Merge branch 'drm-intel-fixes' into drm-intel-next
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 0a5bea9..987a165 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1199,6 +1199,26 @@
}
EXPORT_SYMBOL(cpufreq_quick_get);
+/**
+ * cpufreq_quick_get_max - get the max reported CPU frequency for this CPU
+ * @cpu: CPU number
+ *
+ * Just return the max possible frequency for a given CPU.
+ */
+unsigned int cpufreq_quick_get_max(unsigned int cpu)
+{
+ struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+ unsigned int ret_freq = 0;
+
+ if (policy) {
+ ret_freq = policy->max;
+ cpufreq_cpu_put(policy);
+ }
+
+ return ret_freq;
+}
+EXPORT_SYMBOL(cpufreq_quick_get_max);
+
static unsigned int __cpufreq_get(unsigned int cpu)
{
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0a893f7..e2662497 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -865,7 +865,7 @@
MEMSTAT_VID_SHIFT);
seq_printf(m, "Current P-state: %d\n",
(rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT);
- } else if (IS_GEN6(dev)) {
+ } else if (IS_GEN6(dev) || IS_GEN7(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);
@@ -1123,6 +1123,44 @@
return 0;
}
+static int i915_ring_freq_table(struct seq_file *m, void *unused)
+{
+ struct drm_info_node *node = (struct drm_info_node *) m->private;
+ struct drm_device *dev = node->minor->dev;
+ drm_i915_private_t *dev_priv = dev->dev_private;
+ int ret;
+ int gpu_freq, ia_freq;
+
+ if (!(IS_GEN6(dev) || IS_GEN7(dev))) {
+ seq_printf(m, "unsupported on this chipset\n");
+ return 0;
+ }
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
+
+ seq_printf(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\n");
+
+ for (gpu_freq = dev_priv->min_delay; gpu_freq <= dev_priv->max_delay;
+ gpu_freq++) {
+ I915_WRITE(GEN6_PCODE_DATA, gpu_freq);
+ I915_WRITE(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY |
+ GEN6_PCODE_READ_MIN_FREQ_TABLE);
+ if (wait_for((I915_READ(GEN6_PCODE_MAILBOX) &
+ GEN6_PCODE_READY) == 0, 10)) {
+ DRM_ERROR("pcode read of freq table timed out\n");
+ continue;
+ }
+ ia_freq = I915_READ(GEN6_PCODE_DATA);
+ seq_printf(m, "%d\t\t%d\n", gpu_freq * 50, ia_freq * 100);
+ }
+
+ mutex_unlock(&dev->struct_mutex);
+
+ return 0;
+}
+
static int i915_gfxec(struct seq_file *m, void *unused)
{
struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1430,6 +1468,7 @@
{"i915_inttoext_table", i915_inttoext_table, 0},
{"i915_drpc_info", i915_drpc_info, 0},
{"i915_emon_status", i915_emon_status, 0},
+ {"i915_ring_freq_table", i915_ring_freq_table, 0},
{"i915_gfxec", i915_gfxec, 0},
{"i915_fbc_status", i915_fbc_status, 0},
{"i915_sr_status", i915_sr_status, 0},
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 013d304..649278f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -70,6 +70,9 @@
static bool i915_try_reset = true;
module_param_named(reset, i915_try_reset, bool, 0600);
+bool i915_enable_hangcheck = true;
+module_param_named(enable_hangcheck, i915_enable_hangcheck, bool, 0644);
+
static struct drm_driver driver;
extern int intel_agp_enabled;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f245c58..4958ce0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -994,6 +994,7 @@
extern int i915_vbt_sdvo_panel_type;
extern unsigned int i915_enable_rc6;
extern unsigned int i915_enable_fbc;
+extern bool i915_enable_hangcheck;
extern int i915_suspend(struct drm_device *dev, pm_message_t state);
extern int i915_resume(struct drm_device *dev);
@@ -1163,7 +1164,7 @@
int __must_check i915_gem_object_set_domain(struct drm_i915_gem_object *obj,
uint32_t read_domains,
uint32_t write_domain);
-int __must_check i915_gem_object_flush_gpu(struct drm_i915_gem_object *obj);
+int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
