Merge branch 'topic/bxt-stage1' into drm-intel-next-queued
Separate topic branch for bxt didn't work out since we needed to
refactor the gmbus code a bit to make it look decent. So backmerge.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index b3989e2..b49dc51 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1289,6 +1289,29 @@
EXPORT_SYMBOL(drm_plane_index);
/**
+ * drm_plane_from_index - find the registered plane at an index
+ * @dev: DRM device
+ * @idx: index of registered plane to find for
+ *
+ * Given a plane index, return the registered plane from DRM device's
+ * list of planes with matching index.
+ */
+struct drm_plane *
+drm_plane_from_index(struct drm_device *dev, int idx)
+{
+ struct drm_plane *plane;
+ unsigned int i = 0;
+
+ list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
+ if (i == idx)
+ return plane;
+ i++;
+ }
+ return NULL;
+}
+EXPORT_SYMBOL(drm_plane_from_index);
+
+/**
* drm_plane_force_disable - Forcibly disable a plane
* @plane: plane to disable
*
diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c
index 0f2587ff..89b08a8 100644
--- a/drivers/gpu/drm/i915/dvo_ivch.c
+++ b/drivers/gpu/drm/i915/dvo_ivch.c
@@ -23,6 +23,9 @@
* Authors:
* Eric Anholt <eric@anholt.net>
*
+ * Minor modifications (Dithering enable):
+ * Thomas Richter <thor@math.tu-berlin.de>
+ *
*/
#include "dvo.h"
@@ -59,6 +62,8 @@
# define VR01_DVO_BYPASS_ENABLE (1 << 1)
/** Enables the DVO clock */
# define VR01_DVO_ENABLE (1 << 0)
+/** Enable dithering for 18bpp panels. Not documented. */
+# define VR01_DITHER_ENABLE (1 << 4)
/*
* LCD Interface Format
@@ -74,6 +79,8 @@
# define VR10_INTERFACE_2X18 (2 << 2)
/** Enables 2x24-bit LVDS output */
# define VR10_INTERFACE_2X24 (3 << 2)
+/** Mask that defines the depth of the pipeline */
+# define VR10_INTERFACE_DEPTH_MASK (3 << 2)
/*
* VR20 LCD Horizontal Display Size
@@ -342,9 +349,15 @@
struct drm_display_mode *adjusted_mode)
{
uint16_t vr40 = 0;
- uint16_t vr01;
+ uint16_t vr01 = 0;
+ uint16_t vr10;
- vr01 = 0;
+ ivch_read(dvo, VR10, &vr10);
+ /* Enable dithering for 18 bpp pipelines */
+ vr10 &= VR10_INTERFACE_DEPTH_MASK;
+ if (vr10 == VR10_INTERFACE_2X18 || vr10 == VR10_INTERFACE_1X18)
+ vr01 = VR01_DITHER_ENABLE;
+
vr40 = (VR40_STALL_ENABLE | VR40_VERTICAL_INTERP_ENABLE |
VR40_HORIZONTAL_INTERP_ENABLE);
@@ -353,7 +366,7 @@
uint16_t x_ratio, y_ratio;
vr01 |= VR01_PANEL_FIT_ENABLE;
- vr40 |= VR40_CLOCK_GATING_ENABLE;
+ vr40 |= VR40_CLOCK_GATING_ENABLE | VR40_ENHANCED_PANEL_FITTING;
x_ratio = (((mode->hdisplay - 1) << 16) /
(adjusted_mode->hdisplay - 1)) >> 2;
y_ratio = (((mode->vdisplay - 1) << 16) /
@@ -380,6 +393,8 @@
DRM_DEBUG_KMS("VR00: 0x%04x\n", val);
ivch_read(dvo, VR01, &val);
DRM_DEBUG_KMS("VR01: 0x%04x\n", val);
+ ivch_read(dvo, VR10, &val);
+ DRM_DEBUG_KMS("VR10: 0x%04x\n", val);
ivch_read(dvo, VR30, &val);
DRM_DEBUG_KMS("VR30: 0x%04x\n", val);
ivch_read(dvo, VR40, &val);
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 61ae8ff..9605ff8 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -869,6 +869,9 @@
batch_len + batch_start_offset > src_obj->base.size)
return ERR_PTR(-E2BIG);
+ if (WARN_ON(dest_obj->pages_pin_count == 0))
+ return ERR_PTR(-ENODEV);
+
ret = i915_gem_obj_prepare_shmem_read(src_obj, &needs_clflush);
if (ret) {
DRM_DEBUG_DRIVER("CMD: failed to prepare shadow batch\n");
@@ -882,13 +885,6 @@
goto unpin_src;
}
- ret = i915_gem_object_get_pages(dest_obj);
- if (ret) {
- DRM_DEBUG_DRIVER("CMD: Failed to get pages for shadow batch\n");
- goto unmap_src;
- }
- i915_gem_object_pin_pages(dest_obj);
-
ret = i915_gem_object_set_to_cpu_domain(dest_obj, true);
if (ret) {
DRM_DEBUG_DRIVER("CMD: Failed to set shadow batch to CPU\n");
@@ -898,7 +894,6 @@
dst = vmap_batch(dest_obj, 0, batch_len);
if (!dst) {
DRM_DEBUG_DRIVER("CMD: Failed to vmap shadow batch\n");
- i915_gem_object_unpin_pages(dest_obj);
ret = -ENOMEM;
goto unmap_src;
}
@@ -1129,7 +1124,6 @@
}
vunmap(batch_base);
- i915_gem_object_unpin_pages(shadow_batch_obj);
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index effb7fc..2394924 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -123,8 +123,9 @@
struct i915_vma *vma;
int pin_count = 0;
- seq_printf(m, "%pK: %s%s%s %8zdKiB %02x %02x %x %x %x%s%s%s",
+ seq_printf(m, "%pK: %s%s%s%s %8zdKiB %02x %02x %x %x %x%s%s%s",
&obj->base,
+ obj->active ? "*" : " ",
get_pin_flag(obj),
get_tiling_flag(obj),
get_global_flag(obj),
@@ -159,9 +160,9 @@
}
if (obj->stolen)
seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
- if (obj->pin_mappable || obj->fault_mappable) {
+ if (obj->pin_display || obj->fault_mappable) {
char s[3], *t = s;
- if (obj->pin_mappable)
+ if (obj->pin_display)
*t++ = 'p';
if (obj->fault_mappable)
*t++ = 'f';
@@ -361,31 +362,39 @@
return 0;
}
-#define print_file_stats(m, name, stats) \
- seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu global, %zu shared, %zu unbound)\n", \
- name, \
- stats.count, \
- stats.total, \
- stats.active, \
- stats.inactive, \
- stats.global, \
- stats.shared, \
- stats.unbound)
+#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", \
+ name, \
+ stats.count, \
+ stats.total, \
+ stats.active, \
+ stats.inactive, \
+ stats.global, \
+ stats.shared, \
+ stats.unbound); \
+} while (0)
static void print_batch_pool_stats(struct seq_file *m,
struct drm_i915_private *dev_priv)
{
struct drm_i915_gem_object *obj;
struct file_stats stats;
+ struct intel_engine_cs *ring;
+ int i, j;
memset(&stats, 0, sizeof(stats));
- list_for_each_entry(obj,
- &dev_priv->mm.batch_pool.cache_list,
- batch_pool_list)
- per_file_stats(0, obj, &stats);
+ for_each_ring(ring, dev_priv, i) {
+ for (j = 0; j < ARRAY_SIZE(ring->batch_pool.cache_list); j++) {
+ list_for_each_entry(obj,
+ &ring->batch_pool.cache_list[j],
+ batch_pool_link)
+ per_file_stats(0, obj, &stats);
+ }
+ }
- print_file_stats(m, "batch pool", stats);
+ print_file_stats(m, "[k]batch pool", stats);
}
#define count_vmas(list, member) do { \
@@ -449,7 +458,7 @@
size += i915_gem_obj_ggtt_size(obj);
++count;
}
- if (obj->pin_mappable) {
+ if (obj->pin_display) {
mappable_size += i915_gem_obj_ggtt_size(obj);
++mappable_count;
}
@@ -471,8 +480,6 @@
seq_putc(m, '\n');
print_batch_pool_stats(m, dev_priv);
-
- seq_putc(m, '\n');
list_for_each_entry_reverse(file, &dev->filelist, lhead) {
struct file_stats stats;
struct task_struct *task;
@@ -613,24 +620,39 @@
struct drm_device *dev = node->minor->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj;
- int count = 0;
- int ret;
+ struct intel_engine_cs *ring;
+ int total = 0;
+ int ret, i, j;
ret = mutex_lock_interruptible(&dev->struct_mutex);
if (ret)
return ret;
- seq_puts(m, "cache:\n");
- list_for_each_entry(obj,
- &dev_priv->mm.batch_pool.cache_list,
- batch_pool_list) {
- seq_puts(m, " ");
- describe_obj(m, obj);
- seq_putc(m, '\n');
- count++;
+ for_each_ring(ring, dev_priv, i) {
+ for (j = 0; j < ARRAY_SIZE(ring->batch_pool.cache_list); j++) {
+ int count;
+
+ count = 0;
+ list_for_each_entry(obj,
+ &ring->batch_pool.cache_list[j],
+ batch_pool_link)
+ count++;
+ seq_printf(m, "%s cache[%d]: %d objects\n",
+ ring->name, j, count);
+
+ list_for_each_entry(obj,
+ &ring->batch_pool.cache_list[j],
+ batch_pool_link) {
+ seq_puts(m, " ");
+ describe_obj(m, obj);
+ seq_putc(m, '\n');
+ }
+
+ total += count;
+ }
}
- seq_printf(m, "total: %d\n", count);
+ seq_printf(m, "total: %d\n", total);
mutex_unlock(&dev->struct_mutex);
@@ -643,31 +665,44 @@
struct drm_device *dev = node->minor->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring;
- struct drm_i915_gem_request *gem_request;
- int ret, count, i;
+ struct drm_i915_gem_request *rq;
+ int ret, any, i;
ret = mutex_lock_interruptible(&dev->struct_mutex);
if (ret)
return ret;
- count = 0;
+ any = 0;
for_each_ring(ring, dev_priv, i) {
- if (list_empty(&ring->request_list))
+ int count;
+
+ count = 0;
+ list_for_each_entry(rq, &ring->request_list, list)
+ count++;
+ if (count == 0)
continue;
- seq_printf(m, "%s requests:\n", ring->name);
- list_for_each_entry(gem_request,
- &ring->request_list,
- list) {
- seq_printf(m, " %x @ %d\n",
- gem_request->seqno,
- (int) (jiffies - gem_request->emitted_jiffies));
+ seq_printf(m, "%s requests: %d\n", ring->name, count);
+ list_for_each_entry(rq, &ring->request_list, list) {
+ struct task_struct *task;
+
+ rcu_read_lock();
+ task = NULL;
+ if (rq->pid)
+ task = pid_task(rq->pid, PIDTYPE_PID);
+ seq_printf(m, " %x @ %d: %s [%d]\n",
+ rq->seqno,
+ (int) (jiffies - rq->emitted_jiffies),
+ task ? task->comm : "<unknown>",
+ task ? task->pid : -1);
+ rcu_read_unlock();
}
- count++;
+
+ any++;
}
mutex_unlock(&dev->struct_mutex);
- if (count == 0)
+ if (any == 0)
seq_puts(m, "No requests\n");
return 0;
@@ -2153,8 +2188,6 @@
if (!ppgtt)
return;
- seq_printf(m, "Page directories: %d\n", ppgtt->num_pd_pages);
- seq_printf(m, "Page tables: %d\n", ppgtt->num_pd_entries);
for_each_ring(ring, dev_priv, unused) {
seq_printf(m, "%s\n", ring->name);
for (i = 0; i < 4; i++) {
@@ -2226,6 +2259,44 @@
return 0;
}
+static int i915_rps_boost_info(struct seq_file *m, void *data)
+{
+ struct drm_info_node *node = m->private;
+ struct drm_device *dev = node->minor->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_file *file;
+ int ret;
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
+
+ ret = mutex_lock_interruptible(&dev_priv->rps.hw_lock);
+ if (ret)
+ goto unlock;
+
+ list_for_each_entry_reverse(file, &dev->filelist, lhead) {
+ struct drm_i915_file_private *file_priv = file->driver_priv;
+ struct task_struct *task;
+
+ rcu_read_lock();
+ task = pid_task(file->pid, PIDTYPE_PID);
+ seq_printf(m, "%s [%d]: %d boosts%s\n",
+ task ? task->comm : "<unknown>",
+ task ? task->pid : -1,
+ file_priv->rps_boosts,
+ list_empty(&file_priv->rps_boost) ? "" : ", active");
+ rcu_read_unlock();
+ }
+ seq_printf(m, "Kernel boosts: %d\n", dev_priv->rps.boosts);
+
+ mutex_unlock(&dev_priv->rps.hw_lock);
+unlock:
+ mutex_unlock(&dev->struct_mutex);
+
+ return ret;
+}
+
static int i915_llc(struct seq_file *m, void *data)
{
struct drm_info_node *node = m->private;
@@ -4738,6 +4809,7 @@
{"i915_ddb_info", i915_ddb_info, 0},
{"i915_sseu_status", i915_sseu_status, 0},
{"i915_drrs_status", i915_drrs_status, 0},
+ {"i915_rps_boost_info", i915_rps_boost_info, 0},
};
#define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
@@ -4827,3 +4899,99 @@
drm_debugfs_remove_files(info_list, 1, minor);
}
}
+
+struct dpcd_block {
+ /* DPCD dump start address. */
+ unsigned int offset;
+ /* DPCD dump end address, inclusive. If unset, .size will be used. */
+ unsigned int end;
+ /* DPCD dump size. Used if .end is unset. If unset, defaults to 1. */
+ size_t size;
+ /* Only valid for eDP. */
+ bool edp;
+};
+
+static const struct dpcd_block i915_dpcd_debug[] = {
+ { .offset = DP_DPCD_REV, .size = DP_RECEIVER_CAP_SIZE },
+ { .offset = DP_PSR_SUPPORT, .end = DP_PSR_CAPS },
+ { .offset = DP_DOWNSTREAM_PORT_0, .size = 16 },
+ { .offset = DP_LINK_BW_SET, .end = DP_EDP_CONFIGURATION_SET },
+ { .offset = DP_SINK_COUNT, .end = DP_ADJUST_REQUEST_LANE2_3 },
+ { .offset = DP_SET_POWER },
+ { .offset = DP_EDP_DPCD_REV },
+ { .offset = DP_EDP_GENERAL_CAP_1, .end = DP_EDP_GENERAL_CAP_3 },
+ { .offset = DP_EDP_DISPLAY_CONTROL_REGISTER, .end = DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB },
+ { .offset = DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET, .end = DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET },
+};
+
+static int i915_dpcd_show(struct seq_file *m, void *data)
+{
+ struct drm_connector *connector = m->private;
+ struct intel_dp *intel_dp =
+ enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+ uint8_t buf[16];
+ ssize_t err;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(i915_dpcd_debug); i++) {
+ const struct dpcd_block *b = &i915_dpcd_debug[i];
+ size_t size = b->end ? b->end - b->offset + 1 : (b->size ?: 1);
+
+ if (b->edp &&
+ connector->connector_type != DRM_MODE_CONNECTOR_eDP)
+ continue;
+
+ /* low tech for now */
+ if (WARN_ON(size > sizeof(buf)))
+ continue;
+
+ err = drm_dp_dpcd_read(&intel_dp->aux, b->offset, buf, size);
+ if (err <= 0) {
+ DRM_ERROR("dpcd read (%zu bytes at %u) failed (%zd)\n",
+ size, b->offset, err);
+ continue;
+ }
+
+ seq_printf(m, "%04x: %*ph\n", b->offset, (int) size, buf);
+ };
+
+ return 0;
+}
+
+static int i915_dpcd_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, i915_dpcd_show, inode->i_private);
+}
+
+static const struct file_operations i915_dpcd_fops = {
+ .owner = THIS_MODULE,
+ .open = i915_dpcd_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+/**
+ * i915_debugfs_connector_add - add i915 specific connector debugfs files
+ * @connector: pointer to a registered drm_connector
+ *
+ * Cleanup will be done by drm_connector_unregister() through a call to
+ * drm_debugfs_connector_remove().
+ *
+ * Returns 0 on success, negative error codes on error.
+ */
+int i915_debugfs_connector_add(struct drm_connector *connector)
+{
+ struct dentry *root = connector->debugfs_entry;
+
+ /* The connector must have been registered beforehands. */
+ if (!root)
+ return -ENODEV;
+
+ if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
+ connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+ debugfs_create_file("i915_dpcd", S_IRUGO, root, connector,
+ &i915_dpcd_fops);
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index a9b7770..e44116f 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1039,8 +1039,12 @@
put_bridge:
pci_dev_put(dev_priv->bridge_dev);
free_priv:
- if (dev_priv->slab)
- kmem_cache_destroy(dev_priv->slab);
+ if (dev_priv->requests)
+ kmem_cache_destroy(dev_priv->requests);
+ if (dev_priv->vmas)
+ kmem_cache_destroy(dev_priv->vmas);
+ if (dev_priv->objects)
+ kmem_cache_destroy(dev_priv->objects);
kfree(dev_priv);
return ret;
}
@@ -1105,7 +1109,6 @@
mutex_lock(&dev->struct_mutex);
i915_gem_cleanup_ringbuffer(dev);
- i915_gem_batch_pool_fini(&dev_priv->mm.batch_pool);
i915_gem_context_fini(dev);
mutex_unlock(&dev->struct_mutex);
i915_gem_cleanup_stolen(dev);
@@ -1124,8 +1127,12 @@
if (dev_priv->regs != NULL)
pci_iounmap(dev->pdev, dev_priv->regs);
- if (dev_priv->slab)
- kmem_cache_destroy(dev_priv->slab);
+ if (dev_priv->requests)
+ kmem_cache_destroy(dev_priv->requests);
+ if (dev_priv->vmas)
+ kmem_cache_destroy(dev_priv->vmas);
+ if (dev_priv->objects)
+ kmem_cache_destroy(dev_priv->objects);
pci_dev_put(dev_priv->bridge_dev);
kfree(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 48434cb6..c1a3cdb5 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1207,11 +1207,13 @@
int err;
val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
- WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on);
#define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT)
/* Wait for a previous force-off to settle */
- if (force_on) {
+ if (force_on && !IS_CHERRYVIEW(dev_priv->dev)) {
+ /* WARN_ON only for the Valleyview */
+ WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on);
+
err = wait_for(!COND, 20);
if (err) {
DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n",
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 99facbf..3b21249 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -56,7 +56,7 @@
#define DRIVER_NAME "i915"
#define DRIVER_DESC "Intel Graphics"
-#define DRIVER_DATE "20150327"
+#define DRIVER_DATE "20150410"
#undef WARN_ON
/* Many gcc seem to no see through this and fall over :( */
@@ -455,6 +455,7 @@
u32 semaphore_seqno[I915_NUM_RINGS - 1];
/* Register state */
+ u32 start;
u32 tail;
u32 head;
u32 ctl;
@@ -881,6 +882,8 @@
struct delayed_work work;
unsigned busy_frontbuffer_bits;
bool link_standby;
+ bool psr2_support;
+ bool aux_frame_sync;
};
enum intel_pch {
@@ -1033,11 +1036,16 @@
u8 rp0_freq; /* Non-overclocked max frequency. */
u32 cz_freq;
+ u8 up_threshold; /* Current %busy required to uplock */
+ u8 down_threshold; /* Current %busy required to downclock */
+
int last_adj;
enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
bool enabled;
struct delayed_work delayed_resume_work;
+ struct list_head clients;
+ unsigned boosts;
/* manual wa residency calculations */
struct intel_rps_ei up_ei, down_ei;
@@ -1135,11 +1143,6 @@
int which_slice;
};
-struct i915_gem_batch_pool {
- struct drm_device *dev;
- struct list_head cache_list;
-};
-
struct i915_gem_mm {
/** Memory allocator for GTT stolen memory */
struct drm_mm stolen;
@@ -1153,13 +1156,6 @@
*/
struct list_head unbound_list;
- /*
- * A pool of objects to use as shadow copies of client batch buffers
- * when the command parser is enabled. Prevents the client from
- * modifying the batch contents after software parsing.
- */
- struct i915_gem_batch_pool batch_pool;
-
/** Usable portion of the GTT for GEM */
unsigned long stolen_base; /* limited to low memory (32-bit) */
@@ -1562,7 +1558,9 @@
struct drm_i915_private {
struct drm_device *dev;
- struct kmem_cache *slab;
+ struct kmem_cache *objects;
+ struct kmem_cache *vmas;
+ struct kmem_cache *requests;
const struct intel_device_info info;
@@ -1574,8 +1572,7 @@
struct i915_virtual_gpu vgpu;
- struct intel_gmbus gmbus[GMBUS_NUM_PORTS];
-
+ struct intel_gmbus gmbus[GMBUS_NUM_PINS];
/** gmbus_mutex protects against concurrent usage of the single hw gmbus
* controller on different i2c buses. */
@@ -1814,20 +1811,18 @@
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
- int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
- struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ int (*execbuf_submit)(struct drm_device *dev, struct drm_file *file,
+ struct intel_engine_cs *ring,
+ struct intel_context *ctx,
+ struct drm_i915_gem_execbuffer2 *args,
+ struct list_head *vmas,
+ struct drm_i915_gem_object *batch_obj,
+ u64 exec_start, u32 flags);
int (*init_rings)(struct drm_device *dev);
void (*cleanup_ring)(struct intel_engine_cs *ring);
void (*stop_ring)(struct intel_engine_cs *ring);
} gt;
- uint32_t request_uniq;
-
/*
* NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
* will be rejected. Instead look for a better place.
@@ -1916,7 +1911,7 @@
/** Used in execbuf to temporarily hold a ref */
struct list_head obj_exec_link;
- struct list_head batch_pool_list;
+ struct list_head batch_pool_link;
/**
* This is set if the object is on the active lists (has pending
@@ -1968,7 +1963,6 @@
* accurate mappable working set.
*/
unsigned int fault_mappable:1;
- unsigned int pin_mappable:1;
unsigned int pin_display:1;
/*
@@ -1985,6 +1979,10 @@
struct sg_table *pages;
int pages_pin_count;
+ struct get_page {
+ struct scatterlist *sg;
+ int last;
+ } get_page;
/* prime dma-buf support */
void *dma_buf_vmapping;
@@ -2045,6 +2043,7 @@
struct kref ref;
/** On Which ring this request was generated */
+ struct drm_i915_private *i915;
struct intel_engine_cs *ring;
/** GEM sequence number associated with this request. */
@@ -2092,8 +2091,6 @@
/** process identifier submitting this request */
struct pid *pid;
- uint32_t uniq;
-
/**
* The ELSP only accepts two elements at a time, so we queue
* context/tail pairs on a given queue (ring->execlist_queue) until the
@@ -2115,6 +2112,8 @@
};
+int i915_gem_request_alloc(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
void i915_gem_request_free(struct kref *req_ref);
static inline uint32_t
@@ -2142,6 +2141,19 @@
kref_put(&req->ref, i915_gem_request_free);
}
+static inline void
+i915_gem_request_unreference__unlocked(struct drm_i915_gem_request *req)
+{
+ struct drm_device *dev;
+
+ if (!req)
+ return;
+
+ dev = req->ring->dev;
+ if (kref_put_mutex(&req->ref, i915_gem_request_free, &dev->struct_mutex))
+ mutex_unlock(&dev->struct_mutex);
+}
+
static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
struct drm_i915_gem_request *src)
{
@@ -2167,12 +2179,13 @@
struct {
spinlock_t lock;
struct list_head request_list;
- struct delayed_work idle_work;
} mm;
struct idr context_idr;
- atomic_t rps_wait_boost;
- struct intel_engine_cs *bsd_ring;
+ struct list_head rps_boost;
+ struct intel_engine_cs *bsd_ring;
+
+ unsigned rps_boosts;
};
/*
@@ -2524,6 +2537,13 @@
enum forcewake_domains domains);
void intel_uncore_forcewake_put(struct drm_i915_private *dev_priv,
enum forcewake_domains domains);
+/* Like above but the caller must manage the uncore.lock itself.
+ * Must be used with I915_READ_FW and friends.
+ */
+void intel_uncore_forcewake_get__locked(struct drm_i915_private *dev_priv,
+ enum forcewake_domains domains);
+void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv,
+ enum forcewake_domains domains);
void assert_forcewakes_inactive(struct drm_i915_private *dev_priv);
static inline bool intel_vgpu_active(struct drm_device *dev)
{
@@ -2645,15 +2665,32 @@
int *needs_clflush);
int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
-static inline struct page *i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
+
+static inline int __sg_page_count(struct scatterlist *sg)
{
- struct sg_page_iter sg_iter;
-
- for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, n)
- return sg_page_iter_page(&sg_iter);
-
- return NULL;
+ return sg->length >> PAGE_SHIFT;
}
+
+static inline struct page *
+i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
+{
+ if (WARN_ON(n >= obj->base.size >> PAGE_SHIFT))
+ return NULL;
+
+ if (n < obj->get_page.last) {
+ obj->get_page.sg = obj->pages->sgl;
+ obj->get_page.last = 0;
+ }
+
+ while (obj->get_page.last + __sg_page_count(obj->get_page.sg) <= n) {
+ obj->get_page.last += __sg_page_count(obj->get_page.sg++);
+ if (unlikely(sg_is_chain(obj->get_page.sg)))
+ obj->get_page.sg = sg_chain_ptr(obj->get_page.sg);
+ }
+
+ return nth_page(sg_page(obj->get_page.sg), n - obj->get_page.last);
+}
+
static inline void i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
{
BUG_ON(obj->pages == NULL);
@@ -2997,8 +3034,10 @@
int i915_debugfs_init(struct drm_minor *minor);
void i915_debugfs_cleanup(struct drm_minor *minor);
#ifdef CONFIG_DEBUG_FS
+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 void intel_display_crc_init(struct drm_device *dev) {}
#endif
@@ -3025,13 +3064,6 @@
void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
-/* i915_gem_batch_pool.c */
-void i915_gem_batch_pool_init(struct drm_device *dev,
- struct i915_gem_batch_pool *pool);
-void i915_gem_batch_pool_fini(struct i915_gem_batch_pool *pool);
-struct drm_i915_gem_object*
-i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool, size_t size);
-
/* i915_cmd_parser.c */
int i915_cmd_parser_get_version(void);
int i915_cmd_parser_init_ring(struct intel_engine_cs *ring);
@@ -3055,13 +3087,11 @@
/* intel_i2c.c */
extern int intel_setup_gmbus(struct drm_device *dev);
extern void intel_teardown_gmbus(struct drm_device *dev);
-static inline bool intel_gmbus_is_port_valid(unsigned port)
-{
- return (port >= GMBUS_PORT_SSC && port <= GMBUS_PORT_DPD);
-}
+extern bool intel_gmbus_is_valid_pin(struct drm_i915_private *dev_priv,
+ unsigned int pin);
-extern struct i2c_adapter *intel_gmbus_get_adapter(
- struct drm_i915_private *dev_priv, unsigned port);
+extern struct i2c_adapter *
+intel_gmbus_get_adapter(struct drm_i915_private *dev_priv, unsigned int pin);
extern void intel_gmbus_set_speed(struct i2c_adapter *adapter, int speed);
extern void intel_gmbus_force_bit(struct i2c_adapter *adapter, bool force_bit);
static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter)
@@ -3207,6 +3237,17 @@
#define POSTING_READ(reg) (void)I915_READ_NOTRACE(reg)
#define POSTING_READ16(reg) (void)I915_READ16_NOTRACE(reg)
+/* These are untraced mmio-accessors that are only valid to be used inside
+ * criticial sections inside IRQ handlers where forcewake is explicitly
+ * controlled.
+ * Think twice, and think again, before using these.
+ * Note: Should only be used between intel_uncore_forcewake_irqlock() and
+ * intel_uncore_forcewake_irqunlock().
