Merge tag 'omapdrm-4.20-2' of...

Merge tag 'omapdrm-4.20-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tomba/linux into drm-next

omapdrm fixes and cleanups for 4.20

- fix memory barrier bug in DMM driver
- fix interrupt management in DMM driver
- partial workaround for errata i878
- fix use of freed memory
- some cleanups
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/36bdd576-2b5c-d69e-24af-05572652b08e@ti.com

drivers/gpu/drm/omapdrm/dss/dispc.c

@@ -1140,18 +1140,6 @@ static void dispc_ovl_set_color_mode(struct dispc_device *dispc,
 	REG_FLD_MOD(dispc, DISPC_OVL_ATTRIBUTES(plane), m, 4, 1);
 }
 
-static bool format_is_yuv(u32 fourcc)
-{
-	switch (fourcc) {
-	case DRM_FORMAT_YUYV:
-	case DRM_FORMAT_UYVY:
-	case DRM_FORMAT_NV12:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void dispc_ovl_configure_burst_type(struct dispc_device *dispc,
 					   enum omap_plane_id plane,
 					   enum omap_dss_rotation_type rotation)
@@ -1910,11 +1898,14 @@ static void dispc_ovl_set_scaling_uv(struct dispc_device *dispc,
 	int scale_x = out_width != orig_width;
 	int scale_y = out_height != orig_height;
 	bool chroma_upscale = plane != OMAP_DSS_WB;
+	const struct drm_format_info *info;
+
+	info = drm_format_info(fourcc);
 
 	if (!dispc_has_feature(dispc, FEAT_HANDLE_UV_SEPARATE))
 		return;
 
-	if (!format_is_yuv(fourcc)) {
+	if (!info->is_yuv) {
 		/* reset chroma resampling for RGB formats  */
 		if (plane != OMAP_DSS_WB)
 			REG_FLD_MOD(dispc, DISPC_OVL_ATTRIBUTES2(plane),
@@ -2624,7 +2615,7 @@ static int dispc_ovl_setup_common(struct dispc_device *dispc,
 	unsigned int offset0, offset1;
 	s32 row_inc;
 	s32 pix_inc;
-	u16 frame_width, frame_height;
+	u16 frame_width;
 	unsigned int field_offset = 0;
 	u16 in_height = height;
 	u16 in_width = width;
@@ -2632,6 +2623,9 @@ static int dispc_ovl_setup_common(struct dispc_device *dispc,
 	bool ilace = !!(vm->flags & DISPLAY_FLAGS_INTERLACED);
 	unsigned long pclk = dispc_plane_pclk_rate(dispc, plane);
 	unsigned long lclk = dispc_plane_lclk_rate(dispc, plane);
+	const struct drm_format_info *info;
+
+	info = drm_format_info(fourcc);
 
 	/* when setting up WB, dispc_plane_pclk_rate() returns 0 */
 	if (plane == OMAP_DSS_WB)
@@ -2640,7 +2634,7 @@ static int dispc_ovl_setup_common(struct dispc_device *dispc,
 	if (paddr == 0 && rotation_type != OMAP_DSS_ROT_TILER)
 		return -EINVAL;
 
-	if (format_is_yuv(fourcc) && (in_width & 1)) {
+	if (info->is_yuv && (in_width & 1)) {
 		DSSERR("input width %d is not even for YUV format\n", in_width);
 		return -EINVAL;
 	}
@@ -2680,7 +2674,7 @@ static int dispc_ovl_setup_common(struct dispc_device *dispc,
 		DSSDBG("predecimation %d x %x, new input size %d x %d\n",
 			x_predecim, y_predecim, in_width, in_height);
 
-	if (format_is_yuv(fourcc) && (in_width & 1)) {
+	if (info->is_yuv && (in_width & 1)) {
 		DSSDBG("predecimated input width is not even for YUV format\n");
 		DSSDBG("adjusting input width %d -> %d\n",
 			in_width, in_width & ~1);
@@ -2688,7 +2682,7 @@ static int dispc_ovl_setup_common(struct dispc_device *dispc,
 		in_width &= ~1;
 	}
 
-	if (format_is_yuv(fourcc))
+	if (info->is_yuv)
 		cconv = 1;
 
 	if (ilace && !fieldmode) {
@@ -2714,13 +2708,10 @@ static int dispc_ovl_setup_common(struct dispc_device *dispc,
 	row_inc = 0;
 	pix_inc = 0;
 
