Merge tag 'drm-fixes-2019-06-21' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Just catching up on the week since back from holidays, everything
  seems quite sane.

  core:
   - copy_to_user fix for really legacy codepaths.

  vmwgfx:
   - two dma fixes
   - one virt hw interaction fix

  i915:
   - modesetting fix
   - gvt fix

  panfrost:
   - BO unmapping fix

  imx:
   - image converter fixes"

* tag 'drm-fixes-2019-06-21' of git://anongit.freedesktop.org/drm/drm:
  drm/i915: Don't clobber M/N values during fastset check
  drm: return -EFAULT if copy_to_user() fails
  drm/panfrost: Make sure a BO is only unmapped when appropriate
  drm/i915/gvt: ignore unexpected pvinfo write
  gpu: ipu-v3: image-convert: Fix image downsize coefficients
  gpu: ipu-v3: image-convert: Fix input bytesperline for packed formats
  gpu: ipu-v3: image-convert: Fix input bytesperline width/height align
  drm/vmwgfx: fix a warning due to missing dma_parms
  drm/vmwgfx: Honor the sg list segment size limitation
  drm/vmwgfx: Use the backdoor port if the HB port is not available

11 files changed, 209 insertions, 65 deletions

diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index bfc419ed9d6c..ceca79b1468d 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -1340,7 +1340,10 @@ static int copy_one_buf(void *data, int count, struct drm_buf_entry *from)
 				 .size = from->buf_size,
 				 .low_mark = from->low_mark,
 				 .high_mark = from->high_mark};
-	return copy_to_user(to, &v, offsetof(struct drm_buf_desc, flags));
+
+	if (copy_to_user(to, &v, offsetof(struct drm_buf_desc, flags)))
+		return -EFAULT;
+	return 0;
 }
 
 int drm_legacy_infobufs(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index 374b372da58a..3972ebe48463 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -375,7 +375,10 @@ static int copy_one_buf32(void *data, int count, struct drm_buf_entry *from)
 			      .size = from->buf_size,
 			      .low_mark = from->low_mark,
 			      .high_mark = from->high_mark};
-	return copy_to_user(to + count, &v, offsetof(drm_buf_desc32_t, flags));
+
+	if (copy_to_user(to + count, &v, offsetof(drm_buf_desc32_t, flags)))
+		return -EFAULT;
+	return 0;
 }
 
 static int drm_legacy_infobufs32(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index a6ade66349bd..25f78196b964 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1254,18 +1254,15 @@ static int send_display_ready_uevent(struct intel_vgpu *vgpu, int ready)
 static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	u32 data;
-	int ret;
-
-	write_vreg(vgpu, offset, p_data, bytes);
-	data = vgpu_vreg(vgpu, offset);
+	u32 data = *(u32 *)p_data;
+	bool invalid_write = false;
 
 	switch (offset) {
 	case _vgtif_reg(display_ready):
 		send_display_ready_uevent(vgpu, data ? 1 : 0);
 		break;
 	case _vgtif_reg(g2v_notify):
-		ret = handle_g2v_notification(vgpu, data);
+		handle_g2v_notification(vgpu, data);
 		break;
 	/* add xhot and yhot to handled list to avoid error log */
 	case _vgtif_reg(cursor_x_hot):
@@ -1282,13 +1279,19 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	case _vgtif_reg(execlist_context_descriptor_hi):
 		break;
 	case _vgtif_reg(rsv5[0])..._vgtif_reg(rsv5[3]):
+		invalid_write = true;
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_INSUFFICIENT_RESOURCE);
 		break;
 	default:
+		invalid_write = true;
 		gvt_vgpu_err("invalid pvinfo write offset %x bytes %x data %x\n",
 				offset, bytes, data);
 		break;
 	}
+
+	if (!invalid_write)
+		write_vreg(vgpu, offset, p_data, bytes);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b69440cf41ea..75105a2c59ea 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12005,9 +12005,6 @@ intel_compare_link_m_n(const struct intel_link_m_n *m_n,
 			      m2_n2->gmch_m, m2_n2->gmch_n, !adjust) &&
 	    intel_compare_m_n(m_n->link_m, m_n->link_n,
 			      m2_n2->link_m, m2_n2->link_n, !adjust)) {
-		if (adjust)
-			*m2_n2 = *m_n;
-
 		return true;
 	}
 