+ */
+#define I915_READ_FW(reg__) readl(dev_priv->regs + (reg__))
+#define I915_WRITE_FW(reg__, val__) writel(val__, dev_priv->regs + (reg__))
+#define POSTING_READ_FW(reg__) (void)I915_READ_FW(reg__)
+
/* "Broadcast RGB" property */
#define INTEL_BROADCAST_RGB_AUTO 0
#define INTEL_BROADCAST_RGB_FULL 1
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d07c0b1..89d9ebe 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -378,13 +378,13 @@
void *i915_gem_object_alloc(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- return kmem_cache_zalloc(dev_priv->slab, GFP_KERNEL);
+ return kmem_cache_zalloc(dev_priv->objects, GFP_KERNEL);
}
void i915_gem_object_free(struct drm_i915_gem_object *obj)
{
struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
- kmem_cache_free(dev_priv->slab, obj);
+ kmem_cache_free(dev_priv->objects, obj);
}
static int
@@ -1181,12 +1181,27 @@
return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings);
}
-static bool can_wait_boost(struct drm_i915_file_private *file_priv)
+static int __i915_spin_request(struct drm_i915_gem_request *rq)
{
- if (file_priv == NULL)
- return true;
+ unsigned long timeout;
- return !atomic_xchg(&file_priv->rps_wait_boost, true);
+ if (i915_gem_request_get_ring(rq)->irq_refcount)
+ return -EBUSY;
+
+ timeout = jiffies + 1;
+ while (!need_resched()) {
+ if (i915_gem_request_completed(rq, true))
+ return 0;
+
+ if (time_after_eq(jiffies, timeout))
+ break;
+
+ cpu_relax_lowlatency();
+ }
+ if (i915_gem_request_completed(rq, false))
+ return 0;
+
+ return -EAGAIN;
}
/**
@@ -1230,20 +1245,23 @@
timeout_expire = timeout ?
jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0;
- if (INTEL_INFO(dev)->gen >= 6 && ring->id == RCS && can_wait_boost(file_priv)) {
- gen6_rps_boost(dev_priv);
- if (file_priv)
- mod_delayed_work(dev_priv->wq,
- &file_priv->mm.idle_work,
- msecs_to_jiffies(100));
- }
-
- if (!irq_test_in_progress && WARN_ON(!ring->irq_get(ring)))
- return -ENODEV;
+ if (INTEL_INFO(dev)->gen >= 6)
+ gen6_rps_boost(dev_priv, file_priv);
/* Record current time in case interrupted by signal, or wedged */
trace_i915_gem_request_wait_begin(req);
before = ktime_get_raw_ns();
+
+ /* Optimistic spin for the next jiffie before touching IRQs */
+ ret = __i915_spin_request(req);
+ if (ret == 0)
+ goto out;
+
+ if (!irq_test_in_progress && WARN_ON(!ring->irq_get(ring))) {
+ ret = -ENODEV;
+ goto out;
+ }
+
for (;;) {
struct timer_list timer;
@@ -1292,14 +1310,15 @@
destroy_timer_on_stack(&timer);
}
}
- now = ktime_get_raw_ns();
- trace_i915_gem_request_wait_end(req);
-
if (!irq_test_in_progress)
ring->irq_put(ring);
finish_wait(&ring->irq_queue, &wait);
+out:
+ now = ktime_get_raw_ns();
+ trace_i915_gem_request_wait_end(req);
+
if (timeout) {
s64 tres = *timeout - (now - before);
@@ -2178,6 +2197,10 @@
return ret;
list_add_tail(&obj->global_list, &dev_priv->mm.unbound_list);
+
+ obj->get_page.sg = obj->pages->sgl;
+ obj->get_page.last = 0;
+
return 0;
}
@@ -2420,7 +2443,6 @@
i915_queue_hangcheck(ring->dev);
- cancel_delayed_work_sync(&dev_priv->mm.idle_work);
queue_delayed_work(dev_priv->wq,
&dev_priv->mm.retire_work,
round_jiffies_up_relative(HZ));
@@ -2515,7 +2537,45 @@
i915_gem_context_unreference(ctx);
}
- kfree(req);
+ kmem_cache_free(req->i915->requests, req);
+}
+
+int i915_gem_request_alloc(struct intel_engine_cs *ring,
+ struct intel_context *ctx)
+{
+ struct drm_i915_private *dev_priv = to_i915(ring->dev);
+ struct drm_i915_gem_request *rq;
+ int ret;
+
+ if (ring->outstanding_lazy_request)
+ return 0;
+
+ rq = kmem_cache_zalloc(dev_priv->requests, GFP_KERNEL);
+ if (rq == NULL)
+ return -ENOMEM;
+
+ kref_init(&rq->ref);
+ rq->i915 = dev_priv;
+
+ ret = i915_gem_get_seqno(ring->dev, &rq->seqno);
+ if (ret) {
+ kfree(rq);
+ return ret;
+ }
+
+ rq->ring = ring;
+
+ if (i915.enable_execlists)
+ ret = intel_logical_ring_alloc_request_extras(rq, ctx);
+ else
+ ret = intel_ring_alloc_request_extras(rq);
+ if (ret) {
+ kfree(rq);
+ return ret;
+ }
+
+ ring->outstanding_lazy_request = rq;
+ return 0;
}
struct drm_i915_gem_request *
@@ -2577,7 +2637,6 @@
struct drm_i915_gem_request,
execlist_link);
list_del(&submit_req->execlist_link);
- intel_runtime_pm_put(dev_priv);
if (submit_req->ctx != ring->default_context)
intel_lr_context_unpin(ring, submit_req->ctx);
@@ -2767,8 +2826,25 @@
{
struct drm_i915_private *dev_priv =
container_of(work, typeof(*dev_priv), mm.idle_work.work);
+ struct drm_device *dev = dev_priv->dev;
+ struct intel_engine_cs *ring;
+ int i;
- intel_mark_idle(dev_priv->dev);
+ for_each_ring(ring, dev_priv, i)
+ if (!list_empty(&ring->request_list))
+ return;
+
+ intel_mark_idle(dev);
+
+ if (mutex_trylock(&dev->struct_mutex)) {
+ struct intel_engine_cs *ring;
+ int i;
+
+ for_each_ring(ring, dev_priv, i)
+ i915_gem_batch_pool_fini(&ring->batch_pool);
+
+ mutex_unlock(&dev->struct_mutex);
+ }
}
/**
@@ -2866,9 +2942,7 @@
ret = __i915_wait_request(req, reset_counter, true,
args->timeout_ns > 0 ? &args->timeout_ns : NULL,
file->driver_priv);
- mutex_lock(&dev->struct_mutex);
- i915_gem_request_unreference(req);
- mutex_unlock(&dev->struct_mutex);
+ i915_gem_request_unreference__unlocked(req);
return ret;
out:
@@ -3514,17 +3588,6 @@
if (ret)
goto err_remove_node;
- /* allocate before insert / bind */
- if (vma->vm->allocate_va_range) {
- trace_i915_va_alloc(vma->vm, vma->node.start, vma->node.size,
- VM_TO_TRACE_NAME(vma->vm));
- ret = vma->vm->allocate_va_range(vma->vm,
- vma->node.start,
- vma->node.size);
- if (ret)
- goto err_remove_node;
- }
-
trace_i915_vma_bind(vma, flags);
ret = i915_vma_bind(vma, obj->cache_level,
flags & PIN_GLOBAL ? GLOBAL_BIND : 0);
@@ -4071,9 +4134,7 @@
if (ret == 0)
queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0);
- mutex_lock(&dev->struct_mutex);
- i915_gem_request_unreference(target);
- mutex_unlock(&dev->struct_mutex);
+ i915_gem_request_unreference__unlocked(target);
return ret;
}
@@ -4194,9 +4255,6 @@
WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable);
vma->pin_count++;
- if (flags & PIN_MAPPABLE)
- obj->pin_mappable |= true;
-
return 0;
}
@@ -4234,8 +4292,7 @@
WARN_ON(vma->pin_count == 0);
WARN_ON(!i915_gem_obj_ggtt_bound_view(obj, view));
- if (--vma->pin_count == 0 && view->type == I915_GGTT_VIEW_NORMAL)
- obj->pin_mappable = false;
+ --vma->pin_count;
}
bool
@@ -4374,7 +4431,7 @@
INIT_LIST_HEAD(&obj->ring_list);
INIT_LIST_HEAD(&obj->obj_exec_link);
INIT_LIST_HEAD(&obj->vma_list);
- INIT_LIST_HEAD(&obj->batch_pool_list);
+ INIT_LIST_HEAD(&obj->batch_pool_link);
obj->ops = ops;
@@ -4576,7 +4633,7 @@
list_del(&vma->vma_link);
- kfree(vma);
+ kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma);
}
static void
@@ -4863,12 +4920,12 @@
}
if (!i915.enable_execlists) {
- dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
+ dev_priv->gt.execbuf_submit = i915_gem_ringbuffer_submission;
dev_priv->gt.init_rings = i915_gem_init_rings;
dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
dev_priv->gt.stop_ring = intel_stop_ring_buffer;
} else {
- dev_priv->gt.do_execbuf = intel_execlists_submission;
+ dev_priv->gt.execbuf_submit = intel_execlists_submission;
dev_priv->gt.init_rings = intel_logical_rings_init;
dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
dev_priv->gt.stop_ring = intel_logical_ring_stop;
@@ -4950,11 +5007,21 @@
struct drm_i915_private *dev_priv = dev->dev_private;
int i;
- dev_priv->slab =
+ dev_priv->objects =
kmem_cache_create("i915_gem_object",
sizeof(struct drm_i915_gem_object), 0,
SLAB_HWCACHE_ALIGN,
NULL);
+ dev_priv->vmas =
+ kmem_cache_create("i915_gem_vma",
+ sizeof(struct i915_vma), 0,
+ SLAB_HWCACHE_ALIGN,
+ NULL);
+ dev_priv->requests =
+ kmem_cache_create("i915_gem_request",
+ sizeof(struct drm_i915_gem_request), 0,
+ SLAB_HWCACHE_ALIGN,
+ NULL);
INIT_LIST_HEAD(&dev_priv->vm_list);
i915_init_vm(dev_priv, &dev_priv->gtt.base);
@@ -4997,8 +5064,6 @@
i915_gem_shrinker_init(dev_priv);
- i915_gem_batch_pool_init(dev, &dev_priv->mm.batch_pool);
-
mutex_init(&dev_priv->fb_tracking.lock);
}
@@ -5006,8 +5071,6 @@
{
struct drm_i915_file_private *file_priv = file->driver_priv;
- cancel_delayed_work_sync(&file_priv->mm.idle_work);
-
/* Clean up our request list when the client is going away, so that
* later retire_requests won't dereference our soon-to-be-gone
* file_priv.
@@ -5023,15 +5086,12 @@
request->file_priv = NULL;
}
spin_unlock(&file_priv->mm.lock);
-}
-static void
-i915_gem_file_idle_work_handler(struct work_struct *work)
-{
- struct drm_i915_file_private *file_priv =
- container_of(work, typeof(*file_priv), mm.idle_work.work);
-
- atomic_set(&file_priv->rps_wait_boost, false);
+ if (!list_empty(&file_priv->rps_boost)) {
+ mutex_lock(&to_i915(dev)->rps.hw_lock);
+ list_del(&file_priv->rps_boost);
+ mutex_unlock(&to_i915(dev)->rps.hw_lock);
+ }
}
int i915_gem_open(struct drm_device *dev, struct drm_file *file)
@@ -5048,11 +5108,10 @@
file->driver_priv = file_priv;
file_priv->dev_priv = dev->dev_private;
file_priv->file = file;
+ INIT_LIST_HEAD(&file_priv->rps_boost);
spin_lock_init(&file_priv->mm.lock);
INIT_LIST_HEAD(&file_priv->mm.request_list);
- INIT_DELAYED_WORK(&file_priv->mm.idle_work,
- i915_gem_file_idle_work_handler);
ret = i915_gem_context_open(dev, file);
if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_batch_pool.c b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
index c690170..7bf2f3f 100644
--- a/drivers/gpu/drm/i915/i915_gem_batch_pool.c
+++ b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
@@ -23,6 +23,7 @@
*/
#include "i915_drv.h"
+#include "i915_gem_batch_pool.h"
/**
* DOC: batch pool
@@ -46,8 +47,12 @@
void i915_gem_batch_pool_init(struct drm_device *dev,
struct i915_gem_batch_pool *pool)
{
+ int n;
+
pool->dev = dev;
- INIT_LIST_HEAD(&pool->cache_list);
+
+ for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++)
+ INIT_LIST_HEAD(&pool->cache_list[n]);
}
/**
@@ -58,33 +63,35 @@
*/
void i915_gem_batch_pool_fini(struct i915_gem_batch_pool *pool)
{
+ int n;
+
WARN_ON(!mutex_is_locked(&pool->dev->struct_mutex));
- while (!list_empty(&pool->cache_list)) {
- struct drm_i915_gem_object *obj =
- list_first_entry(&pool->cache_list,
- struct drm_i915_gem_object,
- batch_pool_list);
+ for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++) {
+ while (!list_empty(&pool->cache_list[n])) {
+ struct drm_i915_gem_object *obj =
+ list_first_entry(&pool->cache_list[n],
+ struct drm_i915_gem_object,
+ batch_pool_link);
- WARN_ON(obj->active);
-
- list_del_init(&obj->batch_pool_list);
- drm_gem_object_unreference(&obj->base);
+ list_del(&obj->batch_pool_link);
+ drm_gem_object_unreference(&obj->base);
+ }
}
}
/**
- * i915_gem_batch_pool_get() - select a buffer from the pool
+ * i915_gem_batch_pool_get() - allocate a buffer from the pool
* @pool: the batch buffer pool
* @size: the minimum desired size of the returned buffer
*
- * Finds or allocates a batch buffer in the pool with at least the requested
- * size. The caller is responsible for any domain, active/inactive, or
- * purgeability management for the returned buffer.
+ * Returns an inactive buffer from @pool with at least @size bytes,
+ * with the pages pinned. The caller must i915_gem_object_unpin_pages()
+ * on the returned object.
*
* Note: Callers must hold the struct_mutex
*
- * Return: the selected batch buffer object
+ * Return: the buffer object or an error pointer
*/
struct drm_i915_gem_object *
i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool,
@@ -92,46 +99,53 @@
{
struct drm_i915_gem_object *obj = NULL;
struct drm_i915_gem_object *tmp, *next;
+ struct list_head *list;
+ int n;
WARN_ON(!mutex_is_locked(&pool->dev->struct_mutex));
- list_for_each_entry_safe(tmp, next,
- &pool->cache_list, batch_pool_list) {
+ /* Compute a power-of-two bucket, but throw everything greater than
+ * 16KiB into the same bucket: i.e. the the buckets hold objects of
+ * (1 page, 2 pages, 4 pages, 8+ pages).
+ */
+ n = fls(size >> PAGE_SHIFT) - 1;
+ if (n >= ARRAY_SIZE(pool->cache_list))
+ n = ARRAY_SIZE(pool->cache_list) - 1;
+ list = &pool->cache_list[n];
+ list_for_each_entry_safe(tmp, next, list, batch_pool_link) {
+ /* The batches are strictly LRU ordered */
if (tmp->active)
- continue;
+ break;
/* While we're looping, do some clean up */
if (tmp->madv == __I915_MADV_PURGED) {
- list_del(&tmp->batch_pool_list);
+ list_del(&tmp->batch_pool_link);
drm_gem_object_unreference(&tmp->base);
continue;
}
- /*
- * Select a buffer that is at least as big as needed
- * but not 'too much' bigger. A better way to do this
- * might be to bucket the pool objects based on size.
- */
- if (tmp->base.size >= size &&
- tmp->base.size <= (2 * size)) {
+ if (tmp->base.size >= size) {
obj = tmp;
break;
}
}
- if (!obj) {
+ if (obj == NULL) {
+ int ret;
+
obj = i915_gem_alloc_object(pool->dev, size);
- if (!obj)
+ if (obj == NULL)
return ERR_PTR(-ENOMEM);
- list_add_tail(&obj->batch_pool_list, &pool->cache_list);
+ ret = i915_gem_object_get_pages(obj);
+ if (ret)
+ return ERR_PTR(ret);
+
+ obj->madv = I915_MADV_DONTNEED;
}
- else
- /* Keep list in LRU order */
- list_move_tail(&obj->batch_pool_list, &pool->cache_list);
- obj->madv = I915_MADV_WILLNEED;
-
+ list_move_tail(&obj->batch_pool_link, list);
+ i915_gem_object_pin_pages(obj);
return obj;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_batch_pool.h b/drivers/gpu/drm/i915/i915_gem_batch_pool.h
new file mode 100644
index 0000000..848e907
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_batch_pool.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#ifndef I915_GEM_BATCH_POOL_H
+#define I915_GEM_BATCH_POOL_H
+
+#include "i915_drv.h"
+
+struct i915_gem_batch_pool {
+ struct drm_device *dev;
+ struct list_head cache_list[4];
+};
+
+/* i915_gem_batch_pool.c */
+void i915_gem_batch_pool_init(struct drm_device *dev,
+ struct i915_gem_batch_pool *pool);
+void i915_gem_batch_pool_fini(struct i915_gem_batch_pool *pool);
+struct drm_i915_gem_object*
+i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool, size_t size);
+
+#endif /* I915_GEM_BATCH_POOL_H */
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index f3e84c4..e4c57a3 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -157,7 +157,9 @@
struct drm_i915_gem_object *obj;
int ret;
- obj = i915_gem_alloc_object(dev, size);
+ obj = i915_gem_object_create_stolen(dev, size);
+ if (obj == NULL)
+ obj = i915_gem_alloc_object(dev, size);
if (obj == NULL)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a3190e79..48ac560 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -37,7 +37,6 @@
#define __EXEC_OBJECT_HAS_FENCE (1<<30)
#define __EXEC_OBJECT_NEEDS_MAP (1<<29)
#define __EXEC_OBJECT_NEEDS_BIAS (1<<28)
-#define __EXEC_OBJECT_PURGEABLE (1<<27)
#define BATCH_OFFSET_BIAS (256*1024)
@@ -224,12 +223,7 @@
if (entry->flags & __EXEC_OBJECT_HAS_PIN)
vma->pin_count--;
- if (entry->flags & __EXEC_OBJECT_PURGEABLE)
- obj->madv = I915_MADV_DONTNEED;
-
- entry->flags &= ~(__EXEC_OBJECT_HAS_FENCE |
- __EXEC_OBJECT_HAS_PIN |
- __EXEC_OBJECT_PURGEABLE);
+ entry->flags &= ~(__EXEC_OBJECT_HAS_FENCE | __EXEC_OBJECT_HAS_PIN);
}
static void eb_destroy(struct eb_vmas *eb)
@@ -1142,12 +1136,11 @@
u32 batch_len,
bool is_master)
{
- struct drm_i915_private *dev_priv = to_i915(batch_obj->base.dev);
struct drm_i915_gem_object *shadow_batch_obj;
struct i915_vma *vma;
int ret;
- shadow_batch_obj = i915_gem_batch_pool_get(&dev_priv->mm.batch_pool,
+ shadow_batch_obj = i915_gem_batch_pool_get(&ring->batch_pool,
PAGE_ALIGN(batch_len));
if (IS_ERR(shadow_batch_obj))
return shadow_batch_obj;
@@ -1165,11 +1158,13 @@
if (ret)
goto err;
+ i915_gem_object_unpin_pages(shadow_batch_obj);
+
memset(shadow_exec_entry, 0, sizeof(*shadow_exec_entry));
vma = i915_gem_obj_to_ggtt(shadow_batch_obj);
vma->exec_entry = shadow_exec_entry;
- vma->exec_entry->flags = __EXEC_OBJECT_PURGEABLE | __EXEC_OBJECT_HAS_PIN;
+ vma->exec_entry->flags = __EXEC_OBJECT_HAS_PIN;
drm_gem_object_reference(&shadow_batch_obj->base);
list_add_tail(&vma->exec_list, &eb->vmas);
@@ -1178,6 +1173,7 @@
return shadow_batch_obj;
err:
+ i915_gem_object_unpin_pages(shadow_batch_obj);
if (ret == -EACCES) /* unhandled chained batch */
return batch_obj;
else
@@ -1601,9 +1597,9 @@
} else
exec_start += i915_gem_obj_offset(batch_obj, vm);
- ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
- &eb->vmas, batch_obj, exec_start,
- dispatch_flags);
+ ret = dev_priv->gt.execbuf_submit(dev, file, ring, ctx, args,
+ &eb->vmas, batch_obj, exec_start,
+ dispatch_flags);
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index f48d845..9041f3d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -320,7 +320,7 @@
return 0;
}
-static void unmap_and_free_pt(struct i915_page_table_entry *pt,
+static void unmap_and_free_pt(struct i915_page_table *pt,
struct drm_device *dev)
{
if (WARN_ON(!pt->page))
@@ -332,9 +332,27 @@
kfree(pt);
}
-static struct i915_page_table_entry *alloc_pt_single(struct drm_device *dev)
+static void gen8_initialize_pt(struct i915_address_space *vm,
+ struct i915_page_table *pt)
{
- struct i915_page_table_entry *pt;
+ gen8_pte_t *pt_vaddr, scratch_pte;
+ int i;
+
+ pt_vaddr = kmap_atomic(pt->page);
+ scratch_pte = gen8_pte_encode(vm->scratch.addr,
+ I915_CACHE_LLC, true);
+
+ for (i = 0; i < GEN8_PTES; i++)
+ pt_vaddr[i] = scratch_pte;
+
+ if (!HAS_LLC(vm->dev))
+ drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
+ kunmap_atomic(pt_vaddr);
+}
+
+static struct i915_page_table *alloc_pt_single(struct drm_device *dev)
+{
+ struct i915_page_table *pt;
const size_t count = INTEL_INFO(dev)->gen >= 8 ?
GEN8_PTES : GEN6_PTES;
int ret = -ENOMEM;
@@ -383,7 +401,7 @@
*
* Return: 0 if allocation succeeded.
*/
-static int alloc_pt_range(struct i915_page_directory_entry *pd, uint16_t pde, size_t count,
+static int alloc_pt_range(struct i915_page_directory *pd, uint16_t pde, size_t count,
struct drm_device *dev)
{
int i, ret;
@@ -393,7 +411,7 @@
return -EINVAL;
for (i = pde; i < pde + count; i++) {
- struct i915_page_table_entry *pt = alloc_pt_single(dev);
+ struct i915_page_table *pt = alloc_pt_single(dev);
if (IS_ERR(pt)) {
ret = PTR_ERR(pt);
@@ -413,34 +431,55 @@
return ret;
}
-static void unmap_and_free_pd(struct i915_page_directory_entry *pd)
+static void unmap_and_free_pd(struct i915_page_directory *pd,
+ struct drm_device *dev)
{
if (pd->page) {
+ i915_dma_unmap_single(pd, dev);
__free_page(pd->page);
+ kfree(pd->used_pdes);
kfree(pd);
}
}
-static struct i915_page_directory_entry *alloc_pd_single(void)
+static struct i915_page_directory *alloc_pd_single(struct drm_device *dev)
{
- struct i915_page_directory_entry *pd;
+ struct i915_page_directory *pd;
+ int ret = -ENOMEM;
pd = kzalloc(sizeof(*pd), GFP_KERNEL);
if (!pd)
return ERR_PTR(-ENOMEM);
- pd->page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (!pd->page) {
- kfree(pd);
- return ERR_PTR(-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;
+
+ ret = i915_dma_map_single(pd, dev);
+ if (ret)
+ goto free_page;
return pd;
+
+free_page:
+ __free_page(pd->page);
+free_bitmap:
+ kfree(pd->used_pdes);
+free_pd:
+ kfree(pd);
+
+ return ERR_PTR(ret);
}
/* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
- uint64_t val)
+static int gen8_write_pdp(struct intel_engine_cs *ring,
+ unsigned entry,
+ dma_addr_t addr)
{
int ret;
@@ -452,10 +491,10 @@
intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(ring, GEN8_RING_PDP_UDW(ring, entry));
- intel_ring_emit(ring, (u32)(val >> 32));
+ intel_ring_emit(ring, upper_32_bits(addr));
intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(ring, GEN8_RING_PDP_LDW(ring, entry));
- intel_ring_emit(ring, (u32)(val));
+ intel_ring_emit(ring, lower_32_bits(addr));
intel_ring_advance(ring);
return 0;
@@ -466,12 +505,12 @@
{
int i, ret;
- /* bit of a hack to find the actual last used pd */
- int used_pd = ppgtt->num_pd_entries / I915_PDES;
-
- for (i = used_pd - 1; i >= 0; i--) {
- dma_addr_t addr = ppgtt->pdp.page_directory[i]->daddr;
- ret = gen8_write_pdp(ring, i, addr);
+ 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);
if (ret)
return ret;
}
@@ -497,8 +536,8 @@
I915_CACHE_LLC, use_scratch);
while (num_entries) {
- struct i915_page_directory_entry *pd;
- struct i915_page_table_entry *pt;
+ struct i915_page_directory *pd;
+ struct i915_page_table *pt;
struct page *page_table;
if (WARN_ON(!ppgtt->pdp.page_directory[pdpe]))
@@ -559,8 +598,8 @@
break;
if (pt_vaddr == NULL) {
- struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[pdpe];
- struct i915_page_table_entry *pt = pd->page_table[pde];
+ 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);
@@ -588,14 +627,43 @@
}
}
-static void gen8_free_page_tables(struct i915_page_directory_entry *pd, struct drm_device *dev)
+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);
+}
+
+static void gen8_free_page_tables(struct i915_page_directory *pd, struct drm_device *dev)
{
int i;
if (!pd->page)
return;
- for (i = 0; i < I915_PDES; i++) {
+ for_each_set_bit(i, pd->used_pdes, I915_PDES) {
if (WARN_ON(!pd->page_table[i]))
continue;
@@ -608,45 +676,16 @@
{
int i;
- for (i = 0; i < ppgtt->num_pd_pages; i++) {
+ for_each_set_bit(i, ppgtt->pdp.used_pdpes, GEN8_LEGACY_PDPES) {
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]);
+ unmap_and_free_pd(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
}
-}
-static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
-{
- struct pci_dev *hwdev = ppgtt->base.dev->pdev;
- int i, j;
-
- for (i = 0; i < ppgtt->num_pd_pages; i++) {
- /* TODO: In the future we'll support sparse mappings, so this
- * will have to change. */
- if (!ppgtt->pdp.page_directory[i]->daddr)
- continue;
-
- pci_unmap_page(hwdev, ppgtt->pdp.page_directory[i]->daddr, PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
-
- for (j = 0; j < I915_PDES; j++) {
- struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
- struct i915_page_table_entry *pt;
- dma_addr_t addr;
-
- if (WARN_ON(!pd->page_table[j]))
- continue;
-
- pt = pd->page_table[j];
- addr = pt->daddr;
-
- if (addr)
- pci_unmap_page(hwdev, addr, PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
- }
- }
+ unmap_and_free_pd(ppgtt->scratch_pd, ppgtt->base.dev);
+ unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
}
static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
@@ -654,230 +693,371 @@
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
- gen8_ppgtt_unmap_pages(ppgtt);
gen8_ppgtt_free(ppgtt);
}
-static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
+/**
+ * gen8_ppgtt_alloc_pagetabs() - Allocate page tables for VA range.
+ * @ppgtt: Master ppgtt structure.
+ * @pd: Page directory for this address range.
+ * @start: Starting virtual address to begin allocations.
+ * @length Size of the allocations.
+ * @new_pts: Bitmap set by function with new allocations. Likely used by the
+ * caller to free on error.
+ *
+ * Allocate the required number of page tables. Extremely similar to
+ * gen8_ppgtt_alloc_page_directories(). The main difference is here we are limited by
+ * the page directory boundary (instead of the page directory pointer). That
+ * boundary is 1GB virtual. Therefore, unlike gen8_ppgtt_alloc_page_directories(), it is
+ * possible, and likely that the caller will need to use multiple calls of this
+ * function to achieve the appropriate allocation.
+ *
+ * Return: 0 if success; negative error code otherwise.
+ */
+static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt,
+ struct i915_page_directory *pd,
+ uint64_t start,
+ uint64_t length,
+ unsigned long *new_pts)
{
- int i, ret;
+ struct drm_device *dev = ppgtt->base.dev;
+ struct i915_page_table *pt;
+ uint64_t temp;
+ uint32_t pde;
- for (i = 0; i < ppgtt->num_pd_pages; i++) {
- ret = alloc_pt_range(ppgtt->pdp.page_directory[i],
- 0, I915_PDES, ppgtt->base.dev);
- if (ret)
+ gen8_for_each_pde(pt, pd, start, length, temp, pde) {
+ /* Don't reallocate page tables */
+ if (pt) {
+ /* Scratch is never allocated this way */
+ WARN_ON(pt == ppgtt->scratch_pt);
+ continue;
+ }
+
+ pt = alloc_pt_single(dev);
+ if (IS_ERR(pt))
goto unwind_out;
+
+ gen8_initialize_pt(&ppgtt->base, pt);
+ pd->page_table[pde] = pt;
+ set_bit(pde, new_pts);
}
return 0;
unwind_out:
- while (i--)
- gen8_free_page_tables(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
+ for_each_set_bit(pde, new_pts, I915_PDES)
+ unmap_and_free_pt(pd->page_table[pde], dev);
return -ENOMEM;
}
-static int gen8_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt,
- const int max_pdp)
+/**
+ * gen8_ppgtt_alloc_page_directories() - Allocate page directories for VA range.
+ * @ppgtt: Master ppgtt structure.
+ * @pdp: Page directory pointer for this address range.
+ * @start: Starting virtual address to begin allocations.
+ * @length Size of the allocations.
+ * @new_pds Bitmap set by function with new allocations. Likely used by the
+ * caller to free on error.
+ *
+ * Allocate the required number of page directories starting at the pde index of
+ * @start, and ending at the pde index @start + @length. This function will skip
+ * over already allocated page directories within the range, and only allocate
+ * new ones, setting the appropriate pointer within the pdp as well as the
+ * correct position in the bitmap @new_pds.
+ *
+ * The function will only allocate the pages within the range for a give page
+ * directory pointer. In other words, if @start + @length straddles a virtually
+ * addressed PDP boundary (512GB for 4k pages), there will be more allocations
+ * required by the caller, This is not currently possible, and the BUG in the
+ * code will prevent it.
+ *
+ * Return: 0 if success; negative error code otherwise.
+ */
+static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt,
+ struct i915_page_directory_pointer *pdp,
+ uint64_t start,
+ uint64_t length,
+ unsigned long *new_pds)
+{
+ struct drm_device *dev = ppgtt->base.dev;
+ struct i915_page_directory *pd;
+ uint64_t temp;
+ uint32_t pdpe;
+
+ WARN_ON(!bitmap_empty(new_pds, GEN8_LEGACY_PDPES));
+
+ /* FIXME: PPGTT container_of won't work for 64b */
+ WARN_ON((start + length) > 0x800000000ULL);
+
+ gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
+ if (pd)
+ continue;
+
+ pd = alloc_pd_single(dev);
+ if (IS_ERR(pd))
+ goto unwind_out;
+
+ gen8_initialize_pd(&ppgtt->base, pd);
+ pdp->page_directory[pdpe] = pd;
+ 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);
+
+ return -ENOMEM;
+}
+
+static void
+free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long **new_pts)
{
int i;
- for (i = 0; i < max_pdp; i++) {
- ppgtt->pdp.page_directory[i] = alloc_pd_single();
- if (IS_ERR(ppgtt->pdp.page_directory[i]))
- goto unwind_out;
- }
-
- ppgtt->num_pd_pages = max_pdp;
- BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPES);
-
- return 0;
-
-unwind_out:
- while (i--)
- unmap_and_free_pd(ppgtt->pdp.page_directory[i]);
-
- return -ENOMEM;
+ for (i = 0; i < GEN8_LEGACY_PDPES; i++)
+ kfree(new_pts[i]);
+ kfree(new_pts);
+ kfree(new_pds);
}
-static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
- const int max_pdp)
+/* Fills in the page directory bitmap, and the array of page tables bitmap. Both
+ * of these are based on the number of PDPEs in the system.