int __must_check i915_gem_init_ringbuffer(struct drm_device *dev);
void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
void i915_gem_do_init(struct drm_device *dev,
@@ -1182,7 +1183,8 @@
i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj,
bool write);
int __must_check
-i915_gem_object_set_to_display_plane(struct drm_i915_gem_object *obj,
+i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
+ u32 alignment,
struct intel_ring_buffer *pipelined);
int i915_gem_attach_phys_object(struct drm_device *dev,
struct drm_i915_gem_object *obj,
@@ -1196,9 +1198,14 @@
uint32_t
i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj);
+int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
+ enum i915_cache_level cache_level);
+
/* i915_gem_gtt.c */
void i915_gem_restore_gtt_mappings(struct drm_device *dev);
int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj);
+void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,
+ enum i915_cache_level cache_level);
void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj);
/* i915_gem_evict.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5c0d124..e9d1d5c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1771,8 +1771,11 @@
ring->outstanding_lazy_request = false;
if (!dev_priv->mm.suspended) {
- mod_timer(&dev_priv->hangcheck_timer,
- jiffies + msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD));
+ if (i915_enable_hangcheck) {
+ mod_timer(&dev_priv->hangcheck_timer,
+ jiffies +
+ msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD));
+ }
if (was_empty)
queue_delayed_work(dev_priv->wq,
&dev_priv->mm.retire_work, HZ);
@@ -2143,6 +2146,30 @@
return 0;
}
+static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj)
+{
+ u32 old_write_domain, old_read_domains;
+
+ /* Act a barrier for all accesses through the GTT */
+ mb();
+
+ /* Force a pagefault for domain tracking on next user access */
+ i915_gem_release_mmap(obj);
+
+ if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0)
+ return;
+
+ old_read_domains = obj->base.read_domains;
+ old_write_domain = obj->base.write_domain;
+
+ obj->base.read_domains &= ~I915_GEM_DOMAIN_GTT;
+ obj->base.write_domain &= ~I915_GEM_DOMAIN_GTT;
+
+ trace_i915_gem_object_change_domain(obj,
+ old_read_domains,
+ old_write_domain);
+}
+
/**
* Unbinds an object from the GTT aperture.
*/
@@ -2159,23 +2186,28 @@
return -EINVAL;
}
- /* blow away mappings if mapped through GTT */
- i915_gem_release_mmap(obj);
-
- /* Move the object to the CPU domain to ensure that
- * any possible CPU writes while it's not in the GTT
- * are flushed when we go to remap it. This will
- * also ensure that all pending GPU writes are finished
- * before we unbind.
- */
- ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+ ret = i915_gem_object_finish_gpu(obj);
if (ret == -ERESTARTSYS)
return ret;
/* Continue on if we fail due to EIO, the GPU is hung so we
* should be safe and we need to cleanup or else we might
* cause memory corruption through use-after-free.
*/
+
+ i915_gem_object_finish_gtt(obj);
+
+ /* Move the object to the CPU domain to ensure that
+ * any possible CPU writes while it's not in the GTT
+ * are flushed when we go to remap it.
+ */
+ if (ret == 0)
+ ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+ if (ret == -ERESTARTSYS)
+ return ret;
if (ret) {
+ /* In the event of a disaster, abandon all caches and
+ * hope for the best.
+ */
i915_gem_clflush_object(obj);
obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
}
@@ -2997,51 +3029,139 @@
return 0;
}
-/*
- * Prepare buffer for display plane. Use uninterruptible for possible flush
- * wait, as in modesetting process we're not supposed to be interrupted.
