Merge tag 'drm-intel-next-2019-02-07' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- Expose RPCS (SSEU) configuration to userspace for Ice Lake
in order to allow userspace to reconfigure the subslice config
per context basis. (Tvrtko, Lionel)

Driver Changes:

- Execbuf and preemption improvements including selftests (Chris)
- Rename HAS_GMCH_DISPLAY/HAS_GMCH (Rodrigo)
- Debugfs error handling fix for robustness (Greg)
- Improve reg_rw traces (Ville)
- Push clear_intel_crtc_state onto the heap (Chris)
- Watermark fixes for Ice Lake (Ville)
- Fix enable count array size and bounds checking (Tvrtko)
- MST Fixes (Lyude)
- Prevent race and handle error on I915_GEM_MMAP (Joonas)
- Initial rework for an full atomic gamma mode (Ville)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190208165000.GA30314@intel.com

55 files changed, 2756 insertions, 937 deletions

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 210d0e8777b6..1787e1299b1b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -57,7 +57,9 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o intel_pipe_crc.o
 i915-$(CONFIG_PERF_EVENTS) += i915_pmu.o
 
 # GEM code
-i915-y += i915_cmd_parser.o \
+i915-y += \
+	  i915_active.o \
+	  i915_cmd_parser.o \
 	  i915_gem_batch_pool.o \
 	  i915_gem_clflush.o \
 	  i915_gem_context.o \
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
new file mode 100644
index 000000000000..215b6ff8aa73
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -0,0 +1,286 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_active.h"
+
+#define BKL(ref) (&(ref)->i915->drm.struct_mutex)
+
+/*
+ * Active refs memory management
+ *
+ * To be more economical with memory, we reap all the i915_active trees as
+ * they idle (when we know the active requests are inactive) and allocate the
+ * nodes from a local slab cache to hopefully reduce the fragmentation.
+ */
+static struct i915_global_active {
+	struct kmem_cache *slab_cache;
+} global;
+
+struct active_node {
+	struct i915_active_request base;
+	struct i915_active *ref;
+	struct rb_node node;
+	u64 timeline;
+};
+
+static void
+__active_park(struct i915_active *ref)
+{
+	struct active_node *it, *n;
+
+	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
+		GEM_BUG_ON(i915_active_request_isset(&it->base));
+		kmem_cache_free(global.slab_cache, it);
+	}
+	ref->tree = RB_ROOT;
+}
+
+static void
+__active_retire(struct i915_active *ref)
+{
+	GEM_BUG_ON(!ref->count);
+	if (--ref->count)
+		return;
+
+	/* return the unused nodes to our slabcache */
+	__active_park(ref);
+
+	ref->retire(ref);
+}
+
+static void
+node_retire(struct i915_active_request *base, struct i915_request *rq)
+{
+	__active_retire(container_of(base, struct active_node, base)->ref);
+}
+
+static void
+last_retire(struct i915_active_request *base, struct i915_request *rq)
+{
+	__active_retire(container_of(base, struct i915_active, last));
+}
+
+static struct i915_active_request *
+active_instance(struct i915_active *ref, u64 idx)
+{
+	struct active_node *node;
+	struct rb_node **p, *parent;
+	struct i915_request *old;
+
+	/*
+	 * We track the most recently used timeline to skip a rbtree search
+	 * for the common case, under typical loads we never need the rbtree
+	 * at all. We can reuse the last slot if it is empty, that is
+	 * after the previous activity has been retired, or if it matches the
+	 * current timeline.
+	 *
+	 * Note that we allow the timeline to be active simultaneously in
+	 * the rbtree and the last cache. We do this to avoid having
+	 * to search and replace the rbtree element for a new timeline, with
+	 * the cost being that we must be aware that the ref may be retired
+	 * twice for the same timeline (as the older rbtree element will be
+	 * retired before the new request added to last).
+	 */
+	old = i915_active_request_raw(&ref->last, BKL(ref));
+	if (!old || old->fence.context == idx)
+		goto out;
+
+	/* Move the currently active fence into the rbtree */
+	idx = old->fence.context;
+
+	parent = NULL;
+	p = &ref->tree.rb_node;
+	while (*p) {
+		parent = *p;
+
+		node = rb_entry(parent, struct active_node, node);
+		if (node->timeline == idx)
+			goto replace;
+
+		if (node->timeline < idx)
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+
+	node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
+
+	/* kmalloc may retire the ref->last (thanks shrinker)! */
+	if (unlikely(!i915_active_request_raw(&ref->last, BKL(ref)))) {
+		kmem_cache_free(global.slab_cache, node);
+		goto out;
+	}
+
+	if (unlikely(!node))
+		return ERR_PTR(-ENOMEM);
+
+	i915_active_request_init(&node->base, NULL, node_retire);
+	node->ref = ref;
+	node->timeline = idx;
+
+	rb_link_node(&node->node, parent, p);
+	rb_insert_color(&node->node, &ref->tree);
+
+replace:
+	/*
+	 * Overwrite the previous active slot in the rbtree with last,
+	 * leaving last zeroed. If the previous slot is still active,
+	 * we must be careful as we now only expect to receive one retire
+	 * callback not two, and so much undo the active counting for the
+	 * overwritten slot.
+	 */
+	if (i915_active_request_isset(&node->base)) {
+		/* Retire ourselves from the old rq->active_list */
+		__list_del_entry(&node->base.link);
+		ref->count--;
+		GEM_BUG_ON(!ref->count);
+	}
+	GEM_BUG_ON(list_empty(&ref->last.link));
+	list_replace_init(&ref->last.link, &node->base.link);
+	node->base.request = fetch_and_zero(&ref->last.request);
+
+out:
+	return &ref->last;
+}
+
+void i915_active_init(struct drm_i915_private *i915,
+		      struct i915_active *ref,
+		      void (*retire)(struct i915_active *ref))
+{
+	ref->i915 = i915;
+	ref->retire = retire;
+	ref->tree = RB_ROOT;
+	i915_active_request_init(&ref->last, NULL, last_retire);
+	ref->count = 0;
+}
+
+int i915_active_ref(struct i915_active *ref,
+		    u64 timeline,
+		    struct i915_request *rq)
+{
+	struct i915_active_request *active;
+
+	active = active_instance(ref, timeline);
+	if (IS_ERR(active))
+		return PTR_ERR(active);
+
+	if (!i915_active_request_isset(active))
+		ref->count++;
+	__i915_active_request_set(active, rq);
+
+	GEM_BUG_ON(!ref->count);
+	return 0;
+}
+
+bool i915_active_acquire(struct i915_active *ref)
+{
+	lockdep_assert_held(BKL(ref));
+	return !ref->count++;
+}
+
+void i915_active_release(struct i915_active *ref)
+{
+	lockdep_assert_held(BKL(ref));
+	__active_retire(ref);
+}
+
+int i915_active_wait(struct i915_active *ref)
+{
+	struct active_node *it, *n;
+	int ret = 0;
+
+	if (i915_active_acquire(ref))
+		goto out_release;
+
+	ret = i915_active_request_retire(&ref->last, BKL(ref));
+	if (ret)
+		goto out_release;
+
+	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
+		ret = i915_active_request_retire(&it->base, BKL(ref));
+		if (ret)
+			break;
+	}
+
+out_release:
+	i915_active_release(ref);
+	return ret;
+}
+
+int i915_request_await_active_request(struct i915_request *rq,
+				      struct i915_active_request *active)
+{
+	struct i915_request *barrier =
+		i915_active_request_raw(active, &rq->i915->drm.struct_mutex);
+
+	return barrier ? i915_request_await_dma_fence(rq, &barrier->fence) : 0;
+}
+
+int i915_request_await_active(struct i915_request *rq, struct i915_active *ref)
+{
+	struct active_node *it, *n;
+	int ret;
+
+	ret = i915_request_await_active_request(rq, &ref->last);
+	if (ret)
+		return ret;
+
+	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
+		ret = i915_request_await_active_request(rq, &it->base);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void i915_active_fini(struct i915_active *ref)
+{
+	GEM_BUG_ON(i915_active_request_isset(&ref->last));
+	GEM_BUG_ON(!RB_EMPTY_ROOT(&ref->tree));
+	GEM_BUG_ON(ref->count);
+}
+#endif
+
+int i915_active_request_set(struct i915_active_request *active,
+			    struct i915_request *rq)
+{
+	int err;
+
+	/* Must maintain ordering wrt previous active requests */
+	err = i915_request_await_active_request(rq, active);
+	if (err)
+		return err;
+
+	__i915_active_request_set(active, rq);
+	return 0;
+}
+
+void i915_active_retire_noop(struct i915_active_request *active,
+			     struct i915_request *request)
+{
+	/* Space left intentionally blank */
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_active.c"
+#endif
+
+int __init i915_global_active_init(void)
+{
+	global.slab_cache = KMEM_CACHE(active_node, SLAB_HWCACHE_ALIGN);
+	if (!global.slab_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void __exit i915_global_active_exit(void)
+{
+	kmem_cache_destroy(global.slab_cache);
+}
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
new file mode 100644
index 000000000000..12b5c1d287d1
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -0,0 +1,425 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef _I915_ACTIVE_H_
+#define _I915_ACTIVE_H_
+
+#include <linux/lockdep.h>
+
+#include "i915_active_types.h"
+#include "i915_request.h"
+
+/*
+ * We treat requests as fences. This is not be to confused with our
+ * "fence registers" but pipeline synchronisation objects ala GL_ARB_sync.
+ * We use the fences to synchronize access from the CPU with activity on the
+ * GPU, for example, we should not rewrite an object's PTE whilst the GPU
+ * is reading them. We also track fences at a higher level to provide
+ * implicit synchronisation around GEM objects, e.g. set-domain will wait
+ * for outstanding GPU rendering before marking the object ready for CPU
+ * access, or a pageflip will wait until the GPU is complete before showing
+ * the frame on the scanout.
+ *
+ * In order to use a fence, the object must track the fence it needs to
+ * serialise with. For example, GEM objects want to track both read and
+ * write access so that we can perform concurrent read operations between
+ * the CPU and GPU engines, as well as waiting for all rendering to
+ * complete, or waiting for the last GPU user of a "fence register". The
+ * object then embeds a #i915_active_request to track the most recent (in
+ * retirement order) request relevant for the desired mode of access.
+ * The #i915_active_request is updated with i915_active_request_set() to
+ * track the most recent fence request, typically this is done as part of
+ * i915_vma_move_to_active().
+ *
+ * When the #i915_active_request completes (is retired), it will
+ * signal its completion to the owner through a callback as well as mark
+ * itself as idle (i915_active_request.request == NULL). The owner
+ * can then perform any action, such as delayed freeing of an active
+ * resource including itself.
+ */
+
+void i915_active_retire_noop(struct i915_active_request *active,
+			     struct i915_request *request);
+
+/**
+ * i915_active_request_init - prepares the activity tracker for use
+ * @active - the active tracker
+ * @rq - initial request to track, can be NULL
+ * @func - a callback when then the tracker is retired (becomes idle),
+ *         can be NULL
+ *
+ * i915_active_request_init() prepares the embedded @active struct for use as
+ * an activity tracker, that is for tracking the last known active request
+ * associated with it. When the last request becomes idle, when it is retired
+ * after completion, the optional callback @func is invoked.
+ */
+static inline void
+i915_active_request_init(struct i915_active_request *active,
+			 struct i915_request *rq,
+			 i915_active_retire_fn retire)
+{
+	RCU_INIT_POINTER(active->request, rq);
+	INIT_LIST_HEAD(&active->link);
+	active->retire = retire ?: i915_active_retire_noop;
+}
+
+#define INIT_ACTIVE_REQUEST(name) i915_active_request_init((name), NULL, NULL)
+
+/**
+ * i915_active_request_set - updates the tracker to watch the current request
+ * @active - the active tracker
+ * @request - the request to watch
+ *
+ * __i915_active_request_set() watches the given @request for completion. Whilst
+ * that @request is busy, the @active reports busy. When that @request is
+ * retired, the @active tracker is updated to report idle.
+ */
+static inline void
+__i915_active_request_set(struct i915_active_request *active,
+			  struct i915_request *request)
+{
+	list_move(&active->link, &request->active_list);
+	rcu_assign_pointer(active->request, request);
+}
+
+int __must_check
+i915_active_request_set(struct i915_active_request *active,
+			struct i915_request *rq);
+
+/**
+ * i915_active_request_set_retire_fn - updates the retirement callback
+ * @active - the active tracker
+ * @fn - the routine called when the request is retired
+ * @mutex - struct_mutex used to guard retirements
+ *
+ * i915_active_request_set_retire_fn() updates the function pointer that
+ * is called when the final request associated with the @active tracker
+ * is retired.
+ */
+static inline void
+i915_active_request_set_retire_fn(struct i915_active_request *active,
+				  i915_active_retire_fn fn,
+				  struct mutex *mutex)
+{
+	lockdep_assert_held(mutex);
+	active->retire = fn ?: i915_active_retire_noop;
+}
+
+static inline struct i915_request *
+__i915_active_request_peek(const struct i915_active_request *active)
+{
+	/*
+	 * Inside the error capture (running with the driver in an unknown
+	 * state), we want to bend the rules slightly (a lot).
+	 *
+	 * Work is in progress to make it safer, in the meantime this keeps
+	 * the known issue from spamming the logs.
+	 */
+	return rcu_dereference_protected(active->request, 1);
+}
+
+/**
+ * i915_active_request_raw - return the active request
+ * @active - the active tracker
+ *
+ * i915_active_request_raw() returns the current request being tracked, or NULL.
+ * It does not obtain a reference on the request for the caller, so the caller
+ * must hold struct_mutex.
+ */
+static inline struct i915_request *
+i915_active_request_raw(const struct i915_active_request *active,
+			struct mutex *mutex)
+{
+	return rcu_dereference_protected(active->request,
+					 lockdep_is_held(mutex));
+}
+
+/**
+ * i915_active_request_peek - report the active request being monitored
+ * @active - the active tracker
+ *
+ * i915_active_request_peek() returns the current request being tracked if
+ * still active, or NULL. It does not obtain a reference on the request
+ * for the caller, so the caller must hold struct_mutex.
+ */
+static inline struct i915_request *
+i915_active_request_peek(const struct i915_active_request *active,
+			 struct mutex *mutex)
+{
+	struct i915_request *request;
+
+	request = i915_active_request_raw(active, mutex);
+	if (!request || i915_request_completed(request))
+		return NULL;
+
+	return request;
+}
+
+/**
+ * i915_active_request_get - return a reference to the active request
+ * @active - the active tracker
+ *
+ * i915_active_request_get() returns a reference to the active request, or NULL
+ * if the active tracker is idle. The caller must hold struct_mutex.
+ */
+static inline struct i915_request *
+i915_active_request_get(const struct i915_active_request *active,
+			struct mutex *mutex)
+{
+	return i915_request_get(i915_active_request_peek(active, mutex));
+}
+
+/**
+ * __i915_active_request_get_rcu - return a reference to the active request
+ * @active - the active tracker
+ *
+ * __i915_active_request_get() returns a reference to the active request,
+ * or NULL if the active tracker is idle. The caller must hold the RCU read
+ * lock, but the returned pointer is safe to use outside of RCU.
+ */
+static inline struct i915_request *
+__i915_active_request_get_rcu(const struct i915_active_request *active)
+{
+	/*
+	 * Performing a lockless retrieval of the active request is super
+	 * tricky. SLAB_TYPESAFE_BY_RCU merely guarantees that the backing
+	 * slab of request objects will not be freed whilst we hold the
+	 * RCU read lock. It does not guarantee that the request itself
+	 * will not be freed and then *reused*. Viz,
+	 *
+	 * Thread A			Thread B
+	 *
+	 * rq = active.request
+	 *				retire(rq) -> free(rq);
+	 *				(rq is now first on the slab freelist)
+	 *				active.request = NULL
+	 *
+	 *				rq = new submission on a new object
+	 * ref(rq)
+	 *
+	 * To prevent the request from being reused whilst the caller
+	 * uses it, we take a reference like normal. Whilst acquiring
+	 * the reference we check that it is not in a destroyed state
+	 * (refcnt == 0). That prevents the request being reallocated
+	 * whilst the caller holds on to it. To check that the request
+	 * was not reallocated as we acquired the reference we have to
+	 * check that our request remains the active request across
+	 * the lookup, in the same manner as a seqlock. The visibility
+	 * of the pointer versus the reference counting is controlled
+	 * by using RCU barriers (rcu_dereference and rcu_assign_pointer).
+	 *
+	 * In the middle of all that, we inspect whether the request is
+	 * complete. Retiring is lazy so the request may be completed long
+	 * before the active tracker is updated. Querying whether the
+	 * request is complete is far cheaper (as it involves no locked
+	 * instructions setting cachelines to exclusive) than acquiring
+	 * the reference, so we do it first. The RCU read lock ensures the
+	 * pointer dereference is valid, but does not ensure that the
+	 * seqno nor HWS is the right one! However, if the request was
+	 * reallocated, that means the active tracker's request was complete.
+	 * If the new request is also complete, then both are and we can
+	 * just report the active tracker is idle. If the new request is
+	 * incomplete, then we acquire a reference on it and check that
+	 * it remained the active request.
+	 *
+	 * It is then imperative that we do not zero the request on
+	 * reallocation, so that we can chase the dangling pointers!
+	 * See i915_request_alloc().
+	 */
+	do {
+		struct i915_request *request;
+
+		request = rcu_dereference(active->request);
+		if (!request || i915_request_completed(request))
+			return NULL;
+
+		/*
+		 * An especially silly compiler could decide to recompute the
+		 * result of i915_request_completed, more specifically
+		 * re-emit the load for request->fence.seqno. A race would catch
+		 * a later seqno value, which could flip the result from true to
+		 * false. Which means part of the instructions below might not
+		 * be executed, while later on instructions are executed. Due to
+		 * barriers within the refcounting the inconsistency can't reach
+		 * past the call to i915_request_get_rcu, but not executing
+		 * that while still executing i915_request_put() creates
+		 * havoc enough.  Prevent this with a compiler barrier.
+		 */
+		barrier();
+
+		request = i915_request_get_rcu(request);
+
+		/*
+		 * What stops the following rcu_access_pointer() from occurring
+		 * before the above i915_request_get_rcu()? If we were
+		 * to read the value before pausing to get the reference to
+		 * the request, we may not notice a change in the active
+		 * tracker.
+		 *
+		 * The rcu_access_pointer() is a mere compiler barrier, which
+		 * means both the CPU and compiler are free to perform the
+		 * memory read without constraint. The compiler only has to
+		 * ensure that any operations after the rcu_access_pointer()
+		 * occur afterwards in program order. This means the read may
+		 * be performed earlier by an out-of-order CPU, or adventurous
+		 * compiler.
+		 *
+		 * The atomic operation at the heart of
+		 * i915_request_get_rcu(), see dma_fence_get_rcu(), is
+		 * atomic_inc_not_zero() which is only a full memory barrier
+		 * when successful. That is, if i915_request_get_rcu()
+		 * returns the request (and so with the reference counted
+		 * incremented) then the following read for rcu_access_pointer()
+		 * must occur after the atomic operation and so confirm
+		 * that this request is the one currently being tracked.
+		 *
+		 * The corresponding write barrier is part of
+		 * rcu_assign_pointer().
+		 */
+		if (!request || request == rcu_access_pointer(active->request))
+			return rcu_pointer_handoff(request);
+
+		i915_request_put(request);
+	} while (1);
+}
+
+/**
+ * i915_active_request_get_unlocked - return a reference to the active request
+ * @active - the active tracker
+ *
+ * i915_active_request_get_unlocked() returns a reference to the active request,
+ * or NULL if the active tracker is idle. The reference is obtained under RCU,
+ * so no locking is required by the caller.
+ *
+ * The reference should be freed with i915_request_put().
+ */
+static inline struct i915_request *
+i915_active_request_get_unlocked(const struct i915_active_request *active)
+{
+	struct i915_request *request;
+
+	rcu_read_lock();
+	request = __i915_active_request_get_rcu(active);
+	rcu_read_unlock();
+
+	return request;
+}
+
+/**
+ * i915_active_request_isset - report whether the active tracker is assigned
+ * @active - the active tracker
+ *
+ * i915_active_request_isset() returns true if the active tracker is currently
+ * assigned to a request. Due to the lazy retiring, that request may be idle
+ * and this may report stale information.
+ */
+static inline bool
+i915_active_request_isset(const struct i915_active_request *active)
+{
+	return rcu_access_pointer(active->request);
+}
+
+/**
+ * i915_active_request_retire - waits until the request is retired
+ * @active - the active request on which to wait
+ *
+ * i915_active_request_retire() waits until the request is completed,
+ * and then ensures that at least the retirement handler for this
+ * @active tracker is called before returning. If the @active
+ * tracker is idle, the function returns immediately.
+ */
+static inline int __must_check
+i915_active_request_retire(struct i915_active_request *active,
+			   struct mutex *mutex)
+{
+	struct i915_request *request;
+	long ret;
+
+	request = i915_active_request_raw(active, mutex);
+	if (!request)
+		return 0;
+
+	ret = i915_request_wait(request,
+				I915_WAIT_INTERRUPTIBLE | I915_WAIT_LOCKED,
+				MAX_SCHEDULE_TIMEOUT);
+	if (ret < 0)
+		return ret;
+
+	list_del_init(&active->link);
+	RCU_INIT_POINTER(active->request, NULL);
+
+	active->retire(active, request);
+
+	return 0;
+}
+
+/*
+ * GPU activity tracking
+ *
+ * Each set of commands submitted to the GPU compromises a single request that
+ * signals a fence upon completion. struct i915_request combines the
+ * command submission, scheduling and fence signaling roles. If we want to see
+ * if a particular task is complete, we need to grab the fence (struct
+ * i915_request) for that task and check or wait for it to be signaled. More
+ * often though we want to track the status of a bunch of tasks, for example
+ * to wait for the GPU to finish accessing some memory across a variety of
+ * different command pipelines from different clients. We could choose to
+ * track every single request associated with the task, but knowing that
+ * each request belongs to an ordered timeline (later requests within a
+ * timeline must wait for earlier requests), we need only track the
+ * latest request in each timeline to determine the overall status of the
+ * task.
+ *
+ * struct i915_active provides this tracking across timelines. It builds a
+ * composite shared-fence, and is updated as new work is submitted to the task,
+ * forming a snapshot of the current status. It should be embedded into the
+ * different resources that need to track their associated GPU activity to
+ * provide a callback when that GPU activity has ceased, or otherwise to
+ * provide a serialisation point either for request submission or for CPU
+ * synchronisation.
+ */
+
+void i915_active_init(struct drm_i915_private *i915,
+		      struct i915_active *ref,
+		      void (*retire)(struct i915_active *ref));
+
+int i915_active_ref(struct i915_active *ref,
+		    u64 timeline,
+		    struct i915_request *rq);
+
+int i915_active_wait(struct i915_active *ref);
+
+int i915_request_await_active(struct i915_request *rq,
+			      struct i915_active *ref);
+int i915_request_await_active_request(struct i915_request *rq,
+				      struct i915_active_request *active);
+
+bool i915_active_acquire(struct i915_active *ref);
+
+static inline void i915_active_cancel(struct i915_active *ref)
+{
+	GEM_BUG_ON(ref->count != 1);
+	ref->count = 0;
+}
+
+void i915_active_release(struct i915_active *ref);
+
+static inline bool
+i915_active_is_idle(const struct i915_active *ref)
+{
+	return !ref->count;
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void i915_active_fini(struct i915_active *ref);
+#else
+static inline void i915_active_fini(struct i915_active *ref) { }
+#endif
+
+int i915_global_active_init(void);
+void i915_global_active_exit(void);
+
+#endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
new file mode 100644
index 000000000000..b679253b53a5
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -0,0 +1,36 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef _I915_ACTIVE_TYPES_H_
+#define _I915_ACTIVE_TYPES_H_
+
+#include <linux/rbtree.h>
+#include <linux/rcupdate.h>
+
+struct drm_i915_private;
+struct i915_active_request;
+struct i915_request;
+
+typedef void (*i915_active_retire_fn)(struct i915_active_request *,
+				      struct i915_request *);
+
+struct i915_active_request {
+	struct i915_request __rcu *request;
+	struct list_head link;
+	i915_active_retire_fn retire;
+};
+
+struct i915_active {
+	struct drm_i915_private *i915;
+
+	struct rb_root tree;
+	struct i915_active_request last;
+	unsigned int count;
+
+	void (*retire)(struct i915_active *ref);
+};
+
+#endif /* _I915_ACTIVE_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fa2c226fc779..0bd890c04fe4 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -207,7 +207,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		if (vma->fence)
 			seq_printf(m, " , fence: %d%s",
 				   vma->fence->id,
-				   i915_gem_active_isset(&vma->last_fence) ? "*" : "");
+				   i915_active_request_isset(&vma->last_fence) ? "*" : "");
 		seq_puts(m, ")");
 	}
 	if (obj->stolen)
@@ -3728,7 +3728,7 @@ static int spr_wm_latency_open(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *dev_priv = inode->i_private;
 