+ */
+static
+int __must_check alloc_gen8_temp_bitmaps(unsigned long **new_pds,
+ unsigned long ***new_pts)
{
- int ret;
+ int i;
+ unsigned long *pds;
+ unsigned long **pts;
- ret = gen8_ppgtt_allocate_page_directories(ppgtt, max_pdp);
- if (ret)
- return ret;
+ pds = kcalloc(BITS_TO_LONGS(GEN8_LEGACY_PDPES), sizeof(unsigned long), GFP_KERNEL);
+ if (!pds)
+ return -ENOMEM;
- ret = gen8_ppgtt_allocate_page_tables(ppgtt);
- if (ret)
- goto err_out;
+ pts = kcalloc(GEN8_LEGACY_PDPES, sizeof(unsigned long *), GFP_KERNEL);
+ if (!pts) {
+ kfree(pds);
+ return -ENOMEM;
+ }
- ppgtt->num_pd_entries = max_pdp * I915_PDES;
+ for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
+ pts[i] = kcalloc(BITS_TO_LONGS(I915_PDES),
+ sizeof(unsigned long), GFP_KERNEL);
+ if (!pts[i])
+ goto err_out;
+ }
+
+ *new_pds = pds;
+ *new_pts = pts;
return 0;
err_out:
- gen8_ppgtt_free(ppgtt);
+ free_gen8_temp_bitmaps(pds, pts);
+ return -ENOMEM;
+}
+
+static int gen8_alloc_va_range(struct i915_address_space *vm,
+ uint64_t start,
+ uint64_t length)
+{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+ unsigned long *new_page_dirs, **new_page_tables;
+ struct i915_page_directory *pd;
+ const uint64_t orig_start = start;
+ const uint64_t orig_length = length;
+ uint64_t temp;
+ uint32_t pdpe;
+ int ret;
+
+#ifndef CONFIG_64BIT
+ /* Disallow 64b address on 32b platforms. Nothing is wrong with doing
+ * this in hardware, but a lot of the drm code is not prepared to handle
+ * 64b offset on 32b platforms.
+ * This will be addressed when 48b PPGTT is added */
+ if (start + length > 0x100000000ULL)
+ return -E2BIG;
+#endif
+
+ /* Wrap is never okay since we can only represent 48b, and we don't
+ * actually use the other side of the canonical address space.
+ */
+ if (WARN_ON(start + length < start))
+ return -ERANGE;
+
+ ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables);
+ if (ret)
+ return ret;
+
+ /* Do the allocations first so we can easily bail out */
+ ret = gen8_ppgtt_alloc_page_directories(ppgtt, &ppgtt->pdp, start, length,
+ new_page_dirs);
+ if (ret) {
+ free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
+ return ret;
+ }
+
+ /* For every page directory referenced, allocate page tables */
+ gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+ ret = gen8_ppgtt_alloc_pagetabs(ppgtt, pd, start, length,
+ new_page_tables[pdpe]);
+ if (ret)
+ goto err_out;
+ }
+
+ start = orig_start;
+ length = orig_length;
+
+ /* 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);
+ struct i915_page_table *pt;
+ uint64_t pd_len = gen8_clamp_pd(start, length);
+ uint64_t pd_start = start;
+ uint32_t pde;
+
+ /* Every pd should be allocated, we just did that above. */
+ WARN_ON(!pd);
+
+ gen8_for_each_pde(pt, pd, pd_start, pd_len, temp, pde) {
+ /* Same reasoning as pd */
+ WARN_ON(!pt);
+ WARN_ON(!pd_len);
+ WARN_ON(!gen8_pte_count(pd_start, pd_len));
+
+ /* Set our used ptes within the page table */
+ bitmap_set(pt->used_ptes,
+ gen8_pte_index(pd_start),
+ gen8_pte_count(pd_start, pd_len));
+
+ /* Our pde is now pointing to the pagetable, pt */
+ set_bit(pde, pd->used_pdes);
+
+ /* Map the PDE to the page table */
+ __gen8_do_map_pt(page_directory + pde, pt, vm->dev);
+
+ /* 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_atomic(page_directory);
+
+ set_bit(pdpe, ppgtt->pdp.used_pdpes);
+ }
+
+ free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
+ 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);
+ }
+
+ for_each_set_bit(pdpe, new_page_dirs, GEN8_LEGACY_PDPES)
+ unmap_and_free_pd(ppgtt->pdp.page_directory[pdpe], vm->dev);
+
+ free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
return ret;
}
-static int gen8_ppgtt_setup_page_directories(struct i915_hw_ppgtt *ppgtt,
- const int pd)
-{
- dma_addr_t pd_addr;
- int ret;
-
- pd_addr = pci_map_page(ppgtt->base.dev->pdev,
- ppgtt->pdp.page_directory[pd]->page, 0,
- PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-
- ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pd_addr);
- if (ret)
- return ret;
-
- ppgtt->pdp.page_directory[pd]->daddr = pd_addr;
-
- return 0;
-}
-
-static int gen8_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt,
- const int pd,
- const int pt)
-{
- dma_addr_t pt_addr;
- struct i915_page_directory_entry *pdir = ppgtt->pdp.page_directory[pd];
- struct i915_page_table_entry *ptab = pdir->page_table[pt];
- struct page *p = ptab->page;
- int ret;
-
- pt_addr = pci_map_page(ppgtt->base.dev->pdev,
- p, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
- ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pt_addr);
- if (ret)
- return ret;
-
- ptab->daddr = pt_addr;
-
- return 0;
-}
-
/*
* GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
* with a net effect resembling a 2-level page table in normal x86 terms. Each
* PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
* space.
*
- * FIXME: split allocation into smaller pieces. For now we only ever do this
- * once, but with full PPGTT, the multiple contiguous allocations will be bad.
- * TODO: Do something with the size parameter
*/
-static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
+static int gen8_ppgtt_init_common(struct i915_hw_ppgtt *ppgtt, uint64_t size)
{
- const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
- const int min_pt_pages = I915_PDES * max_pdp;
- int i, j, ret;
+ ppgtt->scratch_pt = alloc_pt_single(ppgtt->base.dev);
+ if (IS_ERR(ppgtt->scratch_pt))
+ return PTR_ERR(ppgtt->scratch_pt);
- if (size % (1<<30))
- DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
+ ppgtt->scratch_pd = alloc_pd_single(ppgtt->base.dev);
+ if (IS_ERR(ppgtt->scratch_pd))
+ return PTR_ERR(ppgtt->scratch_pd);
- /* 1. Do all our allocations for page directories and page tables.
- * We allocate more than was asked so that we can point the unused parts
- * to valid entries that point to scratch page. Dynamic page tables
- * will fix this eventually.
- */
- ret = gen8_ppgtt_alloc(ppgtt, GEN8_LEGACY_PDPES);
+ gen8_initialize_pt(&ppgtt->base, ppgtt->scratch_pt);
+ gen8_initialize_pd(&ppgtt->base, ppgtt->scratch_pd);
+
+ ppgtt->base.start = 0;
+ ppgtt->base.total = size;
+ ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+ ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
+
+ ppgtt->switch_mm = gen8_mm_switch;
+
+ return 0;
+}
+
+static int gen8_aliasing_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+{
+ struct drm_device *dev = ppgtt->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint64_t start = 0, size = dev_priv->gtt.base.total;
+ int ret;
+
+ ret = gen8_ppgtt_init_common(ppgtt, dev_priv->gtt.base.total);
if (ret)
return ret;
- /*
- * 2. Create DMA mappings for the page directories and page tables.
- */
- for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
- ret = gen8_ppgtt_setup_page_directories(ppgtt, i);
- if (ret)
- goto bail;
-
- for (j = 0; j < I915_PDES; j++) {
- ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
- if (ret)
- goto bail;
- }
+ /* Aliasing PPGTT has to always work and be mapped because of the way we
+ * use RESTORE_INHIBIT in the context switch. This will be fixed
+ * eventually. */
+ ret = gen8_alloc_va_range(&ppgtt->base, start, size);
+ if (ret) {
+ unmap_and_free_pd(ppgtt->scratch_pd, ppgtt->base.dev);
+ unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
+ return ret;
}
- /*
- * 3. Map all the page directory entires to point to the page tables
- * we've allocated.
- *
- * For now, the PPGTT helper functions all require that the PDEs are
- * plugged in correctly. So we do that now/here. For aliasing PPGTT, we
- * will never need to touch the PDEs again.
- */
- for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
- struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
- gen8_pde_t *pd_vaddr;
- pd_vaddr = kmap_atomic(ppgtt->pdp.page_directory[i]->page);
- for (j = 0; j < I915_PDES; j++) {
- struct i915_page_table_entry *pt = pd->page_table[j];
- dma_addr_t addr = pt->daddr;
- pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr,
- I915_CACHE_LLC);
- }
- if (!HAS_LLC(ppgtt->base.dev))
- drm_clflush_virt_range(pd_vaddr, PAGE_SIZE);
- kunmap_atomic(pd_vaddr);
- }
-
- ppgtt->switch_mm = gen8_mm_switch;
+ ppgtt->base.allocate_va_range = NULL;
ppgtt->base.clear_range = gen8_ppgtt_clear_range;
- ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
- ppgtt->base.cleanup = gen8_ppgtt_cleanup;
- ppgtt->base.start = 0;
+ ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
- /* This is the area that we advertise as usable for the caller */
- ppgtt->base.total = max_pdp * I915_PDES * GEN8_PTES * PAGE_SIZE;
-
- /* Set all ptes to a valid scratch page. Also above requested space */
- ppgtt->base.clear_range(&ppgtt->base, 0,
- ppgtt->num_pd_pages * GEN8_PTES * PAGE_SIZE,
- true);
-
- DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n",
- ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp);
- DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n",
- ppgtt->num_pd_entries,
- (ppgtt->num_pd_entries - min_pt_pages) + size % (1<<30));
return 0;
+}
-bail:
- gen8_ppgtt_unmap_pages(ppgtt);
- gen8_ppgtt_free(ppgtt);
- return ret;
+static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+{
+ int ret;
+
+ ret = gen8_ppgtt_init_common(ppgtt, (1ULL << 32));
+ if (ret)
+ return ret;
+
+ ppgtt->base.allocate_va_range = gen8_alloc_va_range;
+ ppgtt->base.clear_range = gen8_ppgtt_clear_range;
+
+ return 0;
}
static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
{
- struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
struct i915_address_space *vm = &ppgtt->base;
- gen6_pte_t __iomem *pd_addr;
+ struct i915_page_table *unused;
gen6_pte_t scratch_pte;
uint32_t pd_entry;
- int pte, pde;
+ 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);
- pd_addr = (gen6_pte_t __iomem *)dev_priv->gtt.gsm +
- ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
-
- seq_printf(m, " VM %p (pd_offset %x-%x):\n", vm,
- ppgtt->pd.pd_offset,
- ppgtt->pd.pd_offset + ppgtt->num_pd_entries);
- for (pde = 0; pde < ppgtt->num_pd_entries; pde++) {
+ 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;
- pd_entry = readl(pd_addr + pde);
+ pd_entry = readl(ppgtt->pd_addr + pde);
expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
if (pd_entry != expected)
@@ -914,8 +1094,8 @@
}
/* Write pde (index) from the page directory @pd to the page table @pt */
-static void gen6_write_pde(struct i915_page_directory_entry *pd,
- const int pde, struct i915_page_table_entry *pt)
+static void gen6_write_pde(struct i915_page_directory *pd,
+ const int pde, struct i915_page_table *pt)
{
/* Caller needs to make sure the write completes if necessary */
struct i915_hw_ppgtt *ppgtt =
@@ -931,10 +1111,10 @@
/* Write all the page tables found in the ppgtt structure to incrementing page
* directories. */
static void gen6_write_page_range(struct drm_i915_private *dev_priv,
- struct i915_page_directory_entry *pd,
+ struct i915_page_directory *pd,
uint32_t start, uint32_t length)
{
- struct i915_page_table_entry *pt;
+ struct i915_page_table *pt;
uint32_t pde, temp;
gen6_for_each_pde(pt, pd, start, length, temp, pde)
@@ -1169,7 +1349,7 @@
}
static void gen6_initialize_pt(struct i915_address_space *vm,
- struct i915_page_table_entry *pt)
+ struct i915_page_table *pt)
{
gen6_pte_t *pt_vaddr, scratch_pte;
int i;
@@ -1195,7 +1375,7 @@
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
- struct i915_page_table_entry *pt;
+ struct i915_page_table *pt;
const uint32_t start_save = start, length_save = length;
uint32_t pde, temp;
int ret;
@@ -1263,7 +1443,7 @@
unwind_out:
for_each_set_bit(pde, new_page_tables, I915_PDES) {
- struct i915_page_table_entry *pt = ppgtt->pd.page_table[pde];
+ 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);
@@ -1275,17 +1455,16 @@
static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
{
- int i;
+ struct i915_page_table *pt;
+ uint32_t pde;
- for (i = 0; i < ppgtt->num_pd_entries; i++) {
- struct i915_page_table_entry *pt = ppgtt->pd.page_table[i];
-
+ gen6_for_all_pdes(pt, ppgtt, pde) {
if (pt != ppgtt->scratch_pt)
- unmap_and_free_pt(ppgtt->pd.page_table[i], ppgtt->base.dev);
+ unmap_and_free_pt(pt, ppgtt->base.dev);
}
unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
- unmap_and_free_pd(&ppgtt->pd);
+ unmap_and_free_pd(&ppgtt->pd, ppgtt->base.dev);
}
static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
@@ -1342,7 +1521,6 @@
if (ppgtt->node.start < dev_priv->gtt.mappable_end)
DRM_DEBUG("Forced to use aperture for PDEs\n");
- ppgtt->num_pd_entries = I915_PDES;
return 0;
err_out:
@@ -1358,7 +1536,7 @@
static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
uint64_t start, uint64_t length)
{
- struct i915_page_table_entry *unused;
+ struct i915_page_table *unused;
uint32_t pde, temp;
gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde)
@@ -1390,7 +1568,7 @@
if (aliasing) {
/* preallocate all pts */
- ret = alloc_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries,
+ ret = alloc_pt_range(&ppgtt->pd, 0, I915_PDES,
ppgtt->base.dev);
if (ret) {
@@ -1399,12 +1577,12 @@
}
}
- ppgtt->base.allocate_va_range = gen6_alloc_va_range;
+ ppgtt->base.allocate_va_range = aliasing ? NULL : gen6_alloc_va_range;
ppgtt->base.clear_range = gen6_ppgtt_clear_range;
ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
ppgtt->base.cleanup = gen6_ppgtt_cleanup;
ppgtt->base.start = 0;
- ppgtt->base.total = ppgtt->num_pd_entries * GEN6_PTES * PAGE_SIZE;
+ ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
ppgtt->debug_dump = gen6_dump_ppgtt;
ppgtt->pd.pd_offset =
@@ -1440,8 +1618,10 @@
if (INTEL_INFO(dev)->gen < 8)
return gen6_ppgtt_init(ppgtt, aliasing);
+ else if (aliasing)
+ return gen8_aliasing_ppgtt_init(ppgtt);
else
- return gen8_ppgtt_init(ppgtt, dev_priv->gtt.base.total);
+ return gen8_ppgtt_init(ppgtt);
}
int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
{
@@ -2542,7 +2722,8 @@
if (WARN_ON(i915_is_ggtt(vm) != !!ggtt_view))
return ERR_PTR(-EINVAL);
- vma = kzalloc(sizeof(*vma), GFP_KERNEL);
+
+ vma = kmem_cache_zalloc(to_i915(obj->base.dev)->vmas, GFP_KERNEL);
if (vma == NULL)
return ERR_PTR(-ENOMEM);
@@ -2756,8 +2937,22 @@
int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
u32 flags)
{
+ int ret;
+
+ if (vma->vm->allocate_va_range) {
+ trace_i915_va_alloc(vma->vm, vma->node.start,
+ vma->node.size,
+ VM_TO_TRACE_NAME(vma->vm));
+
+ ret = vma->vm->allocate_va_range(vma->vm,
+ vma->node.start,
+ vma->node.size);
+ if (ret)
+ return ret;
+ }
+
if (i915_is_ggtt(vma->vm)) {
- int ret = i915_get_ggtt_vma_pages(vma);
+ ret = i915_get_ggtt_vma_pages(vma);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index fc03c99..29de64d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -206,26 +206,28 @@
u32 flags);
};
-struct i915_page_table_entry {
+struct i915_page_table {
struct page *page;
dma_addr_t daddr;
unsigned long *used_ptes;
};
-struct i915_page_directory_entry {
+struct i915_page_directory {
struct page *page; /* NULL for GEN6-GEN7 */
union {
uint32_t pd_offset;
dma_addr_t daddr;
};
- struct i915_page_table_entry *page_table[I915_PDES]; /* PDEs */
+ unsigned long *used_pdes;
+ struct i915_page_table *page_table[I915_PDES]; /* PDEs */
};
-struct i915_page_directory_pointer_entry {
+struct i915_page_directory_pointer {
/* struct page *page; */
- struct i915_page_directory_entry *page_directory[GEN8_LEGACY_PDPES];
+ DECLARE_BITMAP(used_pdpes, GEN8_LEGACY_PDPES);
+ struct i915_page_directory *page_directory[GEN8_LEGACY_PDPES];
};
struct i915_address_space {
@@ -314,14 +316,13 @@
struct kref ref;
struct drm_mm_node node;
unsigned long pd_dirty_rings;
- unsigned num_pd_entries;
- unsigned num_pd_pages; /* gen8+ */
union {
- struct i915_page_directory_pointer_entry pdp;
- struct i915_page_directory_entry pd;
+ struct i915_page_directory_pointer pdp;
+ struct i915_page_directory pd;
};
- struct i915_page_table_entry *scratch_pt;
+ struct i915_page_table *scratch_pt;
+ struct i915_page_directory *scratch_pd;
struct drm_i915_file_private *file_priv;
@@ -349,6 +350,11 @@
temp = min_t(unsigned, temp, length), \
start += temp, length -= temp)
+#define gen6_for_all_pdes(pt, ppgtt, iter) \
+ for (iter = 0; \
+ pt = ppgtt->pd.page_table[iter], iter < I915_PDES; \
+ iter++)
+
static inline uint32_t i915_pte_index(uint64_t address, uint32_t pde_shift)
{
const uint32_t mask = NUM_PTE(pde_shift) - 1;
@@ -397,6 +403,63 @@
return i915_pde_index(addr, GEN6_PDE_SHIFT);
}
+/* Equivalent to the gen6 version, For each pde iterates over every pde
+ * between from start until start + length. On gen8+ it simply iterates
+ * over every page directory entry in a page directory.
+ */
+#define gen8_for_each_pde(pt, pd, start, length, temp, iter) \
+ for (iter = gen8_pde_index(start); \
+ pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES; \
+ iter++, \
+ temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT) - start, \
+ temp = min(temp, length), \
+ start += temp, length -= temp)
+
+#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \
+ for (iter = gen8_pdpe_index(start); \
+ pd = (pdp)->page_directory[iter], length > 0 && iter < GEN8_LEGACY_PDPES; \
+ iter++, \
+ temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start, \
+ temp = min(temp, length), \
+ start += temp, length -= temp)
+
+/* Clamp length to the next page_directory boundary */
+static inline uint64_t gen8_clamp_pd(uint64_t start, uint64_t length)
+{
+ uint64_t next_pd = ALIGN(start + 1, 1 << GEN8_PDPE_SHIFT);
+
+ if (next_pd > (start + length))
+ return length;
+
+ return next_pd - start;
+}
+
+static inline uint32_t gen8_pte_index(uint64_t address)
+{
+ return i915_pte_index(address, GEN8_PDE_SHIFT);
+}
+
+static inline uint32_t gen8_pde_index(uint64_t address)
+{
+ return i915_pde_index(address, GEN8_PDE_SHIFT);
+}
+
+static inline uint32_t gen8_pdpe_index(uint64_t address)
+{
+ return (address >> GEN8_PDPE_SHIFT) & GEN8_PDPE_MASK;
+}
+
+static inline uint32_t gen8_pml4e_index(uint64_t address)
+{
+ WARN_ON(1); /* For 64B */
+ return 0;
+}
+
+static inline size_t gen8_pte_count(uint64_t address, uint64_t length)
+{
+ return i915_pte_count(address, length, GEN8_PDE_SHIFT);
+}
+
int i915_gem_gtt_init(struct drm_device *dev);
void i915_gem_init_global_gtt(struct drm_device *dev);
void i915_global_gtt_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index f7929e7..f6ecbda 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -184,9 +184,12 @@
struct i915_vma *vma;
int count = 0;
- list_for_each_entry(vma, &obj->vma_list, vma_link)
+ list_for_each_entry(vma, &obj->vma_list, vma_link) {
if (drm_mm_node_allocated(&vma->node))
count++;
+ if (vma->pin_count)
+ count++;
+ }
return count;
}
@@ -210,8 +213,7 @@
count += obj->base.size >> PAGE_SHIFT;
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
- if (!i915_gem_obj_is_pinned(obj) &&
- obj->pages_pin_count == num_vma_bound(obj))
+ if (obj->pages_pin_count == num_vma_bound(obj))
count += obj->base.size >> PAGE_SHIFT;
}
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 1d4e60d..ac22614 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -251,10 +251,11 @@
return;
err_printf(m, "%s command stream:\n", ring_str(ring_idx));
- err_printf(m, " HEAD: 0x%08x\n", ring->head);
- err_printf(m, " TAIL: 0x%08x\n", ring->tail);
- err_printf(m, " CTL: 0x%08x\n", ring->ctl);
- err_printf(m, " HWS: 0x%08x\n", ring->hws);
+ err_printf(m, " START: 0x%08x\n", ring->start);
+ err_printf(m, " HEAD: 0x%08x\n", ring->head);
+ err_printf(m, " TAIL: 0x%08x\n", ring->tail);
+ err_printf(m, " CTL: 0x%08x\n", ring->ctl);
+ err_printf(m, " HWS: 0x%08x\n", ring->hws);
err_printf(m, " ACTHD: 0x%08x %08x\n", (u32)(ring->acthd>>32), (u32)ring->acthd);
err_printf(m, " IPEIR: 0x%08x\n", ring->ipeir);
err_printf(m, " IPEHR: 0x%08x\n", ring->ipehr);
@@ -883,6 +884,7 @@
ering->instpm = I915_READ(RING_INSTPM(ring->mmio_base));
ering->seqno = ring->get_seqno(ring, false);
ering->acthd = intel_ring_get_active_head(ring);
+ ering->start = I915_READ_START(ring);
ering->head = I915_READ_HEAD(ring);
ering->tail = I915_READ_TAIL(ring);
ering->ctl = I915_READ_CTL(ring);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 14ecb4d..46bcbff 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -985,8 +985,7 @@
return;
}
-static void notify_ring(struct drm_device *dev,
- struct intel_engine_cs *ring)
+static void notify_ring(struct intel_engine_cs *ring)
{
if (!intel_ring_initialized(ring))
return;
@@ -1049,7 +1048,7 @@
if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) {
if (!vlv_c0_above(dev_priv,
&dev_priv->rps.down_ei, &now,
- VLV_RP_DOWN_EI_THRESHOLD))
+ dev_priv->rps.down_threshold))
events |= GEN6_PM_RP_DOWN_THRESHOLD;
dev_priv->rps.down_ei = now;
}
@@ -1057,7 +1056,7 @@
if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
if (vlv_c0_above(dev_priv,
&dev_priv->rps.up_ei, &now,
- VLV_RP_UP_EI_THRESHOLD))
+ dev_priv->rps.up_threshold))
events |= GEN6_PM_RP_UP_THRESHOLD;
dev_priv->rps.up_ei = now;
}
@@ -1095,21 +1094,20 @@
pm_iir |= vlv_wa_c0_ei(dev_priv, pm_iir);
adj = dev_priv->rps.last_adj;
+ new_delay = dev_priv->rps.cur_freq;
if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
if (adj > 0)
adj *= 2;
- else {
- /* CHV needs even encode values */
- adj = IS_CHERRYVIEW(dev_priv->dev) ? 2 : 1;
- }
- new_delay = dev_priv->rps.cur_freq + adj;
-
+ else /* CHV needs even encode values */
+ adj = IS_CHERRYVIEW(dev_priv) ? 2 : 1;
/*
* For better performance, jump directly
* to RPe if we're below it.
