Merge tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux

Merge drm updates from Dave Airlie:
 "This is the main drm pull request for 4.8.

  I'm down with a cold at the moment so hopefully this isn't in too bad
  a state, I finished pulling stuff last week mostly (nouveau fixes just
  went in today), so only this message should be influenced by illness.
  Apologies to anyone who's major feature I missed :-)

  Core:
        Lockless GEM BO freeing
        Non-blocking atomic work
        Documentation changes (rst/sphinx)
        Prep for new fencing changes
        Simple display helpers
        Master/auth changes
        Register/unregister rework
        Loads of trivial patches/fixes.

  New stuff:
        ARM Mali display driver (not the 3D chip)
        sii902x RGB->HDMI bridge

  Panel:
        Support for new panels
        Improved backlight support

  Bridge:
        Convert ADV7511 to bridge driver
        ADV7533 support
        TC358767 (DSI/DPI to eDP) encoder chip support

  i915:
        BXT support enabled by default
        GVT-g infrastructure
        GuC command submission and fixes
        BXT workarounds
        SKL/BKL workarounds
        Demidlayering device registration
        Thundering herd fixes
        Missing pci ids
        Atomic updates

  amdgpu/radeon:
        ATPX improvements for better dGPU power control on PX systems
        New power features for CZ/BR/ST
        Pipelined BO moves and evictions in TTM
        GPU scheduler improvements
        GPU reset improvements
        Overclocking on dGPUs with amdgpu
        Polaris powermanagement enabled

  nouveau:
        GK20A/GM20B volt and clock improvements.
        Initial support for GP100/GP104 GPUs, GP104 will not yet support
        acceleration due to NVIDIA having not released firmware for them as of yet.

  exynos:
        Exynos5433 SoC with IOMMU support.

  vc4:
        Shader validation for branching

  imx-drm:
        Atomic mode setting conversion
        Reworked DMFC FIFO allocation
        External bridge support

  analogix-dp:
        RK3399 eDP support
        Lots of fixes.

  rockchip:
        Lots of small fixes.

  msm:
        DT bindings cleanups
        Shrinker and madvise support
        ASoC HDMI codec support

  tegra:
        Host1x driver cleanups
        SOR reworking for DP support
        Runtime PM support

  omapdrm:
        PLL enhancements
        Header refactoring
        Gamma table support

  arcgpu:
        Simulator support

  virtio-gpu:
        Atomic modesetting fixes.

  rcar-du:
        Misc fixes.

  mediatek:
        MT8173 HDMI support

  sti:
        ASOC HDMI codec support
        Minor fixes

  fsl-dcu:
        Suspend/resume support
        Bridge support

  amdkfd:
        Minor fixes.

  etnaviv:
        Enable GPU clock gating

  hisilicon:
        Vblank and other fixes"

* tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux: (1575 commits)
  drm/nouveau/gr/nv3x: fix instobj write offsets in gr setup
  drm/nouveau/acpi: fix lockup with PCIe runtime PM
  drm/nouveau/acpi: check for function 0x1B before using it
  drm/nouveau/acpi: return supported DSM functions
  drm/nouveau/acpi: ensure matching ACPI handle and supported functions
  drm/nouveau/fbcon: fix font width not divisible by 8
  drm/amd/powerplay: remove enable_clock_power_gatings_tasks from initialize and resume events
  drm/amd/powerplay: move clockgating to after ungating power in pp for uvd/vce
  drm/amdgpu: add query device id and revision id into system info entry at CGS
  drm/amdgpu: add new definition in bif header
  drm/amd/powerplay: rename smum header guards
  drm/amdgpu: enable UVD context buffer for older HW
  drm/amdgpu: fix default UVD context size
  drm/amdgpu: fix incorrect type of info_id
  drm/amdgpu: make amdgpu_cgs_call_acpi_method as static
  drm/amdgpu: comment out unused defaults_staturn_pro static const structure to fix the build
  drm/amdgpu: enable UVD VM only on polaris
  drm/amdgpu: increase timeout of IB test
  drm/amdgpu: add destroy session when generate VCE destroy msg.
  drm/amd: fix deadlock of job_list_lock V2
  ...