- */
-int
-i915_gem_object_set_to_display_plane(struct drm_i915_gem_object *obj,
- struct intel_ring_buffer *pipelined)
+int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
+ enum i915_cache_level cache_level)
{
- uint32_t old_read_domains;
int ret;
- /* Not valid to be called on unbound objects. */
- if (obj->gtt_space == NULL)
- return -EINVAL;
+ if (obj->cache_level == cache_level)
+ return 0;
+
+ if (obj->pin_count) {
+ DRM_DEBUG("can not change the cache level of pinned objects\n");
+ return -EBUSY;
+ }
+
+ if (obj->gtt_space) {
+ ret = i915_gem_object_finish_gpu(obj);
+ if (ret)
+ return ret;
+
+ i915_gem_object_finish_gtt(obj);
+
+ /* Before SandyBridge, you could not use tiling or fence
+ * registers with snooped memory, so relinquish any fences
+ * currently pointing to our region in the aperture.
+ */
+ if (INTEL_INFO(obj->base.dev)->gen < 6) {
+ ret = i915_gem_object_put_fence(obj);
+ if (ret)
+ return ret;
+ }
+
+ i915_gem_gtt_rebind_object(obj, cache_level);
+ }
+
+ if (cache_level == I915_CACHE_NONE) {
+ u32 old_read_domains, old_write_domain;
+
+ /* If we're coming from LLC cached, then we haven't
+ * actually been tracking whether the data is in the
+ * CPU cache or not, since we only allow one bit set
+ * in obj->write_domain and have been skipping the clflushes.
+ * Just set it to the CPU cache for now.
+ */
+ WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);
+ WARN_ON(obj->base.read_domains & ~I915_GEM_DOMAIN_CPU);
+
+ old_read_domains = obj->base.read_domains;
+ old_write_domain = obj->base.write_domain;
+
+ obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+ obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+
+ trace_i915_gem_object_change_domain(obj,
+ old_read_domains,
+ old_write_domain);
+ }
+
+ obj->cache_level = cache_level;
+ return 0;
+}
+
+/*
+ * Prepare buffer for display plane (scanout, cursors, etc).
+ * Can be called from an uninterruptible phase (modesetting) and allows
+ * any flushes to be pipelined (for pageflips).
+ *
+ * For the display plane, we want to be in the GTT but out of any write
+ * domains. So in many ways this looks like set_to_gtt_domain() apart from the
+ * ability to pipeline the waits, pinning and any additional subtleties
+ * that may differentiate the display plane from ordinary buffers.
+ */
+int
+i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
+ u32 alignment,
+ struct intel_ring_buffer *pipelined)
+{
+ u32 old_read_domains, old_write_domain;
+ int ret;
ret = i915_gem_object_flush_gpu_write_domain(obj);
if (ret)
return ret;
-
- /* Currently, we are always called from an non-interruptible context. */
if (pipelined != obj->ring) {
ret = i915_gem_object_wait_rendering(obj);
if (ret)
return ret;
}
+ /* The display engine is not coherent with the LLC cache on gen6. As
+ * a result, we make sure that the pinning that is about to occur is
+ * done with uncached PTEs. This is lowest common denominator for all
+ * chipsets.
+ *
+ * However for gen6+, we could do better by using the GFDT bit instead
+ * of uncaching, which would allow us to flush all the LLC-cached data
+ * with that bit in the PTE to main memory with just one PIPE_CONTROL.
+ */
+ ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
+ if (ret)
+ return ret;
+
+ /* As the user may map the buffer once pinned in the display plane
+ * (e.g. libkms for the bootup splash), we have to ensure that we
+ * always use map_and_fenceable for all scanout buffers.
+ */
+ ret = i915_gem_object_pin(obj, alignment, true);
+ if (ret)
+ return ret;
+
i915_gem_object_flush_cpu_write_domain(obj);
+ old_write_domain = obj->base.write_domain;
old_read_domains = obj->base.read_domains;
+
+ /* It should now be out of any other write domains, and we can update
+ * the domain values for our changes.