*/
- if (new_delay < dev_priv->rps.efficient_freq)
+ if (new_delay < dev_priv->rps.efficient_freq - adj) {
new_delay = dev_priv->rps.efficient_freq;
+ adj = 0;
+ }
} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
if (dev_priv->rps.cur_freq > dev_priv->rps.efficient_freq)
new_delay = dev_priv->rps.efficient_freq;
@@ -1119,24 +1117,22 @@
} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
if (adj < 0)
adj *= 2;
- else {
- /* CHV needs even encode values */
- adj = IS_CHERRYVIEW(dev_priv->dev) ? -2 : -1;
- }
- new_delay = dev_priv->rps.cur_freq + adj;
+ else /* CHV needs even encode values */
+ adj = IS_CHERRYVIEW(dev_priv) ? -2 : -1;
} else { /* unknown event */
- new_delay = dev_priv->rps.cur_freq;
+ adj = 0;
}
+ dev_priv->rps.last_adj = adj;
+
/* sysfs frequency interfaces may have snuck in while servicing the
* interrupt
*/
+ new_delay += adj;
new_delay = clamp_t(int, new_delay,
dev_priv->rps.min_freq_softlimit,
dev_priv->rps.max_freq_softlimit);
- dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_freq;
-
intel_set_rps(dev_priv->dev, new_delay);
mutex_unlock(&dev_priv->rps.hw_lock);
@@ -1251,9 +1247,9 @@
{
if (gt_iir &
(GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
- notify_ring(dev, &dev_priv->ring[RCS]);
+ notify_ring(&dev_priv->ring[RCS]);
if (gt_iir & ILK_BSD_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[VCS]);
+ notify_ring(&dev_priv->ring[VCS]);
}
static void snb_gt_irq_handler(struct drm_device *dev,
@@ -1263,11 +1259,11 @@
if (gt_iir &
(GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
- notify_ring(dev, &dev_priv->ring[RCS]);
+ notify_ring(&dev_priv->ring[RCS]);
if (gt_iir & GT_BSD_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[VCS]);
+ notify_ring(&dev_priv->ring[VCS]);
if (gt_iir & GT_BLT_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[BCS]);
+ notify_ring(&dev_priv->ring[BCS]);
if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
GT_BSD_CS_ERROR_INTERRUPT |
@@ -1278,88 +1274,74 @@
ivybridge_parity_error_irq_handler(dev, gt_iir);
}
-static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
- struct drm_i915_private *dev_priv,
+static irqreturn_t gen8_gt_irq_handler(struct drm_i915_private *dev_priv,
u32 master_ctl)
{
- struct intel_engine_cs *ring;
- u32 rcs, bcs, vcs;
- uint32_t tmp = 0;
irqreturn_t ret = IRQ_NONE;
if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) {
- tmp = I915_READ(GEN8_GT_IIR(0));
+ u32 tmp = I915_READ_FW(GEN8_GT_IIR(0));
if (tmp) {
- I915_WRITE(GEN8_GT_IIR(0), tmp);
+ I915_WRITE_FW(GEN8_GT_IIR(0), tmp);
ret = IRQ_HANDLED;
- rcs = tmp >> GEN8_RCS_IRQ_SHIFT;
- ring = &dev_priv->ring[RCS];
- if (rcs & GT_RENDER_USER_INTERRUPT)
- notify_ring(dev, ring);
- if (rcs & GT_CONTEXT_SWITCH_INTERRUPT)
- intel_lrc_irq_handler(ring);
+ if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT))
+ intel_lrc_irq_handler(&dev_priv->ring[RCS]);
+ if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT))
+ notify_ring(&dev_priv->ring[RCS]);
- bcs = tmp >> GEN8_BCS_IRQ_SHIFT;
- ring = &dev_priv->ring[BCS];
- if (bcs & GT_RENDER_USER_INTERRUPT)
- notify_ring(dev, ring);
- if (bcs & GT_CONTEXT_SWITCH_INTERRUPT)
- intel_lrc_irq_handler(ring);
+ if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT))
+ intel_lrc_irq_handler(&dev_priv->ring[BCS]);
+ if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT))
+ notify_ring(&dev_priv->ring[BCS]);
} else
DRM_ERROR("The master control interrupt lied (GT0)!\n");
}
if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
- tmp = I915_READ(GEN8_GT_IIR(1));
+ u32 tmp = I915_READ_FW(GEN8_GT_IIR(1));
if (tmp) {
- I915_WRITE(GEN8_GT_IIR(1), tmp);
+ I915_WRITE_FW(GEN8_GT_IIR(1), tmp);
ret = IRQ_HANDLED;
- vcs = tmp >> GEN8_VCS1_IRQ_SHIFT;
- ring = &dev_priv->ring[VCS];
- if (vcs & GT_RENDER_USER_INTERRUPT)
- notify_ring(dev, ring);
- if (vcs & GT_CONTEXT_SWITCH_INTERRUPT)
- intel_lrc_irq_handler(ring);
+ if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT))
+ intel_lrc_irq_handler(&dev_priv->ring[VCS]);
+ if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT))
+ notify_ring(&dev_priv->ring[VCS]);
- vcs = tmp >> GEN8_VCS2_IRQ_SHIFT;
- ring = &dev_priv->ring[VCS2];
- if (vcs & GT_RENDER_USER_INTERRUPT)
- notify_ring(dev, ring);
- if (vcs & GT_CONTEXT_SWITCH_INTERRUPT)
- intel_lrc_irq_handler(ring);
+ if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT))
+ intel_lrc_irq_handler(&dev_priv->ring[VCS2]);
+ if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT))
+ notify_ring(&dev_priv->ring[VCS2]);
} else
DRM_ERROR("The master control interrupt lied (GT1)!\n");
}
+ if (master_ctl & GEN8_GT_VECS_IRQ) {
+ u32 tmp = I915_READ_FW(GEN8_GT_IIR(3));
+ if (tmp) {
+ I915_WRITE_FW(GEN8_GT_IIR(3), tmp);
+ ret = IRQ_HANDLED;
+
+ if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT))
+ intel_lrc_irq_handler(&dev_priv->ring[VECS]);
+ if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT))
+ notify_ring(&dev_priv->ring[VECS]);
+ } else
+ DRM_ERROR("The master control interrupt lied (GT3)!\n");
+ }
+
if (master_ctl & GEN8_GT_PM_IRQ) {
- tmp = I915_READ(GEN8_GT_IIR(2));
+ u32 tmp = I915_READ_FW(GEN8_GT_IIR(2));
if (tmp & dev_priv->pm_rps_events) {
- I915_WRITE(GEN8_GT_IIR(2),
- tmp & dev_priv->pm_rps_events);
+ I915_WRITE_FW(GEN8_GT_IIR(2),
+ tmp & dev_priv->pm_rps_events);
ret = IRQ_HANDLED;
gen6_rps_irq_handler(dev_priv, tmp);
} else
DRM_ERROR("The master control interrupt lied (PM)!\n");
}
- if (master_ctl & GEN8_GT_VECS_IRQ) {
- tmp = I915_READ(GEN8_GT_IIR(3));
- if (tmp) {
- I915_WRITE(GEN8_GT_IIR(3), tmp);
- ret = IRQ_HANDLED;
-
- vcs = tmp >> GEN8_VECS_IRQ_SHIFT;
- ring = &dev_priv->ring[VECS];
- if (vcs & GT_RENDER_USER_INTERRUPT)
- notify_ring(dev, ring);
- if (vcs & GT_CONTEXT_SWITCH_INTERRUPT)
- intel_lrc_irq_handler(ring);
- } else
- DRM_ERROR("The master control interrupt lied (GT3)!\n");
- }
-
return ret;
}
@@ -1654,7 +1636,7 @@
if (HAS_VEBOX(dev_priv->dev)) {
if (pm_iir & PM_VEBOX_USER_INTERRUPT)
- notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
+ notify_ring(&dev_priv->ring[VECS]);
if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
@@ -1848,7 +1830,7 @@
I915_WRITE(VLV_IIR, iir);
}
- gen8_gt_irq_handler(dev, dev_priv, master_ctl);
+ gen8_gt_irq_handler(dev_priv, master_ctl);
/* Call regardless, as some status bits might not be
* signalled in iir */
@@ -2181,17 +2163,16 @@
aux_mask |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
GEN9_AUX_CHANNEL_D;
- master_ctl = I915_READ(GEN8_MASTER_IRQ);
+ master_ctl = I915_READ_FW(GEN8_MASTER_IRQ);
master_ctl &= ~GEN8_MASTER_IRQ_CONTROL;
if (!master_ctl)
return IRQ_NONE;
- I915_WRITE(GEN8_MASTER_IRQ, 0);
- POSTING_READ(GEN8_MASTER_IRQ);
+ I915_WRITE_FW(GEN8_MASTER_IRQ, 0);
/* Find, clear, then process each source of interrupt */
- ret = gen8_gt_irq_handler(dev, dev_priv, master_ctl);
+ ret = gen8_gt_irq_handler(dev_priv, master_ctl);
if (master_ctl & GEN8_DE_MISC_IRQ) {
tmp = I915_READ(GEN8_DE_MISC_IIR);
@@ -2284,8 +2265,8 @@
}
- I915_WRITE(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
- POSTING_READ(GEN8_MASTER_IRQ);
+ I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
+ POSTING_READ_FW(GEN8_MASTER_IRQ);
return ret;
}
@@ -3696,7 +3677,7 @@
new_iir = I915_READ16(IIR); /* Flush posted writes */
if (iir & I915_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[RCS]);
+ notify_ring(&dev_priv->ring[RCS]);
for_each_pipe(dev_priv, pipe) {
int plane = pipe;
@@ -3887,7 +3868,7 @@
new_iir = I915_READ(IIR); /* Flush posted writes */
if (iir & I915_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[RCS]);
+ notify_ring(&dev_priv->ring[RCS]);
for_each_pipe(dev_priv, pipe) {
int plane = pipe;
@@ -4114,9 +4095,9 @@
new_iir = I915_READ(IIR); /* Flush posted writes */
if (iir & I915_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[RCS]);
+ notify_ring(&dev_priv->ring[RCS]);
if (iir & I915_BSD_USER_INTERRUPT)
- notify_ring(dev, &dev_priv->ring[VCS]);
+ notify_ring(&dev_priv->ring[VCS]);
for_each_pipe(dev_priv, pipe) {
if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS &&
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 21e69ca..87d9c0f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -671,8 +671,6 @@
#define FB_FMAX_VMIN_FREQ_LO_MASK 0xf8000000
#define VLV_CZ_CLOCK_TO_MILLI_SEC 100000
-#define VLV_RP_UP_EI_THRESHOLD 90
-#define VLV_RP_DOWN_EI_THRESHOLD 70
/* vlv2 north clock has */
#define CCK_FUSE_REG 0x8
@@ -1787,16 +1785,16 @@
#define GMBUS_RATE_400KHZ (2<<8) /* reserved on Pineview */
#define GMBUS_RATE_1MHZ (3<<8) /* reserved on Pineview */
#define GMBUS_HOLD_EXT (1<<7) /* 300ns hold time, rsvd on Pineview */
-#define GMBUS_PORT_DISABLED 0
-#define GMBUS_PORT_SSC 1
-#define GMBUS_PORT_VGADDC 2
-#define GMBUS_PORT_PANEL 3
-#define GMBUS_PORT_DPD_CHV 3 /* HDMID_CHV */
-#define GMBUS_PORT_DPC 4 /* HDMIC */
-#define GMBUS_PORT_DPB 5 /* SDVO, HDMIB */
-#define GMBUS_PORT_DPD 6 /* HDMID */
-#define GMBUS_PORT_RESERVED 7 /* 7 reserved */
-#define GMBUS_NUM_PORTS (GMBUS_PORT_DPD - GMBUS_PORT_SSC + 1)
+#define GMBUS_PIN_DISABLED 0
+#define GMBUS_PIN_SSC 1
+#define GMBUS_PIN_VGADDC 2
+#define GMBUS_PIN_PANEL 3
+#define GMBUS_PIN_DPD_CHV 3 /* HDMID_CHV */
+#define GMBUS_PIN_DPC 4 /* HDMIC */
+#define GMBUS_PIN_DPB 5 /* SDVO, HDMIB */
+#define GMBUS_PIN_DPD 6 /* HDMID */
+#define GMBUS_PIN_RESERVED 7 /* 7 reserved */
+#define GMBUS_NUM_PINS 7 /* including 0 */
#define GMBUS1 0x5104 /* command/status */
#define GMBUS_SW_CLR_INT (1<<31)
#define GMBUS_SW_RDY (1<<30)
@@ -2747,6 +2745,20 @@
#define EDP_PSR_DEBUG_MASK_MEMUP (1<<26)
#define EDP_PSR_DEBUG_MASK_HPD (1<<25)
+#define EDP_PSR2_CTL 0x6f900
+#define EDP_PSR2_ENABLE (1<<31)
+#define EDP_SU_TRACK_ENABLE (1<<30)
+#define EDP_MAX_SU_DISABLE_TIME(t) ((t)<<20)
+#define EDP_MAX_SU_DISABLE_TIME_MASK (0x1f<<20)
+#define EDP_PSR2_TP2_TIME_500 (0<<8)
+#define EDP_PSR2_TP2_TIME_100 (1<<8)
+#define EDP_PSR2_TP2_TIME_2500 (2<<8)
+#define EDP_PSR2_TP2_TIME_50 (3<<8)
+#define EDP_PSR2_TP2_TIME_MASK (3<<8)
+#define EDP_PSR2_FRAME_BEFORE_SU_SHIFT 4
+#define EDP_PSR2_FRAME_BEFORE_SU_MASK (0xf<<4)
+#define EDP_PSR2_IDLE_MASK 0xf
+
/* VGA port control */
#define ADPA 0x61100
#define PCH_ADPA 0xe1100
@@ -4853,7 +4865,9 @@
#define PLANE_CTL_ALPHA_HW_PREMULTIPLY ( 3 << 4)
#define PLANE_CTL_ROTATE_MASK 0x3
#define PLANE_CTL_ROTATE_0 0x0
+#define PLANE_CTL_ROTATE_90 0x1
#define PLANE_CTL_ROTATE_180 0x2
+#define PLANE_CTL_ROTATE_270 0x3
#define _PLANE_STRIDE_1_A 0x70188
#define _PLANE_STRIDE_2_A 0x70288
#define _PLANE_STRIDE_3_A 0x70388
@@ -5095,6 +5109,121 @@
#define PS_WIN_SZ(pipe) _PIPE(pipe, _PSA_WIN_SZ, _PSB_WIN_SZ)
#define PS_WIN_POS(pipe) _PIPE(pipe, _PSA_WIN_POS, _PSB_WIN_POS)
+/*
+ * Skylake scalers
+ */
+#define _PS_1A_CTRL 0x68180
+#define _PS_2A_CTRL 0x68280
+#define _PS_1B_CTRL 0x68980
+#define _PS_2B_CTRL 0x68A80
+#define _PS_1C_CTRL 0x69180
+#define PS_SCALER_EN (1 << 31)
+#define PS_SCALER_MODE_MASK (3 << 28)
+#define PS_SCALER_MODE_DYN (0 << 28)
+#define PS_SCALER_MODE_HQ (1 << 28)
+#define PS_PLANE_SEL_MASK (7 << 25)
+#define PS_PLANE_SEL(plane) ((plane + 1) << 25)
+#define PS_FILTER_MASK (3 << 23)
+#define PS_FILTER_MEDIUM (0 << 23)
+#define PS_FILTER_EDGE_ENHANCE (2 << 23)
+#define PS_FILTER_BILINEAR (3 << 23)
+#define PS_VERT3TAP (1 << 21)
+#define PS_VERT_INT_INVERT_FIELD1 (0 << 20)
+#define PS_VERT_INT_INVERT_FIELD0 (1 << 20)
+#define PS_PWRUP_PROGRESS (1 << 17)
+#define PS_V_FILTER_BYPASS (1 << 8)
+#define PS_VADAPT_EN (1 << 7)
+#define PS_VADAPT_MODE_MASK (3 << 5)
+#define PS_VADAPT_MODE_LEAST_ADAPT (0 << 5)
+#define PS_VADAPT_MODE_MOD_ADAPT (1 << 5)
+#define PS_VADAPT_MODE_MOST_ADAPT (3 << 5)
+
+#define _PS_PWR_GATE_1A 0x68160
+#define _PS_PWR_GATE_2A 0x68260
+#define _PS_PWR_GATE_1B 0x68960
+#define _PS_PWR_GATE_2B 0x68A60
+#define _PS_PWR_GATE_1C 0x69160
+#define PS_PWR_GATE_DIS_OVERRIDE (1 << 31)
+#define PS_PWR_GATE_SETTLING_TIME_32 (0 << 3)
+#define PS_PWR_GATE_SETTLING_TIME_64 (1 << 3)
+#define PS_PWR_GATE_SETTLING_TIME_96 (2 << 3)
+#define PS_PWR_GATE_SETTLING_TIME_128 (3 << 3)
+#define PS_PWR_GATE_SLPEN_8 0
+#define PS_PWR_GATE_SLPEN_16 1
+#define PS_PWR_GATE_SLPEN_24 2
+#define PS_PWR_GATE_SLPEN_32 3
+
+#define _PS_WIN_POS_1A 0x68170
+#define _PS_WIN_POS_2A 0x68270
+#define _PS_WIN_POS_1B 0x68970
+#define _PS_WIN_POS_2B 0x68A70
+#define _PS_WIN_POS_1C 0x69170
+
+#define _PS_WIN_SZ_1A 0x68174
+#define _PS_WIN_SZ_2A 0x68274
+#define _PS_WIN_SZ_1B 0x68974
+#define _PS_WIN_SZ_2B 0x68A74
+#define _PS_WIN_SZ_1C 0x69174
+
+#define _PS_VSCALE_1A 0x68184
+#define _PS_VSCALE_2A 0x68284
+#define _PS_VSCALE_1B 0x68984
+#define _PS_VSCALE_2B 0x68A84
+#define _PS_VSCALE_1C 0x69184
+
+#define _PS_HSCALE_1A 0x68190
+#define _PS_HSCALE_2A 0x68290
+#define _PS_HSCALE_1B 0x68990
+#define _PS_HSCALE_2B 0x68A90
+#define _PS_HSCALE_1C 0x69190
+
+#define _PS_VPHASE_1A 0x68188
+#define _PS_VPHASE_2A 0x68288
+#define _PS_VPHASE_1B 0x68988
+#define _PS_VPHASE_2B 0x68A88
+#define _PS_VPHASE_1C 0x69188
+
+#define _PS_HPHASE_1A 0x68194
+#define _PS_HPHASE_2A 0x68294
+#define _PS_HPHASE_1B 0x68994
+#define _PS_HPHASE_2B 0x68A94
+#define _PS_HPHASE_1C 0x69194
+
+#define _PS_ECC_STAT_1A 0x681D0
+#define _PS_ECC_STAT_2A 0x682D0
+#define _PS_ECC_STAT_1B 0x689D0
+#define _PS_ECC_STAT_2B 0x68AD0
+#define _PS_ECC_STAT_1C 0x691D0
+
+#define _ID(id, a, b) ((a) + (id)*((b)-(a)))
+#define SKL_PS_CTRL(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_1A_CTRL, _PS_2A_CTRL), \
+ _ID(id, _PS_1B_CTRL, _PS_2B_CTRL))
+#define SKL_PS_PWR_GATE(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_PWR_GATE_1A, _PS_PWR_GATE_2A), \
+ _ID(id, _PS_PWR_GATE_1B, _PS_PWR_GATE_2B))
+#define SKL_PS_WIN_POS(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_WIN_POS_1A, _PS_WIN_POS_2A), \
+ _ID(id, _PS_WIN_POS_1B, _PS_WIN_POS_2B))
+#define SKL_PS_WIN_SZ(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_WIN_SZ_1A, _PS_WIN_SZ_2A), \
+ _ID(id, _PS_WIN_SZ_1B, _PS_WIN_SZ_2B))
+#define SKL_PS_VSCALE(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_VSCALE_1A, _PS_VSCALE_2A), \
+ _ID(id, _PS_VSCALE_1B, _PS_VSCALE_2B))
+#define SKL_PS_HSCALE(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_HSCALE_1A, _PS_HSCALE_2A), \
+ _ID(id, _PS_HSCALE_1B, _PS_HSCALE_2B))
+#define SKL_PS_VPHASE(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_VPHASE_1A, _PS_VPHASE_2A), \
+ _ID(id, _PS_VPHASE_1B, _PS_VPHASE_2B))
+#define SKL_PS_HPHASE(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_HPHASE_1A, _PS_HPHASE_2A), \
+ _ID(id, _PS_HPHASE_1B, _PS_HPHASE_2B))
+#define SKL_PS_ECC_STAT(pipe, id) _PIPE(pipe, \
+ _ID(id, _PS_ECC_STAT_1A, _PS_ECC_STAT_2A), \
+ _ID(id, _PS_ECC_STAT_1B, _PS_ECC_STAT_2B)
+
/* legacy palette */
#define _LGC_PALETTE_A 0x4a000
#define _LGC_PALETTE_B 0x4a800
@@ -5324,6 +5453,9 @@
#define GEN7_L3SQCREG1 0xB010
#define VLV_B0_WA_L3SQCREG1_VALUE 0x00D30000
+#define GEN8_L3SQCREG1 0xB100
+#define BDW_WA_L3SQCREG1_DEFAULT 0x784000
+
#define GEN7_L3CNTLREG1 0xB01C
#define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8C
#define GEN7_L3AGDIS (1<<19)
@@ -6091,6 +6223,7 @@
# define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7)
#define GEN6_UCGCTL2 0x9404
+# define GEN6_VFUNIT_CLOCK_GATE_DISABLE (1 << 31)
# define GEN7_VDSUNIT_CLOCK_GATE_DISABLE (1 << 30)
# define GEN7_TDLUNIT_CLOCK_GATE_DISABLE (1 << 22)
# define GEN6_RCZUNIT_CLOCK_GATE_DISABLE (1 << 13)
@@ -6189,6 +6322,8 @@
#define GEN9_MEDIA_PG_IDLE_HYSTERESIS 0xA0C4
#define GEN9_RENDER_PG_IDLE_HYSTERESIS 0xA0C8
#define GEN9_PG_ENABLE 0xA210
+#define GEN9_RENDER_PG_ENABLE (1<<0)
+#define GEN9_MEDIA_PG_ENABLE (1<<1)
#define VLV_CHICKEN_3 (VLV_DISPLAY_BASE + 0x7040C)
#define PIXEL_OVERLAP_CNT_MASK (3 << 30)
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index b3070a4..2aa140e 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -221,7 +221,7 @@
DECLARE_EVENT_CLASS(i915_page_table_entry_update,
TP_PROTO(struct i915_address_space *vm, u32 pde,
- struct i915_page_table_entry *pt, u32 first, u32 count, u32 bits),
+ struct i915_page_table *pt, u32 first, u32 count, u32 bits),
TP_ARGS(vm, pde, pt, first, count, bits),
TP_STRUCT__entry(
@@ -251,7 +251,7 @@
DEFINE_EVENT(i915_page_table_entry_update, i915_page_table_entry_map,
TP_PROTO(struct i915_address_space *vm, u32 pde,
- struct i915_page_table_entry *pt, u32 first, u32 count, u32 bits),
+ struct i915_page_table *pt, u32 first, u32 count, u32 bits),
TP_ARGS(vm, pde, pt, first, count, bits)
);
@@ -505,7 +505,6 @@
TP_STRUCT__entry(
__field(u32, dev)
__field(u32, ring)
- __field(u32, uniq)
__field(u32, seqno)
),
@@ -514,13 +513,11 @@
i915_gem_request_get_ring(req);
__entry->dev = ring->dev->primary->index;
__entry->ring = ring->id;
- __entry->uniq = req ? req->uniq : 0;
__entry->seqno = i915_gem_request_get_seqno(req);
),
- TP_printk("dev=%u, ring=%u, uniq=%u, seqno=%u",
- __entry->dev, __entry->ring, __entry->uniq,
- __entry->seqno)
+ TP_printk("dev=%u, ring=%u, seqno=%u",
+ __entry->dev, __entry->ring, __entry->seqno)
);
DEFINE_EVENT(i915_gem_request, i915_gem_request_add,
@@ -565,7 +562,6 @@
TP_STRUCT__entry(
__field(u32, dev)
__field(u32, ring)
- __field(u32, uniq)
__field(u32, seqno)
__field(bool, blocking)
),
@@ -581,14 +577,13 @@
i915_gem_request_get_ring(req);
__entry->dev = ring->dev->primary->index;
__entry->ring = ring->id;
- __entry->uniq = req ? req->uniq : 0;
__entry->seqno = i915_gem_request_get_seqno(req);
__entry->blocking =
mutex_is_locked(&ring->dev->struct_mutex);
),
- TP_printk("dev=%u, ring=%u, uniq=%u, seqno=%u, blocking=%s",
- __entry->dev, __entry->ring, __entry->uniq,
+ TP_printk("dev=%u, ring=%u, seqno=%u, blocking=%s",
+ __entry->dev, __entry->ring,
__entry->seqno, __entry->blocking ? "yes (NB)" : "no")
);
@@ -597,33 +592,6 @@
TP_ARGS(req)
);
-DECLARE_EVENT_CLASS(i915_ring,
- TP_PROTO(struct intel_engine_cs *ring),
- TP_ARGS(ring),
-
- TP_STRUCT__entry(
- __field(u32, dev)
- __field(u32, ring)
- ),
-
- TP_fast_assign(
- __entry->dev = ring->dev->primary->index;
- __entry->ring = ring->id;
- ),
-
- TP_printk("dev=%u, ring=%u", __entry->dev, __entry->ring)
-);
-
-DEFINE_EVENT(i915_ring, i915_ring_wait_begin,
- TP_PROTO(struct intel_engine_cs *ring),
- TP_ARGS(ring)
-);
-
-DEFINE_EVENT(i915_ring, i915_ring_wait_end,
- TP_PROTO(struct intel_engine_cs *ring),
- TP_ARGS(ring)
-);
-
TRACE_EVENT(i915_flip_request,
TP_PROTO(int plane, struct drm_i915_gem_object *obj),
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 3903b90..3c4b7cd 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -48,6 +48,8 @@
int ncrtcs = dev->mode_config.num_crtc;
int nconnectors = dev->mode_config.num_connector;
enum pipe nuclear_pipe = INVALID_PIPE;
+ struct intel_crtc *nuclear_crtc = NULL;
+ struct intel_crtc_state *crtc_state = NULL;
int ret;
int i;
bool not_nuclear = false;
@@ -76,8 +78,14 @@
state->allow_modeset = false;
for (i = 0; i < ncrtcs; i++) {
struct intel_crtc *crtc = to_intel_crtc(state->crtcs[i]);
+ if (crtc)
+ memset(&crtc->atomic, 0, sizeof(crtc->atomic));
if (crtc && crtc->pipe != nuclear_pipe)
not_nuclear = true;
+ if (crtc && crtc->pipe == nuclear_pipe) {
+ nuclear_crtc = crtc;
+ crtc_state = to_intel_crtc_state(state->crtc_states[i]);
+ }
}
for (i = 0; i < nconnectors; i++)
if (state->connectors[i] != NULL)
@@ -92,6 +100,11 @@
if (ret)
return ret;
+ /* FIXME: move to crtc atomic check function once it is ready */
+ ret = intel_atomic_setup_scalers(dev, nuclear_crtc, crtc_state);
+ if (ret)
+ return ret;
+
return ret;
}
@@ -155,6 +168,18 @@
swap(state->plane_states[i], plane->state);
plane->state->state = NULL;
}
+
+ /* swap crtc_state */
+ for (i = 0; i < dev->mode_config.num_crtc; i++) {
+ struct drm_crtc *crtc = state->crtcs[i];
+ if (!crtc) {
+ continue;
+ }
+
+ to_intel_crtc(crtc)->config->scaler_state =
+ to_intel_crtc_state(state->crtc_states[i])->scaler_state;
+ }
+
drm_atomic_helper_commit_planes(dev, state);
drm_atomic_helper_wait_for_vblanks(dev, state);
drm_atomic_helper_cleanup_planes(dev, state);
@@ -241,3 +266,151 @@
{
drm_atomic_helper_crtc_destroy_state(crtc, state);
}
+
+/**
+ * intel_atomic_setup_scalers() - setup scalers for crtc per staged requests
+ * @dev: DRM device
+ * @crtc: intel crtc
+ * @crtc_state: incoming crtc_state to validate and setup scalers
+ *
+ * This function sets up scalers based on staged scaling requests for
+ * a @crtc and its planes. It is called from crtc level check path. If request
+ * is a supportable request, it attaches scalers to requested planes and crtc.
+ *
+ * This function takes into account the current scaler(s) in use by any planes
+ * not being part of this atomic state
+ *
+ * Returns:
+ * 0 - scalers were setup succesfully
+ * error code - otherwise
+ */
+int intel_atomic_setup_scalers(struct drm_device *dev,
+ struct intel_crtc *intel_crtc,
+ struct intel_crtc_state *crtc_state)
+{
+ struct drm_plane *plane = NULL;
+ struct intel_plane *intel_plane;
+ struct intel_plane_state *plane_state = NULL;
+ struct intel_crtc_scaler_state *scaler_state;
+ struct drm_atomic_state *drm_state;
+ int num_scalers_need;
+ int i, j;
+
+ if (INTEL_INFO(dev)->gen < 9 || !intel_crtc || !crtc_state)
+ return 0;
+
+ scaler_state = &crtc_state->scaler_state;
+ drm_state = crtc_state->base.state;
+
+ num_scalers_need = hweight32(scaler_state->scaler_users);
+ DRM_DEBUG_KMS("crtc_state = %p need = %d avail = %d scaler_users = 0x%x\n",
+ crtc_state, num_scalers_need, intel_crtc->num_scalers,
+ scaler_state->scaler_users);
+
+ /*
+ * High level flow:
+ * - staged scaler requests are already in scaler_state->scaler_users
+ * - check whether staged scaling requests can be supported
+ * - add planes using scalers that aren't in current transaction
+ * - assign scalers to requested users
+ * - as part of plane commit, scalers will be committed
+ * (i.e., either attached or detached) to respective planes in hw
+ * - as part of crtc_commit, scaler will be either attached or detached
+ * to crtc in hw
+ */
+
+ /* fail if required scalers > available scalers */
+ if (num_scalers_need > intel_crtc->num_scalers){
+ DRM_DEBUG_KMS("Too many scaling requests %d > %d\n",
+ num_scalers_need, intel_crtc->num_scalers);
+ return -EINVAL;
+ }
+
+ /* walkthrough scaler_users bits and start assigning scalers */
+ for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) {
+ int *scaler_id;
+
+ /* skip if scaler not required */
+ if (!(scaler_state->scaler_users & (1 << i)))
+ continue;
+
+ if (i == SKL_CRTC_INDEX) {
+ /* panel fitter case: assign as a crtc scaler */
+ scaler_id = &scaler_state->scaler_id;
+ } else {
+ if (!drm_state)
+ continue;
+
+ /* plane scaler case: assign as a plane scaler */
+ /* find the plane that set the bit as scaler_user */
+ plane = drm_state->planes[i];
+
+ /*
+ * to enable/disable hq mode, add planes that are using scaler
+ * into this transaction
+ */
+ if (!plane) {
+ struct drm_plane_state *state;
+ plane = drm_plane_from_index(dev, i);
+ state = drm_atomic_get_plane_state(drm_state, plane);
+ if (IS_ERR(state)) {
+ DRM_DEBUG_KMS("Failed to add [PLANE:%d] to drm_state\n",
+ plane->base.id);
+ return PTR_ERR(state);
+ }
+ }
+
+ intel_plane = to_intel_plane(plane);
+
+ /* plane on different crtc cannot be a scaler user of this crtc */
+ if (WARN_ON(intel_plane->pipe != intel_crtc->pipe)) {
+ continue;
+ }
+
+ plane_state = to_intel_plane_state(drm_state->plane_states[i]);
+ scaler_id = &plane_state->scaler_id;
+ }
+
+ if (*scaler_id < 0) {
+ /* find a free scaler */
+ for (j = 0; j < intel_crtc->num_scalers; j++) {
+ if (!scaler_state->scalers[j].in_use) {
+ scaler_state->scalers[j].in_use = 1;
+ *scaler_id = scaler_state->scalers[j].id;
+ DRM_DEBUG_KMS("Attached scaler id %u.%u to %s:%d\n",
+ intel_crtc->pipe,
+ i == SKL_CRTC_INDEX ? scaler_state->scaler_id :
+ plane_state->scaler_id,
+ i == SKL_CRTC_INDEX ? "CRTC" : "PLANE",
+ i == SKL_CRTC_INDEX ? intel_crtc->base.base.id :
+ plane->base.id);
+ break;
+ }
+ }
+ }
+
+ if (WARN_ON(*scaler_id < 0)) {
+ DRM_DEBUG_KMS("Cannot find scaler for %s:%d\n",
+ i == SKL_CRTC_INDEX ? "CRTC" : "PLANE",
+ i == SKL_CRTC_INDEX ? intel_crtc->base.base.id:plane->base.id);
+ continue;
+ }
+
+ /* set scaler mode */
+ if (num_scalers_need == 1 && intel_crtc->pipe != PIPE_C) {
+ /*
+ * when only 1 scaler is in use on either pipe A or B,
+ * scaler 0 operates in high quality (HQ) mode.
+ * In this case use scaler 0 to take advantage of HQ mode
+ */
+ *scaler_id = 0;
+ scaler_state->scalers[0].in_use = 1;
+ scaler_state->scalers[0].mode = PS_SCALER_MODE_HQ;
+ scaler_state->scalers[1].in_use = 0;
+ } else {
+ scaler_state->scalers[*scaler_id].mode = PS_SCALER_MODE_DYN;
+ }
+ }
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index 976b891..a27ee8c 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -162,6 +162,30 @@
(1 << drm_plane_index(plane));
}
+ if (state->fb && intel_rotation_90_or_270(state->rotation)) {
+ if (!(state->fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
+ state->fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED)) {
+ DRM_DEBUG_KMS("Y/Yf tiling required for 90/270!\n");
+ return -EINVAL;
+ }
+
+ /*
+ * 90/270 is not allowed with RGB64 16:16:16:16,
+ * RGB 16-bit 5:6:5, and Indexed 8-bit.
+ * TBD: Add RGB64 case once its added in supported format list.
+ */
+ switch (state->fb->pixel_format) {
+ case DRM_FORMAT_C8:
+ case DRM_FORMAT_RGB565:
+ DRM_DEBUG_KMS("Unsupported pixel format %s for 90/270!\n",
+ drm_get_format_name(state->fb->pixel_format));
+ return -EINVAL;
+
+ default:
+ break;
+ }
+ }
+
return intel_plane->check_plane(plane, intel_state);
}
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 2396cc7..0d5b1ce 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -485,7 +485,8 @@
return -ENODEV;
intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
- ret = intel_ddi_get_cdclk_freq(dev_priv);
+ ret = dev_priv->display.get_display_clock_speed(dev_priv->dev);
+
intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
return ret;
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index c684085..c08368c 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -438,7 +438,7 @@
if (block_size >= sizeof(*general)) {
int bus_pin = general->crt_ddc_gmbus_pin;
DRM_DEBUG_KMS("crt_ddc_bus_pin: %d\n", bus_pin);
- if (intel_gmbus_is_port_valid(bus_pin))
+ if (intel_gmbus_is_valid_pin(dev_priv, bus_pin))
dev_priv->vbt.crt_ddc_pin = bus_pin;
} else {
DRM_DEBUG_KMS("BDB_GD too small (%d). Invalid.\n",
@@ -447,6 +447,12 @@
}
}
+static union child_device_config *
+child_device_ptr(struct bdb_general_definitions *p_defs, int i)
+{
+ return (void *) &p_defs->devices[i * p_defs->child_dev_size];
+}
+
static void
parse_sdvo_device_mapping(struct drm_i915_private *dev_priv,
struct bdb_header *bdb)
@@ -476,10 +482,10 @@
block_size = get_blocksize(p_defs);
/* get the number of child device */
child_device_num = (block_size - sizeof(*p_defs)) /
- sizeof(*p_child);
+ p_defs->child_dev_size;
count = 0;
for (i = 0; i < child_device_num; i++) {
- p_child = &(p_defs->devices[i]);
+ p_child = child_device_ptr(p_defs, i);
if (!p_child->old.device_type) {
/* skip the device block if device type is invalid */
continue;
@@ -1067,25 +1073,19 @@
DRM_DEBUG_KMS("No general definition block is found, no devices defined.\n");
return;
}
- /* judge whether the size of child device meets the requirements.