-	if (plane == OMAP_DSS_WB) {
+	if (plane == OMAP_DSS_WB)
 		frame_width = out_width;
-		frame_height = out_height;
-	} else {
+	else
 		frame_width = in_width;
-		frame_height = height;
-	}
 
 	calc_offset(screen_width, frame_width,
 			fourcc, fieldmode, field_offset,

drivers/gpu/drm/omapdrm/dss/dss.c

@@ -947,7 +947,7 @@ dss_debugfs_create_file(struct dss_device *dss, const char *name,
 				&dss_debug_fops);
 	if (IS_ERR(d)) {
 		kfree(entry);
-		return ERR_PTR(PTR_ERR(d));
+		return ERR_CAST(d);
 	}
 
 	entry->dentry = d;

drivers/gpu/drm/omapdrm/omap_connector.c

@@ -164,10 +164,11 @@ static void omap_connector_destroy(struct drm_connector *connector)
 
 	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
-	kfree(omap_connector);
 
 	omapdss_device_put(omap_connector->output);
 	omapdss_device_put(omap_connector->display);
+
+	kfree(omap_connector);
 }
 
 #define MAX_EDID  512

drivers/gpu/drm/omapdrm/omap_dmm_priv.h

@@ -159,6 +159,7 @@ struct dmm_platform_data {
 
 struct dmm {
 	struct device *dev;
+	dma_addr_t phys_base;
 	void __iomem *base;
 	int irq;
 
@@ -189,6 +190,12 @@ struct dmm {
 	struct list_head alloc_head;
 
 	const struct dmm_platform_data *plat_data;
+
+	bool dmm_workaround;
+	spinlock_t wa_lock;
+	u32 *wa_dma_data;
+	dma_addr_t wa_dma_handle;
+	struct dma_chan *wa_dma_chan;
 };
 
 #endif

drivers/gpu/drm/omapdrm/omap_dmm_tiler.c

@@ -18,6 +18,7 @@
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -79,14 +80,138 @@ static const u32 reg[][4] = {
 			DMM_PAT_DESCR__2, DMM_PAT_DESCR__3},
 };
 
+static int dmm_dma_copy(struct dmm *dmm, dma_addr_t src, dma_addr_t dst)
+{
+	struct dma_device *dma_dev = dmm->wa_dma_chan->device;
+	struct dma_async_tx_descriptor *tx;
+	enum dma_status status;
+	dma_cookie_t cookie;
+
+	tx = dma_dev->device_prep_dma_memcpy(dmm->wa_dma_chan, dst, src, 4, 0);
+	if (!tx) {
+		dev_err(dmm->dev, "Failed to prepare DMA memcpy\n");
+		return -EIO;
+	}
+
+	cookie = tx->tx_submit(tx);
+	if (dma_submit_error(cookie)) {
+		dev_err(dmm->dev, "Failed to do DMA tx_submit\n");
+		return -EIO;
+	}
+
+	dma_async_issue_pending(dmm->wa_dma_chan);
+	status = dma_sync_wait(dmm->wa_dma_chan, cookie);
+	if (status != DMA_COMPLETE)
+		dev_err(dmm->dev, "i878 wa DMA copy failure\n");
+
+	dmaengine_terminate_all(dmm->wa_dma_chan);
+	return 0;
+}
+
+static u32 dmm_read_wa(struct dmm *dmm, u32 reg)
+{
+	dma_addr_t src, dst;
+	int r;
+
+	src = dmm->phys_base + reg;
+	dst = dmm->wa_dma_handle;
+
+	r = dmm_dma_copy(dmm, src, dst);
+	if (r) {
+		dev_err(dmm->dev, "sDMA read transfer timeout\n");
+		return readl(dmm->base + reg);
+	}
+
+	/*
+	 * As per i878 workaround, the DMA is used to access the DMM registers.
+	 * Make sure that the readl is not moved by the compiler or the CPU
+	 * earlier than the DMA finished writing the value to memory.
+	 */
+	rmb();
+	return readl(dmm->wa_dma_data);
+}
+
+static void dmm_write_wa(struct dmm *dmm, u32 val, u32 reg)
+{
+	dma_addr_t src, dst;
+	int r;
+
+	writel(val, dmm->wa_dma_data);
+	/*
+	 * As per i878 workaround, the DMA is used to access the DMM registers.
+	 * Make sure that the writel is not moved by the compiler or the CPU, so
+	 * the data will be in place before we start the DMA to do the actual
+	 * register write.
+	 */
+	wmb();
+
+	src = dmm->wa_dma_handle;
+	dst = dmm->phys_base + reg;
+
+	r = dmm_dma_copy(dmm, src, dst);
+	if (r) {
+		dev_err(dmm->dev, "sDMA write transfer timeout\n");
+		writel(val, dmm->base + reg);
+	}
+}
+
 static u32 dmm_read(struct dmm *dmm, u32 reg)
 {
-	return readl(dmm->base + reg);
+	if (dmm->dmm_workaround) {
+		u32 v;
+		unsigned long flags;
+
+		spin_lock_irqsave(&dmm->wa_lock, flags);
+		v = dmm_read_wa(dmm, reg);
+		spin_unlock_irqrestore(&dmm->wa_lock, flags);
+
+		return v;
+	} else {
+		return readl(dmm->base + reg);
+	}
 }
 