@@ -13149,6 +13146,33 @@ static int calc_watermark_data(struct intel_atomic_state *state)
 	return 0;
 }
 
+static void intel_crtc_check_fastset(struct intel_crtc_state *old_crtc_state,
+				     struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *dev_priv =
+		to_i915(new_crtc_state->base.crtc->dev);
+
+	if (!intel_pipe_config_compare(dev_priv, old_crtc_state,
+				       new_crtc_state, true))
+		return;
+
+	new_crtc_state->base.mode_changed = false;
+	new_crtc_state->update_pipe = true;
+
+	/*
+	 * If we're not doing the full modeset we want to
+	 * keep the current M/N values as they may be
+	 * sufficiently different to the computed values
+	 * to cause problems.
+	 *
+	 * FIXME: should really copy more fuzzy state here
+	 */
+	new_crtc_state->fdi_m_n = old_crtc_state->fdi_m_n;
+	new_crtc_state->dp_m_n = old_crtc_state->dp_m_n;
+	new_crtc_state->dp_m2_n2 = old_crtc_state->dp_m2_n2;
+	new_crtc_state->has_drrs = old_crtc_state->has_drrs;
+}
+
 /**
  * intel_atomic_check - validate state object
  * @dev: drm device
@@ -13197,12 +13221,8 @@ static int intel_atomic_check(struct drm_device *dev,
 			return ret;
 		}
 
-		if (intel_pipe_config_compare(dev_priv,
-					to_intel_crtc_state(old_crtc_state),
-					pipe_config, true)) {
-			crtc_state->mode_changed = false;
-			pipe_config->update_pipe = true;
-		}
+		intel_crtc_check_fastset(to_intel_crtc_state(old_crtc_state),
+					 pipe_config);
 
 		if (needs_modeset(crtc_state))
 			any_ms = true;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index a5528a360ef4..97d64ceedbb4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -19,7 +19,8 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj)
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	struct panfrost_device *pfdev = obj->dev->dev_private;
 
-	panfrost_mmu_unmap(bo);
+	if (bo->is_mapped)
+		panfrost_mmu_unmap(bo);
 
 	spin_lock(&pfdev->mm_lock);
 	drm_mm_remove_node(&bo->node);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index 045000eb5fcf..6dbcaba020fc 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -11,6 +11,7 @@ struct panfrost_gem_object {
 	struct drm_gem_shmem_object base;
 
 	struct drm_mm_node node;
+	bool is_mapped;
 };
 
 static inline
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 762b1bd2a8c2..92ac995dd9c6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -156,6 +156,9 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo)
 	struct sg_table *sgt;
 	int ret;
 
+	if (WARN_ON(bo->is_mapped))
+		return 0;
+
 	sgt = drm_gem_shmem_get_pages_sgt(obj);
 	if (WARN_ON(IS_ERR(sgt)))
 		return PTR_ERR(sgt);
@@ -189,6 +192,7 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo)
 
 	pm_runtime_mark_last_busy(pfdev->dev);
 	pm_runtime_put_autosuspend(pfdev->dev);
+	bo->is_mapped = true;
 
 	return 0;
 }
@@ -203,6 +207,9 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 	size_t unmapped_len = 0;
 	int ret;
 
+	if (WARN_ON(!bo->is_mapped))
+		return;
+
 	dev_dbg(pfdev->dev, "unmap: iova=%llx, len=%zx", iova, len);
 
 	ret = pm_runtime_get_sync(pfdev->dev);
@@ -230,6 +237,7 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 
 	pm_runtime_mark_last_busy(pfdev->dev);
 	pm_runtime_put_autosuspend(pfdev->dev);
+	bo->is_mapped = false;
 }
 
 static void mmu_tlb_inv_context_s1(void *cookie)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 4ff11a0077e1..9506190a0300 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -747,6 +747,9 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	if (unlikely(ret != 0))
 		goto out_err0;
 
