return NULL;
}
- ret = i915_gem_obj_ggtt_pin(ctx, 4096, true, false);
+ ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0);
if (ret) {
DRM_ERROR("failed to pin power context: %d\n", ret);
goto err_unref;
dev_priv->rps.last_adj = 0;
}
+/* gen6_set_rps is called to update the frequency request, but should also be
+ * called when the range (min_delay and max_delay) is modified so that we can
+ * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */
void gen6_set_rps(struct drm_device *dev, u8 val)
{
struct drm_i915_private *dev_priv = dev->dev_private;
WARN_ON(val > dev_priv->rps.max_delay);
WARN_ON(val < dev_priv->rps.min_delay);
- if (val == dev_priv->rps.cur_delay)
+ if (val == dev_priv->rps.cur_delay) {
+ /* min/max delay may still have been modified so be sure to
+ * write the limits value */
+ I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
+ gen6_rps_limits(dev_priv, val));
+
return;
+ }
gen6_set_rps_thresholds(dev_priv, val);
trace_intel_gpu_freq_change(val * 50);
}
+/* vlv_set_rps_idle: Set the frequency to Rpn if Gfx clocks are down
+ *
+ * * If Gfx is Idle, then
+ * 1. Mask Turbo interrupts
+ * 2. Bring up Gfx clock
+ * 3. Change the freq to Rpn and wait till P-Unit updates freq
+ * 4. Clear the Force GFX CLK ON bit so that Gfx can down
+ * 5. Unmask Turbo interrupts
+*/
+static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
+{
+ /*
+ * When we are idle. Drop to min voltage state.
+ */
+
+ if (dev_priv->rps.cur_delay <= dev_priv->rps.min_delay)
+ return;
+
+ /* Mask turbo interrupt so that they will not come in between */
+ I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
+
+ /* Bring up the Gfx clock */
+ I915_WRITE(VLV_GTLC_SURVIVABILITY_REG,
+ I915_READ(VLV_GTLC_SURVIVABILITY_REG) |
+ VLV_GFX_CLK_FORCE_ON_BIT);
+
+ if (wait_for(((VLV_GFX_CLK_STATUS_BIT &
+ I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 5)) {
+ DRM_ERROR("GFX_CLK_ON request timed out\n");
+ return;
+ }
+
+ dev_priv->rps.cur_delay = dev_priv->rps.min_delay;
+
+ vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ,
+ dev_priv->rps.min_delay);
+
+ if (wait_for(((vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS))
+ & GENFREQSTATUS) == 0, 5))
+ DRM_ERROR("timed out waiting for Punit\n");
+
+ /* Release the Gfx clock */
+ I915_WRITE(VLV_GTLC_SURVIVABILITY_REG,
+ I915_READ(VLV_GTLC_SURVIVABILITY_REG) &
+ ~VLV_GFX_CLK_FORCE_ON_BIT);
+
+ /* Unmask Up interrupts */
+ dev_priv->rps.rp_up_masked = true;
+ gen6_set_pm_mask(dev_priv, GEN6_PM_RP_DOWN_THRESHOLD,
+ dev_priv->rps.min_delay);
+}
+
void gen6_rps_idle(struct drm_i915_private *dev_priv)
{
struct drm_device *dev = dev_priv->dev;
mutex_lock(&dev_priv->rps.hw_lock);
if (dev_priv->rps.enabled) {
if (IS_VALLEYVIEW(dev))
- valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
+ vlv_set_rps_idle(dev_priv);
else
gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
dev_priv->rps.last_adj = 0;
static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
{
- if (IS_GEN6(dev))
- DRM_DEBUG_DRIVER("Sandybridge: deep RC6 disabled\n");
-
- if (IS_HASWELL(dev))
- DRM_DEBUG_DRIVER("Haswell: only RC6 available\n");
-
DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n",
- (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
- (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
- (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
+ (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
+ (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
+ (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
}
int intel_enable_rc6(const struct drm_device *dev)
if (INTEL_INFO(dev)->gen == 5)
return 0;
- if (IS_HASWELL(dev))
- return INTEL_RC6_ENABLE;
-
- /* snb/ivb have more than one rc6 state. */
- if (INTEL_INFO(dev)->gen == 6)
- return INTEL_RC6_ENABLE;
+ if (IS_IVYBRIDGE(dev))
+ return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
- return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
+ return INTEL_RC6_ENABLE;
}
static void gen6_enable_rps_interrupts(struct drm_device *dev)
/* 3: Enable RC6 */
