Merge tag 'for-v4.6-rc/omap-fixes-a' of git://git.kernel.org/pub/scm/linux/kernel/git/pjw/omap-pending into omap-for-v4.6/fixes

ARM: OMAP2+: first hwmod fix for v4.6-rc

Fix a longstanding bug in the hwmod code that could cause
hardware SYSCONFIG register values to not match the kernel's
idea of what they should be, and that could result in lower
performance during IP block idle entry.

Basic build, boot, and PM test logs are available here:

http://www.pwsan.com/omap/testlogs/omap-hwmod-fixes-a-for-v4.6-rc/20160326231727/

5 files changed, 22 insertions, 12 deletions

diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index da462afcb225..c27858ae0552 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -18,6 +18,7 @@
 #include <linux/host1x.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/of_device.h>
 
 #include "bus.h"
 #include "dev.h"
@@ -82,8 +83,10 @@ static int host1x_device_parse_dt(struct host1x_device *device,
 		if (of_match_node(driver->subdevs, np) &&
 		    of_device_is_available(np)) {
 			err = host1x_subdev_add(device, np);
-			if (err < 0)
+			if (err < 0) {
+				of_node_put(np);
 				return err;
+			}
 		}
 	}
 
@@ -394,6 +397,7 @@ static int host1x_device_add(struct host1x *host1x,
 	device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask;
 	device->dev.dma_mask = &device->dev.coherent_dma_mask;
 	dev_set_name(&device->dev, "%s", driver->driver.name);
+	of_dma_configure(&device->dev, host1x->dev->of_node);
 	device->dev.release = host1x_device_release;
 	device->dev.bus = &host1x_bus_type;
 	device->dev.parent = host1x->dev;
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 5a8c8d55317a..a18db4d5347c 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -52,8 +52,8 @@ static void host1x_pushbuffer_destroy(struct push_buffer *pb)
 	struct host1x *host1x = cdma_to_host1x(cdma);
 
 	if (pb->phys != 0)
-		dma_free_writecombine(host1x->dev, pb->size_bytes + 4,
-				      pb->mapped, pb->phys);
+		dma_free_wc(host1x->dev, pb->size_bytes + 4, pb->mapped,
+			    pb->phys);
 
 	pb->mapped = NULL;
 	pb->phys = 0;
@@ -76,8 +76,8 @@ static int host1x_pushbuffer_init(struct push_buffer *pb)
 	pb->pos = 0;
 
 	/* allocate and map pushbuffer memory */
-	pb->mapped = dma_alloc_writecombine(host1x->dev, pb->size_bytes + 4,
-					    &pb->phys, GFP_KERNEL);
+	pb->mapped = dma_alloc_wc(host1x->dev, pb->size_bytes + 4, &pb->phys,
+				  GFP_KERNEL);
 	if (!pb->mapped)
 		goto fail;
 
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 314bf3718cc7..ff348690df94 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -23,6 +23,7 @@
 #include <linux/of_device.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/dma-mapping.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/host1x.h>
@@ -68,6 +69,7 @@ static const struct host1x_info host1x01_info = {
 	.nb_bases	= 8,
 	.init		= host1x01_init,
 	.sync_offset	= 0x3000,
+	.dma_mask	= DMA_BIT_MASK(32),
 };
 
 static const struct host1x_info host1x02_info = {
@@ -77,6 +79,7 @@ static const struct host1x_info host1x02_info = {
 	.nb_bases = 12,
 	.init = host1x02_init,
 	.sync_offset = 0x3000,
+	.dma_mask = DMA_BIT_MASK(32),
 };
 
 static const struct host1x_info host1x04_info = {
@@ -86,6 +89,7 @@ static const struct host1x_info host1x04_info = {
 	.nb_bases = 64,
 	.init = host1x04_init,
 	.sync_offset = 0x2100,
+	.dma_mask = DMA_BIT_MASK(34),
 };
 
 static const struct host1x_info host1x05_info = {
@@ -95,6 +99,7 @@ static const struct host1x_info host1x05_info = {
 	.nb_bases = 64,
 	.init = host1x05_init,
 	.sync_offset = 0x2100,
+	.dma_mask = DMA_BIT_MASK(34),
 };
 
 static struct of_device_id host1x_of_match[] = {
@@ -148,6 +153,8 @@ static int host1x_probe(struct platform_device *pdev)
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
 
+	dma_set_mask_and_coherent(host->dev, host->info->dma_mask);
+
 	if (host->info->init) {
 		err = host->info->init(host);
 		if (err)
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index 0b6e8e9629c5..dace124994bb 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -96,6 +96,7 @@ struct host1x_info {
 	int	nb_mlocks;		/* host1x: number of mlocks */
 	int	(*init)(struct host1x *); /* initialize per SoC ops */
 	int	sync_offset;
+	u64	dma_mask;		/* mask of addressable memory */
 };
 
 struct host1x {
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 63bd63f3c7df..b4515d544039 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -225,7 +225,7 @@ unpin:
 	return 0;
 }
 
-static unsigned int do_relocs(struct host1x_job *job, struct host1x_bo *cmdbuf)
+static int do_relocs(struct host1x_job *job, struct host1x_bo *cmdbuf)
 {
 	int i = 0;
 	u32 last_page = ~0;
@@ -467,9 +467,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
 		size += g->words * sizeof(u32);
 	}
 
-	job->gather_copy_mapped = dma_alloc_writecombine(dev, size,
-							 &job->gather_copy,
-							 GFP_KERNEL);
+	job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy,
+					       GFP_KERNEL);
 	if (!job->gather_copy_mapped) {
 		job->gather_copy_mapped = NULL;
 		return -ENOMEM;
@@ -578,9 +577,8 @@ void host1x_job_unpin(struct host1x_job *job)
 	job->num_unpins = 0;
 
 	if (job->gather_copy_size)
-		dma_free_writecombine(job->channel->dev, job->gather_copy_size,
-				      job->gather_copy_mapped,
-				      job->gather_copy);
+		dma_free_wc(job->channel->dev, job->gather_copy_size,
+		            job->gather_copy_mapped, job->gather_copy);
 }
 EXPORT_SYMBOL(host1x_job_unpin);