5 files changed, 61 insertions, 43 deletions

diff --git a/drivers/gpu/host1x/hw/cdma_hw.c b/drivers/gpu/host1x/hw/cdma_hw.c
index 305ea8f3382d..659c1bbfeeba 100644
--- a/drivers/gpu/host1x/hw/cdma_hw.c
+++ b/drivers/gpu/host1x/hw/cdma_hw.c
@@ -41,7 +41,7 @@ static void cdma_timeout_cpu_incr(struct host1x_cdma *cdma, u32 getptr,
 {
 	struct host1x *host1x = cdma_to_host1x(cdma);
 	struct push_buffer *pb = &cdma->push_buffer;
-	u32 i;
+	unsigned int i;
 
 	for (i = 0; i < syncpt_incrs; i++)
 		host1x_syncpt_incr(cdma->timeout.syncpt);
@@ -58,6 +58,7 @@ static void cdma_timeout_cpu_incr(struct host1x_cdma *cdma, u32 getptr,
 			&pb->phys, getptr);
 		getptr = (getptr + 8) & (pb->size_bytes - 1);
 	}
+
 	wmb();
 }
 
@@ -162,12 +163,14 @@ static void cdma_stop(struct host1x_cdma *cdma)
 	struct host1x_channel *ch = cdma_to_channel(cdma);
 
 	mutex_lock(&cdma->lock);
+
 	if (cdma->running) {
 		host1x_cdma_wait_locked(cdma, CDMA_EVENT_SYNC_QUEUE_EMPTY);
 		host1x_ch_writel(ch, HOST1X_CHANNEL_DMACTRL_DMASTOP,
 				 HOST1X_CHANNEL_DMACTRL);
 		cdma->running = false;
 	}
+
 	mutex_unlock(&cdma->lock);
 }
 
@@ -213,11 +216,11 @@ static void cdma_resume(struct host1x_cdma *cdma, u32 getptr)
 	u32 cmdproc_stop;
 
 	dev_dbg(host1x->dev,
-		"resuming channel (id %d, DMAGET restart = 0x%x)\n",
+		"resuming channel (id %u, DMAGET restart = 0x%x)\n",
 		ch->id, getptr);
 
 	cmdproc_stop = host1x_sync_readl(host1x, HOST1X_SYNC_CMDPROC_STOP);
-	cmdproc_stop &= ~(BIT(ch->id));
+	cmdproc_stop &= ~BIT(ch->id);
 	host1x_sync_writel(host1x, cmdproc_stop, HOST1X_SYNC_CMDPROC_STOP);
 
 	cdma->torndown = false;
@@ -231,14 +234,11 @@ static void cdma_resume(struct host1x_cdma *cdma, u32 getptr)
  */
 static void cdma_timeout_handler(struct work_struct *work)
 {
+	u32 prev_cmdproc, cmdproc_stop, syncpt_val;
 	struct host1x_cdma *cdma;
 	struct host1x *host1x;
 	struct host1x_channel *ch;
 
-	u32 syncpt_val;
-
-	u32 prev_cmdproc, cmdproc_stop;
-
 	cdma = container_of(to_delayed_work(work), struct host1x_cdma,
 			    timeout.wq);
 	host1x = cdma_to_host1x(cdma);
@@ -277,9 +277,9 @@ static void cdma_timeout_handler(struct work_struct *work)
 		return;
 	}
 
-	dev_warn(host1x->dev, "%s: timeout: %d (%s), HW thresh %d, done %d\n",
-		__func__, cdma->timeout.syncpt->id, cdma->timeout.syncpt->name,
-		syncpt_val, cdma->timeout.syncpt_val);
+	dev_warn(host1x->dev, "%s: timeout: %u (%s), HW thresh %d, done %d\n",
+		 __func__, cdma->timeout.syncpt->id, cdma->timeout.syncpt->name,
+		 syncpt_val, cdma->timeout.syncpt_val);
 
