev, DP_B, PORT_B);
}
if (!found && (I915_READ(GEN3_SDVOC) & SDVO_DETECTED)) {
- if (SUPPORTS_INTEGRATED_HDMI(dev)) {
+ if (IS_G4X(dev)) {
DRM_DEBUG_KMS("probing HDMI on SDVOC\n");
intel_hdmi_init(dev, GEN4_HDMIC, PORT_C);
}
- if (SUPPORTS_INTEGRATED_DP(dev))
+ if (IS_G4X(dev))
intel_dp_init(dev, DP_C, PORT_C);
}
- if (SUPPORTS_INTEGRATED_DP(dev) &&
+ if (IS_G4X(dev) &&
(I915_READ(DP_D) & DP_DETECTED))
intel_dp_init(dev, DP_D, PORT_D);
} else if (IS_GEN2(dev))
return drm_gem_handle_create(file, &obj->base, handle);
}
+static int intel_user_framebuffer_dirty(struct drm_framebuffer *fb,
+ struct drm_file *file,
+ unsigned flags, unsigned color,
+ struct drm_clip_rect *clips,
+ unsigned num_clips)
+{
+ struct drm_device *dev = fb->dev;
+ struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+ struct drm_i915_gem_object *obj = intel_fb->obj;
+
+ mutex_lock(&dev->struct_mutex);
+ intel_fb_obj_flush(obj, false, ORIGIN_GTT);
+ mutex_unlock(&dev->struct_mutex);
+
+ return 0;
+}
+
static const struct drm_framebuffer_funcs intel_fb_funcs = {
.destroy = intel_user_framebuffer_destroy,
.create_handle = intel_user_framebuffer_create_handle,
+ .dirty = intel_user_framebuffer_dirty,
};
static
.output_poll_changed = intel_fbdev_output_poll_changed,
.atomic_check = intel_atomic_check,
.atomic_commit = intel_atomic_commit,
+ .atomic_state_alloc = intel_atomic_state_alloc,
+ .atomic_state_clear = intel_atomic_state_clear,
};
/* Set up chip specific display functions */
haswell_crtc_compute_clock;
dev_priv->display.crtc_enable = haswell_crtc_enable;
dev_priv->display.crtc_disable = haswell_crtc_disable;
- dev_priv->display.off = ironlake_crtc_off;
dev_priv->display.update_primary_plane =
skylake_update_primary_plane;
} else if (HAS_DDI(dev)) {
haswell_crtc_compute_clock;
dev_priv->display.crtc_enable = haswell_crtc_enable;
dev_priv->display.crtc_disable = haswell_crtc_disable;
- dev_priv->display.off = ironlake_crtc_off;
dev_priv->display.update_primary_plane =
ironlake_update_primary_plane;
} else if (HAS_PCH_SPLIT(dev)) {
ironlake_crtc_compute_clock;
dev_priv->display.crtc_enable = ironlake_crtc_enable;
dev_priv->display.crtc_disable = ironlake_crtc_disable;
- dev_priv->display.off = ironlake_crtc_off;
dev_priv->display.update_primary_plane =
ironlake_update_primary_plane;
} else if (IS_VALLEYVIEW(dev)) {
dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock;
dev_priv->display.crtc_enable = valleyview_crtc_enable;
dev_priv->display.crtc_disable = i9xx_crtc_disable;
- dev_priv->display.off = i9xx_crtc_off;
dev_priv->display.update_primary_plane =
i9xx_update_primary_plane;
} else {
dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock;
dev_priv->display.crtc_enable = i9xx_crtc_enable;
dev_priv->display.crtc_disable = i9xx_crtc_disable;
- dev_priv->display.off = i9xx_crtc_off;
dev_priv->display.update_primary_plane =
i9xx_update_primary_plane;
}
if (IS_SKYLAKE(dev))
dev_priv->display.get_display_clock_speed =
skylake_get_display_clock_speed;
+ else if (IS_BROXTON(dev))
+ dev_priv->display.get_display_clock_speed =
+ broxton_get_display_clock_speed;
else if (IS_BROADWELL(dev))
dev_priv->display.get_display_clock_speed =
broadwell_get_display_clock_speed;
dev_priv->display.get_display_clock_speed =
ilk_get_display_clock_speed;
else if (IS_I945G(dev) || IS_BROADWATER(dev) ||
- IS_GEN6(dev) || IS_IVYBRIDGE(dev) || (IS_G33(dev) && !IS_PINEVIEW_M(dev)))
+ IS_GEN6(dev) || IS_IVYBRIDGE(dev))
dev_priv->display.get_display_clock_speed =
i945_get_display_clock_speed;
+ else if (IS_GM45(dev))
+ dev_priv->display.get_display_clock_speed =
+ gm45_get_display_clock_speed;
+ else if (IS_CRESTLINE(dev))
+ dev_priv->display.get_display_clock_speed =
+ i965gm_get_display_clock_speed;
+ else if (IS_PINEVIEW(dev))
+ dev_priv->display.get_display_clock_speed =
+ pnv_get_display_clock_speed;
+ else if (IS_G33(dev) || IS_G4X(dev))
+ dev_priv->display.get_display_clock_speed =
+ g33_get_display_clock_speed;
else if (IS_I915G(dev))
dev_priv->display.get_display_clock_speed =
i915_get_display_clock_speed;
i865_get_display_clock_speed;
else if (IS_I85X(dev))
dev_priv->display.get_display_clock_speed =
- i855_get_display_clock_speed;
- else /* 852, 830 */
+ i85x_get_display_clock_speed;
+ else { /* 830 */
+ WARN(!IS_I830(dev), "Unknown platform. Assuming 133 MHz CDCLK\n");
dev_priv->display.get_display_clock_speed =
i830_get_display_clock_speed;
+ }
if (IS_GEN5(dev)) {
dev_priv->display.fdi_link_train = ironlake_fdi_link_train;
dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
dev_priv->display.fdi_link_train = hsw_fdi_link_train;
+ if (IS_BROADWELL(dev)) {
+ dev_priv->display.modeset_commit_cdclk =
+ broadwell_modeset_commit_cdclk;
+ dev_priv->display.modeset_calc_cdclk =
+ broadwell_modeset_calc_cdclk;
+ }
} else if (IS_VALLEYVIEW(dev)) {
- dev_priv->display.modeset_global_resources =
- valleyview_modeset_global_resources;
+ dev_priv->display.modeset_commit_cdclk =
+ valleyview_modeset_commit_cdclk;
+ dev_priv->display.modeset_calc_cdclk =
+ valleyview_modeset_calc_cdclk;
} else if (IS_BROXTON(dev)) {
- dev_priv->display.modeset_global_resources =
- broxton_modeset_global_resources;
+ dev_priv->display.modeset_commit_cdclk =
+ broxton_modeset_commit_cdclk;
+ dev_priv->display.modeset_calc_cdclk =
+ broxton_modeset_calc_cdclk;
}
switch (INTEL_INFO(dev)->gen) {
void intel_modeset_init_hw(struct drm_device *dev)
{
+ intel_update_cdclk(dev);
intel_prepare_ddi(dev);
-
- if (IS_VALLEYVIEW(dev))
- vlv_update_cdclk(dev);
-
intel_init_clock_gating(dev);
-
intel_enable_gt_powersave(dev);
}
intel_setup_outputs(dev);
/* Just in case the BIOS is doing something questionable. */
- intel_fbc_disable(dev);
+ intel_fbc_disable(dev_priv);
drm_modeset_lock_all(dev);
- intel_modeset_setup_hw_state(dev, false);
+ intel_modeset_setup_hw_state(dev);
drm_modeset_unlock_all(dev);
for_each_intel_crtc(dev, crtc) {
+ struct intel_initial_plane_config plane_config = {};
+
if (!crtc->active)
continue;
* can even allow for smooth boot transitions if the BIOS
* fb is large enough for the active pipe configuration.
*/
- if (dev_priv->display.get_initial_plane_config) {
- dev_priv->display.get_initial_plane_config(crtc,
- &crtc->plane_config);
- /*
- * If the fb is shared between multiple heads, we'll
- * just get the first one.
- */
- intel_find_initial_plane_obj(crtc, &crtc->plane_config);
- }
+ dev_priv->display.get_initial_plane_config(crtc,
+ &plane_config);
+
+ /*
+ * If the fb is shared between multiple heads, we'll
+ * just get the first one.
+ */
+ intel_find_initial_plane_obj(crtc, &plane_config);
}
}
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_encoder *encoder;
u32 reg;
+ bool enable;
/* Clear any frame start delays used for debugging left by the BIOS */
reg = PIPECONF(crtc->config->cpu_transcoder);
/* restore vblank interrupts to correct state */
drm_crtc_vblank_reset(&crtc->base);
if (crtc->active) {
+ drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode);
update_scanline_offset(crtc);
drm_crtc_vblank_on(&crtc->base);
}
* disable the crtc (and hence change the state) if it is wrong. Note
* that gen4+ has a fixed plane -> pipe mapping. */
if (INTEL_INFO(dev)->gen < 4 && !intel_check_plane_mapping(crtc)) {
- struct intel_connector *connector;
bool plane;
DRM_DEBUG_KMS("[CRTC:%d] wrong plane connection detected!\n",
plane = crtc->plane;
to_intel_plane_state(crtc->base.primary->state)->visible = true;
crtc->plane = !plane;
- intel_crtc_disable_planes(&crtc->base);
- dev_priv->display.crtc_disable(&crtc->base);
+ intel_crtc_disable_noatomic(&crtc->base);
crtc->plane = plane;
-
- /* ... and break all links. */
- for_each_intel_connector(dev, connector) {
- if (connector->encoder->base.crtc != &crtc->base)
- continue;
-
- connector->base.dpms = DRM_MODE_DPMS_OFF;
- connector->base.encoder = NULL;
- }
- /* multiple connectors may have the same encoder:
- * handle them and break crtc link separately */
- for_each_intel_connector(dev, connector)
- if (connector->encoder->base.crtc == &crtc->base) {
- connector->encoder->base.crtc = NULL;
- connector->encoder->connectors_active = false;
- }
-
- WARN_ON(crtc->active);
- crtc->base.state->enable = false;
- crtc->base.state->active = false;
- crtc->base.enabled = false;
}
if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
/* Adjust the state of the output pipe according to whether we
* have active connectors/encoders. */
- intel_crtc_update_dpms(&crtc->base);
+ enable = false;
+ for_each_encoder_on_crtc(dev, &crtc->base, encoder)
+ enable |= encoder->connectors_active;
- if (crtc->active != crtc->base.state->enable) {
- struct intel_encoder *encoder;
+ if (!enable)
+ intel_crtc_disable_noatomic(&crtc->base);
+
+ if (crtc->active != crtc->base.state->active) {
/* This can happen either due to bugs in the get_hw_state
- * functions or because the pipe is force-enabled due to the
+ * functions or because of calls to intel_crtc_disable_noatomic,
+ * or because the pipe is force-enabled due to the
* pipe A quirk. */
DRM_DEBUG_KMS("[CRTC:%d] hw state adjusted, was %s, now %s\n",
crtc->base.base.id,
crtc->base.state->enable ? "enabled" : "disabled",
crtc->active ? "enabled" : "disabled");
- crtc->base.state->enable = crtc->active;
+ WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, NULL) < 0);
crtc->base.state->active = crtc->active;
crtc->base.enabled = crtc->active;
{
struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
- if (!crtc->active)
- return false;
+ return !!(I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE);
+}
+
+static void readout_plane_state(struct intel_crtc *crtc,
+ struct intel_crtc_state *crtc_state)
+{
+ struct intel_plane *p;
+ struct intel_plane_state *plane_state;
+ bool active = crtc_state->base.active;
+
+ for_each_intel_plane(crtc->base.dev, p) {
+ if (crtc->pipe != p->pipe)
+ continue;
+
+ plane_state = to_intel_plane_state(p->base.state);
+
+ if (p->base.type == DRM_PLANE_TYPE_PRIMARY)
+ plane_state->visible = primary_get_hw_state(crtc);
+ else {
+ if (active)
+ p->disable_plane(&p->base, &crtc->base);
- return I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE;
+ plane_state->visible = false;
+ }
+ }
}
static void intel_modeset_readout_hw_state(struct drm_device *dev)
int i;
for_each_intel_crtc(dev, crtc) {
- struct drm_plane *primary = crtc->base.primary;
- struct intel_plane_state *plane_state;
-
+ __drm_atomic_helper_crtc_destroy_state(&crtc->base, crtc->base.state);
memset(crtc->config, 0, sizeof(*crtc->config));
+ crtc->config->base.crtc = &crtc->base;
crtc->config->quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE;
crtc->active = dev_priv->display.get_pipe_config(crtc,
crtc->config);
- crtc->base.state->enable = crtc->active;
crtc->base.state->active = crtc->active;
crtc->base.enabled = crtc->active;
- plane_state = to_intel_plane_state(primary->state);
- plane_state->visible = primary_get_hw_state(crtc);
+ memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
+ if (crtc->base.state->active) {
+ intel_mode_from_pipe_config(&crtc->base.mode, crtc->config);
+ intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config);
+ WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
+
+ /*
+ * The initial mode needs to be set in order to keep
+ * the atomic core happy. It wants a valid mode if the
+ * crtc's enabled, so we do the above call.
+ *
+ * At this point some state updated by the connectors
+ * in their ->detect() callback has not run yet, so
+ * no recalculation can be done yet.
+ *
+ * Even if we could do a recalculation and modeset
+ * right now it would cause a double modeset if
+ * fbdev or userspace chooses a different initial mode.
+ *
+ * So to prevent the double modeset, fail the memcmp
+ * test in drm_atomic_set_mode_for_crtc to get a new
+ * mode blob, and compare if the mode blob changed
+ * when the PIPE_CONFIG_QUIRK_INHERITED_MODE quirk is
+ * set.
+ *
+ * If that happens, someone indicated they wanted a
+ * mode change, which means it's safe to do a full
+ * recalculation.