- * If the child device size obtained from general definition block
- * is different with sizeof(struct child_device_config), skip the
- * parsing of sdvo device info
- */
- if (p_defs->child_dev_size != sizeof(*p_child)) {
- /* different child dev size . Ignore it */
- DRM_DEBUG_KMS("different child size is found. Invalid.\n");
+ if (p_defs->child_dev_size < sizeof(*p_child)) {
+ DRM_ERROR("General definiton block child device size is too small.\n");
return;
}
/* get the block size of general definitions */
block_size = get_blocksize(p_defs);
/* get the number of child device */
child_device_num = (block_size - sizeof(*p_defs)) /
- sizeof(*p_child);
+ p_defs->child_dev_size;
count = 0;
/* get the number of child device that is present */
for (i = 0; i < child_device_num; i++) {
- p_child = &(p_defs->devices[i]);
+ p_child = child_device_ptr(p_defs, i);
if (!p_child->common.device_type) {
/* skip the device block if device type is invalid */
continue;
@@ -1105,7 +1105,7 @@
dev_priv->vbt.child_dev_num = count;
count = 0;
for (i = 0; i < child_device_num; i++) {
- p_child = &(p_defs->devices[i]);
+ p_child = child_device_ptr(p_defs, i);
if (!p_child->common.device_type) {
/* skip the device block if device type is invalid */
continue;
@@ -1133,7 +1133,7 @@
struct drm_device *dev = dev_priv->dev;
enum port port;
- dev_priv->vbt.crt_ddc_pin = GMBUS_PORT_VGADDC;
+ dev_priv->vbt.crt_ddc_pin = GMBUS_PIN_VGADDC;
/* Default to having backlight */
dev_priv->vbt.backlight.present = true;
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index 6afd5be..af0b476 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -277,9 +277,9 @@
* And the device num is related with the size of general definition
* block. It is obtained by using the following formula:
* number = (block_size - sizeof(bdb_general_definitions))/
- * sizeof(child_device_config);
+ * defs->child_dev_size;
*/
- union child_device_config devices[0];
+ uint8_t devices[0];
} __packed;
/* Mask for DRRS / Panel Channel / SSC / BLT control bits extraction */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 6095a99..93bb515 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -747,7 +747,7 @@
goto out;
/* Try to probe digital port for output in DVI-I -> VGA mode. */
- i2c = intel_gmbus_get_adapter(dev_priv, GMBUS_PORT_DPB);
+ i2c = intel_gmbus_get_adapter(dev_priv, GMBUS_PIN_DPB);
ret = intel_crt_ddc_get_modes(connector, i2c);
out:
@@ -851,7 +851,7 @@
if (!crt)
return;
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector) {
kfree(crt);
return;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 1c9d439..5b50484 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1689,105 +1689,6 @@
}
}
-static int skl_get_cdclk_freq(struct drm_i915_private *dev_priv)
-{
- uint32_t lcpll1 = I915_READ(LCPLL1_CTL);
- uint32_t cdctl = I915_READ(CDCLK_CTL);
- uint32_t linkrate;
-
- if (!(lcpll1 & LCPLL_PLL_ENABLE)) {
- WARN(1, "LCPLL1 not enabled\n");
- return 24000; /* 24MHz is the cd freq with NSSC ref */
- }
-
- if ((cdctl & CDCLK_FREQ_SEL_MASK) == CDCLK_FREQ_540)
- return 540000;
-
- linkrate = (I915_READ(DPLL_CTRL1) &
- DPLL_CRTL1_LINK_RATE_MASK(SKL_DPLL0)) >> 1;
-
- if (linkrate == DPLL_CRTL1_LINK_RATE_2160 ||
- linkrate == DPLL_CRTL1_LINK_RATE_1080) {
- /* vco 8640 */
- switch (cdctl & CDCLK_FREQ_SEL_MASK) {
- case CDCLK_FREQ_450_432:
- return 432000;
- case CDCLK_FREQ_337_308:
- return 308570;
- case CDCLK_FREQ_675_617:
- return 617140;
- default:
- WARN(1, "Unknown cd freq selection\n");
- }
- } else {
- /* vco 8100 */
- switch (cdctl & CDCLK_FREQ_SEL_MASK) {
- case CDCLK_FREQ_450_432:
- return 450000;
- case CDCLK_FREQ_337_308:
- return 337500;
- case CDCLK_FREQ_675_617:
- return 675000;
- default:
- WARN(1, "Unknown cd freq selection\n");
- }
- }
-
- /* error case, do as if DPLL0 isn't enabled */
- return 24000;
-}
-
-static int bdw_get_cdclk_freq(struct drm_i915_private *dev_priv)
-{
- uint32_t lcpll = I915_READ(LCPLL_CTL);
- uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
-
- if (lcpll & LCPLL_CD_SOURCE_FCLK)
- return 800000;
- else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
- return 450000;
- else if (freq == LCPLL_CLK_FREQ_450)
- return 450000;
- else if (freq == LCPLL_CLK_FREQ_54O_BDW)
- return 540000;
- else if (freq == LCPLL_CLK_FREQ_337_5_BDW)
- return 337500;
- else
- return 675000;
-}
-
-static int hsw_get_cdclk_freq(struct drm_i915_private *dev_priv)
-{
- struct drm_device *dev = dev_priv->dev;
- uint32_t lcpll = I915_READ(LCPLL_CTL);
- uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
-
- if (lcpll & LCPLL_CD_SOURCE_FCLK)
- return 800000;
- else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
- return 450000;
- else if (freq == LCPLL_CLK_FREQ_450)
- return 450000;
- else if (IS_HSW_ULT(dev))
- return 337500;
- else
- return 540000;
-}
-
-int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv)
-{
- struct drm_device *dev = dev_priv->dev;
-
- if (IS_SKYLAKE(dev))
- return skl_get_cdclk_freq(dev_priv);
-
- if (IS_BROADWELL(dev))
- return bdw_get_cdclk_freq(dev_priv);
-
- /* Haswell */
- return hsw_get_cdclk_freq(dev_priv);
-}
-
static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv,
struct intel_shared_dpll *pll)
{
@@ -1974,7 +1875,7 @@
hsw_shared_dplls_init(dev_priv);
DRM_DEBUG_KMS("CDCLK running at %dKHz\n",
- intel_ddi_get_cdclk_freq(dev_priv));
+ dev_priv->display.get_display_clock_speed(dev));
if (IS_SKYLAKE(dev)) {
if (!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_ENABLE))
@@ -2200,7 +2101,7 @@
struct intel_connector *connector;
enum port port = intel_dig_port->port;
- connector = kzalloc(sizeof(*connector), GFP_KERNEL);
+ connector = intel_connector_alloc();
if (!connector)
return NULL;
@@ -2219,7 +2120,7 @@
struct intel_connector *connector;
enum port port = intel_dig_port->port;
- connector = kzalloc(sizeof(*connector), GFP_KERNEL);
+ connector = intel_connector_alloc();
if (!connector)
return NULL;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d35f406..9f72d9a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -103,6 +103,8 @@
const struct intel_crtc_state *pipe_config);
static void intel_begin_crtc_commit(struct drm_crtc *crtc);
static void intel_finish_crtc_commit(struct drm_crtc *crtc);
+static void skl_init_scalers(struct drm_device *dev, struct intel_crtc *intel_crtc,
+ struct intel_crtc_state *crtc_state);
static struct intel_encoder *intel_find_encoder(struct intel_connector *connector, int pipe)
{
@@ -2338,13 +2340,6 @@
info->pitch = fb->pitches[0];
info->fb_modifier = fb->modifier[0];
- if (!(info->fb_modifier == I915_FORMAT_MOD_Y_TILED ||
- info->fb_modifier == I915_FORMAT_MOD_Yf_TILED)) {
- DRM_DEBUG_KMS(
- "Y or Yf tiling is needed for 90/270 rotation!\n");
- return -EINVAL;
- }
-
return 0;
}
@@ -2936,6 +2931,35 @@
return i915_gem_obj_ggtt_offset_view(obj, view);
}
+/*
+ * This function detaches (aka. unbinds) unused scalers in hardware
+ */
+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);
+ }
+ }
+}
+
static void skylake_update_primary_plane(struct drm_crtc *crtc,
struct drm_framebuffer *fb,
int x, int y)
@@ -2945,8 +2969,12 @@
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
struct drm_i915_gem_object *obj;
int pipe = intel_crtc->pipe;
- u32 plane_ctl, stride_div;
+ u32 plane_ctl, stride_div, stride;
+ u32 tile_height, plane_offset, plane_size;
+ unsigned int rotation;
+ int x_offset, y_offset;
unsigned long surf_addr;
+ struct drm_plane *plane;
if (!intel_crtc->primary_enabled) {
I915_WRITE(PLANE_CTL(pipe, 0), 0);
@@ -3007,21 +3035,51 @@
}
plane_ctl |= PLANE_CTL_PLANE_GAMMA_DISABLE;
- if (crtc->primary->state->rotation == BIT(DRM_ROTATE_180))
+
+ plane = crtc->primary;
+ rotation = plane->state->rotation;
+ switch (rotation) {
+ case BIT(DRM_ROTATE_90):
+ plane_ctl |= PLANE_CTL_ROTATE_90;
+ break;
+
+ case BIT(DRM_ROTATE_180):
plane_ctl |= PLANE_CTL_ROTATE_180;
+ break;
+
+ case BIT(DRM_ROTATE_270):
+ plane_ctl |= PLANE_CTL_ROTATE_270;
+ break;
+ }
obj = intel_fb_obj(fb);
stride_div = intel_fb_stride_alignment(dev, fb->modifier[0],
fb->pixel_format);
- surf_addr = intel_plane_obj_offset(to_intel_plane(crtc->primary), obj);
+ surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj);
+
+ if (intel_rotation_90_or_270(rotation)) {
+ /* stride = Surface height in tiles */
+ tile_height = intel_tile_height(dev, fb->bits_per_pixel,
+ fb->modifier[0]);
+ stride = DIV_ROUND_UP(fb->height, tile_height);
+ x_offset = stride * tile_height - y - (plane->state->src_h >> 16);
+ y_offset = x;
+ plane_size = ((plane->state->src_w >> 16) - 1) << 16 |
+ ((plane->state->src_h >> 16) - 1);
+ } else {
+ stride = fb->pitches[0] / stride_div;
+ x_offset = x;
+ y_offset = y;
+ plane_size = ((plane->state->src_h >> 16) - 1) << 16 |
+ ((plane->state->src_w >> 16) - 1);
+ }
+ plane_offset = y_offset << 16 | x_offset;
I915_WRITE(PLANE_CTL(pipe, 0), plane_ctl);
I915_WRITE(PLANE_POS(pipe, 0), 0);
- I915_WRITE(PLANE_OFFSET(pipe, 0), (y << 16) | x);
- I915_WRITE(PLANE_SIZE(pipe, 0),
- (intel_crtc->config->pipe_src_h - 1) << 16 |
- (intel_crtc->config->pipe_src_w - 1));
- I915_WRITE(PLANE_STRIDE(pipe, 0), fb->pitches[0] / stride_div);
+ I915_WRITE(PLANE_OFFSET(pipe, 0), plane_offset);
+ I915_WRITE(PLANE_SIZE(pipe, 0), plane_size);
+ I915_WRITE(PLANE_STRIDE(pipe, 0), stride);
I915_WRITE(PLANE_SURF(pipe, 0), surf_addr);
POSTING_READ(PLANE_SURF(pipe, 0));
@@ -4251,16 +4309,175 @@
}
}
-static void skylake_pfit_enable(struct intel_crtc *crtc)
+/**
+ * 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)
+{
+ 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;
+
+ 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;
+ } 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;
+ }
+ need_scaling = (src_w != dst_w || src_h != dst_h);
+
+ /*
+ * if plane is being disabled or scaler is no more required or force detach
+ * - free scaler binded to this plane/crtc
+ * - in order to do this, update crtc->scaler_usage
+ *
+ * Here scaler state in crtc_state is set free so that
+ * scaler can be assigned to other user. Actual register
+ * 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 (*scaler_id >= 0) {
+ scaler_state->scaler_users &= ~(1 << idx);
+ 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,
+ scaler_state->scaler_users);
+ *scaler_id = -1;
+ }
+ return 0;
+ }
+
+ /* range checks */
+ if (src_w < SKL_MIN_SRC_W || src_h < SKL_MIN_SRC_H ||
+ dst_w < SKL_MIN_DST_W || dst_h < SKL_MIN_DST_H ||
+
+ 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 "
+ "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 (intel_plane && intel_plane->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 */
+ 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_ARGB2101010:
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_ABGR2101010:
+ 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);
+ return 0;
+}
+
+static void skylake_pfit_update(struct intel_crtc *crtc, int enable)
{
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);
+
+ /* 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;
if (crtc->config->pch_pfit.enabled) {
- I915_WRITE(PS_CTL(pipe), PS_ENABLE);
- I915_WRITE(PS_WIN_POS(pipe), crtc->config->pch_pfit.pos);
- I915_WRITE(PS_WIN_SZ(pipe), crtc->config->pch_pfit.size);
+ int id;
+
+ if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) {
+ DRM_ERROR("Requesting pfit without getting a scaler first\n");
+ return;
+ }
+
+ id = scaler_state->scaler_id;
+ I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
+ PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
+ I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
+ I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
+
+ DRM_DEBUG_KMS("for crtc_state = %p scaler_id = %d\n", crtc->config, id);
}
}
@@ -4665,7 +4882,7 @@
intel_ddi_enable_pipe_clock(intel_crtc);
if (IS_SKYLAKE(dev))
- skylake_pfit_enable(intel_crtc);
+ skylake_pfit_update(intel_crtc, 1);
else
ironlake_pfit_enable(intel_crtc);
@@ -4701,21 +4918,6 @@
intel_crtc_enable_planes(crtc);
}
-static void skylake_pfit_disable(struct intel_crtc *crtc)
-{
- struct drm_device *dev = crtc->base.dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- int pipe = crtc->pipe;
-
- /* To avoid upsetting the power well on haswell only disable the pfit if
- * it's in use. The hw state code will make sure we get this right. */
- if (crtc->config->pch_pfit.enabled) {
- I915_WRITE(PS_CTL(pipe), 0);
- I915_WRITE(PS_WIN_POS(pipe), 0);
- I915_WRITE(PS_WIN_SZ(pipe), 0);
- }
-}
-
static void ironlake_pfit_disable(struct intel_crtc *crtc)
{
struct drm_device *dev = crtc->base.dev;
@@ -4828,7 +5030,7 @@
intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
if (IS_SKYLAKE(dev))
- skylake_pfit_disable(intel_crtc);
+ skylake_pfit_update(intel_crtc, 0);
else
ironlake_pfit_disable(intel_crtc);
@@ -5160,36 +5362,48 @@
}
/* compute the max pixel clock for new configuration */
-static int intel_mode_max_pixclk(struct drm_i915_private *dev_priv)
+static int intel_mode_max_pixclk(struct drm_atomic_state *state)
{
- struct drm_device *dev = dev_priv->dev;
+ struct drm_device *dev = state->dev;
struct intel_crtc *intel_crtc;
+ struct intel_crtc_state *crtc_state;
int max_pixclk = 0;
for_each_intel_crtc(dev, intel_crtc) {
- if (intel_crtc->new_enabled)
- max_pixclk = max(max_pixclk,
- intel_crtc->new_config->base.adjusted_mode.crtc_clock);
+ crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
+ if (IS_ERR(crtc_state))
+ return PTR_ERR(crtc_state);
+
+ if (!crtc_state->base.enable)
+ continue;
+
+ max_pixclk = max(max_pixclk,
+ crtc_state->base.adjusted_mode.crtc_clock);
}
return max_pixclk;
}
-static void valleyview_modeset_global_pipes(struct drm_device *dev,
+static int valleyview_modeset_global_pipes(struct drm_atomic_state *state,
unsigned *prepare_pipes)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_i915_private *dev_priv = to_i915(state->dev);
struct intel_crtc *intel_crtc;
- int max_pixclk = intel_mode_max_pixclk(dev_priv);
+ int max_pixclk = intel_mode_max_pixclk(state);
+
+ if (max_pixclk < 0)
+ return max_pixclk;
if (valleyview_calc_cdclk(dev_priv, max_pixclk) ==
dev_priv->vlv_cdclk_freq)
- return;
+ return 0;
/* disable/enable all currently active pipes while we change cdclk */
- for_each_intel_crtc(dev, intel_crtc)
+ for_each_intel_crtc(state->dev, intel_crtc)
if (intel_crtc->base.state->enable)
*prepare_pipes |= (1 << intel_crtc->pipe);
+
+ return 0;
}
static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv)
@@ -5232,8 +5446,18 @@
{
struct drm_device *dev = state->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- int max_pixclk = intel_mode_max_pixclk(dev_priv);
- int req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
+ int max_pixclk = intel_mode_max_pixclk(state);
+ int req_cdclk;
+
+ /* The only reason this can fail is if we fail to add the crtc_state
+ * to the atomic state. But that can't happen since the call to
+ * intel_mode_max_pixclk() in valleyview_modeset_global_pipes() (which
+ * can't have failed otherwise the mode set would be aborted) added all
+ * the states already. */
+ if (WARN_ON(max_pixclk < 0))
+ return;
+
+ req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
if (req_cdclk != dev_priv->vlv_cdclk_freq) {
/*
@@ -5554,7 +5778,7 @@
dev_priv->display.crtc_disable(crtc);
dev_priv->display.off(crtc);
- crtc->primary->funcs->disable_plane(crtc->primary);
+ drm_plane_helper_disable(crtc->primary);
/* Update computed state. */
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
@@ -5636,6 +5860,34 @@
}
}
+int intel_connector_init(struct intel_connector *connector)
+{
+ struct drm_connector_state *connector_state;
+
+ connector_state = kzalloc(sizeof *connector_state, GFP_KERNEL);
+ if (!connector_state)
+ return -ENOMEM;
+
+ connector->base.state = connector_state;
+ return 0;
+}
+
+struct intel_connector *intel_connector_alloc(void)
+{
+ struct intel_connector *connector;
+
+ connector = kzalloc(sizeof *connector, GFP_KERNEL);
+ if (!connector)
+ return NULL;
+
+ if (intel_connector_init(connector) < 0) {
+ kfree(connector);
+ return NULL;
+ }
+
+ return connector;
+}
+
/* Even simpler default implementation, if there's really no special case to
* consider. */
void intel_connector_dpms(struct drm_connector *connector, int mode)
@@ -5667,65 +5919,80 @@
return encoder->get_hw_state(encoder, &pipe);
}
-static int pipe_required_fdi_lanes(struct drm_device *dev, enum pipe pipe)
+static int pipe_required_fdi_lanes(struct intel_crtc_state *crtc_state)
{
- struct intel_crtc *crtc =
- to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe));
-
- if (crtc->base.state->enable &&
- crtc->config->has_pch_encoder)
- return crtc->config->fdi_lanes;
+ if (crtc_state->base.enable && crtc_state->has_pch_encoder)
+ return crtc_state->fdi_lanes;
return 0;
}
-static bool ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
+static int ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
struct intel_crtc_state *pipe_config)
{
+ struct drm_atomic_state *state = pipe_config->base.state;
+ struct intel_crtc *other_crtc;
+ struct intel_crtc_state *other_crtc_state;
+
DRM_DEBUG_KMS("checking fdi config on pipe %c, lanes %i\n",
pipe_name(pipe), pipe_config->fdi_lanes);
if (pipe_config->fdi_lanes > 4) {
DRM_DEBUG_KMS("invalid fdi lane config on pipe %c: %i lanes\n",
pipe_name(pipe), pipe_config->fdi_lanes);
- return false;
+ return -EINVAL;
}
if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
if (pipe_config->fdi_lanes > 2) {
DRM_DEBUG_KMS("only 2 lanes on haswell, required: %i lanes\n",
pipe_config->fdi_lanes);
- return false;
+ return -EINVAL;
} else {
- return true;
+ return 0;
}
}
if (INTEL_INFO(dev)->num_pipes == 2)
- return true;
+ return 0;
/* Ivybridge 3 pipe is really complicated */
switch (pipe) {
case PIPE_A:
- return true;
+ return 0;
case PIPE_B:
- if (pipe_config->fdi_lanes > 2 &&
- pipe_required_fdi_lanes(dev, PIPE_C) > 0) {
+ if (pipe_config->fdi_lanes <= 2)
+ return 0;
+
+ other_crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, PIPE_C));
+ other_crtc_state =
+ intel_atomic_get_crtc_state(state, other_crtc);
+ if (IS_ERR(other_crtc_state))
+ return PTR_ERR(other_crtc_state);
+
+ if (pipe_required_fdi_lanes(other_crtc_state) > 0) {
DRM_DEBUG_KMS("invalid shared fdi lane config on pipe %c: %i lanes\n",
pipe_name(pipe), pipe_config->fdi_lanes);
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
case PIPE_C:
if (pipe_config->fdi_lanes > 2) {
DRM_DEBUG_KMS("only 2 lanes on pipe %c: required %i lanes\n",
pipe_name(pipe), pipe_config->fdi_lanes);
- return false;
+ return -EINVAL;
}
- if (pipe_required_fdi_lanes(dev, PIPE_B) > 2) {
+
+ other_crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, PIPE_B));
+ other_crtc_state =
+ intel_atomic_get_crtc_state(state, other_crtc);
+ if (IS_ERR(other_crtc_state))
+ return PTR_ERR(other_crtc_state);
+
+ if (pipe_required_fdi_lanes(other_crtc_state) > 2) {
DRM_DEBUG_KMS("fdi link B uses too many lanes to enable link C\n");
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
default:
BUG();
}
@@ -5737,8 +6004,8 @@
{
struct drm_device *dev = intel_crtc->base.dev;
struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
- int lane, link_bw, fdi_dotclock;
- bool setup_ok, needs_recompute = false;
+ int lane, link_bw, fdi_dotclock, ret;
+ bool needs_recompute = false;
retry:
/* FDI is a binary signal running at ~2.7GHz, encoding
@@ -5760,9 +6027,9 @@
intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
link_bw, &pipe_config->fdi_m_n);
- setup_ok = ironlake_check_fdi_lanes(intel_crtc->base.dev,
- intel_crtc->pipe, pipe_config);
- if (!setup_ok && pipe_config->pipe_bpp > 6*3) {
+ ret = ironlake_check_fdi_lanes(intel_crtc->base.dev,
+ intel_crtc->pipe, pipe_config);
+ if (ret == -EINVAL && pipe_config->pipe_bpp > 6*3) {
pipe_config->pipe_bpp -= 2*3;
DRM_DEBUG_KMS("fdi link bw constraint, reducing pipe bpp to %i\n",
pipe_config->pipe_bpp);
@@ -5775,7 +6042,7 @@
if (needs_recompute)
return RETRY;
- return setup_ok ? 0 : -EINVAL;
+ return ret;
}
static void hsw_compute_ips_config(struct intel_crtc *crtc,
@@ -5792,6 +6059,7 @@
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) {
@@ -5846,7 +6114,101 @@
if (pipe_config->has_pch_encoder)
return ironlake_fdi_compute_config(crtc, pipe_config);
- return 0;
+ /* 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;
+}
+
+static int skylake_get_display_clock_speed(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ uint32_t lcpll1 = I915_READ(LCPLL1_CTL);
+ uint32_t cdctl = I915_READ(CDCLK_CTL);
+ uint32_t linkrate;
+
+ if (!(lcpll1 & LCPLL_PLL_ENABLE)) {
+ WARN(1, "LCPLL1 not enabled\n");
+ return 24000; /* 24MHz is the cd freq with NSSC ref */
+ }
+
+ if ((cdctl & CDCLK_FREQ_SEL_MASK) == CDCLK_FREQ_540)
+ return 540000;
+
+ linkrate = (I915_READ(DPLL_CTRL1) &
+ DPLL_CRTL1_LINK_RATE_MASK(SKL_DPLL0)) >> 1;
+
+ if (linkrate == DPLL_CRTL1_LINK_RATE_2160 ||
+ linkrate == DPLL_CRTL1_LINK_RATE_1080) {
+ /* vco 8640 */
+ switch (cdctl & CDCLK_FREQ_SEL_MASK) {
+ case CDCLK_FREQ_450_432:
+ return 432000;
+ case CDCLK_FREQ_337_308:
+ return 308570;
+ case CDCLK_FREQ_675_617:
+ return 617140;
+ default:
+ WARN(1, "Unknown cd freq selection\n");
+ }
+ } else {
+ /* vco 8100 */
+ switch (cdctl & CDCLK_FREQ_SEL_MASK) {
+ case CDCLK_FREQ_450_432:
+ return 450000;
+ case CDCLK_FREQ_337_308:
+ return 337500;
+ case CDCLK_FREQ_675_617:
+ return 675000;
+ default:
+ WARN(1, "Unknown cd freq selection\n");
+ }
+ }
+
+ /* error case, do as if DPLL0 isn't enabled */
+ return 24000;
+}
+
+static int broadwell_get_display_clock_speed(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t lcpll = I915_READ(LCPLL_CTL);
+ uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
+
+ if (lcpll & LCPLL_CD_SOURCE_FCLK)
+ return 800000;
+ else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
+ return 450000;
+ else if (freq == LCPLL_CLK_FREQ_450)
+ return 450000;
+ else if (freq == LCPLL_CLK_FREQ_54O_BDW)
+ return 540000;
+ else if (freq == LCPLL_CLK_FREQ_337_5_BDW)
+ return 337500;
+ else
+ return 675000;
+}
+
+static int haswell_get_display_clock_speed(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t lcpll = I915_READ(LCPLL_CTL);
+ uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
+
+ if (lcpll & LCPLL_CD_SOURCE_FCLK)
+ return 800000;
+ else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
+ return 450000;
+ else if (freq == LCPLL_CLK_FREQ_450)
+ return 450000;
+ else if (IS_HSW_ULT(dev))
+ return 337500;
+ else
+ return 540000;
}
static int valleyview_get_display_clock_speed(struct drm_device *dev)
@@ -5871,6 +6233,11 @@
return DIV_ROUND_CLOSEST(dev_priv->hpll_freq << 1, divider + 1);
}
+static int ilk_get_display_clock_speed(struct drm_device *dev)
+{
+ return 450000;
+}
+
static int i945_get_display_clock_speed(struct drm_device *dev)
{
return 400000;
@@ -5878,7 +6245,7 @@
static int i915_get_display_clock_speed(struct drm_device *dev)
{
- return 333000;
+ return 333333;
}
static int i9xx_misc_get_display_clock_speed(struct drm_device *dev)
@@ -5894,19 +6261,19 @@
switch (gcfgc & GC_DISPLAY_CLOCK_MASK) {
case GC_DISPLAY_CLOCK_267_MHZ_PNV:
- return 267000;
+ return 266667;
case GC_DISPLAY_CLOCK_333_MHZ_PNV:
- return 333000;
+ return 333333;
case GC_DISPLAY_CLOCK_444_MHZ_PNV:
- return 444000;
+ return 444444;
case GC_DISPLAY_CLOCK_200_MHZ_PNV:
return 200000;
default:
DRM_ERROR("Unknown pnv display core clock 0x%04x\n", gcfgc);
case GC_DISPLAY_CLOCK_133_MHZ_PNV:
- return 133000;
+ return 133333;
case GC_DISPLAY_CLOCK_167_MHZ_PNV:
- return 167000;
+ return 166667;
}
}
@@ -5917,11 +6284,11 @@
pci_read_config_word(dev->pdev, GCFGC, &gcfgc);
if (gcfgc & GC_LOW_FREQUENCY_ENABLE)
- return 133000;
+ return 133333;
else {
switch (gcfgc & GC_DISPLAY_CLOCK_MASK) {
case GC_DISPLAY_CLOCK_333_MHZ:
- return 333000;
+ return 333333;
default:
case GC_DISPLAY_CLOCK_190_200_MHZ:
return 190000;
@@ -5931,7 +6298,7 @@
static int i865_get_display_clock_speed(struct drm_device *dev)
{
- return 266000;
+ return 266667;
}
static int i855_get_display_clock_speed(struct drm_device *dev)
@@ -5947,7 +6314,7 @@
case GC_CLOCK_166_250:
return 250000;
case GC_CLOCK_100_133:
- return 133000;
+ return 133333;
}
/* Shouldn't happen */
@@ -5956,7 +6323,7 @@
static int i830_get_display_clock_speed(struct drm_device *dev)
{
- return 133000;
+ return 133333;
}
static void
@@ -7952,14 +8319,28 @@
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- uint32_t tmp;
+ struct intel_crtc_scaler_state *scaler_state = &pipe_config->scaler_state;
+ uint32_t ps_ctrl = 0;
+ int id = -1;
+ int i;
- tmp = I915_READ(PS_CTL(crtc->pipe));
+ /* find scaler attached to this pipe */
+ for (i = 0; i < crtc->num_scalers; i++) {
+ ps_ctrl = I915_READ(SKL_PS_CTRL(crtc->pipe, i));
+ if (ps_ctrl & PS_SCALER_EN && !(ps_ctrl & PS_PLANE_SEL_MASK)) {
+ id = i;
+ pipe_config->pch_pfit.enabled = true;
+ pipe_config->pch_pfit.pos = I915_READ(SKL_PS_WIN_POS(crtc->pipe, i));
+ pipe_config->pch_pfit.size = I915_READ(SKL_PS_WIN_SZ(crtc->pipe, i));
+ break;
+ }
+ }
- if (tmp & PS_ENABLE) {
- pipe_config->pch_pfit.enabled = true;
- pipe_config->pch_pfit.pos = I915_READ(PS_WIN_POS(crtc->pipe));
- pipe_config->pch_pfit.size = I915_READ(PS_WIN_SZ(crtc->pipe));
+ scaler_state->scaler_id = id;
+ if (id >= 0) {
+ scaler_state->scaler_users |= (1 << SKL_CRTC_INDEX);
+ } else {
+ scaler_state->scaler_users &= ~(1 << SKL_CRTC_INDEX);
}
}
@@ -8593,12 +8974,19 @@
intel_get_pipe_timings(crtc, pipe_config);
+ if (INTEL_INFO(dev)->gen >= 9) {
+ skl_init_scalers(dev, crtc, pipe_config);
+ }
+
pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
if (intel_display_power_is_enabled(dev_priv, pfit_domain)) {
if (IS_SKYLAKE(dev))
skylake_get_pfit_config(crtc, pipe_config);
else
ironlake_get_pfit_config(crtc, pipe_config);
+ } else {
+ pipe_config->scaler_state.scaler_id = -1;
+ pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX);
}
if (IS_HASWELL(dev))
@@ -9042,7 +9430,6 @@
intel_crtc = to_intel_crtc(crtc);
intel_crtc->new_enabled = true;
- intel_crtc->new_config = intel_crtc->config;
old->dpms_mode = connector->dpms;
old->load_detect_temp = true;
old->release_fb = NULL;
@@ -9098,10 +9485,6 @@
fail:
intel_crtc->new_enabled = crtc->state->enable;
- if (intel_crtc->new_enabled)
- intel_crtc->new_config = intel_crtc->config;
- else
- intel_crtc->new_config = NULL;
fail_unlock:
if (state) {
drm_atomic_state_free(state);
@@ -9147,7 +9530,6 @@
to_intel_connector(connector)->new_encoder = NULL;
intel_encoder->new_crtc = NULL;
intel_crtc->new_enabled = false;
- intel_crtc->new_config = NULL;
connector_state->best_encoder = NULL;
connector_state->crtc = NULL;
@@ -10057,6 +10439,7 @@
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);
+ struct intel_unpin_work *work;
WARN_ON(!in_interrupt());
@@ -10064,12 +10447,16 @@
return;
spin_lock(&dev->event_lock);
- if (intel_crtc->unpin_work && __intel_pageflip_stall_check(dev, crtc)) {
+ work = intel_crtc->unpin_work;
+ if (work != NULL && __intel_pageflip_stall_check(dev, crtc)) {
WARN_ONCE(1, "Kicking stuck page flip: queued at %d, now %d\n",
- intel_crtc->unpin_work->flip_queued_vblank,
- drm_vblank_count(dev, pipe));
+ work->flip_queued_vblank, drm_vblank_count(dev, pipe));
page_flip_completed(intel_crtc);
+ work = NULL;
}
+ if (work != NULL &&
+ drm_vblank_count(dev, pipe) - work->flip_queued_vblank > 1)
+ intel_queue_rps_boost_for_request(dev, work->flip_queued_req);
spin_unlock(&dev->event_lock);
}
@@ -10087,6 +10474,7 @@
enum pipe pipe = intel_crtc->pipe;
struct intel_unpin_work *work;
struct intel_engine_cs *ring;
+ bool mmio_flip;
int ret;
/*
@@ -10184,15 +10572,23 @@
ring = &dev_priv->ring[RCS];
}
+ mmio_flip = use_mmio_flip(ring, obj);
+
+ /* When using CS flips, we want to emit semaphores between rings.
