From 8a943c6021ba8b95a36c842327e468df1fddd4a7 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 14 May 2019 22:43:36 +0200
Subject: drm/sun4i: Fix sun8i HDMI PHY clock initialization

Current code initializes HDMI PHY clock driver before reset line is
deasserted and clocks enabled. Because of that, initial readout of
clock divider is incorrect (0 instead of 2). This causes any clock
rate with divider 1 (register value 0) to be set incorrectly.

Fix this by moving initialization of HDMI PHY clock driver after reset
line is deasserted and clocks enabled.

Cc: stable@vger.kernel.org # 4.17+
Fixes: 4f86e81748fe ("drm/sun4i: Add support for H3 HDMI PHY variant")
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190514204337.11068-2-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index 66ea3a902e36..afc6d4a9c20b 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -672,22 +672,13 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 				goto err_put_clk_pll0;
 			}
 		}
-
-		ret = sun8i_phy_clk_create(phy, dev,
-					   phy->variant->has_second_pll);
-		if (ret) {
-			dev_err(dev, "Couldn't create the PHY clock\n");
-			goto err_put_clk_pll1;
-		}
-
-		clk_prepare_enable(phy->clk_phy);
 	}
 
 	phy->rst_phy = of_reset_control_get_shared(node, "phy");
 	if (IS_ERR(phy->rst_phy)) {
 		dev_err(dev, "Could not get phy reset control\n");
 		ret = PTR_ERR(phy->rst_phy);
-		goto err_disable_clk_phy;
+		goto err_put_clk_pll1;
 	}
 
 	ret = reset_control_deassert(phy->rst_phy);
@@ -708,18 +699,29 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 		goto err_disable_clk_bus;
 	}
 
+	if (phy->variant->has_phy_clk) {
+		ret = sun8i_phy_clk_create(phy, dev,
+					   phy->variant->has_second_pll);
+		if (ret) {
+			dev_err(dev, "Couldn't create the PHY clock\n");
+			goto err_disable_clk_mod;
+		}
+
+		clk_prepare_enable(phy->clk_phy);
+	}
+
 	hdmi->phy = phy;
 
 	return 0;
 
+err_disable_clk_mod:
+	clk_disable_unprepare(phy->clk_mod);
 err_disable_clk_bus:
 	clk_disable_unprepare(phy->clk_bus);
 err_deassert_rst_phy:
 	reset_control_assert(phy->rst_phy);
 err_put_rst_phy:
 	reset_control_put(phy->rst_phy);
-err_disable_clk_phy:
-	clk_disable_unprepare(phy->clk_phy);
 err_put_clk_pll1:
 	clk_put(phy->clk_pll1);
 err_put_clk_pll0:
-- 
cgit v1.2.3-58-ga151


From 831adffb3b7b8df4c8e20b7b00843129fb87a166 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 14 May 2019 22:43:37 +0200
Subject: drm/sun4i: Fix sun8i HDMI PHY configuration for > 148.5 MHz

Vendor provided documentation says that EMP bits should be set to 3 for
pixel clocks greater than 148.5 MHz.

Fix that.

Cc: stable@vger.kernel.org # 4.17+
Fixes: 4f86e81748fe ("drm/sun4i: Add support for H3 HDMI PHY variant")
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190514204337.11068-3-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index afc6d4a9c20b..43643ad31730 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -293,7 +293,8 @@ static int sun8i_hdmi_phy_config_h3(struct dw_hdmi *hdmi,
 				 SUN8I_HDMI_PHY_ANA_CFG2_REG_BIGSW |
 				 SUN8I_HDMI_PHY_ANA_CFG2_REG_SLV(4);
 		ana_cfg3_init |= SUN8I_HDMI_PHY_ANA_CFG3_REG_AMPCK(9) |
-				 SUN8I_HDMI_PHY_ANA_CFG3_REG_AMP(13);
+				 SUN8I_HDMI_PHY_ANA_CFG3_REG_AMP(13) |
+				 SUN8I_HDMI_PHY_ANA_CFG3_REG_EMP(3);
 	}
 
 	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_ANA_CFG1_REG,
-- 
cgit v1.2.3-58-ga151


From 51a0d1a90bff5d90a1a1c58e165928a0dd92268a Mon Sep 17 00:00:00 2001
From: Jagan Teki <jagan@amarulasolutions.com>
Date: Mon, 13 May 2019 00:11:26 +0530
Subject: drm/sun4i: sun6i_mipi_dsi: Fix hsync_porch overflow

Loop N1 instruction delay for burst mode devices are computed
based on horizontal sync and porch timing values.

The current driver is using u16 type for computing this hsync_porch
value, which would failed to fit within the u16 type for large sync
and porch timings devices. This would result in hsync_porch overflow
and eventually computed wrong instruction delay value.

Example, timings, where it produces the overflow
{
	.hdisplay       = 1080,
	.hsync_start    = 1080 + 408,
        .hsync_end      = 1080 + 408 + 4,
        .htotal         = 1080 + 408 + 4 + 38,
}

It reproduces the desired delay value 65487 but the correct working
value should be 7.

So, Fix it by computing hsync_porch value separately with u32 type.

Fixes: 1c1a7aa3663c ("drm/sun4i: dsi: Add burst support")
Signed-off-by: Jagan Teki <jagan@amarulasolutions.com>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190512184128.13720-2-jagan@amarulasolutions.com
---
 drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 6ff585055a07..bfa7e2b146df 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -457,8 +457,9 @@ static void sun6i_dsi_setup_inst_loop(struct sun6i_dsi *dsi,
 	u16 delay = 50 - 1;
 
 	if (device->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
-		delay = (mode->htotal - mode->hdisplay) * 150;
-		delay /= (mode->clock / 1000) * 8;
+		u32 hsync_porch = (mode->htotal - mode->hdisplay) * 150;
+
+		delay = (hsync_porch / ((mode->clock / 1000) * 8));
 		delay -= 50;
 	}
 
-- 
cgit v1.2.3-58-ga151


From 06b2b1a40e3a9a1ea80b4c51885d863ca194ef3f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 13 May 2019 13:01:00 +0100
Subject: drm/i915: Rearrange i915_scheduler.c

To avoid pulling in a forward declaration in the next patch, move the
i915_sched_node handling to after the main dfs of the scheduler.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190513120102.29660-1-chris@chris-wilson.co.uk
(cherry picked from commit 5ae87063c162679a61f2141041d0918cc3045daf)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_scheduler.c | 210 +++++++++++++++++-----------------
 1 file changed, 105 insertions(+), 105 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 39bc4f54e272..5756fcfe343d 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -35,109 +35,6 @@ static inline bool node_signaled(const struct i915_sched_node *node)
 	return i915_request_completed(node_to_request(node));
 }
 
-void i915_sched_node_init(struct i915_sched_node *node)
-{
-	INIT_LIST_HEAD(&node->signalers_list);
-	INIT_LIST_HEAD(&node->waiters_list);
-	INIT_LIST_HEAD(&node->link);
-	node->attr.priority = I915_PRIORITY_INVALID;
-	node->semaphores = 0;
-	node->flags = 0;
-}
-
-static struct i915_dependency *
-i915_dependency_alloc(void)
-{
-	return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
-}
-
-static void
-i915_dependency_free(struct i915_dependency *dep)
-{
-	kmem_cache_free(global.slab_dependencies, dep);
-}
-
-bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
-				      struct i915_sched_node *signal,
-				      struct i915_dependency *dep,
-				      unsigned long flags)
-{
-	bool ret = false;
-
-	spin_lock_irq(&schedule_lock);
-
-	if (!node_signaled(signal)) {
-		INIT_LIST_HEAD(&dep->dfs_link);
-		list_add(&dep->wait_link, &signal->waiters_list);
-		list_add(&dep->signal_link, &node->signalers_list);
-		dep->signaler = signal;
-		dep->flags = flags;
-
-		/* Keep track of whether anyone on this chain has a semaphore */
-		if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN &&
-		    !node_started(signal))
-			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
-
-		ret = true;
-	}
-
-	spin_unlock_irq(&schedule_lock);
-
-	return ret;
-}
-
-int i915_sched_node_add_dependency(struct i915_sched_node *node,
-				   struct i915_sched_node *signal)
-{
-	struct i915_dependency *dep;
-
-	dep = i915_dependency_alloc();
-	if (!dep)
-		return -ENOMEM;
-
-	if (!__i915_sched_node_add_dependency(node, signal, dep,
-					      I915_DEPENDENCY_ALLOC))
-		i915_dependency_free(dep);
-
-	return 0;
-}
-
-void i915_sched_node_fini(struct i915_sched_node *node)
-{
-	struct i915_dependency *dep, *tmp;
-
-	GEM_BUG_ON(!list_empty(&node->link));
-
-	spin_lock_irq(&schedule_lock);
-
-	/*
-	 * Everyone we depended upon (the fences we wait to be signaled)
-	 * should retire before us and remove themselves from our list.
-	 * However, retirement is run independently on each timeline and
-	 * so we may be called out-of-order.
-	 */
-	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
-		GEM_BUG_ON(!node_signaled(dep->signaler));
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
-
-		list_del(&dep->wait_link);
-		if (dep->flags & I915_DEPENDENCY_ALLOC)
-			i915_dependency_free(dep);
-	}
-
-	/* Remove ourselves from everyone who depends upon us */
-	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
-		GEM_BUG_ON(dep->signaler != node);
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
-
-		list_del(&dep->signal_link);
-		if (dep->flags & I915_DEPENDENCY_ALLOC)
-			i915_dependency_free(dep);
-	}
-
-	spin_unlock_irq(&schedule_lock);
-}
-
 static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 {
 	return rb_entry(rb, struct i915_priolist, node);
@@ -239,6 +136,11 @@ out:
 	return &p->requests[idx];
 }
 