+ */
+ crtc->base.state->mode.private_flags = ~0;
+ }
+
+ crtc->base.hwmode = crtc->config->base.adjusted_mode;
+ readout_plane_state(crtc, to_intel_crtc_state(crtc->base.state));
DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n",
crtc->base.base.id,
}
}
-/* Scan out the current hw modeset state, sanitizes it and maps it into the drm
- * and i915 state tracking structures. */
-void intel_modeset_setup_hw_state(struct drm_device *dev,
- bool force_restore)
+/* Scan out the current hw modeset state,
+ * and sanitizes it to the current state
+ */
+static void
+intel_modeset_setup_hw_state(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
enum pipe pipe;
intel_modeset_readout_hw_state(dev);
- /*
- * Now that we have the config, copy it to each CRTC struct
- * Note that this could go away if we move to using crtc_config
- * checking everywhere.
- */
- for_each_intel_crtc(dev, crtc) {
- if (crtc->active && i915.fastboot) {
- intel_mode_from_pipe_config(&crtc->base.mode,
- crtc->config);
- DRM_DEBUG_KMS("[CRTC:%d] found active mode: ",
- crtc->base.base.id);
- drm_mode_debug_printmodeline(&crtc->base.mode);
- }
- }
-
/* HW state is read out, now we need to sanitize this mess. */
for_each_intel_encoder(dev, encoder) {
intel_sanitize_encoder(encoder);
pll->on = false;
}
- if (IS_GEN9(dev))
+ if (IS_VALLEYVIEW(dev))
+ vlv_wm_get_hw_state(dev);
+ else if (IS_GEN9(dev))
skl_wm_get_hw_state(dev);
else if (HAS_PCH_SPLIT(dev))
ilk_wm_get_hw_state(dev);
- if (force_restore) {
- i915_redisable_vga(dev);
+ for_each_intel_crtc(dev, crtc) {
+ unsigned long put_domains;
- /*
- * We need to use raw interfaces for restoring state to avoid
- * checking (bogus) intermediate states.
- */
- for_each_pipe(dev_priv, pipe) {
- struct drm_crtc *crtc =
- dev_priv->pipe_to_crtc_mapping[pipe];
+ put_domains = modeset_get_crtc_power_domains(&crtc->base);
+ if (WARN_ON(put_domains))
+ modeset_put_power_domains(dev_priv, put_domains);
+ }
+ intel_display_set_init_power(dev_priv, false);
+}
- intel_crtc_restore_mode(crtc);
- }
- } else {
- intel_modeset_update_staged_output_state(dev);
+void intel_display_resume(struct drm_device *dev)
+{
+ struct drm_atomic_state *state = drm_atomic_state_alloc(dev);
+ struct intel_connector *conn;
+ struct intel_plane *plane;
+ struct drm_crtc *crtc;
+ int ret;
+
+ if (!state)
+ return;
+
+ state->acquire_ctx = dev->mode_config.acquire_ctx;
+
+ /* preserve complete old state, including dpll */
+ intel_atomic_get_shared_dpll_state(state);
+
+ for_each_crtc(dev, crtc) {
+ struct drm_crtc_state *crtc_state =
+ drm_atomic_get_crtc_state(state, crtc);
+
+ ret = PTR_ERR_OR_ZERO(crtc_state);
+ if (ret)
+ goto err;
+
+ /* force a restore */
+ crtc_state->mode_changed = true;
}
- intel_modeset_check_state(dev);
+ for_each_intel_plane(dev, plane) {
+ ret = PTR_ERR_OR_ZERO(drm_atomic_get_plane_state(state, &plane->base));
+ if (ret)
+ goto err;
+ }
+
+ for_each_intel_connector(dev, conn) {
+ ret = PTR_ERR_OR_ZERO(drm_atomic_get_connector_state(state, &conn->base));
+ if (ret)
+ goto err;
+ }
+
+ intel_modeset_setup_hw_state(dev);
+
+ i915_redisable_vga(dev);
+ ret = drm_atomic_commit(state);
+ if (!ret)
+ return;
+
+err:
+ DRM_ERROR("Restoring old state failed with %i\n", ret);
+ drm_atomic_state_free(state);
}
void intel_modeset_gem_init(struct drm_device *dev)
ret = intel_pin_and_fence_fb_obj(c->primary,
c->primary->fb,
c->primary->state,
- NULL);
+ NULL, NULL);
mutex_unlock(&dev->struct_mutex);
if (ret) {
DRM_ERROR("failed to pin boot fb on pipe %d\n",
to_intel_crtc(c)->pipe);
drm_framebuffer_unreference(c->primary->fb);
c->primary->fb = NULL;
+ c->primary->crtc = c->primary->state->crtc = NULL;
update_state_fb(c->primary);
+ c->state->plane_mask &= ~(1 << drm_plane_index(c->primary));
}
}
*/
drm_kms_helper_poll_fini(dev);
- mutex_lock(&dev->struct_mutex);
-
intel_unregister_dsm_handler();
- intel_fbc_disable(dev);
-
- mutex_unlock(&dev->struct_mutex);
+ intel_fbc_disable(dev_priv);
/* flush any delayed tasks or pending work */
flush_scheduled_work();
{ .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } }
};
+static const int bxt_rates[] = { 162000, 216000, 243000, 270000,
+ 324000, 432000, 540000 };
static const int skl_rates[] = { 162000, 216000, 270000,
324000, 432000, 540000 };
static const int chv_rates[] = { 162000, 202500, 210000, 216000,
{
struct drm_device *dev = intel_dp_to_dev(intel_dp);
- if (HAS_PCH_SPLIT(dev))
+ if (IS_BROXTON(dev))
+ return BXT_PP_CONTROL(0);
+ else if (HAS_PCH_SPLIT(dev))
return PCH_PP_CONTROL;
else
return VLV_PIPE_PP_CONTROL(vlv_power_sequencer_pipe(intel_dp));
{
struct drm_device *dev = intel_dp_to_dev(intel_dp);
- if (HAS_PCH_SPLIT(dev))
+ if (IS_BROXTON(dev))
+ return BXT_PP_STATUS(0);
+ else if (HAS_PCH_SPLIT(dev))
return PCH_PP_STATUS;
else
return VLV_PIPE_PP_STATUS(vlv_power_sequencer_pipe(intel_dp));
return 0;
if (intel_dig_port->port == PORT_A) {
- return DIV_ROUND_UP(dev_priv->display.get_display_clock_speed(dev), 2000);
+ return DIV_ROUND_UP(dev_priv->cdclk_freq, 2000);
+
} else {
return DIV_ROUND_UP(intel_pch_rawclk(dev), 2);
}
if (intel_dig_port->port == PORT_A) {
if (index)
return 0;
- return DIV_ROUND_CLOSEST(dev_priv->display.get_display_clock_speed(dev), 2000);
+ return DIV_ROUND_CLOSEST(dev_priv->cdclk_freq, 2000);
} else if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
/* Workaround for non-ULT HSW */
switch (index) {
continue;
}
if (status & DP_AUX_CH_CTL_DONE)
- break;
+ goto done;
}
- if (status & DP_AUX_CH_CTL_DONE)
- break;
}
if ((status & DP_AUX_CH_CTL_DONE) == 0) {
goto out;
}
+ done:
/* Check for timeout or receive error.
* Timeouts occur when the sink is not connected
*/
static void
hsw_dp_set_ddi_pll_sel(struct intel_crtc_state *pipe_config, int link_bw)
{
+ memset(&pipe_config->dpll_hw_state, 0,
+ sizeof(pipe_config->dpll_hw_state));
+
switch (link_bw) {
case DP_LINK_BW_1_62:
pipe_config->ddi_pll_sel = PORT_CLK_SEL_LCPLL_810;
static int
intel_dp_source_rates(struct drm_device *dev, const int **source_rates)
{
- if (IS_SKYLAKE(dev)) {
+ if (IS_BROXTON(dev)) {
+ *source_rates = bxt_rates;
+ return ARRAY_SIZE(bxt_rates);
+ } else if (IS_SKYLAKE(dev)) {
*source_rates = skl_rates;
return ARRAY_SIZE(skl_rates);
} else if (IS_CHERRYVIEW(dev)) {
if (INTEL_INFO(dev)->gen >= 9) {
int ret;
- ret = skl_update_scaler_users(intel_crtc, pipe_config, NULL, NULL, 0);
+ ret = skl_update_scaler_crtc(pipe_config);
if (ret)
return ret;
}
lockdep_assert_held(&dev_priv->pps_mutex);
control = I915_READ(_pp_ctrl_reg(intel_dp));
- control &= ~PANEL_UNLOCK_MASK;
- control |= PANEL_UNLOCK_REGS;
+ if (!IS_BROXTON(dev)) {
+ control &= ~PANEL_UNLOCK_MASK;
+ control |= PANEL_UNLOCK_REGS;
+ }
return control;
}
}
}
-/* Gen7.5's (HSW) DP voltage swing and pre-emphasis control */
-static uint32_t
-hsw_signal_levels(uint8_t train_set)
-{
- int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
- DP_TRAIN_PRE_EMPHASIS_MASK);
- switch (signal_levels) {
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- return DDI_BUF_TRANS_SELECT(0);
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_1:
- return DDI_BUF_TRANS_SELECT(1);
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_2:
- return DDI_BUF_TRANS_SELECT(2);
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_3:
- return DDI_BUF_TRANS_SELECT(3);
-
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- return DDI_BUF_TRANS_SELECT(4);
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_1:
- return DDI_BUF_TRANS_SELECT(5);
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_2:
- return DDI_BUF_TRANS_SELECT(6);
-
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- return DDI_BUF_TRANS_SELECT(7);
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_1:
- return DDI_BUF_TRANS_SELECT(8);
-
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_3 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- return DDI_BUF_TRANS_SELECT(9);
- default:
- DRM_DEBUG_KMS("Unsupported voltage swing/pre-emphasis level:"
- "0x%x\n", signal_levels);
- return DDI_BUF_TRANS_SELECT(0);
- }
-}
-
-static void bxt_signal_levels(struct intel_dp *intel_dp)
-{
- struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
- enum port port = dport->port;
- struct drm_device *dev = dport->base.base.dev;
- struct intel_encoder *encoder = &dport->base;
- uint8_t train_set = intel_dp->train_set[0];
- uint32_t level = 0;
-
- int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
- DP_TRAIN_PRE_EMPHASIS_MASK);
- switch (signal_levels) {
- default:
- DRM_DEBUG_KMS("Unsupported voltage swing/pre-emph level\n");
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- level = 0;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_1:
- level = 1;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_2:
- level = 2;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_3:
- level = 3;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- level = 4;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_1:
- level = 5;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_2:
- level = 6;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- level = 7;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_1:
- level = 8;
- break;
- case DP_TRAIN_VOLTAGE_SWING_LEVEL_3 | DP_TRAIN_PRE_EMPH_LEVEL_0:
- level = 9;
- break;
- }
-
- bxt_ddi_vswing_sequence(dev, level, port, encoder->type);
-}
-
/* Properly updates "DP" with the correct signal levels. */
static void
intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP)
struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
enum port port = intel_dig_port->port;
struct drm_device *dev = intel_dig_port->base.base.dev;
- uint32_t signal_levels, mask;
+ uint32_t signal_levels, mask = 0;
uint8_t train_set = intel_dp->train_set[0];
- if (IS_BROXTON(dev)) {
- signal_levels = 0;
- bxt_signal_levels(intel_dp);
- mask = 0;
- } else if (HAS_DDI(dev)) {
- signal_levels = hsw_signal_levels(train_set);
- mask = DDI_BUF_EMP_MASK;
+ if (HAS_DDI(dev)) {
+ signal_levels = ddi_signal_levels(intel_dp);
+
+ if (IS_BROXTON(dev))
+ signal_levels = 0;
+ else
+ mask = DDI_BUF_EMP_MASK;
} else if (IS_CHERRYVIEW(dev)) {
signal_levels = chv_signal_levels(intel_dp);
- mask = 0;
} else if (IS_VALLEYVIEW(dev)) {
signal_levels = vlv_signal_levels(intel_dp);
- mask = 0;
} else if (IS_GEN7(dev) && port == PORT_A) {
signal_levels = gen7_edp_signal_levels(train_set);
mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
.destroy = intel_dp_encoder_destroy,
};
-void
-intel_dp_hot_plug(struct intel_encoder *intel_encoder)
-{
- return;
-}
-
enum irqreturn
intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct edp_power_seq cur, vbt, spec,
*final = &intel_dp->pps_delays;
- u32 pp_on, pp_off, pp_div, pp;
- int pp_ctrl_reg, pp_on_reg, pp_off_reg, pp_div_reg;
+ u32 pp_on, pp_off, pp_div = 0, pp_ctl = 0;
+ int pp_ctrl_reg, pp_on_reg, pp_off_reg, pp_div_reg = 0;
lockdep_assert_held(&dev_priv->pps_mutex);
if (final->t11_t12 != 0)
return;
- if (HAS_PCH_SPLIT(dev)) {
+ if (IS_BROXTON(dev)) {
+ /*
+ * TODO: BXT has 2 sets of PPS registers.