+ */
+ BUG_ON((obj->base.write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
obj->base.read_domains |= I915_GEM_DOMAIN_GTT;
trace_i915_gem_object_change_domain(obj,
old_read_domains,
- obj->base.write_domain);
+ old_write_domain);
return 0;
}
int
-i915_gem_object_flush_gpu(struct drm_i915_gem_object *obj)
+i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj)
{
int ret;
- if (!obj->active)
+ if ((obj->base.read_domains & I915_GEM_GPU_DOMAINS) == 0)
return 0;
if (obj->base.write_domain & I915_GEM_GPU_DOMAINS) {
@@ -3050,6 +3170,9 @@
return ret;
}
+ /* Ensure that we invalidate the GPU's caches and TLBs. */
+ obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
+
return i915_gem_object_wait_rendering(obj);
}
@@ -3576,7 +3699,23 @@
obj->base.write_domain = I915_GEM_DOMAIN_CPU;
obj->base.read_domains = I915_GEM_DOMAIN_CPU;
- obj->cache_level = I915_CACHE_NONE;
+ if (IS_GEN6(dev)) {
+ /* On Gen6, we can have the GPU use the LLC (the CPU
+ * cache) for about a 10% performance improvement
+ * compared to uncached. Graphics requests other than
+ * display scanout are coherent with the CPU in
+ * accessing this cache. This means in this mode we
+ * don't need to clflush on the CPU side, and on the
+ * GPU side we only need to flush internal caches to
+ * get data visible to the CPU.
+ *
+ * However, we maintain the display planes as UC, and so
+ * need to rebind when first used as such.
+ */
+ obj->cache_level = I915_CACHE_LLC;
+ } else
+ obj->cache_level = I915_CACHE_NONE;
+
obj->base.driver_private = NULL;
obj->fence_reg = I915_FENCE_REG_NONE;
INIT_LIST_HEAD(&obj->mm_list);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e46b645..7a709cd 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -59,24 +59,8 @@
(dev_priv->mm.gtt_end - dev_priv->mm.gtt_start) / PAGE_SIZE);
list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list) {
- unsigned int agp_type =
- cache_level_to_agp_type(dev, obj->cache_level);
-
i915_gem_clflush_object(obj);
-
- if (dev_priv->mm.gtt->needs_dmar) {
- BUG_ON(!obj->sg_list);
-
- intel_gtt_insert_sg_entries(obj->sg_list,
- obj->num_sg,
- obj->gtt_space->start >> PAGE_SHIFT,
- agp_type);
- } else
- intel_gtt_insert_pages(obj->gtt_space->start
- >> PAGE_SHIFT,
- obj->base.size >> PAGE_SHIFT,
- obj->pages,
- agp_type);
+ i915_gem_gtt_rebind_object(obj, obj->cache_level);
}
intel_gtt_chipset_flush();
@@ -110,6 +94,27 @@
return 0;
}
+void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,
+ enum i915_cache_level cache_level)
+{
+ struct drm_device *dev = obj->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned int agp_type = cache_level_to_agp_type(dev, cache_level);
+
+ if (dev_priv->mm.gtt->needs_dmar) {
+ BUG_ON(!obj->sg_list);
+
+ intel_gtt_insert_sg_entries(obj->sg_list,
+ obj->num_sg,
+ obj->gtt_space->start >> PAGE_SHIFT,
+ agp_type);
+ } else
+ intel_gtt_insert_pages(obj->gtt_space->start >> PAGE_SHIFT,
+ obj->base.size >> PAGE_SHIFT,
+ obj->pages,
+ agp_type);
+}
+
void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
{
intel_gtt_clear_range(obj->gtt_space->start >> PAGE_SHIFT,
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 226d8b2..2e18161 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -361,10 +361,12 @@
ring->irq_seqno = seqno;
wake_up_all(&ring->irq_queue);
-
- dev_priv->hangcheck_count = 0;
- mod_timer(&dev_priv->hangcheck_timer,
- jiffies + msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD));
+ if (i915_enable_hangcheck) {
+ dev_priv->hangcheck_count = 0;