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		return -ENODEV;
 
 	return single_open(file, spr_wm_latency_show, dev_priv);
@@ -3738,7 +3738,7 @@ static int cur_wm_latency_open(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *dev_priv = inode->i_private;
 
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		return -ENODEV;
 
 	return single_open(file, cur_wm_latency_show, dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a7aaa1ac4c99..7de90701f6f1 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -2543,6 +2543,10 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv)
 static int vlv_wait_for_pw_status(struct drm_i915_private *dev_priv,
 				  u32 mask, u32 val)
 {
+	i915_reg_t reg = VLV_GTLC_PW_STATUS;
+	u32 reg_value;
+	int ret;
+
 	/* The HW does not like us polling for PW_STATUS frequently, so
 	 * use the sleeping loop rather than risk the busy spin within
 	 * intel_wait_for_register().
@@ -2550,8 +2554,12 @@ static int vlv_wait_for_pw_status(struct drm_i915_private *dev_priv,
 	 * Transitioning between RC6 states should be at most 2ms (see
 	 * valleyview_enable_rps) so use a 3ms timeout.
 	 */
-	return wait_for((I915_READ_NOTRACE(VLV_GTLC_PW_STATUS) & mask) == val,
-			3);
+	ret = wait_for(((reg_value = I915_READ_NOTRACE(reg)) & mask) == val, 3);
+
+	/* just trace the final value */
+	trace_i915_reg_rw(false, reg, reg_value, sizeof(reg_value), true);
+
+	return ret;
 }
 
 int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 534e52e3a8da..9adc7bb9e69c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -91,8 +91,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20190202"
-#define DRIVER_TIMESTAMP	1549095268
+#define DRIVER_DATE		"20190207"
+#define DRIVER_TIMESTAMP	1549572331
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
@@ -323,8 +323,20 @@ struct drm_i915_display_funcs {
 	/* display clock increase/decrease */
 	/* pll clock increase/decrease */
 
-	void (*load_csc_matrix)(struct intel_crtc_state *crtc_state);
-	void (*load_luts)(struct intel_crtc_state *crtc_state);
+	/*
+	 * Program double buffered color management registers during
+	 * vblank evasion. The registers should then latch during the
+	 * next vblank start, alongside any other double buffered registers
+	 * involved with the same commit.
+	 */
+	void (*color_commit)(const struct intel_crtc_state *crtc_state);
+	/*
+	 * Load LUTs (and other single buffered color management
+	 * registers). Will (hopefully) be called during the vblank
+	 * following the latching of any double buffered registers
+	 * involved with the same commit.
+	 */
+	void (*load_luts)(const struct intel_crtc_state *crtc_state);
 };
 
 #define CSR_VERSION(major, minor)	((major) << 16 | (minor))
@@ -2490,7 +2502,7 @@ static inline unsigned int i915_sg_segment_size(void)
 
 #define HAS_FW_BLC(dev_priv) 	(INTEL_GEN(dev_priv) > 2)
 #define HAS_FBC(dev_priv)	(INTEL_INFO(dev_priv)->display.has_fbc)
-#define HAS_CUR_FBC(dev_priv)	(!HAS_GMCH_DISPLAY(dev_priv) && INTEL_GEN(dev_priv) >= 7)
+#define HAS_CUR_FBC(dev_priv)	(!HAS_GMCH(dev_priv) && INTEL_GEN(dev_priv) >= 7)
 
 #define HAS_IPS(dev_priv)	(IS_HSW_ULT(dev_priv) || IS_BROADWELL(dev_priv))
 
@@ -2570,7 +2582,7 @@ static inline unsigned int i915_sg_segment_size(void)
 #define HAS_PCH_NOP(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_NOP)
 #define HAS_PCH_SPLIT(dev_priv) (INTEL_PCH_TYPE(dev_priv) != PCH_NONE)
 
-#define HAS_GMCH_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch_display)
+#define HAS_GMCH(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch)
 
 #define HAS_LSPCON(dev_priv) (INTEL_GEN(dev_priv) >= 9)
 
@@ -3305,6 +3317,20 @@ mkwrite_device_info(struct drm_i915_private *dev_priv)
 	return (struct intel_device_info *)INTEL_INFO(dev_priv);
 }
 
+static inline struct intel_sseu
+intel_device_default_sseu(struct drm_i915_private *i915)
+{
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+	struct intel_sseu value = {
+		.slice_mask = sseu->slice_mask,
+		.subslice_mask = sseu->subslice_mask[0],
+		.min_eus_per_subslice = sseu->max_eus_per_subslice,
+		.max_eus_per_subslice = sseu->max_eus_per_subslice,
+	};
+
+	return value;
+}
+
 /* modesetting */
 extern void intel_modeset_init_hw(struct drm_device *dev);
 extern int intel_modeset_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e802af64d628..6728ea5c71d4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1681,6 +1681,16 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+static inline bool
+__vma_matches(struct vm_area_struct *vma, struct file *filp,
+	      unsigned long addr, unsigned long size)
+{
+	if (vma->vm_file != filp)
+		return false;
+
+	return vma->vm_start == addr && (vma->vm_end - vma->vm_start) == size;
+}
+
 /**
  * i915_gem_mmap_ioctl - Maps the contents of an object, returning the address
  *			 it is mapped to.
@@ -1730,6 +1740,9 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 	addr = vm_mmap(obj->base.filp, 0, args->size,
 		       PROT_READ | PROT_WRITE, MAP_SHARED,
 		       args->offset);
+	if (IS_ERR_VALUE(addr))
+		goto err;
+
 	if (args->flags & I915_MMAP_WC) {
 		struct mm_struct *mm = current->mm;
 		struct vm_area_struct *vma;
@@ -1739,23 +1752,28 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			return -EINTR;
 		}
 		vma = find_vma(mm, addr);
-		if (vma)
+		if (vma && __vma_matches(vma, obj->base.filp, addr, args->size))
 			vma->vm_page_prot =
 				pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 		else
 			addr = -ENOMEM;
 		up_write(&mm->mmap_sem);
+		if (IS_ERR_VALUE(addr))
+			goto err;
 
 		/* This may race, but that's ok, it only gets set */
 		WRITE_ONCE(obj->frontbuffer_ggtt_origin, ORIGIN_CPU);
 	}
 	i915_gem_object_put(obj);
-	if (IS_ERR((void *)addr))
-		return addr;
 
 	args->addr_ptr = (u64)addr;
 
 	return 0;
+
+err:
+	i915_gem_object_put(obj);
+
+	return addr;
 }
 
 static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
@@ -3020,7 +3038,7 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 
 	GEM_BUG_ON(i915->gt.active_requests);
 	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
+		GEM_BUG_ON(__i915_active_request_peek(&engine->timeline.last_request));
 		GEM_BUG_ON(engine->last_retired_context !=
 			   to_intel_context(i915->kernel_context, engine));
 	}
@@ -3266,7 +3284,7 @@ wait_for_timelines(struct drm_i915_private *i915,
 	list_for_each_entry(tl, &gt->active_list, link) {
 		struct i915_request *rq;
 
-		rq = i915_gem_active_get_unlocked(&tl->last_request);
+		rq = i915_active_request_get_unlocked(&tl->last_request);
 		if (!rq)
 			continue;
 
@@ -4167,7 +4185,8 @@ out:
 }
 
 static void
-frontbuffer_retire(struct i915_gem_active *active, struct i915_request *request)
+frontbuffer_retire(struct i915_active_request *active,
+		   struct i915_request *request)
 {
 	struct drm_i915_gem_object *obj =
 		container_of(active, typeof(*obj), frontbuffer_write);
@@ -4194,7 +4213,8 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 	obj->resv = &obj->__builtin_resv;
 
 	obj->frontbuffer_ggtt_origin = ORIGIN_GTT;
-	init_request_active(&obj->frontbuffer_write, frontbuffer_retire);
+	i915_active_request_init(&obj->frontbuffer_write,
+				 NULL, frontbuffer_retire);
 
 	obj->mm.madv = I915_MADV_WILLNEED;
 	INIT_RADIX_TREE(&obj->mm.get_page.radix, GFP_KERNEL | __GFP_NOWARN);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 6faf1f6faab5..280813a4bf82 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -89,6 +89,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_lrc_reg.h"
 #include "intel_workarounds.h"
 
 #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
@@ -321,6 +322,15 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
 	return desc;
 }
 
+static void intel_context_retire(struct i915_active_request *active,
+				 struct i915_request *rq)
+{
+	struct intel_context *ce =
+		container_of(active, typeof(*ce), active_tracker);
+
+	intel_context_unpin(ce);
+}
+
 void
 intel_context_init(struct intel_context *ce,
 		   struct i915_gem_context *ctx,
@@ -330,6 +340,12 @@ intel_context_init(struct intel_context *ce,
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
+
+	/* Use the whole device by default */
+	ce->sseu = intel_device_default_sseu(ctx->i915);
+
+	i915_active_request_init(&ce->active_tracker,
+				 NULL, intel_context_retire);
 }
 
 static struct i915_gem_context *
@@ -653,8 +669,8 @@ last_request_on_engine(struct i915_timeline *timeline,
 
 	GEM_BUG_ON(timeline == &engine->timeline);
 
-	rq = i915_gem_active_raw(&timeline->last_request,
-				 &engine->i915->drm.struct_mutex);
+	rq = i915_active_request_raw(&timeline->last_request,
+				     &engine->i915->drm.struct_mutex);
 	if (rq && rq->engine == engine) {
 		GEM_TRACE("last request for %s on engine %s: %llx:%llu\n",
 			  timeline->name, engine->name,
@@ -847,6 +863,56 @@ out:
 	return 0;
 }
 
+static int get_sseu(struct i915_gem_context *ctx,
+		    struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_gem_context_param_sseu user_sseu;
+	struct intel_engine_cs *engine;
+	struct intel_context *ce;
+	int ret;
+
+	if (args->size == 0)
+		goto out;
+	else if (args->size < sizeof(user_sseu))
+		return -EINVAL;
+
+	if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+			   sizeof(user_sseu)))
+		return -EFAULT;
+
+	if (user_sseu.flags || user_sseu.rsvd)
+		return -EINVAL;
+
+	engine = intel_engine_lookup_user(ctx->i915,
+					  user_sseu.engine_class,
+					  user_sseu.engine_instance);
+	if (!engine)
+		return -EINVAL;
+
+	/* Only use for mutex here is to serialize get_param and set_param. */
+	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+	if (ret)
+		return ret;
+
+	ce = to_intel_context(ctx, engine);
+
+	user_sseu.slice_mask = ce->sseu.slice_mask;
+	user_sseu.subslice_mask = ce->sseu.subslice_mask;
+	user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice;
+	user_sseu.max_eus_per_subslice = ce->sseu.max_eus_per_subslice;
+
+	mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+	if (copy_to_user(u64_to_user_ptr(args->value), &user_sseu,
+			 sizeof(user_sseu)))
+		return -EFAULT;
+
+out:
+	args->size = sizeof(user_sseu);
+
+	return 0;
+}
+
 int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file)
 {
@@ -859,15 +925,17 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	if (!ctx)
 		return -ENOENT;
 
-	args->size = 0;
 	switch (args->param) {
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 		ret = -EINVAL;
 		break;
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
+		args->size = 0;
 		args->value = test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags);
 		break;
 	case I915_CONTEXT_PARAM_GTT_SIZE:
+		args->size = 0;
+
 		if (ctx->ppgtt)
 			args->value = ctx->ppgtt->vm.total;
 		else if (to_i915(dev)->mm.aliasing_ppgtt)
@@ -876,14 +944,20 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 			args->value = to_i915(dev)->ggtt.vm.total;
 		break;
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		args->size = 0;
 		args->value = i915_gem_context_no_error_capture(ctx);
 		break;
 	case I915_CONTEXT_PARAM_BANNABLE:
+		args->size = 0;
 		args->value = i915_gem_context_is_bannable(ctx);
 		break;
 	case I915_CONTEXT_PARAM_PRIORITY:
+		args->size = 0;
 		args->value = ctx->sched.priority >> I915_USER_PRIORITY_SHIFT;
 		break;
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = get_sseu(ctx, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -893,6 +967,281 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	return ret;
 }
 
+static int gen8_emit_rpcs_config(struct i915_request *rq,
+				 struct intel_context *ce,
+				 struct intel_sseu sseu)
+{
+	u64 offset;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	offset = i915_ggtt_offset(ce->state) +
+		 LRC_STATE_PN * PAGE_SIZE +
+		 (CTX_R_PWR_CLK_STATE + 1) * 4;
+
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = lower_32_bits(offset);
+	*cs++ = upper_32_bits(offset);
+	*cs++ = gen8_make_rpcs(rq->i915, &sseu);
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int
+gen8_modify_rpcs_gpu(struct intel_context *ce,
+		     struct intel_engine_cs *engine,
+		     struct intel_sseu sseu)
+{
+	struct drm_i915_private *i915 = engine->i915;
+	struct i915_request *rq, *prev;
+	intel_wakeref_t wakeref;
+	int ret;
+
+	GEM_BUG_ON(!ce->pin_count);
+
+	lockdep_assert_held(&i915->drm.struct_mutex);
+
+	/* Submitting requests etc needs the hw awake. */
+	wakeref = intel_runtime_pm_get(i915);
+
+	rq = i915_request_alloc(engine, i915->kernel_context);
+	if (IS_ERR(rq)) {
+		ret = PTR_ERR(rq);
+		goto out_put;
+	}
+
+	/* Queue this switch after all other activity by this context. */
+	prev = i915_active_request_raw(&ce->ring->timeline->last_request,
+				       &i915->drm.struct_mutex);
+	if (prev && !i915_request_completed(prev)) {
+		ret = i915_request_await_dma_fence(rq, &prev->fence);
+		if (ret < 0)
+			goto out_add;
+	}
+
+	/* Order all following requests to be after. */
+	ret = i915_timeline_set_barrier(ce->ring->timeline, rq);
+	if (ret)
+		goto out_add;
+
+	ret = gen8_emit_rpcs_config(rq, ce, sseu);
+	if (ret)
+		goto out_add;
+
+	/*
+	 * Guarantee context image and the timeline remains pinned until the
+	 * modifying request is retired by setting the ce activity tracker.
+	 *
+	 * But we only need to take one pin on the account of it. Or in other
+	 * words transfer the pinned ce object to tracked active request.
+	 */
+	if (!i915_active_request_isset(&ce->active_tracker))
+		__intel_context_pin(ce);
+	__i915_active_request_set(&ce->active_tracker, rq);
+
+out_add:
+	i915_request_add(rq);
+out_put:
+	intel_runtime_pm_put(i915, wakeref);
+
+	return ret;
+}
+
+static int
+__i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+				    struct intel_engine_cs *engine,
+				    struct intel_sseu sseu)
+{
+	struct intel_context *ce = to_intel_context(ctx, engine);
+	int ret = 0;
+
+	GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
+	GEM_BUG_ON(engine->id != RCS);
+
+	/* Nothing to do if unmodified. */
+	if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
+		return 0;
+
+	/*
+	 * If context is not idle we have to submit an ordered request to modify
+	 * its context image via the kernel context. Pristine and idle contexts
+	 * will be configured on pinning.
+	 */
+	if (ce->pin_count)
+		ret = gen8_modify_rpcs_gpu(ce, engine, sseu);
+
+	if (!ret)
+		ce->sseu = sseu;
+
+	return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine,
+				  struct intel_sseu sseu)
+{
+	int ret;
+
+	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+	if (ret)
+		return ret;
+
+	ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+
+	mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+	return ret;
+}
+
+static int
+user_to_context_sseu(struct drm_i915_private *i915,
+		     const struct drm_i915_gem_context_param_sseu *user,
+		     struct intel_sseu *context)
+{
+	const struct sseu_dev_info *device = &RUNTIME_INFO(i915)->sseu;
+
+	/* No zeros in any field. */
+	if (!user->slice_mask || !user->subslice_mask ||
+	    !user->min_eus_per_subslice || !user->max_eus_per_subslice)
+		return -EINVAL;
+
+	/* Max > min. */
+	if (user->max_eus_per_subslice < user->min_eus_per_subslice)
+		return -EINVAL;
+
+	/*
+	 * Some future proofing on the types since the uAPI is wider than the
+	 * current internal implementation.
+	 */
+	if (overflows_type(user->slice_mask, context->slice_mask) ||
+	    overflows_type(user->subslice_mask, context->subslice_mask) ||
+	    overflows_type(user->min_eus_per_subslice,
+			   context->min_eus_per_subslice) ||
+	    overflows_type(user->max_eus_per_subslice,
+			   context->max_eus_per_subslice))
+		return -EINVAL;
+
+	/* Check validity against hardware. */
+	if (user->slice_mask & ~device->slice_mask)
+		return -EINVAL;
+
+	if (user->subslice_mask & ~device->subslice_mask[0])
+		return -EINVAL;
+
+	if (user->max_eus_per_subslice > device->max_eus_per_subslice)
+		return -EINVAL;
+
+	context->slice_mask = user->slice_mask;
+	context->subslice_mask = user->subslice_mask;
+	context->min_eus_per_subslice = user->min_eus_per_subslice;
+	context->max_eus_per_subslice = user->max_eus_per_subslice;
+
+	/* Part specific restrictions. */
+	if (IS_GEN(i915, 11)) {
+		unsigned int hw_s = hweight8(device->slice_mask);
+		unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]);
+		unsigned int req_s = hweight8(context->slice_mask);
+		unsigned int req_ss = hweight8(context->subslice_mask);
+
+		/*
+		 * Only full subslice enablement is possible if more than one
+		 * slice is turned on.
+		 */
+		if (req_s > 1 && req_ss != hw_ss_per_s)
+			return -EINVAL;
+
+		/*
+		 * If more than four (SScount bitfield limit) subslices are
+		 * requested then the number has to be even.
+		 */
+		if (req_ss > 4 && (req_ss & 1))
+			return -EINVAL;
+
+		/*
+		 * If only one slice is enabled and subslice count is below the
+		 * device full enablement, it must be at most half of the all
+		 * available subslices.
+		 */
+		if (req_s == 1 && req_ss < hw_ss_per_s &&
+		    req_ss > (hw_ss_per_s / 2))
+			return -EINVAL;
+
+		/* ABI restriction - VME use case only. */
+
+		/* All slices or one slice only. */
+		if (req_s != 1 && req_s != hw_s)
+			return -EINVAL;
+
+		/*
+		 * Half subslices or full enablement only when one slice is
+		 * enabled.
+		 */
+		if (req_s == 1 &&
+		    (req_ss != hw_ss_per_s && req_ss != (hw_ss_per_s / 2)))
+			return -EINVAL;
+
+		/* No EU configuration changes. */
+		if ((user->min_eus_per_subslice !=
+		     device->max_eus_per_subslice) ||
+		    (user->max_eus_per_subslice !=
+		     device->max_eus_per_subslice))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_sseu(struct i915_gem_context *ctx,
+		    struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_private *i915 = ctx->i915;
+	struct drm_i915_gem_context_param_sseu user_sseu;
+	struct intel_engine_cs *engine;
+	struct intel_sseu sseu;
+	int ret;
+
+	if (args->size < sizeof(user_sseu))
+		return -EINVAL;
+
+	if (!IS_GEN(i915, 11))
+		return -ENODEV;
+
+	if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+			   sizeof(user_sseu)))
+		return -EFAULT;
+
+	if (user_sseu.flags || user_sseu.rsvd)
+		return -EINVAL;
+
+	engine = intel_engine_lookup_user(i915,
+					  user_sseu.engine_class,
+					  user_sseu.engine_instance);
+	if (!engine)
+		return -EINVAL;
+
+	/* Only render engine supports RPCS configuration. */
+	if (engine->class != RENDER_CLASS)
+		return -ENODEV;
+
+	ret = user_to_context_sseu(i915, &user_sseu, &sseu);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+	if (ret)
+		return ret;
+
+	args->size = sizeof(user_sseu);
+
+	return 0;
+}
+
 int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file)
 {
@@ -955,7 +1304,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 					I915_USER_PRIORITY(priority);
 		}
 		break;
-
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = set_sseu(ctx, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 6ba40ff6b91f..ca150a764c24 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -31,6 +31,7 @@
 
 #include "i915_gem.h"
 #include "i915_scheduler.h"
+#include "intel_device_info.h"
 
 struct pid;
 
@@ -53,6 +54,16 @@ struct intel_context_ops {
 	void (*destroy)(struct intel_context *ce);
 };
 
+/*
+ * Powergating configuration for a particular (context,engine).
+ */
+struct intel_sseu {
+	u8 slice_mask;
+	u8 subslice_mask;
+	u8 min_eus_per_subslice;
+	u8 max_eus_per_subslice;
+};
+
 /**
  * struct i915_gem_context - client state
  *
@@ -172,7 +183,16 @@ struct i915_gem_context {
 		u64 lrc_desc;
 		int pin_count;
 