+ * Correct Register for Broxton need to be identified
+ * using VBT. hardcoding for now
+ */
+ pp_ctrl_reg = BXT_PP_CONTROL(0);
+ pp_on_reg = BXT_PP_ON_DELAYS(0);
+ pp_off_reg = BXT_PP_OFF_DELAYS(0);
+ } else if (HAS_PCH_SPLIT(dev)) {
pp_ctrl_reg = PCH_PP_CONTROL;
pp_on_reg = PCH_PP_ON_DELAYS;
pp_off_reg = PCH_PP_OFF_DELAYS;
/* Workaround: Need to write PP_CONTROL with the unlock key as
* the very first thing. */
- pp = ironlake_get_pp_control(intel_dp);
- I915_WRITE(pp_ctrl_reg, pp);
+ pp_ctl = ironlake_get_pp_control(intel_dp);
pp_on = I915_READ(pp_on_reg);
pp_off = I915_READ(pp_off_reg);
- pp_div = I915_READ(pp_div_reg);
+ if (!IS_BROXTON(dev)) {
+ I915_WRITE(pp_ctrl_reg, pp_ctl);
+ pp_div = I915_READ(pp_div_reg);
+ }
/* Pull timing values out of registers */
cur.t1_t3 = (pp_on & PANEL_POWER_UP_DELAY_MASK) >>
cur.t10 = (pp_off & PANEL_POWER_DOWN_DELAY_MASK) >>
PANEL_POWER_DOWN_DELAY_SHIFT;
- cur.t11_t12 = ((pp_div & PANEL_POWER_CYCLE_DELAY_MASK) >>
+ if (IS_BROXTON(dev)) {
+ u16 tmp = (pp_ctl & BXT_POWER_CYCLE_DELAY_MASK) >>
+ BXT_POWER_CYCLE_DELAY_SHIFT;
+ if (tmp > 0)
+ cur.t11_t12 = (tmp - 1) * 1000;
+ else
+ cur.t11_t12 = 0;
+ } else {
+ cur.t11_t12 = ((pp_div & PANEL_POWER_CYCLE_DELAY_MASK) >>
PANEL_POWER_CYCLE_DELAY_SHIFT) * 1000;
+ }
DRM_DEBUG_KMS("cur t1_t3 %d t8 %d t9 %d t10 %d t11_t12 %d\n",
cur.t1_t3, cur.t8, cur.t9, cur.t10, cur.t11_t12);
struct drm_i915_private *dev_priv = dev->dev_private;
u32 pp_on, pp_off, pp_div, port_sel = 0;
int div = HAS_PCH_SPLIT(dev) ? intel_pch_rawclk(dev) : intel_hrawclk(dev);
- int pp_on_reg, pp_off_reg, pp_div_reg;
+ int pp_on_reg, pp_off_reg, pp_div_reg = 0, pp_ctrl_reg;
enum port port = dp_to_dig_port(intel_dp)->port;
const struct edp_power_seq *seq = &intel_dp->pps_delays;
lockdep_assert_held(&dev_priv->pps_mutex);
- if (HAS_PCH_SPLIT(dev)) {
+ if (IS_BROXTON(dev)) {
+ /*
+ * TODO: BXT has 2 sets of PPS registers.
+ * Correct Register for Broxton need to be identified
+ * using VBT. hardcoding for now
+ */
+ pp_ctrl_reg = BXT_PP_CONTROL(0);
+ pp_on_reg = BXT_PP_ON_DELAYS(0);
+ pp_off_reg = BXT_PP_OFF_DELAYS(0);
+
+ } else if (HAS_PCH_SPLIT(dev)) {
pp_on_reg = PCH_PP_ON_DELAYS;
pp_off_reg = PCH_PP_OFF_DELAYS;
pp_div_reg = PCH_PP_DIVISOR;
(seq->t10 << PANEL_POWER_DOWN_DELAY_SHIFT);
/* Compute the divisor for the pp clock, simply match the Bspec
* formula. */
- pp_div = ((100 * div)/2 - 1) << PP_REFERENCE_DIVIDER_SHIFT;
- pp_div |= (DIV_ROUND_UP(seq->t11_t12, 1000)
- << PANEL_POWER_CYCLE_DELAY_SHIFT);
+ if (IS_BROXTON(dev)) {
+ pp_div = I915_READ(pp_ctrl_reg);
+ pp_div &= ~BXT_POWER_CYCLE_DELAY_MASK;
+ pp_div |= (DIV_ROUND_UP((seq->t11_t12 + 1), 1000)
+ << BXT_POWER_CYCLE_DELAY_SHIFT);
+ } else {
+ pp_div = ((100 * div)/2 - 1) << PP_REFERENCE_DIVIDER_SHIFT;
+ pp_div |= (DIV_ROUND_UP(seq->t11_t12, 1000)
+ << PANEL_POWER_CYCLE_DELAY_SHIFT);
+ }
/* Haswell doesn't have any port selection bits for the panel
* power sequencer any more. */
I915_WRITE(pp_on_reg, pp_on);
I915_WRITE(pp_off_reg, pp_off);
- I915_WRITE(pp_div_reg, pp_div);
+ if (IS_BROXTON(dev))
+ I915_WRITE(pp_ctrl_reg, pp_div);
+ else
+ I915_WRITE(pp_div_reg, pp_div);
DRM_DEBUG_KMS("panel power sequencer register settings: PP_ON %#x, PP_OFF %#x, PP_DIV %#x\n",
I915_READ(pp_on_reg),
I915_READ(pp_off_reg),
+ IS_BROXTON(dev) ?
+ (I915_READ(pp_ctrl_reg) & BXT_POWER_CYCLE_DELAY_MASK) :
I915_READ(pp_div_reg));
}
}
/**
- * intel_edp_drrs_invalidate - Invalidate DRRS
+ * intel_edp_drrs_invalidate - Disable Idleness DRRS
* @dev: DRM device
* @frontbuffer_bits: frontbuffer plane tracking bits
*
- * When there is a disturbance on screen (due to cursor movement/time
- * update etc), DRRS needs to be invalidated, i.e. need to switch to
- * high RR.
+ * This function gets called everytime rendering on the given planes start.
+ * Hence DRRS needs to be Upclocked, i.e. (LOW_RR -> HIGH_RR).
*
* Dirty frontbuffers relevant to DRRS are tracked in busy_frontbuffer_bits.
*/
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) {
+ frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(pipe);
+ dev_priv->drrs.busy_frontbuffer_bits |= frontbuffer_bits;
+
+ /* invalidate means busy screen hence upclock */
+ if (frontbuffer_bits && dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR)
intel_dp_set_drrs_state(dev_priv->dev,
dev_priv->drrs.dp->attached_connector->panel.
fixed_mode->vrefresh);
- }
-
- frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(pipe);
- dev_priv->drrs.busy_frontbuffer_bits |= frontbuffer_bits;
mutex_unlock(&dev_priv->drrs.mutex);
}
/**
- * intel_edp_drrs_flush - Flush DRRS
+ * intel_edp_drrs_flush - Restart Idleness DRRS
* @dev: DRM device
* @frontbuffer_bits: frontbuffer plane tracking bits
*
- * When there is no movement on screen, DRRS work can be scheduled.
- * This DRRS work is responsible for setting relevant registers after a
- * timeout of 1 second.
+ * This function gets called every time rendering on the given planes has
+ * completed or flip on a crtc is completed. So DRRS should be upclocked
+ * (LOW_RR -> HIGH_RR). And also Idleness detection should be started again,
+ * if no other planes are dirty.
*
* Dirty frontbuffers relevant to DRRS are tracked in busy_frontbuffer_bits.
*/
crtc = dp_to_dig_port(dev_priv->drrs.dp)->base.base.crtc;
pipe = to_intel_crtc(crtc)->pipe;
+
+ frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(pipe);
dev_priv->drrs.busy_frontbuffer_bits &= ~frontbuffer_bits;
- if (dev_priv->drrs.refresh_rate_type != DRRS_LOW_RR &&
- !dev_priv->drrs.busy_frontbuffer_bits)
+ /* flush means busy screen hence upclock */
+ if (frontbuffer_bits && dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR)
+ intel_dp_set_drrs_state(dev_priv->dev,
+ dev_priv->drrs.dp->attached_connector->panel.
+ fixed_mode->vrefresh);
+
+ /*
+ * flush also means no more activity hence schedule downclock, if all
+ * other fbs are quiescent too
+ */
+ if (!dev_priv->drrs.busy_frontbuffer_bits)
schedule_delayed_work(&dev_priv->drrs.work,
msecs_to_jiffies(1000));
mutex_unlock(&dev_priv->drrs.mutex);
intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
}
intel_encoder->cloneable = 0;
- intel_encoder->hot_plug = intel_dp_hot_plug;
intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
- dev_priv->hpd_irq_port[port] = intel_dig_port;
+ dev_priv->hotplug.irq_port[port] = intel_dig_port;
if (!intel_dp_init_connector(intel_dig_port, intel_connector)) {
drm_encoder_cleanup(encoder);
/* disable MST */
for (i = 0; i < I915_MAX_PORTS; i++) {
- struct intel_digital_port *intel_dig_port = dev_priv->hpd_irq_port[i];
+ struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
if (!intel_dig_port)
continue;
int i;
for (i = 0; i < I915_MAX_PORTS; i++) {
- struct intel_digital_port *intel_dig_port = dev_priv->hpd_irq_port[i];
+ struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
if (!intel_dig_port)
continue;
if (intel_dig_port->base.type == INTEL_OUTPUT_DISPLAYPORT) {
#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
+#include "intel_mocs.h"
#define GEN9_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)
#define GEN8_CTX_PRIVILEGE (1<<8)
#define ASSIGN_CTX_PDP(ppgtt, reg_state, n) { \
- const u64 _addr = test_bit(n, ppgtt->pdp.used_pdpes) ? \
- ppgtt->pdp.page_directory[n]->daddr : \
- ppgtt->scratch_pd->daddr; \
+ const u64 _addr = i915_page_dir_dma_addr((ppgtt), (n)); \
reg_state[CTX_PDP ## n ## _UDW+1] = upper_32_bits(_addr); \
reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
}
FAULT_AND_CONTINUE /* Unsupported */
};
#define GEN8_CTX_ID_SHIFT 32
+#define CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT 0x17
-static int intel_lr_context_pin(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+static int intel_lr_context_pin(struct drm_i915_gem_request *rq);
/**
* intel_sanitize_enable_execlists() - sanitize i915.enable_execlists
return lrca >> 12;
}
-static uint64_t execlists_ctx_descriptor(struct intel_engine_cs *ring,
- struct drm_i915_gem_object *ctx_obj)
+static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_request *rq)
{
+ struct intel_engine_cs *ring = rq->ring;
struct drm_device *dev = ring->dev;
+ struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
uint64_t desc;
uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj);
return desc;
}
-static void execlists_elsp_write(struct intel_engine_cs *ring,
- struct drm_i915_gem_object *ctx_obj0,
- struct drm_i915_gem_object *ctx_obj1)
+static void execlists_elsp_write(struct drm_i915_gem_request *rq0,
+ struct drm_i915_gem_request *rq1)
{
+
+ struct intel_engine_cs *ring = rq0->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- uint64_t temp = 0;
- uint32_t desc[4];
+ uint64_t desc[2];
- /* XXX: You must always write both descriptors in the order below. */
- if (ctx_obj1)
- temp = execlists_ctx_descriptor(ring, ctx_obj1);
- else
- temp = 0;
- desc[1] = (u32)(temp >> 32);
- desc[0] = (u32)temp;
+ if (rq1) {
+ desc[1] = execlists_ctx_descriptor(rq1);
+ rq1->elsp_submitted++;
+ } else {
+ desc[1] = 0;
+ }
- temp = execlists_ctx_descriptor(ring, ctx_obj0);
- desc[3] = (u32)(temp >> 32);
- desc[2] = (u32)temp;
+ desc[0] = execlists_ctx_descriptor(rq0);
+ rq0->elsp_submitted++;
+ /* You must always write both descriptors in the order below. */
spin_lock(&dev_priv->uncore.lock);
intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
- I915_WRITE_FW(RING_ELSP(ring), desc[1]);
- I915_WRITE_FW(RING_ELSP(ring), desc[0]);
- I915_WRITE_FW(RING_ELSP(ring), desc[3]);
+ I915_WRITE_FW(RING_ELSP(ring), upper_32_bits(desc[1]));
+ I915_WRITE_FW(RING_ELSP(ring), lower_32_bits(desc[1]));
+ I915_WRITE_FW(RING_ELSP(ring), upper_32_bits(desc[0]));
/* The context is automatically loaded after the following */
- I915_WRITE_FW(RING_ELSP(ring), desc[2]);
+ I915_WRITE_FW(RING_ELSP(ring), lower_32_bits(desc[0]));
- /* ELSP is a wo register, so use another nearby reg for posting instead */
+ /* ELSP is a wo register, use another nearby reg for posting */
POSTING_READ_FW(RING_EXECLIST_STATUS(ring));
intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
spin_unlock(&dev_priv->uncore.lock);
}
-static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
- struct drm_i915_gem_object *ring_obj,
- struct i915_hw_ppgtt *ppgtt,
- u32 tail)
+static int execlists_update_context(struct drm_i915_gem_request *rq)
{
+ struct intel_engine_cs *ring = rq->ring;
+ struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
+ struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
+ struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj;
struct page *page;
uint32_t *reg_state;
+ BUG_ON(!ctx_obj);
+ WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
+ WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
+
page = i915_gem_object_get_page(ctx_obj, 1);
reg_state = kmap_atomic(page);
- reg_state[CTX_RING_TAIL+1] = tail;
- reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
+ reg_state[CTX_RING_TAIL+1] = rq->tail;
+ reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
/* True PPGTT with dynamic page allocation: update PDP registers and
* point the unallocated PDPs to the scratch page
return 0;
}
-static void execlists_submit_contexts(struct intel_engine_cs *ring,
- struct intel_context *to0, u32 tail0,
- struct intel_context *to1, u32 tail1)
+static void execlists_submit_requests(struct drm_i915_gem_request *rq0,
+ struct drm_i915_gem_request *rq1)
{
- struct drm_i915_gem_object *ctx_obj0 = to0->engine[ring->id].state;
- struct intel_ringbuffer *ringbuf0 = to0->engine[ring->id].ringbuf;
- struct drm_i915_gem_object *ctx_obj1 = NULL;
- struct intel_ringbuffer *ringbuf1 = NULL;
-
- BUG_ON(!ctx_obj0);
- WARN_ON(!i915_gem_obj_is_pinned(ctx_obj0));
- WARN_ON(!i915_gem_obj_is_pinned(ringbuf0->obj));
-
- execlists_update_context(ctx_obj0, ringbuf0->obj, to0->ppgtt, tail0);
+ execlists_update_context(rq0);
- if (to1) {
- ringbuf1 = to1->engine[ring->id].ringbuf;
- ctx_obj1 = to1->engine[ring->id].state;
- BUG_ON(!ctx_obj1);
- WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));
- WARN_ON(!i915_gem_obj_is_pinned(ringbuf1->obj));
+ if (rq1)
+ execlists_update_context(rq1);
- execlists_update_context(ctx_obj1, ringbuf1->obj, to1->ppgtt, tail1);
- }
-
- execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
+ execlists_elsp_write(rq0, rq1);
}
static void execlists_context_unqueue(struct intel_engine_cs *ring)
WARN_ON(req1 && req1->elsp_submitted);
- execlists_submit_contexts(ring, req0->ctx, req0->tail,
- req1 ? req1->ctx : NULL,
- req1 ? req1->tail : 0);
-
- req0->elsp_submitted++;
- if (req1)
- req1->elsp_submitted++;
+ execlists_submit_requests(req0, req1);
}
static bool execlists_check_remove_request(struct intel_engine_cs *ring,
((u32)ring->next_context_status_buffer & 0x07) << 8);
}
-static int execlists_context_queue(struct intel_engine_cs *ring,
- struct intel_context *to,
- u32 tail,
- struct drm_i915_gem_request *request)
+static int execlists_context_queue(struct drm_i915_gem_request *request)
{
+ struct intel_engine_cs *ring = request->ring;
struct drm_i915_gem_request *cursor;
int num_elements = 0;
- if (to != ring->default_context)
- intel_lr_context_pin(ring, to);
+ if (request->ctx != ring->default_context)
+ intel_lr_context_pin(request);
- if (!request) {
- /*
- * If there isn't a request associated with this submission,
- * create one as a temporary holder.