+ * However, when using mmio flips we will create a task to do the
+ * synchronisation, so all we want here is to pin the framebuffer
+ * into the display plane and skip any waits.
+ */
ret = intel_pin_and_fence_fb_obj(crtc->primary, fb,
- crtc->primary->state, ring);
+ crtc->primary->state,
+ mmio_flip ? i915_gem_request_get_ring(obj->last_read_req) : ring);
if (ret)
goto cleanup_pending;
work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), obj)
+ intel_crtc->dspaddr_offset;
- if (use_mmio_flip(ring, obj)) {
+ if (mmio_flip) {
ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring,
page_flip_flags);
if (ret)
@@ -10287,11 +10683,6 @@
for_each_intel_crtc(dev, crtc) {
crtc->new_enabled = crtc->base.state->enable;
-
- if (crtc->new_enabled)
- crtc->new_config = crtc->config;
- else
- crtc->new_config = NULL;
}
}
@@ -10449,8 +10840,14 @@
struct intel_crtc_state *pipe_config,
const char *context)
{
- DRM_DEBUG_KMS("[CRTC:%d]%s config for pipe %c\n", crtc->base.base.id,
- context, pipe_name(crtc->pipe));
+ struct drm_device *dev = crtc->base.dev;
+ struct drm_plane *plane;
+ struct intel_plane *intel_plane;
+ struct intel_plane_state *state;
+ struct drm_framebuffer *fb;
+
+ DRM_DEBUG_KMS("[CRTC:%d]%s config %p for pipe %c\n", crtc->base.base.id,
+ context, pipe_config, pipe_name(crtc->pipe));
DRM_DEBUG_KMS("cpu_transcoder: %c\n", transcoder_name(pipe_config->cpu_transcoder));
DRM_DEBUG_KMS("pipe bpp: %i, dithering: %i\n",
@@ -10487,6 +10884,9 @@
DRM_DEBUG_KMS("port clock: %d\n", pipe_config->port_clock);
DRM_DEBUG_KMS("pipe src size: %dx%d\n",
pipe_config->pipe_src_w, pipe_config->pipe_src_h);
+ DRM_DEBUG_KMS("num_scalers: %d\n", crtc->num_scalers);
+ DRM_DEBUG_KMS("scaler_users: 0x%x\n", pipe_config->scaler_state.scaler_users);
+ DRM_DEBUG_KMS("scaler id: %d\n", pipe_config->scaler_state.scaler_id);
DRM_DEBUG_KMS("gmch pfit: control: 0x%08x, ratios: 0x%08x, lvds border: 0x%08x\n",
pipe_config->gmch_pfit.control,
pipe_config->gmch_pfit.pgm_ratios,
@@ -10497,6 +10897,40 @@
pipe_config->pch_pfit.enabled ? "enabled" : "disabled");
DRM_DEBUG_KMS("ips: %i\n", pipe_config->ips_enabled);
DRM_DEBUG_KMS("double wide: %i\n", pipe_config->double_wide);
+
+ DRM_DEBUG_KMS("planes on this crtc\n");
+ list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
+ intel_plane = to_intel_plane(plane);
+ if (intel_plane->pipe != crtc->pipe)
+ continue;
+
+ state = to_intel_plane_state(plane->state);
+ fb = state->base.fb;
+ if (!fb) {
+ DRM_DEBUG_KMS("%s PLANE:%d plane: %u.%u idx: %d "
+ "disabled, scaler_id = %d\n",
+ plane->type == DRM_PLANE_TYPE_CURSOR ? "CURSOR" : "STANDARD",
+ plane->base.id, intel_plane->pipe,
+ (crtc->base.primary == plane) ? 0 : intel_plane->plane + 1,
+ drm_plane_index(plane), state->scaler_id);
+ continue;
+ }
+
+ DRM_DEBUG_KMS("%s PLANE:%d plane: %u.%u idx: %d enabled",
+ plane->type == DRM_PLANE_TYPE_CURSOR ? "CURSOR" : "STANDARD",
+ plane->base.id, intel_plane->pipe,
+ crtc->base.primary == plane ? 0 : intel_plane->plane + 1,
+ drm_plane_index(plane));
+ DRM_DEBUG_KMS("\tFB:%d, fb = %ux%u format = 0x%x",
+ fb->base.id, fb->width, fb->height, fb->pixel_format);
+ DRM_DEBUG_KMS("\tscaler:%d src (%u, %u) %ux%u dst (%u, %u) %ux%u\n",
+ state->scaler_id,
+ state->src.x1 >> 16, state->src.y1 >> 16,
+ drm_rect_width(&state->src) >> 16,
+ drm_rect_height(&state->src) >> 16,
+ state->dst.x1, state->dst.y1,
+ drm_rect_width(&state->dst), drm_rect_height(&state->dst));
+ }
}
static bool encoders_cloneable(const struct intel_encoder *a,
@@ -10507,16 +10941,24 @@
b->cloneable & (1 << a->type));
}
-static bool check_single_encoder_cloning(struct intel_crtc *crtc,
+static bool check_single_encoder_cloning(struct drm_atomic_state *state,
+ struct intel_crtc *crtc,
struct intel_encoder *encoder)
{
- struct drm_device *dev = crtc->base.dev;
struct intel_encoder *source_encoder;
+ struct drm_connector_state *connector_state;
+ int i;
- for_each_intel_encoder(dev, source_encoder) {
- if (source_encoder->new_crtc != crtc)
+ for (i = 0; i < state->num_connector; i++) {
+ if (!state->connectors[i])
continue;
+ connector_state = state->connector_states[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;
}
@@ -10524,39 +10966,53 @@
return true;
}
-static bool check_encoder_cloning(struct intel_crtc *crtc)
+static bool check_encoder_cloning(struct drm_atomic_state *state,
+ struct intel_crtc *crtc)
{
- struct drm_device *dev = crtc->base.dev;
struct intel_encoder *encoder;
+ struct drm_connector_state *connector_state;
+ int i;
- for_each_intel_encoder(dev, encoder) {
- if (encoder->new_crtc != crtc)
+ for (i = 0; i < state->num_connector; i++) {
+ if (!state->connectors[i])
continue;
- if (!check_single_encoder_cloning(crtc, encoder))
+ connector_state = state->connector_states[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_device *dev)
+static bool check_digital_port_conflicts(struct drm_atomic_state *state)
{
- struct intel_connector *connector;
+ struct drm_device *dev = state->dev;
+ struct intel_encoder *encoder;
+ struct drm_connector_state *connector_state;
unsigned int used_ports = 0;
+ int i;
/*
* Walk the connector list instead of the encoder
* list to detect the problem on ddi platforms
* where there's just one encoder per digital port.
*/
- for_each_intel_connector(dev, connector) {
- struct intel_encoder *encoder = connector->new_encoder;
-
- if (!encoder)
+ for (i = 0; i < state->num_connector; i++) {
+ if (!state->connectors[i])
continue;
- WARN_ON(!encoder->new_crtc);
+ connector_state = state->connector_states[i];
+ if (!connector_state->best_encoder)
+ continue;
+
+ encoder = to_intel_encoder(connector_state->best_encoder);
+
+ WARN_ON(!connector_state->crtc);
switch (encoder->type) {
unsigned int port_mask;
@@ -10585,11 +11041,14 @@
clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
{
struct drm_crtc_state tmp_state;
+ struct intel_crtc_scaler_state scaler_state;
- /* Clear only the intel specific part of the crtc state */
+ /* Clear only the intel specific part of the crtc state excluding scalers */
tmp_state = crtc_state->base;
+ scaler_state = crtc_state->scaler_state;
memset(crtc_state, 0, sizeof *crtc_state);
crtc_state->base = tmp_state;
+ crtc_state->scaler_state = scaler_state;
}
static struct intel_crtc_state *
@@ -10598,7 +11057,6 @@
struct drm_display_mode *mode,
struct drm_atomic_state *state)
{
- struct drm_device *dev = crtc->dev;
struct intel_encoder *encoder;
struct intel_connector *connector;
struct drm_connector_state *connector_state;
@@ -10607,12 +11065,12 @@
int i;
bool retry = true;
- if (!check_encoder_cloning(to_intel_crtc(crtc))) {
+ if (!check_encoder_cloning(state, to_intel_crtc(crtc))) {
DRM_DEBUG_KMS("rejecting invalid cloning configuration\n");
return ERR_PTR(-EINVAL);
}
- if (!check_digital_port_conflicts(dev)) {
+ if (!check_digital_port_conflicts(state)) {
DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
return ERR_PTR(-EINVAL);
}
@@ -10852,9 +11310,6 @@
/* Double check state. */
for_each_intel_crtc(dev, intel_crtc) {
WARN_ON(intel_crtc->base.state->enable != intel_crtc_in_use(&intel_crtc->base));
- WARN_ON(intel_crtc->new_config &&
- intel_crtc->new_config != intel_crtc->config);
- WARN_ON(intel_crtc->base.state->enable != !!intel_crtc->new_config);
}
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
@@ -11059,6 +11514,8 @@
PIPE_CONF_CHECK_I(pch_pfit.size);
}
+ PIPE_CONF_CHECK_I(scaler_state.scaler_id);
+
/* BDW+ don't expose a synchronous way to read the state */
if (IS_HASWELL(dev))
PIPE_CONF_CHECK_I(ips_enabled);
@@ -11443,6 +11900,8 @@
if (IS_ERR(pipe_config))
return pipe_config;
+ pipe_config->base.enable = true;
+
intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config,
"[modeset]");
}
@@ -11450,10 +11909,11 @@
return intel_atomic_get_crtc_state(state, to_intel_crtc(crtc));;
}
-static int __intel_set_mode_setup_plls(struct drm_device *dev,
+static int __intel_set_mode_setup_plls(struct drm_atomic_state *state,
unsigned modeset_pipes,
unsigned disable_pipes)
{
+ struct drm_device *dev = state->dev;
struct drm_i915_private *dev_priv = to_i915(dev);
unsigned clear_pipes = modeset_pipes | disable_pipes;
struct intel_crtc *intel_crtc;
@@ -11467,9 +11927,15 @@
goto done;
for_each_intel_crtc_masked(dev, modeset_pipes, intel_crtc) {
- struct intel_crtc_state *state = intel_crtc->new_config;
+ struct intel_crtc_state *crtc_state =
+ intel_atomic_get_crtc_state(state, intel_crtc);
+
+ /* Modeset pipes should have a new state by now */
+ if (WARN_ON(IS_ERR(crtc_state)))
+ continue;
+
ret = dev_priv->display.crtc_compute_clock(intel_crtc,
- state);
+ crtc_state);
if (ret) {
intel_shared_dpll_abort_config(dev_priv);
goto done;
@@ -11491,6 +11957,7 @@
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_display_mode *saved_mode;
+ struct drm_atomic_state *state = pipe_config->base.state;
struct intel_crtc_state *crtc_state_copy = NULL;
struct intel_crtc *intel_crtc;
int ret = 0;
@@ -11507,9 +11974,6 @@
*saved_mode = crtc->mode;
- if (modeset_pipes)
- to_intel_crtc(crtc)->new_config = pipe_config;
-
/*
* See if the config requires any additional preparation, e.g.
* to adjust global state with pipes off. We need to do this
@@ -11518,13 +11982,15 @@
* adjusted_mode bits in the crtc directly.
*/
if (IS_VALLEYVIEW(dev)) {
- valleyview_modeset_global_pipes(dev, &prepare_pipes);
+ ret = valleyview_modeset_global_pipes(state, &prepare_pipes);
+ if (ret)
+ goto done;
/* may have added more to prepare_pipes than we should */
prepare_pipes &= ~disable_pipes;
}
- ret = __intel_set_mode_setup_plls(dev, modeset_pipes, disable_pipes);
+ ret = __intel_set_mode_setup_plls(state, modeset_pipes, disable_pipes);
if (ret)
goto done;
@@ -11562,21 +12028,18 @@
* update the the output configuration. */
intel_modeset_update_state(dev, prepare_pipes);
- modeset_update_crtc_power_domains(pipe_config->base.state);
+ modeset_update_crtc_power_domains(state);
- /* Set up the DPLL and any encoders state that needs to adjust or depend
- * on the DPLL.
- */
for_each_intel_crtc_masked(dev, modeset_pipes, intel_crtc) {
struct drm_plane *primary = intel_crtc->base.primary;
int vdisplay, hdisplay;
drm_crtc_get_hv_timing(mode, &hdisplay, &vdisplay);
- ret = primary->funcs->update_plane(primary, &intel_crtc->base,
- fb, 0, 0,
- hdisplay, vdisplay,
- x << 16, y << 16,
- hdisplay << 16, vdisplay << 16);
+ ret = drm_plane_helper_update(primary, &intel_crtc->base,
+ fb, 0, 0,
+ hdisplay, vdisplay,
+ x << 16, y << 16,
+ hdisplay << 16, vdisplay << 16);
}
/* Now enable the clocks, plane, pipe, and connectors that we set up. */
@@ -11600,9 +12063,6 @@
sizeof *crtc_state_copy);
intel_crtc->config = crtc_state_copy;
intel_crtc->base.state = &crtc_state_copy->base;
-
- if (modeset_pipes)
- intel_crtc->new_config = intel_crtc->config;
} else {
kfree(crtc_state_copy);
}
@@ -11781,11 +12241,6 @@
count = 0;
for_each_intel_crtc(dev, crtc) {
crtc->new_enabled = config->save_crtc_enabled[count++];
-
- if (crtc->new_enabled)
- crtc->new_config = crtc->config;
- else
- crtc->new_config = NULL;
}
count = 0;
@@ -11993,6 +12448,7 @@
connector->encoder = connector->new_encoder;
} else {
connector_state->crtc = NULL;
+ connector_state->best_encoder = NULL;
}
}
for_each_intel_crtc(dev, crtc) {
@@ -12011,11 +12467,6 @@
crtc->new_enabled ? "en" : "dis");
config->mode_changed = true;
}
-
- if (crtc->new_enabled)
- crtc->new_config = crtc->config;
- else
- crtc->new_config = NULL;
}
return 0;
@@ -12042,7 +12493,6 @@
}
crtc->new_enabled = false;
- crtc->new_config = NULL;
}
static int intel_crtc_set_config(struct drm_mode_set *set)
@@ -12140,10 +12590,10 @@
int vdisplay, hdisplay;
drm_crtc_get_hv_timing(set->mode, &hdisplay, &vdisplay);
- ret = primary->funcs->update_plane(primary, set->crtc, set->fb,
- 0, 0, hdisplay, vdisplay,
- set->x << 16, set->y << 16,
- hdisplay << 16, vdisplay << 16);
+ ret = drm_plane_helper_update(primary, set->crtc, set->fb,
+ 0, 0, hdisplay, vdisplay,
+ set->x << 16, set->y << 16,
+ hdisplay << 16, vdisplay << 16);
/*
* We need to make sure the primary plane is re-enabled if it
@@ -12428,16 +12878,21 @@
struct drm_rect *dest = &state->dst;
struct drm_rect *src = &state->src;
const struct drm_rect *clip = &state->clip;
+ bool can_position = false;
int ret;
crtc = crtc ? crtc : plane->crtc;
intel_crtc = to_intel_crtc(crtc);
+ if (INTEL_INFO(dev)->gen >= 9)
+ can_position = true;
+
ret = drm_plane_helper_check_update(plane, crtc, fb,
src, dest, clip,
DRM_PLANE_HELPER_NO_SCALING,
DRM_PLANE_HELPER_NO_SCALING,
- false, true, &state->visible);
+ can_position, true,
+ &state->visible);
if (ret)
return ret;
@@ -12627,8 +13082,8 @@
}
const struct drm_plane_funcs intel_plane_funcs = {
- .update_plane = drm_plane_helper_update,
- .disable_plane = drm_plane_helper_disable,
+ .update_plane = drm_atomic_helper_update_plane,
+ .disable_plane = drm_atomic_helper_disable_plane,
.destroy = intel_plane_destroy,
.set_property = drm_atomic_helper_plane_set_property,
.atomic_get_property = intel_plane_atomic_get_property,
@@ -12659,10 +13114,12 @@
primary->can_scale = false;
primary->max_downscale = 1;
+ state->scaler_id = -1;
primary->pipe = pipe;
primary->plane = pipe;
primary->check_plane = intel_check_primary_plane;
primary->commit_plane = intel_commit_primary_plane;
+ primary->ckey.flags = I915_SET_COLORKEY_NONE;
if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4)
primary->plane = !pipe;
@@ -12679,23 +13136,32 @@
intel_primary_formats, num_formats,
DRM_PLANE_TYPE_PRIMARY);
- if (INTEL_INFO(dev)->gen >= 4) {
- if (!dev->mode_config.rotation_property)
- dev->mode_config.rotation_property =
- drm_mode_create_rotation_property(dev,
- BIT(DRM_ROTATE_0) |
- BIT(DRM_ROTATE_180));
- if (dev->mode_config.rotation_property)
- drm_object_attach_property(&primary->base.base,
- dev->mode_config.rotation_property,
- state->base.rotation);
- }
+ if (INTEL_INFO(dev)->gen >= 4)
+ intel_create_rotation_property(dev, primary);
drm_plane_helper_add(&primary->base, &intel_plane_helper_funcs);
return &primary->base;
}
+void intel_create_rotation_property(struct drm_device *dev, struct intel_plane *plane)
+{
+ if (!dev->mode_config.rotation_property) {
+ unsigned long flags = BIT(DRM_ROTATE_0) |
+ BIT(DRM_ROTATE_180);
+
+ if (INTEL_INFO(dev)->gen >= 9)
+ flags |= BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270);
+
+ dev->mode_config.rotation_property =
+ drm_mode_create_rotation_property(dev, flags);
+ }
+ if (dev->mode_config.rotation_property)
+ drm_object_attach_property(&plane->base.base,
+ dev->mode_config.rotation_property,
+ plane->base.state->rotation);
+}
+
static int
intel_check_cursor_plane(struct drm_plane *plane,
struct intel_plane_state *state)
@@ -12813,6 +13279,7 @@
cursor->max_downscale = 1;
cursor->pipe = pipe;
cursor->plane = pipe;
+ state->scaler_id = -1;
cursor->check_plane = intel_check_cursor_plane;
cursor->commit_plane = intel_commit_cursor_plane;
@@ -12839,6 +13306,24 @@
return &cursor->base;
}
+static void skl_init_scalers(struct drm_device *dev, struct intel_crtc *intel_crtc,
+ struct intel_crtc_state *crtc_state)
+{
+ int i;
+ struct intel_scaler *intel_scaler;
+ struct intel_crtc_scaler_state *scaler_state = &crtc_state->scaler_state;
+
+ 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;
+ }
+
+ scaler_state->scaler_id = -1;
+}
+
static void intel_crtc_init(struct drm_device *dev, int pipe)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -12858,6 +13343,16 @@
intel_crtc_set_state(intel_crtc, crtc_state);
crtc_state->base.crtc = &intel_crtc->base;
+ /* initialize shared scalers */
+ if (INTEL_INFO(dev)->gen >= 9) {
+ if (pipe == PIPE_C)
+ intel_crtc->num_scalers = 1;
+ else
+ intel_crtc->num_scalers = SKL_NUM_SCALERS;
+
+ skl_init_scalers(dev, intel_crtc, crtc_state);
+ }
+
primary = intel_primary_plane_create(dev, pipe);
if (!primary)
goto fail;
@@ -13003,7 +13498,6 @@
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_encoder *encoder;
- struct drm_connector *connector;
bool dpd_is_edp = false;
intel_lvds_init(dev);
@@ -13148,39 +13642,6 @@
if (SUPPORTS_TV(dev))
intel_tv_init(dev);
- /*
- * FIXME: We don't have full atomic support yet, but we want to be
- * able to enable/test plane updates via the atomic interface in the
- * meantime. However as soon as we flip DRIVER_ATOMIC on, the DRM core
- * will take some atomic codepaths to lookup properties during
- * drmModeGetConnector() that unconditionally dereference
- * connector->state.
- *
- * We create a dummy connector state here for each connector to ensure
- * the DRM core doesn't try to dereference a NULL connector->state.
- * The actual connector properties will never be updated or contain
- * useful information, but since we're doing this specifically for
- * testing/debug of the plane operations (and only when a specific
- * kernel module option is given), that shouldn't really matter.
- *
- * We are also relying on these states to convert the legacy mode set
- * to use a drm_atomic_state struct. The states are kept consistent
- * with actual state, so that it is safe to rely on that instead of
- * the staged config.
- *
- * Once atomic support for crtc's + connectors lands, this loop should
- * be removed since we'll be setting up real connector state, which
- * will contain Intel-specific properties.
- */
- list_for_each_entry(connector,
- &dev->mode_config.connector_list,
- head) {
- if (!WARN_ON(connector->state)) {
- connector->state = kzalloc(sizeof(*connector->state),
- GFP_KERNEL);
- }
- }
-
intel_psr_init(dev);
for_each_intel_encoder(dev, encoder) {
@@ -13489,10 +13950,23 @@
}
/* Returns the core display clock speed */
- if (IS_VALLEYVIEW(dev))
+ if (IS_SKYLAKE(dev))
+ dev_priv->display.get_display_clock_speed =
+ skylake_get_display_clock_speed;
+ else if (IS_BROADWELL(dev))
+ dev_priv->display.get_display_clock_speed =
+ broadwell_get_display_clock_speed;
+ else if (IS_HASWELL(dev))
+ dev_priv->display.get_display_clock_speed =
+ haswell_get_display_clock_speed;
+ else if (IS_VALLEYVIEW(dev))
dev_priv->display.get_display_clock_speed =
valleyview_get_display_clock_speed;
- else if (IS_I945G(dev) || (IS_G33(dev) && !IS_PINEVIEW_M(dev)))
+ else if (IS_GEN5(dev))
+ 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)))
dev_priv->display.get_display_clock_speed =
i945_get_display_clock_speed;
else if (IS_I915G(dev))
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index b70e635..3ea68e1 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -696,15 +696,13 @@
{
struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
struct drm_device *dev = intel_dig_port->base.base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
if (index)
return 0;
if (intel_dig_port->port == PORT_A) {
- if (IS_GEN6(dev) || IS_GEN7(dev))
- return 200; /* SNB & IVB eDP input clock at 400Mhz */
- else
- return 225; /* eDP input clock at 450Mhz */
+ return DIV_ROUND_UP(dev_priv->display.get_display_clock_speed(dev), 2000);
} else {
return DIV_ROUND_UP(intel_pch_rawclk(dev), 2);
}
@@ -719,7 +717,7 @@
if (intel_dig_port->port == PORT_A) {
if (index)
return 0;
- return DIV_ROUND_CLOSEST(intel_ddi_get_cdclk_freq(dev_priv), 2000);
+ return DIV_ROUND_CLOSEST(dev_priv->display.get_display_clock_speed(dev), 2000);
} else if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
/* Workaround for non-ULT HSW */
switch (index) {
@@ -1353,6 +1351,14 @@
if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
adjusted_mode);
+
+ if (INTEL_INFO(dev)->gen >= 9) {
+ int ret;
+ ret = skl_update_scaler_users(intel_crtc, pipe_config, NULL, NULL, 0);
+ if (ret)
+ return ret;
+ }
+
if (!HAS_PCH_SPLIT(dev))
intel_gmch_panel_fitting(intel_crtc, pipe_config,
intel_connector->panel.fitting_mode);
@@ -3787,6 +3793,21 @@
dev_priv->psr.sink_support = true;
DRM_DEBUG_KMS("Detected EDP PSR Panel.\n");
}
+
+ if (INTEL_INFO(dev)->gen >= 9 &&
+ (intel_dp->psr_dpcd[0] & DP_PSR2_IS_SUPPORTED)) {
+ uint8_t frame_sync_cap;
+
+ dev_priv->psr.sink_support = true;
+ intel_dp_dpcd_read_wake(&intel_dp->aux,
+ DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP,
+ &frame_sync_cap, 1);
+ dev_priv->psr.aux_frame_sync = frame_sync_cap ? true : false;
+ /* PSR2 needs frame sync as well */
+ dev_priv->psr.psr2_support = dev_priv->psr.aux_frame_sync;
+ DRM_DEBUG_KMS("PSR2 %s on sink",
+ dev_priv->psr.psr2_support ? "supported" : "not supported");
+ }
}
/* Training Pattern 3 support, both source and sink */
@@ -5571,6 +5592,8 @@
I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd);
}
+ i915_debugfs_connector_add(connector);
+
return true;
}
@@ -5587,7 +5610,7 @@
if (!intel_dig_port)
return;
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector) {
kfree(intel_dig_port);
return;
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 5329c85..7335089 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -150,14 +150,14 @@
enum port port = intel_dig_port->port;
int ret;
uint32_t temp;
- struct intel_connector *found = NULL, *intel_connector;
+ struct intel_connector *found = NULL, *connector;
int slots;
struct drm_crtc *crtc = encoder->base.crtc;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- for_each_intel_connector(dev, intel_connector) {
- if (intel_connector->new_encoder == encoder) {
- found = intel_connector;
+ for_each_intel_connector(dev, connector) {
+ if (connector->base.state->best_encoder == &encoder->base) {
+ found = connector;
break;
}
}
@@ -415,7 +415,7 @@
struct drm_connector *connector;
int i;
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector)
return NULL;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 6036e3b..6a2ee0c 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -256,6 +256,26 @@
* enable/disable the primary plane
*/
bool hides_primary;
+
+ /*
+ * scaler_id
+ * = -1 : not using a scaler
+ * >= 0 : using a scalers
+ *
+ * plane requiring a scaler:
+ * - During check_plane, its bit is set in
+ * crtc_state->scaler_state.scaler_users by calling helper function
+ * update_scaler_users.
+ * - scaler_id indicates the scaler it got assigned.
+ *
+ * plane doesn't require a scaler:
+ * - this can happen when scaling is no more required or plane simply
+ * got disabled.
+ * - During check_plane, corresponding bit is reset in
+ * crtc_state->scaler_state.scaler_users by calling helper function
+ * update_scaler_users.
+ */
+ int scaler_id;
};
struct intel_initial_plane_config {
@@ -265,6 +285,49 @@
u32 base;
};
+#define SKL_MIN_SRC_W 8
+#define SKL_MAX_SRC_W 4096
+#define SKL_MIN_SRC_H 8
+#define SKL_MAX_SRC_H 2304
+#define SKL_MIN_DST_W 8
+#define SKL_MAX_DST_W 4096
+#define SKL_MIN_DST_H 8
+#define SKL_MAX_DST_H 2304
+
+struct intel_scaler {
+ int id;
+ int in_use;
+ uint32_t mode;
+};
+
+struct intel_crtc_scaler_state {
+#define SKL_NUM_SCALERS 2
+ struct intel_scaler scalers[SKL_NUM_SCALERS];
+
+ /*
+ * scaler_users: keeps track of users requesting scalers on this crtc.
+ *
+ * If a bit is set, a user is using a scaler.
+ * Here user can be a plane or crtc as defined below:
+ * bits 0-30 - plane (bit position is index from drm_plane_index)
+ * bit 31 - crtc
+ *
+ * Instead of creating a new index to cover planes and crtc, using
+ * existing drm_plane_index for planes which is well less than 31
+ * planes and bit 31 for crtc. This should be fine to cover all
+ * our platforms.
+ *
+ * intel_atomic_setup_scalers will setup available scalers to users
+ * requesting scalers. It will gracefully fail if request exceeds
+ * avilability.