+	dma_set_max_seg_size(dev->dev, min_t(unsigned int, U32_MAX & PAGE_MASK,
+					     SCATTERLIST_MAX_SEGMENT));
+
 	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
 		DRM_INFO("Max GMR ids is %u\n",
 			 (unsigned)dev_priv->max_gmr_ids);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 8b9270f31409..e4e09d47c5c0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -136,6 +136,114 @@ static int vmw_close_channel(struct rpc_channel *channel)
 	return 0;
 }
 
+/**
+ * vmw_port_hb_out - Send the message payload either through the
+ * high-bandwidth port if available, or through the backdoor otherwise.
+ * @channel: The rpc channel.
+ * @msg: NULL-terminated message.
+ * @hb: Whether the high-bandwidth port is available.
+ *
+ * Return: The port status.
+ */
+static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
+				     const char *msg, bool hb)
+{
+	unsigned long si, di, eax, ebx, ecx, edx;
+	unsigned long msg_len = strlen(msg);
+
+	if (hb) {
+		unsigned long bp = channel->cookie_high;
+
+		si = (uintptr_t) msg;
+		di = channel->cookie_low;
+
+		VMW_PORT_HB_OUT(
+			(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
+			msg_len, si, di,
+			VMW_HYPERVISOR_HB_PORT | (channel->channel_id << 16),
+			VMW_HYPERVISOR_MAGIC, bp,
+			eax, ebx, ecx, edx, si, di);
+
+		return ebx;
+	}
+
+	/* HB port not available. Send the message 4 bytes at a time. */
+	ecx = MESSAGE_STATUS_SUCCESS << 16;
+	while (msg_len && (HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS)) {
+		unsigned int bytes = min_t(size_t, msg_len, 4);
+		unsigned long word = 0;
+
+		memcpy(&word, msg, bytes);
+		msg_len -= bytes;
+		msg += bytes;
+		si = channel->cookie_high;
+		di = channel->cookie_low;
+
+		VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
+			 word, si, di,
+			 VMW_HYPERVISOR_PORT | (channel->channel_id << 16),
+			 VMW_HYPERVISOR_MAGIC,
+			 eax, ebx, ecx, edx, si, di);
+	}
+
+	return ecx;
+}
+
+/**
+ * vmw_port_hb_in - Receive the message payload either through the
+ * high-bandwidth port if available, or through the backdoor otherwise.
+ * @channel: The rpc channel.
+ * @reply: Pointer to buffer holding reply.
+ * @reply_len: Length of the reply.
+ * @hb: Whether the high-bandwidth port is available.
+ *
+ * Return: The port status.
+ */
+static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply,
+				    unsigned long reply_len, bool hb)
+{
+	unsigned long si, di, eax, ebx, ecx, edx;
+
+	if (hb) {
+		unsigned long bp = channel->cookie_low;
+
+		si = channel->cookie_high;
+		di = (uintptr_t) reply;
+
+		VMW_PORT_HB_IN(
+			(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
+			reply_len, si, di,
+			VMW_HYPERVISOR_HB_PORT | (channel->channel_id << 16),
+			VMW_HYPERVISOR_MAGIC, bp,
+			eax, ebx, ecx, edx, si, di);
+
+		return ebx;
+	}
+
+	/* HB port not available. Retrieve the message 4 bytes at a time. */
+	ecx = MESSAGE_STATUS_SUCCESS << 16;
+	while (reply_len) {
+		unsigned int bytes = min_t(unsigned long, reply_len, 4);
+
+		si = channel->cookie_high;
+		di = channel->cookie_low;
+
+		VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_RECVPAYLOAD << 16),
+			 MESSAGE_STATUS_SUCCESS, si, di,
+			 VMW_HYPERVISOR_PORT | (channel->channel_id << 16),
+			 VMW_HYPERVISOR_MAGIC,
+			 eax, ebx, ecx, edx, si, di);
+
+		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
+			break;
+
+		memcpy(reply, &ebx, bytes);
+		reply_len -= bytes;
+		reply += bytes;
+	}
+
+	return ecx;
+}
 