 	/* stop HW, resetting channel/module */
 	host1x_hw_cdma_freeze(host1x, cdma);
@@ -291,7 +291,7 @@ static void cdma_timeout_handler(struct work_struct *work)
 /*
  * Init timeout resources
  */
-static int cdma_timeout_init(struct host1x_cdma *cdma, u32 syncpt_id)
+static int cdma_timeout_init(struct host1x_cdma *cdma, unsigned int syncpt)
 {
 	INIT_DELAYED_WORK(&cdma->timeout.wq, cdma_timeout_handler);
 	cdma->timeout.initialized = true;
@@ -306,6 +306,7 @@ static void cdma_timeout_destroy(struct host1x_cdma *cdma)
 {
 	if (cdma->timeout.initialized)
 		cancel_delayed_work(&cdma->timeout.wq);
+
 	cdma->timeout.initialized = false;
 }
 
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 946c332c3906..5e8df78b7acd 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -46,6 +46,7 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo,
 		 */
 		for (i = 0; i < words; i += TRACE_MAX_LENGTH) {
 			u32 num_words = min(words - i, TRACE_MAX_LENGTH);
+
 			offset += i * sizeof(u32);
 
 			trace_host1x_cdma_push_gather(dev_name(dev), bo,
@@ -66,6 +67,7 @@ static void submit_gathers(struct host1x_job *job)
 		struct host1x_job_gather *g = &job->gathers[i];
 		u32 op1 = host1x_opcode_gather(g->words);
 		u32 op2 = g->base + g->offset;
+
 		trace_write_gather(cdma, g->bo, g->offset, op1 & 0xffff);
 		host1x_cdma_push(cdma, op1, op2);
 	}
@@ -75,7 +77,8 @@ static inline void synchronize_syncpt_base(struct host1x_job *job)
 {
 	struct host1x *host = dev_get_drvdata(job->channel->dev->parent);
 	struct host1x_syncpt *sp = host->syncpt + job->syncpt_id;
-	u32 id, value;
+	unsigned int id;
+	u32 value;
 
 	value = host1x_syncpt_read_max(sp);
 	id = sp->base->id;
diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c
index cc3f1825c735..7a4a3286e4a7 100644
--- a/drivers/gpu/host1x/hw/debug_hw.c
+++ b/drivers/gpu/host1x/hw/debug_hw.c
@@ -40,8 +40,7 @@ enum {
 
 static unsigned int show_channel_command(struct output *o, u32 val)
 {
-	unsigned mask;
-	unsigned subop;
+	unsigned int mask, subop;
 
 	switch (val >> 28) {
 	case HOST1X_OPCODE_SETCLASS:
@@ -51,12 +50,11 @@ static unsigned int show_channel_command(struct output *o, u32 val)
 					    val >> 6 & 0x3ff,
 					    val >> 16 & 0xfff, mask);
 			return hweight8(mask);
-		} else {
-			host1x_debug_output(o, "SETCL(class=%03x)\n",
-					    val >> 6 & 0x3ff);
-			return 0;
 		}
 
+		host1x_debug_output(o, "SETCL(class=%03x)\n", val >> 6 & 0x3ff);
+		return 0;
+
 	case HOST1X_OPCODE_INCR:
 		host1x_debug_output(o, "INCR(offset=%03x, [",
 				    val >> 16 & 0xfff);
@@ -143,7 +141,8 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma)
 	struct host1x_job *job;
 
 	list_for_each_entry(job, &cdma->sync_queue, list) {
-		int i;
+		unsigned int i;
+
 		host1x_debug_output(o, "\n%p: JOB, syncpt_id=%d, syncpt_val=%d, first_get=%08x, timeout=%d num_slots=%d, num_handles=%d\n",
 				    job, job->syncpt_id, job->syncpt_end,
 				    job->first_get, job->timeout,
@@ -190,7 +189,7 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 	cbread = host1x_sync_readl(host, HOST1X_SYNC_CBREAD(ch->id));
 	cbstat = host1x_sync_readl(host, HOST1X_SYNC_CBSTAT(ch->id));
 