if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
- DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off");
+ intel_print_rc6_info(dev, rc6_mask);
I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
- GEN6_RC_CTL_EI_MODE(1) |
- rc6_mask);
+ GEN6_RC_CTL_EI_MODE(1) |
+ rc6_mask);
/* 4 Program defaults and thresholds for RPS*/
I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(10)); /* Request 500 MHz */
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_ring_buffer *ring;
- u32 rp_state_cap;
+ u32 rp_state_cap, hw_max, hw_min;
u32 gt_perf_status;
u32 rc6vids, pcu_mbox, rc6_mask = 0;
u32 gtfifodbg;
gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
/* In units of 50MHz */
- dev_priv->rps.hw_max = dev_priv->rps.max_delay = rp_state_cap & 0xff;
- dev_priv->rps.min_delay = (rp_state_cap >> 16) & 0xff;
+ dev_priv->rps.hw_max = hw_max = rp_state_cap & 0xff;
+ hw_min = (rp_state_cap >> 16) & 0xff;
dev_priv->rps.rp1_delay = (rp_state_cap >> 8) & 0xff;
dev_priv->rps.rp0_delay = (rp_state_cap >> 0) & 0xff;
dev_priv->rps.rpe_delay = dev_priv->rps.rp1_delay;
dev_priv->rps.cur_delay = 0;
+ /* Preserve min/max settings in case of re-init */
+ if (dev_priv->rps.max_delay == 0)
+ dev_priv->rps.max_delay = hw_max;
+
+ if (dev_priv->rps.min_delay == 0)
+ dev_priv->rps.min_delay = hw_min;
+
/* disable the counters and set deterministic thresholds */
I915_WRITE(GEN6_RC_CONTROL, 0);
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_ring_buffer *ring;
- u32 gtfifodbg, val, rc6_mode = 0;
+ u32 gtfifodbg, val, hw_max, hw_min, rc6_mode = 0;
int i;
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
dev_priv->rps.cur_delay);
- dev_priv->rps.max_delay = valleyview_rps_max_freq(dev_priv);
- dev_priv->rps.hw_max = dev_priv->rps.max_delay;
+ dev_priv->rps.hw_max = hw_max = valleyview_rps_max_freq(dev_priv);
DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay),
- dev_priv->rps.max_delay);
+ vlv_gpu_freq(dev_priv, hw_max),
+ hw_max);
dev_priv->rps.rpe_delay = valleyview_rps_rpe_freq(dev_priv);
DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
dev_priv->rps.rpe_delay);
- dev_priv->rps.min_delay = valleyview_rps_min_freq(dev_priv);
+ hw_min = valleyview_rps_min_freq(dev_priv);
DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay),
- dev_priv->rps.min_delay);
+ vlv_gpu_freq(dev_priv, hw_min),
+ hw_min);
+
+ /* Preserve min/max settings in case of re-init */
+ if (dev_priv->rps.max_delay == 0)
+ dev_priv->rps.max_delay = hw_max;
+
+ if (dev_priv->rps.min_delay == 0)
+ dev_priv->rps.min_delay = hw_min;
DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
+ dev_priv->rps.rp_up_masked = false;
+ dev_priv->rps.rp_down_masked = false;
+
gen6_enable_rps_interrupts(dev);
gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
{
+ struct drm_device *dev = dev_priv->dev;
unsigned long val;
- if (dev_priv->info->gen != 5)
+ if (INTEL_INFO(dev)->gen != 5)
return 0;
spin_lock_irq(&mchdev_lock);
static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
{
+ struct drm_device *dev = dev_priv->dev;
static const struct v_table {
u16 vd; /* in .1 mil */
u16 vm; /* in .1 mil */
{ 16000, 14875, },
{ 16125, 15000, },
};
- if (dev_priv->info->is_mobile)
+ if (INTEL_INFO(dev)->is_mobile)
return v_table[pxvid].vm;
else
return v_table[pxvid].vd;
void i915_update_gfx_val(struct drm_i915_private *dev_priv)
{
- if (dev_priv->info->gen != 5)
+ struct drm_device *dev = dev_priv->dev;
+
+ if (INTEL_INFO(dev)->gen != 5)
return;
spin_lock_irq(&mchdev_lock);
unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
{
+ struct drm_device *dev = dev_priv->dev;
unsigned long val;
- if (dev_priv->info->gen != 5)
+ if (INTEL_INFO(dev)->gen != 5)
return 0;
spin_lock_irq(&mchdev_lock);
i915_mch_dev = NULL;
spin_unlock_irq(&mchdev_lock);
}
+
static void intel_init_emon(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
I915_WRITE(GEN6_GT_MODE,
_MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE));
+ /*
+ * BSpec recoomends 8x4 when MSAA is used,
+ * however in practice 16x4 seems fastest.