+ mod_timer(&dev_priv->hangcheck_timer,
+ jiffies +
+ msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD));
+ }
}
static void gen6_pm_rps_work(struct work_struct *work)
@@ -1664,6 +1666,9 @@
uint32_t acthd, instdone, instdone1;
bool err = false;
+ if (!i915_enable_hangcheck)
+ return;
+
/* If all work is done then ACTHD clearly hasn't advanced. */
if (i915_hangcheck_ring_idle(&dev_priv->ring[RCS], &err) &&
i915_hangcheck_ring_idle(&dev_priv->ring[VCS], &err) &&
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5d5def7..4a446b1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3434,7 +3434,9 @@
#define GEN6_PCODE_MAILBOX 0x138124
#define GEN6_PCODE_READY (1<<31)
#define GEN6_READ_OC_PARAMS 0xc
-#define GEN6_PCODE_WRITE_MIN_FREQ_TABLE 0x9
+#define GEN6_PCODE_WRITE_MIN_FREQ_TABLE 0x8
+#define GEN6_PCODE_READ_MIN_FREQ_TABLE 0x9
#define GEN6_PCODE_DATA 0x138128
+#define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8
#endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 5257cfc..8cd1c8b 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -878,8 +878,10 @@
intel_init_emon(dev);
}
- if (IS_GEN6(dev))
+ if (IS_GEN6(dev)) {
gen6_enable_rps(dev_priv);
+ gen6_update_ring_freq(dev_priv);
+ }
mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 21b6f93..823b8d9 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -24,6 +24,7 @@
* Eric Anholt <eric@anholt.net>
*/
+#include <linux/cpufreq.h>
#include <linux/module.h>
#include <linux/input.h>
#include <linux/i2c.h>
@@ -1812,14 +1813,10 @@
}
dev_priv->mm.interruptible = false;
- ret = i915_gem_object_pin(obj, alignment, true);
+ ret = i915_gem_object_pin_to_display_plane(obj, alignment, pipelined);
if (ret)
goto err_interruptible;
- ret = i915_gem_object_set_to_display_plane(obj, pipelined);
- if (ret)
- goto err_unpin;
-
/* Install a fence for tiled scan-out. Pre-i965 always needs a
* fence, whereas 965+ only requires a fence if using
* framebuffer compression. For simplicity, we always install
@@ -1971,7 +1968,7 @@
* This should only fail upon a hung GPU, in which case we
* can safely continue.
*/
- ret = i915_gem_object_flush_gpu(obj);
+ ret = i915_gem_object_finish_gpu(obj);
(void) ret;
}
@@ -5434,21 +5431,15 @@
goto fail_locked;
}
- ret = i915_gem_object_pin(obj, PAGE_SIZE, true);
- if (ret) {
- DRM_ERROR("failed to pin cursor bo\n");
- goto fail_locked;
- }
-
- ret = i915_gem_object_set_to_gtt_domain(obj, 0);
+ ret = i915_gem_object_pin_to_display_plane(obj, 0, NULL);
if (ret) {
DRM_ERROR("failed to move cursor bo into the GTT\n");
- goto fail_unpin;
+ goto fail_locked;
}
ret = i915_gem_object_put_fence(obj);
if (ret) {
- DRM_ERROR("failed to move cursor bo into the GTT\n");
+ DRM_ERROR("failed to release fence for cursor");
goto fail_unpin;
}
@@ -7283,6 +7274,59 @@
mutex_unlock(&dev_priv->dev->struct_mutex);
}
+void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
+{
+ int min_freq = 15;
+ int gpu_freq, ia_freq, max_ia_freq;
+ int scaling_factor = 180;
+
+ max_ia_freq = cpufreq_quick_get_max(0);
+ /*
+ * Default to measured freq if none found, PCU will ensure we don't go
+ * over
+ */
+ if (!max_ia_freq)
+ max_ia_freq = tsc_khz;
+
+ /* Convert from kHz to MHz */
+ max_ia_freq /= 1000;
+
+ mutex_lock(&dev_priv->dev->struct_mutex);
+
+ /*
+ * For each potential GPU frequency, load a ring frequency we'd like
+ * to use for memory access. We do this by specifying the IA frequency
+ * the PCU should use as a reference to determine the ring frequency.