+ */
+#define SKL_CRTC_INDEX 31
+ unsigned scaler_users;
+
+ /* scaler used by crtc for panel fitting purpose */
+ int scaler_id;
+};
+
struct intel_crtc_state {
struct drm_crtc_state base;
@@ -391,6 +454,8 @@
bool dp_encoder_is_mst;
int pbn;
+
+ struct intel_crtc_scaler_state scaler_state;
};
struct intel_pipe_wm {
@@ -471,7 +536,6 @@
struct intel_initial_plane_config plane_config;
struct intel_crtc_state *config;
- struct intel_crtc_state *new_config;
bool new_enabled;
/* reset counter value when the last flip was submitted */
@@ -493,6 +557,9 @@
struct intel_mmio_flip mmio_flip;
struct intel_crtc_atomic_commit atomic;
+
+ /* scalers available on this crtc */
+ int num_scalers;
};
struct intel_plane_wm_parameters {
@@ -855,7 +922,6 @@
void intel_ddi_init(struct drm_device *dev, enum port port);
enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder);
bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
-int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv);
void intel_ddi_pll_init(struct drm_device *dev);
void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc);
void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
@@ -930,6 +996,8 @@
void intel_crtc_control(struct drm_crtc *crtc, bool enable);
void intel_crtc_update_dpms(struct drm_crtc *crtc);
void intel_encoder_destroy(struct drm_encoder *encoder);
+int intel_connector_init(struct intel_connector *);
+struct intel_connector *intel_connector_alloc(void);
void intel_connector_dpms(struct drm_connector *, int mode);
bool intel_connector_get_hw_state(struct intel_connector *connector);
void intel_modeset_check_state(struct drm_device *dev);
@@ -998,6 +1066,12 @@
return rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270));
}
+unsigned int
+intel_tile_height(struct drm_device *dev, uint32_t bits_per_pixel,
+ uint64_t fb_modifier);
+void intel_create_rotation_property(struct drm_device *dev,
+ struct intel_plane *plane);
+
bool intel_wm_need_update(struct drm_plane *plane,
struct drm_plane_state *state);
@@ -1054,6 +1128,10 @@
struct intel_crtc_state *pipe_config);
void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc);
void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file);
+void skl_detach_scalers(struct intel_crtc *intel_crtc);
+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);
unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
struct drm_i915_gem_object *obj);
@@ -1264,7 +1342,10 @@
void gen6_rps_busy(struct drm_i915_private *dev_priv);
void gen6_rps_reset_ei(struct drm_i915_private *dev_priv);
void gen6_rps_idle(struct drm_i915_private *dev_priv);
-void gen6_rps_boost(struct drm_i915_private *dev_priv);
+void gen6_rps_boost(struct drm_i915_private *dev_priv,
+ struct drm_i915_file_private *file_priv);
+void intel_queue_rps_boost_for_request(struct drm_device *dev,
+ struct drm_i915_gem_request *rq);
void ilk_wm_get_hw_state(struct drm_device *dev);
void skl_wm_get_hw_state(struct drm_device *dev);
void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
@@ -1315,6 +1396,9 @@
return to_intel_crtc_state(crtc_state);
}
+int intel_atomic_setup_scalers(struct drm_device *dev,
+ struct intel_crtc *intel_crtc,
+ struct intel_crtc_state *crtc_state);
/* intel_atomic_plane.c */
struct intel_plane_state *intel_create_plane_state(struct drm_plane *plane);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 572251e..5196642 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -1007,7 +1007,7 @@
if (!intel_dsi)
return;
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector) {
kfree(intel_dsi);
return;
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 4ccd6c3..7c9f852 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -80,7 +80,7 @@
.name = "ch7017",
.dvo_reg = DVOC,
.slave_addr = 0x75,
- .gpio = GMBUS_PORT_DPB,
+ .gpio = GMBUS_PIN_DPB,
.dev_ops = &ch7017_ops,
},
{
@@ -364,7 +364,7 @@
* that's not the case.
*/
intel_ddc_get_modes(connector,
- intel_gmbus_get_adapter(dev_priv, GMBUS_PORT_DPC));
+ intel_gmbus_get_adapter(dev_priv, GMBUS_PIN_DPC));
if (!list_empty(&connector->probed_modes))
return 1;
@@ -469,7 +469,7 @@
if (!intel_dvo)
return;
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector) {
kfree(intel_dvo);
return;
@@ -495,17 +495,19 @@
struct i2c_adapter *i2c;
int gpio;
bool dvoinit;
+ enum pipe pipe;
+ uint32_t dpll[2];
/* Allow the I2C driver info to specify the GPIO to be used in
* special cases, but otherwise default to what's defined
* in the spec.
*/
- if (intel_gmbus_is_port_valid(dvo->gpio))
+ if (intel_gmbus_is_valid_pin(dev_priv, dvo->gpio))
gpio = dvo->gpio;
else if (dvo->type == INTEL_DVO_CHIP_LVDS)
- gpio = GMBUS_PORT_SSC;
+ gpio = GMBUS_PIN_SSC;
else
- gpio = GMBUS_PORT_DPB;
+ gpio = GMBUS_PIN_DPB;
/* Set up the I2C bus necessary for the chip we're probing.
* It appears that everything is on GPIOE except for panels
@@ -520,8 +522,23 @@
*/
intel_gmbus_force_bit(i2c, true);
+ /* ns2501 requires the DVO 2x clock before it will
+ * respond to i2c accesses, so make sure we have
+ * have the clock enabled before we attempt to
+ * initialize the device.
+ */
+ for_each_pipe(dev_priv, pipe) {
+ dpll[pipe] = I915_READ(DPLL(pipe));
+ I915_WRITE(DPLL(pipe), dpll[pipe] | DPLL_DVO_2X_MODE);
+ }
+
dvoinit = dvo->dev_ops->init(&intel_dvo->dev, i2c);
+ /* restore the DVO 2x clock state to original */
+ for_each_pipe(dev_priv, pipe) {
+ I915_WRITE(DPLL(pipe), dpll[pipe]);
+ }
+
intel_gmbus_force_bit(i2c, false);
if (!dvoinit)
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index cacbafd..02252d9 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1681,18 +1681,18 @@
switch (port) {
case PORT_B:
- intel_hdmi->ddc_bus = GMBUS_PORT_DPB;
+ intel_hdmi->ddc_bus = GMBUS_PIN_DPB;
intel_encoder->hpd_pin = HPD_PORT_B;
break;
case PORT_C:
- intel_hdmi->ddc_bus = GMBUS_PORT_DPC;
+ intel_hdmi->ddc_bus = GMBUS_PIN_DPC;
intel_encoder->hpd_pin = HPD_PORT_C;
break;
case PORT_D:
if (IS_CHERRYVIEW(dev))
- intel_hdmi->ddc_bus = GMBUS_PORT_DPD_CHV;
+ intel_hdmi->ddc_bus = GMBUS_PIN_DPD_CHV;
else
- intel_hdmi->ddc_bus = GMBUS_PORT_DPD;
+ intel_hdmi->ddc_bus = GMBUS_PIN_DPD;
intel_encoder->hpd_pin = HPD_PORT_D;
break;
case PORT_A:
@@ -1755,7 +1755,7 @@
if (!intel_dig_port)
return;
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector) {
kfree(intel_dig_port);
return;
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index b31088a..ec9cc8c 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -34,20 +34,27 @@
#include <drm/i915_drm.h>
#include "i915_drv.h"
-struct gmbus_port {
+struct gmbus_pin {
const char *name;
int reg;
};
-static const struct gmbus_port gmbus_ports[] = {
- { "ssc", GPIOB },
- { "vga", GPIOA },
- { "panel", GPIOC },
- { "dpc", GPIOD },
- { "dpb", GPIOE },
- { "dpd", GPIOF },
+/* Map gmbus pin pairs to names and registers. */
+static const struct gmbus_pin gmbus_pins[] = {
+ [GMBUS_PIN_SSC] = { "ssc", GPIOB },
+ [GMBUS_PIN_VGADDC] = { "vga", GPIOA },
+ [GMBUS_PIN_PANEL] = { "panel", GPIOC },
+ [GMBUS_PIN_DPC] = { "dpc", GPIOD },
+ [GMBUS_PIN_DPB] = { "dpb", GPIOE },
+ [GMBUS_PIN_DPD] = { "dpd", GPIOF },
};
+bool intel_gmbus_is_valid_pin(struct drm_i915_private *dev_priv,
+ unsigned int pin)
+{
+ return pin < ARRAY_SIZE(gmbus_pins) && gmbus_pins[pin].reg;
+}
+
/* Intel GPIO access functions */
#define I2C_RISEFALL_TIME 10
@@ -182,15 +189,14 @@
}
static void
-intel_gpio_setup(struct intel_gmbus *bus, u32 pin)
+intel_gpio_setup(struct intel_gmbus *bus, unsigned int pin)
{
struct drm_i915_private *dev_priv = bus->dev_priv;
struct i2c_algo_bit_data *algo;
algo = &bus->bit_algo;
- /* -1 to map pin pair to gmbus index */
- bus->gpio_reg = dev_priv->gpio_mmio_base + gmbus_ports[pin - 1].reg;
+ bus->gpio_reg = dev_priv->gpio_mmio_base + gmbus_pins[pin].reg;
bus->adapter.algo_data = algo;
algo->setsda = set_data;
@@ -517,7 +523,9 @@
int intel_setup_gmbus(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- int ret, i;
+ struct intel_gmbus *bus;
+ unsigned int pin;
+ int ret;
if (HAS_PCH_NOP(dev))
return 0;
@@ -531,16 +539,18 @@
mutex_init(&dev_priv->gmbus_mutex);
init_waitqueue_head(&dev_priv->gmbus_wait_queue);
- for (i = 0; i < GMBUS_NUM_PORTS; i++) {
- struct intel_gmbus *bus = &dev_priv->gmbus[i];
- u32 port = i + 1; /* +1 to map gmbus index to pin pair */
+ for (pin = 0; pin < ARRAY_SIZE(dev_priv->gmbus); pin++) {
+ if (!intel_gmbus_is_valid_pin(dev_priv, pin))
+ continue;
+
+ bus = &dev_priv->gmbus[pin];
bus->adapter.owner = THIS_MODULE;
bus->adapter.class = I2C_CLASS_DDC;
snprintf(bus->adapter.name,
sizeof(bus->adapter.name),
"i915 gmbus %s",
- gmbus_ports[i].name);
+ gmbus_pins[pin].name);
bus->adapter.dev.parent = &dev->pdev->dev;
bus->dev_priv = dev_priv;
@@ -548,13 +558,13 @@
bus->adapter.algo = &gmbus_algorithm;
/* By default use a conservative clock rate */
- bus->reg0 = port | GMBUS_RATE_100KHZ;
+ bus->reg0 = pin | GMBUS_RATE_100KHZ;
/* gmbus seems to be broken on i830 */
if (IS_I830(dev))
bus->force_bit = 1;
- intel_gpio_setup(bus, port);
+ intel_gpio_setup(bus, pin);
ret = i2c_add_adapter(&bus->adapter);
if (ret)
@@ -566,20 +576,23 @@
return 0;
err:
- while (--i) {
- struct intel_gmbus *bus = &dev_priv->gmbus[i];
+ while (--pin) {
+ if (!intel_gmbus_is_valid_pin(dev_priv, pin))
+ continue;
+
+ bus = &dev_priv->gmbus[pin];
i2c_del_adapter(&bus->adapter);
}
return ret;
}
struct i2c_adapter *intel_gmbus_get_adapter(struct drm_i915_private *dev_priv,
- unsigned port)
+ unsigned int pin)
{
- WARN_ON(!intel_gmbus_is_port_valid(port));
- /* -1 to map pin pair to gmbus index */
- return (intel_gmbus_is_port_valid(port)) ?
- &dev_priv->gmbus[port - 1].adapter : NULL;
+ if (WARN_ON(!intel_gmbus_is_valid_pin(dev_priv, pin)))
+ return NULL;
+
+ return &dev_priv->gmbus[pin].adapter;
}
void intel_gmbus_set_speed(struct i2c_adapter *adapter, int speed)
@@ -602,10 +615,14 @@
void intel_teardown_gmbus(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- int i;
+ struct intel_gmbus *bus;
+ unsigned int pin;
- for (i = 0; i < GMBUS_NUM_PORTS; i++) {
- struct intel_gmbus *bus = &dev_priv->gmbus[i];
+ for (pin = 0; pin < ARRAY_SIZE(dev_priv->gmbus); pin++) {
+ if (!intel_gmbus_is_valid_pin(dev_priv, pin))
+ continue;
+
+ bus = &dev_priv->gmbus[pin];
i2c_del_adapter(&bus->adapter);
}
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 71aeeb3..a798d75 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -188,6 +188,15 @@
#define GEN8_CTX_FORCE_RESTORE (1<<2)
#define GEN8_CTX_L3LLC_COHERENT (1<<5)
#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; \
+ reg_state[CTX_PDP ## n ## _UDW+1] = upper_32_bits(_addr); \
+ reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
+}
+
enum {
ADVANCED_CONTEXT = 0,
LEGACY_CONTEXT,
@@ -265,7 +274,8 @@
desc = GEN8_CTX_VALID;
desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT;
- desc |= GEN8_CTX_L3LLC_COHERENT;
+ if (IS_GEN8(ctx_obj->base.dev))
+ desc |= GEN8_CTX_L3LLC_COHERENT;
desc |= GEN8_CTX_PRIVILEGE;
desc |= lrca;
desc |= (u64)intel_execlists_ctx_id(ctx_obj) << GEN8_CTX_ID_SHIFT;
@@ -305,21 +315,24 @@
desc[3] = (u32)(temp >> 32);
desc[2] = (u32)temp;
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
- I915_WRITE(RING_ELSP(ring), desc[1]);
- I915_WRITE(RING_ELSP(ring), desc[0]);
- I915_WRITE(RING_ELSP(ring), desc[3]);
+ 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]);
/* The context is automatically loaded after the following */
- I915_WRITE(RING_ELSP(ring), desc[2]);
+ I915_WRITE_FW(RING_ELSP(ring), desc[2]);
/* ELSP is a wo register, so use another nearby reg for posting instead */
- POSTING_READ(RING_EXECLIST_STATUS(ring));
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+ 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)
{
struct page *page;
@@ -331,6 +344,16 @@
reg_state[CTX_RING_TAIL+1] = tail;
reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
+ /* True PPGTT with dynamic page allocation: update PDP registers and
+ * point the unallocated PDPs to the scratch page
+ */
+ if (ppgtt) {
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
+ }
+
kunmap_atomic(reg_state);
return 0;
@@ -349,7 +372,7 @@
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, tail0);
+ execlists_update_context(ctx_obj0, ringbuf0->obj, to0->ppgtt, tail0);
if (to1) {
ringbuf1 = to1->engine[ring->id].ringbuf;
@@ -358,7 +381,7 @@
WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));
WARN_ON(!i915_gem_obj_is_pinned(ringbuf1->obj));
- execlists_update_context(ctx_obj1, ringbuf1->obj, tail1);
+ execlists_update_context(ctx_obj1, ringbuf1->obj, to1->ppgtt, tail1);
}
execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
@@ -500,8 +523,6 @@
struct drm_i915_gem_request *request)
{
struct drm_i915_gem_request *cursor;
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
- unsigned long flags;
int num_elements = 0;
if (to != ring->default_context)
@@ -518,7 +539,6 @@
request->ring = ring;
request->ctx = to;
kref_init(&request->ref);
- request->uniq = dev_priv->request_uniq++;
i915_gem_context_reference(request->ctx);
} else {
i915_gem_request_reference(request);
@@ -526,9 +546,7 @@
}
request->tail = tail;
- intel_runtime_pm_get(dev_priv);
-
- spin_lock_irqsave(&ring->execlist_lock, flags);
+ spin_lock_irq(&ring->execlist_lock);
list_for_each_entry(cursor, &ring->execlist_queue, execlist_link)
if (++num_elements > 2)
@@ -554,7 +572,7 @@
if (num_elements == 0)
execlists_context_unqueue(ring);
- spin_unlock_irqrestore(&ring->execlist_lock, flags);
+ spin_unlock_irq(&ring->execlist_lock);
return 0;
}
@@ -611,6 +629,173 @@
return logical_ring_invalidate_all_caches(ringbuf, ctx);
}
+int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request,
+ struct intel_context *ctx)
+{
+ int ret;
+
+ if (ctx != request->ring->default_context) {
+ ret = intel_lr_context_pin(request->ring, ctx);
+ 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,
+ int bytes)
+{
+ struct intel_engine_cs *ring = ringbuf->ring;
+ struct drm_i915_gem_request *request;
+ int ret, new_space;
+
+ if (intel_ring_space(ringbuf) >= bytes)
+ return 0;
+
+ list_for_each_entry(request, &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.
+ */
+ struct intel_context *ctx = request->ctx;
+ if (ctx->engine[ring->id].ringbuf != ringbuf)
+ continue;
+
+ /* Would completion of this request free enough space? */
+ new_space = __intel_ring_space(request->postfix, ringbuf->tail,
+ ringbuf->size);
+ if (new_space >= bytes)
+ break;
+ }
+
+ if (WARN_ON(&request->list == &ring->request_list))
+ return -ENOSPC;
+
+ ret = i915_wait_request(request);
+ if (ret)
+ return ret;
+
+ i915_gem_retire_requests_ring(ring);
+
+ WARN_ON(intel_ring_space(ringbuf) < new_space);
+
+ return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
+}
+
+/*
+ * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
+ * @ringbuf: Logical Ringbuffer to advance.
+ *
+ * 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
+ * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
+ * 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)
+{
+ struct intel_engine_cs *ring = ringbuf->ring;
+
+ intel_logical_ring_advance(ringbuf);
+
+ if (intel_ring_stopped(ring))
+ return;
+
+ execlists_context_queue(ring, ctx, ringbuf->tail, request);
+}
+
+static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
+ struct intel_context *ctx)
+{
+ 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--)
+ iowrite32(MI_NOOP, virt++);
+
+ 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)
+{
+ int ret;
+
+ if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
+ ret = logical_ring_wrap_buffer(ringbuf, ctx);
+ if (unlikely(ret))
+ return ret;
+ }
+
+ if (unlikely(ringbuf->space < bytes)) {
+ ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
+ if (unlikely(ret))
+ return ret;
+ }
+
+ return 0;
+}
+
+/**
+ * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
+ *
+ * @ringbuf: Logical ringbuffer.
+ * @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
+ * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
+ * and also preallocates a request (every workload submission is still mediated through
+ * requests, same as it did with legacy ringbuffer submission).
+ *
+ * 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)
+{
+ struct intel_engine_cs *ring = ringbuf->ring;
+ struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int ret;
+
+ 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);
+ if (ret)
+ return ret;
+
+ ringbuf->space -= num_dwords * sizeof(uint32_t);
+ return 0;
+}
+
/**
* execlists_submission() - submit a batchbuffer for execution, Execlists style
* @dev: DRM device.
@@ -722,8 +907,6 @@
void intel_execlists_retire_requests(struct intel_engine_cs *ring)
{
struct drm_i915_gem_request *req, *tmp;
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
- unsigned long flags;
struct list_head retired_list;
WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
@@ -731,9 +914,9 @@
return;
INIT_LIST_HEAD(&retired_list);
- spin_lock_irqsave(&ring->execlist_lock, flags);
+ spin_lock_irq(&ring->execlist_lock);
list_replace_init(&ring->execlist_retired_req_list, &retired_list);
- spin_unlock_irqrestore(&ring->execlist_lock, flags);
+ spin_unlock_irq(&ring->execlist_lock);
list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {
struct intel_context *ctx = req->ctx;
@@ -742,7 +925,6 @@
if (ctx_obj && (ctx != ring->default_context))
intel_lr_context_unpin(ring, ctx);
- intel_runtime_pm_put(dev_priv);
list_del(&req->execlist_link);
i915_gem_request_unreference(req);
}
@@ -787,30 +969,6 @@
return 0;
}
-/*
- * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
- * @ringbuf: Logical Ringbuffer to advance.
- *
- * 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
- * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
- * 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)
-{
- struct intel_engine_cs *ring = ringbuf->ring;
-
- intel_logical_ring_advance(ringbuf);
-
- if (intel_ring_stopped(ring))
- return;
-
- execlists_context_queue(ring, ctx, ringbuf->tail, request);
-}
-
static int intel_lr_context_pin(struct intel_engine_cs *ring,
struct intel_context *ctx)
{
@@ -855,219 +1013,6 @@
}
}
-static int logical_ring_alloc_request(struct intel_engine_cs *ring,
- struct intel_context *ctx)
-{
- struct drm_i915_gem_request *request;
- struct drm_i915_private *dev_private = ring->dev->dev_private;
- int ret;
-
- if (ring->outstanding_lazy_request)
- return 0;
-
- request = kzalloc(sizeof(*request), GFP_KERNEL);
- if (request == NULL)
- return -ENOMEM;
-
- if (ctx != ring->default_context) {
- ret = intel_lr_context_pin(ring, ctx);
- if (ret) {
- kfree(request);
- return ret;
- }
- }
-
- kref_init(&request->ref);
- request->ring = ring;
- request->uniq = dev_private->request_uniq++;
-
- ret = i915_gem_get_seqno(ring->dev, &request->seqno);
- if (ret) {
- intel_lr_context_unpin(ring, ctx);
- kfree(request);
- return ret;
- }
-
- request->ctx = ctx;
- i915_gem_context_reference(request->ctx);
- request->ringbuf = ctx->engine[ring->id].ringbuf;
-
- ring->outstanding_lazy_request = request;
- return 0;
-}
-
-static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
- int bytes)
-{
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_i915_gem_request *request;
- int ret;
-
- if (intel_ring_space(ringbuf) >= bytes)
- return 0;
-
- list_for_each_entry(request, &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.
- */
- struct intel_context *ctx = request->ctx;
- if (ctx->engine[ring->id].ringbuf != ringbuf)
- continue;
-
- /* Would completion of this request free enough space? */
- if (__intel_ring_space(request->tail, ringbuf->tail,
- ringbuf->size) >= bytes) {
- break;
- }
- }
-
- if (&request->list == &ring->request_list)
- return -ENOSPC;
-
- ret = i915_wait_request(request);
- if (ret)
- return ret;
-
- i915_gem_retire_requests_ring(ring);
-
- return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
-}
-
-static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- int bytes)
-{
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_device *dev = ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- unsigned long end;
- int ret;
-
- ret = logical_ring_wait_request(ringbuf, bytes);
- if (ret != -ENOSPC)
- return ret;
-
- /* Force the context submission in case we have been skipping it */
- intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
-
- /* With GEM the hangcheck timer should kick us out of the loop,
- * leaving it early runs the risk of corrupting GEM state (due
- * to running on almost untested codepaths). But on resume
- * timers don't work yet, so prevent a complete hang in that
- * case by choosing an insanely large timeout. */
- end = jiffies + 60 * HZ;
-
- ret = 0;
- do {
- if (intel_ring_space(ringbuf) >= bytes)
- break;
-
- msleep(1);
-
- if (dev_priv->mm.interruptible && signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
-
- ret = i915_gem_check_wedge(&dev_priv->gpu_error,
- dev_priv->mm.interruptible);
- if (ret)
- break;
-
- if (time_after(jiffies, end)) {
- ret = -EBUSY;
- break;
- }
- } while (1);
-
- return ret;
-}
-
-static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
-{
- 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--)
- iowrite32(MI_NOOP, virt++);
-
- 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)
-{
- int ret;
-
- if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
- ret = logical_ring_wrap_buffer(ringbuf, ctx);
- if (unlikely(ret))
- return ret;
- }
-
- if (unlikely(ringbuf->space < bytes)) {
- ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
- if (unlikely(ret))
- return ret;
- }
-
- return 0;
-}
-
-/**
- * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
- *
- * @ringbuf: Logical ringbuffer.
- * @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
- * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
- * and also preallocates a request (every workload submission is still mediated through
- * requests, same as it did with legacy ringbuffer submission).
- *
- * Return: non-zero if the ringbuffer is not ready to be written to.
- */
-int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, 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;
- int ret;
-
- 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 = logical_ring_alloc_request(ring, ctx);
- if (ret)
- return ret;
-
- ringbuf->space -= num_dwords * sizeof(uint32_t);
- return 0;
-}
-
static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
struct intel_context *ctx)
{
@@ -1421,6 +1366,7 @@
ring->cleanup(ring);
i915_cmd_parser_fini_ring(ring);
+ i915_gem_batch_pool_fini(&ring->batch_pool);
if (ring->status_page.obj) {
kunmap(sg_page(ring->status_page.obj->pages->sgl));
@@ -1438,6 +1384,7 @@
ring->dev = dev;
INIT_LIST_HEAD(&ring->active_list);
INIT_LIST_HEAD(&ring->request_list);
+ i915_gem_batch_pool_init(dev, &ring->batch_pool);
init_waitqueue_head(&ring->irq_queue);
INIT_LIST_HEAD(&ring->execlist_queue);
@@ -1790,14 +1737,14 @@
reg_state[CTX_PDP1_LDW] = GEN8_RING_PDP_LDW(ring, 1);
reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
- reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[3]->daddr);
- reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[3]->daddr);
- reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[2]->daddr);
- reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[2]->daddr);
- reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[1]->daddr);
- reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[1]->daddr);
- reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[0]->daddr);
- reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[0]->daddr);
+
+ /* With dynamic page allocation, PDPs may not be allocated at this point,
+ * Point the unallocated PDPs to the scratch page
+ */
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
if (ring->id == RCS) {
reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
reg_state[CTX_R_PWR_CLK_STATE] = GEN8_R_PWR_CLK_STATE;
@@ -1914,7 +1861,7 @@
context_size = round_up(get_lr_context_size(ring), 4096);
- ctx_obj = i915_gem_alloc_context_obj(dev, context_size);
+ ctx_obj = i915_gem_alloc_object(dev, context_size);
if (IS_ERR(ctx_obj)) {
ret = PTR_ERR(ctx_obj);
DRM_DEBUG_DRIVER("Alloc LRC backing obj failed: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index adb731e4..04d3a6d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -36,6 +36,8 @@
#define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0)
/* Logical Rings */
+int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request,
+ struct intel_context *ctx);
void intel_logical_ring_stop(struct intel_engine_cs *ring);
void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
int intel_logical_rings_init(struct drm_device *dev);
@@ -63,9 +65,6 @@
iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
ringbuf->tail += 4;
}
-int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- int num_dwords);
/* Logical Ring Contexts */
void intel_lr_context_free(struct intel_context *ctx);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 06d2da3..9a9df0f 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -781,7 +781,7 @@
child->device_type != DEVICE_TYPE_LFP)
continue;
- if (intel_gmbus_is_port_valid(child->i2c_pin))
+ if (intel_gmbus_is_valid_pin(dev_priv, child->i2c_pin))
*i2c_pin = child->i2c_pin;
/* However, we cannot trust the BIOS writers to populate
@@ -921,7 +921,7 @@
if (dmi_check_system(intel_no_lvds))
return;
- pin = GMBUS_PORT_PANEL;
+ pin = GMBUS_PIN_PANEL;
if (!lvds_is_present_in_vbt(dev, &pin)) {
DRM_DEBUG_KMS("LVDS is not present in VBT\n");
return;
@@ -946,6 +946,12 @@
return;
}
+ if (intel_connector_init(&lvds_connector->base) < 0) {
+ kfree(lvds_connector);
+ kfree(lvds_encoder);
+ return;
+ }
+
lvds_encoder->attached_connector = lvds_connector;
intel_encoder = &lvds_encoder->base;
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index dd92122..5fd2d5a 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -172,10 +172,11 @@
struct intel_crtc *crtc;
struct drm_i915_gem_object *vid_bo;
struct drm_i915_gem_object *old_vid_bo;
- int active;
- int pfit_active;
+ bool active;
+ bool pfit_active;
u32 pfit_vscale_ratio; /* shifted-point number, (1<<12) == 1.0 */
- u32 color_key;
+ u32 color_key:24;
+ u32 color_key_enabled:1;
u32 brightness, contrast, saturation;
u32 old_xscale, old_yscale;
/* register access */
@@ -216,7 +217,7 @@
struct intel_engine_cs *ring = &dev_priv->ring[RCS];
int ret;
- BUG_ON(overlay->last_flip_req);
+ WARN_ON(overlay->last_flip_req);
i915_gem_request_assign(&overlay->last_flip_req,
ring->outstanding_lazy_request);
ret = i915_add_request(ring);
@@ -241,15 +242,15 @@
struct intel_engine_cs *ring = &dev_priv->ring[RCS];
int ret;
- BUG_ON(overlay->active);
- overlay->active = 1;
-
+ WARN_ON(overlay->active);
WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
ret = intel_ring_begin(ring, 4);
if (ret)
return ret;
+ overlay->active = true;
+
intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_ON);
intel_ring_emit(ring, overlay->flip_addr | OFC_UPDATE);
intel_ring_emit(ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
@@ -270,7 +271,7 @@
u32 tmp;
int ret;
- BUG_ON(!overlay->active);
+ WARN_ON(!overlay->active);
if (load_polyphase_filter)
flip_addr |= OFC_UPDATE;
@@ -309,7 +310,8 @@
struct drm_i915_gem_object *obj = overlay->vid_bo;
/* never have the overlay hw on without showing a frame */
- BUG_ON(!overlay->vid_bo);
+ if (WARN_ON(!obj))
+ return;
i915_gem_object_ggtt_unpin(obj);
drm_gem_object_unreference(&obj->base);
@@ -317,7 +319,7 @@
overlay->crtc->overlay = NULL;
overlay->crtc = NULL;
- overlay->active = 0;
+ overlay->active = false;
}
/* overlay needs to be disabled in OCMD reg */
@@ -329,7 +331,7 @@
u32 flip_addr = overlay->flip_addr;
int ret;
- BUG_ON(!overlay->active);
+ WARN_ON(!overlay->active);
/* According to intel docs the overlay hw may hang (when switching
* off) without loading the filter coeffs. It is however unclear whether
@@ -629,31 +631,36 @@
struct overlay_registers __iomem *regs)
{
u32 key = overlay->color_key;
+ u32 flags;
+
+ flags = 0;
+ if (overlay->color_key_enabled)
+ flags |= DST_KEY_ENABLE;
switch (overlay->crtc->base.primary->fb->bits_per_pixel) {
case 8:
- iowrite32(0, ®s->DCLRKV);
- iowrite32(CLK_RGB8I_MASK | DST_KEY_ENABLE, ®s->DCLRKM);
+ key = 0;
+ flags |= CLK_RGB8I_MASK;
break;
case 16:
if (overlay->crtc->base.primary->fb->depth == 15) {
- iowrite32(RGB15_TO_COLORKEY(key), ®s->DCLRKV);
- iowrite32(CLK_RGB15_MASK | DST_KEY_ENABLE,
- ®s->DCLRKM);
+ key = RGB15_TO_COLORKEY(key);
+ flags |= CLK_RGB15_MASK;
} else {
- iowrite32(RGB16_TO_COLORKEY(key), ®s->DCLRKV);
- iowrite32(CLK_RGB16_MASK | DST_KEY_ENABLE,
- ®s->DCLRKM);
+ key = RGB16_TO_COLORKEY(key);
+ flags |= CLK_RGB16_MASK;
}
break;
case 24:
case 32:
- iowrite32(key, ®s->DCLRKV);
- iowrite32(CLK_RGB24_MASK | DST_KEY_ENABLE, ®s->DCLRKM);
+ flags |= CLK_RGB24_MASK;
break;
}
+
+ iowrite32(key, ®s->DCLRKV);
+ iowrite32(flags, ®s->DCLRKM);
}
static u32 overlay_cmd_reg(struct put_image_params *params)
@@ -712,9 +719,8 @@
u32 swidth, swidthsw, sheight, ostride;
enum pipe pipe = overlay->crtc->pipe;
- BUG_ON(!mutex_is_locked(&dev->struct_mutex));
- BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
- BUG_ON(!overlay);
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+ WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
ret = intel_overlay_release_old_vid(overlay);
if (ret != 0)
@@ -824,8 +830,8 @@
struct drm_device *dev = overlay->dev;
int ret;
- BUG_ON(!mutex_is_locked(&dev->struct_mutex));
- BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+ WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
ret = intel_overlay_recover_from_interrupt(overlay);
if (ret != 0)
@@ -1131,10 +1137,10 @@
/* line too wide, i.e. one-line-mode */
if (mode->hdisplay > 1024 &&
intel_panel_fitter_pipe(dev) == crtc->pipe) {
- overlay->pfit_active = 1;
+ overlay->pfit_active = true;
update_pfit_vscale_ratio(overlay);
} else
- overlay->pfit_active = 0;
+ overlay->pfit_active = false;
}
ret = check_overlay_dst(overlay, put_image_rec);
@@ -1329,6 +1335,7 @@
I915_WRITE(OGAMC5, attrs->gamma5);
}
}
+ overlay->color_key_enabled = (attrs->flags & I915_OVERLAY_DISABLE_DEST_COLORKEY) == 0;
ret = 0;
out_unlock:
@@ -1392,6 +1399,7 @@
/* init all values */
overlay->color_key = 0x0101fe;
+ overlay->color_key_enabled = true;
overlay->brightness = -19;
overlay->contrast = 75;
overlay->saturation = 146;
@@ -1432,7 +1440,7 @@
/* The bo's should be free'd by the generic code already.