+void __i915_priolist_free(struct i915_priolist *p)
+{
+	kmem_cache_free(global.slab_priorities, p);
+}
+
 struct sched_cache {
 	struct list_head *priolist;
 };
@@ -436,9 +338,107 @@ void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
 	spin_unlock_irqrestore(&schedule_lock, flags);
 }
 
-void __i915_priolist_free(struct i915_priolist *p)
+void i915_sched_node_init(struct i915_sched_node *node)
 {
-	kmem_cache_free(global.slab_priorities, p);
+	INIT_LIST_HEAD(&node->signalers_list);
+	INIT_LIST_HEAD(&node->waiters_list);
+	INIT_LIST_HEAD(&node->link);
+	node->attr.priority = I915_PRIORITY_INVALID;
+	node->semaphores = 0;
+	node->flags = 0;
+}
+
+static struct i915_dependency *
+i915_dependency_alloc(void)
+{
+	return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
+}
+
+static void
+i915_dependency_free(struct i915_dependency *dep)
+{
+	kmem_cache_free(global.slab_dependencies, dep);
+}
+
+bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
+				      struct i915_sched_node *signal,
+				      struct i915_dependency *dep,
+				      unsigned long flags)
+{
+	bool ret = false;
+
+	spin_lock_irq(&schedule_lock);
+
+	if (!node_signaled(signal)) {
+		INIT_LIST_HEAD(&dep->dfs_link);
+		list_add(&dep->wait_link, &signal->waiters_list);
+		list_add(&dep->signal_link, &node->signalers_list);
+		dep->signaler = signal;
+		dep->flags = flags;
+
+		/* Keep track of whether anyone on this chain has a semaphore */
+		if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN &&
+		    !node_started(signal))
+			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
+
+		ret = true;
+	}
+
+	spin_unlock_irq(&schedule_lock);
+
+	return ret;
+}
+
+int i915_sched_node_add_dependency(struct i915_sched_node *node,
+				   struct i915_sched_node *signal)
+{
+	struct i915_dependency *dep;
+
+	dep = i915_dependency_alloc();
+	if (!dep)
+		return -ENOMEM;
+
+	if (!__i915_sched_node_add_dependency(node, signal, dep,
+					      I915_DEPENDENCY_ALLOC))
+		i915_dependency_free(dep);
+
+	return 0;
+}
+
+void i915_sched_node_fini(struct i915_sched_node *node)
+{
+	struct i915_dependency *dep, *tmp;
+
+	GEM_BUG_ON(!list_empty(&node->link));
+
+	spin_lock_irq(&schedule_lock);
+
+	/*
+	 * Everyone we depended upon (the fences we wait to be signaled)
+	 * should retire before us and remove themselves from our list.
+	 * However, retirement is run independently on each timeline and
+	 * so we may be called out-of-order.
+	 */
+	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
+		GEM_BUG_ON(!node_signaled(dep->signaler));
+		GEM_BUG_ON(!list_empty(&dep->dfs_link));
+
+		list_del(&dep->wait_link);
+		if (dep->flags & I915_DEPENDENCY_ALLOC)
+			i915_dependency_free(dep);
+	}
+
+	/* Remove ourselves from everyone who depends upon us */
+	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
+		GEM_BUG_ON(dep->signaler != node);
+		GEM_BUG_ON(!list_empty(&dep->dfs_link));
+
+		list_del(&dep->signal_link);
+		if (dep->flags & I915_DEPENDENCY_ALLOC)
+			i915_dependency_free(dep);
+	}
+
+	spin_unlock_irq(&schedule_lock);
 }
 
 static void i915_global_scheduler_shrink(void)
-- 
cgit v1.2.3-58-ga151


From f312c23ff92319f5f242b69d93885c53f92030b5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 13 May 2019 13:01:01 +0100
Subject: drm/i915: Pass i915_sched_node around internally

To simplify the next patch, update bump_priority and schedule to accept
the internal i915_sched_ndoe directly and not expect a request pointer.

add/remove: 0/0 grow/shrink: 2/1 up/down: 8/-15 (-7)
Function                                     old     new   delta
i915_schedule_bump_priority                  109     113      +4
i915_schedule                                 50      54      +4
__i915_schedule                              922     907     -15

v2: Adopt node for the old rq local, since it no longer is a request but
the origin node.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190513120102.29660-2-chris@chris-wilson.co.uk
(cherry picked from commit 52c76fb18a34fc08dd06f32b9fc83f1375f083ee)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_scheduler.c | 36 ++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 5756fcfe343d..3cfadb9db988 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -175,7 +175,7 @@ static bool inflight(const struct i915_request *rq,
 	return active->hw_context == rq->hw_context;
 }
 
-static void __i915_schedule(struct i915_request *rq,
+static void __i915_schedule(struct i915_sched_node *node,
 			    const struct i915_sched_attr *attr)
 {
 	struct intel_engine_cs *engine;
@@ -189,13 +189,13 @@ static void __i915_schedule(struct i915_request *rq,
 	lockdep_assert_held(&schedule_lock);
 	GEM_BUG_ON(prio == I915_PRIORITY_INVALID);
 
-	if (i915_request_completed(rq))
+	if (node_signaled(node))
 		return;
 
-	if (prio <= READ_ONCE(rq->sched.attr.priority))
+	if (prio <= READ_ONCE(node->attr.priority))
 		return;
 
-	stack.signaler = &rq->sched;
+	stack.signaler = node;
 	list_add(&stack.dfs_link, &dfs);
 
 	/*
@@ -246,9 +246,9 @@ static void __i915_schedule(struct i915_request *rq,
 	 * execlists_submit_request()), we can set our own priority and skip
 	 * acquiring the engine locks.
 	 */
-	if (rq->sched.attr.priority == I915_PRIORITY_INVALID) {
-		GEM_BUG_ON(!list_empty(&rq->sched.link));
-		rq->sched.attr = *attr;
+	if (node->attr.priority == I915_PRIORITY_INVALID) {
+		GEM_BUG_ON(!list_empty(&node->link));
+		node->attr = *attr;
 
 		if (stack.dfs_link.next == stack.dfs_link.prev)
 			return;
@@ -257,15 +257,14 @@ static void __i915_schedule(struct i915_request *rq,
 	}
 
 	memset(&cache, 0, sizeof(cache));
-	engine = rq->engine;
+	engine = node_to_request(node)->engine;
 	spin_lock(&engine->timeline.lock);
 
 	/* Fifo and depth-first replacement ensure our deps execute before us */
 	list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
-		struct i915_sched_node *node = dep->signaler;
-
 		INIT_LIST_HEAD(&dep->dfs_link);
 
+		node = dep->signaler;
 		engine = sched_lock_engine(node, engine, &cache);
 		lockdep_assert_held(&engine->timeline.lock);
 
@@ -315,13 +314,20 @@ static void __i915_schedule(struct i915_request *rq,
 void i915_schedule(struct i915_request *rq, const struct i915_sched_attr *attr)
 {
 	spin_lock_irq(&schedule_lock);
-	__i915_schedule(rq, attr);
+	__i915_schedule(&rq->sched, attr);
 	spin_unlock_irq(&schedule_lock);
 }
 
+static void __bump_priority(struct i915_sched_node *node, unsigned int bump)
+{
+	struct i915_sched_attr attr = node->attr;
+
+	attr.priority |= bump;
+	__i915_schedule(node, &attr);
+}
+
 void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
 {
-	struct i915_sched_attr attr;
 	unsigned long flags;
 
 	GEM_BUG_ON(bump & ~I915_PRIORITY_MASK);
@@ -330,11 +336,7 @@ void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
 		return;
 
 	spin_lock_irqsave(&schedule_lock, flags);
-
-	attr = rq->sched.attr;
-	attr.priority |= bump;
-	__i915_schedule(rq, &attr);
-
+	__bump_priority(&rq->sched, bump);
 	spin_unlock_irqrestore(&schedule_lock, flags);
 }
 
-- 
cgit v1.2.3-58-ga151


From 9981927cc9e10fb4dbc24b2a5f8c17ab133859a0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 15 May 2019 14:00:50 +0100
Subject: drm/i915: Bump signaler priority on adding a waiter

The handling of the no-preemption priority level imposes the restriction
that we need to maintain the implied ordering even though preemption is
disabled. Otherwise we may end up with an AB-BA deadlock across multiple
engine due to a real preemption event reordering the no-preemption
WAITs. To resolve this issue we currently promote all requests to WAIT
on unsubmission, however this interferes with the timeslicing
requirement that we do not apply any implicit promotion that will defeat
the round-robin timeslice list. (If we automatically promote the active
request it will go back to the head of the queue and not the tail!)