 static void dmm_write(struct dmm *dmm, u32 val, u32 reg)
 {
-	writel(val, dmm->base + reg);
+	if (dmm->dmm_workaround) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&dmm->wa_lock, flags);
+		dmm_write_wa(dmm, val, reg);
+		spin_unlock_irqrestore(&dmm->wa_lock, flags);
+	} else {
+		writel(val, dmm->base + reg);
+	}
+}
+
+static int dmm_workaround_init(struct dmm *dmm)
+{
+	dma_cap_mask_t mask;
+
+	spin_lock_init(&dmm->wa_lock);
+
+	dmm->wa_dma_data = dma_alloc_coherent(dmm->dev,  sizeof(u32),
+					      &dmm->wa_dma_handle, GFP_KERNEL);
+	if (!dmm->wa_dma_data)
+		return -ENOMEM;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_MEMCPY, mask);
+
+	dmm->wa_dma_chan = dma_request_channel(mask, NULL, NULL);
+	if (!dmm->wa_dma_chan) {
+		dma_free_coherent(dmm->dev, 4, dmm->wa_dma_data, dmm->wa_dma_handle);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void dmm_workaround_uninit(struct dmm *dmm)
+{
+	dma_release_channel(dmm->wa_dma_chan);
+
+	dma_free_coherent(dmm->dev, 4, dmm->wa_dma_data, dmm->wa_dma_handle);
 }
 
 /* simple allocator to grab next 16 byte aligned memory from txn */
@@ -285,6 +410,17 @@ static int dmm_txn_commit(struct dmm_txn *txn, bool wait)
 	}
 
 	txn->last_pat->next_pa = 0;
+	/* ensure that the written descriptors are visible to DMM */
+	wmb();
+
+	/*
+	 * NOTE: the wmb() above should be enough, but there seems to be a bug
+	 * in OMAP's memory barrier implementation, which in some rare cases may
+	 * cause the writes not to be observable after wmb().
+	 */
+
+	/* read back to ensure the data is in RAM */
+	readl(&txn->last_pat->next_pa);
 
 	/* write to PAT_DESCR to clear out any pending transaction */
 	dmm_write(dmm, 0x0, reg[PAT_DESCR][engine->id]);
@@ -603,6 +739,10 @@ static int omap_dmm_remove(struct platform_device *dev)
 	unsigned long flags;
 
 	if (omap_dmm) {
+		/* Disable all enabled interrupts */
+		dmm_write(omap_dmm, 0x7e7e7e7e, DMM_PAT_IRQENABLE_CLR);
+		free_irq(omap_dmm->irq, omap_dmm);
+
 		/* free all area regions */
 		spin_lock_irqsave(&list_lock, flags);
 		list_for_each_entry_safe(block, _block, &omap_dmm->alloc_head,
@@ -625,8 +765,8 @@ static int omap_dmm_remove(struct platform_device *dev)
 		if (omap_dmm->dummy_page)
 			__free_page(omap_dmm->dummy_page);
 
-		if (omap_dmm->irq > 0)
-			free_irq(omap_dmm->irq, omap_dmm);
+		if (omap_dmm->dmm_workaround)
+			dmm_workaround_uninit(omap_dmm);
 
 		iounmap(omap_dmm->base);
 		kfree(omap_dmm);
@@ -673,6 +813,7 @@ static int omap_dmm_probe(struct platform_device *dev)
 		goto fail;
 	}
 