+		/**
+		 * active_tracker: Active tracker for the external rq activity
+		 * on this intel_context object.
+		 */
+		struct i915_active_request active_tracker;
+
 		const struct intel_context_ops *ops;
+
+		/** sseu: Control eu/slice partitioning */
+		struct intel_sseu sseu;
 	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8eedf7cac493..02adcaf6ebea 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -753,6 +753,68 @@ static int eb_select_context(struct i915_execbuffer *eb)
 	return 0;
 }
 
+static struct i915_request *__eb_wait_for_ring(struct intel_ring *ring)
+{
+	struct i915_request *rq;
+
+	/*
+	 * Completely unscientific finger-in-the-air estimates for suitable
+	 * maximum user request size (to avoid blocking) and then backoff.
+	 */
+	if (intel_ring_update_space(ring) >= PAGE_SIZE)
+		return NULL;
+
+	/*
+	 * Find a request that after waiting upon, there will be at least half
+	 * the ring available. The hysteresis allows us to compete for the
+	 * shared ring and should mean that we sleep less often prior to
+	 * claiming our resources, but not so long that the ring completely
+	 * drains before we can submit our next request.
+	 */
+	list_for_each_entry(rq, &ring->request_list, ring_link) {
+		if (__intel_ring_space(rq->postfix,
+				       ring->emit, ring->size) > ring->size / 2)
+			break;
+	}
+	if (&rq->ring_link == &ring->request_list)
+		return NULL; /* weird, we will check again later for real */
+
+	return i915_request_get(rq);
+}
+
+static int eb_wait_for_ring(const struct i915_execbuffer *eb)
+{
+	const struct intel_context *ce;
+	struct i915_request *rq;
+	int ret = 0;
+
+	/*
+	 * Apply a light amount of backpressure to prevent excessive hogs
+	 * from blocking waiting for space whilst holding struct_mutex and
+	 * keeping all of their resources pinned.
+	 */
+
+	ce = to_intel_context(eb->ctx, eb->engine);
+	if (!ce->ring) /* first use, assume empty! */
+		return 0;
+
+	rq = __eb_wait_for_ring(ce->ring);
+	if (rq) {
+		mutex_unlock(&eb->i915->drm.struct_mutex);
+
+		if (i915_request_wait(rq,
+				      I915_WAIT_INTERRUPTIBLE,
+				      MAX_SCHEDULE_TIMEOUT) < 0)
+			ret = -EINTR;
+
+		i915_request_put(rq);
+
+		mutex_lock(&eb->i915->drm.struct_mutex);
+	}
+
+	return ret;
+}
+
 static int eb_lookup_vmas(struct i915_execbuffer *eb)
 {
 	struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
@@ -2291,6 +2353,10 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (err)
 		goto err_rpm;
 
+	err = eb_wait_for_ring(&eb); /* may temporarily drop struct_mutex */
+	if (unlikely(err))
+		goto err_unlock;
+
 	err = eb_relocate(&eb);
 	if (err) {
 		/*
@@ -2435,6 +2501,7 @@ err_batch_unpin:
 err_vma:
 	if (eb.exec)
 		eb_release_vmas(&eb);
+err_unlock:
 	mutex_unlock(&dev->struct_mutex);
 err_rpm:
 	intel_runtime_pm_put(eb.i915, wakeref);
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 46e259661294..e037e94792f3 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -223,7 +223,7 @@ static int fence_update(struct drm_i915_fence_reg *fence,
 			 i915_gem_object_get_tiling(vma->obj)))
 			return -EINVAL;
 
-		ret = i915_gem_active_retire(&vma->last_fence,
+		ret = i915_active_request_retire(&vma->last_fence,
 					     &vma->obj->base.dev->struct_mutex);
 		if (ret)
 			return ret;
@@ -232,7 +232,7 @@ static int fence_update(struct drm_i915_fence_reg *fence,
 	if (fence->vma) {
 		struct i915_vma *old = fence->vma;
 
-		ret = i915_gem_active_retire(&old->last_fence,
+		ret = i915_active_request_retire(&old->last_fence,
 					     &old->obj->base.dev->struct_mutex);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 49b00996a15e..d646d37eec2f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1917,14 +1917,13 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	if (!vma)
 		return ERR_PTR(-ENOMEM);
 
-	init_request_active(&vma->last_fence, NULL);
+	i915_active_init(i915, &vma->active, NULL);
+	INIT_ACTIVE_REQUEST(&vma->last_fence);
 
 	vma->vm = &ggtt->vm;
 	vma->ops = &pd_vma_ops;
 	vma->private = ppgtt;
 
-	vma->active = RB_ROOT;
-
 	vma->size = size;
 	vma->fence_size = size;
 	vma->flags = I915_VMA_GGTT;
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 73fec917d097..fab040331cdb 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -175,7 +175,7 @@ struct drm_i915_gem_object {
 
 	atomic_t frontbuffer_bits;
 	unsigned int frontbuffer_ggtt_origin; /* write once */
-	struct i915_gem_active frontbuffer_write;
+	struct i915_active_request frontbuffer_write;
 
 	/** Current tiling stride for the object, if it's tiled. */
 	unsigned int tiling_and_stride;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 6e2e5ed2bd0a..9a65341fec09 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1062,23 +1062,23 @@ i915_error_object_create(struct drm_i915_private *i915,
 }
 
 /* The error capture is special as tries to run underneath the normal
- * locking rules - so we use the raw version of the i915_gem_active lookup.
+ * locking rules - so we use the raw version of the i915_active_request lookup.
  */
 static inline u32
-__active_get_seqno(struct i915_gem_active *active)
+__active_get_seqno(struct i915_active_request *active)
 {
 	struct i915_request *request;
 
-	request = __i915_gem_active_peek(active);
+	request = __i915_active_request_peek(active);
 	return request ? request->global_seqno : 0;
 }
 
 static inline int
-__active_get_engine_id(struct i915_gem_active *active)
+__active_get_engine_id(struct i915_active_request *active)
 {
 	struct i915_request *request;
 
-	request = __i915_gem_active_peek(active);
+	request = __i915_active_request_peek(active);
 	return request ? request->engine->id : -1;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 5d05572c9ff4..66f82f3f050f 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -28,6 +28,7 @@
 
 #include <drm/drm_drv.h>
 
+#include "i915_active.h"
 #include "i915_drv.h"
 #include "i915_selftest.h"
 
@@ -89,7 +90,7 @@
 	.num_pipes = 1, \
 	.display.has_overlay = 1, \
 	.display.overlay_needs_physical = 1, \
-	.display.has_gmch_display = 1, \
+	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
 	.hws_needs_physical = 1, \
 	.unfenced_needs_alignment = 1, \
@@ -130,7 +131,7 @@ static const struct intel_device_info intel_i865g_info = {
 #define GEN3_FEATURES \
 	GEN(3), \
 	.num_pipes = 2, \
-	.display.has_gmch_display = 1, \
+	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
 	.ring_mask = RENDER_RING, \
 	.has_snoop = true, \
@@ -207,7 +208,7 @@ static const struct intel_device_info intel_pineview_info = {
 	GEN(4), \
 	.num_pipes = 2, \
 	.display.has_hotplug = 1, \
-	.display.has_gmch_display = 1, \
+	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
 	.ring_mask = RENDER_RING, \
 	.has_snoop = true, \
@@ -383,7 +384,7 @@ static const struct intel_device_info intel_valleyview_info = {
 	.num_pipes = 2,
 	.has_runtime_pm = 1,
 	.has_rc6 = 1,
-	.display.has_gmch_display = 1,
+	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
 	.ppgtt = INTEL_PPGTT_FULL,
 	.has_snoop = true,
@@ -475,7 +476,7 @@ static const struct intel_device_info intel_cherryview_info = {
 	.has_runtime_pm = 1,
 	.has_rc6 = 1,
 	.has_logical_ring_contexts = 1,
-	.display.has_gmch_display = 1,
+	.display.has_gmch = 1,
 	.ppgtt = INTEL_PPGTT_FULL,
 	.has_reset_engine = 1,
 	.has_snoop = true,
@@ -800,6 +801,8 @@ static int __init i915_init(void)
 	bool use_kms = true;
 	int err;
 
+	i915_global_active_init();
+
 	err = i915_mock_selftests();
 	if (err)
 		return err > 0 ? 0 : err;
@@ -831,6 +834,7 @@ static void __exit i915_exit(void)
 		return;
 
 	pci_unregister_driver(&i915_pci_driver);
+	i915_global_active_exit();
 }
 
 module_init(i915_init);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 727118301f91..9ebf99f3d8d3 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1677,6 +1677,11 @@ static void gen8_update_reg_state_unlocked(struct i915_gem_context *ctx,
 
 		CTX_REG(reg_state, state_offset, flex_regs[i], value);
 	}
+
+	CTX_REG(reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
+		gen8_make_rpcs(dev_priv,
+			       &to_intel_context(ctx,
+						 dev_priv->engine[RCS])->sseu));
 }
 
 /*
@@ -2098,21 +2103,21 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	if (ret)
 		goto err_lock;
 
+	stream->ops = &i915_oa_stream_ops;
+	dev_priv->perf.oa.exclusive_stream = stream;
+
 	ret = dev_priv->perf.oa.ops.enable_metric_set(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
 	}
 
-	stream->ops = &i915_oa_stream_ops;
-
-	dev_priv->perf.oa.exclusive_stream = stream;
-
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	return 0;
 
 err_enable:
+	dev_priv->perf.oa.exclusive_stream = NULL;
 	dev_priv->perf.oa.ops.disable_metric_set(dev_priv);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index b1cb2d3cae16..13d70b90dd0f 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -599,7 +599,8 @@ static void i915_pmu_enable(struct perf_event *event)
 	 * Update the bitmask of enabled events and increment
 	 * the event reference counter.
 	 */
-	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);
+	BUILD_BUG_ON(ARRAY_SIZE(i915->pmu.enable_count) != I915_PMU_MASK_BITS);
+	GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count));
 	GEM_BUG_ON(i915->pmu.enable_count[bit] == ~0);
 	i915->pmu.enable |= BIT_ULL(bit);
 	i915->pmu.enable_count[bit]++;
@@ -620,11 +621,16 @@ static void i915_pmu_enable(struct perf_event *event)
 		engine = intel_engine_lookup_user(i915,
 						  engine_event_class(event),
 						  engine_event_instance(event));
-		GEM_BUG_ON(!engine);
-		engine->pmu.enable |= BIT(sample);
 
-		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
+		BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.enable_count) !=
+			     I915_ENGINE_SAMPLE_COUNT);
+		BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.sample) !=
+			     I915_ENGINE_SAMPLE_COUNT);
+		GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count));
+		GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample));
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0);
+
+		engine->pmu.enable |= BIT(sample);
 		engine->pmu.enable_count[sample]++;
 	}
 
@@ -654,9 +660,11 @@ static void i915_pmu_disable(struct perf_event *event)
 		engine = intel_engine_lookup_user(i915,
 						  engine_event_class(event),
 						  engine_event_instance(event));
-		GEM_BUG_ON(!engine);
-		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
+
+		GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count));
+		GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample));
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == 0);
+
 		/*
 		 * Decrement the reference count and clear the enabled
 		 * bitmask when the last listener on an event goes away.
@@ -665,7 +673,7 @@ static void i915_pmu_disable(struct perf_event *event)
 			engine->pmu.enable &= ~BIT(sample);
 	}
 
-	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);
+	GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count));
 	GEM_BUG_ON(i915->pmu.enable_count[bit] == 0);
 	/*
 	 * Decrement the reference count and clear the enabled
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 7f164ca3db12..b3728c5f13e7 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -31,6 +31,8 @@ enum {
 	((1 << I915_PMU_SAMPLE_BITS) + \
 	 (I915_PMU_LAST + 1 - __I915_PMU_OTHER(0)))
 
+#define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1)
+
 struct i915_pmu_sample {
 	u64 cur;
 };
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ede54fdc1676..638a586469f9 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -6000,7 +6000,7 @@ enum {
 #define   PLANE_WM_EN		(1 << 31)
 #define   PLANE_WM_LINES_SHIFT	14
 #define   PLANE_WM_LINES_MASK	0x1f
-#define   PLANE_WM_BLOCKS_MASK	0x3ff
+#define   PLANE_WM_BLOCKS_MASK	0x7ff /* skl+: 10 bits, icl+ 11 bits */
 
 #define _CUR_WM_0(pipe) _PIPE(pipe, _CUR_WM_A_0, _CUR_WM_B_0)
 #define CUR_WM(pipe, level) _MMIO(_CUR_WM_0(pipe) + ((4) * (level)))
@@ -6784,8 +6784,7 @@ enum {
 
 #define _PLANE_BUF_CFG_1_B			0x7127c
 #define _PLANE_BUF_CFG_2_B			0x7137c
-#define  SKL_DDB_ENTRY_MASK			0x3FF
-#define  ICL_DDB_ENTRY_MASK			0x7FF
+#define  DDB_ENTRY_MASK				0x7FF /* skl+: 10 bits, icl+ 11 bits */
 #define  DDB_ENTRY_END_SHIFT			16
 #define _PLANE_BUF_CFG_1(pipe)	\
 	_PIPE(pipe, _PLANE_BUF_CFG_1_A, _PLANE_BUF_CFG_1_B)
@@ -7618,6 +7617,7 @@ enum {
 #define _PIPEB_CHICKEN			0x71038
 #define _PIPEC_CHICKEN			0x72038
 #define  PER_PIXEL_ALPHA_BYPASS_EN	(1 << 7)
+#define  PM_FILL_MAINTAIN_DBUF_FULLNESS	(1 << 0)
 #define PIPE_CHICKEN(pipe)		_MMIO_PIPE(pipe, _PIPEA_CHICKEN,\
 						   _PIPEB_CHICKEN)
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 9ed5baf157a3..c2a5c48c7541 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -29,6 +29,7 @@
 #include <linux/sched/signal.h>
 
 #include "i915_drv.h"
+#include "i915_active.h"
 #include "i915_reset.h"
 
 static const char *i915_fence_get_driver_name(struct dma_fence *fence)
@@ -125,12 +126,6 @@ static void unreserve_gt(struct drm_i915_private *i915)
 		i915_gem_park(i915);
 }
 
-void i915_gem_retire_noop(struct i915_gem_active *active,
-			  struct i915_request *request)
-{
-	/* Space left intentionally blank */
-}
-
 static void advance_ring(struct i915_request *request)
 {
 	struct intel_ring *ring = request->ring;
@@ -244,7 +239,7 @@ static void __retire_engine_upto(struct intel_engine_cs *engine,
 
 static void i915_request_retire(struct i915_request *request)
 {
-	struct i915_gem_active *active, *next;
+	struct i915_active_request *active, *next;
 
 	GEM_TRACE("%s fence %llx:%lld, global=%d, current %d:%d\n",
 		  request->engine->name,
@@ -278,10 +273,10 @@ static void i915_request_retire(struct i915_request *request)
 		 * we may spend an inordinate amount of time simply handling
 		 * the retirement of requests and processing their callbacks.
 		 * Of which, this loop itself is particularly hot due to the
-		 * cache misses when jumping around the list of i915_gem_active.
-		 * So we try to keep this loop as streamlined as possible and
-		 * also prefetch the next i915_gem_active to try and hide
-		 * the likely cache miss.
+		 * cache misses when jumping around the list of
+		 * i915_active_request.  So we try to keep this loop as
+		 * streamlined as possible and also prefetch the next
+		 * i915_active_request to try and hide the likely cache miss.
 		 */
 		prefetchw(next);
 
@@ -526,6 +521,11 @@ out:
 	return kmem_cache_alloc(ce->gem_context->i915->requests, GFP_KERNEL);
 }
 
+static int add_timeline_barrier(struct i915_request *rq)
+{
+	return i915_request_await_active_request(rq, &rq->timeline->barrier);
+}
+
 /**
  * i915_request_alloc - allocate a request structure
  *
@@ -582,7 +582,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 * We use RCU to look up requests in flight. The lookups may
 	 * race with the request being allocated from the slab freelist.
 	 * That is the request we are writing to here, may be in the process
-	 * of being read by __i915_gem_active_get_rcu(). As such,
+	 * of being read by __i915_active_request_get_rcu(). As such,
 	 * we have to be very careful when overwriting the contents. During
 	 * the RCU lookup, we change chase the request->engine pointer,
 	 * read the request->global_seqno and increment the reference count.
@@ -668,6 +668,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 */
 	rq->head = rq->ring->emit;
 
+	ret = add_timeline_barrier(rq);
+	if (ret)
+		goto err_unwind;
+
 	ret = engine->request_alloc(rq);
 	if (ret)
 		goto err_unwind;
@@ -920,8 +924,8 @@ void i915_request_add(struct i915_request *request)
 	 * see a more recent value in the hws than we are tracking.
 	 */
 
-	prev = i915_gem_active_raw(&timeline->last_request,
-				   &request->i915->drm.struct_mutex);
+	prev = i915_active_request_raw(&timeline->last_request,
+				       &request->i915->drm.struct_mutex);
 	if (prev && !i915_request_completed(prev)) {
 		i915_sw_fence_await_sw_fence(&request->submit, &prev->submit,
 					     &request->submitq);
@@ -937,7 +941,7 @@ void i915_request_add(struct i915_request *request)
 	spin_unlock_irq(&timeline->lock);
 
 	GEM_BUG_ON(timeline->seqno != request->fence.seqno);
-	i915_gem_active_set(&timeline->last_request, request);
+	__i915_active_request_set(&timeline->last_request, request);
 
 	list_add_tail(&request->ring_link, &ring->request_list);
 	if (list_is_first(&request->ring_link, &ring->request_list)) {
@@ -968,7 +972,7 @@ void i915_request_add(struct i915_request *request)
 		 * Allow interactive/synchronous clients to jump ahead of
 		 * the bulk clients. (FQ_CODEL)
 		 */
-		if (!prev || i915_request_completed(prev))
+		if (list_empty(&request->sched.signalers_list))
 			attr.priority |= I915_PRIORITY_NEWCLIENT;
 
 		engine->schedule(request, &attr);
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 3cffb96203b9..40f3e8dcbdd5 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -403,387 +403,4 @@ static inline void i915_request_mark_complete(struct i915_request *rq)
 
 void i915_retire_requests(struct drm_i915_private *i915);
 