So we need implicit promotion to prevent reordering around semaphores
where we are not allowed to preempt, and we must avoid implicit
promotion on unsubmission. So instead of at unsubmit, if we apply that
implicit promotion on adding the dependency, we avoid the semaphore
deadlock and we also reduce the gains made by the promotion for user
space waiting. Furthermore, by keeping the earlier dependencies at a
higher level, we reduce the search space for timeslicing without
altering runtime scheduling too badly (no dependencies at all will be
assigned a higher priority for rrul).

v2: Limit the bump to external edges (as originally intended) i.e.
between contexts and out to the user.

Testcase: igt/gem_concurrent_blit
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190515130052.4475-3-chris@chris-wilson.co.uk
(cherry picked from commit 6e7eb7a80769e7250e31652b96918cf7f3e0d285)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_request.c         |  9 ---------
 drivers/gpu/drm/i915/i915_scheduler.c       | 11 +++++++++++
 drivers/gpu/drm/i915/i915_scheduler_types.h |  3 ++-
 drivers/gpu/drm/i915/selftests/intel_lrc.c  | 12 ++++++++----
 4 files changed, 21 insertions(+), 14 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f6c78c0fa74b..f258281bf3f3 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -502,15 +502,6 @@ void __i915_request_unsubmit(struct i915_request *request)
 	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	/*
-	 * As we do not allow WAIT to preempt inflight requests,
-	 * once we have executed a request, along with triggering
-	 * any execution callbacks, we must preserve its ordering
-	 * within the non-preemptible FIFO.
-	 */
-	BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK); /* only internal */
-	request->sched.attr.priority |= __NO_PREEMPTION;
-
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
 		i915_request_cancel_breadcrumb(request);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 3cfadb9db988..108f52e1bf35 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -383,6 +383,16 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 		    !node_started(signal))
 			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 
+		/*
+		 * As we do not allow WAIT to preempt inflight requests,
+		 * once we have executed a request, along with triggering
+		 * any execution callbacks, we must preserve its ordering
+		 * within the non-preemptible FIFO.
+		 */
+		BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK);
+		if (flags & I915_DEPENDENCY_EXTERNAL)
+			__bump_priority(signal, __NO_PREEMPTION);
+
 		ret = true;
 	}
 
@@ -401,6 +411,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 		return -ENOMEM;
 
 	if (!__i915_sched_node_add_dependency(node, signal, dep,
+					      I915_DEPENDENCY_EXTERNAL |
 					      I915_DEPENDENCY_ALLOC))
 		i915_dependency_free(dep);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index f1af3916a808..4f2b2eb7c3e5 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -66,7 +66,8 @@ struct i915_dependency {
 	struct list_head wait_link;
 	struct list_head dfs_link;
 	unsigned long flags;
-#define I915_DEPENDENCY_ALLOC BIT(0)
+#define I915_DEPENDENCY_ALLOC		BIT(0)
+#define I915_DEPENDENCY_EXTERNAL	BIT(1)
 };
 
 #endif /* _I915_SCHEDULER_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index fbee030db940..e8b0b5dbcb2c 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -99,12 +99,14 @@ static int live_busywait_preempt(void *arg)
 	ctx_hi = kernel_context(i915);
 	if (!ctx_hi)
 		goto err_unlock;
-	ctx_hi->sched.priority = INT_MAX;
+	ctx_hi->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
 	ctx_lo = kernel_context(i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority = INT_MIN;
+	ctx_lo->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
@@ -954,12 +956,14 @@ static int live_preempt_hang(void *arg)
 	ctx_hi = kernel_context(i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
-	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+	ctx_hi->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
 	ctx_lo = kernel_context(i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+	ctx_lo->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
 	for_each_engine(engine, i915, id) {
 		struct i915_request *rq;
-- 
cgit v1.2.3-58-ga151


From c80274bb5882ea1493551df7768977c5a43aa9d9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 15 May 2019 14:00:51 +0100
Subject: drm/i915: Downgrade NEWCLIENT to non-preemptive

Commit 1413b2bc0717 ("drm/i915: Trim NEWCLIENT boosting") had the
intended consequence of not allowing a sequence of work that merely
crossed into a new engine the privilege to be promoted to NEWCLIENT
status. It also had the unintended consequence of actually making
NEWCLIENT effective on heavily oversubscribed transcode machines and
impacting upon their throughput.

If we consider a client packet composed of (rcsA, rcsB, vcs) and 30 of
those clients, using the NEWCLIENT boost that will be scheduled as

	rcsA x 30, (rcsB, vcs) x 30

where as before it would have been

	(rcsA, rcsB, vcs) x 30

That is with NEWCLIENT only boosting the first request of each client,
we would execute all rcsA requests prior to running on the vcs engines;
acruing a lot of dead time as compared to the previous case where the
vcs engine would be started in parallel to processing the second client.

The previous patch has the effect of delaying submission until it is
required by a third party (either the user with an explicit wait, or by
another client/engine). We reduce the NEWCLIENT bump to a mere WAIT,
which has the effect of removing its preemptive grant and reducing it to
the same level as any other user interaction -- that it will not be
promoted above the interengine dependencies, and so preventing NEWCLIENTS
from starving other engines. This a large nerf to the rrul properties of
the current NEWCLIENT, but it still does give prioritised submission to
new requests from light workloads.

References: b16c765122f9 ("drm/i915: Priority boost for new clients")
Fixes: 1413b2bc0717 ("drm/i915: Trim NEWCLIENT boosting") # customer impact
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Dmitry Ermilov <dmitry.ermilov@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190515130052.4475-4-chris@chris-wilson.co.uk
(cherry picked from commit 68fc728b01fcc93b26d52f6e884e738962a49a66)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_priolist_types.h | 5 ++---
 drivers/gpu/drm/i915/i915_request.c        | 2 +-
 drivers/gpu/drm/i915/intel_lrc.c           | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index cc44ebd3b553..49709de69875 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -20,15 +20,14 @@ enum {
 	I915_PRIORITY_INVALID = INT_MIN
 };
 
-#define I915_USER_PRIORITY_SHIFT 3
+#define I915_USER_PRIORITY_SHIFT 2
 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
 
 #define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT)
 #define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1)
 
 #define I915_PRIORITY_WAIT		((u8)BIT(0))
-#define I915_PRIORITY_NEWCLIENT		((u8)BIT(1))
-#define I915_PRIORITY_NOSEMAPHORE	((u8)BIT(2))
+#define I915_PRIORITY_NOSEMAPHORE	((u8)BIT(1))
 
 #define __NO_PREEMPTION (I915_PRIORITY_WAIT)
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f258281bf3f3..ede79886cf98 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1228,7 +1228,7 @@ void i915_request_add(struct i915_request *request)
 		 * the bulk clients. (FQ_CODEL)
 		 */
 		if (list_empty(&request->sched.signalers_list))
-			attr.priority |= I915_PRIORITY_NEWCLIENT;
+			attr.priority |= I915_PRIORITY_WAIT;
 
 		engine->schedule(request, &attr);
 	}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4e0a351bfbca..11e5a86610bf 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -164,7 +164,7 @@
 #define WA_TAIL_DWORDS 2
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
-#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT | I915_PRIORITY_NOSEMAPHORE)
+#define ACTIVE_PRIORITY (I915_PRIORITY_NOSEMAPHORE)
 
 static int execlists_context_deferred_alloc(struct intel_context *ce,
 					    struct intel_engine_cs *engine);
-- 
cgit v1.2.3-58-ga151


From a491cc8e1597ea25803191cded49d3686702a406 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 15 May 2019 14:00:49 +0100
Subject: drm/i915: Truly bump ready tasks ahead of busywaits

In commit b7404c7ecb38 ("drm/i915: Bump ready tasks ahead of
busywaits"), I tried cutting a corner in order to not install a signal
for each of our dependencies, and only listened to requests on which we
were intending to busywait. The compromise that was made was that
instead of then being able to promote the request with a full
NOSEMAPHORE like its non-busywaiting brethren, as we had not ensured we
had cleared the semaphore chain, we settled for only using the NEWCLIENT
boost. With an over saturated system with multiple NEWCLIENTS in flight
at any time, this was found to be an inadequate promotion and left us
with a much poorer scheduling order than prior to using semaphores.