+	omap_dmm->phys_base = mem->start;
 	omap_dmm->base = ioremap(mem->start, SZ_2K);
 
 	if (!omap_dmm->base) {
@@ -688,6 +829,22 @@ static int omap_dmm_probe(struct platform_device *dev)
 
 	omap_dmm->dev = &dev->dev;
 
+	if (of_machine_is_compatible("ti,dra7")) {
+		/*
+		 * DRA7 Errata i878 says that MPU should not be used to access
+		 * RAM and DMM at the same time. As it's not possible to prevent
+		 * MPU accessing RAM, we need to access DMM via a proxy.
+		 */
+		if (!dmm_workaround_init(omap_dmm)) {
+			omap_dmm->dmm_workaround = true;
+			dev_info(&dev->dev,
+				"workaround for errata i878 in use\n");
+		} else {
+			dev_warn(&dev->dev,
+				 "failed to initialize work-around for i878\n");
+		}
+	}
+
 	hwinfo = dmm_read(omap_dmm, DMM_PAT_HWINFO);
 	omap_dmm->num_engines = (hwinfo >> 24) & 0x1F;
 	omap_dmm->num_lut = (hwinfo >> 16) & 0x1F;
@@ -714,24 +871,6 @@ static int omap_dmm_probe(struct platform_device *dev)
 	dmm_write(omap_dmm, 0x88888888, DMM_TILER_OR__0);
 	dmm_write(omap_dmm, 0x88888888, DMM_TILER_OR__1);
 
-	ret = request_irq(omap_dmm->irq, omap_dmm_irq_handler, IRQF_SHARED,
-				"omap_dmm_irq_handler", omap_dmm);
-
-	if (ret) {
-		dev_err(&dev->dev, "couldn't register IRQ %d, error %d\n",
-			omap_dmm->irq, ret);
-		omap_dmm->irq = -1;
-		goto fail;
-	}
-
-	/* Enable all interrupts for each refill engine except
-	 * ERR_LUT_MISS<n> (which is just advisory, and we don't care
-	 * about because we want to be able to refill live scanout
-	 * buffers for accelerated pan/scroll) and FILL_DSC<n> which
-	 * we just generally don't care about.
-	 */
-	dmm_write(omap_dmm, 0x7e7e7e7e, DMM_PAT_IRQENABLE_SET);
-
 	omap_dmm->dummy_page = alloc_page(GFP_KERNEL | __GFP_DMA32);
 	if (!omap_dmm->dummy_page) {
 		dev_err(&dev->dev, "could not allocate dummy page\n");
@@ -823,6 +962,24 @@ static int omap_dmm_probe(struct platform_device *dev)
 		.p1.y = omap_dmm->container_height - 1,
 	};
 
+	ret = request_irq(omap_dmm->irq, omap_dmm_irq_handler, IRQF_SHARED,
+				"omap_dmm_irq_handler", omap_dmm);
+
+	if (ret) {
+		dev_err(&dev->dev, "couldn't register IRQ %d, error %d\n",
+			omap_dmm->irq, ret);
+		omap_dmm->irq = -1;
+		goto fail;
+	}
+
+	/* Enable all interrupts for each refill engine except
+	 * ERR_LUT_MISS<n> (which is just advisory, and we don't care
+	 * about because we want to be able to refill live scanout
+	 * buffers for accelerated pan/scroll) and FILL_DSC<n> which
+	 * we just generally don't care about.
+	 */
+	dmm_write(omap_dmm, 0x7e7e7e7e, DMM_PAT_IRQENABLE_SET);
+
 	/* initialize all LUTs to dummy page entries */
 	for (i = 0; i < omap_dmm->num_lut; i++) {
 		area.tcm = omap_dmm->tcm[i];

drivers/gpu/drm/omapdrm/omap_drv.c

@@ -439,7 +439,7 @@ static int ioctl_gem_info(struct drm_device *dev, void *data,
 	args->size = omap_gem_mmap_size(obj);
 	args->offset = omap_gem_mmap_offset(obj);
 
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return ret;
 }
@@ -614,7 +614,7 @@ static int omapdrm_init(struct omap_drm_private *priv, struct device *dev)
 	omap_disconnect_pipelines(ddev);
 err_crtc_uninit:
 	omap_crtc_pre_uninit(priv);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 	return ret;
 }
 