-/*
- * We treat requests as fences. This is not be to confused with our
- * "fence registers" but pipeline synchronisation objects ala GL_ARB_sync.
- * We use the fences to synchronize access from the CPU with activity on the
- * GPU, for example, we should not rewrite an object's PTE whilst the GPU
- * is reading them. We also track fences at a higher level to provide
- * implicit synchronisation around GEM objects, e.g. set-domain will wait
- * for outstanding GPU rendering before marking the object ready for CPU
- * access, or a pageflip will wait until the GPU is complete before showing
- * the frame on the scanout.
- *
- * In order to use a fence, the object must track the fence it needs to
- * serialise with. For example, GEM objects want to track both read and
- * write access so that we can perform concurrent read operations between
- * the CPU and GPU engines, as well as waiting for all rendering to
- * complete, or waiting for the last GPU user of a "fence register". The
- * object then embeds a #i915_gem_active to track the most recent (in
- * retirement order) request relevant for the desired mode of access.
- * The #i915_gem_active is updated with i915_gem_active_set() to track the
- * most recent fence request, typically this is done as part of
- * i915_vma_move_to_active().
- *
- * When the #i915_gem_active completes (is retired), it will
- * signal its completion to the owner through a callback as well as mark
- * itself as idle (i915_gem_active.request == NULL). The owner
- * can then perform any action, such as delayed freeing of an active
- * resource including itself.
- */
-struct i915_gem_active;
-
-typedef void (*i915_gem_retire_fn)(struct i915_gem_active *,
-				   struct i915_request *);
-
-struct i915_gem_active {
-	struct i915_request __rcu *request;
-	struct list_head link;
-	i915_gem_retire_fn retire;
-};
-
-void i915_gem_retire_noop(struct i915_gem_active *,
-			  struct i915_request *request);
-
-/**
- * init_request_active - prepares the activity tracker for use
- * @active - the active tracker
- * @func - a callback when then the tracker is retired (becomes idle),
- *         can be NULL
- *
- * init_request_active() prepares the embedded @active struct for use as
- * an activity tracker, that is for tracking the last known active request
- * associated with it. When the last request becomes idle, when it is retired
- * after completion, the optional callback @func is invoked.
- */
-static inline void
-init_request_active(struct i915_gem_active *active,
-		    i915_gem_retire_fn retire)
-{
-	RCU_INIT_POINTER(active->request, NULL);
-	INIT_LIST_HEAD(&active->link);
-	active->retire = retire ?: i915_gem_retire_noop;
-}
-
-/**
- * i915_gem_active_set - updates the tracker to watch the current request
- * @active - the active tracker
- * @request - the request to watch
- *
- * i915_gem_active_set() watches the given @request for completion. Whilst
- * that @request is busy, the @active reports busy. When that @request is
- * retired, the @active tracker is updated to report idle.
- */
-static inline void
-i915_gem_active_set(struct i915_gem_active *active,
-		    struct i915_request *request)
-{
-	list_move(&active->link, &request->active_list);
-	rcu_assign_pointer(active->request, request);
-}
-
-/**
- * i915_gem_active_set_retire_fn - updates the retirement callback
- * @active - the active tracker
- * @fn - the routine called when the request is retired
- * @mutex - struct_mutex used to guard retirements
- *
- * i915_gem_active_set_retire_fn() updates the function pointer that
- * is called when the final request associated with the @active tracker
- * is retired.
- */
-static inline void
-i915_gem_active_set_retire_fn(struct i915_gem_active *active,
-			      i915_gem_retire_fn fn,
-			      struct mutex *mutex)
-{
-	lockdep_assert_held(mutex);
-	active->retire = fn ?: i915_gem_retire_noop;
-}
-
-static inline struct i915_request *
-__i915_gem_active_peek(const struct i915_gem_active *active)
-{
-	/*
-	 * Inside the error capture (running with the driver in an unknown
-	 * state), we want to bend the rules slightly (a lot).
-	 *
-	 * Work is in progress to make it safer, in the meantime this keeps
-	 * the known issue from spamming the logs.
-	 */
-	return rcu_dereference_protected(active->request, 1);
-}
-
-/**
- * i915_gem_active_raw - return the active request
- * @active - the active tracker
- *
- * i915_gem_active_raw() returns the current request being tracked, or NULL.
- * It does not obtain a reference on the request for the caller, so the caller
- * must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_gem_active_raw(const struct i915_gem_active *active, struct mutex *mutex)
-{
-	return rcu_dereference_protected(active->request,
-					 lockdep_is_held(mutex));
-}
-
-/**
- * i915_gem_active_peek - report the active request being monitored
- * @active - the active tracker
- *
- * i915_gem_active_peek() returns the current request being tracked if
- * still active, or NULL. It does not obtain a reference on the request
- * for the caller, so the caller must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_gem_active_peek(const struct i915_gem_active *active, struct mutex *mutex)
-{
-	struct i915_request *request;
-
-	request = i915_gem_active_raw(active, mutex);
-	if (!request || i915_request_completed(request))
-		return NULL;
-
-	return request;
-}
-
-/**
- * i915_gem_active_get - return a reference to the active request
- * @active - the active tracker
- *
- * i915_gem_active_get() returns a reference to the active request, or NULL
- * if the active tracker is idle. The caller must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_gem_active_get(const struct i915_gem_active *active, struct mutex *mutex)
-{
-	return i915_request_get(i915_gem_active_peek(active, mutex));
-}
-
-/**
- * __i915_gem_active_get_rcu - return a reference to the active request
- * @active - the active tracker
- *
- * __i915_gem_active_get() returns a reference to the active request, or NULL
- * if the active tracker is idle. The caller must hold the RCU read lock, but
- * the returned pointer is safe to use outside of RCU.
- */
-static inline struct i915_request *
-__i915_gem_active_get_rcu(const struct i915_gem_active *active)
-{
-	/*
-	 * Performing a lockless retrieval of the active request is super
-	 * tricky. SLAB_TYPESAFE_BY_RCU merely guarantees that the backing
-	 * slab of request objects will not be freed whilst we hold the
-	 * RCU read lock. It does not guarantee that the request itself
-	 * will not be freed and then *reused*. Viz,
-	 *
-	 * Thread A			Thread B
-	 *
-	 * rq = active.request
-	 *				retire(rq) -> free(rq);
-	 *				(rq is now first on the slab freelist)
-	 *				active.request = NULL
-	 *
-	 *				rq = new submission on a new object
-	 * ref(rq)
-	 *
-	 * To prevent the request from being reused whilst the caller
-	 * uses it, we take a reference like normal. Whilst acquiring
-	 * the reference we check that it is not in a destroyed state
-	 * (refcnt == 0). That prevents the request being reallocated
-	 * whilst the caller holds on to it. To check that the request
-	 * was not reallocated as we acquired the reference we have to
-	 * check that our request remains the active request across
-	 * the lookup, in the same manner as a seqlock. The visibility
-	 * of the pointer versus the reference counting is controlled
-	 * by using RCU barriers (rcu_dereference and rcu_assign_pointer).
-	 *
-	 * In the middle of all that, we inspect whether the request is
-	 * complete. Retiring is lazy so the request may be completed long
-	 * before the active tracker is updated. Querying whether the
-	 * request is complete is far cheaper (as it involves no locked
-	 * instructions setting cachelines to exclusive) than acquiring
-	 * the reference, so we do it first. The RCU read lock ensures the
-	 * pointer dereference is valid, but does not ensure that the
-	 * seqno nor HWS is the right one! However, if the request was
-	 * reallocated, that means the active tracker's request was complete.
-	 * If the new request is also complete, then both are and we can
-	 * just report the active tracker is idle. If the new request is
-	 * incomplete, then we acquire a reference on it and check that
-	 * it remained the active request.
-	 *
-	 * It is then imperative that we do not zero the request on
-	 * reallocation, so that we can chase the dangling pointers!
-	 * See i915_request_alloc().
-	 */
-	do {
-		struct i915_request *request;
-
-		request = rcu_dereference(active->request);
-		if (!request || i915_request_completed(request))
-			return NULL;
-
-		/*
-		 * An especially silly compiler could decide to recompute the
-		 * result of i915_request_completed, more specifically
-		 * re-emit the load for request->fence.seqno. A race would catch
-		 * a later seqno value, which could flip the result from true to
-		 * false. Which means part of the instructions below might not
-		 * be executed, while later on instructions are executed. Due to
-		 * barriers within the refcounting the inconsistency can't reach
-		 * past the call to i915_request_get_rcu, but not executing
-		 * that while still executing i915_request_put() creates
-		 * havoc enough.  Prevent this with a compiler barrier.
-		 */
-		barrier();
-
-		request = i915_request_get_rcu(request);
-
-		/*
-		 * What stops the following rcu_access_pointer() from occurring
-		 * before the above i915_request_get_rcu()? If we were
-		 * to read the value before pausing to get the reference to
-		 * the request, we may not notice a change in the active
-		 * tracker.
-		 *
-		 * The rcu_access_pointer() is a mere compiler barrier, which
-		 * means both the CPU and compiler are free to perform the
-		 * memory read without constraint. The compiler only has to
-		 * ensure that any operations after the rcu_access_pointer()
-		 * occur afterwards in program order. This means the read may
-		 * be performed earlier by an out-of-order CPU, or adventurous
-		 * compiler.
-		 *
-		 * The atomic operation at the heart of
-		 * i915_request_get_rcu(), see dma_fence_get_rcu(), is
-		 * atomic_inc_not_zero() which is only a full memory barrier
-		 * when successful. That is, if i915_request_get_rcu()
-		 * returns the request (and so with the reference counted
-		 * incremented) then the following read for rcu_access_pointer()
-		 * must occur after the atomic operation and so confirm
-		 * that this request is the one currently being tracked.
-		 *
-		 * The corresponding write barrier is part of
-		 * rcu_assign_pointer().
-		 */
-		if (!request || request == rcu_access_pointer(active->request))
-			return rcu_pointer_handoff(request);
-
-		i915_request_put(request);
-	} while (1);
-}
-
-/**
- * i915_gem_active_get_unlocked - return a reference to the active request
- * @active - the active tracker
- *
- * i915_gem_active_get_unlocked() returns a reference to the active request,
- * or NULL if the active tracker is idle. The reference is obtained under RCU,
- * so no locking is required by the caller.
- *
- * The reference should be freed with i915_request_put().
- */
-static inline struct i915_request *
-i915_gem_active_get_unlocked(const struct i915_gem_active *active)
-{
-	struct i915_request *request;
-
-	rcu_read_lock();
-	request = __i915_gem_active_get_rcu(active);
-	rcu_read_unlock();
-
-	return request;
-}
-
-/**
- * i915_gem_active_isset - report whether the active tracker is assigned
- * @active - the active tracker
- *
- * i915_gem_active_isset() returns true if the active tracker is currently
- * assigned to a request. Due to the lazy retiring, that request may be idle
- * and this may report stale information.
- */
-static inline bool
-i915_gem_active_isset(const struct i915_gem_active *active)
-{
-	return rcu_access_pointer(active->request);
-}
-
-/**
- * i915_gem_active_wait - waits until the request is completed
- * @active - the active request on which to wait
- * @flags - how to wait
- * @timeout - how long to wait at most
- * @rps - userspace client to charge for a waitboost
- *
- * i915_gem_active_wait() waits until the request is completed before
- * returning, without requiring any locks to be held. Note that it does not
- * retire any requests before returning.
- *
- * This function relies on RCU in order to acquire the reference to the active
- * request without holding any locks. See __i915_gem_active_get_rcu() for the
- * glory details on how that is managed. Once the reference is acquired, we
- * can then wait upon the request, and afterwards release our reference,
- * free of any locking.
- *
- * This function wraps i915_request_wait(), see it for the full details on
- * the arguments.
- *
- * Returns 0 if successful, or a negative error code.
- */
-static inline int
-i915_gem_active_wait(const struct i915_gem_active *active, unsigned int flags)
-{
-	struct i915_request *request;
-	long ret = 0;
-
-	request = i915_gem_active_get_unlocked(active);
-	if (request) {
-		ret = i915_request_wait(request, flags, MAX_SCHEDULE_TIMEOUT);
-		i915_request_put(request);
-	}
-
-	return ret < 0 ? ret : 0;
-}
-
-/**
- * i915_gem_active_retire - waits until the request is retired
- * @active - the active request on which to wait
- *
- * i915_gem_active_retire() waits until the request is completed,
- * and then ensures that at least the retirement handler for this
- * @active tracker is called before returning. If the @active
- * tracker is idle, the function returns immediately.
- */
-static inline int __must_check
-i915_gem_active_retire(struct i915_gem_active *active,
-		       struct mutex *mutex)
-{
-	struct i915_request *request;
-	long ret;
-
-	request = i915_gem_active_raw(active, mutex);
-	if (!request)
-		return 0;
-
-	ret = i915_request_wait(request,
-				I915_WAIT_INTERRUPTIBLE | I915_WAIT_LOCKED,
-				MAX_SCHEDULE_TIMEOUT);
-	if (ret < 0)
-		return ret;
-
-	list_del_init(&active->link);
-	RCU_INIT_POINTER(active->request, NULL);
-
-	active->retire(active, request);
-
-	return 0;
-}
-
-#define for_each_active(mask, idx) \
-	for (; mask ? idx = ffs(mask) - 1, 1 : 0; mask &= ~BIT(idx))
-
 #endif /* I915_REQUEST_H */
diff --git a/drivers/gpu/drm/i915/i915_reset.c b/drivers/gpu/drm/i915/i915_reset.c
index 4462007a681c..0e0ddf2e6815 100644
--- a/drivers/gpu/drm/i915/i915_reset.c
+++ b/drivers/gpu/drm/i915/i915_reset.c
@@ -862,7 +862,7 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 		struct i915_request *rq;
 		long timeout;
 
-		rq = i915_gem_active_get_unlocked(&tl->last_request);
+		rq = i915_active_request_get_unlocked(&tl->last_request);
 		if (!rq)
 			continue;
 
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index f18afa2bac8d..d2f2a9c2fabd 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -86,7 +86,7 @@ int i915_save_state(struct drm_i915_private *dev_priv)
 	} else if (IS_GEN(dev_priv, 2)) {
 		for (i = 0; i < 7; i++)
 			dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i));
-	} else if (HAS_GMCH_DISPLAY(dev_priv)) {
+	} else if (HAS_GMCH(dev_priv)) {
 		for (i = 0; i < 16; i++) {
 			dev_priv->regfile.saveSWF0[i] = I915_READ(SWF0(i));
 			dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i));
@@ -131,7 +131,7 @@ int i915_restore_state(struct drm_i915_private *dev_priv)
 	} else if (IS_GEN(dev_priv, 2)) {
 		for (i = 0; i < 7; i++)
 			I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]);
-	} else if (HAS_GMCH_DISPLAY(dev_priv)) {
+	} else if (HAS_GMCH(dev_priv)) {
 		for (i = 0; i < 16; i++) {
 			I915_WRITE(SWF0(i), dev_priv->regfile.saveSWF0[i]);
 			I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]);
diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c
index 5ea3af393ffe..b2202d2e58a2 100644
--- a/drivers/gpu/drm/i915/i915_timeline.c
+++ b/drivers/gpu/drm/i915/i915_timeline.c
@@ -163,7 +163,8 @@ int i915_timeline_init(struct drm_i915_private *i915,
 
 	spin_lock_init(&timeline->lock);
 
-	init_request_active(&timeline->last_request, NULL);
+	INIT_ACTIVE_REQUEST(&timeline->barrier);
+	INIT_ACTIVE_REQUEST(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
@@ -235,6 +236,7 @@ void i915_timeline_fini(struct i915_timeline *timeline)
 {
 	GEM_BUG_ON(timeline->pin_count);
 	GEM_BUG_ON(!list_empty(&timeline->requests));
+	GEM_BUG_ON(i915_active_request_isset(&timeline->barrier));
 
 	i915_syncmap_free(&timeline->sync);
 	hwsp_free(timeline);
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index 8caeb66d1cd5..7bec7d2e45bf 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 
+#include "i915_active.h"
 #include "i915_request.h"
 #include "i915_syncmap.h"
 #include "i915_utils.h"
@@ -58,10 +59,10 @@ struct i915_timeline {
 
 	/* Contains an RCU guarded pointer to the last request. No reference is
 	 * held to the request, users must carefully acquire a reference to
-	 * the request using i915_gem_active_get_request_rcu(), or hold the
+	 * the request using i915_active_request_get_request_rcu(), or hold the
 	 * struct_mutex.
 	 */
-	struct i915_gem_active last_request;
+	struct i915_active_request last_request;
 
 	/**
 	 * We track the most recent seqno that we wait on in every context so
@@ -74,6 +75,16 @@ struct i915_timeline {
 	 */
 	struct i915_syncmap *sync;
 
+	/**
+	 * Barrier provides the ability to serialize ordering between different
+	 * timelines.
+	 *
+	 * Users can call i915_timeline_set_barrier which will make all
+	 * subsequent submissions to this timeline be executed only after the
+	 * barrier has been completed.
+	 */
+	struct i915_active_request barrier;
+
 	struct list_head link;
 	const char *name;
 	struct drm_i915_private *i915;
@@ -155,4 +166,19 @@ void i915_timelines_init(struct drm_i915_private *i915);
 void i915_timelines_park(struct drm_i915_private *i915);
 void i915_timelines_fini(struct drm_i915_private *i915);
 
+/**
+ * i915_timeline_set_barrier - orders submission between different timelines
+ * @timeline: timeline to set the barrier on
+ * @rq: request after which new submissions can proceed
+ *
+ * Sets the passed in request as the serialization point for all subsequent
+ * submissions on @timeline. Subsequent requests will not be submitted to GPU
+ * until the barrier has been completed.
+ */
+static inline int
+i915_timeline_set_barrier(struct i915_timeline *tl, struct i915_request *rq)
+{
+	return i915_active_request_set(&tl->barrier, rq);
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index d83b8ad5f859..b713bed20c38 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -63,22 +63,23 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 
 #endif
 
-struct i915_vma_active {
-	struct i915_gem_active base;
-	struct i915_vma *vma;
-	struct rb_node node;
-	u64 timeline;
-};
+static void obj_bump_mru(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
-static void
-__i915_vma_retire(struct i915_vma *vma, struct i915_request *rq)
+	spin_lock(&i915->mm.obj_lock);
+	if (obj->bind_count)
+		list_move_tail(&obj->mm.link, &i915->mm.bound_list);
+	spin_unlock(&i915->mm.obj_lock);
+
+	obj->mm.dirty = true; /* be paranoid  */
+}
+
+static void __i915_vma_retire(struct i915_active *ref)
 {
+	struct i915_vma *vma = container_of(ref, typeof(*vma), active);
 	struct drm_i915_gem_object *obj = vma->obj;
 
-	GEM_BUG_ON(!i915_vma_is_active(vma));
-	if (--vma->active_count)
-		return;
-
 	GEM_BUG_ON(!i915_gem_object_is_active(obj));
 	if (--obj->active_count)
 		return;
@@ -90,16 +91,12 @@ __i915_vma_retire(struct i915_vma *vma, struct i915_request *rq)
 		reservation_object_unlock(obj->resv);
 	}
 
-	/* Bump our place on the bound list to keep it roughly in LRU order
+	/*
+	 * Bump our place on the bound list to keep it roughly in LRU order
 	 * so that we don't steal from recently used but inactive objects
 	 * (unless we are forced to ofc!)
 	 */
-	spin_lock(&rq->i915->mm.obj_lock);
-	if (obj->bind_count)
-		list_move_tail(&obj->mm.link, &rq->i915->mm.bound_list);
-	spin_unlock(&rq->i915->mm.obj_lock);
-
-	obj->mm.dirty = true; /* be paranoid  */
+	obj_bump_mru(obj);
 
 	if (i915_gem_object_has_active_reference(obj)) {
 		i915_gem_object_clear_active_reference(obj);
@@ -107,21 +104,6 @@ __i915_vma_retire(struct i915_vma *vma, struct i915_request *rq)
 	}
 }
 
-static void
-i915_vma_retire(struct i915_gem_active *base, struct i915_request *rq)
-{
-	struct i915_vma_active *active =
-		container_of(base, typeof(*active), base);
-
-	__i915_vma_retire(active->vma, rq);
-}
-
-static void
-i915_vma_last_retire(struct i915_gem_active *base, struct i915_request *rq)
-{
-	__i915_vma_retire(container_of(base, struct i915_vma, last_active), rq);
-}
-
 static struct i915_vma *
 vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
@@ -137,10 +119,9 @@ vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	vma->active = RB_ROOT;
+	i915_active_init(vm->i915, &vma->active, __i915_vma_retire);
+	INIT_ACTIVE_REQUEST(&vma->last_fence);
 
-	init_request_active(&vma->last_active, i915_vma_last_retire);
-	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
 	vma->ops = &vm->vma_ops;
 	vma->obj = obj;
@@ -823,12 +804,11 @@ void i915_vma_reopen(struct i915_vma *vma)
 static void __i915_vma_destroy(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	struct i915_vma_active *iter, *n;
 
 	GEM_BUG_ON(vma->node.allocated);
 	GEM_BUG_ON(vma->fence);
 
-	GEM_BUG_ON(i915_gem_active_isset(&vma->last_fence));
+	GEM_BUG_ON(i915_active_request_isset(&vma->last_fence));
 
 	mutex_lock(&vma->vm->mutex);
 	list_del(&vma->vm_link);
@@ -843,10 +823,7 @@ static void __i915_vma_destroy(struct i915_vma *vma)
 		spin_unlock(&obj->vma.lock);
 	}
 
-	rbtree_postorder_for_each_entry_safe(iter, n, &vma->active, node) {
-		GEM_BUG_ON(i915_gem_active_isset(&iter->base));
-		kfree(iter);
-	}
+	i915_active_fini(&vma->active);
 
 	kmem_cache_free(i915->vmas, vma);
 }
@@ -931,104 +908,15 @@ static void export_fence(struct i915_vma *vma,
 	reservation_object_unlock(resv);
 }
 
-static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
-{
-	struct i915_vma_active *active;
-	struct rb_node **p, *parent;
-	struct i915_request *old;
-
-	/*
-	 * We track the most recently used timeline to skip a rbtree search
-	 * for the common case, under typical loads we never need the rbtree
-	 * at all. We can reuse the last_active slot if it is empty, that is
-	 * after the previous activity has been retired, or if the active
-	 * matches the current timeline.
-	 *
-	 * Note that we allow the timeline to be active simultaneously in
-	 * the rbtree and the last_active cache. We do this to avoid having
-	 * to search and replace the rbtree element for a new timeline, with
-	 * the cost being that we must be aware that the vma may be retired
-	 * twice for the same timeline (as the older rbtree element will be
-	 * retired before the new request added to last_active).
-	 */
-	old = i915_gem_active_raw(&vma->last_active,
-				  &vma->vm->i915->drm.struct_mutex);
-	if (!old || old->fence.context == idx)
-		goto out;
-
-	/* Move the currently active fence into the rbtree */
-	idx = old->fence.context;
-
-	parent = NULL;
-	p = &vma->active.rb_node;
-	while (*p) {
-		parent = *p;
-
-		active = rb_entry(parent, struct i915_vma_active, node);
-		if (active->timeline == idx)
-			goto replace;
-
-		if (active->timeline < idx)
-			p = &parent->rb_right;
-		else
-			p = &parent->rb_left;
-	}
-
-	active = kmalloc(sizeof(*active), GFP_KERNEL);
-
-	/* kmalloc may retire the vma->last_active request (thanks shrinker)! */
-	if (unlikely(!i915_gem_active_raw(&vma->last_active,
-					  &vma->vm->i915->drm.struct_mutex))) {
-		kfree(active);
-		goto out;
-	}
-
-	if (unlikely(!active))
-		return ERR_PTR(-ENOMEM);
-
-	init_request_active(&active->base, i915_vma_retire);
-	active->vma = vma;
-	active->timeline = idx;
-
-	rb_link_node(&active->node, parent, p);
-	rb_insert_color(&active->node, &vma->active);
-
-replace:
-	/*
-	 * Overwrite the previous active slot in the rbtree with last_active,
-	 * leaving last_active zeroed. If the previous slot is still active,
-	 * we must be careful as we now only expect to receive one retire
-	 * callback not two, and so much undo the active counting for the
-	 * overwritten slot.
-	 */
-	if (i915_gem_active_isset(&active->base)) {
-		/* Retire ourselves from the old rq->active_list */
-		__list_del_entry(&active->base.link);
-		vma->active_count--;
-		GEM_BUG_ON(!vma->active_count);
-	}
-	GEM_BUG_ON(list_empty(&vma->last_active.link));
-	list_replace_init(&vma->last_active.link, &active->base.link);
-	active->base.request = fetch_and_zero(&vma->last_active.request);
-
-out:
-	return &vma->last_active;
-}
-
 int i915_vma_move_to_active(struct i915_vma *vma,
 			    struct i915_request *rq,
 			    unsigned int flags)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	struct i915_gem_active *active;
 
 	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
-	active = active_instance(vma, rq->fence.context);
-	if (IS_ERR(active))
-		return PTR_ERR(active);
-
 	/*
 	 * Add a reference if we're newly entering the active list.
 	 * The order in which we add operations to the retirement queue is
@@ -1037,9 +925,15 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	 * add the active reference first and queue for it to be dropped
 	 * *last*.
 	 */
-	if (!i915_gem_active_isset(active) && !vma->active_count++)
+	if (!vma->active.count)
 		obj->active_count++;
-	i915_gem_active_set(active, rq);
+
+	if (unlikely(i915_active_ref(&vma->active, rq->fence.context, rq))) {
+		if (!vma->active.count)
+			obj->active_count--;
+		return -ENOMEM;
+	}
+
 	GEM_BUG_ON(!i915_vma_is_active(vma));
 	GEM_BUG_ON(!obj->active_count);
 
@@ -1048,14 +942,14 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 		obj->write_domain = I915_GEM_DOMAIN_RENDER;
 
 		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
-			i915_gem_active_set(&obj->frontbuffer_write, rq);
+			__i915_active_request_set(&obj->frontbuffer_write, rq);
 
 		obj->read_domains = 0;
 	}
 	obj->read_domains |= I915_GEM_GPU_DOMAINS;
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
-		i915_gem_active_set(&vma->last_fence, rq);
+		__i915_active_request_set(&vma->last_fence, rq);
 
 	export_fence(vma, rq, flags);
 	return 0;
@@ -1073,8 +967,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 	 */
 	might_sleep();
 	if (i915_vma_is_active(vma)) {
-		struct i915_vma_active *active, *n;
-
 		/*
 		 * When a closed VMA is retired, it is unbound - eek.
 		 * In order to prevent it from being recursively closed,
@@ -1090,21 +982,12 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 */
 		__i915_vma_pin(vma);
 
-		ret = i915_gem_active_retire(&vma->last_active,
-					     &vma->vm->i915->drm.struct_mutex);
+		ret = i915_active_wait(&vma->active);
 		if (ret)
 			goto unpin;
 
-		rbtree_postorder_for_each_entry_safe(active, n,
-						     &vma->active, node) {
-			ret = i915_gem_active_retire(&active->base,
-						     &vma->vm->i915->drm.struct_mutex);
-			if (ret)
-				goto unpin;
-		}
-
-		ret = i915_gem_active_retire(&vma->last_fence,
-					     &vma->vm->i915->drm.struct_mutex);
+		ret = i915_active_request_retire(&vma->last_fence,
+					      &vma->vm->i915->drm.struct_mutex);
 unpin:
 		__i915_vma_unpin(vma);
 		if (ret)
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 5793abe509a2..7c742027f866 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -34,6 +34,7 @@
 #include "i915_gem_fence_reg.h"
 #include "i915_gem_object.h"
 
+#include "i915_active.h"
 #include "i915_request.h"
 
 enum i915_cache_level;
@@ -108,10 +109,8 @@ struct i915_vma {
 #define I915_VMA_USERFAULT	BIT(I915_VMA_USERFAULT_BIT)
 #define I915_VMA_GGTT_WRITE	BIT(15)
 