The outcome of this patch, is that all requests have NOSEMAPHORE
priority when they have no dependencies and are ready to run and not
busywait, restoring the pre-semaphore ordering on saturated systems.

We can demonstrate the effect of poor scheduling order by oversaturating
the system using gem_wsim on a system with multiple vcs engines
(i.e running the same workloads across more clients than required for
peak throughput, e.g. media_load_balance_17i7.wsim -c4 -b context):

x v5.1 (normalized)
+ tip
* fix
+------------------------------------------------------------------------+
|                                                                    x   |
|                                                                    x   |
|                                                                    x   |
|                                                                    x   |
|                                                                   %x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %%x   |
|                                                                  %#x   |
|                                                                  %#x   |
|                                                                  %#x   |
|                                                                  %#x   |
|                                                                  %#x   |
|         +                                                        %#xx  |
|         +                                                        %#xx  |
|         +                                                       %%#xx  |
|         +                                                       %%#xx  |
|         +                                                       %%#xx  |
|         +                                                       %%#xx  |
|         +                                                       %%##x  |
|         +++                                                     %%##x  |
|         +++                                                     %%##x  |
|         +++                                                     %%##x  |
|        ++++                                                     %%##x  |
|        ++++                                                     %%##x  |
|        ++++                                                     %%##xx |
|        ++++                                                     %###xx |
|        ++++                                                     %###xx |
|        ++++                                                     %###xx |
|        ++++                                                     %###xx |
|        ++++ +                                                   %#O#xx |
|        ++++ +                                                   %#O#xx |
|        ++++++ +                                                 %#O#xx |
|       ++++++++++                                                %OOOxxx|
|       ++++++++++       +                                       %#OOO#xx|
|     + ++++++++++++ ++ +++++    +                        ++    @@OOOO#xx|
|                                                                   |A_| |
||__________M_______A____________________|                               |
|                                                                 |A_|   |
+------------------------------------------------------------------------+
    N           Min           Max        Median           Avg        Stddev
x 120       0.99456       1.00628      0.999985     1.0001545  0.0024387139
+ 120      0.873021       1.00037      0.884134    0.90148752   0.039190862
Difference at 99.5% confidence
	-0.098667 +/- 0.0110762
	-9.86517% +/- 1.10745%
	(Student's t, pooled s = 0.0277657)
% 120      0.990207       1.00165     0.9970265    0.99699748     0.0021024
Difference at 99.5% confidence
	-0.003157 +/- 0.000908245
	-0.315651% +/- 0.0908105%
	(Student's t, pooled s = 0.00227678)

Fixes: b7404c7ecb38 ("drm/i915: Bump ready tasks ahead of busywaits")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Dmitry Ermilov <dmitry.ermilov@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190515130052.4475-2-chris@chris-wilson.co.uk
(cherry picked from commit 17db337f5098d29415314c4a588b842fc684394b)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_request.c | 31 ++++++++++++-------------------
 1 file changed, 12 insertions(+), 19 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index ede79886cf98..c88e538b2ef4 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -573,18 +573,7 @@ semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		/*
-		 * We only check a small portion of our dependencies
-		 * and so cannot guarantee that there remains no
-		 * semaphore chain across all. Instead of opting
-		 * for the full NOSEMAPHORE boost, we go for the
-		 * smaller (but still preempting) boost of
-		 * NEWCLIENT. This will be enough to boost over
-		 * a busywaiting request (as that cannot be
-		 * NEWCLIENT) without accidentally boosting
-		 * a busywait over real work elsewhere.
-		 */
-		i915_schedule_bump_priority(request, I915_PRIORITY_NEWCLIENT);
+		i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
 		break;
 
 	case FENCE_FREE:
@@ -865,12 +854,6 @@ emit_semaphore_wait(struct i915_request *to,
 	if (err < 0)
 		return err;
 
-	err = i915_sw_fence_await_dma_fence(&to->semaphore,
-					    &from->fence, 0,
-					    I915_FENCE_GFP);
-	if (err < 0)
-		return err;
-
 	/* We need to pin the signaler's HWSP until we are finished reading. */
 	err = i915_timeline_read_hwsp(from, to, &hwsp_offset);
 	if (err)
@@ -936,8 +919,18 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 						    &from->fence, 0,
 						    I915_FENCE_GFP);
 	}
+	if (ret < 0)
+		return ret;
+
+	if (to->sched.flags & I915_SCHED_HAS_SEMAPHORE_CHAIN) {
+		ret = i915_sw_fence_await_dma_fence(&to->semaphore,
+						    &from->fence, 0,
+						    I915_FENCE_GFP);
+		if (ret < 0)
+			return ret;
+	}
 
-	return ret < 0 ? ret : 0;
+	return 0;
 }
 
 int
-- 
cgit v1.2.3-58-ga151


From ada637e70f96862ff5ba20a169506b58cf567db9 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Tue, 14 May 2019 09:05:37 -0400
Subject: drm/amd/display: Add ASICREV_IS_PICASSO

[WHY]
We only want to load DMCU FW on Picasso and Raven 2, not on Raven 1.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/include/dal_asic_id.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 34d6fdcb32e2..4c8ce7938f01 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -138,13 +138,14 @@
 #endif
 #define RAVEN_UNKNOWN 0xFF
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
-#endif /* DCN1_01 */
 #define ASIC_REV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
 #define RAVEN1_F0 0xF0
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
 
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
+#endif /* DCN1_01 */
 
 #define FAMILY_RV 142 /* DCN 1*/
 
-- 
cgit v1.2.3-58-ga151


From 55143dc23ca4792868ea8c17bce65ca7b3d3e8c4 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Mon, 29 Apr 2019 09:39:15 -0400
Subject: drm/amd/display: Don't load DMCU for Raven 1

[WHY]
Some early Raven boards had a bad SBIOS that doesn't play nicely with
the DMCU FW. We thought the issues were fixed by ignoring errors on DMCU
load but that doesn't seem to be the case. We've still seen reports of
users unable to boot their systems at all.

[HOW]
Disable DMCU load on Raven 1. Only load it for Raven 2 and Picasso.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 995f9df66142..0680c740f6fe 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -29,6 +29,7 @@
 #include "dm_services_types.h"
 #include "dc.h"
 #include "dc/inc/core_types.h"
+#include "dal_asic_id.h"
 
 #include "vid.h"
 #include "amdgpu.h"
@@ -640,7 +641,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 
 static int load_dmcu_fw(struct amdgpu_device *adev)
 {
-	const char *fw_name_dmcu;
+	const char *fw_name_dmcu = NULL;
 	int r;
 	const struct dmcu_firmware_header_v1_0 *hdr;
 
@@ -663,7 +664,14 @@ static int load_dmcu_fw(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		return 0;
 	case CHIP_RAVEN:
-		fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
+		if (ASICREV_IS_PICASSO(adev->external_rev_id))
+			fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+		else if (ASICREV_IS_RAVEN2(adev->external_rev_id))
+			fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
+#endif
+		else
+			return 0;
 		break;
 	default:
 		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
-- 
cgit v1.2.3-58-ga151


From 0a5a9c276c335870a1cecc4f02b76d6d6f663c8b Mon Sep 17 00:00:00 2001
From: Kent Russell <kent.russell@amd.com>
Date: Mon, 13 May 2019 09:00:05 -0400
Subject: drm/amdkfd: Add missing Polaris10 ID

This was added to amdgpu but was missed in amdkfd

Signed-off-by: Kent Russell <kent.russell@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.rg
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index c1e4d44d6137..4dd8489144d0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -355,6 +355,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x67CF, &polaris10_device_info },	/* Polaris10 */
 	{ 0x67D0, &polaris10_vf_device_info },	/* Polaris10 vf*/
 	{ 0x67DF, &polaris10_device_info },	/* Polaris10 */
+	{ 0x6FDF, &polaris10_device_info },	/* Polaris10 */
 	{ 0x67E0, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67E1, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67E3, &polaris11_device_info },	/* Polaris11 */
-- 
cgit v1.2.3-58-ga151


From 379109351f4f6f2405cf54e7a296055f589c3ad1 Mon Sep 17 00:00:00 2001
From: Flora Cui <flora.cui@amd.com>
Date: Fri, 17 May 2019 11:33:56 +0800
Subject: drm/amdgpu: keep stolen memory on picasso

otherwise screen corrupts during modprobe.

Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3fd79e07944d..4e6fcaeb1303 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -626,6 +626,7 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
 	case CHIP_VEGA10:
 		return true;
 	case CHIP_RAVEN:
+		return (adev->pdev->device == 0x15d8);
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	default:
-- 
cgit v1.2.3-58-ga151


From 5887a59961e2295c5b02f39dbc0ecf9212709b7b Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 17 May 2019 09:21:13 -0500
Subject: drm/amdgpu/soc15: skip reset on init

Not necessary on soc15 and breaks driver reload on server cards.

