Merge tag 'drm-intel-next-fixes-2016-12-22' of git://anongit.freedesktop.org/git/drm-intel into drm-fixes

First set of i915 fixes for code in next.

* tag 'drm-intel-next-fixes-2016-12-22' of git://anongit.freedesktop.org/git/drm-intel:
drm/i915: skip the first 4k of stolen memory on everything >= gen8
drm/i915: Fallback to single PAGE_SIZE segments for DMA remapping
drm/i915: Fix use after free in logical_render_ring_init
drm/i915: disable PSR by default on HSW/BDW
drm/i915: Fix setting of boost freq tunable
drm/i915: tune down the fast link training vs boot fail
drm/i915: Reorder phys backing storage release
drm/i915/gen9: Fix PCODE polling during SAGV disabling
drm/i915/gen9: Fix PCODE polling during CDCLK change notification
drm/i915/dsi: Fix chv_exec_gpio disabling the GPIOs it is setting
drm/i915/dsi: Fix swapping of MIPI_SEQ_DEASSERT_RESET / MIPI_SEQ_ASSERT_RESET
drm/i915/dsi: Do not clear DPOUNIT_CLOCK_GATE_DISABLE from vlv_init_display_clock_gating
drm/i915: drop the struct_mutex when wedged or trying to reset

drivers/gpu/drm/i915/i915_drv.h

···
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val);
+int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
+		      u32 reply_mask, u32 reply, int timeout_base_ms);
 
 /* intel_sideband.c */
 u32 vlv_punit_read(struct drm_i915_private *dev_priv, u32 addr);

drivers/gpu/drm/i915/i915_gem.c

···
 i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 {
 	struct address_space *mapping = obj->base.filp->f_mapping;
-	char *vaddr = obj->phys_handle->vaddr;
+	drm_dma_handle_t *phys;
 	struct sg_table *st;
 	struct scatterlist *sg;
+	char *vaddr;
 	int i;
 
 	if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj)))
 		return ERR_PTR(-EINVAL);
 
+	/* Always aligning to the object size, allows a single allocation
+	 * to handle all possible callers, and given typical object sizes,
+	 * the alignment of the buddy allocation will naturally match.
+	 */
+	phys = drm_pci_alloc(obj->base.dev,
+			     obj->base.size,
+			     roundup_pow_of_two(obj->base.size));
+	if (!phys)
+		return ERR_PTR(-ENOMEM);
+
+	vaddr = phys->vaddr;
 	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
 		struct page *page;
 		char *src;
 
 		page = shmem_read_mapping_page(mapping, i);
-		if (IS_ERR(page))
-			return ERR_CAST(page);
+		if (IS_ERR(page)) {
+			st = ERR_CAST(page);
+			goto err_phys;
+		}
 
 		src = kmap_atomic(page);
 		memcpy(vaddr, src, PAGE_SIZE);
···
 	i915_gem_chipset_flush(to_i915(obj->base.dev));
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (st == NULL)
-		return ERR_PTR(-ENOMEM);
+	if (!st) {
+		st = ERR_PTR(-ENOMEM);
+		goto err_phys;
+	}
 
 	if (sg_alloc_table(st, 1, GFP_KERNEL)) {
 		kfree(st);
-		return ERR_PTR(-ENOMEM);
+		st = ERR_PTR(-ENOMEM);
+		goto err_phys;
 	}
 
 	sg = st->sgl;
 	sg->offset = 0;
 	sg->length = obj->base.size;
 
-	sg_dma_address(sg) = obj->phys_handle->busaddr;
+	sg_dma_address(sg) = phys->busaddr;
 	sg_dma_len(sg) = obj->base.size;
 
+	obj->phys_handle = phys;
+	return st;
+
+err_phys:
+	drm_pci_free(obj->base.dev, phys);
 	return st;
 }
 
···
 
 	sg_free_table(pages);
 	kfree(pages);
+
+	drm_pci_free(obj->base.dev, obj->phys_handle);
 }
 
 static void
 i915_gem_object_release_phys(struct drm_i915_gem_object *obj)
 {
-	drm_pci_free(obj->base.dev, obj->phys_handle);
 	i915_gem_object_unpin_pages(obj);
 }
 
···
 i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
 			    int align)
 {
-	drm_dma_handle_t *phys;
 	int ret;
 
-	if (obj->phys_handle) {
-		if ((unsigned long)obj->phys_handle->vaddr & (align -1))
-			return -EBUSY;
+	if (align > obj->base.size)
+		return -EINVAL;
 
+	if (obj->ops == &i915_gem_phys_ops)
 		return 0;
-	}
 
 	if (obj->mm.madv != I915_MADV_WILLNEED)
 		return -EFAULT;
···
 	if (obj->mm.pages)
 		return -EBUSY;
 