-	unsigned int active_count;
-	struct rb_root active;
-	struct i915_gem_active last_active;
-	struct i915_gem_active last_fence;
+	struct i915_active active;
+	struct i915_active_request last_fence;
 
 	/**
 	 * Support different GGTT views into the same object.
@@ -154,9 +153,9 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 void i915_vma_unpin_and_release(struct i915_vma **p_vma, unsigned int flags);
 #define I915_VMA_RELEASE_MAP BIT(0)
 
-static inline bool i915_vma_is_active(struct i915_vma *vma)
+static inline bool i915_vma_is_active(const struct i915_vma *vma)
 {
-	return vma->active_count;
+	return !i915_active_is_idle(&vma->active);
 }
 
 int __must_check i915_vma_move_to_active(struct i915_vma *vma,
diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c
index 4b0044cdcf1a..71a1f12c6b2a 100644
--- a/drivers/gpu/drm/i915/intel_color.c
+++ b/drivers/gpu/drm/i915/intel_color.c
@@ -74,12 +74,12 @@
 #define ILK_CSC_COEFF_1_0		\
 	((7 << 12) | ILK_CSC_COEFF_FP(CTM_COEFF_1_0, 8))
 
-static bool lut_is_legacy(struct drm_property_blob *lut)
+static bool lut_is_legacy(const struct drm_property_blob *lut)
 {
 	return drm_color_lut_size(lut) == LEGACY_LUT_LENGTH;
 }
 
-static bool crtc_state_is_legacy_gamma(struct intel_crtc_state *crtc_state)
+static bool crtc_state_is_legacy_gamma(const struct intel_crtc_state *crtc_state)
 {
 	return !crtc_state->base.degamma_lut &&
 		!crtc_state->base.ctm &&
@@ -115,8 +115,8 @@ static u64 *ctm_mult_by_limited(u64 *result, const u64 *input)
 
 static void ilk_load_ycbcr_conversion_matrix(struct intel_crtc *crtc)
 {
-	int pipe = crtc->pipe;
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	I915_WRITE(PIPE_CSC_PREOFF_HI(pipe), 0);
 	I915_WRITE(PIPE_CSC_PREOFF_ME(pipe), 0);
@@ -137,13 +137,14 @@ static void ilk_load_ycbcr_conversion_matrix(struct intel_crtc *crtc)
 	I915_WRITE(PIPE_CSC_MODE(pipe), 0);
 }
 
-static void ilk_load_csc_matrix(struct intel_crtc_state *crtc_state)
+static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int i, pipe = crtc->pipe;
-	u16 coeffs[9] = { 0, };
 	bool limited_color_range = false;
+	enum pipe pipe = crtc->pipe;
+	u16 coeffs[9] = {};
+	int i;
 
 	/*
 	 * FIXME if there's a gamma LUT after the CSC, we should
@@ -256,16 +257,16 @@ static void ilk_load_csc_matrix(struct intel_crtc_state *crtc_state)
 /*
  * Set up the pipe CSC unit on CherryView.
  */
-static void cherryview_load_csc_matrix(struct intel_crtc_state *crtc_state)
+static void cherryview_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	u32 mode;
 
 	if (crtc_state->base.ctm) {
-		struct drm_color_ctm *ctm = crtc_state->base.ctm->data;
-		u16 coeffs[9] = { 0, };
+		const struct drm_color_ctm *ctm = crtc_state->base.ctm->data;
+		u16 coeffs[9] = {};
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(coeffs); i++) {
@@ -303,25 +304,16 @@ static void cherryview_load_csc_matrix(struct intel_crtc_state *crtc_state)
 	I915_WRITE(CGM_PIPE_MODE(pipe), mode);
 }
 
-void intel_color_set_csc(struct intel_crtc_state *crtc_state)
-{
-	struct drm_device *dev = crtc_state->base.crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	if (dev_priv->display.load_csc_matrix)
-		dev_priv->display.load_csc_matrix(crtc_state);
-}
-
 /* Loads the legacy palette/gamma unit for the CRTC. */
-static void i9xx_load_luts_internal(struct intel_crtc_state *crtc_state,
-				    struct drm_property_blob *blob)
+static void i9xx_load_luts_internal(const struct intel_crtc_state *crtc_state,
+				    const struct drm_property_blob *blob)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	int i;
 
-	if (HAS_GMCH_DISPLAY(dev_priv)) {
+	if (HAS_GMCH(dev_priv)) {
 		if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI))
 			assert_dsi_pll_enabled(dev_priv);
 		else
@@ -329,14 +321,15 @@ static void i9xx_load_luts_internal(struct intel_crtc_state *crtc_state,
 	}
 
 	if (blob) {
-		struct drm_color_lut *lut = blob->data;
+		const struct drm_color_lut *lut = blob->data;
+
 		for (i = 0; i < 256; i++) {
 			u32 word =
 				(drm_color_lut_extract(lut[i].red, 8) << 16) |
 				(drm_color_lut_extract(lut[i].green, 8) << 8) |
 				drm_color_lut_extract(lut[i].blue, 8);
 
-			if (HAS_GMCH_DISPLAY(dev_priv))
+			if (HAS_GMCH(dev_priv))
 				I915_WRITE(PALETTE(pipe, i), word);
 			else
 				I915_WRITE(LGC_PALETTE(pipe, i), word);
@@ -345,7 +338,7 @@ static void i9xx_load_luts_internal(struct intel_crtc_state *crtc_state,
 		for (i = 0; i < 256; i++) {
 			u32 word = (i << 16) | (i << 8) | i;
 
-			if (HAS_GMCH_DISPLAY(dev_priv))
+			if (HAS_GMCH(dev_priv))
 				I915_WRITE(PALETTE(pipe, i), word);
 			else
 				I915_WRITE(LGC_PALETTE(pipe, i), word);
@@ -353,48 +346,34 @@ static void i9xx_load_luts_internal(struct intel_crtc_state *crtc_state,
 	}
 }
 
-static void i9xx_load_luts(struct intel_crtc_state *crtc_state)
+static void i9xx_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	i9xx_load_luts_internal(crtc_state, crtc_state->base.gamma_lut);
 }
 
-/* Loads the legacy palette/gamma unit for the CRTC on Haswell. */
-static void haswell_load_luts(struct intel_crtc_state *crtc_state)
+static void hsw_color_commit(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	bool reenable_ips = false;
 
-	/*
-	 * Workaround : Do not read or write the pipe palette/gamma data while
-	 * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled.
-	 */
-	if (IS_HASWELL(dev_priv) && crtc_state->ips_enabled &&
-	    (crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)) {
-		hsw_disable_ips(crtc_state);
-		reenable_ips = true;
-	}
-
-	crtc_state->gamma_mode = GAMMA_MODE_MODE_8BIT;
-	I915_WRITE(GAMMA_MODE(crtc->pipe), GAMMA_MODE_MODE_8BIT);
+	I915_WRITE(GAMMA_MODE(crtc->pipe), crtc_state->gamma_mode);
 
-	i9xx_load_luts(crtc_state);
-
-	if (reenable_ips)
-		hsw_enable_ips(crtc_state);
+	ilk_load_csc_matrix(crtc_state);
 }
 
-static void bdw_load_degamma_lut(struct intel_crtc_state *crtc_state)
+static void bdw_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
 	u32 i, lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
+	enum pipe pipe = crtc->pipe;
 
 	I915_WRITE(PREC_PAL_INDEX(pipe),
 		   PAL_PREC_SPLIT_MODE | PAL_PREC_AUTO_INCREMENT);
 
-	if (crtc_state->base.degamma_lut) {
-		struct drm_color_lut *lut = crtc_state->base.degamma_lut->data;
+	if (degamma_lut) {
+		const struct drm_color_lut *lut = degamma_lut->data;
 
 		for (i = 0; i < lut_size; i++) {
 			u32 word =
@@ -414,11 +393,13 @@ static void bdw_load_degamma_lut(struct intel_crtc_state *crtc_state)
 	}
 }
 
-static void bdw_load_gamma_lut(struct intel_crtc_state *crtc_state, u32 offset)
+static void bdw_load_gamma_lut(const struct intel_crtc_state *crtc_state, u32 offset)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
 	u32 i, lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	enum pipe pipe = crtc->pipe;
 
 	WARN_ON(offset & ~PAL_PREC_INDEX_VALUE_MASK);
 
@@ -427,8 +408,8 @@ static void bdw_load_gamma_lut(struct intel_crtc_state *crtc_state, u32 offset)
 		   PAL_PREC_AUTO_INCREMENT |
 		   offset);
 
-	if (crtc_state->base.gamma_lut) {
-		struct drm_color_lut *lut = crtc_state->base.gamma_lut->data;
+	if (gamma_lut) {
+		const struct drm_color_lut *lut = gamma_lut->data;
 
 		for (i = 0; i < lut_size; i++) {
 			u32 word =
@@ -462,35 +443,32 @@ static void bdw_load_gamma_lut(struct intel_crtc_state *crtc_state, u32 offset)
 }
 
 /* Loads the palette/gamma unit for the CRTC on Broadwell+. */
-static void broadwell_load_luts(struct intel_crtc_state *crtc_state)
+static void broadwell_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	if (crtc_state_is_legacy_gamma(crtc_state)) {
-		haswell_load_luts(crtc_state);
-		return;
-	}
-
-	bdw_load_degamma_lut(crtc_state);
-	bdw_load_gamma_lut(crtc_state,
-			   INTEL_INFO(dev_priv)->color.degamma_lut_size);
-
-	crtc_state->gamma_mode = GAMMA_MODE_MODE_SPLIT;
-	I915_WRITE(GAMMA_MODE(pipe), GAMMA_MODE_MODE_SPLIT);
-	POSTING_READ(GAMMA_MODE(pipe));
+		i9xx_load_luts(crtc_state);
+	} else {
+		bdw_load_degamma_lut(crtc_state);
+		bdw_load_gamma_lut(crtc_state,
+				   INTEL_INFO(dev_priv)->color.degamma_lut_size);
 
-	/*
-	 * Reset the index, otherwise it prevents the legacy palette to be
-	 * written properly.
-	 */
-	I915_WRITE(PREC_PAL_INDEX(pipe), 0);
+		/*
+		 * Reset the index, otherwise it prevents the legacy palette to be
+		 * written properly.
+		 */
+		I915_WRITE(PREC_PAL_INDEX(pipe), 0);
+	}
 }
 
-static void glk_load_degamma_lut(struct intel_crtc_state *crtc_state)
+static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	const u32 lut_size = 33;
 	u32 i;
 
@@ -517,48 +495,49 @@ static void glk_load_degamma_lut(struct intel_crtc_state *crtc_state)
 		I915_WRITE(PRE_CSC_GAMC_DATA(pipe), (1 << 16));
 }
 
-static void glk_load_luts(struct intel_crtc_state *crtc_state)
+static void glk_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	glk_load_degamma_lut(crtc_state);
 
 	if (crtc_state_is_legacy_gamma(crtc_state)) {
-		haswell_load_luts(crtc_state);
-		return;
-	}
-
-	bdw_load_gamma_lut(crtc_state, 0);
+		i9xx_load_luts(crtc_state);
+	} else {
+		bdw_load_gamma_lut(crtc_state, 0);
 
-	crtc_state->gamma_mode = GAMMA_MODE_MODE_10BIT;
-	I915_WRITE(GAMMA_MODE(pipe), GAMMA_MODE_MODE_10BIT);
-	POSTING_READ(GAMMA_MODE(pipe));
+		/*
+		 * Reset the index, otherwise it prevents the legacy palette to be
+		 * written properly.
+		 */
+		I915_WRITE(PREC_PAL_INDEX(pipe), 0);
+	}
 }
 
-/* Loads the palette/gamma unit for the CRTC on CherryView. */
-static void cherryview_load_luts(struct intel_crtc_state *crtc_state)
+static void cherryview_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_crtc *crtc = crtc_state->base.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	enum pipe pipe = to_intel_crtc(crtc)->pipe;
-	struct drm_color_lut *lut;
-	u32 i, lut_size;
-	u32 word0, word1;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	enum pipe pipe = crtc->pipe;
+
+	cherryview_load_csc_matrix(crtc_state);
 
 	if (crtc_state_is_legacy_gamma(crtc_state)) {
-		/* Turn off degamma/gamma on CGM block. */
-		I915_WRITE(CGM_PIPE_MODE(pipe),
-			   (crtc_state->base.ctm ? CGM_PIPE_MODE_CSC : 0));
-		i9xx_load_luts_internal(crtc_state, crtc_state->base.gamma_lut);
+		i9xx_load_luts_internal(crtc_state, gamma_lut);
 		return;
 	}
 
-	if (crtc_state->base.degamma_lut) {
-		lut = crtc_state->base.degamma_lut->data;
-		lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
+	if (degamma_lut) {
+		const struct drm_color_lut *lut = degamma_lut->data;
+		int i, lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
+
 		for (i = 0; i < lut_size; i++) {
+			u32 word0, word1;
+
 			/* Write LUT in U0.14 format. */
 			word0 =
 			(drm_color_lut_extract(lut[i].green, 14) << 16) |
@@ -570,10 +549,13 @@ static void cherryview_load_luts(struct intel_crtc_state *crtc_state)
 		}
 	}
 
-	if (crtc_state->base.gamma_lut) {
-		lut = crtc_state->base.gamma_lut->data;
-		lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	if (gamma_lut) {
+		const struct drm_color_lut *lut = gamma_lut->data;
+		int i, lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+
 		for (i = 0; i < lut_size; i++) {
+			u32 word0, word1;
+
 			/* Write LUT in U0.10 format. */
 			word0 =
 			(drm_color_lut_extract(lut[i].green, 10) << 16) |
@@ -585,11 +567,6 @@ static void cherryview_load_luts(struct intel_crtc_state *crtc_state)
 		}
 	}
 
-	I915_WRITE(CGM_PIPE_MODE(pipe),
-		   (crtc_state->base.ctm ? CGM_PIPE_MODE_CSC : 0) |
-		   (crtc_state->base.degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) |
-		   (crtc_state->base.gamma_lut ? CGM_PIPE_MODE_GAMMA : 0));
-
 	/*
 	 * Also program a linear LUT in the legacy block (behind the
 	 * CGM block).
@@ -597,14 +574,21 @@ static void cherryview_load_luts(struct intel_crtc_state *crtc_state)
 	i9xx_load_luts_internal(crtc_state, NULL);
 }
 
-void intel_color_load_luts(struct intel_crtc_state *crtc_state)
+void intel_color_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
 
 	dev_priv->display.load_luts(crtc_state);
 }
 
+void intel_color_commit(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+
+	if (dev_priv->display.color_commit)
+		dev_priv->display.color_commit(crtc_state);
+}
+
 static int check_lut_size(const struct drm_property_blob *lut, int expected)
 {
 	int len;
@@ -625,6 +609,8 @@ static int check_lut_size(const struct drm_property_blob *lut, int expected)
 int intel_color_check(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
 	int gamma_length, degamma_length;
 	u32 gamma_tests, degamma_tests;
 
@@ -634,17 +620,25 @@ int intel_color_check(struct intel_crtc_state *crtc_state)
 	gamma_tests = INTEL_INFO(dev_priv)->color.gamma_lut_tests;
 
 	/* Always allow legacy gamma LUT with no further checking. */
-	if (crtc_state_is_legacy_gamma(crtc_state))
+	if (crtc_state_is_legacy_gamma(crtc_state)) {
+		crtc_state->gamma_mode = GAMMA_MODE_MODE_8BIT;
 		return 0;
+	}
 
-	if (check_lut_size(crtc_state->base.degamma_lut, degamma_length) ||
-	    check_lut_size(crtc_state->base.gamma_lut, gamma_length))
+	if (check_lut_size(degamma_lut, degamma_length) ||
+	    check_lut_size(gamma_lut, gamma_length))
 		return -EINVAL;
 
-	if (drm_color_lut_check(crtc_state->base.degamma_lut, degamma_tests) ||
-	    drm_color_lut_check(crtc_state->base.gamma_lut, gamma_tests))
+	if (drm_color_lut_check(degamma_lut, degamma_tests) ||
+	    drm_color_lut_check(gamma_lut, gamma_tests))
 		return -EINVAL;
 
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		crtc_state->gamma_mode = GAMMA_MODE_MODE_10BIT;
+	else if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
+		crtc_state->gamma_mode = GAMMA_MODE_MODE_SPLIT;
+	else
+		crtc_state->gamma_mode = GAMMA_MODE_MODE_8BIT;
 
 	return 0;
 }
@@ -656,18 +650,17 @@ void intel_color_init(struct intel_crtc *crtc)
 	drm_mode_crtc_set_gamma_size(&crtc->base, 256);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->display.load_csc_matrix = cherryview_load_csc_matrix;
 		dev_priv->display.load_luts = cherryview_load_luts;
 	} else if (IS_HASWELL(dev_priv)) {
-		dev_priv->display.load_csc_matrix = ilk_load_csc_matrix;
-		dev_priv->display.load_luts = haswell_load_luts;
+		dev_priv->display.load_luts = i9xx_load_luts;
+		dev_priv->display.color_commit = hsw_color_commit;
 	} else if (IS_BROADWELL(dev_priv) || IS_GEN9_BC(dev_priv) ||
 		   IS_BROXTON(dev_priv)) {
-		dev_priv->display.load_csc_matrix = ilk_load_csc_matrix;
 		dev_priv->display.load_luts = broadwell_load_luts;
+		dev_priv->display.color_commit = hsw_color_commit;
 	} else if (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) {
-		dev_priv->display.load_csc_matrix = ilk_load_csc_matrix;
 		dev_priv->display.load_luts = glk_load_luts;
+		dev_priv->display.color_commit = hsw_color_commit;
 	} else {
 		dev_priv->display.load_luts = i9xx_load_luts;
 	}
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 7bf09cef591a..e8b8661df746 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -115,7 +115,7 @@ enum intel_ppgtt {
 	func(has_ddi); \
 	func(has_dp_mst); \
 	func(has_fbc); \
-	func(has_gmch_display); \
+	func(has_gmch); \
 	func(has_hotplug); \
 	func(has_ipc); \
 	func(has_overlay); \
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index df7a7a310f2f..619f1a20cc2d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1805,7 +1805,7 @@ static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state)
 	 * a plane.  On ILK+ the pipe PLLs are integrated, so we don't
 	 * need the check.
 	 */
-	if (HAS_GMCH_DISPLAY(dev_priv)) {
+	if (HAS_GMCH(dev_priv)) {
 		if (intel_crtc_has_type(new_crtc_state, INTEL_OUTPUT_DSI))
 			assert_dsi_pll_enabled(dev_priv);
 		else
@@ -2094,7 +2094,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	 * complicated than this. For example, Cherryview appears quite
 	 * happy to scanout from anywhere within its global aperture.
 	 */
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		pinctl |= PIN_MAPPABLE;
 
 	vma = i915_gem_object_pin_to_display_plane(obj,
@@ -3195,7 +3195,7 @@ i9xx_plane_max_stride(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 
-	if (!HAS_GMCH_DISPLAY(dev_priv)) {
+	if (!HAS_GMCH(dev_priv)) {
 		return 32*1024;
 	} else if (INTEL_GEN(dev_priv) >= 4) {
 		if (modifier == I915_FORMAT_MOD_X_TILED)
@@ -3215,28 +3215,38 @@ i9xx_plane_max_stride(struct intel_plane *plane,
 	}
 }
 
+static u32 i9xx_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 dspcntr = 0;
+
+	dspcntr |= DISPPLANE_GAMMA_ENABLE;
+
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		dspcntr |= DISPPLANE_PIPE_CSC_ENABLE;
+
+	if (INTEL_GEN(dev_priv) < 5)
+		dspcntr |= DISPPLANE_SEL_PIPE(crtc->pipe);
+
+	return dspcntr;
+}
+
 static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(plane_state->base.plane->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	unsigned int rotation = plane_state->base.rotation;
 	u32 dspcntr;
 
-	dspcntr = DISPLAY_PLANE_ENABLE | DISPPLANE_GAMMA_ENABLE;
+	dspcntr = DISPLAY_PLANE_ENABLE;
 
 	if (IS_G4X(dev_priv) || IS_GEN(dev_priv, 5) ||
 	    IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv))
 		dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
 
-	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-		dspcntr |= DISPPLANE_PIPE_CSC_ENABLE;
-
-	if (INTEL_GEN(dev_priv) < 5)
-		dspcntr |= DISPPLANE_SEL_PIPE(crtc->pipe);
-
 	switch (fb->format->format) {
 	case DRM_FORMAT_C8:
 		dspcntr |= DISPPLANE_8BPP;
@@ -3364,11 +3374,13 @@ static void i9xx_update_plane(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
 	u32 linear_offset;
-	u32 dspcntr = plane_state->ctl;
 	int x = plane_state->color_plane[0].x;
 	int y = plane_state->color_plane[0].y;
 	unsigned long irqflags;
 	u32 dspaddr_offset;
+	u32 dspcntr;
+
+	dspcntr = plane_state->ctl | i9xx_plane_ctl_crtc(crtc_state);
 
 	linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0);
 
@@ -3428,10 +3440,23 @@ static void i9xx_disable_plane(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
 	unsigned long irqflags;
+	u32 dspcntr;
+
+	/*
+	 * DSPCNTR pipe gamma enable on g4x+ and pipe csc
+	 * enable on ilk+ affect the pipe bottom color as
+	 * well, so we must configure them even if the plane
+	 * is disabled.
+	 *
+	 * On pre-g4x there is no way to gamma correct the
+	 * pipe bottom color but we'll keep on doing this
+	 * anyway.
+	 */
+	dspcntr = i9xx_plane_ctl_crtc(crtc_state);
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
-	I915_WRITE_FW(DSPCNTR(i9xx_plane), 0);
+	I915_WRITE_FW(DSPCNTR(i9xx_plane), dspcntr);
 	if (INTEL_GEN(dev_priv) >= 4)
 		I915_WRITE_FW(DSPSURF(i9xx_plane), 0);
 	else
@@ -3668,6 +3693,20 @@ static u32 cnl_plane_ctl_flip(unsigned int reflect)
 	return 0;
 }
 
+u32 skl_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	u32 plane_ctl = 0;
+
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		return plane_ctl;
+
+	plane_ctl |= PLANE_CTL_PIPE_GAMMA_ENABLE;
+	plane_ctl |= PLANE_CTL_PIPE_CSC_ENABLE;
+
+	return plane_ctl;
+}
+
 u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state)
 {
@@ -3682,10 +3721,7 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 
 	if (INTEL_GEN(dev_priv) < 10 && !IS_GEMINILAKE(dev_priv)) {
 		plane_ctl |= skl_plane_ctl_alpha(plane_state);
-		plane_ctl |=
-			PLANE_CTL_PIPE_GAMMA_ENABLE |
-			PLANE_CTL_PIPE_CSC_ENABLE |
-			PLANE_CTL_PLANE_GAMMA_DISABLE;
+		plane_ctl |= PLANE_CTL_PLANE_GAMMA_DISABLE;
 
 		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_ctl |= PLANE_CTL_YUV_TO_RGB_CSC_FORMAT_BT709;
@@ -3710,19 +3746,27 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 	return plane_ctl;
 }
 