Acked-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/soc15.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4900e4958dec..b7e594c2bfb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -730,6 +730,11 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev)
 {
 	u32 sol_reg;
 
+	/* Just return false for soc15 GPUs.  Reset does not seem to
+	 * be necessary.
+	 */
+	return false;
+
 	if (adev->flags & AMD_IS_APU)
 		return false;
 
-- 
cgit v1.2.3-58-ga151


From 067e75b3d786b6bd7863e86f9a8025284be87ac8 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 17 May 2019 09:31:43 -0500
Subject: drm/amdgpu/gmc9: set vram_width properly for SR-IOV

For SR-IOV, vram_width can't be read from ATOM as
RAVEN, and DF related registers is not readable, so hardcord
is the only way to set the correct vram_width.

Reviewed-by: Yintian Tao <yttao@amd.com>
Signed-off-by: Trigger Huang <Trigger.Huang@amd.com>
Signed-off-by: Yintian Tao <yttao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 4e6fcaeb1303..3b7370d914a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -813,8 +813,16 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 	int chansize, numchan;
 	int r;
 
-	if (amdgpu_emu_mode != 1)
+	if (amdgpu_sriov_vf(adev)) {
+		/* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN,
+		 * and DF related registers is not readable, seems hardcord is the
+		 * only way to set the correct vram_width
+		 */
+		adev->gmc.vram_width = 2048;
+	} else if (amdgpu_emu_mode != 1) {
 		adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
+	}
+
 	if (!adev->gmc.vram_width) {
 		/* hbm memory channel size */
 		if (adev->flags & AMD_IS_APU)
-- 
cgit v1.2.3-58-ga151


From 029f41535ac5e07e1fa17ca963a9f9fd05fb665f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 15 May 2019 12:51:30 +0300
Subject: drm/amd/powerplay: fix locking in smu_feature_set_supported()

There is a typo so the code unlocks twice instead of taking the lock and
then releasing it.

Fixes: f14a323db5b0 ("drm/amd/powerplay: implement update enabled feature state to smc for smu11")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index c058c784180e..eec329ab6037 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -280,7 +280,7 @@ int smu_feature_set_supported(struct smu_context *smu, int feature_id,
 
 	WARN_ON(feature_id > feature->feature_num);
 
-	mutex_unlock(&feature->mutex);
+	mutex_lock(&feature->mutex);
 	if (enable)
 		test_and_set_bit(feature_id, feature->supported);
 	else
-- 
cgit v1.2.3-58-ga151


From 057f91645cef412fe460b17fa50726c8a1c5921c Mon Sep 17 00:00:00 2001
From: Yintian Tao <yttao@amd.com>
Date: Thu, 16 May 2019 13:07:26 +0800
Subject: drm/amdgpu: skip fw pri bo alloc for SRIOV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSP fw primary buffer is not used under SRIOV.
Under SRIOV, VBIOS or hypervisor driver will load psp
sos and psp sysdrv. Therefore, we don't need to
allocate memory for it.

v2: remove superfluous check for amdgpu_bo_free_kernel().

Signed-off-by: Yintian Tao <yttao@amd.com>
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 05897b05766b..86cc24b2e0aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -877,13 +877,16 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	if (!psp->cmd)
 		return -ENOMEM;
 
-	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-					AMDGPU_GEM_DOMAIN_GTT,
-					&psp->fw_pri_bo,
-					&psp->fw_pri_mc_addr,
-					&psp->fw_pri_buf);
-	if (ret)
-		goto failed;
+	/* this fw pri bo is not used under SRIOV */
+	if (!amdgpu_sriov_vf(psp->adev)) {
+		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
+					      AMDGPU_GEM_DOMAIN_GTT,
+					      &psp->fw_pri_bo,
+					      &psp->fw_pri_mc_addr,
+					      &psp->fw_pri_buf);
+		if (ret)
+			goto failed;
+	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
 					AMDGPU_GEM_DOMAIN_VRAM,
-- 
cgit v1.2.3-58-ga151


From 43d8107f0bdcaa4300e40231cc45ecbd1f77f73f Mon Sep 17 00:00:00 2001
From: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Date: Fri, 25 Jan 2019 16:35:35 -0500
Subject: drm/amdkfd: Fix compute profile switching

Fix compute profile switching on process termination.

Add a dedicated reference counter to keep track of entry/exit to/from
compute profile. This enables switching compute profiles for other
reasons than process creation or termination.

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c               | 16 ++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 11 ++++++-----
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h                 |  7 +++++++
 3 files changed, 29 insertions(+), 5 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 4dd8489144d0..765b58a17dc7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -463,6 +463,7 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 	kfd->pdev = pdev;
 	kfd->init_complete = false;
 	kfd->kfd2kgd = f2g;
+	atomic_set(&kfd->compute_profile, 0);
 
 	mutex_init(&kfd->doorbell_mutex);
 	memset(&kfd->doorbell_available_index, 0,
@@ -1037,6 +1038,21 @@ void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 		atomic_inc(&kfd->sram_ecc_flag);
 }
 
+void kfd_inc_compute_active(struct kfd_dev *kfd)
+{
+	if (atomic_inc_return(&kfd->compute_profile) == 1)
+		amdgpu_amdkfd_set_compute_idle(kfd->kgd, false);
+}
+
+void kfd_dec_compute_active(struct kfd_dev *kfd)
+{
+	int count = atomic_dec_return(&kfd->compute_profile);
+
+	if (count == 0)
+		amdgpu_amdkfd_set_compute_idle(kfd->kgd, true);
+	WARN_ONCE(count < 0, "Compute profile ref. count error");
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 /* This function will send a package to HIQ to hang the HWS
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index c6c9530e704e..ae381450601c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -811,8 +811,8 @@ static int register_process(struct device_queue_manager *dqm,
 
 	retval = dqm->asic_ops.update_qpd(dqm, qpd);
 
-	if (dqm->processes_count++ == 0)
-		amdgpu_amdkfd_set_compute_idle(dqm->dev->kgd, false);
+	dqm->processes_count++;
+	kfd_inc_compute_active(dqm->dev);
 
 	dqm_unlock(dqm);
 
@@ -835,9 +835,8 @@ static int unregister_process(struct device_queue_manager *dqm,
 		if (qpd == cur->qpd) {
 			list_del(&cur->list);
 			kfree(cur);
-			if (--dqm->processes_count == 0)
-				amdgpu_amdkfd_set_compute_idle(
-					dqm->dev->kgd, true);
+			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			goto out;
 		}
 	}
@@ -1539,6 +1538,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 			list_del(&cur->list);
 			kfree(cur);
 			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			break;
 		}
 	}
@@ -1626,6 +1626,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 			list_del(&cur->list);
 			kfree(cur);
 			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9e0230965675..487d5da337c1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -279,6 +279,9 @@ struct kfd_dev {
 
 	/* SRAM ECC flag */
 	atomic_t sram_ecc_flag;
+
+	/* Compute Profile ref. count */
+	atomic_t compute_profile;
 };
 
 enum kfd_mempool {
@@ -978,6 +981,10 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
 bool kfd_is_locked(void);
 
+/* Compute profile */
+void kfd_inc_compute_active(struct kfd_dev *dev);
+void kfd_dec_compute_active(struct kfd_dev *dev);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
-- 
cgit v1.2.3-58-ga151


From a8c2d5ab9e71be3f9431c47bd45329a36e1fc650 Mon Sep 17 00:00:00 2001
From: Weinan <weinan.z.li@intel.com>
Date: Fri, 10 May 2019 15:57:20 +0800
Subject: drm/i915/gvt: emit init breadcrumb for gvt request

"To track whether a request has started on HW, we can emit a breadcrumb at
the beginning of the request and check its timeline's HWSP to see if the
breadcrumb has advanced past the start of this request." It means all the
request which timeline's has_init_breadcrumb is true, then the
emit_init_breadcrumb process must have before emitting the real commands,
otherwise, the scheduler might get a wrong state of this request during
reset. If the request is exactly the guilty one, the scheduler won't
terminate it with the wrong state. To avoid this, do emit_init_breadcrumb
for all the requests from gvt.

v2: cc to stable kernel

Fixes: 8547444137ec ("drm/i915: Identify active requests")
Cc: stable@vger.kernel.org
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Weinan <weinan.z.li@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 7c99bbc3e2b8..ccd71152c9bc 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -298,12 +298,31 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	struct i915_request *req = workload->req;
 	void *shadow_ring_buffer_va;
 	u32 *cs;
+	int err;
 
 	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915)
 		|| IS_COFFEELAKE(req->i915))
 		&& is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
+	/*
+	 * To track whether a request has started on HW, we can emit a
+	 * breadcrumb at the beginning of the request and check its
+	 * timeline's HWSP to see if the breadcrumb has advanced past the
+	 * start of this request. Actually, the request must have the
+	 * init_breadcrumb if its timeline set has_init_bread_crumb, or the
+	 * scheduler might get a wrong state of it during reset. Since the
+	 * requests from gvt always set the has_init_breadcrumb flag, here
+	 * need to do the emit_init_breadcrumb for all the requests.
+	 */
+	if (req->engine->emit_init_breadcrumb) {
+		err = req->engine->emit_init_breadcrumb(req);
+		if (err) {
+			gvt_vgpu_err("fail to emit init breadcrumb\n");
+			return err;
+		}
+	}
+
 	/* allocate shadow ring buffer */
 	cs = intel_ring_begin(workload->req, workload->rb_len / sizeof(u32));
 	if (IS_ERR(cs)) {
-- 
cgit v1.2.3-58-ga151


From df2ea3c296b1f3d66f297d240124c2ebd74c3db3 Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Tue, 7 May 2019 22:14:04 -0400
Subject: drm/i915/gvt: use cmd to restore in-context mmios to hw for gen9
 platform

for restore-inhibit context, hardware will not load in-context mmios
(engine context part) to hardware, but hardware will save the mmio
values in hardware back to context image. So, in order to save correct
values of vGPU back to context image, values of vGPU mmios have to be
loaded into hardware first for restore-inhibit context.