-	host1x_debug_output(o, "%d-%s: ", ch->id, dev_name(ch->dev));
+	host1x_debug_output(o, "%u-%s: ", ch->id, dev_name(ch->dev));
 
 	if (HOST1X_CHANNEL_DMACTRL_DMASTOP_V(dmactrl) ||
 	    !ch->cdma.push_buffer.mapped) {
@@ -200,14 +199,13 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 
 	if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) == HOST1X_CLASS_HOST1X &&
 	    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
-	    HOST1X_UCLASS_WAIT_SYNCPT)
+			HOST1X_UCLASS_WAIT_SYNCPT)
 		host1x_debug_output(o, "waiting on syncpt %d val %d\n",
 				    cbread >> 24, cbread & 0xffffff);
 	else if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) ==
-	   HOST1X_CLASS_HOST1X &&
-	   HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
-	   HOST1X_UCLASS_WAIT_SYNCPT_BASE) {
-
+				HOST1X_CLASS_HOST1X &&
+		 HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
+				HOST1X_UCLASS_WAIT_SYNCPT_BASE) {
 		base = (cbread >> 16) & 0xff;
 		baseval =
 			host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_BASE(base));
@@ -236,7 +234,7 @@ static void host1x_debug_show_channel_fifo(struct host1x *host,
 	u32 val, rd_ptr, wr_ptr, start, end;
 	unsigned int data_count = 0;
 
-	host1x_debug_output(o, "%d: fifo:\n", ch->id);
+	host1x_debug_output(o, "%u: fifo:\n", ch->id);
 
 	val = host1x_ch_readl(ch, HOST1X_CHANNEL_FIFOSTAT);
 	host1x_debug_output(o, "FIFOSTAT %08x\n", val);
@@ -290,20 +288,22 @@ static void host1x_debug_show_channel_fifo(struct host1x *host,
 
 static void host1x_debug_show_mlocks(struct host1x *host, struct output *o)
 {
-	int i;
+	unsigned int i;
 
 	host1x_debug_output(o, "---- mlocks ----\n");
+
 	for (i = 0; i < host1x_syncpt_nb_mlocks(host); i++) {
 		u32 owner =
 			host1x_sync_readl(host, HOST1X_SYNC_MLOCK_OWNER(i));
 		if (HOST1X_SYNC_MLOCK_OWNER_CH_OWNS_V(owner))
-			host1x_debug_output(o, "%d: locked by channel %d\n",
+			host1x_debug_output(o, "%u: locked by channel %u\n",
 				i, HOST1X_SYNC_MLOCK_OWNER_CHID_V(owner));
 		else if (HOST1X_SYNC_MLOCK_OWNER_CPU_OWNS_V(owner))
-			host1x_debug_output(o, "%d: locked by cpu\n", i);
+			host1x_debug_output(o, "%u: locked by cpu\n", i);
 		else
-			host1x_debug_output(o, "%d: unlocked\n", i);
+			host1x_debug_output(o, "%u: unlocked\n", i);
 	}
+
 	host1x_debug_output(o, "\n");
 }
 
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index e1e31e9e67cd..dacb8009a605 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -38,14 +38,14 @@ static void host1x_intr_syncpt_handle(struct host1x_syncpt *syncpt)
 	host1x_sync_writel(host, BIT_MASK(id),
 		HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(BIT_WORD(id)));
 
-	queue_work(host->intr_wq, &syncpt->intr.work);
+	schedule_work(&syncpt->intr.work);
 }
 
 static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 {
 	struct host1x *host = dev_id;
 	unsigned long reg;
-	int i, id;
+	unsigned int i, id;
 
 	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
 		reg = host1x_sync_readl(host,
@@ -62,7 +62,7 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 
 static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 {
-	u32 i;
+	unsigned int i;
 
 	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) {
 		host1x_sync_writel(host, 0xffffffffu,
@@ -72,10 +72,12 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 	}
 }
 
-static int _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
-	void (*syncpt_thresh_work)(struct work_struct *))
+static int
+_host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
+			    void (*syncpt_thresh_work)(struct work_struct *))
 {
-	int i, err;
+	unsigned int i;
+	int err;
 
 	host1x_hw_intr_disable_all_syncpt_intrs(host);
 