+u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	u32 plane_color_ctl = 0;
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		return plane_color_ctl;
+
+	plane_color_ctl |= PLANE_COLOR_PIPE_GAMMA_ENABLE;
+	plane_color_ctl |= PLANE_COLOR_PIPE_CSC_ENABLE;
+
+	return plane_color_ctl;
+}
+
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
 	u32 plane_color_ctl = 0;
 
-	if (INTEL_GEN(dev_priv) < 11) {
-		plane_color_ctl |= PLANE_COLOR_PIPE_GAMMA_ENABLE;
-		plane_color_ctl |= PLANE_COLOR_PIPE_CSC_ENABLE;
-	}
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(plane_state);
 
@@ -3771,7 +3815,7 @@ __intel_display_resume(struct drm_device *dev,
 	}
 
 	/* ignore any reset values/BIOS leftovers in the WM registers */
-	if (!HAS_GMCH_DISPLAY(to_i915(dev)))
+	if (!HAS_GMCH(to_i915(dev)))
 		to_intel_atomic_state(state)->skip_intermediate_wm = true;
 
 	ret = drm_atomic_helper_commit_duplicated_state(state, ctx);
@@ -3896,6 +3940,30 @@ unlock:
 	clear_bit(I915_RESET_MODESET, &dev_priv->gpu_error.flags);
 }
 
+static void icl_set_pipe_chicken(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
+	u32 tmp;
+
+	tmp = I915_READ(PIPE_CHICKEN(pipe));
+
+	/*
+	 * Display WA #1153: icl
+	 * enable hardware to bypass the alpha math
+	 * and rounding for per-pixel values 00 and 0xff
+	 */
+	tmp |= PER_PIXEL_ALPHA_BYPASS_EN;
+
+	/*
+	 * W/A for underruns with linear/X-tiled with
+	 * WM1+ disabled.
+	 */
+	tmp |= PM_FILL_MAINTAIN_DBUF_FULLNESS;
+
+	I915_WRITE(PIPE_CHICKEN(pipe), tmp);
+}
+
 static void intel_update_pipe_config(const struct intel_crtc_state *old_crtc_state,
 				     const struct intel_crtc_state *new_crtc_state)
 {
@@ -3940,6 +4008,9 @@ static void intel_update_pipe_config(const struct intel_crtc_state *old_crtc_sta
 		I915_WRITE(SKL_BOTTOM_COLOR(crtc->pipe),
 			   SKL_BOTTOM_COLOR_GAMMA_ENABLE |
 			   SKL_BOTTOM_COLOR_CSC_ENABLE);
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_set_pipe_chicken(crtc);
 }
 
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
@@ -5294,7 +5365,7 @@ intel_pre_disable_primary_noatomic(struct drm_crtc *crtc)
 	 * event which is after the vblank start event, so we need to have a
 	 * wait-for-vblank between disabling the plane and the pipe.
 	 */
-	if (HAS_GMCH_DISPLAY(dev_priv) &&
+	if (HAS_GMCH(dev_priv) &&
 	    intel_set_memory_cxsr(dev_priv, false))
 		intel_wait_for_vblank(dev_priv, pipe);
 }
@@ -5302,18 +5373,36 @@ intel_pre_disable_primary_noatomic(struct drm_crtc *crtc)
 static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_state,
 				       const struct intel_crtc_state *new_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
 	if (!old_crtc_state->ips_enabled)
 		return false;
 
 	if (needs_modeset(&new_crtc_state->base))
 		return true;
 
+	/*
+	 * Workaround : Do not read or write the pipe palette/gamma data while
+	 * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled.
+	 *
+	 * Disable IPS before we program the LUT.
+	 */
+	if (IS_HASWELL(dev_priv) &&
+	    (new_crtc_state->base.color_mgmt_changed ||
+	     new_crtc_state->update_pipe) &&
+	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
+		return true;
+
 	return !new_crtc_state->ips_enabled;
 }
 
 static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_state,
 				       const struct intel_crtc_state *new_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
 	if (!new_crtc_state->ips_enabled)
 		return false;
 
@@ -5321,6 +5410,18 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s
 		return true;
 
 	/*
+	 * Workaround : Do not read or write the pipe palette/gamma data while
+	 * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled.
+	 *
+	 * Re-enable IPS after the LUT has been programmed.
+	 */
+	if (IS_HASWELL(dev_priv) &&
+	    (new_crtc_state->base.color_mgmt_changed ||
+	     new_crtc_state->update_pipe) &&
+	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
+		return true;
+
+	/*
 	 * We can't read out IPS on broadwell, assume the worst and
 	 * forcibly enable IPS on the first fastset.
 	 */
@@ -5431,7 +5532,7 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	 * event which is after the vblank start event, so we need to have a
 	 * wait-for-vblank between disabling the plane and the pipe.
 	 */
-	if (HAS_GMCH_DISPLAY(dev_priv) && old_crtc_state->base.active &&
+	if (HAS_GMCH(dev_priv) && old_crtc_state->base.active &&
 	    pipe_config->disable_cxsr && intel_set_memory_cxsr(dev_priv, false))
 		intel_wait_for_vblank(dev_priv, crtc->pipe);
 
@@ -5708,6 +5809,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	 * clocks enabled
 	 */
 	intel_color_load_luts(pipe_config);
+	intel_color_commit(pipe_config);
 
 	if (dev_priv->display.initial_watermarks != NULL)
 		dev_priv->display.initial_watermarks(old_intel_state, pipe_config);
@@ -5782,7 +5884,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
 	bool psl_clkgate_wa;
-	u32 pipe_chicken;
 
 	if (WARN_ON(intel_crtc->active))
 		return;
@@ -5818,8 +5919,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	haswell_set_pipemisc(pipe_config);
 
-	intel_color_set_csc(pipe_config);
-
 	intel_crtc->active = true;
 
 	/* Display WA #1180: WaDisableScalarClockGating: glk, cnl */
@@ -5838,17 +5937,10 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	 * clocks enabled
 	 */
 	intel_color_load_luts(pipe_config);
+	intel_color_commit(pipe_config);
 
-	/*
-	 * Display WA #1153: enable hardware to bypass the alpha math
-	 * and rounding for per-pixel values 00 and 0xff
-	 */
-	if (INTEL_GEN(dev_priv) >= 11) {
-		pipe_chicken = I915_READ(PIPE_CHICKEN(pipe));
-		if (!(pipe_chicken & PER_PIXEL_ALPHA_BYPASS_EN))
-			I915_WRITE_FW(PIPE_CHICKEN(pipe),
-				      pipe_chicken | PER_PIXEL_ALPHA_BYPASS_EN);
-	}
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_set_pipe_chicken(intel_crtc);
 
 	intel_ddi_set_pipe_settings(pipe_config);
 	if (!transcoder_is_dsi(cpu_transcoder))
@@ -6183,8 +6275,6 @@ static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	i9xx_set_pipeconf(pipe_config);
 
-	intel_color_set_csc(pipe_config);
-
 	intel_crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
@@ -6204,6 +6294,7 @@ static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config,
 	i9xx_pfit_enable(pipe_config);
 
 	intel_color_load_luts(pipe_config);
+	intel_color_commit(pipe_config);
 
 	dev_priv->display.initial_watermarks(old_intel_state,
 					     pipe_config);
@@ -6260,6 +6351,7 @@ static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config,
 	i9xx_pfit_enable(pipe_config);
 
 	intel_color_load_luts(pipe_config);
+	intel_color_commit(pipe_config);
 
 	if (dev_priv->display.initial_watermarks != NULL)
 		dev_priv->display.initial_watermarks(old_intel_state,
@@ -6705,7 +6797,7 @@ static void intel_crtc_compute_pixel_rate(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
 
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		/* FIXME calculate proper pipe pixel rate for GMCH pfit */
 		crtc_state->pixel_rate =
 			crtc_state->base.adjusted_mode.crtc_clock;
@@ -9814,7 +9906,7 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 	base += plane_state->color_plane[0].offset;
 
 	/* ILK+ do this automagically */
-	if (HAS_GMCH_DISPLAY(dev_priv) &&
+	if (HAS_GMCH(dev_priv) &&
 	    plane_state->base.rotation & DRM_MODE_ROTATE_180)
 		base += (plane_state->base.crtc_h *
 			 plane_state->base.crtc_w - 1) * fb->format->cpp[0];
@@ -9927,11 +10019,15 @@ i845_cursor_max_stride(struct intel_plane *plane,
 	return 2048;
 }
 
+static u32 i845_cursor_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	return CURSOR_GAMMA_ENABLE;
+}
+
 static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state)
 {
 	return CURSOR_ENABLE |
-		CURSOR_GAMMA_ENABLE |
 		CURSOR_FORMAT_ARGB |
 		CURSOR_STRIDE(plane_state->color_plane[0].stride);
 }
@@ -10001,7 +10097,9 @@ static void i845_update_cursor(struct intel_plane *plane,
 		unsigned int width = plane_state->base.crtc_w;
 		unsigned int height = plane_state->base.crtc_h;
 
-		cntl = plane_state->ctl;
+		cntl = plane_state->ctl |
+			i845_cursor_ctl_crtc(crtc_state);
+
 		size = (height << 12) | width;
 
 		base = intel_cursor_base(plane_state);
@@ -10068,27 +10166,36 @@ i9xx_cursor_max_stride(struct intel_plane *plane,
 	return plane->base.dev->mode_config.cursor_width * 4;
 }
 
-static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
-			   const struct intel_plane_state *plane_state)
+static u32 i9xx_cursor_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 cntl = 0;
 
-	if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv))
-		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
+	if (INTEL_GEN(dev_priv) >= 11)
+		return cntl;
 
-	if (INTEL_GEN(dev_priv) <= 10) {
-		cntl |= MCURSOR_GAMMA_ENABLE;
+	cntl |= MCURSOR_GAMMA_ENABLE;
 
-		if (HAS_DDI(dev_priv))
-			cntl |= MCURSOR_PIPE_CSC_ENABLE;
-	}
+	if (HAS_DDI(dev_priv))
+		cntl |= MCURSOR_PIPE_CSC_ENABLE;
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv))
 		cntl |= MCURSOR_PIPE_SELECT(crtc->pipe);
 
+	return cntl;
+}
+
+static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
+			   const struct intel_plane_state *plane_state)
+{
+	struct drm_i915_private *dev_priv =
+		to_i915(plane_state->base.plane->dev);
+	u32 cntl = 0;
+
+	if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv))
+		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
+
 	switch (plane_state->base.crtc_w) {
 	case 64:
 		cntl |= MCURSOR_MODE_64_ARGB_AX;
@@ -10213,7 +10320,8 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 	unsigned long irqflags;
 
 	if (plane_state && plane_state->base.visible) {
-		cntl = plane_state->ctl;
+		cntl = plane_state->ctl |
+			i9xx_cursor_ctl_crtc(crtc_state);
 
 		if (plane_state->base.crtc_h != plane_state->base.crtc_w)
 			fbc_ctl = CUR_FBC_CTL_EN | (plane_state->base.crtc_h - 1);
@@ -11045,7 +11153,8 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 	int ret;
 	bool mode_changed = needs_modeset(crtc_state);
 
-	if (mode_changed && !crtc_state->active)
+	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv) &&
+	    mode_changed && !crtc_state->active)
 		pipe_config->update_wm_post = true;
 
 	if (mode_changed && crtc_state->enable &&
@@ -11057,7 +11166,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 			return ret;
 	}
 
-	if (crtc_state->color_mgmt_changed) {
+	if (mode_changed || crtc_state->color_mgmt_changed) {
 		ret = intel_color_check(pipe_config);
 		if (ret)
 			return ret;
@@ -11356,7 +11465,7 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 			      pipe_config->scaler_state.scaler_users,
 		              pipe_config->scaler_state.scaler_id);
 
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		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,
@@ -11468,44 +11577,38 @@ static bool check_digital_port_conflicts(struct drm_atomic_state *state)
 	return ret;
 }
 
-static void
+static int
 clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc_scaler_state scaler_state;
-	struct intel_dpll_hw_state dpll_hw_state;
-	struct intel_shared_dpll *shared_dpll;
-	struct intel_crtc_wm_state wm_state;
-	bool force_thru, ips_force_disable;
+	struct intel_crtc_state *saved_state;
+
+	saved_state = kzalloc(sizeof(*saved_state), GFP_KERNEL);
+	if (!saved_state)
+		return -ENOMEM;
 
 	/* FIXME: before the switch to atomic started, a new pipe_config was
 	 * kzalloc'd. Code that depends on any field being zero should be
 	 * fixed, so that the crtc_state can be safely duplicated. For now,
 	 * only fields that are know to not cause problems are preserved. */
 
-	scaler_state = crtc_state->scaler_state;
-	shared_dpll = crtc_state->shared_dpll;
-	dpll_hw_state = crtc_state->dpll_hw_state;
-	force_thru = crtc_state->pch_pfit.force_thru;
-	ips_force_disable = crtc_state->ips_force_disable;
+	saved_state->scaler_state = crtc_state->scaler_state;
+	saved_state->shared_dpll = crtc_state->shared_dpll;
+	saved_state->dpll_hw_state = crtc_state->dpll_hw_state;
+	saved_state->pch_pfit.force_thru = crtc_state->pch_pfit.force_thru;
+	saved_state->ips_force_disable = crtc_state->ips_force_disable;
 	if (IS_G4X(dev_priv) ||
 	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		wm_state = crtc_state->wm;
+		saved_state->wm = crtc_state->wm;
 
 	/* Keep base drm_crtc_state intact, only clear our extended struct */
 	BUILD_BUG_ON(offsetof(struct intel_crtc_state, base));
-	memset(&crtc_state->base + 1, 0,
+	memcpy(&crtc_state->base + 1, &saved_state->base + 1,
 	       sizeof(*crtc_state) - sizeof(crtc_state->base));
 
-	crtc_state->scaler_state = scaler_state;
-	crtc_state->shared_dpll = shared_dpll;
-	crtc_state->dpll_hw_state = dpll_hw_state;
-	crtc_state->pch_pfit.force_thru = force_thru;
-	crtc_state->ips_force_disable = ips_force_disable;
-	if (IS_G4X(dev_priv) ||
-	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		crtc_state->wm = wm_state;
+	kfree(saved_state);
+	return 0;
 }
 
 static int
@@ -11520,7 +11623,9 @@ intel_modeset_pipe_config(struct drm_crtc *crtc,
 	int i;
 	bool retry = true;
 
-	clear_intel_crtc_state(pipe_config);
+	ret = clear_intel_crtc_state(pipe_config);
+	if (ret)
+		return ret;
 
 	pipe_config->cpu_transcoder =
 		(enum transcoder) to_intel_crtc(crtc)->pipe;
@@ -13096,7 +13201,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 
 			/* FIXME unify this for all platforms */
 			if (!new_crtc_state->active &&
-			    !HAS_GMCH_DISPLAY(dev_priv) &&
+			    !HAS_GMCH(dev_priv) &&
 			    dev_priv->display.initial_watermarks)
 				dev_priv->display.initial_watermarks(intel_state,
 								     new_intel_crtc_state);
@@ -13150,6 +13255,16 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	 */
 	drm_atomic_helper_wait_for_flip_done(dev, state);
 
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		new_intel_crtc_state = to_intel_crtc_state(new_crtc_state);
+
+		if (new_crtc_state->active &&
+		    !needs_modeset(new_crtc_state) &&
+		    (new_intel_crtc_state->base.color_mgmt_changed ||
+		     new_intel_crtc_state->update_pipe))
+			intel_color_load_luts(new_intel_crtc_state);
+	}
+
 	/*
 	 * Now that the vblank has passed, we can go ahead and program the
 	 * optimal watermarks on platforms that need two-step watermark
@@ -13665,19 +13780,16 @@ static void intel_begin_crtc_commit(struct drm_crtc *crtc,
 		intel_atomic_get_new_crtc_state(old_intel_state, intel_crtc);
 	bool modeset = needs_modeset(&intel_cstate->base);
 
-	if (!modeset &&
-	    (intel_cstate->base.color_mgmt_changed ||
-	     intel_cstate->update_pipe)) {
-		intel_color_set_csc(intel_cstate);
-		intel_color_load_luts(intel_cstate);
-	}
-
 	/* Perform vblank evasion around commit operation */
 	intel_pipe_update_start(intel_cstate);
 
 	if (modeset)
 		goto out;
 
+	if (intel_cstate->base.color_mgmt_changed ||
+	    intel_cstate->update_pipe)
+		intel_color_commit(intel_cstate);
+
 	if (intel_cstate->update_pipe)
 		intel_update_pipe_config(old_intel_cstate, intel_cstate);
 	else if (INTEL_GEN(dev_priv) >= 9)
@@ -15074,7 +15186,7 @@ retry:
 	 * intermediate watermarks (since we don't trust the current
 	 * watermarks).
 	 */
-	if (!HAS_GMCH_DISPLAY(dev_priv))
+	if (!HAS_GMCH(dev_priv))
 		intel_state->skip_intermediate_wm = true;
 
 	ret = intel_atomic_check(dev, state);
@@ -15315,7 +15427,7 @@ int intel_modeset_init(struct drm_device *dev)
 	 * Note that we need to do this after reconstructing the BIOS fb's
 	 * since the watermark calculation done here will use pstate->fb.
 	 */
-	if (!HAS_GMCH_DISPLAY(dev_priv))
+	if (!HAS_GMCH(dev_priv))
 		sanitize_watermarks(dev);
 
 	/*
@@ -15524,7 +15636,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc,
 	if (crtc_state->base.active && !intel_crtc_has_encoders(crtc))
 		intel_crtc_disable_noatomic(&crtc->base, ctx);
 
-	if (crtc_state->base.active || HAS_GMCH_DISPLAY(dev_priv)) {
+	if (crtc_state->base.active || HAS_GMCH(dev_priv)) {
 		/*
 		 * We start out with underrun reporting disabled to avoid races.
 		 * For correct bookkeeping mark this on active crtcs.
@@ -16271,7 +16383,7 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv)
 
 		error->pipe[i].source = I915_READ(PIPESRC(i));
 
-		if (HAS_GMCH_DISPLAY(dev_priv))
+		if (HAS_GMCH(dev_priv))
 			error->pipe[i].stat = I915_READ(PIPESTAT(i));
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 681e88405ada..cf709835fb9a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1061,6 +1061,10 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp)
 #define C (((status = I915_READ_NOTRACE(ch_ctl)) & DP_AUX_CH_CTL_SEND_BUSY) == 0)
 	done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
 				  msecs_to_jiffies_timeout(10));
+
+	/* just trace the final value */
+	trace_i915_reg_rw(false, ch_ctl, status, sizeof(status), true);
+
 	if (!done)
 		DRM_ERROR("dp aux hw did not signal timeout!\n");
 #undef C
@@ -1227,6 +1231,8 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 			break;
 		msleep(1);
 	}
+	/* just trace the final value */
+	trace_i915_reg_rw(false, ch_ctl, status, sizeof(status), true);
 
 	if (try == 3) {
 		static u32 last_status = -1;
@@ -2141,7 +2147,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 				return ret;
 		}
 
-		if (HAS_GMCH_DISPLAY(dev_priv))
+		if (HAS_GMCH(dev_priv))
 			intel_gmch_panel_fitting(intel_crtc, pipe_config,
 						 conn_state->scaling_mode);
 		else
@@ -2152,7 +2158,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
 
-	if (HAS_GMCH_DISPLAY(dev_priv) &&
+	if (HAS_GMCH(dev_priv) &&
 	    adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
 		return -EINVAL;
 
@@ -4608,12 +4614,10 @@ go_again:
 
 			return ret;
 		} else {
-			struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 			DRM_DEBUG_KMS("failed to get ESI - device may have failed\n");
 			intel_dp->is_mst = false;
-			drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, intel_dp->is_mst);
-			/* send a hotplug event */
-			drm_kms_helper_hotplug_event(intel_dig_port->base.base.dev);
+			drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr,
+							intel_dp->is_mst);
 		}
 	}
 	return -EINVAL;
@@ -5300,7 +5304,7 @@ bool intel_digital_port_connected(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (HAS_GMCH_DISPLAY(dev_priv)) {
+	if (HAS_GMCH(dev_priv)) {
 		if (IS_GM45(dev_priv))
 			return gm45_digital_port_connected(encoder);
 		else
@@ -6038,7 +6042,7 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 		intel_attach_force_audio_property(connector);
 
 	intel_attach_broadcast_rgb_property(connector);
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		drm_connector_attach_max_bpc_property(connector, 6, 10);
 	else if (INTEL_GEN(dev_priv) >= 5)
 		drm_connector_attach_max_bpc_property(connector, 6, 12);
@@ -6047,7 +6051,7 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 		u32 allowed_scalers;
 
 		allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN);
-		if (!HAS_GMCH_DISPLAY(dev_priv))
+		if (!HAS_GMCH(dev_priv))
 			allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
 
 		drm_connector_attach_scaling_mode_property(connector, allowed_scalers);
@@ -6919,7 +6923,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
 	drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
 
-	if (!HAS_GMCH_DISPLAY(dev_priv))
+	if (!HAS_GMCH(dev_priv))
 		connector->interlace_allowed = true;
 	connector->doublescan_allowed = 0;
 
@@ -7096,7 +7100,10 @@ void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 			continue;
 
 		ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr);
-		if (ret)
-			intel_dp_check_mst_status(intel_dp);
+		if (ret) {
+			intel_dp->is_mst = false;
+			drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr,
+							false);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 90ba5436370e..15db41394b9e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -213,6 +213,16 @@ struct intel_fbdev {
 	unsigned long vma_flags;
 	async_cookie_t cookie;
 	int preferred_bpp;
+
+	/* Whether or not fbdev hpd processing is temporarily suspended */
+	bool hpd_suspended : 1;
+	/* Set when a hotplug was received while HPD processing was
+	 * suspended
+	 */
+	bool hpd_waiting : 1;
+
+	/* Protects hpd_suspended */
+	struct mutex hpd_lock;
 };
 
 struct intel_encoder {
@@ -1756,9 +1766,10 @@ static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *state)
 
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
+u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state);
 u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state);
-u32 glk_color_ctl(const struct intel_plane_state *plane_state);
+u32 skl_plane_ctl_crtc(const struct intel_crtc_state *crtc_state);
 u32 skl_plane_stride(const struct intel_plane_state *plane_state,
 		     int plane);
 int skl_check_plane_surface(struct intel_plane_state *plane_state);
@@ -2379,8 +2390,8 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 /* intel_color.c */
 void intel_color_init(struct intel_crtc *crtc);
 int intel_color_check(struct intel_crtc_state *crtc_state);
-void intel_color_set_csc(struct intel_crtc_state *crtc_state);
-void intel_color_load_luts(struct intel_crtc_state *crtc_state);
+void intel_color_commit(const struct intel_crtc_state *crtc_state);
+void intel_color_load_luts(const struct intel_crtc_state *crtc_state);
 