+ */
+ for (gpu_freq = dev_priv->max_delay; gpu_freq >= dev_priv->min_delay;
+ gpu_freq--) {
+ int diff = dev_priv->max_delay - gpu_freq;
+
+ /*
+ * For GPU frequencies less than 750MHz, just use the lowest
+ * ring freq.
+ */
+ if (gpu_freq < min_freq)
+ ia_freq = 800;
+ else
+ ia_freq = max_ia_freq - ((diff * scaling_factor) / 2);
+ ia_freq = DIV_ROUND_CLOSEST(ia_freq, 100);
+
+ I915_WRITE(GEN6_PCODE_DATA,
+ (ia_freq << GEN6_PCODE_FREQ_IA_RATIO_SHIFT) |
+ gpu_freq);
+ I915_WRITE(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY |
+ GEN6_PCODE_WRITE_MIN_FREQ_TABLE);
+ if (wait_for((I915_READ(GEN6_PCODE_MAILBOX) &
+ GEN6_PCODE_READY) == 0, 10)) {
+ DRM_ERROR("pcode write of freq table timed out\n");
+ continue;
+ }
+ }
+
+ mutex_unlock(&dev_priv->dev->struct_mutex);
+}
+
static void ironlake_init_clock_gating(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -7926,8 +7970,10 @@
intel_init_emon(dev);
}
- if (IS_GEN6(dev))
+ if (IS_GEN6(dev) || IS_GEN7(dev)) {
gen6_enable_rps(dev_priv);
+ gen6_update_ring_freq(dev_priv);
+ }
INIT_WORK(&dev_priv->idle_work, intel_idle_update);
setup_timer(&dev_priv->idle_timer, intel_gpu_idle_timer,
@@ -7968,7 +8014,7 @@
if (IS_IRONLAKE_M(dev))
ironlake_disable_drps(dev);
- if (IS_GEN6(dev))
+ if (IS_GEN6(dev) || IS_GEN7(dev))
gen6_disable_rps(dev);
if (IS_IRONLAKE_M(dev))
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9ffa61e..8ac3bd8 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -317,6 +317,7 @@
extern void ironlake_enable_drps(struct drm_device *dev);
extern void ironlake_disable_drps(struct drm_device *dev);
extern void gen6_enable_rps(struct drm_i915_private *dev_priv);
+extern void gen6_update_ring_freq(struct drm_i915_private *dev_priv);
extern void gen6_disable_rps(struct drm_device *dev);
extern void intel_init_emon(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 9e2959b..d360380 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -773,14 +773,10 @@
if (ret != 0)
return ret;
- ret = i915_gem_object_pin(new_bo, PAGE_SIZE, true);
+ ret = i915_gem_object_pin_to_display_plane(new_bo, 0, NULL);
if (ret != 0)
return ret;
- ret = i915_gem_object_set_to_gtt_domain(new_bo, 0);
- if (ret != 0)
- goto out_unpin;
-
ret = i915_gem_object_put_fence(new_bo);
if (ret)
goto out_unpin;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 95c4b14..e961568 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -236,7 +236,8 @@
ret = -ENOMEM;
goto err;
}
- obj->cache_level = I915_CACHE_LLC;
+
+ i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
ret = i915_gem_object_pin(obj, 4096, true);
if (ret)
@@ -776,7 +777,8 @@
ret = -ENOMEM;
goto err;
}
- obj->cache_level = I915_CACHE_LLC;
+
+ i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
ret = i915_gem_object_pin(obj, 4096, true);
if (ret != 0) {
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 11be48e..6216115 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -324,11 +324,16 @@
/* query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it */
#ifdef CONFIG_CPU_FREQ
unsigned int cpufreq_quick_get(unsigned int cpu);
+unsigned int cpufreq_quick_get_max(unsigned int cpu);
#else
static inline unsigned int cpufreq_quick_get(unsigned int cpu)
{
return 0;
}
+static inline unsigned int cpufreq_quick_get_max(unsigned int cpu)
+{
+ return 0;
+}
#endif