-	/* create a new object */
-	phys = drm_pci_alloc(obj->base.dev, obj->base.size, align);
-	if (!phys)
-		return -ENOMEM;
-
-	obj->phys_handle = phys;
 	obj->ops = &i915_gem_phys_ops;
 
 	return i915_gem_object_pin_pages(obj);
···
 i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	int page_count, i;
+	const unsigned long page_count = obj->base.size / PAGE_SIZE;
+	unsigned long i;
 	struct address_space *mapping;
 	struct sg_table *st;
 	struct scatterlist *sg;
···
 	if (st == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	page_count = obj->base.size / PAGE_SIZE;
+rebuild_st:
 	if (sg_alloc_table(st, page_count, GFP_KERNEL)) {
 		kfree(st);
 		return ERR_PTR(-ENOMEM);
···
 	i915_sg_trim(st);
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
-	if (ret)
-		goto err_pages;
+	if (ret) {
+		/* DMA remapping failed? One possible cause is that
+		 * it could not reserve enough large entries, asking
+		 * for PAGE_SIZE chunks instead may be helpful.
+		 */
+		if (max_segment > PAGE_SIZE) {
+			for_each_sgt_page(page, sgt_iter, st)
+				put_page(page);
+			sg_free_table(st);
+
+			max_segment = PAGE_SIZE;
+			goto rebuild_st;
+		} else {
+			dev_warn(&dev_priv->drm.pdev->dev,
+				 "Failed to DMA remap %lu pages\n",
+				 page_count);
+			goto err_pages;
+		}
+	}
 
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_do_bit_17_swizzle(obj, st);

drivers/gpu/drm/i915/i915_gem_stolen.c

···
 		return -ENODEV;
 
 	/* See the comment at the drm_mm_init() call for more about this check.
-	 * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete)
+	 * WaSkipStolenMemoryFirstPage:bdw+ (incomplete)
 	 */
-	if (start < 4096 && (IS_GEN8(dev_priv) ||
-			     IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)))
+	if (start < 4096 && INTEL_GEN(dev_priv) >= 8)
 		start = 4096;
 
 	mutex_lock(&dev_priv->mm.stolen_lock);

drivers/gpu/drm/i915/i915_sysfs.c

···
 
 static DEVICE_ATTR(gt_act_freq_mhz, S_IRUGO, gt_act_freq_mhz_show, NULL);
 static DEVICE_ATTR(gt_cur_freq_mhz, S_IRUGO, gt_cur_freq_mhz_show, NULL);
-static DEVICE_ATTR(gt_boost_freq_mhz, S_IRUGO, gt_boost_freq_mhz_show, gt_boost_freq_mhz_store);
+static DEVICE_ATTR(gt_boost_freq_mhz, S_IRUGO | S_IWUSR, gt_boost_freq_mhz_show, gt_boost_freq_mhz_store);
 static DEVICE_ATTR(gt_max_freq_mhz, S_IRUGO | S_IWUSR, gt_max_freq_mhz_show, gt_max_freq_mhz_store);
 static DEVICE_ATTR(gt_min_freq_mhz, S_IRUGO | S_IWUSR, gt_min_freq_mhz_show, gt_min_freq_mhz_store);
 

drivers/gpu/drm/i915/intel_bios.h

···
 	u16 t11_t12;
 } __packed;
 
-/* MIPI Sequence Block definitions */
+/*
+ * MIPI Sequence Block definitions
+ *
+ * Note the VBT spec has AssertReset / DeassertReset swapped from their
+ * usual naming, we use the proper names here to avoid confusion when
+ * reading the code.
+ */
 enum mipi_seq {
 	MIPI_SEQ_END = 0,
-	MIPI_SEQ_ASSERT_RESET,
+	MIPI_SEQ_DEASSERT_RESET,	/* Spec says MipiAssertResetPin */
 	MIPI_SEQ_INIT_OTP,
 	MIPI_SEQ_DISPLAY_ON,
 	MIPI_SEQ_DISPLAY_OFF,
-	MIPI_SEQ_DEASSERT_RESET,
+	MIPI_SEQ_ASSERT_RESET,		/* Spec says MipiDeassertResetPin */
 	MIPI_SEQ_BACKLIGHT_ON,		/* sequence block v2+ */
 	MIPI_SEQ_BACKLIGHT_OFF,		/* sequence block v2+ */
 	MIPI_SEQ_TEAR_ON,		/* sequence block v2+ */

drivers/gpu/drm/i915/intel_display.c

···
 	dev_priv->cdclk_pll.vco = 0;
 }
 
-static bool skl_cdclk_pcu_ready(struct drm_i915_private *dev_priv)
-{
-	int ret;
-	u32 val;
-
-	/* inform PCU we want to change CDCLK */
-	val = SKL_CDCLK_PREPARE_FOR_CHANGE;
-	mutex_lock(&dev_priv->rps.hw_lock);
-	ret = sandybridge_pcode_read(dev_priv, SKL_PCODE_CDCLK_CONTROL, &val);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-
-	return ret == 0 && (val & SKL_CDCLK_READY_FOR_CHANGE);
-}
-
-static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv)
-{
-	return _wait_for(skl_cdclk_pcu_ready(dev_priv), 3000, 10) == 0;
-}
-
 static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco)
 {
 	u32 freq_select, pcu_ack;
+	int ret;
 