- */
- request = kzalloc(sizeof(*request), GFP_KERNEL);
- if (request == NULL)
- return -ENOMEM;
- request->ring = ring;
- request->ctx = to;
- kref_init(&request->ref);
- i915_gem_context_reference(request->ctx);
- } else {
- i915_gem_request_reference(request);
- WARN_ON(to != request->ctx);
- }
- request->tail = tail;
+ i915_gem_request_reference(request);
+
+ request->tail = request->ringbuf->tail;
spin_lock_irq(&ring->execlist_lock);
struct drm_i915_gem_request,
execlist_link);
- if (to == tail_req->ctx) {
+ if (request->ctx == tail_req->ctx) {
WARN(tail_req->elsp_submitted != 0,
"More than 2 already-submitted reqs queued\n");
list_del(&tail_req->execlist_link);
return 0;
}
-static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
+static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = req->ring;
uint32_t flush_domains;
int ret;
if (ring->gpu_caches_dirty)
flush_domains = I915_GEM_GPU_DOMAINS;
- ret = ring->emit_flush(ringbuf, ctx,
- I915_GEM_GPU_DOMAINS, flush_domains);
+ ret = ring->emit_flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
if (ret)
return ret;
return 0;
}
-static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
struct list_head *vmas)
{
- struct intel_engine_cs *ring = ringbuf->ring;
- const unsigned other_rings = ~intel_ring_flag(ring);
+ const unsigned other_rings = ~intel_ring_flag(req->ring);
struct i915_vma *vma;
uint32_t flush_domains = 0;
bool flush_chipset = false;
struct drm_i915_gem_object *obj = vma->obj;
if (obj->active & other_rings) {
- ret = i915_gem_object_sync(obj, ring);
+ ret = i915_gem_object_sync(obj, req->ring, &req);
if (ret)
return ret;
}
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
*/
- return logical_ring_invalidate_all_caches(ringbuf, ctx);
+ return logical_ring_invalidate_all_caches(req);
}
-int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request,
- struct intel_context *ctx)
+int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request)
{
int ret;
- if (ctx != request->ring->default_context) {
- ret = intel_lr_context_pin(request->ring, ctx);
+ request->ringbuf = request->ctx->engine[request->ring->id].ringbuf;
+
+ if (request->ctx != request->ring->default_context) {
+ ret = intel_lr_context_pin(request);
if (ret)
return ret;
}
- request->ringbuf = ctx->engine[request->ring->id].ringbuf;
- request->ctx = ctx;
- i915_gem_context_reference(request->ctx);
-
return 0;
}
-static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int logical_ring_wait_for_space(struct drm_i915_gem_request *req,
int bytes)
{
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_i915_gem_request *request;
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
+ struct intel_engine_cs *ring = req->ring;
+ struct drm_i915_gem_request *target;
unsigned space;
int ret;
if (intel_ring_space(ringbuf) >= bytes)
return 0;
- list_for_each_entry(request, &ring->request_list, list) {
+ /* The whole point of reserving space is to not wait! */
+ WARN_ON(ringbuf->reserved_in_use);
+
+ list_for_each_entry(target, &ring->request_list, list) {
/*
* The request queue is per-engine, so can contain requests
* from multiple ringbuffers. Here, we must ignore any that
* aren't from the ringbuffer we're considering.
*/
- if (request->ringbuf != ringbuf)
+ if (target->ringbuf != ringbuf)
continue;
/* Would completion of this request free enough space? */
- space = __intel_ring_space(request->postfix, ringbuf->tail,
+ space = __intel_ring_space(target->postfix, ringbuf->tail,
ringbuf->size);
if (space >= bytes)
break;
}
- if (WARN_ON(&request->list == &ring->request_list))
+ if (WARN_ON(&target->list == &ring->request_list))
return -ENOSPC;
- ret = i915_wait_request(request);
+ ret = i915_wait_request(target);
if (ret)
return ret;
/*
* intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
- * @ringbuf: Logical Ringbuffer to advance.
+ * @request: Request to advance the logical ringbuffer of.
*
* The tail is updated in our logical ringbuffer struct, not in the actual context. What
* really happens during submission is that the context and current tail will be placed
* point, the tail *inside* the context is updated and the ELSP written to.
*/
static void
-intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- struct drm_i915_gem_request *request)
+intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = request->ring;
- intel_logical_ring_advance(ringbuf);
+ intel_logical_ring_advance(request->ringbuf);
if (intel_ring_stopped(ring))
return;
- execlists_context_queue(ring, ctx, ringbuf->tail, request);
+ execlists_context_queue(request);
}
-static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
+static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
{
uint32_t __iomem *virt;
int rem = ringbuf->size - ringbuf->tail;
- if (ringbuf->space < rem) {
- int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
-
- if (ret)
- return ret;
- }
-
virt = ringbuf->virtual_start + ringbuf->tail;
rem /= 4;
while (rem--)
ringbuf->tail = 0;
intel_ring_update_space(ringbuf);
-
- return 0;
}
-static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, int bytes)
+static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
{
- int ret;
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
+ int remain_usable = ringbuf->effective_size - ringbuf->tail;
+ int remain_actual = ringbuf->size - ringbuf->tail;
+ int ret, total_bytes, wait_bytes = 0;
+ bool need_wrap = false;
+
+ if (ringbuf->reserved_in_use)
+ total_bytes = bytes;
+ else
+ total_bytes = bytes + ringbuf->reserved_size;
- if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
- ret = logical_ring_wrap_buffer(ringbuf, ctx);
- if (unlikely(ret))
- return ret;
+ if (unlikely(bytes > remain_usable)) {
+ /*
+ * Not enough space for the basic request. So need to flush
+ * out the remainder and then wait for base + reserved.
+ */
+ wait_bytes = remain_actual + total_bytes;
+ need_wrap = true;
+ } else {
+ if (unlikely(total_bytes > remain_usable)) {
+ /*
+ * The base request will fit but the reserved space
+ * falls off the end. So only need to to wait for the
+ * reserved size after flushing out the remainder.
+ */
+ wait_bytes = remain_actual + ringbuf->reserved_size;
+ need_wrap = true;
+ } else if (total_bytes > ringbuf->space) {
+ /* No wrapping required, just waiting. */
+ wait_bytes = total_bytes;
+ }
}
- if (unlikely(ringbuf->space < bytes)) {
- ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
+ if (wait_bytes) {
+ ret = logical_ring_wait_for_space(req, wait_bytes);
if (unlikely(ret))
return ret;
+
+ if (need_wrap)
+ __wrap_ring_buffer(ringbuf);
}
return 0;
/**
* intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
*
- * @ringbuf: Logical ringbuffer.
+ * @request: The request to start some new work for
+ * @ctx: Logical ring context whose ringbuffer is being prepared.
* @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
*
* The ringbuffer might not be ready to accept the commands right away (maybe it needs to
*
* Return: non-zero if the ringbuffer is not ready to be written to.
*/
-static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, int num_dwords)
+int intel_logical_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
{
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_device *dev = ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_i915_private *dev_priv;
int ret;
+ WARN_ON(req == NULL);
+ dev_priv = req->ring->dev->dev_private;
+
ret = i915_gem_check_wedge(&dev_priv->gpu_error,
dev_priv->mm.interruptible);
if (ret)
return ret;
- ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
- if (ret)
- return ret;
-
- /* Preallocate the olr before touching the ring */
- ret = i915_gem_request_alloc(ring, ctx);
+ ret = logical_ring_prepare(req, num_dwords * sizeof(uint32_t));
if (ret)
return ret;
- ringbuf->space -= num_dwords * sizeof(uint32_t);
+ req->ringbuf->space -= num_dwords * sizeof(uint32_t);
return 0;
}
+int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request)
+{
+ /*
+ * The first call merely notes the reserve request and is common for
+ * all back ends. The subsequent localised _begin() call actually
+ * ensures that the reservation is available. Without the begin, if
+ * the request creator immediately submitted the request without
+ * adding any commands to it then there might not actually be
+ * sufficient room for the submission commands.
+ */
+ intel_ring_reserved_space_reserve(request->ringbuf, MIN_SPACE_FOR_ADD_REQUEST);
+
+ return intel_logical_ring_begin(request, 0);
+}
+
/**
* execlists_submission() - submit a batchbuffer for execution, Execlists style
* @dev: DRM device.
*
* Return: non-zero if the submission fails.
*/
-int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+int intel_execlists_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags)
+ struct list_head *vmas)
{
+ struct drm_device *dev = params->dev;
+ struct intel_engine_cs *ring = params->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_ringbuffer *ringbuf = params->ctx->engine[ring->id].ringbuf;
+ u64 exec_start;
int instp_mode;
u32 instp_mask;
int ret;
return -EINVAL;
}
- ret = execlists_move_to_gpu(ringbuf, ctx, vmas);
+ ret = execlists_move_to_gpu(params->request, vmas);
if (ret)
return ret;
if (ring == &dev_priv->ring[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ ret = intel_logical_ring_begin(params->request, 4);
if (ret)
return ret;
dev_priv->relative_constants_mode = instp_mode;
}
- ret = ring->emit_bb_start(ringbuf, ctx, exec_start, dispatch_flags);
+ exec_start = params->batch_obj_vm_offset +
+ args->batch_start_offset;
+
+ ret = ring->emit_bb_start(params->request, exec_start, params->dispatch_flags);
if (ret)
return ret;
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+ trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
- i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+ i915_gem_execbuffer_move_to_active(vmas, params->request);
+ i915_gem_execbuffer_retire_commands(params);
return 0;
}
ctx->engine[ring->id].state;
if (ctx_obj && (ctx != ring->default_context))
- intel_lr_context_unpin(ring, ctx);
+ intel_lr_context_unpin(req);
list_del(&req->execlist_link);
i915_gem_request_unreference(req);
}
I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING));
}
-int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
+int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (!ring->gpu_caches_dirty)
return 0;
- ret = ring->emit_flush(ringbuf, ctx, 0, I915_GEM_GPU_DOMAINS);
+ ret = ring->emit_flush(req, 0, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
return 0;
}
-static int intel_lr_context_pin(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_lr_context_pin(struct drm_i915_gem_request *rq)
{
- struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_engine_cs *ring = rq->ring;
+ struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
+ struct intel_ringbuffer *ringbuf = rq->ringbuf;
int ret = 0;
WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
- if (ctx->engine[ring->id].pin_count++ == 0) {
+ if (rq->ctx->engine[ring->id].pin_count++ == 0) {
ret = i915_gem_obj_ggtt_pin(ctx_obj,
GEN8_LR_CONTEXT_ALIGN, 0);
if (ret)
unpin_ctx_obj:
i915_gem_object_ggtt_unpin(ctx_obj);
reset_pin_count:
- ctx->engine[ring->id].pin_count = 0;
+ rq->ctx->engine[ring->id].pin_count = 0;
return ret;
}
-void intel_lr_context_unpin(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+void intel_lr_context_unpin(struct drm_i915_gem_request *rq)
{
- struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_engine_cs *ring = rq->ring;
+ struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
+ struct intel_ringbuffer *ringbuf = rq->ringbuf;
if (ctx_obj) {
WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
- if (--ctx->engine[ring->id].pin_count == 0) {
+ if (--rq->ctx->engine[ring->id].pin_count == 0) {
intel_unpin_ringbuffer_obj(ringbuf);
i915_gem_object_ggtt_unpin(ctx_obj);
}
}
}
-static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
int ret, i;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_engine_cs *ring = req->ring;
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_workarounds *w = &dev_priv->workarounds;
return 0;
ring->gpu_caches_dirty = true;
- ret = logical_ring_flush_all_caches(ringbuf, ctx);
+ ret = logical_ring_flush_all_caches(req);
if (ret)
return ret;
- ret = intel_logical_ring_begin(ringbuf, ctx, w->count * 2 + 2);
+ ret = intel_logical_ring_begin(req, w->count * 2 + 2);
if (ret)
return ret;
intel_logical_ring_advance(ringbuf);
ring->gpu_caches_dirty = true;
- ret = logical_ring_flush_all_caches(ringbuf, ctx);
+ ret = logical_ring_flush_all_caches(req);
if (ret)
return ret;
return 0;
}
+#define wa_ctx_emit(batch, index, cmd) \
+ do { \
+ int __index = (index)++; \
+ if (WARN_ON(__index >= (PAGE_SIZE / sizeof(uint32_t)))) { \
+ return -ENOSPC; \
+ } \
+ batch[__index] = (cmd); \
+ } while (0)
+
+
+/*
+ * In this WA we need to set GEN8_L3SQCREG4[21:21] and reset it after
+ * PIPE_CONTROL instruction. This is required for the flush to happen correctly
+ * but there is a slight complication as this is applied in WA batch where the
+ * values are only initialized once so we cannot take register value at the
+ * beginning and reuse it further; hence we save its value to memory, upload a
+ * constant value with bit21 set and then we restore it back with the saved value.