@@ -106,18 +108,21 @@ static int _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
 }
 
 static void _host1x_intr_set_syncpt_threshold(struct host1x *host,
-	u32 id, u32 thresh)
+					      unsigned int id,
+					      u32 thresh)
 {
 	host1x_sync_writel(host, thresh, HOST1X_SYNC_SYNCPT_INT_THRESH(id));
 }
 
-static void _host1x_intr_enable_syncpt_intr(struct host1x *host, u32 id)
+static void _host1x_intr_enable_syncpt_intr(struct host1x *host,
+					    unsigned int id)
 {
 	host1x_sync_writel(host, BIT_MASK(id),
 		HOST1X_SYNC_SYNCPT_THRESH_INT_ENABLE_CPU0(BIT_WORD(id)));
 }
 
-static void _host1x_intr_disable_syncpt_intr(struct host1x *host, u32 id)
+static void _host1x_intr_disable_syncpt_intr(struct host1x *host,
+					     unsigned int id)
 {
 	host1x_sync_writel(host, BIT_MASK(id),
 		HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(BIT_WORD(id)));
@@ -127,8 +132,13 @@ static void _host1x_intr_disable_syncpt_intr(struct host1x *host, u32 id)
 
 static int _host1x_free_syncpt_irq(struct host1x *host)
 {
+	unsigned int i;
+
 	devm_free_irq(host->dev, host->intr_syncpt_irq, host);
-	flush_workqueue(host->intr_wq);
+
+	for (i = 0; i < host->info->nb_pts; i++)
+		cancel_work_sync(&host->syncpt[i].intr.work);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/host1x/hw/syncpt_hw.c b/drivers/gpu/host1x/hw/syncpt_hw.c
index 56e85395ac24..c93f74fcce72 100644
--- a/drivers/gpu/host1x/hw/syncpt_hw.c
+++ b/drivers/gpu/host1x/hw/syncpt_hw.c
@@ -26,8 +26,9 @@
  */
 static void syncpt_restore(struct host1x_syncpt *sp)
 {
+	u32 min = host1x_syncpt_read_min(sp);
 	struct host1x *host = sp->host;
-	int min = host1x_syncpt_read_min(sp);
+
 	host1x_sync_writel(host, min, HOST1X_SYNC_SYNCPT(sp->id));
 }
 
@@ -37,6 +38,7 @@ static void syncpt_restore(struct host1x_syncpt *sp)
 static void syncpt_restore_wait_base(struct host1x_syncpt *sp)
 {
 	struct host1x *host = sp->host;
+
 	host1x_sync_writel(host, sp->base_val,
 			   HOST1X_SYNC_SYNCPT_BASE(sp->id));
 }
@@ -47,6 +49,7 @@ static void syncpt_restore_wait_base(struct host1x_syncpt *sp)
 static void syncpt_read_wait_base(struct host1x_syncpt *sp)
 {
 	struct host1x *host = sp->host;
+
 	sp->base_val =
 		host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_BASE(sp->id));
 }
@@ -85,6 +88,7 @@ static int syncpt_cpu_incr(struct host1x_syncpt *sp)
 	if (!host1x_syncpt_client_managed(sp) &&
 	    host1x_syncpt_idle(sp))
 		return -EINVAL;
+
 	host1x_sync_writel(host, BIT_MASK(sp->id),
 			   HOST1X_SYNC_SYNCPT_CPU_INCR(reg_offset));
 	wmb();
@@ -95,10 +99,10 @@ static int syncpt_cpu_incr(struct host1x_syncpt *sp)
 /* remove a wait pointed to by patch_addr */
 static int syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr)
 {
-	u32 override = host1x_class_host_wait_syncpt(
-		HOST1X_SYNCPT_RESERVED, 0);
+	u32 override = host1x_class_host_wait_syncpt(HOST1X_SYNCPT_RESERVED, 0);
 
 	*((u32 *)patch_addr) = override;
+
 	return 0;
 }