 	WARN_ON((cdclk == 24000) != (vco == 0));
 
 	DRM_DEBUG_DRIVER("Changing CDCLK to %d kHz (VCO %d kHz)\n", cdclk, vco);
 
-	if (!skl_cdclk_wait_for_pcu_ready(dev_priv)) {
-		DRM_ERROR("failed to inform PCU about cdclk change\n");
+	mutex_lock(&dev_priv->rps.hw_lock);
+	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+				SKL_CDCLK_PREPARE_FOR_CHANGE,
+				SKL_CDCLK_READY_FOR_CHANGE,
+				SKL_CDCLK_READY_FOR_CHANGE, 3);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	if (ret) {
+		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
+			  ret);
 		return;
 	}
 

drivers/gpu/drm/i915/intel_dp.c

···
 		return;
 
 	/* FIXME: we need to synchronize this sort of stuff with hardware
-	 * readout */
-	if (WARN_ON_ONCE(!intel_dp->lane_count))
+	 * readout. Currently fast link training doesn't work on boot-up. */
+	if (!intel_dp->lane_count)
 		return;
 
 	/* if link training is requested we should perform it always */

drivers/gpu/drm/i915/intel_dsi_panel_vbt.c

···
 	mutex_lock(&dev_priv->sb_lock);
 	vlv_iosf_sb_write(dev_priv, port, cfg1, 0);
 	vlv_iosf_sb_write(dev_priv, port, cfg0,
-			  CHV_GPIO_GPIOCFG_GPO | CHV_GPIO_GPIOTXSTATE(value));
+			  CHV_GPIO_GPIOEN | CHV_GPIO_GPIOCFG_GPO |
+			  CHV_GPIO_GPIOTXSTATE(value));
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
···
  */
 
 static const char * const seq_name[] = {
-	[MIPI_SEQ_ASSERT_RESET] = "MIPI_SEQ_ASSERT_RESET",
+	[MIPI_SEQ_DEASSERT_RESET] = "MIPI_SEQ_DEASSERT_RESET",
 	[MIPI_SEQ_INIT_OTP] = "MIPI_SEQ_INIT_OTP",
 	[MIPI_SEQ_DISPLAY_ON] = "MIPI_SEQ_DISPLAY_ON",
 	[MIPI_SEQ_DISPLAY_OFF]  = "MIPI_SEQ_DISPLAY_OFF",
-	[MIPI_SEQ_DEASSERT_RESET] = "MIPI_SEQ_DEASSERT_RESET",
+	[MIPI_SEQ_ASSERT_RESET] = "MIPI_SEQ_ASSERT_RESET",
 	[MIPI_SEQ_BACKLIGHT_ON] = "MIPI_SEQ_BACKLIGHT_ON",
 	[MIPI_SEQ_BACKLIGHT_OFF] = "MIPI_SEQ_BACKLIGHT_OFF",
 	[MIPI_SEQ_TEAR_ON] = "MIPI_SEQ_TEAR_ON",

drivers/gpu/drm/i915/intel_lrc.c

···
 			  ret);
 	}
 
-	ret = logical_ring_init(engine);
-	if (ret) {
-		lrc_destroy_wa_ctx_obj(engine);
-	}
-
-	return ret;
+	return logical_ring_init(engine);
 }
 
 int logical_xcs_ring_init(struct intel_engine_cs *engine)

drivers/gpu/drm/i915/intel_pm.c

···
 	return 0;
 }
 
-static int
-intel_do_sagv_disable(struct drm_i915_private *dev_priv)
-{
-	int ret;
-	uint32_t temp = GEN9_SAGV_DISABLE;
-
-	ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
-				     &temp);
-	if (ret)
-		return ret;
-	else
-		return temp & GEN9_SAGV_IS_DISABLED;
-}
-
 int
 intel_disable_sagv(struct drm_i915_private *dev_priv)
 {
-	int ret, result;
+	int ret;
 
 	if (!intel_has_sagv(dev_priv))
 		return 0;
···
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	/* bspec says to keep retrying for at least 1 ms */
-	ret = wait_for(result = intel_do_sagv_disable(dev_priv), 1);
+	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+				GEN9_SAGV_DISABLE,
+				GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED,
+				1);
 	mutex_unlock(&dev_priv->rps.hw_lock);
-
-	if (ret == -ETIMEDOUT) {
-		DRM_ERROR("Request to disable SAGV timed out\n");
-		return -ETIMEDOUT;
-	}
 