 
 /**
@@ -148,11 +256,10 @@ static int vmw_close_channel(struct rpc_channel *channel)
  */
 static int vmw_send_msg(struct rpc_channel *channel, const char *msg)
 {
-	unsigned long eax, ebx, ecx, edx, si, di, bp;
+	unsigned long eax, ebx, ecx, edx, si, di;
 	size_t msg_len = strlen(msg);
 	int retries = 0;
 
-
 	while (retries < RETRIES) {
 		retries++;
 
@@ -166,23 +273,14 @@ static int vmw_send_msg(struct rpc_channel *channel, const char *msg)
 			VMW_HYPERVISOR_MAGIC,
 			eax, ebx, ecx, edx, si, di);
 
-		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0 ||
-		    (HIGH_WORD(ecx) & MESSAGE_STATUS_HB) == 0) {
-			/* Expected success + high-bandwidth. Give up. */
+		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) {
+			/* Expected success. Give up. */
 			return -EINVAL;
 		}
 
 		/* Send msg */
-		si  = (uintptr_t) msg;
-		di  = channel->cookie_low;
-		bp  = channel->cookie_high;
-
-		VMW_PORT_HB_OUT(
-			(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-			msg_len, si, di,
-			VMW_HYPERVISOR_HB_PORT | (channel->channel_id << 16),
-			VMW_HYPERVISOR_MAGIC, bp,
-			eax, ebx, ecx, edx, si, di);
+		ebx = vmw_port_hb_out(channel, msg,
+				      !!(HIGH_WORD(ecx) & MESSAGE_STATUS_HB));
 
 		if ((HIGH_WORD(ebx) & MESSAGE_STATUS_SUCCESS) != 0) {
 			return 0;
@@ -211,7 +309,7 @@ STACK_FRAME_NON_STANDARD(vmw_send_msg);
 static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 			size_t *msg_len)
 {
-	unsigned long eax, ebx, ecx, edx, si, di, bp;
+	unsigned long eax, ebx, ecx, edx, si, di;
 	char *reply;
 	size_t reply_len;
 	int retries = 0;
@@ -233,8 +331,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 			VMW_HYPERVISOR_MAGIC,
 			eax, ebx, ecx, edx, si, di);
 
-		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0 ||
-		    (HIGH_WORD(ecx) & MESSAGE_STATUS_HB) == 0) {
+		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) {
 			DRM_ERROR("Failed to get reply size for host message.\n");
 			return -EINVAL;
 		}
@@ -252,17 +349,8 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 
 
 		/* Receive buffer */
-		si  = channel->cookie_high;
-		di  = (uintptr_t) reply;
-		bp  = channel->cookie_low;
-
-		VMW_PORT_HB_IN(
-			(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-			reply_len, si, di,
-			VMW_HYPERVISOR_HB_PORT | (channel->channel_id << 16),
-			VMW_HYPERVISOR_MAGIC, bp,
-			eax, ebx, ecx, edx, si, di);
-
+		ebx = vmw_port_hb_in(channel, reply, reply_len,
+				     !!(HIGH_WORD(ecx) & MESSAGE_STATUS_HB));
 		if ((HIGH_WORD(ebx) & MESSAGE_STATUS_SUCCESS) == 0) {
 			kfree(reply);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index a6ea75b58a83..d8ea3dd10af0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -441,11 +441,11 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 		if (unlikely(ret != 0))
 			return ret;
 
-		ret = sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
-						vsgt->num_pages, 0,
-						(unsigned long)
-						vsgt->num_pages << PAGE_SHIFT,
-						GFP_KERNEL);
+		ret = __sg_alloc_table_from_pages
+			(&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
+			 (unsigned long) vsgt->num_pages << PAGE_SHIFT,
+			 dma_get_max_seg_size(dev_priv->dev->dev),
+			 GFP_KERNEL);
 		if (unlikely(ret != 0))
 			goto out_sg_alloc_fail;
 