+ * To simplify the WA, a constant value is formed by using the default value
+ * of this register. This shouldn't be a problem because we are only modifying
+ * it for a short period and this batch in non-premptible. We can ofcourse
+ * use additional instructions that read the actual value of the register
+ * at that time and set our bit of interest but it makes the WA complicated.
+ *
+ * This WA is also required for Gen9 so extracting as a function avoids
+ * code duplication.
+ */
+static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *ring,
+ uint32_t *const batch,
+ uint32_t index)
+{
+ uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
+
+ /*
+ * WaDisableLSQCROPERFforOCL:skl
+ * This WA is implemented in skl_init_clock_gating() but since
+ * this batch updates GEN8_L3SQCREG4 with default value we need to
+ * set this bit here to retain the WA during flush.
+ */
+ if (IS_SKYLAKE(ring->dev) && INTEL_REVID(ring->dev) <= SKL_REVID_E0)
+ l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
+
+ wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8(1) |
+ MI_SRM_LRM_GLOBAL_GTT));
+ wa_ctx_emit(batch, index, GEN8_L3SQCREG4);
+ wa_ctx_emit(batch, index, ring->scratch.gtt_offset + 256);
+ wa_ctx_emit(batch, index, 0);
+
+ wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
+ wa_ctx_emit(batch, index, GEN8_L3SQCREG4);
+ wa_ctx_emit(batch, index, l3sqc4_flush);
+
+ wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
+ wa_ctx_emit(batch, index, (PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_DC_FLUSH_ENABLE));
+ wa_ctx_emit(batch, index, 0);
+ wa_ctx_emit(batch, index, 0);
+ wa_ctx_emit(batch, index, 0);
+ wa_ctx_emit(batch, index, 0);
+
+ wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8(1) |
+ MI_SRM_LRM_GLOBAL_GTT));
+ wa_ctx_emit(batch, index, GEN8_L3SQCREG4);
+ wa_ctx_emit(batch, index, ring->scratch.gtt_offset + 256);
+ wa_ctx_emit(batch, index, 0);
+
+ return index;
+}
+
+static inline uint32_t wa_ctx_start(struct i915_wa_ctx_bb *wa_ctx,
+ uint32_t offset,
+ uint32_t start_alignment)
+{
+ return wa_ctx->offset = ALIGN(offset, start_alignment);
+}
+
+static inline int wa_ctx_end(struct i915_wa_ctx_bb *wa_ctx,
+ uint32_t offset,
+ uint32_t size_alignment)
+{
+ wa_ctx->size = offset - wa_ctx->offset;
+
+ WARN(wa_ctx->size % size_alignment,
+ "wa_ctx_bb failed sanity checks: size %d is not aligned to %d\n",
+ wa_ctx->size, size_alignment);
+ return 0;
+}
+
+/**
+ * gen8_init_indirectctx_bb() - initialize indirect ctx batch with WA
+ *
+ * @ring: only applicable for RCS
+ * @wa_ctx: structure representing wa_ctx
+ * offset: specifies start of the batch, should be cache-aligned. This is updated
+ * with the offset value received as input.
+ * size: size of the batch in DWORDS but HW expects in terms of cachelines
+ * @batch: page in which WA are loaded
+ * @offset: This field specifies the start of the batch, it should be
+ * cache-aligned otherwise it is adjusted accordingly.
+ * Typically we only have one indirect_ctx and per_ctx batch buffer which are
+ * initialized at the beginning and shared across all contexts but this field
+ * helps us to have multiple batches at different offsets and select them based
+ * on a criteria. At the moment this batch always start at the beginning of the page
+ * and at this point we don't have multiple wa_ctx batch buffers.
+ *
+ * The number of WA applied are not known at the beginning; we use this field
+ * to return the no of DWORDS written.
+ *
+ * It is to be noted that this batch does not contain MI_BATCH_BUFFER_END
+ * so it adds NOOPs as padding to make it cacheline aligned.
+ * MI_BATCH_BUFFER_END will be added to perctx batch and both of them together
+ * makes a complete batch buffer.
+ *
+ * Return: non-zero if we exceed the PAGE_SIZE limit.
+ */
+
+static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
+ struct i915_wa_ctx_bb *wa_ctx,
+ uint32_t *const batch,
+ uint32_t *offset)
+{
+ uint32_t scratch_addr;
+ uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
+
+ /* WaDisableCtxRestoreArbitration:bdw,chv */
+ wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE);
+
+ /* WaFlushCoherentL3CacheLinesAtContextSwitch:bdw */
+ if (IS_BROADWELL(ring->dev)) {
+ index = gen8_emit_flush_coherentl3_wa(ring, batch, index);
+ if (index < 0)
+ return index;
+ }
+
+ /* WaClearSlmSpaceAtContextSwitch:bdw,chv */
+ /* Actual scratch location is at 128 bytes offset */
+ scratch_addr = ring->scratch.gtt_offset + 2*CACHELINE_BYTES;
+
+ wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
+ wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
+ PIPE_CONTROL_GLOBAL_GTT_IVB |
+ PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_QW_WRITE));
+ wa_ctx_emit(batch, index, scratch_addr);
+ wa_ctx_emit(batch, index, 0);
+ wa_ctx_emit(batch, index, 0);
+ wa_ctx_emit(batch, index, 0);
+
+ /* Pad to end of cacheline */
+ while (index % CACHELINE_DWORDS)
+ wa_ctx_emit(batch, index, MI_NOOP);
+
+ /*
+ * MI_BATCH_BUFFER_END is not required in Indirect ctx BB because
+ * execution depends on the length specified in terms of cache lines
+ * in the register CTX_RCS_INDIRECT_CTX
+ */
+
+ return wa_ctx_end(wa_ctx, *offset = index, CACHELINE_DWORDS);
+}
+
+/**
+ * gen8_init_perctx_bb() - initialize per ctx batch with WA
+ *
+ * @ring: only applicable for RCS
+ * @wa_ctx: structure representing wa_ctx
+ * offset: specifies start of the batch, should be cache-aligned.
+ * size: size of the batch in DWORDS but HW expects in terms of cachelines
+ * @batch: page in which WA are loaded
+ * @offset: This field specifies the start of this batch.
+ * This batch is started immediately after indirect_ctx batch. Since we ensure
+ * that indirect_ctx ends on a cacheline this batch is aligned automatically.
+ *
+ * The number of DWORDS written are returned using this field.
+ *
+ * This batch is terminated with MI_BATCH_BUFFER_END and so we need not add padding
+ * to align it with cacheline as padding after MI_BATCH_BUFFER_END is redundant.
+ */
+static int gen8_init_perctx_bb(struct intel_engine_cs *ring,
+ struct i915_wa_ctx_bb *wa_ctx,
+ uint32_t *const batch,
+ uint32_t *offset)
+{
+ uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
+
+ /* WaDisableCtxRestoreArbitration:bdw,chv */
+ wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+
+ wa_ctx_emit(batch, index, MI_BATCH_BUFFER_END);
+
+ return wa_ctx_end(wa_ctx, *offset = index, 1);
+}
+
+static int gen9_init_indirectctx_bb(struct intel_engine_cs *ring,
+ struct i915_wa_ctx_bb *wa_ctx,
+ uint32_t *const batch,
+ uint32_t *offset)
+{
+ int ret;
+ struct drm_device *dev = ring->dev;
+ uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
+
+ /* WaDisableCtxRestoreArbitration:skl,bxt */
+ if ((IS_SKYLAKE(dev) && (INTEL_REVID(dev) <= SKL_REVID_D0)) ||
+ (IS_BROXTON(dev) && (INTEL_REVID(dev) == BXT_REVID_A0)))
+ wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE);
+
+ /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt */
+ ret = gen8_emit_flush_coherentl3_wa(ring, batch, index);
+ if (ret < 0)
+ return ret;
+ index = ret;
+
+ /* Pad to end of cacheline */
+ while (index % CACHELINE_DWORDS)
+ wa_ctx_emit(batch, index, MI_NOOP);
+
+ return wa_ctx_end(wa_ctx, *offset = index, CACHELINE_DWORDS);
+}
+
+static int gen9_init_perctx_bb(struct intel_engine_cs *ring,
+ struct i915_wa_ctx_bb *wa_ctx,
+ uint32_t *const batch,
+ uint32_t *offset)
+{
+ struct drm_device *dev = ring->dev;
+ uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
+
+ /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
+ if ((IS_SKYLAKE(dev) && (INTEL_REVID(dev) <= SKL_REVID_B0)) ||
+ (IS_BROXTON(dev) && (INTEL_REVID(dev) == BXT_REVID_A0))) {
+ wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
+ wa_ctx_emit(batch, index, GEN9_SLICE_COMMON_ECO_CHICKEN0);
+ wa_ctx_emit(batch, index,
+ _MASKED_BIT_ENABLE(DISABLE_PIXEL_MASK_CAMMING));
+ wa_ctx_emit(batch, index, MI_NOOP);
+ }
+
+ /* WaDisableCtxRestoreArbitration:skl,bxt */
+ if ((IS_SKYLAKE(dev) && (INTEL_REVID(dev) <= SKL_REVID_D0)) ||
+ (IS_BROXTON(dev) && (INTEL_REVID(dev) == BXT_REVID_A0)))
+ wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+
+ wa_ctx_emit(batch, index, MI_BATCH_BUFFER_END);
+
+ return wa_ctx_end(wa_ctx, *offset = index, 1);
+}
+
+static int lrc_setup_wa_ctx_obj(struct intel_engine_cs *ring, u32 size)
+{
+ int ret;
+
+ ring->wa_ctx.obj = i915_gem_alloc_object(ring->dev, PAGE_ALIGN(size));
+ if (!ring->wa_ctx.obj) {
+ DRM_DEBUG_DRIVER("alloc LRC WA ctx backing obj failed.\n");
+ return -ENOMEM;
+ }
+
+ ret = i915_gem_obj_ggtt_pin(ring->wa_ctx.obj, PAGE_SIZE, 0);
+ if (ret) {
+ DRM_DEBUG_DRIVER("pin LRC WA ctx backing obj failed: %d\n",
+ ret);
+ drm_gem_object_unreference(&ring->wa_ctx.obj->base);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void lrc_destroy_wa_ctx_obj(struct intel_engine_cs *ring)
+{
+ if (ring->wa_ctx.obj) {
+ i915_gem_object_ggtt_unpin(ring->wa_ctx.obj);
+ drm_gem_object_unreference(&ring->wa_ctx.obj->base);
+ ring->wa_ctx.obj = NULL;
+ }
+}
+
+static int intel_init_workaround_bb(struct intel_engine_cs *ring)
+{
+ int ret;
+ uint32_t *batch;
+ uint32_t offset;
+ struct page *page;
+ struct i915_ctx_workarounds *wa_ctx = &ring->wa_ctx;
+
+ WARN_ON(ring->id != RCS);
+
+ /* update this when WA for higher Gen are added */
+ if (INTEL_INFO(ring->dev)->gen > 9) {
+ DRM_ERROR("WA batch buffer is not initialized for Gen%d\n",
+ INTEL_INFO(ring->dev)->gen);
+ return 0;
+ }
+
+ /* some WA perform writes to scratch page, ensure it is valid */
+ if (ring->scratch.obj == NULL) {
+ DRM_ERROR("scratch page not allocated for %s\n", ring->name);
+ return -EINVAL;
+ }
+
+ ret = lrc_setup_wa_ctx_obj(ring, PAGE_SIZE);
+ if (ret) {
+ DRM_DEBUG_DRIVER("Failed to setup context WA page: %d\n", ret);
+ return ret;
+ }
+
+ page = i915_gem_object_get_page(wa_ctx->obj, 0);
+ batch = kmap_atomic(page);
+ offset = 0;
+
+ if (INTEL_INFO(ring->dev)->gen == 8) {
+ ret = gen8_init_indirectctx_bb(ring,
+ &wa_ctx->indirect_ctx,
+ batch,
+ &offset);
+ if (ret)
+ goto out;
+
+ ret = gen8_init_perctx_bb(ring,
+ &wa_ctx->per_ctx,
+ batch,
+ &offset);
+ if (ret)
+ goto out;
+ } else if (INTEL_INFO(ring->dev)->gen == 9) {
+ ret = gen9_init_indirectctx_bb(ring,
+ &wa_ctx->indirect_ctx,
+ batch,
+ &offset);
+ if (ret)
+ goto out;
+
+ ret = gen9_init_perctx_bb(ring,
+ &wa_ctx->per_ctx,
+ batch,
+ &offset);
+ if (ret)
+ goto out;
+ }
+
+out:
+ kunmap_atomic(batch);
+ if (ret)
+ lrc_destroy_wa_ctx_obj(ring);
+
+ return ret;
+}
+
static int gen8_init_common_ring(struct intel_engine_cs *ring)
{
struct drm_device *dev = ring->dev;
I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
+ if (ring->status_page.obj) {
+ I915_WRITE(RING_HWS_PGA(ring->mmio_base),
+ (u32)ring->status_page.gfx_addr);
+ POSTING_READ(RING_HWS_PGA(ring->mmio_base));
+ }
+
I915_WRITE(RING_MODE_GEN7(ring),
_MASKED_BIT_DISABLE(GFX_REPLAY_MODE) |
_MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
return init_workarounds_ring(ring);
}
-static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
+{
+ struct i915_hw_ppgtt *ppgtt = req->ctx->ppgtt;
+ struct intel_engine_cs *ring = req->ring;
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
+ const int num_lri_cmds = GEN8_LEGACY_PDPES * 2;
+ int i, ret;
+
+ ret = intel_logical_ring_begin(req, num_lri_cmds * 2 + 2);
+ if (ret)
+ return ret;
+
+ intel_logical_ring_emit(ringbuf, MI_LOAD_REGISTER_IMM(num_lri_cmds));
+ for (i = GEN8_LEGACY_PDPES - 1; i >= 0; i--) {
+ const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
+
+ intel_logical_ring_emit(ringbuf, GEN8_RING_PDP_UDW(ring, i));
+ intel_logical_ring_emit(ringbuf, upper_32_bits(pd_daddr));
+ intel_logical_ring_emit(ringbuf, GEN8_RING_PDP_LDW(ring, i));
+ intel_logical_ring_emit(ringbuf, lower_32_bits(pd_daddr));
+ }
+
+ intel_logical_ring_emit(ringbuf, MI_NOOP);
+ intel_logical_ring_advance(ringbuf);
+
+ return 0;
+}
+
+static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
u64 offset, unsigned dispatch_flags)
{
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ /* Don't rely in hw updating PDPs, specially in lite-restore.
