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);
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),
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_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.
+ *
+ * Note that PS/WM thread counts depend on the WIZ hashing
+ * disable bit, which we don't touch here, but it's good
+ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+ */
+ 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) &
~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
+
+ /*
+ * BSpec recommends 8x4 when MSAA is used,
+ * however in practice 16x4 seems fastest.
+ *
+ * Note that PS/WM thread counts depend on the WIZ hashing
+ * disable bit, which we don't touch here, but it's good
+ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+ */
+ I915_WRITE(GEN7_GT_MODE,
+ GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
}
static void haswell_init_clock_gating(struct drm_device *dev)
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.
+ *
+ * Note that PS/WM thread counts depend on the WIZ hashing
+ * disable bit, which we don't touch here, but it's good
+ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+ */
+ 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);
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));
+ if (0) { /* causes HiZ corruption on ivb:gt1 */
+ /* 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.
+ *
+ * Note that PS/WM thread counts depend on the WIZ hashing
+ * disable bit, which we don't touch here, but it's good
+ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+ */
+ 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;
_MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
- /* WaDisableL3CacheAging:vlv */
- I915_WRITE(GEN7_L3CNTLREG1, I915_READ(GEN7_L3CNTLREG1) | GEN7_L3AGDIS);
-
/* WaForceL3Serialization:vlv */
I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
~L3SQ_URB_READ_CAM_MATCH_DISABLE);
* enable it, so check if it's enabled and also check if we've requested it to
* be enabled.
*/
-static bool hsw_power_well_enabled(struct drm_device *dev,
+static bool hsw_power_well_enabled(struct drm_i915_private *dev_priv,
struct i915_power_well *power_well)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
return I915_READ(HSW_PWR_WELL_DRIVER) ==
(HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
}
-bool intel_display_power_enabled_sw(struct drm_device *dev,
+bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv,
enum intel_display_power_domain domain)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_power_domains *power_domains;
power_domains = &dev_priv->power_domains;
return power_domains->domain_use_count[domain];
}
-bool intel_display_power_enabled(struct drm_device *dev,
+bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
enum intel_display_power_domain domain)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_power_domains *power_domains;
struct i915_power_well *power_well;
bool is_enabled;
if (power_well->always_on)
continue;
- if (!power_well->is_enabled(dev, power_well)) {
+ if (!power_well->is_enabled(dev_priv, power_well)) {
is_enabled = false;
break;
}
spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
}
-static void hsw_set_power_well(struct drm_device *dev,
+static void hsw_set_power_well(struct drm_i915_private *dev_priv,
struct i915_power_well *power_well, bool enable)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
bool is_enabled, enable_requested;
uint32_t tmp;
}
}
-static void __intel_power_well_get(struct drm_device *dev,
+static void __intel_power_well_get(struct drm_i915_private *dev_priv,
struct i915_power_well *power_well)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
if (!power_well->count++ && power_well->set) {
hsw_disable_package_c8(dev_priv);
- power_well->set(dev, power_well, true);
+ power_well->set(dev_priv, power_well, true);
}
}
-static void __intel_power_well_put(struct drm_device *dev,
+static void __intel_power_well_put(struct drm_i915_private *dev_priv,
struct i915_power_well *power_well)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
WARN_ON(!power_well->count);
if (!--power_well->count && power_well->set &&
i915.disable_power_well) {
- power_well->set(dev, power_well, false);
+ power_well->set(dev_priv, power_well, false);
hsw_enable_package_c8(dev_priv);
}
}
-void intel_display_power_get(struct drm_device *dev,
+void intel_display_power_get(struct drm_i915_private *dev_priv,
enum intel_display_power_domain domain)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_power_domains *power_domains;
struct i915_power_well *power_well;
int i;
mutex_lock(&power_domains->lock);
for_each_power_well(i, power_well, BIT(domain), power_domains)
- __intel_power_well_get(dev, power_well);
+ __intel_power_well_get(dev_priv, power_well);
power_domains->domain_use_count[domain]++;
mutex_unlock(&power_domains->lock);
}
-void intel_display_power_put(struct drm_device *dev,
+void intel_display_power_put(struct drm_i915_private *dev_priv,
enum intel_display_power_domain domain)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_power_domains *power_domains;
struct i915_power_well *power_well;
int i;
power_domains->domain_use_count[domain]--;
for_each_power_well_rev(i, power_well, BIT(domain), power_domains)
- __intel_power_well_put(dev, power_well);
+ __intel_power_well_put(dev_priv, power_well);
mutex_unlock(&power_domains->lock);
}
dev_priv = container_of(hsw_pwr, struct drm_i915_private,
power_domains);
- intel_display_power_get(dev_priv->dev, POWER_DOMAIN_AUDIO);
+ intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
}
EXPORT_SYMBOL_GPL(i915_request_power_well);
dev_priv = container_of(hsw_pwr, struct drm_i915_private,
power_domains);
- intel_display_power_put(dev_priv->dev, POWER_DOMAIN_AUDIO);
+ intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
}
EXPORT_SYMBOL_GPL(i915_release_power_well);
(power_domains)->power_well_count = ARRAY_SIZE(__power_wells); \
})
-int intel_power_domains_init(struct drm_device *dev)
+int intel_power_domains_init(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_power_domains *power_domains = &dev_priv->power_domains;
mutex_init(&power_domains->lock);
* The enabling order will be from lower to higher indexed wells,
* the disabling order is reversed.
*/
- if (IS_HASWELL(dev)) {
+ if (IS_HASWELL(dev_priv->dev)) {
set_power_wells(power_domains, hsw_power_wells);
hsw_pwr = power_domains;
- } else if (IS_BROADWELL(dev)) {
+ } else if (IS_BROADWELL(dev_priv->dev)) {
set_power_wells(power_domains, bdw_power_wells);
hsw_pwr = power_domains;
} else {
return 0;
}
-void intel_power_domains_remove(struct drm_device *dev)
+void intel_power_domains_remove(struct drm_i915_private *dev_priv)
{
hsw_pwr = NULL;
}
-static void intel_power_domains_resume(struct drm_device *dev)
+static void intel_power_domains_resume(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_power_domains *power_domains = &dev_priv->power_domains;
struct i915_power_well *power_well;
int i;
mutex_lock(&power_domains->lock);
for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) {
if (power_well->set)
- power_well->set(dev, power_well, power_well->count > 0);
+ power_well->set(dev_priv, power_well, power_well->count > 0);
}
mutex_unlock(&power_domains->lock);
}
* to be enabled, and it will only be disabled if none of the registers is
* requesting it to be enabled.
*/
-void intel_power_domains_init_hw(struct drm_device *dev)
+void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
/* For now, we need the power well to be always enabled. */
- intel_display_set_init_power(dev, true);
- intel_power_domains_resume(dev);
+ intel_display_set_init_power(dev_priv, true);
+ intel_power_domains_resume(dev_priv);
- if (!(IS_HASWELL(dev) || IS_BROADWELL(dev)))
+ if (!(IS_HASWELL(dev_priv->dev) || IS_BROADWELL(dev_priv->dev)))
return;
/* We're taking over the BIOS, so clear any requests made by it since
projects / deliverable / linux.git / blobdiff