In this patch, the mechanism is applied to all gen9 platform.

The reason excluding gen8 platforms is only because of lacking of testing
on those platforms.

v3: for mocs registers, goto in-context mmios save-restore path for skl
platform as well (weinan li)
v2: update vreg when scanning indirect context for inhibit context for
gen9

Cc: Weinan Li <weinan.z.li@intel.com>
Acked-by: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/cmd_parser.c   | 14 +++++++++-----
 drivers/gpu/drm/i915/gvt/mmio_context.c | 10 +++-------
 drivers/gpu/drm/i915/gvt/scheduler.c    |  4 +---
 3 files changed, 13 insertions(+), 15 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index ab002cfd3cab..5cb59c0b4bbe 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -896,12 +896,16 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 	}
 
 	/* TODO
-	 * Right now only scan LRI command on KBL and in inhibit context.
-	 * It's good enough to support initializing mmio by lri command in
-	 * vgpu inhibit context on KBL.
+	 * In order to let workload with inhibit context to generate
+	 * correct image data into memory, vregs values will be loaded to
+	 * hw via LRIs in the workload with inhibit context. But as
+	 * indirect context is loaded prior to LRIs in workload, we don't
+	 * want reg values specified in indirect context overwritten by
+	 * LRIs in workloads. So, when scanning an indirect context, we
+	 * update reg values in it into vregs, so LRIs in workload with
+	 * inhibit context will restore with correct values
 	 */
-	if ((IS_KABYLAKE(s->vgpu->gvt->dev_priv)
-		|| IS_COFFEELAKE(s->vgpu->gvt->dev_priv)) &&
+	if (IS_GEN(gvt->dev_priv, 9) &&
 			intel_gvt_mmio_is_in_ctx(gvt, offset) &&
 			!strncmp(cmd, "lri", 3)) {
 		intel_gvt_hypervisor_read_gpa(s->vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index edf6d646eb25..299b602b0643 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -392,10 +392,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 	if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
 		return;
 
-	if (ring_id == RCS0 &&
-	    (IS_KABYLAKE(dev_priv) ||
-	     IS_BROXTON(dev_priv) ||
-	     IS_COFFEELAKE(dev_priv)))
+	if (ring_id == RCS0 && IS_GEN(dev_priv, 9))
 		return;
 
 	if (!pre && !gen9_render_mocs.initialized)
@@ -470,11 +467,10 @@ static void switch_mmio(struct intel_vgpu *pre,
 			continue;
 		/*
 		 * No need to do save or restore of the mmio which is in context
-		 * state image on kabylake, it's initialized by lri command and
+		 * state image on gen9, it's initialized by lri command and
 		 * save or restore with context together.
 		 */
-		if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)
-			|| IS_COFFEELAKE(dev_priv)) && mmio->in_context)
+		if (IS_GEN(dev_priv, 9) && mmio->in_context)
 			continue;
 
 		// save
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index ccd71152c9bc..13632dba8b2a 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -300,9 +300,7 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	u32 *cs;
 	int err;
 
-	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915)
-		|| IS_COFFEELAKE(req->i915))
-		&& is_inhibit_context(req->hw_context))
+	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/*
-- 
cgit v1.2.3-58-ga151


From 39947afc6c063940cbd80824e75eb0cf84591c3c Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Tue, 7 May 2019 22:15:00 -0400
Subject: drm/i915/gvt: Tiled Resources mmios are in-context mmios for gen9+

TRVATTL3PTRDW(0x4de0-0x4de4), TRNULLDETCT(0x4de8), TRINVTILEDETCT(0x4dec),
TRTTE(0x4df0), TRVADR(0x4df4) are in-context mmios for gen9+

Fixes: 178657139307 ("drm/i915/gvt: vGPU context switch")
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/mmio_context.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 299b602b0643..f4e60d736cfb 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -108,12 +108,12 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS0, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */
 	{RCS0, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */
 	{RCS0, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */
-	{RCS0, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */
-	{RCS0, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */
-	{RCS0, TRNULLDETCT, 0, false}, /* 0x4de8 */
-	{RCS0, TRINVTILEDETCT, 0, false}, /* 0x4dec */
-	{RCS0, TRVADR, 0, false}, /* 0x4df0 */
-	{RCS0, TRTTE, 0, false}, /* 0x4df4 */
+	{RCS0, TRVATTL3PTRDW(0), 0, true}, /* 0x4de0 */
+	{RCS0, TRVATTL3PTRDW(1), 0, true}, /* 0x4de4 */
+	{RCS0, TRNULLDETCT, 0, true}, /* 0x4de8 */
+	{RCS0, TRINVTILEDETCT, 0, true}, /* 0x4dec */
+	{RCS0, TRVADR, 0, true}, /* 0x4df0 */
+	{RCS0, TRTTE, 0, true}, /* 0x4df4 */
 
 	{BCS0, RING_GFX_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2229c */
 	{BCS0, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
-- 
cgit v1.2.3-58-ga151


From b6241002039118d6bea78f50f8f19195b41ab602 Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Tue, 7 May 2019 22:16:33 -0400
Subject: drm/i915/gvt: add 0x4dfc to gen9 save-restore list

0x4dfc is in-context mmio for gen9+, but each vm have different settings
need to add it to save-restore list along with other trtt registers

Fixes: 178657139307 ("drm/i915/gvt: vGPU context switch")
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/mmio_context.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index f4e60d736cfb..90bb3df0db50 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -114,6 +114,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS0, TRINVTILEDETCT, 0, true}, /* 0x4dec */
 	{RCS0, TRVADR, 0, true}, /* 0x4df0 */
 	{RCS0, TRTTE, 0, true}, /* 0x4df4 */
+	{RCS0, _MMIO(0x4dfc), 0, true},
 
 	{BCS0, RING_GFX_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2229c */
 	{BCS0, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
-- 
cgit v1.2.3-58-ga151


From e175a2520c7788a323ae93f04013b8fdaa552c69 Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Tue, 7 May 2019 22:16:44 -0400
Subject: drm/i915/gvt: do not let TRTTE and 0x4dfc write passthrough to
 hardware

the vGPU write on TRTTE and 0x4dfc is now write to vreg first. their
values all be restored hardware when context switching.

Fixes: e39c5add3221 ("drm/i915/gvt: vGPU MMIO virtualization")
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 15 ---------------
 1 file changed, 15 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90673fca792f..e09bd6e0cc4d 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1364,7 +1364,6 @@ static int dma_ctrl_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	u32 trtte = *(u32 *)p_data;
 
 	if ((trtte & 1) && (trtte & (1 << 1)) == 0) {
@@ -1373,11 +1372,6 @@ static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset,
 		return -EINVAL;
 	}
 	write_vreg(vgpu, offset, p_data, bytes);
-	/* TRTTE is not per-context */
-
-	mmio_hw_access_pre(dev_priv);
-	I915_WRITE(_MMIO(offset), vgpu_vreg(vgpu, offset));
-	mmio_hw_access_post(dev_priv);
 
 	return 0;
 }
@@ -1385,15 +1379,6 @@ static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int gen9_trtt_chicken_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-	u32 val = *(u32 *)p_data;
-
-	if (val & 1) {
-		/* unblock hw logic */
-		mmio_hw_access_pre(dev_priv);
-		I915_WRITE(_MMIO(offset), val);
-		mmio_hw_access_post(dev_priv);
-	}
 	write_vreg(vgpu, offset, p_data, bytes);
 	return 0;
 }
-- 
cgit v1.2.3-58-ga151


From 591c39ffac4ab1ddf2ea6d49331cb614e0682b28 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 13 May 2019 12:22:44 +0300
Subject: drm/i915/gvt: Fix an error code in
 ppgtt_populate_spt_by_guest_entry()

"ret" is uninitialized on this path but it should be -EINVAL.