+ * Ideally, we should set Force PD Restore in ctx descriptor,
+ * but we can't. Force Restore would be a second option, but
+ * it is unsafe in case of lite-restore (because the ctx is
+ * not idle). */
+ if (req->ctx->ppgtt &&
+ (intel_ring_flag(req->ring) & req->ctx->ppgtt->pd_dirty_rings)) {
+ ret = intel_logical_ring_emit_pdps(req);
+ if (ret)
+ return ret;
+
+ req->ctx->ppgtt->pd_dirty_rings &= ~intel_ring_flag(req->ring);
+ }
+
+ ret = intel_logical_ring_begin(req, 4);
if (ret)
return ret;
/* FIXME(BDW): Address space and security selectors. */
- intel_logical_ring_emit(ringbuf, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8));
+ intel_logical_ring_emit(ringbuf, MI_BATCH_BUFFER_START_GEN8 |
+ (ppgtt<<8) |
+ (dispatch_flags & I915_DISPATCH_RS ?
+ MI_BATCH_RESOURCE_STREAMER : 0));
intel_logical_ring_emit(ringbuf, lower_32_bits(offset));
intel_logical_ring_emit(ringbuf, upper_32_bits(offset));
intel_logical_ring_emit(ringbuf, MI_NOOP);
spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
}
-static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int gen8_emit_flush(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 unused)
{
+ struct intel_ringbuffer *ringbuf = request->ringbuf;
struct intel_engine_cs *ring = ringbuf->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t cmd;
int ret;
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ ret = intel_logical_ring_begin(request, 4);
if (ret)
return ret;
return 0;
}
-static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_ringbuffer *ringbuf = request->ringbuf;
struct intel_engine_cs *ring = ringbuf->ring;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
bool vf_flush_wa;
vf_flush_wa = INTEL_INFO(ring->dev)->gen >= 9 &&
flags & PIPE_CONTROL_VF_CACHE_INVALIDATE;
- ret = intel_logical_ring_begin(ringbuf, ctx, vf_flush_wa ? 12 : 6);
+ ret = intel_logical_ring_begin(request, vf_flush_wa ? 12 : 6);
if (ret)
return ret;
intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
}
-static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
- struct drm_i915_gem_request *request)
+static int gen8_emit_request(struct drm_i915_gem_request *request)
{
+ struct intel_ringbuffer *ringbuf = request->ringbuf;
struct intel_engine_cs *ring = ringbuf->ring;
u32 cmd;
int ret;
* used as a workaround for not being allowed to do lite
* restore with HEAD==TAIL (WaIdleLiteRestore).
*/
- ret = intel_logical_ring_begin(ringbuf, request->ctx, 8);
+ ret = intel_logical_ring_begin(request, 8);
if (ret)
return ret;
(ring->status_page.gfx_addr +
(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
intel_logical_ring_emit(ringbuf, 0);
- intel_logical_ring_emit(ringbuf,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
intel_logical_ring_emit(ringbuf, MI_NOOP);
- intel_logical_ring_advance_and_submit(ringbuf, request->ctx, request);
+ intel_logical_ring_advance_and_submit(request);
/*
* Here we add two extra NOOPs as padding to avoid
return 0;
}
-static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
{
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
struct render_state so;
- struct drm_i915_file_private *file_priv = ctx->file_priv;
- struct drm_file *file = file_priv ? file_priv->file : NULL;
int ret;
- ret = i915_gem_render_state_prepare(ring, &so);
+ ret = i915_gem_render_state_prepare(req->ring, &so);
if (ret)
return ret;
if (so.rodata == NULL)
return 0;
- ret = ring->emit_bb_start(ringbuf,
- ctx,
- so.ggtt_offset,
- I915_DISPATCH_SECURE);
+ ret = req->ring->emit_bb_start(req, so.ggtt_offset,
+ I915_DISPATCH_SECURE);
if (ret)
goto out;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
- ret = __i915_add_request(ring, file, so.obj);
- /* intel_logical_ring_add_request moves object to inactive if it
- * fails */
out:
i915_gem_render_state_fini(&so);
return ret;
}
-static int gen8_init_rcs_context(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_logical_ring_workarounds_emit(ring, ctx);
+ ret = intel_logical_ring_workarounds_emit(req);
if (ret)
return ret;
- return intel_lr_context_render_state_init(ring, ctx);
+ ret = intel_rcs_context_init_mocs(req);
+ /*
+ * Failing to program the MOCS is non-fatal.The system will not
+ * run at peak performance. So generate an error and carry on.
+ */
+ if (ret)
+ DRM_ERROR("MOCS failed to program: expect performance issues.\n");
+
+ return intel_lr_context_render_state_init(req);
}
/**
intel_logical_ring_stop(ring);
WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
if (ring->cleanup)
ring->cleanup(ring);
kunmap(sg_page(ring->status_page.obj->pages->sgl));
ring->status_page.obj = NULL;
}
+
+ lrc_destroy_wa_ctx_obj(ring);
}
static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
ring->emit_bb_start = gen8_emit_bb_start;
ring->dev = dev;
- ret = logical_ring_init(dev, ring);
+
+ ret = intel_init_pipe_control(ring);
if (ret)
return ret;
- return intel_init_pipe_control(ring);
+ ret = intel_init_workaround_bb(ring);
+ if (ret) {
+ /*
+ * We continue even if we fail to initialize WA batch
+ * because we only expect rare glitches but nothing
+ * critical to prevent us from using GPU
+ */
+ DRM_ERROR("WA batch buffer initialization failed: %d\n",
+ ret);
+ }
+
+ ret = logical_ring_init(dev, ring);
+ if (ret) {
+ lrc_destroy_wa_ctx_obj(ring);
+ }
+
+ return ret;
}
static int logical_bsd_ring_init(struct drm_device *dev)
reg_state[CTX_CONTEXT_CONTROL] = RING_CONTEXT_CONTROL(ring);
reg_state[CTX_CONTEXT_CONTROL+1] =
_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
- CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+ CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
+ CTX_CTRL_RS_CTX_ENABLE);
reg_state[CTX_RING_HEAD] = RING_HEAD(ring->mmio_base);
reg_state[CTX_RING_HEAD+1] = 0;
reg_state[CTX_RING_TAIL] = RING_TAIL(ring->mmio_base);
reg_state[CTX_SECOND_BB_STATE] = ring->mmio_base + 0x118;
reg_state[CTX_SECOND_BB_STATE+1] = 0;
if (ring->id == RCS) {
- /* TODO: according to BSpec, the register state context
- * for CHV does not have these. OTOH, these registers do
- * exist in CHV. I'm waiting for a clarification */
reg_state[CTX_BB_PER_CTX_PTR] = ring->mmio_base + 0x1c0;
reg_state[CTX_BB_PER_CTX_PTR+1] = 0;
reg_state[CTX_RCS_INDIRECT_CTX] = ring->mmio_base + 0x1c4;
reg_state[CTX_RCS_INDIRECT_CTX+1] = 0;
reg_state[CTX_RCS_INDIRECT_CTX_OFFSET] = ring->mmio_base + 0x1c8;
reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] = 0;
+ if (ring->wa_ctx.obj) {
+ struct i915_ctx_workarounds *wa_ctx = &ring->wa_ctx;
+ uint32_t ggtt_offset = i915_gem_obj_ggtt_offset(wa_ctx->obj);
+
+ reg_state[CTX_RCS_INDIRECT_CTX+1] =
+ (ggtt_offset + wa_ctx->indirect_ctx.offset * sizeof(uint32_t)) |
+ (wa_ctx->indirect_ctx.size / CACHELINE_DWORDS);
+
+ reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] =
+ CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT << 6;
+
+ reg_state[CTX_BB_PER_CTX_PTR+1] =
+ (ggtt_offset + wa_ctx->per_ctx.offset * sizeof(uint32_t)) |
+ 0x01;
+ }
}
reg_state[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9);
reg_state[CTX_LRI_HEADER_1] |= MI_LRI_FORCE_POSTED;
lrc_setup_hardware_status_page(ring, ctx_obj);
else if (ring->id == RCS && !ctx->rcs_initialized) {
if (ring->init_context) {
- ret = ring->init_context(ring, ctx);
+ struct drm_i915_gem_request *req;
+
+ ret = i915_gem_request_alloc(ring, ctx, &req);
+ if (ret)
+ return ret;
+
+ ret = ring->init_context(req);
if (ret) {
DRM_ERROR("ring init context: %d\n", ret);
+ i915_gem_request_cancel(req);
ctx->engine[ring->id].ringbuf = NULL;
ctx->engine[ring->id].state = NULL;
goto error;
}
+
+ i915_add_request_no_flush(req);
}
ctx->rcs_initialized = true;
*
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include <linux/acpi.h>
#include <acpi/video.h>
#define MBOX_ACPI (1<<0)
#define MBOX_SWSCI (1<<1)
#define MBOX_ASLE (1<<2)
+#define MBOX_ASLE_EXT (1<<4)
struct opregion_header {
u8 signature[16];
u8 vbios_ver[16];
u8 driver_ver[16];
u32 mboxes;
- u8 reserved[164];
+ u32 driver_model;
+ u32 pcon;
+ u8 dver[32];
+ u8 rsvd[124];
} __packed;
/* OpRegion mailbox #1: public ACPI methods */
u32 evts; /* ASL supported events */
u32 cnot; /* current OS notification */
u32 nrdy; /* driver status */
- u8 rsvd2[60];
+ u32 did2[7]; /* extended supported display devices ID list */
+ u32 cpd2[7]; /* extended attached display devices list */
+ u8 rsvd2[4];
} __packed;
/* OpRegion mailbox #2: SWSCI */
u32 pcft; /* power conservation features */
u32 srot; /* supported rotation angles */
u32 iuer; /* IUER events */
- u8 rsvd[86];
+ u64 fdss;
+ u32 fdsp;
+ u32 stat;
+ u8 rsvd[70];
} __packed;
/* Driver readiness indicator */
return -EINVAL;
}
- /*
- * If the vendor backlight interface is not in use and ACPI backlight interface
- * is broken, do not bother processing backlight change requests from firmware.
- */
- static bool should_ignore_backlight_request(void)
- {
- return acpi_video_backlight_support() &&
- !acpi_video_verify_backlight_support();
- }
-
static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
{
struct drm_i915_private *dev_priv = dev->dev_private;
DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
- if (should_ignore_backlight_request()) {
+ if (acpi_video_get_backlight_type() == acpi_backlight_native) {
DRM_DEBUG_KMS("opregion backlight request ignored\n");
return 0;
}
* (version 3)
*/
+static u32 get_did(struct intel_opregion *opregion, int i)
+{
+ u32 did;
+
+ if (i < ARRAY_SIZE(opregion->acpi->didl)) {
+ did = ioread32(&opregion->acpi->didl[i]);
+ } else {
+ i -= ARRAY_SIZE(opregion->acpi->didl);
+
+ if (WARN_ON(i >= ARRAY_SIZE(opregion->acpi->did2)))
+ return 0;
+
+ did = ioread32(&opregion->acpi->did2[i]);
+ }
+
+ return did;
+}
+
+static void set_did(struct intel_opregion *opregion, int i, u32 val)
+{
+ if (i < ARRAY_SIZE(opregion->acpi->didl)) {
+ iowrite32(val, &opregion->acpi->didl[i]);
+ } else {
+ i -= ARRAY_SIZE(opregion->acpi->didl);
+
+ if (WARN_ON(i >= ARRAY_SIZE(opregion->acpi->did2)))
+ return;
+
+ iowrite32(val, &opregion->acpi->did2[i]);
+ }
+}
+
static void intel_didl_outputs(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct acpi_device *acpi_dev, *acpi_cdev, *acpi_video_bus = NULL;
unsigned long long device_id;
acpi_status status;
- u32 temp;
+ u32 temp, max_outputs;
int i = 0;
handle = ACPI_HANDLE(&dev->pdev->dev);
}
if (!acpi_video_bus) {
- pr_warn("No ACPI video bus found\n");
+ DRM_ERROR("No ACPI video bus found\n");
return;
}
+ /*
+ * In theory, did2, the extended didl, gets added at opregion version
+ * 3.0. In practice, however, we're supposed to set it for earlier
+ * versions as well, since a BIOS that doesn't understand did2 should
+ * not look at it anyway. Use a variable so we can tweak this if a need
+ * arises later.