@@ -643,7 +643,7 @@ static void omapdrm_cleanup(struct omap_drm_private *priv)
 	omap_disconnect_pipelines(ddev);
 	omap_crtc_pre_uninit(priv);
 
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 }
 
 static int pdev_probe(struct platform_device *pdev)

drivers/gpu/drm/omapdrm/omap_fb.c

@@ -319,7 +319,7 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev,
 
 error:
 	while (--i >= 0)
-		drm_gem_object_unreference_unlocked(bos[i]);
+		drm_gem_object_put_unlocked(bos[i]);
 
 	return fb;
 }

drivers/gpu/drm/omapdrm/omap_fbdev.c

@@ -150,7 +150,7 @@ static int omap_fbdev_create(struct drm_fb_helper *helper,
 		/* note: if fb creation failed, we can't rely on fb destroy
 		 * to unref the bo:
 		 */
-		drm_gem_object_unreference_unlocked(fbdev->bo);
+		drm_gem_object_put_unlocked(fbdev->bo);
 		ret = PTR_ERR(fb);
 		goto fail;
 	}

drivers/gpu/drm/omapdrm/omap_gem.c

@@ -638,7 +638,7 @@ int omap_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
 
 	*offset = omap_gem_mmap_offset(obj);
 
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 fail:
 	return ret;
@@ -1312,7 +1312,7 @@ int omap_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 	}
 
 	/* drop reference from allocate - handle holds it now */
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return 0;
 }

drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c

@@ -168,7 +168,7 @@ struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev,
 			 * Importing dmabuf exported from out own gem increases
 			 * refcount on gem itself instead of f_count of dmabuf.
 			 */
-			drm_gem_object_reference(obj);
+			drm_gem_object_get(obj);
 			return obj;
 		}
 	}

drivers/gpu/drm/omapdrm/tcm-sita.h

-/*
- * SImple Tiler Allocator (SiTA) private structures.
- *
- * Copyright (C) 2009-2011 Texas Instruments Incorporated - http://www.ti.com/
- * Author: Ravi Ramachandra <r.ramachandra@ti.com>
- *
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- *
- * * Redistributions in binary form must reproduce the above copyright
- *   notice, this list of conditions and the following disclaimer in the
- *   documentation and/or other materials provided with the distribution.
- *
- * * Neither the name of Texas Instruments Incorporated nor the names of
- *   its contributors may be used to endorse or promote products derived
- *   from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
- * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
- * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
- * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
- * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
- * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
- * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
- * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _TCM_SITA_H
-#define _TCM_SITA_H
-
-#include "tcm.h"
-
-/* length between two coordinates */
-#define LEN(a, b) ((a) > (b) ? (a) - (b) + 1 : (b) - (a) + 1)
-
-enum criteria {
-	CR_MAX_NEIGHS		= 0x01,
-	CR_FIRST_FOUND		= 0x10,
-	CR_BIAS_HORIZONTAL	= 0x20,
-	CR_BIAS_VERTICAL	= 0x40,
-	CR_DIAGONAL_BALANCE	= 0x80
-};
-
-/* nearness to the beginning of the search field from 0 to 1000 */
-struct nearness_factor {
-	s32 x;
-	s32 y;
-};
-
-/*
- * Statistics on immediately neighboring slots.  Edge is the number of
- * border segments that are also border segments of the scan field.  Busy
- * refers to the number of neighbors that are occupied.
- */
-struct neighbor_stats {
-	u16 edge;
-	u16 busy;
-};
-
-/* structure to keep the score of a potential allocation */
-struct score {
-	struct nearness_factor	f;
-	struct neighbor_stats	n;
-	struct tcm_area		a;
-	u16    neighs;		/* number of busy neighbors */
-};
-
-struct sita_pvt {
-	spinlock_t lock;	/* spinlock to protect access */
-	struct tcm_pt div_pt;	/* divider point splitting container */
-	struct tcm_area ***map;	/* pointers to the parent area for each slot */
-};
-
-/* assign coordinates to area */
-static inline
-void assign(struct tcm_area *a, u16 x0, u16 y0, u16 x1, u16 y1)
-{
-	a->p0.x = x0;
-	a->p0.y = y0;
-	a->p1.x = x1;
-	a->p1.y = y1;
-}
-
-#endif