 /* intel_lspcon.c */
 bool lspcon_init(struct intel_digital_port *intel_dig_port);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 71c01eb13af1..49fa43ff02ba 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1086,7 +1086,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 * the last request that remains in the timeline. When idle, it is
 	 * the last executed context as tracked by retirement.
 	 */
-	rq = __i915_gem_active_peek(&engine->timeline.last_request);
+	rq = __i915_active_request_peek(&engine->timeline.last_request);
 	if (rq)
 		return rq->hw_context == kernel_context;
 	else
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 8cf3efe88f02..376ffe842e26 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -681,6 +681,7 @@ int intel_fbdev_init(struct drm_device *dev)
 	if (ifbdev == NULL)
 		return -ENOMEM;
 
+	mutex_init(&ifbdev->hpd_lock);
 	drm_fb_helper_prepare(dev, &ifbdev->helper, &intel_fb_helper_funcs);
 
 	if (!intel_fbdev_init_bios(dev, ifbdev))
@@ -754,6 +755,26 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv)
 	intel_fbdev_destroy(ifbdev);
 }
 
+/* Suspends/resumes fbdev processing of incoming HPD events. When resuming HPD
+ * processing, fbdev will perform a full connector reprobe if a hotplug event
+ * was received while HPD was suspended.
+ */
+static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state)
+{
+	bool send_hpd = false;
+
+	mutex_lock(&ifbdev->hpd_lock);
+	ifbdev->hpd_suspended = state == FBINFO_STATE_SUSPENDED;
+	send_hpd = !ifbdev->hpd_suspended && ifbdev->hpd_waiting;
+	ifbdev->hpd_waiting = false;
+	mutex_unlock(&ifbdev->hpd_lock);
+
+	if (send_hpd) {
+		DRM_DEBUG_KMS("Handling delayed fbcon HPD event\n");
+		drm_fb_helper_hotplug_event(&ifbdev->helper);
+	}
+}
+
 void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -775,6 +796,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 		 */
 		if (state != FBINFO_STATE_RUNNING)
 			flush_work(&dev_priv->fbdev_suspend_work);
+
 		console_lock();
 	} else {
 		/*
@@ -802,17 +824,26 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 
 	drm_fb_helper_set_suspend(&ifbdev->helper, state);
 	console_unlock();
+
+	intel_fbdev_hpd_set_suspend(ifbdev, state);
 }
 
 void intel_fbdev_output_poll_changed(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
+	bool send_hpd;
 
 	if (!ifbdev)
 		return;
 
 	intel_fbdev_sync(ifbdev);
-	if (ifbdev->vma || ifbdev->helper.deferred_setup)
+
+	mutex_lock(&ifbdev->hpd_lock);
+	send_hpd = !ifbdev->hpd_suspended;
+	ifbdev->hpd_waiting = true;
+	mutex_unlock(&ifbdev->hpd_lock);
+
+	if (send_hpd && (ifbdev->vma || ifbdev->helper.deferred_setup))
 		drm_fb_helper_hotplug_event(&ifbdev->helper);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c
index 3b9285130ef5..f33de4be4b89 100644
--- a/drivers/gpu/drm/i915/intel_fifo_underrun.c
+++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c
@@ -258,7 +258,7 @@ static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 	old = !crtc->cpu_fifo_underrun_disabled;
 	crtc->cpu_fifo_underrun_disabled = !enable;
 
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (IS_GEN_RANGE(dev_priv, 5, 6))
 		ironlake_set_fifo_underrun_reporting(dev, pipe, enable);
@@ -369,7 +369,7 @@ void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv,
 		return;
 
 	/* GMCH can't disable fifo underruns, filter them. */
-	if (HAS_GMCH_DISPLAY(dev_priv) &&
+	if (HAS_GMCH(dev_priv) &&
 	    crtc->cpu_fifo_underrun_disabled)
 		return;
 
@@ -421,7 +421,7 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv)
 		if (crtc->cpu_fifo_underrun_disabled)
 			continue;
 
-		if (HAS_GMCH_DISPLAY(dev_priv))
+		if (HAS_GMCH(dev_priv))
 			i9xx_check_fifo_underruns(crtc);
 		else if (IS_GEN(dev_priv, 7))
 			ivybridge_check_fifo_underruns(crtc);
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index b53582c0c6c1..806fdfd7c78a 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -140,6 +140,9 @@ static struct dentry *create_buf_file_callback(const char *filename,
 
 	buf_file = debugfs_create_file(filename, mode,
 				       parent, buf, &relay_file_operations);
+	if (IS_ERR(buf_file))
+		return NULL;
+
 	return buf_file;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 97a98e1bea56..f125a62eba8c 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1588,7 +1588,7 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 
 	if (hdmi->has_hdmi_sink && !force_dvi) {
 		/* if we can't do 8bpc we may still be able to do 12bpc */
-		if (status != MODE_OK && !HAS_GMCH_DISPLAY(dev_priv))
+		if (status != MODE_OK && !HAS_GMCH(dev_priv))
 			status = hdmi_port_clock_valid(hdmi, clock * 3 / 2,
 						       true, force_dvi);
 
@@ -1613,7 +1613,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 		&crtc_state->base.adjusted_mode;
 	int i;
 
-	if (HAS_GMCH_DISPLAY(dev_priv))
+	if (HAS_GMCH(dev_priv))
 		return false;
 
 	if (bpc == 10 && INTEL_GEN(dev_priv) < 11)
@@ -2150,7 +2150,7 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 	drm_connector_attach_content_type_property(connector);
 	connector->state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 
-	if (!HAS_GMCH_DISPLAY(dev_priv))
+	if (!HAS_GMCH(dev_priv))
 		drm_connector_attach_max_bpc_property(connector, 8, 12);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index e027d2b4abe5..b8937c788f03 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -470,7 +470,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			 * hotplug bits itself. So only WARN about unexpected
 			 * interrupts on saner platforms.
 			 */
-			WARN_ONCE(!HAS_GMCH_DISPLAY(dev_priv),
+			WARN_ONCE(!HAS_GMCH(dev_priv),
 				  "Received HPD interrupt on pin %d although disabled\n", pin);
 			continue;
 		}
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 4f6dc8c94634..5a733e711355 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -823,7 +823,7 @@ int intel_setup_gmbus(struct drm_i915_private *dev_priv)
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		dev_priv->gpio_mmio_base = VLV_DISPLAY_BASE;
-	else if (!HAS_GMCH_DISPLAY(dev_priv))
+	else if (!HAS_GMCH(dev_priv))
 		/*
 		 * Broxton uses the same PCH offsets for South Display Engine,
 		 * even though it doesn't have a PCH.
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index a9eb0211ce77..5e98fd79bd9d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1266,8 +1266,6 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	return i915_vma_pin(vma, 0, 0, flags);
 }
 
-static u32 make_rpcs(struct drm_i915_private *dev_priv);
-
 static void
 __execlists_update_reg_state(struct intel_engine_cs *engine,
 			     struct intel_context *ce)
@@ -1281,7 +1279,8 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
 
 	/* RPCS */
 	if (engine->class == RENDER_CLASS)
-		regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915);
+		regs[CTX_R_PWR_CLK_STATE + 1] = gen8_make_rpcs(engine->i915,
+							       &ce->sseu);
 }
 
 static struct intel_context *
@@ -2431,22 +2430,50 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
 	return logical_ring_init(engine);
 }
 
-static u32
-make_rpcs(struct drm_i915_private *dev_priv)
+u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu)
 {
-	bool subslice_pg = RUNTIME_INFO(dev_priv)->sseu.has_subslice_pg;
-	u8 slices = hweight8(RUNTIME_INFO(dev_priv)->sseu.slice_mask);
-	u8 subslices = hweight8(RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0]);
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+	bool subslice_pg = sseu->has_subslice_pg;
+	struct intel_sseu ctx_sseu;
+	u8 slices, subslices;
 	u32 rpcs = 0;
 
 	/*
 	 * No explicit RPCS request is needed to ensure full
 	 * slice/subslice/EU enablement prior to Gen9.
 	*/
-	if (INTEL_GEN(dev_priv) < 9)
+	if (INTEL_GEN(i915) < 9)
 		return 0;
 
 	/*
+	 * If i915/perf is active, we want a stable powergating configuration
+	 * on the system.
+	 *
+	 * We could choose full enablement, but on ICL we know there are use
+	 * cases which disable slices for functional, apart for performance
+	 * reasons. So in this case we select a known stable subset.
+	 */
+	if (!i915->perf.oa.exclusive_stream) {
+		ctx_sseu = *req_sseu;
+	} else {
+		ctx_sseu = intel_device_default_sseu(i915);
+
+		if (IS_GEN(i915, 11)) {
+			/*
+			 * We only need subslice count so it doesn't matter
+			 * which ones we select - just turn off low bits in the
+			 * amount of half of all available subslices per slice.
+			 */
+			ctx_sseu.subslice_mask =
+				~(~0 << (hweight8(ctx_sseu.subslice_mask) / 2));
+			ctx_sseu.slice_mask = 0x1;
+		}
+	}
+
+	slices = hweight8(ctx_sseu.slice_mask);
+	subslices = hweight8(ctx_sseu.subslice_mask);
+
+	/*
 	 * Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits
 	 * wide and Icelake has up to eight subslices, specfial programming is
 	 * needed in order to correctly enable all subslices.
@@ -2471,7 +2498,9 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * subslices are enabled, or a count between one and four on the first
 	 * slice.
 	 */
-	if (IS_GEN(dev_priv, 11) && slices == 1 && subslices >= 4) {
+	if (IS_GEN(i915, 11) &&
+	    slices == 1 &&
+	    subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
 		GEM_BUG_ON(subslices & 1);
 
 		subslice_pg = false;
@@ -2484,10 +2513,10 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * must make an explicit request through RPCS for full
 	 * enablement.
 	*/
-	if (RUNTIME_INFO(dev_priv)->sseu.has_slice_pg) {
+	if (sseu->has_slice_pg) {
 		u32 mask, val = slices;
 
-		if (INTEL_GEN(dev_priv) >= 11) {
+		if (INTEL_GEN(i915) >= 11) {
 			mask = GEN11_RPCS_S_CNT_MASK;
 			val <<= GEN11_RPCS_S_CNT_SHIFT;
 		} else {
@@ -2512,18 +2541,16 @@ make_rpcs(struct drm_i915_private *dev_priv)
 		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val;
 	}
 
-	if (RUNTIME_INFO(dev_priv)->sseu.has_eu_pg) {
+	if (sseu->has_eu_pg) {
 		u32 val;
 
-		val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice <<
-		      GEN8_RPCS_EU_MIN_SHIFT;
+		val = ctx_sseu.min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
 		val &= GEN8_RPCS_EU_MIN_MASK;
 
 		rpcs |= val;
 
-		val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice <<
-		      GEN8_RPCS_EU_MAX_SHIFT;
+		val = ctx_sseu.max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
 		val &= GEN8_RPCS_EU_MAX_MASK;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 3d86c27c6b32..f1aec8a6986f 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -112,4 +112,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 							const char *prefix),
 				   unsigned int max);
 
+u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
+
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index a9238fd07e30..c0df1dbb0069 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -186,7 +186,7 @@ struct intel_overlay {
 	struct overlay_registers __iomem *regs;
 	u32 flip_addr;
 	/* flip handling */
-	struct i915_gem_active last_flip;
+	struct i915_active_request last_flip;
 };
 
 static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv,
@@ -214,23 +214,23 @@ static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv,
 
 static void intel_overlay_submit_request(struct intel_overlay *overlay,
 					 struct i915_request *rq,
-					 i915_gem_retire_fn retire)
+					 i915_active_retire_fn retire)
 {
-	GEM_BUG_ON(i915_gem_active_peek(&overlay->last_flip,
-					&overlay->i915->drm.struct_mutex));
-	i915_gem_active_set_retire_fn(&overlay->last_flip, retire,
-				      &overlay->i915->drm.struct_mutex);
-	i915_gem_active_set(&overlay->last_flip, rq);
+	GEM_BUG_ON(i915_active_request_peek(&overlay->last_flip,
+					    &overlay->i915->drm.struct_mutex));
+	i915_active_request_set_retire_fn(&overlay->last_flip, retire,
+					  &overlay->i915->drm.struct_mutex);
+	__i915_active_request_set(&overlay->last_flip, rq);
 	i915_request_add(rq);
 }
 
 static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 					 struct i915_request *rq,
-					 i915_gem_retire_fn retire)
+					 i915_active_retire_fn retire)
 {
 	intel_overlay_submit_request(overlay, rq, retire);
-	return i915_gem_active_retire(&overlay->last_flip,
-				      &overlay->i915->drm.struct_mutex);
+	return i915_active_request_retire(&overlay->last_flip,
+					  &overlay->i915->drm.struct_mutex);
 }
 
 static struct i915_request *alloc_request(struct intel_overlay *overlay)
@@ -351,8 +351,9 @@ static void intel_overlay_release_old_vma(struct intel_overlay *overlay)
 	i915_vma_put(vma);
 }
 
-static void intel_overlay_release_old_vid_tail(struct i915_gem_active *active,
-					       struct i915_request *rq)
+static void
+intel_overlay_release_old_vid_tail(struct i915_active_request *active,
+				   struct i915_request *rq)
 {
 	struct intel_overlay *overlay =
 		container_of(active, typeof(*overlay), last_flip);
@@ -360,7 +361,7 @@ static void intel_overlay_release_old_vid_tail(struct i915_gem_active *active,
 	intel_overlay_release_old_vma(overlay);
 }
 
-static void intel_overlay_off_tail(struct i915_gem_active *active,
+static void intel_overlay_off_tail(struct i915_active_request *active,
 				   struct i915_request *rq)
 {
 	struct intel_overlay *overlay =
@@ -423,8 +424,8 @@ static int intel_overlay_off(struct intel_overlay *overlay)
  * We have to be careful not to repeat work forever an make forward progess. */
 static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
 {
-	return i915_gem_active_retire(&overlay->last_flip,
-				      &overlay->i915->drm.struct_mutex);
+	return i915_active_request_retire(&overlay->last_flip,
+					  &overlay->i915->drm.struct_mutex);
 }
 
 /* Wait for pending overlay flip and release old frame.
@@ -1357,7 +1358,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 	overlay->contrast = 75;
 	overlay->saturation = 146;
 
-	init_request_active(&overlay->last_flip, NULL);
+	INIT_ACTIVE_REQUEST(&overlay->last_flip);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ed9786241307..0f15685529a0 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3927,14 +3927,9 @@ static unsigned int skl_cursor_allocation(int num_active)
 static void skl_ddb_entry_init_from_hw(struct drm_i915_private *dev_priv,
 				       struct skl_ddb_entry *entry, u32 reg)
 {
-	u16 mask;
 
-	if (INTEL_GEN(dev_priv) >= 11)
-		mask = ICL_DDB_ENTRY_MASK;
-	else
-		mask = SKL_DDB_ENTRY_MASK;
-	entry->start = reg & mask;
-	entry->end = (reg >> DDB_ENTRY_END_SHIFT) & mask;
+	entry->start = reg & DDB_ENTRY_MASK;
+	entry->end = (reg >> DDB_ENTRY_END_SHIFT) & DDB_ENTRY_MASK;
 
 	if (entry->end)
 		entry->end += 1;
@@ -4319,7 +4314,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	int num_active;
 	u64 plane_data_rate[I915_MAX_PLANES] = {};
 	u64 uv_plane_data_rate[I915_MAX_PLANES] = {};
-	u16 blocks = 0;
+	u32 blocks;
 	int level;
 
 	/* Clear the partitioning for disabled planes. */
@@ -4694,8 +4689,11 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *cstate,
 	uint_fixed_16_16_t selected_result;
 	u32 res_blocks, res_lines, min_ddb_alloc = 0;
 
-	if (latency == 0)
+	if (latency == 0) {
+		/* reject it */
+		result->min_ddb_alloc = U16_MAX;
 		return;
+	}
 
 	/* Display WA #1141: kbl,cfl */
 	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) ||
@@ -4783,8 +4781,11 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *cstate,
 	if (!skl_wm_has_lines(dev_priv, level))
 		res_lines = 0;
 
-	if (res_lines > 31)
+	if (res_lines > 31) {
+		/* reject it */
+		result->min_ddb_alloc = U16_MAX;
 		return;
+	}
 
 	/*
 	 * If res_lines is valid, assume we can use this watermark level
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b889b27f8aeb..7f841dba87b3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -49,19 +49,6 @@ static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
 		I915_GEM_HWS_INDEX_ADDR);
 }
 
-static unsigned int __intel_ring_space(unsigned int head,
-				       unsigned int tail,
-				       unsigned int size)
-{
-	/*
-	 * "If the Ring Buffer Head Pointer and the Tail Pointer are on the
-	 * same cacheline, the Head Pointer must not be greater than the Tail
-	 * Pointer."
-	 */
-	GEM_BUG_ON(!is_power_of_2(size));
-	return (head - tail - CACHELINE_BYTES) & (size - 1);
-}
-
 unsigned int intel_ring_update_space(struct intel_ring *ring)
 {
 	unsigned int space;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 34d0a148e664..710ffb221775 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -403,16 +403,17 @@ struct intel_engine_cs {
 		/**
 		 * @enable_count: Reference count for the enabled samplers.
 		 *
-		 * Index number corresponds to the bit number from @enable.
+		 * Index number corresponds to @enum drm_i915_pmu_engine_sample.
 		 */
-		unsigned int enable_count[I915_PMU_SAMPLE_BITS];
+		unsigned int enable_count[I915_ENGINE_SAMPLE_COUNT];
 		/**
 		 * @sample: Counter values for sampling events.
 		 *
 		 * Our internal timer stores the current counters in this field.
+		 *
+		 * Index number corresponds to @enum drm_i915_pmu_engine_sample.
 		 */
-#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1)
-		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
+		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_COUNT];
 	} pmu;
 
 	/*
@@ -592,7 +593,20 @@ intel_engine_has_preemption(const struct intel_engine_cs *engine)
 
 static inline bool __execlists_need_preempt(int prio, int last)
 {
-	return prio > max(0, last);
+	/*
+	 * Allow preemption of low -> normal -> high, but we do
+	 * not allow low priority tasks to preempt other low priority
+	 * tasks under the impression that latency for low priority
+	 * tasks does not matter (as much as background throughput),
+	 * so kiss.
+	 *
+	 * More naturally we would write
+	 *	prio >= max(0, last);
+	 * except that we wish to prevent triggering preemption at the same
+	 * priority level: the task that is running should remain running
+	 * to preserve FIFO ordering of dependencies.
+	 */
+	return prio > max(I915_PRIORITY_NORMAL - 1, last);
 }
 
 static inline void
@@ -818,6 +832,18 @@ intel_ring_set_tail(struct intel_ring *ring, unsigned int tail)
 	return tail;
 }
 
+static inline unsigned int
+__intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
+{
+	/*
+	 * "If the Ring Buffer Head Pointer and the Tail Pointer are on the
+	 * same cacheline, the Head Pointer must not be greater than the Tail
+	 * Pointer."
+	 */
+	GEM_BUG_ON(!is_power_of_2(size));
+	return (head - tail - CACHELINE_BYTES) & (size - 1);
+}
+
 void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno);
 
 int intel_engine_setup_common(struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index cd42e81f8a90..b56a1a9ad01d 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -484,9 +484,16 @@ skl_program_plane(struct intel_plane *plane,
 	struct intel_plane *linked = plane_state->linked_plane;
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	u8 alpha = plane_state->base.alpha >> 8;
+	u32 plane_color_ctl = 0;
 	unsigned long irqflags;
 	u32 keymsk, keymax;
 
+	plane_ctl |= skl_plane_ctl_crtc(crtc_state);
+
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		plane_color_ctl = plane_state->color_ctl |
+			glk_plane_color_ctl_crtc(crtc_state);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
@@ -533,8 +540,7 @@ skl_program_plane(struct intel_plane *plane,
 	}
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
-		I915_WRITE_FW(PLANE_COLOR_CTL(pipe, plane_id),
-			      plane_state->color_ctl);
+		I915_WRITE_FW(PLANE_COLOR_CTL(pipe, plane_id), plane_color_ctl);
 
 	if (fb->format->is_yuv && icl_is_hdr_plane(plane))
 		icl_program_input_csc(plane, crtc_state, plane_state);
@@ -733,6 +739,11 @@ vlv_update_clrc(const struct intel_plane_state *plane_state)
 		      SP_SH_SIN(sh_sin) | SP_SH_COS(sh_cos));
 }
 
+static u32 vlv_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	return SP_GAMMA_ENABLE;
+}
+
 static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
@@ -741,7 +752,7 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 sprctl;
 
-	sprctl = SP_ENABLE | SP_GAMMA_ENABLE;
+	sprctl = SP_ENABLE;
 
 	switch (fb->format->format) {
 	case DRM_FORMAT_YUYV:
@@ -808,7 +819,6 @@ vlv_update_plane(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
-	u32 sprctl = plane_state->ctl;
 	u32 sprsurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
@@ -819,6 +829,9 @@ vlv_update_plane(struct intel_plane *plane,
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
 	unsigned long irqflags;
+	u32 sprctl;
+
+	sprctl = plane_state->ctl | vlv_sprite_ctl_crtc(crtc_state);
 
 	/* Sizes are 0 based */
 	crtc_w--;
@@ -901,6 +914,19 @@ vlv_plane_get_hw_state(struct intel_plane *plane,
 	return ret;
 }
 
+static u32 ivb_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	u32 sprctl = 0;
+
+	sprctl |= SPRITE_GAMMA_ENABLE;
+
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		sprctl |= SPRITE_PIPE_CSC_ENABLE;
+
+	return sprctl;
+}
+
 static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
@@ -911,14 +937,11 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 sprctl;
 
-	sprctl = SPRITE_ENABLE | SPRITE_GAMMA_ENABLE;
+	sprctl = SPRITE_ENABLE;
 
 	if (IS_IVYBRIDGE(dev_priv))
 		sprctl |= SPRITE_TRICKLE_FEED_DISABLE;
 
-	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-		sprctl |= SPRITE_PIPE_CSC_ENABLE;
-
 	switch (fb->format->format) {
 	case DRM_FORMAT_XBGR8888:
 		sprctl |= SPRITE_FORMAT_RGBX888 | SPRITE_RGB_ORDER_RGBX;
@@ -970,7 +993,6 @@ ivb_update_plane(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
-	u32 sprctl = plane_state->ctl, sprscale = 0;
 	u32 sprsurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
@@ -982,8 +1004,11 @@ ivb_update_plane(struct intel_plane *plane,
 	u32 y = plane_state->color_plane[0].y;
 	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	u32 sprctl, sprscale = 0;
 	unsigned long irqflags;
 
+	sprctl = plane_state->ctl | ivb_sprite_ctl_crtc(crtc_state);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
@@ -1080,6 +1105,11 @@ g4x_sprite_max_stride(struct intel_plane *plane,
 	return 16384;
 }
 
+static u32 g4x_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
+{
+	return DVS_GAMMA_ENABLE;
+}
+
 static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
@@ -1090,7 +1120,7 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 dvscntr;
 