Fixes: 930c8dfea4b8 ("drm/i915/gvt: Check if get_next_pt_type() always returns a valid value")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 08c74e65836b..244ad1729764 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1076,8 +1076,10 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 	} else {
 		int type = get_next_pt_type(we->type);
 
-		if (!gtt_type_is_pt(type))
+		if (!gtt_type_is_pt(type)) {
+			ret = -EINVAL;
 			goto err;
+		}
 
 		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
-- 
cgit v1.2.3-58-ga151


From 63cb44441826e842b7285575b96db631cc9f2505 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Tue, 7 May 2019 11:07:53 +0200
Subject: drm/vmwgfx: Don't send drm sysfs hotplug events on initial master set

This may confuse user-space clients like plymouth that opens a drm
file descriptor as a result of a hotplug event and then generates a
new event...

Cc: <stable@vger.kernel.org>
Fixes: 5ea1734827bb ("drm/vmwgfx: Send a hotplug event at master_set")
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index bf6c3500d363..4ff11a0077e1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1239,7 +1239,13 @@ static int vmw_master_set(struct drm_device *dev,
 	}
 
 	dev_priv->active_master = vmaster;
-	drm_sysfs_hotplug_event(dev);
+
+	/*
+	 * Inform a new master that the layout may have changed while
+	 * it was gone.
+	 */
+	if (!from_open)
+		drm_sysfs_hotplug_event(dev);
 
 	return 0;
 }
-- 
cgit v1.2.3-58-ga151


From 8407f8a1d940fe28c4243ad4f0cb6a44dcee88f6 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Tue, 7 May 2019 11:10:10 +0200
Subject: drm/vmwgfx: Fix user space handle equal to zero

User-space handles equal to zero are interpreted as uninitialized or
illegal by some drm systems (most notably kms). This means that a
dumb buffer or surface with a zero user-space handle can never be
used as a kms frame-buffer.

Cc: <stable@vger.kernel.org>
Fixes: c7eae62666ad ("drm/vmwgfx: Make the object handles idr-generated")
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/ttm_object.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c
index 36990b80e790..16077785ad47 100644
--- a/drivers/gpu/drm/vmwgfx/ttm_object.c
+++ b/drivers/gpu/drm/vmwgfx/ttm_object.c
@@ -174,7 +174,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile,
 	kref_init(&base->refcount);
 	idr_preload(GFP_KERNEL);
 	spin_lock(&tdev->object_lock);
-	ret = idr_alloc(&tdev->idr, base, 0, 0, GFP_NOWAIT);
+	ret = idr_alloc(&tdev->idr, base, 1, 0, GFP_NOWAIT);
 	spin_unlock(&tdev->object_lock);
 	idr_preload_end();
 	if (ret < 0)
-- 
cgit v1.2.3-58-ga151


From e41c20cf50a8a7d0dfa337a7530590aacef4193b Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 4 Apr 2019 13:25:43 +0000
Subject: drm/vmwgfx: Fix compat mode shader operation

In compat mode, we allowed host-backed user-space with guest-backed
kernel / device. In this mode, set shader commands was broken since
no relocations were emitted. Fix this.

Cc: <stable@vger.kernel.org>
Fixes: e8c66efbfe3a ("drm/vmwgfx: Make user resource lookups reference-free during validation")
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 2ff7ba04d8c8..315f9efce765 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2010,6 +2010,11 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,
 		return 0;
 
 	if (cmd->body.shid != SVGA3D_INVALID_ID) {
+		/*
+		 * This is the compat shader path - Per device guest-backed
+		 * shaders, but user-space thinks it's per context host-
+		 * backed shaders.
+		 */
 		res = vmw_shader_lookup(vmw_context_res_man(ctx),
 					cmd->body.shid, cmd->body.type);
 		if (!IS_ERR(res)) {
@@ -2017,6 +2022,14 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,
 							    VMW_RES_DIRTY_NONE);
 			if (unlikely(ret != 0))
 				return ret;
+
+			ret = vmw_resource_relocation_add
+				(sw_context, res,
+				 vmw_ptr_diff(sw_context->buf_start,
+					      &cmd->body.shid),
+				 vmw_res_rel_normal);
+			if (unlikely(ret != 0))
+				return ret;
 		}
 	}
 
-- 
cgit v1.2.3-58-ga151


From 8dc39cfca32c9a4e6deddaa0e76bd47d56f1876b Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Wed, 15 May 2019 17:45:23 +0200
Subject: drm/vmwgfx: Use the dma scatter-gather iterator to get dma addresses

Use struct sg_dma_page_iter in favour struct of sg_page_iter, which fairly
recently was declared useless for obtaining dma addresses.

With a struct sg_dma_page_iter we can't call sg_page_iter_page() so
when the page is needed, use the same page lookup mechanism as for the
non-sg dma modes instead of calling sg_dma_page_iter.

Note, the fixes tag doesn't really point to a commit introducing a
failure / regression, but rather to a commit that implemented a simple
workaround for this problem.

Cc: Jason Gunthorpe <jgg@mellanox.com>
Fixes: d901b2760dc6 ("lib/scatterlist: Provide a DMA page iterator")
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h        |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 27 +++++++--------------------
 2 files changed, 8 insertions(+), 21 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 96983c47fb40..366dcfc1f9bb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -296,7 +296,7 @@ struct vmw_sg_table {
 struct vmw_piter {
 	struct page **pages;
 	const dma_addr_t *addrs;
-	struct sg_page_iter iter;
+	struct sg_dma_page_iter iter;
 	unsigned long i;
 	unsigned long num_pages;
 	bool (*next)(struct vmw_piter *);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index a3357ff7540d..a6ea75b58a83 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -266,7 +266,9 @@ static bool __vmw_piter_non_sg_next(struct vmw_piter *viter)
 
 static bool __vmw_piter_sg_next(struct vmw_piter *viter)
 {
-	return __sg_page_iter_next(&viter->iter);
+	bool ret = __vmw_piter_non_sg_next(viter);
+
+	return __sg_page_iter_dma_next(&viter->iter) && ret;
 }
 
 
@@ -284,12 +286,6 @@ static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter)
 	return viter->pages[viter->i];
 }
 
-static struct page *__vmw_piter_sg_page(struct vmw_piter *viter)
-{
-	return sg_page_iter_page(&viter->iter);
-}
-
-
 /**
  * Helper functions to return the DMA address of the current page.
  *
@@ -311,13 +307,7 @@ static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
 
 static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter)
 {
-	/*
-	 * FIXME: This driver wrongly mixes DMA and CPU SG list iteration and
-	 * needs revision. See
-	 * https://lore.kernel.org/lkml/20190104223531.GA1705@ziepe.ca/
-	 */
-	return sg_page_iter_dma_address(
-		container_of(&viter->iter, struct sg_dma_page_iter, base));
+	return sg_page_iter_dma_address(&viter->iter);
 }
 
 
@@ -336,26 +326,23 @@ void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
 {
 	viter->i = p_offset - 1;
 	viter->num_pages = vsgt->num_pages;
+	viter->page = &__vmw_piter_non_sg_page;
+	viter->pages = vsgt->pages;
 	switch (vsgt->mode) {
 	case vmw_dma_phys:
 		viter->next = &__vmw_piter_non_sg_next;
 		viter->dma_address = &__vmw_piter_phys_addr;
-		viter->page = &__vmw_piter_non_sg_page;
-		viter->pages = vsgt->pages;
 		break;
 	case vmw_dma_alloc_coherent:
 		viter->next = &__vmw_piter_non_sg_next;
 		viter->dma_address = &__vmw_piter_dma_addr;
-		viter->page = &__vmw_piter_non_sg_page;
 		viter->addrs = vsgt->addrs;
-		viter->pages = vsgt->pages;
 		break;
 	case vmw_dma_map_populate:
 	case vmw_dma_map_bind:
 		viter->next = &__vmw_piter_sg_next;
 		viter->dma_address = &__vmw_piter_sg_addr;
-		viter->page = &__vmw_piter_sg_page;
-		__sg_page_iter_start(&viter->iter, vsgt->sgt->sgl,
+		__sg_page_iter_start(&viter->iter.base, vsgt->sgt->sgl,
 				     vsgt->sgt->orig_nents, p_offset);
 		break;
 	default:
-- 
cgit v1.2.3-58-ga151


From bcd6aa7b6cbfd6f985f606c6f76046d782905820 Mon Sep 17 00:00:00 2001
From: Murray McAllister <murray.mcallister@gmail.com>
Date: Sat, 11 May 2019 18:01:37 +1200
Subject: drm/vmwgfx: NULL pointer dereference from vmw_cmd_dx_view_define()

If SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW is called with a surface
ID of SVGA3D_INVALID_ID, the srf struct will remain NULL after
vmw_cmd_res_check(), leading to a null pointer dereference in
vmw_view_add().