+ */
+ max_outputs = ARRAY_SIZE(opregion->acpi->didl) +
+ ARRAY_SIZE(opregion->acpi->did2);
+
list_for_each_entry(acpi_cdev, &acpi_video_bus->children, node) {
- if (i >= 8) {
- dev_dbg(&dev->pdev->dev,
- "More than 8 outputs detected via ACPI\n");
+ if (i >= max_outputs) {
+ DRM_DEBUG_KMS("More than %u outputs detected via ACPI\n",
+ max_outputs);
return;
}
- status =
- acpi_evaluate_integer(acpi_cdev->handle, "_ADR",
- NULL, &device_id);
+ status = acpi_evaluate_integer(acpi_cdev->handle, "_ADR",
+ NULL, &device_id);
if (ACPI_SUCCESS(status)) {
if (!device_id)
goto blind_set;
- iowrite32((u32)(device_id & 0x0f0f),
- &opregion->acpi->didl[i]);
- i++;
+ set_did(opregion, i++, (u32)(device_id & 0x0f0f));
}
}
end:
- /* If fewer than 8 outputs, the list must be null terminated */
- if (i < 8)
- iowrite32(0, &opregion->acpi->didl[i]);
+ DRM_DEBUG_KMS("%d outputs detected\n", i);
+
+ /* If fewer than max outputs, the list must be null terminated */
+ if (i < max_outputs)
+ set_did(opregion, i, 0);
return;
blind_set:
i = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
int output_type = ACPI_OTHER_OUTPUT;
- if (i >= 8) {
- dev_dbg(&dev->pdev->dev,
- "More than 8 outputs in connector list\n");
+ if (i >= max_outputs) {
+ DRM_DEBUG_KMS("More than %u outputs in connector list\n",
+ max_outputs);
return;
}
switch (connector->connector_type) {
output_type = ACPI_LVDS_OUTPUT;
break;
}
- temp = ioread32(&opregion->acpi->didl[i]);
- iowrite32(temp | (1<<31) | output_type | i,
- &opregion->acpi->didl[i]);
+ temp = get_did(opregion, i);
+ set_did(opregion, i, temp | (1 << 31) | output_type | i);
i++;
}
goto end;
* display switching hotkeys. Just like DIDL, CADL is NULL-terminated if
* there are less than eight devices. */
do {
- disp_id = ioread32(&opregion->acpi->didl[i]);
+ disp_id = get_did(opregion, i);
iowrite32(disp_id, &opregion->acpi->cadl[i]);
} while (++i < 8 && disp_id != 0);
}
char buf[sizeof(OPREGION_SIGNATURE)];
int err = 0;
+ BUILD_BUG_ON(sizeof(struct opregion_header) != 0x100);
+ BUILD_BUG_ON(sizeof(struct opregion_acpi) != 0x100);
+ BUILD_BUG_ON(sizeof(struct opregion_swsci) != 0x100);
+ BUILD_BUG_ON(sizeof(struct opregion_asle) != 0x100);
+
pci_read_config_dword(dev->pdev, PCI_ASLS, &asls);
DRM_DEBUG_DRIVER("graphic opregion physical addr: 0x%x\n", asls);
if (asls == 0) {
return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
}
-void __intel_ring_advance(struct intel_engine_cs *ring)
+static void __intel_ring_advance(struct intel_engine_cs *ring)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
ringbuf->tail &= ringbuf->size - 1;
}
static int
-gen2_render_ring_flush(struct intel_engine_cs *ring,
+gen2_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 cmd;
int ret;
if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
cmd |= MI_READ_FLUSH;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
}
static int
-gen4_render_ring_flush(struct intel_engine_cs *ring,
+gen4_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
u32 cmd;
int ret;
(IS_G4X(dev) || IS_GEN5(dev)))
cmd |= MI_INVALIDATE_ISP;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
* really our business. That leaves only stall at scoreboard.
*/
static int
-intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
+intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
-
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
}
static int
-gen6_render_ring_flush(struct intel_engine_cs *ring,
- u32 invalidate_domains, u32 flush_domains)
+gen6_render_ring_flush(struct drm_i915_gem_request *req,
+ u32 invalidate_domains, u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = 0;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
/* Force SNB workarounds for PIPE_CONTROL flushes */
- ret = intel_emit_post_sync_nonzero_flush(ring);
+ ret = intel_emit_post_sync_nonzero_flush(req);
if (ret)
return ret;
flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
}
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
}
static int
-gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
+gen7_render_ring_cs_stall_wa(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
}
static int
-gen7_render_ring_flush(struct intel_engine_cs *ring,
+gen7_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains, u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = 0;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
/* Workaround: we must issue a pipe_control with CS-stall bit
* set before a pipe_control command that has the state cache
* invalidate bit set. */
- gen7_render_ring_cs_stall_wa(ring);
+ gen7_render_ring_cs_stall_wa(req);
}
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
}
static int
-gen8_emit_pipe_control(struct intel_engine_cs *ring,
+gen8_emit_pipe_control(struct drm_i915_gem_request *req,
u32 flags, u32 scratch_addr)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
}
static int
-gen8_render_ring_flush(struct intel_engine_cs *ring,
+gen8_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains, u32 flush_domains)
{
u32 flags = 0;
- u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+ u32 scratch_addr = req->ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
flags |= PIPE_CONTROL_CS_STALL;
flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
/* WaCsStallBeforeStateCacheInvalidate:bdw,chv */
- ret = gen8_emit_pipe_control(ring,
+ ret = gen8_emit_pipe_control(req,
PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_STALL_AT_SCOREBOARD,
0);
return ret;
}
- return gen8_emit_pipe_control(ring, flags, scratch_addr);
+ return gen8_emit_pipe_control(req, flags, scratch_addr);
}
static void ring_write_tail(struct intel_engine_cs *ring,
return ret;
}
-static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
int ret, i;
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_workarounds *w = &dev_priv->workarounds;
return 0;
ring->gpu_caches_dirty = true;
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(req);
if (ret)
return ret;
- ret = intel_ring_begin(ring, (w->count * 2 + 2));
+ ret = intel_ring_begin(req, (w->count * 2 + 2));
if (ret)
return ret;
intel_ring_advance(ring);
ring->gpu_caches_dirty = true;
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(req);
if (ret)
return ret;
return 0;
}
-static int intel_rcs_ctx_init(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_ring_workarounds_emit(ring, ctx);
+ ret = intel_ring_workarounds_emit(req);
if (ret != 0)
return ret;
- ret = i915_gem_render_state_init(ring);
+ ret = i915_gem_render_state_init(req);
if (ret)
DRM_ERROR("init render state: %d\n", ret);
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
+
+ /* WaDisableAsyncFlipPerfMode:bdw */
+ WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
/* WaDisablePartialInstShootdown:bdw */
/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
+
+ /* WaDisableAsyncFlipPerfMode:chv */
+ WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
/* WaDisablePartialInstShootdown:chv */
/* WaDisableThreadStallDopClockGating:chv */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
/* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
WA_SET_BIT_MASKED(GEN7_COMMON_SLICE_CHICKEN1,
GEN9_RHWO_OPTIMIZATION_DISABLE);
- WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN0,
- DISABLE_PIXEL_MASK_CAMMING);
+ /*
+ * WA also requires GEN9_SLICE_COMMON_ECO_CHICKEN0[14:14] to be set
+ * but we do that in per ctx batchbuffer as there is an issue
+ * with this register not getting restored on ctx restore
+ */
}
if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) >= SKL_REVID_C0) ||
WA_SET_BIT_MASKED(HIZ_CHICKEN,
BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
+ if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+ INTEL_REVID(dev) == SKL_REVID_D0)
+ /* WaBarrierPerformanceFixDisable:skl */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FENCE_DEST_SLM_DISABLE |
+ HDC_BARRIER_PERFORMANCE_DISABLE);
+
if (INTEL_REVID(dev) <= SKL_REVID_D0) {
/*
*Use Force Non-Coherent whenever executing a 3D context. This
HDC_FORCE_NON_COHERENT);
}
+ if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+ INTEL_REVID(dev) == SKL_REVID_D0)
+ /* WaBarrierPerformanceFixDisable:skl */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FENCE_DEST_SLM_DISABLE |
+ HDC_BARRIER_PERFORMANCE_DISABLE);
+
return skl_tune_iz_hashing(ring);
}
* to use MI_WAIT_FOR_EVENT within the CS. It should already be
* programmed to '1' on all products.
*
- * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
+ * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
*/
- if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 9)
+ if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
/* Required for the hardware to program scanline values for waiting */
_MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
}
- if (INTEL_INFO(dev)->gen >= 6)
+ if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
if (HAS_L3_DPF(dev))
intel_fini_pipe_control(ring);
}
-static int gen8_rcs_signal(struct intel_engine_cs *signaller,
+static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
unsigned int num_dwords)
{
#define MBOX_UPDATE_DWORDS 8
+ struct intel_engine_cs *signaller = signaller_req->ring;
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *waiter;
num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
#undef MBOX_UPDATE_DWORDS
- ret = intel_ring_begin(signaller, num_dwords);
+ ret = intel_ring_begin(signaller_req, num_dwords);
if (ret)
return ret;
if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
continue;
- seqno = i915_gem_request_get_seqno(
- signaller->outstanding_lazy_request);
+ seqno = i915_gem_request_get_seqno(signaller_req);
intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6));
intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB |
PIPE_CONTROL_QW_WRITE |
return 0;
}
-static int gen8_xcs_signal(struct intel_engine_cs *signaller,
+static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
unsigned int num_dwords)
{
#define MBOX_UPDATE_DWORDS 6
+ struct intel_engine_cs *signaller = signaller_req->ring;
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *waiter;
num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
#undef MBOX_UPDATE_DWORDS
- ret = intel_ring_begin(signaller, num_dwords);
+ ret = intel_ring_begin(signaller_req, num_dwords);
if (ret)
return ret;
if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
continue;
- seqno = i915_gem_request_get_seqno(
- signaller->outstanding_lazy_request);
+ seqno = i915_gem_request_get_seqno(signaller_req);
intel_ring_emit(signaller, (MI_FLUSH_DW + 1) |
MI_FLUSH_DW_OP_STOREDW);
intel_ring_emit(signaller, lower_32_bits(gtt_offset) |
return 0;
}
-static int gen6_signal(struct intel_engine_cs *signaller,
+static int gen6_signal(struct drm_i915_gem_request *signaller_req,
unsigned int num_dwords)
{
+ struct intel_engine_cs *signaller = signaller_req->ring;
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *useless;
num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
#undef MBOX_UPDATE_DWORDS
- ret = intel_ring_begin(signaller, num_dwords);
+ ret = intel_ring_begin(signaller_req, num_dwords);
if (ret)
return ret;
for_each_ring(useless, dev_priv, i) {
u32 mbox_reg = signaller->semaphore.mbox.signal[i];
if (mbox_reg != GEN6_NOSYNC) {
- u32 seqno = i915_gem_request_get_seqno(
- signaller->outstanding_lazy_request);
+ u32 seqno = i915_gem_request_get_seqno(signaller_req);
intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(signaller, mbox_reg);
intel_ring_emit(signaller, seqno);
/**
* gen6_add_request - Update the semaphore mailbox registers
- *
- * @ring - ring that is adding a request
- * @seqno - return seqno stuck into the ring
+ *
+ * @request - request to write to the ring
*
* Update the mailbox registers in the *other* rings with the current seqno.
* This acts like a signal in the canonical semaphore.
*/
static int
-gen6_add_request(struct intel_engine_cs *ring)
+gen6_add_request(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (ring->semaphore.signal)
- ret = ring->semaphore.signal(ring, 4);
+ ret = ring->semaphore.signal(req, 4);
else
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, MI_USER_INTERRUPT);
__intel_ring_advance(ring);
*/
static int
-gen8_ring_sync(struct intel_engine_cs *waiter,
+gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
struct intel_engine_cs *signaller,
u32 seqno)
{
+ struct intel_engine_cs *waiter = waiter_req->ring;
struct drm_i915_private *dev_priv = waiter->dev->dev_private;
int ret;
- ret = intel_ring_begin(waiter, 4);
+ ret = intel_ring_begin(waiter_req, 4);
if (ret)
return ret;
}
static int
-gen6_ring_sync(struct intel_engine_cs *waiter,
+gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
struct intel_engine_cs *signaller,
u32 seqno)
{
+ struct intel_engine_cs *waiter = waiter_req->ring;
u32 dw1 = MI_SEMAPHORE_MBOX |
MI_SEMAPHORE_COMPARE |
MI_SEMAPHORE_REGISTER;
WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID);
- ret = intel_ring_begin(waiter, 4);
+ ret = intel_ring_begin(waiter_req, 4);
if (ret)
return ret;
} while (0)
static int
-pc_render_add_request(struct intel_engine_cs *ring)
+pc_render_add_request(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
* incoherence by flushing the 6 PIPE_NOTIFY buffers out to
* memory before requesting an interrupt.
*/
- ret = intel_ring_begin(ring, 32);
+ ret = intel_ring_begin(req, 32);
if (ret)
return ret;
PIPE_CONTROL_WRITE_FLUSH |
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, 0);
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
PIPE_CONTROL_NOTIFY);
intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, 0);
__intel_ring_advance(ring);
}
static int
-bsd_ring_flush(struct intel_engine_cs *ring,
+bsd_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
}
static int
-i9xx_add_request(struct intel_engine_cs *ring)
+i9xx_add_request(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, MI_USER_INTERRUPT);
__intel_ring_advance(ring);
}
static int
-i965_dispatch_execbuffer(struct intel_engine_cs *ring,
+i965_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 length,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
#define I830_TLB_ENTRIES (2)
#define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
static int
-i830_dispatch_execbuffer(struct intel_engine_cs *ring,
+i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
u32 cs_offset = ring->scratch.gtt_offset;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
if (len > I830_BATCH_LIMIT)
return -ENOSPC;
- ret = intel_ring_begin(ring, 6 + 2);
+ ret = intel_ring_begin(req, 6 + 2);
if (ret)
return ret;
offset = cs_offset;
}
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
}
static int
-i915_dispatch_execbuffer(struct intel_engine_cs *ring,
+i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
intel_unpin_ringbuffer_obj(ringbuf);
intel_destroy_ringbuffer_obj(ringbuf);
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
if (ring->cleanup)
ring->cleanup(ring);
if (intel_ring_space(ringbuf) >= n)
return 0;
+ /* The whole point of reserving space is to not wait! */
+ WARN_ON(ringbuf->reserved_in_use);
+
list_for_each_entry(request, &ring->request_list, list) {
space = __intel_ring_space(request->postfix, ringbuf->tail,
ringbuf->size);
return 0;
}
-static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
+static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
{
uint32_t __iomem *virt;
- struct intel_ringbuffer *ringbuf = ring->buffer;
int rem = ringbuf->size - ringbuf->tail;
- if (ringbuf->space < rem) {
- int ret = ring_wait_for_space(ring, rem);
- if (ret)
- return ret;
- }
-
virt = ringbuf->virtual_start + ringbuf->tail;
rem /= 4;
while (rem--)
ringbuf->tail = 0;
intel_ring_update_space(ringbuf);
-
- return 0;
}
int intel_ring_idle(struct intel_engine_cs *ring)
{
struct drm_i915_gem_request *req;
- int ret;
-
- /* We need to add any requests required to flush the objects and ring */
- if (ring->outstanding_lazy_request) {
- ret = i915_add_request(ring);
- if (ret)
- return ret;
- }
/* Wait upon the last request to be completed */
if (list_empty(&ring->request_list))
return 0;
}
-static int __intel_ring_prepare(struct intel_engine_cs *ring,
- int bytes)
+int intel_ring_reserve_space(struct drm_i915_gem_request *request)
+{
+ /*
+ * The first call merely notes the reserve request and is common for
+ * all back ends. The subsequent localised _begin() call actually
+ * ensures that the reservation is available. Without the begin, if
+ * the request creator immediately submitted the request without
+ * adding any commands to it then there might not actually be
+ * sufficient room for the submission commands.