* Furthermore modesetting teardown happens beforehand so the
* hardware should be off already */
- BUG_ON(dev_priv->overlay->active);
+ WARN_ON(dev_priv->overlay->active);
drm_gem_object_unreference_unlocked(&dev_priv->overlay->reg_bo->base);
kfree(dev_priv->overlay);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4724638..a80bfd5 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -67,7 +67,7 @@
gen9_init_clock_gating(dev);
- if (INTEL_REVID(dev) == SKL_REVID_A0) {
+ if (INTEL_REVID(dev) <= SKL_REVID_B0) {
/*
* WaDisableSDEUnitClockGating:skl
* WaSetGAPSunitClckGateDisable:skl
@@ -75,6 +75,10 @@
I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
GEN8_GAPSUNIT_CLOCK_GATE_DISABLE |
GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
+ /* WaDisableVFUnitClockGating:skl */
+ I915_WRITE(GEN6_UCGCTL2, I915_READ(GEN6_UCGCTL2) |
+ GEN6_VFUNIT_CLOCK_GATE_DISABLE);
}
if (INTEL_REVID(dev) <= SKL_REVID_D0) {
@@ -1812,7 +1816,7 @@
linetime = DIV_ROUND_CLOSEST(mode->crtc_htotal * 1000 * 8,
mode->crtc_clock);
ips_linetime = DIV_ROUND_CLOSEST(mode->crtc_htotal * 1000 * 8,
- intel_ddi_get_cdclk_freq(dev_priv));
+ dev_priv->display.get_display_clock_speed(dev_priv->dev));
return PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
PIPE_WM_LINETIME_TIME(linetime);
@@ -3202,7 +3206,7 @@
{
struct drm_device *dev = dev_priv->dev;
struct skl_ddb_allocation *cur_ddb, *new_ddb;
- bool reallocated[I915_MAX_PIPES] = {false, false, false};
+ bool reallocated[I915_MAX_PIPES] = {};
struct intel_crtc *crtc;
enum pipe pipe;
@@ -3954,6 +3958,8 @@
GEN6_RP_DOWN_IDLE_AVG);
dev_priv->rps.power = new_power;
+ dev_priv->rps.up_threshold = threshold_up;
+ dev_priv->rps.down_threshold = threshold_down;
dev_priv->rps.last_adj = 0;
}
@@ -4025,8 +4031,11 @@
"Odd GPU freq value\n"))
val &= ~1;
- if (val != dev_priv->rps.cur_freq)
+ if (val != dev_priv->rps.cur_freq) {
vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+ if (!IS_CHERRYVIEW(dev_priv))
+ gen6_set_rps_thresholds(dev_priv, val);
+ }
I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
@@ -4075,6 +4084,7 @@
& GENFREQSTATUS) == 0, 100))
DRM_ERROR("timed out waiting for Punit\n");
+ gen6_set_rps_thresholds(dev_priv, val);
vlv_force_gfx_clock(dev_priv, false);
I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
@@ -4105,10 +4115,14 @@
dev_priv->rps.last_adj = 0;
I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
}
+
+ while (!list_empty(&dev_priv->rps.clients))
+ list_del_init(dev_priv->rps.clients.next);
mutex_unlock(&dev_priv->rps.hw_lock);
}
-void gen6_rps_boost(struct drm_i915_private *dev_priv)
+void gen6_rps_boost(struct drm_i915_private *dev_priv,
+ struct drm_i915_file_private *file_priv)
{
u32 val;
@@ -4116,9 +4130,16 @@
val = dev_priv->rps.max_freq_softlimit;
if (dev_priv->rps.enabled &&
dev_priv->mm.busy &&
- dev_priv->rps.cur_freq < val) {
+ dev_priv->rps.cur_freq < val &&
+ (file_priv == NULL || list_empty(&file_priv->rps_boost))) {
intel_set_rps(dev_priv->dev, val);
dev_priv->rps.last_adj = 0;
+
+ if (file_priv != NULL) {
+ list_add(&file_priv->rps_boost, &dev_priv->rps.clients);
+ file_priv->rps_boosts++;
+ } else
+ dev_priv->rps.boosts++;
}
mutex_unlock(&dev_priv->rps.hw_lock);
}
@@ -4349,8 +4370,13 @@
GEN6_RC_CTL_EI_MODE(1) |
rc6_mask);
- /* 3b: Enable Coarse Power Gating only when RC6 is enabled */
- I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? 3 : 0);
+ /*
+ * 3b: Enable Coarse Power Gating only when RC6 is enabled.
+ * WaDisableRenderPowerGating:skl,bxt - Render PG need to be disabled with RC6.
+ */
+ I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
+ GEN9_MEDIA_PG_ENABLE : 0);
+
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
@@ -6791,6 +6817,41 @@
return val / GT_FREQUENCY_MULTIPLIER;
}
+struct request_boost {
+ struct work_struct work;
+ struct drm_i915_gem_request *rq;
+};
+
+static void __intel_rps_boost_work(struct work_struct *work)
+{
+ struct request_boost *boost = container_of(work, struct request_boost, work);
+
+ if (!i915_gem_request_completed(boost->rq, true))
+ gen6_rps_boost(to_i915(boost->rq->ring->dev), NULL);
+
+ i915_gem_request_unreference__unlocked(boost->rq);
+ kfree(boost);
+}
+
+void intel_queue_rps_boost_for_request(struct drm_device *dev,
+ struct drm_i915_gem_request *rq)
+{
+ struct request_boost *boost;
+
+ if (rq == NULL || INTEL_INFO(dev)->gen < 6)
+ return;
+
+ boost = kmalloc(sizeof(*boost), GFP_ATOMIC);
+ if (boost == NULL)
+ return;
+
+ i915_gem_request_reference(rq);
+ boost->rq = rq;
+
+ INIT_WORK(&boost->work, __intel_rps_boost_work);
+ queue_work(to_i915(dev)->wq, &boost->work);
+}
+
void intel_pm_setup(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -6799,6 +6860,7 @@
INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
intel_gen6_powersave_work);
+ INIT_LIST_HEAD(&dev_priv->rps.clients);
dev_priv->pm.suspended = false;
}
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index a8f9348..27608ce 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -117,6 +117,19 @@
I915_WRITE(VLV_VSCSDP(pipe), val);
}
+static void skl_psr_setup_su_vsc(struct intel_dp *intel_dp)
+{
+ struct edp_vsc_psr psr_vsc;
+
+ /* Prepare VSC Header for SU as per EDP 1.4 spec, Table 6.11 */
+ memset(&psr_vsc, 0, sizeof(psr_vsc));
+ psr_vsc.sdp_header.HB0 = 0;
+ psr_vsc.sdp_header.HB1 = 0x7;
+ psr_vsc.sdp_header.HB2 = 0x3;
+ psr_vsc.sdp_header.HB3 = 0xb;
+ intel_psr_write_vsc(intel_dp, &psr_vsc);
+}
+
static void hsw_psr_setup_vsc(struct intel_dp *intel_dp)
{
struct edp_vsc_psr psr_vsc;
@@ -133,7 +146,7 @@
static void vlv_psr_enable_sink(struct intel_dp *intel_dp)
{
drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
- DP_PSR_ENABLE);
+ DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
}
static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
@@ -165,6 +178,12 @@
drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
DP_PSR_ENABLE & ~DP_PSR_MAIN_LINK_ACTIVE);
+ /* Enable AUX frame sync at sink */
+ if (dev_priv->psr.aux_frame_sync)
+ drm_dp_dpcd_writeb(&intel_dp->aux,
+ DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF,
+ DP_AUX_FRAME_SYNC_ENABLE);
+
aux_data_reg = (INTEL_INFO(dev)->gen >= 9) ?
DPA_AUX_CH_DATA1 : EDP_PSR_AUX_DATA1(dev);
aux_ctl_reg = (INTEL_INFO(dev)->gen >= 9) ?
@@ -183,8 +202,10 @@
val |= DP_AUX_CH_CTL_TIME_OUT_1600us;
val &= ~DP_AUX_CH_CTL_MESSAGE_SIZE_MASK;
val |= (sizeof(aux_msg) << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT);
- /* Use hardcoded data values for PSR */
+ /* Use hardcoded data values for PSR, frame sync and GTC */
val &= ~DP_AUX_CH_CTL_PSR_DATA_AUX_REG_SKL;
+ val &= ~DP_AUX_CH_CTL_FS_DATA_AUX_REG_SKL;
+ val &= ~DP_AUX_CH_CTL_GTC_DATA_AUX_REG_SKL;
I915_WRITE(aux_ctl_reg, val);
} else {
I915_WRITE(aux_ctl_reg,
@@ -232,6 +253,7 @@
struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
struct drm_device *dev = dig_port->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+
uint32_t max_sleep_time = 0x1f;
/* Lately it was identified that depending on panel idle frame count
* calculated at HW can be off by 1. So let's use what came
@@ -255,6 +277,10 @@
max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
EDP_PSR_ENABLE);
+
+ if (dev_priv->psr.psr2_support)
+ I915_WRITE(EDP_PSR2_CTL, EDP_PSR2_ENABLE |
+ EDP_SU_TRACK_ENABLE | EDP_PSR2_TP2_TIME_100);
}
static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
@@ -332,6 +358,7 @@
struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
struct drm_device *dev = intel_dig_port->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc);
if (!HAS_PSR(dev)) {
DRM_DEBUG_KMS("PSR not supported on this platform\n");
@@ -364,6 +391,15 @@
if (HAS_DDI(dev)) {
hsw_psr_setup_vsc(intel_dp);
+ if (dev_priv->psr.psr2_support) {
+ /* PSR2 is restricted to work with panel resolutions upto 3200x2000 */
+ if (crtc->config->pipe_src_w > 3200 ||
+ crtc->config->pipe_src_h > 2000)
+ dev_priv->psr.psr2_support = false;
+ else
+ skl_psr_setup_su_vsc(intel_dp);
+ }
+
/* Avoid continuous PSR exit by masking memup and hpd */
I915_WRITE(EDP_PSR_DEBUG_CTL(dev), EDP_PSR_DEBUG_MASK_MEMUP |
EDP_PSR_DEBUG_MASK_HPD | EDP_PSR_DEBUG_MASK_LPSP);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 000f608..de8c074 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -853,6 +853,9 @@
GEN6_WIZ_HASHING_MASK,
GEN6_WIZ_HASHING_16x4);
+ /* WaProgramL3SqcReg1Default:bdw */
+ WA_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT);
+
return 0;
}
@@ -1989,6 +1992,7 @@
INIT_LIST_HEAD(&ring->active_list);
INIT_LIST_HEAD(&ring->request_list);
INIT_LIST_HEAD(&ring->execlist_queue);
+ i915_gem_batch_pool_init(dev, &ring->batch_pool);
ringbuf->size = 32 * PAGE_SIZE;
ringbuf->ring = ring;
memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
@@ -2067,28 +2071,29 @@
cleanup_status_page(ring);
i915_cmd_parser_fini_ring(ring);
+ i915_gem_batch_pool_fini(&ring->batch_pool);
kfree(ringbuf);
ring->buffer = NULL;
}
-static int intel_ring_wait_request(struct intel_engine_cs *ring, int n)
+static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
struct drm_i915_gem_request *request;
- int ret;
+ int ret, new_space;
if (intel_ring_space(ringbuf) >= n)
return 0;
list_for_each_entry(request, &ring->request_list, list) {
- if (__intel_ring_space(request->postfix, ringbuf->tail,
- ringbuf->size) >= n) {
+ new_space = __intel_ring_space(request->postfix, ringbuf->tail,
+ ringbuf->size);
+ if (new_space >= n)
break;
- }
}
- if (&request->list == &ring->request_list)
+ if (WARN_ON(&request->list == &ring->request_list))
return -ENOSPC;
ret = i915_wait_request(request);
@@ -2097,61 +2102,11 @@
i915_gem_retire_requests_ring(ring);
+ WARN_ON(intel_ring_space(ringbuf) < new_space);
+
return 0;
}
-static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
-{
- struct drm_device *dev = ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_ringbuffer *ringbuf = ring->buffer;
- unsigned long end;
- int ret;
-
- ret = intel_ring_wait_request(ring, n);
- if (ret != -ENOSPC)
- return ret;
-
- /* force the tail write in case we have been skipping them */
- __intel_ring_advance(ring);
-
- /* With GEM the hangcheck timer should kick us out of the loop,
- * leaving it early runs the risk of corrupting GEM state (due
- * to running on almost untested codepaths). But on resume
- * timers don't work yet, so prevent a complete hang in that
- * case by choosing an insanely large timeout. */
- end = jiffies + 60 * HZ;
-
- ret = 0;
- trace_i915_ring_wait_begin(ring);
- do {
- if (intel_ring_space(ringbuf) >= n)
- break;
- ringbuf->head = I915_READ_HEAD(ring);
- if (intel_ring_space(ringbuf) >= n)
- break;
-
- msleep(1);
-
- if (dev_priv->mm.interruptible && signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
-
- ret = i915_gem_check_wedge(&dev_priv->gpu_error,
- dev_priv->mm.interruptible);
- if (ret)
- break;
-
- if (time_after(jiffies, end)) {
- ret = -EBUSY;
- break;
- }
- } while (1);
- trace_i915_ring_wait_end(ring);
- return ret;
-}
-
static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
{
uint32_t __iomem *virt;
@@ -2198,32 +2153,9 @@
return i915_wait_request(req);
}
-static int
-intel_ring_alloc_request(struct intel_engine_cs *ring)
+int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request)
{
- int ret;
- struct drm_i915_gem_request *request;
- struct drm_i915_private *dev_private = ring->dev->dev_private;
-
- if (ring->outstanding_lazy_request)
- return 0;
-
- request = kzalloc(sizeof(*request), GFP_KERNEL);
- if (request == NULL)
- return -ENOMEM;
-
- kref_init(&request->ref);
- request->ring = ring;
- request->ringbuf = ring->buffer;
- request->uniq = dev_private->request_uniq++;
-
- ret = i915_gem_get_seqno(ring->dev, &request->seqno);
- if (ret) {
- kfree(request);
- return ret;
- }
-
- ring->outstanding_lazy_request = request;
+ request->ringbuf = request->ring->buffer;
return 0;
}
@@ -2264,7 +2196,7 @@
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_request(ring);
+ ret = i915_gem_request_alloc(ring, ring->default_context);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c761fe0..39f6dfc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -2,6 +2,7 @@
#define _INTEL_RINGBUFFER_H_
#include <linux/hashtable.h>
+#include "i915_gem_batch_pool.h"
#define I915_CMD_HASH_ORDER 9
@@ -133,6 +134,13 @@
struct drm_device *dev;
struct intel_ringbuffer *buffer;
+ /*
+ * A pool of objects to use as shadow copies of client batch buffers
+ * when the command parser is enabled. Prevents the client from
+ * modifying the batch contents after software parsing.
+ */
+ struct i915_gem_batch_pool batch_pool;
+
struct intel_hw_status_page status_page;
unsigned irq_refcount; /* protected by dev_priv->irq_lock */
@@ -390,6 +398,8 @@
void intel_stop_ring_buffer(struct intel_engine_cs *ring);
void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
+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);
static inline void intel_ring_emit(struct intel_engine_cs *ring,
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index f5b7e1e..10cd332 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2291,10 +2291,11 @@
else
mapping = &dev_priv->sdvo_mappings[1];
- if (mapping->initialized && intel_gmbus_is_port_valid(mapping->i2c_pin))
+ if (mapping->initialized &&
+ intel_gmbus_is_valid_pin(dev_priv, mapping->i2c_pin))
pin = mapping->i2c_pin;
else
- pin = GMBUS_PORT_DPB;
+ pin = GMBUS_PIN_DPB;
sdvo->i2c = intel_gmbus_get_adapter(dev_priv, pin);
@@ -2426,6 +2427,22 @@
}
}
+static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void)
+{
+ struct intel_sdvo_connector *sdvo_connector;
+
+ sdvo_connector = kzalloc(sizeof(*sdvo_connector), GFP_KERNEL);
+ if (!sdvo_connector)
+ return NULL;
+
+ if (intel_connector_init(&sdvo_connector->base) < 0) {
+ kfree(sdvo_connector);
+ return NULL;
+ }
+
+ return sdvo_connector;
+}
+
static bool
intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
{
@@ -2437,7 +2454,7 @@
DRM_DEBUG_KMS("initialising DVI device %d\n", device);
- intel_sdvo_connector = kzalloc(sizeof(*intel_sdvo_connector), GFP_KERNEL);
+ intel_sdvo_connector = intel_sdvo_connector_alloc();
if (!intel_sdvo_connector)
return false;
@@ -2491,7 +2508,7 @@
DRM_DEBUG_KMS("initialising TV type %d\n", type);
- intel_sdvo_connector = kzalloc(sizeof(*intel_sdvo_connector), GFP_KERNEL);
+ intel_sdvo_connector = intel_sdvo_connector_alloc();
if (!intel_sdvo_connector)
return false;
@@ -2570,7 +2587,7 @@
DRM_DEBUG_KMS("initialising LVDS device %d\n", device);
- intel_sdvo_connector = kzalloc(sizeof(*intel_sdvo_connector), GFP_KERNEL);
+ intel_sdvo_connector = intel_sdvo_connector_alloc();
if (!intel_sdvo_connector)
return false;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index a4c0a04..e3d41c0 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -190,10 +190,13 @@
struct drm_i915_gem_object *obj = intel_fb_obj(fb);
const int pipe = intel_plane->pipe;
const int plane = intel_plane->plane + 1;
- u32 plane_ctl, stride_div;
+ u32 plane_ctl, stride_div, stride;
int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
const struct drm_intel_sprite_colorkey *key = &intel_plane->ckey;
unsigned long surf_addr;
+ u32 tile_height, plane_offset, plane_size;
+ unsigned int rotation;
+ int x_offset, y_offset;
plane_ctl = PLANE_CTL_ENABLE |
PLANE_CTL_PIPE_CSC_ENABLE;
@@ -254,8 +257,20 @@
MISSING_CASE(fb->modifier[0]);
}
- if (drm_plane->state->rotation == BIT(DRM_ROTATE_180))
+ rotation = drm_plane->state->rotation;
+ switch (rotation) {
+ case BIT(DRM_ROTATE_90):
+ plane_ctl |= PLANE_CTL_ROTATE_90;
+ break;
+
+ case BIT(DRM_ROTATE_180):
plane_ctl |= PLANE_CTL_ROTATE_180;
+ break;
+
+ case BIT(DRM_ROTATE_270):
+ plane_ctl |= PLANE_CTL_ROTATE_270;
+ break;
+ }
intel_update_sprite_watermarks(drm_plane, crtc, src_w, src_h,
pixel_size, true,
@@ -283,10 +298,26 @@
surf_addr = intel_plane_obj_offset(intel_plane, obj);
- I915_WRITE(PLANE_OFFSET(pipe, plane), (y << 16) | x);
- I915_WRITE(PLANE_STRIDE(pipe, plane), fb->pitches[0] / stride_div);
+ if (intel_rotation_90_or_270(rotation)) {
+ /* stride: Surface height in tiles */
+ tile_height = intel_tile_height(dev, fb->bits_per_pixel,
+ fb->modifier[0]);
+ stride = DIV_ROUND_UP(fb->height, tile_height);
+ plane_size = (src_w << 16) | src_h;
+ x_offset = stride * tile_height - y - (src_h + 1);
+ y_offset = x;
+ } else {
+ stride = fb->pitches[0] / stride_div;
+ plane_size = (src_h << 16) | src_w;
+ x_offset = x;
+ y_offset = y;
+ }
+ plane_offset = y_offset << 16 | x_offset;
+
+ I915_WRITE(PLANE_OFFSET(pipe, plane), plane_offset);
+ I915_WRITE(PLANE_STRIDE(pipe, plane), stride);
I915_WRITE(PLANE_POS(pipe, plane), (crtc_y << 16) | crtc_x);
- I915_WRITE(PLANE_SIZE(pipe, plane), (crtc_h << 16) | crtc_w);
+ I915_WRITE(PLANE_SIZE(pipe, plane), plane_size);
I915_WRITE(PLANE_CTL(pipe, plane), plane_ctl);
I915_WRITE(PLANE_SURF(pipe, plane), surf_addr);
POSTING_READ(PLANE_SURF(pipe, plane));
@@ -1006,10 +1037,10 @@
}
if (state->visible) {
- src->x1 = src_x;
- src->x2 = src_x + src_w;
- src->y1 = src_y;
- src->y2 = src_y + src_h;
+ src->x1 = src_x << 16;
+ src->x2 = (src_x + src_w) << 16;
+ src->y1 = src_y << 16;
+ src->y2 = (src_y + src_h) << 16;
}
dst->x1 = crtc_x;
@@ -1081,10 +1112,10 @@
crtc_y = state->dst.y1;
crtc_w = drm_rect_width(&state->dst);
crtc_h = drm_rect_height(&state->dst);
- src_x = state->src.x1;
- src_y = state->src.y1;
- src_w = drm_rect_width(&state->src);
- src_h = drm_rect_height(&state->src);
+ src_x = state->src.x1 >> 16;
+ src_y = state->src.y1 >> 16;
+ src_w = drm_rect_width(&state->src) >> 16;
+ src_h = drm_rect_height(&state->src) >> 16;
intel_plane->update_plane(plane, crtc, fb,
crtc_x, crtc_y, crtc_w, crtc_h,
src_x, src_y, src_w, src_h);
@@ -1139,11 +1170,11 @@
if (!plane->crtc || !plane->state->fb)
return 0;
- return plane->funcs->update_plane(plane, plane->crtc, plane->state->fb,
- plane->state->crtc_x, plane->state->crtc_y,
- plane->state->crtc_w, plane->state->crtc_h,
- plane->state->src_x, plane->state->src_y,
- plane->state->src_w, plane->state->src_h);
+ return drm_plane_helper_update(plane, plane->crtc, plane->state->fb,
+ plane->state->crtc_x, plane->state->crtc_y,
+ plane->state->crtc_w, plane->state->crtc_h,
+ plane->state->src_x, plane->state->src_y,
+ plane->state->src_w, plane->state->src_h);
}
static uint32_t ilk_plane_formats[] = {
@@ -1263,6 +1294,7 @@
intel_plane->max_downscale = 1;
intel_plane->update_plane = skl_update_plane;
intel_plane->disable_plane = skl_disable_plane;
+ state->scaler_id = -1;
plane_formats = skl_plane_formats;
num_plane_formats = ARRAY_SIZE(skl_plane_formats);
@@ -1276,6 +1308,7 @@
intel_plane->plane = plane;
intel_plane->check_plane = intel_check_sprite_plane;
intel_plane->commit_plane = intel_commit_sprite_plane;
+ intel_plane->ckey.flags = I915_SET_COLORKEY_NONE;
possible_crtcs = (1 << pipe);
ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs,
&intel_plane_funcs,
@@ -1286,16 +1319,7 @@
goto out;
}
- if (!dev->mode_config.rotation_property)
- dev->mode_config.rotation_property =
- drm_mode_create_rotation_property(dev,
- BIT(DRM_ROTATE_0) |
- BIT(DRM_ROTATE_180));
-
- if (dev->mode_config.rotation_property)
- drm_object_attach_property(&intel_plane->base.base,
- dev->mode_config.rotation_property,
- state->base.rotation);
+ intel_create_rotation_property(dev, intel_plane);
drm_plane_helper_add(&intel_plane->base, &intel_plane_helper_funcs);
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index bc1d9d7..8b9d325 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1621,7 +1621,7 @@
return;
}
- intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
+ intel_connector = intel_connector_alloc();
if (!intel_connector) {
kfree(intel_tv);
return;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index ab5cc94..d96d15f 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -375,6 +375,26 @@
intel_disable_gt_powersave(dev);
}
+static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
+ enum forcewake_domains fw_domains)
+{
+ struct intel_uncore_forcewake_domain *domain;
+ enum forcewake_domain_id id;
+
+ if (!dev_priv->uncore.funcs.force_wake_get)
+ return;
+
+ fw_domains &= dev_priv->uncore.fw_domains;
+
+ for_each_fw_domain_mask(domain, fw_domains, dev_priv, id) {
+ if (domain->wake_count++)
+ fw_domains &= ~(1 << id);
+ }
+
+ if (fw_domains)
+ dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
+}
+
/**
* intel_uncore_forcewake_get - grab forcewake domain references
* @dev_priv: i915 device instance
@@ -392,27 +412,57 @@
enum forcewake_domains fw_domains)
{
unsigned long irqflags;
- struct intel_uncore_forcewake_domain *domain;
- enum forcewake_domain_id id;
if (!dev_priv->uncore.funcs.force_wake_get)
return;
WARN_ON(dev_priv->pm.suspended);
+ spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+ __intel_uncore_forcewake_get(dev_priv, fw_domains);
+ spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+}
+
+/**
+ * intel_uncore_forcewake_get__locked - grab forcewake domain references
+ * @dev_priv: i915 device instance
+ * @fw_domains: forcewake domains to get reference on
+ *
+ * See intel_uncore_forcewake_get(). This variant places the onus
+ * on the caller to explicitly handle the dev_priv->uncore.lock spinlock.
+ */
+void intel_uncore_forcewake_get__locked(struct drm_i915_private *dev_priv,
+ enum forcewake_domains fw_domains)
+{
+ assert_spin_locked(&dev_priv->uncore.lock);
+
+ if (!dev_priv->uncore.funcs.force_wake_get)
+ return;
+
+ __intel_uncore_forcewake_get(dev_priv, fw_domains);
+}
+
+static void __intel_uncore_forcewake_put(struct drm_i915_private *dev_priv,
+ enum forcewake_domains fw_domains)
+{
+ struct intel_uncore_forcewake_domain *domain;
+ enum forcewake_domain_id id;
+
+ if (!dev_priv->uncore.funcs.force_wake_put)
+ return;
+
fw_domains &= dev_priv->uncore.fw_domains;
- spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
-
for_each_fw_domain_mask(domain, fw_domains, dev_priv, id) {
- if (domain->wake_count++)
- fw_domains &= ~(1 << id);
+ if (WARN_ON(domain->wake_count == 0))
+ continue;
+
+ if (--domain->wake_count)
+ continue;
+
+ domain->wake_count++;
+ fw_domain_arm_timer(domain);
}
-
- if (fw_domains)
- dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
-
- spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
}
/**
@@ -427,30 +477,34 @@
enum forcewake_domains fw_domains)
{
unsigned long irqflags;
- struct intel_uncore_forcewake_domain *domain;
- enum forcewake_domain_id id;
if (!dev_priv->uncore.funcs.force_wake_put)
return;
- fw_domains &= dev_priv->uncore.fw_domains;
-
spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
-
- for_each_fw_domain_mask(domain, fw_domains, dev_priv, id) {
- if (WARN_ON(domain->wake_count == 0))
- continue;
-
- if (--domain->wake_count)
- continue;
-
- domain->wake_count++;
- fw_domain_arm_timer(domain);
- }
-
+ __intel_uncore_forcewake_put(dev_priv, fw_domains);
spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
}
+/**
+ * intel_uncore_forcewake_put__locked - grab forcewake domain references
+ * @dev_priv: i915 device instance
+ * @fw_domains: forcewake domains to get reference on
+ *
+ * See intel_uncore_forcewake_put(). This variant places the onus
+ * on the caller to explicitly handle the dev_priv->uncore.lock spinlock.
+ */
+void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv,
+ enum forcewake_domains fw_domains)
+{
+ assert_spin_locked(&dev_priv->uncore.lock);
+
+ if (!dev_priv->uncore.funcs.force_wake_put)
+ return;
+
+ __intel_uncore_forcewake_put(dev_priv, fw_domains);
+}
+
void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
{
struct intel_uncore_forcewake_domain *domain;
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 2e80ad1..150b93c 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1263,6 +1263,7 @@
bool is_primary);
extern void drm_plane_cleanup(struct drm_plane *plane);
extern unsigned int drm_plane_index(struct drm_plane *plane);
+extern struct drm_plane * drm_plane_from_index(struct drm_device *dev, int idx);
extern void drm_plane_force_disable(struct drm_plane *plane);
extern int drm_plane_check_pixel_format(const struct drm_plane *plane,
u32 format);
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 551b673..4851d66 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -996,6 +996,7 @@
/* flags */
#define I915_OVERLAY_UPDATE_ATTRS (1<<0)
#define I915_OVERLAY_UPDATE_GAMMA (1<<1)
+#define I915_OVERLAY_DISABLE_DEST_COLORKEY (1<<2)
struct drm_intel_overlay_attrs {
__u32 flags;
__u32 color_key;