+ */
+ I915_WRITE(GEN6_GT_MODE,
+ GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
ilk_init_lp_watermarks(dev);
I915_WRITE(CACHE_MODE_0,
GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
- /* Bspec says we need to always set all mask bits. */
- I915_WRITE(_3D_CHICKEN3, (0xFFFF << 16) |
- _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL);
+ /* WaStripsFansDisableFastClipPerformanceFix:snb */
+ I915_WRITE(_3D_CHICKEN3,
+ _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
+
+ /*
+ * Bspec says:
+ * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
+ * 3DSTATE_SF number of SF output attributes is more than 16."
+ */
+ I915_WRITE(_3D_CHICKEN3,
+ _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
/*
* According to the spec the following bits should be
g4x_disable_trickle_feed(dev);
- /* The default value should be 0x200 according to docs, but the two
- * platforms I checked have a 0 for this. (Maybe BIOS overrides?) */
- I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_DISABLE(0xffff));
- I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_ENABLE(GEN6_GT_MODE_HI));
-
cpt_init_clock_gating(dev);
gen6_check_mch_setup(dev);
I915_WRITE(GEN7_FF_THREAD_MODE,
I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
+ /* enable HiZ Raw Stall Optimization */
+ I915_WRITE(CACHE_MODE_0_GEN7,
+ _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+
/* WaDisable4x2SubspanOptimization:hsw */
I915_WRITE(CACHE_MODE_1,
_MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+ /*
+ * BSpec recommends 8x4 when MSAA is used,
+ * however in practice 16x4 seems fastest.
+ */
+ I915_WRITE(GEN7_GT_MODE,
+ GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
/* WaSwitchSolVfFArbitrationPriority:hsw */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
if (IS_IVB_GT1(dev))
I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
_MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
- else
- I915_WRITE(GEN7_HALF_SLICE_CHICKEN1_GT2,
- _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
/* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
if (IS_IVB_GT1(dev))
I915_WRITE(GEN7_ROW_CHICKEN2,
_MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
- else
+ else {
+ /* must write both registers */
+ I915_WRITE(GEN7_ROW_CHICKEN2,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
I915_WRITE(GEN7_ROW_CHICKEN2_GT2,
_MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
-
+ }
/* WaForceL3Serialization:ivb */
I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
gen7_setup_fixed_func_scheduler(dev_priv);
+ /* enable HiZ Raw Stall Optimization */
+ I915_WRITE(CACHE_MODE_0_GEN7,
+ _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+
/* WaDisable4x2SubspanOptimization:ivb */
I915_WRITE(CACHE_MODE_1,
_MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+ /*
+ * BSpec recommends 8x4 when MSAA is used,
+ * however in practice 16x4 seems fastest.
+ */
+ I915_WRITE(GEN7_GT_MODE,
+ GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
snpcr &= ~GEN6_MBC_SNPCR_MASK;
snpcr |= GEN6_MBC_SNPCR_MED;
I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
+ /*
+ * BSpec says this must be set, even though
+ * WaDisable4x2SubspanOptimization isn't listed for VLV.
+ */
I915_WRITE(CACHE_MODE_1,
_MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
* Disable clock gating on th GCFG unit to prevent a delay
* in the reporting of vblank events.
*/
- I915_WRITE(VLV_GUNIT_CLOCK_GATE, 0xffffffff);
-
- /* Conservative clock gating settings for now */
- I915_WRITE(0x9400, 0xffffffff);
- I915_WRITE(0x9404, 0xffffffff);
- I915_WRITE(0x9408, 0xffffffff);
- I915_WRITE(0x940c, 0xffffffff);
- I915_WRITE(0x9410, 0xffffffff);
- I915_WRITE(0x9414, 0xffffffff);
- I915_WRITE(0x9418, 0xffffffff);
+ I915_WRITE(VLV_GUNIT_CLOCK_GATE, GCFG_DIS);
}
static void g4x_init_clock_gating(struct drm_device *dev)
projects / deliverable / linux.git / blobdiff