Cc: <stable@vger.kernel.org>
Fixes: d80efd5cb3de ("drm/vmwgfx: Initial DX support")
Signed-off-by: Murray McAllister <murray.mcallister@gmail.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 315f9efce765..b4c7553d2814 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2427,6 +2427,10 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv,
 		return -EINVAL;
 
 	cmd = container_of(header, typeof(*cmd), header);
+	if (unlikely(cmd->sid == SVGA3D_INVALID_ID)) {
+		VMW_DEBUG_USER("Invalid surface id.\n");
+		return -EINVAL;
+	}
 	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
 				VMW_RES_DIRTY_NONE, user_surface_converter,
 				&cmd->sid, &srf);
-- 
cgit v1.2.3-58-ga151


From 5ed7f4b5eca11c3c69e7c8b53e4321812bc1ee1e Mon Sep 17 00:00:00 2001
From: Murray McAllister <murray.mcallister@gmail.com>
Date: Mon, 20 May 2019 21:57:34 +1200
Subject: drm/vmwgfx: integer underflow in vmw_cmd_dx_set_shader() leading to
 an invalid read

If SVGA_3D_CMD_DX_SET_SHADER is called with a shader ID
of SVGA3D_INVALID_ID, and a shader type of
SVGA3D_SHADERTYPE_INVALID, the calculated binding.shader_slot
will be 4294967295, leading to an out-of-bounds read in vmw_binding_loc()
when the offset is calculated.

Cc: <stable@vger.kernel.org>
Fixes: d80efd5cb3de ("drm/vmwgfx: Initial DX support")
Signed-off-by: Murray McAllister <murray.mcallister@gmail.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index b4c7553d2814..33533d126277 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2206,7 +2206,8 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv,
 
 	cmd = container_of(header, typeof(*cmd), header);
 
-	if (cmd->body.type >= SVGA3D_SHADERTYPE_DX10_MAX) {
+	if (cmd->body.type >= SVGA3D_SHADERTYPE_DX10_MAX ||
+	    cmd->body.type < SVGA3D_SHADERTYPE_MIN) {
 		VMW_DEBUG_USER("Illegal shader type %u.\n",
 			       (unsigned int) cmd->body.type);
 		return -EINVAL;
-- 
cgit v1.2.3-58-ga151


From 7c420636860a719049fae9403e2c87804f53bdde Mon Sep 17 00:00:00 2001
From: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Date: Tue, 16 Apr 2019 13:46:07 +0200
Subject: drm/gma500/cdv: Check vbt config bits when detecting lvds panels

Some machines have an lvds child device in vbt even though a panel is
not attached. To make detection more reliable we now also check the lvds
config bits available in the vbt.

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1665766
Cc: stable@vger.kernel.org
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190416114607.1072-1-patrik.r.jakobsson@gmail.com
---
 drivers/gpu/drm/gma500/cdv_intel_lvds.c | 3 +++
 drivers/gpu/drm/gma500/intel_bios.c     | 3 +++
 drivers/gpu/drm/gma500/psb_drv.h        | 1 +
 3 files changed, 7 insertions(+)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
index de9531caaca0..9c8446184b17 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
@@ -594,6 +594,9 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 	int pipe;
 	u8 pin;
 
+	if (!dev_priv->lvds_enabled_in_vbt)
+		return;
+
 	pin = GMBUS_PORT_PANEL;
 	if (!lvds_is_present_in_vbt(dev, &pin)) {
 		DRM_DEBUG_KMS("LVDS is not present in VBT\n");
diff --git a/drivers/gpu/drm/gma500/intel_bios.c b/drivers/gpu/drm/gma500/intel_bios.c
index 63bde4e86c6a..e019ea271ffc 100644
--- a/drivers/gpu/drm/gma500/intel_bios.c
+++ b/drivers/gpu/drm/gma500/intel_bios.c
@@ -436,6 +436,9 @@ parse_driver_features(struct drm_psb_private *dev_priv,
 	if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP)
 		dev_priv->edp.support = 1;
 
+	dev_priv->lvds_enabled_in_vbt = driver->lvds_config != 0;
+	DRM_DEBUG_KMS("LVDS VBT config bits: 0x%x\n", driver->lvds_config);
+
 	/* This bit means to use 96Mhz for DPLL_A or not */
 	if (driver->primary_lfp_id)
 		dev_priv->dplla_96mhz = true;
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 941b238bdcc9..bc608ddc3bd1 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -537,6 +537,7 @@ struct drm_psb_private {
 	int lvds_ssc_freq;
 	bool is_lvds_on;
 	bool is_mipi_on;
+	bool lvds_enabled_in_vbt;
 	u32 mipi_ctrl_display;
 
 	unsigned int core_freq;
-- 
cgit v1.2.3-58-ga151


From f3617b449d0bcf3b5d80a97f51498dcf7463cf7e Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 17 May 2019 12:00:42 -0300
Subject: drm/panfrost: Select devfreq

Currently, there is some logic for the driver to work without devfreq.
However, the driver actually fails to probe if !CONFIG_PM_DEVFREQ.

Fix this by selecting devfreq, and drop the additional checks
for devfreq.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20190517150042.776-1-ezequiel@collabora.com
---
 drivers/gpu/drm/panfrost/Kconfig            |  1 +
 drivers/gpu/drm/panfrost/panfrost_devfreq.c | 13 ++-----------
 2 files changed, 3 insertions(+), 11 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/panfrost/Kconfig b/drivers/gpu/drm/panfrost/Kconfig
index 591611dc4e34..81963e964b0f 100644
--- a/drivers/gpu/drm/panfrost/Kconfig
+++ b/drivers/gpu/drm/panfrost/Kconfig
@@ -9,6 +9,7 @@ config DRM_PANFROST
 	select IOMMU_SUPPORT
 	select IOMMU_IO_PGTABLE_LPAE
 	select DRM_GEM_SHMEM_HELPER
+	select PM_DEVFREQ
 	help
 	  DRM driver for ARM Mali Midgard (T6xx, T7xx, T8xx) and
 	  Bifrost (G3x, G5x, G7x) GPUs.
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 238bd1d89d43..29fcffdf2d57 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -140,8 +140,8 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 		return 0;
 
 	ret = dev_pm_opp_of_add_table(&pfdev->pdev->dev);
-	if (ret == -ENODEV) /* Optional, continue without devfreq */
-		return 0;
+	if (ret)
+		return ret;
 
 	panfrost_devfreq_reset(pfdev);
 
@@ -170,9 +170,6 @@ void panfrost_devfreq_resume(struct panfrost_device *pfdev)
 {
 	int i;
 
-	if (!pfdev->devfreq.devfreq)
-		return;
-
 	panfrost_devfreq_reset(pfdev);
 	for (i = 0; i < NUM_JOB_SLOTS; i++)
 		pfdev->devfreq.slot[i].busy = false;
@@ -182,9 +179,6 @@ void panfrost_devfreq_resume(struct panfrost_device *pfdev)
 
 void panfrost_devfreq_suspend(struct panfrost_device *pfdev)
 {
-	if (!pfdev->devfreq.devfreq)
-		return;
-
 	devfreq_suspend_device(pfdev->devfreq.devfreq);
 }
 
@@ -194,9 +188,6 @@ static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev, i
 	ktime_t now;
 	ktime_t last;
 
-	if (!pfdev->devfreq.devfreq)
-		return;
-
 	now = ktime_get();
 	last = pfdev->devfreq.slot[slot].time_last_update;
 
-- 
cgit v1.2.3-58-ga151


From c074989171801171af6c5f53dd16b27f36b31deb Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Fri, 24 May 2019 19:55:32 +1000
Subject: Revert "drm/amd/display: Don't load DMCU for Raven 1"

This reverts commit 55143dc23ca4792868ea8c17bce65ca7b3d3e8c4.

This causes build breakags with some Kconfigs so revert for now.

Fixes: 55143dc23ca4 ("drm/amd/display: Don't load DMCU for Raven 1")

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

(limited to 'drivers')

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0680c740f6fe..995f9df66142 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -29,7 +29,6 @@
 #include "dm_services_types.h"
 #include "dc.h"
 #include "dc/inc/core_types.h"
-#include "dal_asic_id.h"
 
 #include "vid.h"
 #include "amdgpu.h"
@@ -641,7 +640,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 
 static int load_dmcu_fw(struct amdgpu_device *adev)
 {
-	const char *fw_name_dmcu = NULL;
+	const char *fw_name_dmcu;
 	int r;
 	const struct dmcu_firmware_header_v1_0 *hdr;
 
@@ -664,14 +663,7 @@ static int load_dmcu_fw(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		return 0;
 	case CHIP_RAVEN:
-		if (ASICREV_IS_PICASSO(adev->external_rev_id))
-			fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
-		else if (ASICREV_IS_RAVEN2(adev->external_rev_id))
-			fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
-#endif
-		else
-			return 0;
+		fw_name_dmcu = FIRMWARE_RAVEN_DMCU;
 		break;
 	default:
 		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
-- 
cgit v1.2.3-58-ga151