-	dvscntr = DVS_ENABLE | DVS_GAMMA_ENABLE;
+	dvscntr = DVS_ENABLE;
 
 	if (IS_GEN(dev_priv, 6))
 		dvscntr |= DVS_TRICKLE_FEED_DISABLE;
@@ -1146,7 +1176,6 @@ g4x_update_plane(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
-	u32 dvscntr = plane_state->ctl, dvsscale = 0;
 	u32 dvssurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
@@ -1158,8 +1187,11 @@ g4x_update_plane(struct intel_plane *plane,
 	u32 y = plane_state->color_plane[0].y;
 	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	u32 dvscntr, dvsscale = 0;
 	unsigned long irqflags;
 
+	dvscntr = plane_state->ctl | g4x_sprite_ctl_crtc(crtc_state);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index e88f0252d77e..75646a1e0051 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1819,6 +1819,9 @@ int __intel_wait_for_register(struct drm_i915_private *dev_priv,
 				 (reg_value & mask) == value,
 				 slow_timeout_ms * 1000, 10, 1000);
 
+	/* just trace the final value */
+	trace_i915_reg_rw(false, reg, reg_value, sizeof(reg_value), true);
+
 	if (out_value)
 		*out_value = reg_value;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
new file mode 100644
index 000000000000..337b1f98b923
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -0,0 +1,157 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include "../i915_selftest.h"
+
+#include "igt_flush_test.h"
+#include "lib_sw_fence.h"
+
+struct live_active {
+	struct i915_active base;
+	bool retired;
+};
+
+static void __live_active_retire(struct i915_active *base)
+{
+	struct live_active *active = container_of(base, typeof(*active), base);
+
+	active->retired = true;
+}
+
+static int __live_active_setup(struct drm_i915_private *i915,
+			       struct live_active *active)
+{
+	struct intel_engine_cs *engine;
+	struct i915_sw_fence *submit;
+	enum intel_engine_id id;
+	unsigned int count = 0;
+	int err = 0;
+
+	submit = heap_fence_create(GFP_KERNEL);
+	if (!submit)
+		return -ENOMEM;
+
+	i915_active_init(i915, &active->base, __live_active_retire);
+	active->retired = false;
+
+	if (!i915_active_acquire(&active->base)) {
+		pr_err("First i915_active_acquire should report being idle\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		rq = i915_request_alloc(engine, i915->kernel_context);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		err = i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+						       submit,
+						       GFP_KERNEL);
+		if (err >= 0)
+			err = i915_active_ref(&active->base,
+					      rq->fence.context, rq);
+		i915_request_add(rq);
+		if (err) {
+			pr_err("Failed to track active ref!\n");
+			break;
+		}
+
+		count++;
+	}
+
+	i915_active_release(&active->base);
+	if (active->retired && count) {
+		pr_err("i915_active retired before submission!\n");
+		err = -EINVAL;
+	}
+	if (active->base.count != count) {
+		pr_err("i915_active not tracking all requests, found %d, expected %d\n",
+		       active->base.count, count);
+		err = -EINVAL;
+	}
+
+out:
+	i915_sw_fence_commit(submit);
+	heap_fence_put(submit);
+
+	return err;
+}
+
+static int live_active_wait(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct live_active active;
+	intel_wakeref_t wakeref;
+	int err;
+
+	/* Check that we get a callback when requests retire upon waiting */
+
+	mutex_lock(&i915->drm.struct_mutex);
+	wakeref = intel_runtime_pm_get(i915);
+
+	err = __live_active_setup(i915, &active);
+
+	i915_active_wait(&active.base);
+	if (!active.retired) {
+		pr_err("i915_active not retired after waiting!\n");
+		err = -EINVAL;
+	}
+
+	i915_active_fini(&active.base);
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+
+	intel_runtime_pm_put(i915, wakeref);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
+static int live_active_retire(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct live_active active;
+	intel_wakeref_t wakeref;
+	int err;
+
+	/* Check that we get a callback when requests are indirectly retired */
+
+	mutex_lock(&i915->drm.struct_mutex);
+	wakeref = intel_runtime_pm_get(i915);
+
+	err = __live_active_setup(i915, &active);
+
+	/* waits for & retires all requests */
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+
+	if (!active.retired) {
+		pr_err("i915_active not retired after flushing!\n");
+		err = -EINVAL;
+	}
+
+	i915_active_fini(&active.base);
+	intel_runtime_pm_put(i915, wakeref);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
+int i915_active_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_active_wait),
+		SUBTEST(live_active_retire),
+	};
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
+	return i915_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index e2c1f0bc2abe..d00d0bb07784 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -24,10 +24,13 @@
 
 #include <linux/prime_numbers.h>
 
+#include "../i915_reset.h"
 #include "../i915_selftest.h"
 #include "i915_random.h"
 #include "igt_flush_test.h"
 #include "igt_live_test.h"
+#include "igt_reset.h"
+#include "igt_spinner.h"
 
 #include "mock_drm.h"
 #include "mock_gem_device.h"
@@ -576,6 +579,469 @@ out_unlock:
 	return err;
 }
 
+static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
+{
+	struct drm_i915_gem_object *obj;
+	u32 *cmd;
+	int err;
+
+	if (INTEL_GEN(vma->vm->i915) < 8)
+		return ERR_PTR(-EINVAL);
+
+	obj = i915_gem_object_create_internal(vma->vm->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(cmd)) {
+		err = PTR_ERR(cmd);
+		goto err;
+	}
+
+	*cmd++ = MI_STORE_REGISTER_MEM_GEN8;
+	*cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
+	*cmd++ = lower_32_bits(vma->node.start);
+	*cmd++ = upper_32_bits(vma->node.start);
+	*cmd = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_unpin_map(obj);
+
+	err = i915_gem_object_set_to_gtt_domain(obj, false);
+	if (err)
+		goto err;
+
+	vma = i915_vma_instance(obj, vma->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err;
+
+	return vma;
+
+err:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static int
+emit_rpcs_query(struct drm_i915_gem_object *obj,
+		struct i915_gem_context *ctx,
+		struct intel_engine_cs *engine,
+		struct i915_request **rq_out)
+{
+	struct i915_request *rq;
+	struct i915_vma *batch;
+	struct i915_vma *vma;
+	int err;
+
+	GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+
+	vma = i915_vma_instance(obj, &ctx->ppgtt->vm, NULL);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	err = i915_gem_object_set_to_gtt_domain(obj, false);
+	if (err)
+		return err;
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		return err;
+
+	batch = rpcs_query_batch(vma);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto err_vma;
+	}
+
+	rq = i915_request_alloc(engine, ctx);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_batch;
+	}
+
+	err = engine->emit_bb_start(rq, batch->node.start, batch->node.size, 0);
+	if (err)
+		goto err_request;
+
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
+
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
+
+	i915_gem_object_set_active_reference(batch->obj);
+	i915_vma_unpin(batch);
+	i915_vma_close(batch);
+
+	i915_vma_unpin(vma);
+
+	*rq_out = i915_request_get(rq);
+
+	i915_request_add(rq);
+
+	return 0;
+
+skip_request:
+	i915_request_skip(rq, err);
+err_request:
+	i915_request_add(rq);
+err_batch:
+	i915_vma_unpin(batch);
+err_vma:
+	i915_vma_unpin(vma);
+
+	return err;
+}
+
+#define TEST_IDLE	BIT(0)
+#define TEST_BUSY	BIT(1)
+#define TEST_RESET	BIT(2)
+
+static int
+__sseu_prepare(struct drm_i915_private *i915,
+	       const char *name,
+	       unsigned int flags,
+	       struct i915_gem_context *ctx,
+	       struct intel_engine_cs *engine,
+	       struct igt_spinner **spin_out)
+{
+	int ret = 0;
+
+	if (flags & (TEST_BUSY | TEST_RESET)) {
+		struct igt_spinner *spin;
+		struct i915_request *rq;
+
+		spin = kzalloc(sizeof(*spin), GFP_KERNEL);
+		if (!spin) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ret = igt_spinner_init(spin, i915);
+		if (ret)
+			return ret;
+
+		rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
+		if (IS_ERR(rq)) {
+			ret = PTR_ERR(rq);
+			igt_spinner_fini(spin);
+			kfree(spin);
+			goto out;
+		}
+
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(spin, rq)) {
+			pr_err("%s: Spinner failed to start!\n", name);
+			igt_spinner_end(spin);
+			igt_spinner_fini(spin);
+			kfree(spin);
+			ret = -ETIMEDOUT;
+			goto out;
+		}
+
+		*spin_out = spin;
+	}
+
+out:
+	return ret;
+}
+
+static int
+__read_slice_count(struct drm_i915_private *i915,
+		   struct i915_gem_context *ctx,
+		   struct intel_engine_cs *engine,
+		   struct drm_i915_gem_object *obj,
+		   struct igt_spinner *spin,
+		   u32 *rpcs)
+{
+	struct i915_request *rq = NULL;
+	u32 s_mask, s_shift;
+	unsigned int cnt;
+	u32 *buf, val;
+	long ret;
+
+	ret = emit_rpcs_query(obj, ctx, engine, &rq);
+	if (ret)
+		return ret;
+
+	if (spin)
+		igt_spinner_end(spin);
+
+	ret = i915_request_wait(rq, I915_WAIT_LOCKED, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+	if (ret < 0)
+		return ret;
+
+	buf = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		return ret;
+	}
+
+	if (INTEL_GEN(i915) >= 11) {
+		s_mask = GEN11_RPCS_S_CNT_MASK;
+		s_shift = GEN11_RPCS_S_CNT_SHIFT;
+	} else {
+		s_mask = GEN8_RPCS_S_CNT_MASK;
+		s_shift = GEN8_RPCS_S_CNT_SHIFT;
+	}
+
+	val = *buf;
+	cnt = (val & s_mask) >> s_shift;
+	*rpcs = val;
+
+	i915_gem_object_unpin_map(obj);
+
+	return cnt;
+}
+
+static int
+__check_rpcs(const char *name, u32 rpcs, int slices, unsigned int expected,
+	     const char *prefix, const char *suffix)
+{
+	if (slices == expected)
+		return 0;
+
+	if (slices < 0) {
+		pr_err("%s: %s read slice count failed with %d%s\n",
+		       name, prefix, slices, suffix);
+		return slices;
+	}
+
+	pr_err("%s: %s slice count %d is not %u%s\n",
+	       name, prefix, slices, expected, suffix);
+
+	pr_info("RPCS=0x%x; %u%sx%u%s\n",
+		rpcs, slices,
+		(rpcs & GEN8_RPCS_S_CNT_ENABLE) ? "*" : "",
+		(rpcs & GEN8_RPCS_SS_CNT_MASK) >> GEN8_RPCS_SS_CNT_SHIFT,
+		(rpcs & GEN8_RPCS_SS_CNT_ENABLE) ? "*" : "");
+
+	return -EINVAL;
+}
+
+static int
+__sseu_finish(struct drm_i915_private *i915,
+	      const char *name,
+	      unsigned int flags,
+	      struct i915_gem_context *ctx,
+	      struct i915_gem_context *kctx,
+	      struct intel_engine_cs *engine,
+	      struct drm_i915_gem_object *obj,
+	      unsigned int expected,
+	      struct igt_spinner *spin)
+{
+	unsigned int slices =
+		hweight32(intel_device_default_sseu(i915).slice_mask);
+	u32 rpcs = 0;
+	int ret = 0;
+
+	if (flags & TEST_RESET) {
+		ret = i915_reset_engine(engine, "sseu");
+		if (ret)
+			goto out;
+	}
+
+	ret = __read_slice_count(i915, ctx, engine, obj,
+				 flags & TEST_RESET ? NULL : spin, &rpcs);
+	ret = __check_rpcs(name, rpcs, ret, expected, "Context", "!");
+	if (ret)
+		goto out;
+
+	ret = __read_slice_count(i915, kctx, engine, obj, NULL, &rpcs);
+	ret = __check_rpcs(name, rpcs, ret, slices, "Kernel context", "!");
+
+out:
+	if (spin)
+		igt_spinner_end(spin);
+
+	if ((flags & TEST_IDLE) && ret == 0) {
+		ret = i915_gem_wait_for_idle(i915,
+					     I915_WAIT_LOCKED,
+					     MAX_SCHEDULE_TIMEOUT);
+		if (ret)
+			return ret;
+
+		ret = __read_slice_count(i915, ctx, engine, obj, NULL, &rpcs);
+		ret = __check_rpcs(name, rpcs, ret, expected,
+				   "Context", " after idle!");
+	}
+
+	return ret;
+}
+
+static int
+__sseu_test(struct drm_i915_private *i915,
+	    const char *name,
+	    unsigned int flags,
+	    struct i915_gem_context *ctx,
+	    struct intel_engine_cs *engine,
+	    struct drm_i915_gem_object *obj,
+	    struct intel_sseu sseu)
+{
+	struct igt_spinner *spin = NULL;
+	struct i915_gem_context *kctx;
+	int ret;
+
+	kctx = kernel_context(i915);
+	if (IS_ERR(kctx))
+		return PTR_ERR(kctx);
+
+	ret = __sseu_prepare(i915, name, flags, ctx, engine, &spin);
+	if (ret)
+		goto out;
+
+	ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+	if (ret)
+		goto out;
+
+	ret = __sseu_finish(i915, name, flags, ctx, kctx, engine, obj,
+			    hweight32(sseu.slice_mask), spin);
+
+out:
+	if (spin) {
+		igt_spinner_end(spin);
+		igt_spinner_fini(spin);
+		kfree(spin);
+	}
+
+	kernel_context_close(kctx);
+
+	return ret;
+}
+
+static int
+__igt_ctx_sseu(struct drm_i915_private *i915,
+	       const char *name,
+	       unsigned int flags)
+{
+	struct intel_sseu default_sseu = intel_device_default_sseu(i915);
+	struct intel_engine_cs *engine = i915->engine[RCS];
+	struct drm_i915_gem_object *obj;
+	struct i915_gem_context *ctx;
+	struct intel_sseu pg_sseu;
+	intel_wakeref_t wakeref;
+	struct drm_file *file;
+	int ret;
+
+	if (INTEL_GEN(i915) < 9)
+		return 0;
+
+	if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
+		return 0;
+
+	if (hweight32(default_sseu.slice_mask) < 2)
+		return 0;
+
+	/*
+	 * Gen11 VME friendly power-gated configuration with half enabled
+	 * sub-slices.
+	 */
+	pg_sseu = default_sseu;
+	pg_sseu.slice_mask = 1;
+	pg_sseu.subslice_mask =
+		~(~0 << (hweight32(default_sseu.subslice_mask) / 2));
+
+	pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
+		name, flags, hweight32(default_sseu.slice_mask),
+		hweight32(pg_sseu.slice_mask));
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	if (flags & TEST_RESET)
+		igt_global_reset_lock(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	ctx = i915_gem_create_context(i915, file->driver_priv);
+	if (IS_ERR(ctx)) {
+		ret = PTR_ERR(ctx);
+		goto out_unlock;
+	}
+
+	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		ret = PTR_ERR(obj);
+		goto out_unlock;
+	}
+
+	wakeref = intel_runtime_pm_get(i915);
+
+	/* First set the default mask. */
+	ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+	if (ret)
+		goto out_fail;
+
+	/* Then set a power-gated configuration. */
+	ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+	if (ret)
+		goto out_fail;
+
+	/* Back to defaults. */
+	ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+	if (ret)
+		goto out_fail;
+
+	/* One last power-gated configuration for the road. */
+	ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+	if (ret)
+		goto out_fail;
+
+out_fail:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		ret = -EIO;
+
+	i915_gem_object_put(obj);
+
+	intel_runtime_pm_put(i915, wakeref);
+
+out_unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	if (flags & TEST_RESET)
+		igt_global_reset_unlock(i915);
+
+	mock_file_free(i915, file);
+
+	if (ret)
+		pr_err("%s: Failed with %d!\n", name, ret);
+
+	return ret;
+}
+
+static int igt_ctx_sseu(void *arg)
+{
+	struct {
+		const char *name;
+		unsigned int flags;
+	} *phase, phases[] = {
+		{ .name = "basic", .flags = 0 },
+		{ .name = "idle", .flags = TEST_IDLE },
+		{ .name = "busy", .flags = TEST_BUSY },
+		{ .name = "busy-reset", .flags = TEST_BUSY | TEST_RESET },
+		{ .name = "busy-idle", .flags = TEST_BUSY | TEST_IDLE },
+		{ .name = "reset-idle", .flags = TEST_RESET | TEST_IDLE },
+	};
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0, phase = phases; ret == 0 && i < ARRAY_SIZE(phases);
+	     i++, phase++)
+		ret = __igt_ctx_sseu(arg, phase->name, phase->flags);
+
+	return ret;
+}
+
 static int igt_ctx_readonly(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -1162,6 +1628,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 		SUBTEST(live_nop_switch),
 		SUBTEST(igt_ctx_exec),
 		SUBTEST(igt_ctx_readonly),
+		SUBTEST(igt_ctx_sseu),
 		SUBTEST(igt_vm_isolation),
 	};
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 76b4f87fc853..6d766925ad04 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -12,8 +12,9 @@
 selftest(sanitycheck, i915_live_sanitycheck) /* keep first (igt selfcheck) */
 selftest(uncore, intel_uncore_live_selftests)
 selftest(workarounds, intel_workarounds_live_selftests)
-selftest(requests, i915_request_live_selftests)
 selftest(timelines, i915_timeline_live_selftests)
+selftest(requests, i915_request_live_selftests)
+selftest(active, i915_active_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
 selftest(dmabuf, i915_gem_dmabuf_live_selftests)
 selftest(coherency, i915_gem_coherency_live_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index fb35f53c9ce3..58144e024751 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -4,6 +4,8 @@
  * Copyright © 2018 Intel Corporation
  */
 
+#include <linux/prime_numbers.h>
+
 #include "../i915_reset.h"
 
 #include "../i915_selftest.h"
@@ -405,6 +407,106 @@ err_wedged:
 	goto err_client_b;
 }
 
+static int live_chain_preempt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine;
+	struct preempt_client hi, lo;
+	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
+	int err = -ENOMEM;
+
+	/*
+	 * Build a chain AB...BA between two contexts (A, B) and request
+	 * preemption of the last request. It should then complete before
+	 * the previously submitted spinner in B.
+	 */
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+	wakeref = intel_runtime_pm_get(i915);
+
+	if (preempt_client_init(i915, &hi))
+		goto err_unlock;
+
+	if (preempt_client_init(i915, &lo))
+		goto err_client_hi;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_sched_attr attr = {
+			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
+		};
+		int count, i;
+
+		for_each_prime_number_from(count, 1, 32) { /* must fit ring! */
+			struct i915_request *rq;
+
+			rq = igt_spinner_create_request(&hi.spin,
+							hi.ctx, engine,
+							MI_ARB_CHECK);
+			if (IS_ERR(rq))
+				goto err_wedged;
+			i915_request_add(rq);
+			if (!igt_wait_for_spinner(&hi.spin, rq))
+				goto err_wedged;
+
+			rq = igt_spinner_create_request(&lo.spin,
+							lo.ctx, engine,
+							MI_ARB_CHECK);
+			if (IS_ERR(rq))
+				goto err_wedged;
+			i915_request_add(rq);
+
+			for (i = 0; i < count; i++) {
+				rq = i915_request_alloc(engine, lo.ctx);
+				if (IS_ERR(rq))
+					goto err_wedged;
+				i915_request_add(rq);
+			}
+
+			rq = i915_request_alloc(engine, hi.ctx);
+			if (IS_ERR(rq))
+				goto err_wedged;
+			i915_request_add(rq);
+			engine->schedule(rq, &attr);
+
+			igt_spinner_end(&hi.spin);
+			if (i915_request_wait(rq, I915_WAIT_LOCKED, HZ / 5) < 0) {
+				struct drm_printer p =
+					drm_info_printer(i915->drm.dev);
+
+				pr_err("Failed to preempt over chain of %d\n",
+				       count);
+				intel_engine_dump(engine, &p,
+						  "%s\n", engine->name);
+				goto err_wedged;
+			}
+			igt_spinner_end(&lo.spin);
+		}
+	}
+
+	err = 0;
+err_client_lo:
+	preempt_client_fini(&lo);
+err_client_hi:
+	preempt_client_fini(&hi);
+err_unlock:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	intel_runtime_pm_put(i915, wakeref);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+
+err_wedged:
+	igt_spinner_end(&hi.spin);
+	igt_spinner_end(&lo.spin);
+	i915_gem_set_wedged(i915);
+	err = -EIO;
+	goto err_client_lo;
+}
+
 static int live_preempt_hang(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -785,6 +887,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
 		SUBTEST(live_suppress_self_preempt),
+		SUBTEST(live_chain_preempt),
 		SUBTEST(live_preempt_hang),
 		SUBTEST(live_preempt_smoke),
 	};
diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c
index cf39ccd9fc05..d2de9ece2118 100644
--- a/drivers/gpu/drm/i915/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c
@@ -15,7 +15,8 @@ void mock_timeline_init(struct i915_timeline *timeline, u64 context)
 
 	spin_lock_init(&timeline->lock);
 
-	init_request_active(&timeline->last_request, NULL);
+	INIT_ACTIVE_REQUEST(&timeline->barrier);
+	INIT_ACTIVE_REQUEST(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index 696b750acd1d..6403728fe778 100644
--- a/drivers/gpu/drm/i915/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -275,7 +275,7 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 	if (fixed_mode) {
 		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
 
-		if (HAS_GMCH_DISPLAY(dev_priv))
+		if (HAS_GMCH(dev_priv))
 			intel_gmch_panel_fitting(crtc, pipe_config,
 						 conn_state->scaling_mode);
 		else
@@ -1633,7 +1633,7 @@ static void intel_dsi_add_properties(struct intel_connector *connector)
 		u32 allowed_scalers;
 
 		allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN);
-		if (!HAS_GMCH_DISPLAY(dev_priv))
+		if (!HAS_GMCH(dev_priv))
 			allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
 
 		drm_connector_attach_scaling_mode_property(&connector->base,
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 298b2e197744..397810fa2d33 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
 #define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
 #define   I915_CONTEXT_DEFAULT_PRIORITY		0
 #define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
+	/*
+	 * When using the following param, value should be a pointer to
+	 * drm_i915_gem_context_param_sseu.
+	 */
+#define I915_CONTEXT_PARAM_SSEU		0x7
 	__u64 value;
 };
 
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+	/*
+	 * Engine class & instance to be configured or queried.
+	 */
+	__u16 engine_class;
+	__u16 engine_instance;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Mask of slices to enable for the context. Valid values are a subset
+	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+	 */
+	__u64 slice_mask;
+
+	/*
+	 * Mask of subslices to enable for the context. Valid values are a
+	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+	 */
+	__u64 subslice_mask;
+
+	/*
+	 * Minimum/Maximum number of EUs to enable per subslice for the
+	 * context. min_eus_per_subslice must be inferior or equal to
+	 * max_eus_per_subslice.
+	 */
+	__u16 min_eus_per_subslice;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 rsvd;
+};
+
 enum drm_i915_oa_format {
 	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
 	I915_OA_FORMAT_A29,	    /* HSW only */