 	/*
 	 * Some skl systems, pre-release machines in particular,
 	 * don't actually have an SAGV.
 	 */
-	if (IS_SKYLAKE(dev_priv) && result == -ENXIO) {
+	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
 		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
 		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
-	} else if (result < 0) {
-		DRM_ERROR("Failed to disable the SAGV\n");
-		return result;
+	} else if (ret < 0) {
+		DRM_ERROR("Failed to disable the SAGV (%d)\n", ret);
+		return ret;
 	}
 
 	dev_priv->sagv_status = I915_SAGV_DISABLED;
···
 	}
 
 	return 0;
+}
+
+static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
+				  u32 request, u32 reply_mask, u32 reply,
+				  u32 *status)
+{
+	u32 val = request;
+
+	*status = sandybridge_pcode_read(dev_priv, mbox, &val);
+
+	return *status || ((val & reply_mask) == reply);
+}
+
+/**
+ * skl_pcode_request - send PCODE request until acknowledgment
+ * @dev_priv: device private
+ * @mbox: PCODE mailbox ID the request is targeted for
+ * @request: request ID
+ * @reply_mask: mask used to check for request acknowledgment
+ * @reply: value used to check for request acknowledgment
+ * @timeout_base_ms: timeout for polling with preemption enabled
+ *
+ * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
+ * reports an error or an overall timeout of @timeout_base_ms+10 ms expires.
+ * The request is acknowledged once the PCODE reply dword equals @reply after
+ * applying @reply_mask. Polling is first attempted with preemption enabled
+ * for @timeout_base_ms and if this times out for another 10 ms with
+ * preemption disabled.
+ *
+ * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
+ * other error as reported by PCODE.
+ */
+int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
+		      u32 reply_mask, u32 reply, int timeout_base_ms)
+{
+	u32 status;
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+#define COND skl_pcode_try_request(dev_priv, mbox, request, reply_mask, reply, \
+				   &status)
+
+	/*
+	 * Prime the PCODE by doing a request first. Normally it guarantees
+	 * that a subsequent request, at most @timeout_base_ms later, succeeds.
+	 * _wait_for() doesn't guarantee when its passed condition is evaluated
+	 * first, so send the first request explicitly.
+	 */
+	if (COND) {
+		ret = 0;
+		goto out;
+	}
+	ret = _wait_for(COND, timeout_base_ms * 1000, 10);
+	if (!ret)
+		goto out;
+
+	/*
+	 * The above can time out if the number of requests was low (2 in the
+	 * worst case) _and_ PCODE was busy for some reason even after a
+	 * (queued) request and @timeout_base_ms delay. As a workaround retry
+	 * the poll with preemption disabled to maximize the number of
+	 * requests. Increase the timeout from @timeout_base_ms to 10ms to
+	 * account for interrupts that could reduce the number of these
+	 * requests.
+	 */
+	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
+	WARN_ON_ONCE(timeout_base_ms > 3);
+	preempt_disable();
+	ret = wait_for_atomic(COND, 10);
+	preempt_enable();
+
+out:
+	return ret ? ret : status;
+#undef COND
 }
 
 static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val)

drivers/gpu/drm/i915/intel_psr.c

···
 	dev_priv->psr_mmio_base = IS_HASWELL(dev_priv) ?
 		HSW_EDP_PSR_BASE : BDW_EDP_PSR_BASE;
 
-	/* Per platform default */
-	if (i915.enable_psr == -1) {
-		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			i915.enable_psr = 1;
-		else
-			i915.enable_psr = 0;
-	}
+	/* Per platform default: all disabled. */
+	if (i915.enable_psr == -1)
+		i915.enable_psr = 0;
 
 	/* Set link_standby x link_off defaults */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))

drivers/gpu/drm/i915/intel_runtime_pm.c

···
 
 static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv)
 {
-	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
+	u32 val;
+
+	/*
+	 * On driver load, a pipe may be active and driving a DSI display.
+	 * Preserve DPOUNIT_CLOCK_GATE_DISABLE to avoid the pipe getting stuck
+	 * (and never recovering) in this case. intel_dsi_post_disable() will
+	 * clear it when we turn off the display.
+	 */
+	val = I915_READ(DSPCLK_GATE_D);
+	val &= DPOUNIT_CLOCK_GATE_DISABLE;
+	val |= VRHUNIT_CLOCK_GATE_DISABLE;
+	I915_WRITE(DSPCLK_GATE_D, val);
 
 	/*
 	 * Disable trickle feed and enable pnd deadline calculation