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index 36e88434513a..e744f3527ce1 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -400,12 +400,14 @@ static int calc_image_resize_coefficients(struct ipu_image_convert_ctx *ctx,
 	if (WARN_ON(resized_width == 0 || resized_height == 0))
 		return -EINVAL;
 
-	while (downsized_width >= resized_width * 2) {
+	while (downsized_width > 1024 ||
+	       downsized_width >= resized_width * 2) {
 		downsized_width >>= 1;
 		downsize_coeff_h++;
 	}
 
-	while (downsized_height >= resized_height * 2) {
+	while (downsized_height > 1024 ||
+	       downsized_height >= resized_height * 2) {
 		downsized_height >>= 1;
 		downsize_coeff_v++;
 	}
@@ -1876,7 +1878,8 @@ void ipu_image_convert_adjust(struct ipu_image *in, struct ipu_image *out,
 			      enum ipu_rotate_mode rot_mode)
 {
 	const struct ipu_image_pixfmt *infmt, *outfmt;
-	u32 w_align, h_align;
+	u32 w_align_out, h_align_out;
+	u32 w_align_in, h_align_in;
 
 	infmt = get_format(in->pix.pixelformat);
 	outfmt = get_format(out->pix.pixelformat);
@@ -1908,22 +1911,33 @@ void ipu_image_convert_adjust(struct ipu_image *in, struct ipu_image *out,
 	}
 
 	/* align input width/height */
-	w_align = ilog2(tile_width_align(IMAGE_CONVERT_IN, infmt, rot_mode));
-	h_align = ilog2(tile_height_align(IMAGE_CONVERT_IN, infmt, rot_mode));
-	in->pix.width = clamp_align(in->pix.width, MIN_W, MAX_W, w_align);
-	in->pix.height = clamp_align(in->pix.height, MIN_H, MAX_H, h_align);
+	w_align_in = ilog2(tile_width_align(IMAGE_CONVERT_IN, infmt,
+					    rot_mode));
+	h_align_in = ilog2(tile_height_align(IMAGE_CONVERT_IN, infmt,
+					     rot_mode));
+	in->pix.width = clamp_align(in->pix.width, MIN_W, MAX_W,
+				    w_align_in);
+	in->pix.height = clamp_align(in->pix.height, MIN_H, MAX_H,
+				     h_align_in);
 
 	/* align output width/height */
-	w_align = ilog2(tile_width_align(IMAGE_CONVERT_OUT, outfmt, rot_mode));
-	h_align = ilog2(tile_height_align(IMAGE_CONVERT_OUT, outfmt, rot_mode));
-	out->pix.width = clamp_align(out->pix.width, MIN_W, MAX_W, w_align);
-	out->pix.height = clamp_align(out->pix.height, MIN_H, MAX_H, h_align);
+	w_align_out = ilog2(tile_width_align(IMAGE_CONVERT_OUT, outfmt,
+					     rot_mode));
+	h_align_out = ilog2(tile_height_align(IMAGE_CONVERT_OUT, outfmt,
+					      rot_mode));
+	out->pix.width = clamp_align(out->pix.width, MIN_W, MAX_W,
+				     w_align_out);
+	out->pix.height = clamp_align(out->pix.height, MIN_H, MAX_H,
+				      h_align_out);
 
 	/* set input/output strides and image sizes */
 	in->pix.bytesperline = infmt->planar ?
-		clamp_align(in->pix.width, 2 << w_align, MAX_W, w_align) :
+		clamp_align(in->pix.width, 2 << w_align_in, MAX_W,
+			    w_align_in) :
 		clamp_align((in->pix.width * infmt->bpp) >> 3,
-			    2 << w_align, MAX_W, w_align);
+			    ((2 << w_align_in) * infmt->bpp) >> 3,
+			    (MAX_W * infmt->bpp) >> 3,
+			    w_align_in);
 	in->pix.sizeimage = infmt->planar ?
 		(in->pix.height * in->pix.bytesperline * infmt->bpp) >> 3 :
 		in->pix.height * in->pix.bytesperline;