+ */
+ intel_ring_reserved_space_reserve(request->ringbuf, MIN_SPACE_FOR_ADD_REQUEST);
+
+ return intel_ring_begin(request, 0);
+}
+
+void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size)
+{
+ WARN_ON(ringbuf->reserved_size);
+ WARN_ON(ringbuf->reserved_in_use);
+
+ ringbuf->reserved_size = size;
+}
+
+void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf)
+{
+ WARN_ON(ringbuf->reserved_in_use);
+
+ ringbuf->reserved_size = 0;
+ ringbuf->reserved_in_use = false;
+}
+
+void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf)
+{
+ WARN_ON(ringbuf->reserved_in_use);
+
+ ringbuf->reserved_in_use = true;
+ ringbuf->reserved_tail = ringbuf->tail;
+}
+
+void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf)
+{
+ WARN_ON(!ringbuf->reserved_in_use);
+ if (ringbuf->tail > ringbuf->reserved_tail) {
+ WARN(ringbuf->tail > ringbuf->reserved_tail + ringbuf->reserved_size,
+ "request reserved size too small: %d vs %d!\n",
+ ringbuf->tail - ringbuf->reserved_tail, ringbuf->reserved_size);
+ } else {
+ /*
+ * The ring was wrapped while the reserved space was in use.
+ * That means that some unknown amount of the ring tail was
+ * no-op filled and skipped. Thus simply adding the ring size
+ * to the tail and doing the above space check will not work.
+ * Rather than attempt to track how much tail was skipped,
+ * it is much simpler to say that also skipping the sanity
+ * check every once in a while is not a big issue.
+ */
+ }
+
+ ringbuf->reserved_size = 0;
+ ringbuf->reserved_in_use = false;
+}
+
+static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
- int ret;
+ int remain_usable = ringbuf->effective_size - ringbuf->tail;
+ int remain_actual = ringbuf->size - ringbuf->tail;
+ int ret, total_bytes, wait_bytes = 0;
+ bool need_wrap = false;
- if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
- ret = intel_wrap_ring_buffer(ring);
- if (unlikely(ret))
- return ret;
+ if (ringbuf->reserved_in_use)
+ total_bytes = bytes;
+ else
+ total_bytes = bytes + ringbuf->reserved_size;
+
+ if (unlikely(bytes > remain_usable)) {
+ /*
+ * Not enough space for the basic request. So need to flush
+ * out the remainder and then wait for base + reserved.
+ */
+ wait_bytes = remain_actual + total_bytes;
+ need_wrap = true;
+ } else {
+ if (unlikely(total_bytes > remain_usable)) {
+ /*
+ * The base request will fit but the reserved space
+ * falls off the end. So only need to to wait for the
+ * reserved size after flushing out the remainder.
+ */
+ wait_bytes = remain_actual + ringbuf->reserved_size;
+ need_wrap = true;
+ } else if (total_bytes > ringbuf->space) {
+ /* No wrapping required, just waiting. */
+ wait_bytes = total_bytes;
+ }
}
- if (unlikely(ringbuf->space < bytes)) {
- ret = ring_wait_for_space(ring, bytes);
+ if (wait_bytes) {
+ ret = ring_wait_for_space(ring, wait_bytes);
if (unlikely(ret))
return ret;
+
+ if (need_wrap)
+ __wrap_ring_buffer(ringbuf);
}
return 0;
}
-int intel_ring_begin(struct intel_engine_cs *ring,
+int intel_ring_begin(struct drm_i915_gem_request *req,
int num_dwords)
{
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ struct intel_engine_cs *ring;
+ struct drm_i915_private *dev_priv;
int ret;
+ WARN_ON(req == NULL);
+ ring = req->ring;
+ dev_priv = ring->dev->dev_private;
+
ret = i915_gem_check_wedge(&dev_priv->gpu_error,
dev_priv->mm.interruptible);
if (ret)
if (ret)
return ret;
- /* Preallocate the olr before touching the ring */
- ret = i915_gem_request_alloc(ring, ring->default_context);
- if (ret)
- return ret;
-
ring->buffer->space -= num_dwords * sizeof(uint32_t);
return 0;
}
/* Align the ring tail to a cacheline boundary */
-int intel_ring_cacheline_align(struct intel_engine_cs *ring)
+int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t);
int ret;
return 0;
num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords;
- ret = intel_ring_begin(ring, num_dwords);
+ ret = intel_ring_begin(req, num_dwords);
if (ret)
return ret;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- BUG_ON(ring->outstanding_lazy_request);
-
if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
_MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
}
-static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
+static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate, u32 flush)
{
+ struct intel_engine_cs *ring = req->ring;
uint32_t cmd;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
}
static int
-gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+gen8_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
bool ppgtt = USES_PPGTT(ring->dev) &&
!(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
/* FIXME(BDW): Address space and security selectors. */
- intel_ring_emit(ring, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8));
+ intel_ring_emit(ring, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8) |
+ (dispatch_flags & I915_DISPATCH_RS ?
+ MI_BATCH_RESOURCE_STREAMER : 0));
intel_ring_emit(ring, lower_32_bits(offset));
intel_ring_emit(ring, upper_32_bits(offset));
intel_ring_emit(ring, MI_NOOP);
}
static int
-hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+hsw_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
intel_ring_emit(ring,
MI_BATCH_BUFFER_START |
(dispatch_flags & I915_DISPATCH_SECURE ?
- 0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW));
+ 0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW) |
+ (dispatch_flags & I915_DISPATCH_RS ?
+ MI_BATCH_RESOURCE_STREAMER : 0));
/* bit0-7 is the length on GEN6+ */
intel_ring_emit(ring, offset);
intel_ring_advance(ring);
}
static int
-gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+gen6_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
/* Blitter support (SandyBridge+) */
-static int gen6_ring_flush(struct intel_engine_cs *ring,
+static int gen6_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate, u32 flush)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
uint32_t cmd;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
}
int
-intel_ring_flush_all_caches(struct intel_engine_cs *ring)
+intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (!ring->gpu_caches_dirty)
return 0;
- ret = ring->flush(ring, 0, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, 0, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
- trace_i915_gem_ring_flush(ring, 0, I915_GEM_GPU_DOMAINS);
+ trace_i915_gem_ring_flush(req, 0, I915_GEM_GPU_DOMAINS);
ring->gpu_caches_dirty = false;
return 0;
}
int
-intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
+intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
uint32_t flush_domains;
int ret;
if (ring->gpu_caches_dirty)
flush_domains = I915_GEM_GPU_DOMAINS;
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
if (ret)
return ret;
- trace_i915_gem_ring_flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+ trace_i915_gem_ring_flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
ring->gpu_caches_dirty = false;
return 0;
* workarounds!
*/
#define CACHELINE_BYTES 64
+#define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(uint32_t))
/*
* Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
int space;
int size;
int effective_size;
+ int reserved_size;
+ int reserved_tail;
+ bool reserved_in_use;
/** We track the position of the requests in the ring buffer, and
* when each is retired we increment last_retired_head as the GPU
struct intel_context;
struct drm_i915_reg_descriptor;
+/*
+ * we use a single page to load ctx workarounds so all of these
+ * values are referred in terms of dwords
+ *
+ * struct i915_wa_ctx_bb:
+ * offset: specifies batch starting position, also helpful in case
+ * if we want to have multiple batches at different offsets based on
+ * some criteria. It is not a requirement at the moment but provides
+ * an option for future use.
+ * size: size of the batch in DWORDS
+ */
+struct i915_ctx_workarounds {
+ struct i915_wa_ctx_bb {
+ u32 offset;
+ u32 size;
+ } indirect_ctx, per_ctx;
+ struct drm_i915_gem_object *obj;
+};
+
struct intel_engine_cs {
const char *name;
enum intel_ring_id {
struct i915_gem_batch_pool batch_pool;
struct intel_hw_status_page status_page;
+ struct i915_ctx_workarounds wa_ctx;
unsigned irq_refcount; /* protected by dev_priv->irq_lock */
u32 irq_enable_mask; /* bitmask to enable ring interrupt */
int (*init_hw)(struct intel_engine_cs *ring);
- int (*init_context)(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+ int (*init_context)(struct drm_i915_gem_request *req);
void (*write_tail)(struct intel_engine_cs *ring,
u32 value);
- int __must_check (*flush)(struct intel_engine_cs *ring,
+ int __must_check (*flush)(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains);
- int (*add_request)(struct intel_engine_cs *ring);
+ int (*add_request)(struct drm_i915_gem_request *req);
/* Some chipsets are not quite as coherent as advertised and need
* an expensive kick to force a true read of the up-to-date seqno.
* However, the up-to-date seqno is not always required and the last
bool lazy_coherency);
void (*set_seqno)(struct intel_engine_cs *ring,
u32 seqno);
- int (*dispatch_execbuffer)(struct intel_engine_cs *ring,
+ int (*dispatch_execbuffer)(struct drm_i915_gem_request *req,
u64 offset, u32 length,
unsigned dispatch_flags);
#define I915_DISPATCH_SECURE 0x1
#define I915_DISPATCH_PINNED 0x2
+#define I915_DISPATCH_RS 0x4
void (*cleanup)(struct intel_engine_cs *ring);
/* GEN8 signal/wait table - never trust comments!
};
/* AKA wait() */
- int (*sync_to)(struct intel_engine_cs *ring,
- struct intel_engine_cs *to,
+ int (*sync_to)(struct drm_i915_gem_request *to_req,
+ struct intel_engine_cs *from,
u32 seqno);
- int (*signal)(struct intel_engine_cs *signaller,
+ int (*signal)(struct drm_i915_gem_request *signaller_req,
/* num_dwords needed by caller */
unsigned int num_dwords);
} semaphore;
struct list_head execlist_retired_req_list;
u8 next_context_status_buffer;
u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */
- int (*emit_request)(struct intel_ringbuffer *ringbuf,
- struct drm_i915_gem_request *request);
- int (*emit_flush)(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+ int (*emit_request)(struct drm_i915_gem_request *request);
+ int (*emit_flush)(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 flush_domains);
- int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+ int (*emit_bb_start)(struct drm_i915_gem_request *req,
u64 offset, unsigned dispatch_flags);
/**
*/
struct list_head request_list;
- /**
- * Do we have some not yet emitted requests outstanding?
- */
- struct drm_i915_gem_request *outstanding_lazy_request;
+ /**
+ * Seqno of request most recently submitted to request_list.
+ * Used exclusively by hang checker to avoid grabbing lock while
+ * inspecting request list.
+ */
+ u32 last_submitted_seqno;
+
bool gpu_caches_dirty;
wait_queue_head_t irq_queue;
int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request);
-int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
-int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
+int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
+int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
static inline void intel_ring_emit(struct intel_engine_cs *ring,
u32 data)
{
void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
int intel_ring_space(struct intel_ringbuffer *ringbuf);
bool intel_ring_stopped(struct intel_engine_cs *ring);
-void __intel_ring_advance(struct intel_engine_cs *ring);
int __must_check intel_ring_idle(struct intel_engine_cs *ring);
void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
-int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
-int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
+int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
+int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
void intel_fini_pipe_control(struct intel_engine_cs *ring);
int intel_init_pipe_control(struct intel_engine_cs *ring);
return ringbuf->tail;
}
-static inline struct drm_i915_gem_request *
-intel_ring_get_request(struct intel_engine_cs *ring)
-{
- BUG_ON(ring->outstanding_lazy_request == NULL);
- return ring->outstanding_lazy_request;
-}
+/*
+ * Arbitrary size for largest possible 'add request' sequence. The code paths
+ * are complex and variable. Empirical measurement shows that the worst case
+ * is ILK at 136 words. Reserving too much is better than reserving too little
+ * as that allows for corner cases that might have been missed. So the figure
+ * has been rounded up to 160 words.
+ */
+#define MIN_SPACE_FOR_ADD_REQUEST 160
+
+/*
+ * Reserve space in the ring to guarantee that the i915_add_request() call
+ * will always have sufficient room to do its stuff. The request creation
+ * code calls this automatically.
+ */
+void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size);
+/* Cancel the reservation, e.g. because the request is being discarded. */
+void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf);
+/* Use the reserved space - for use by i915_add_request() only. */
+void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf);
+/* Finish with the reserved space - for use by i915_add_request() only. */
+void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf);
+
+/* Legacy ringbuffer specific portion of reservation code: */
+int intel_ring_reserve_space(struct drm_i915_gem_request *request);
#endif /* _INTEL_RINGBUFFER_H_ */
projects / linux-drm-fsl-dcu.git / commitdiff