@@ -10,6 +10,7 @@ host1x-y = \
debug.o \
mipi.o \
fence.o \
+ context.o \
hw/host1x01.o \
hw/host1x02.o \
hw/host1x04.o \
new file mode 100644
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, NVIDIA Corporation.
+ */
+
+#include <linux/device.h>
+#include <linux/kref.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pid.h>
+#include <linux/slab.h>
+
+#include "context.h"
+#include "dev.h"
+
+/*
+ * Due to an issue with T194 NVENC, only 38 bits can be used.
+ * Anyway, 256GiB of IOVA ought to be enough for anyone.
+ */
+static dma_addr_t context_device_dma_mask = DMA_BIT_MASK(38);
+
+int host1x_context_list_init(struct host1x *host1x)
+{
+ struct host1x_context_list *cdl = &host1x->context_list;
+ struct host1x_context *ctx;
+ struct device_node *node;
+ int index;
+ int err;
+
+ node = of_get_child_by_name(host1x->dev->of_node, "memory-contexts");
+ if (!node)
+ return 0;
+
+ cdl->devs = NULL;
+ cdl->len = 0;
+ mutex_init(&cdl->lock);
+
+ err = of_property_count_u32_elems(node, "iommu-map");
+ if (err < 0) {
+ err = 0;
+ goto put_node;
+ }
+
+ cdl->devs = kcalloc(err, sizeof(*cdl->devs), GFP_KERNEL);
+ if (!cdl->devs) {
+ err = -ENOMEM;
+ goto put_node;
+ }
+ cdl->len = err / 4;
+
+ for (index = 0; index < cdl->len; index++) {
+ struct iommu_fwspec *fwspec;
+
+ ctx = &cdl->devs[index];
+
+ ctx->host = host1x;
+
+ device_initialize(&ctx->dev);
+
+ ctx->dev.dma_mask = &context_device_dma_mask;
+ ctx->dev.coherent_dma_mask = context_device_dma_mask;
+ dev_set_name(&ctx->dev, "host1x-ctx.%d", index);
+ ctx->dev.bus = &host1x_context_device_bus_type;
+ ctx->dev.parent = host1x->dev;
+
+ dma_set_max_seg_size(&ctx->dev, UINT_MAX);
+
+ err = device_add(&ctx->dev);
+ if (err) {
+ dev_err(host1x->dev, "could not add context device %d: %d\n", index, err);
+ goto del_devices;
+ }
+
+ err = of_dma_configure_id(&ctx->dev, node, true, &index);
+ if (err) {
+ dev_err(host1x->dev, "IOMMU configuration failed for context device %d: %d\n",
+ index, err);
+ device_del(&ctx->dev);
+ goto del_devices;
+ }
+
+ fwspec = dev_iommu_fwspec_get(&ctx->dev);
+ if (!fwspec) {
+ dev_err(host1x->dev, "Context device %d has no IOMMU!\n", index);
+ device_del(&ctx->dev);
+ goto del_devices;
+ }
+
+ ctx->stream_id = fwspec->ids[0] & 0xffff;
+ }
+
+ of_node_put(node);
+
+ return 0;
+
+del_devices:
+ while (--index >= 0)
+ device_del(&cdl->devs[index].dev);
+
+ kfree(cdl->devs);
+ cdl->len = 0;
+
+put_node:
+ of_node_put(node);
+
+ return err;
+}
+
+void host1x_context_list_free(struct host1x_context_list *cdl)
+{
+ int i;
+
+ for (i = 0; i < cdl->len; i++)
+ device_del(&cdl->devs[i].dev);
+
+ kfree(cdl->devs);
+ cdl->len = 0;
+}
+
+struct host1x_context *host1x_context_alloc(struct host1x *host1x,
+ struct pid *pid)
+{
+ struct host1x_context_list *cdl = &host1x->context_list;
+ struct host1x_context *free = NULL;
+ int i;
+
+ if (!cdl->len)
+ return ERR_PTR(-EOPNOTSUPP);
+
+ mutex_lock(&cdl->lock);
+
+ for (i = 0; i < cdl->len; i++) {
+ struct host1x_context *cd = &cdl->devs[i];
+
+ if (cd->owner == pid) {
+ refcount_inc(&cd->ref);
+ mutex_unlock(&cdl->lock);
+ return cd;
+ } else if (!cd->owner && !free) {
+ free = cd;
+ }
+ }
+
+ if (!free) {
+ mutex_unlock(&cdl->lock);
+ return ERR_PTR(-EBUSY);
+ }
+
+ refcount_set(&free->ref, 1);
+ free->owner = get_pid(pid);
+
+ mutex_unlock(&cdl->lock);
+
+ return free;
+}
+EXPORT_SYMBOL(host1x_context_alloc);
+
+void host1x_context_get(struct host1x_context *cd)
+{
+ refcount_inc(&cd->ref);
+}
+EXPORT_SYMBOL(host1x_context_get);
+
+void host1x_context_put(struct host1x_context *cd)
+{
+ struct host1x_context_list *cdl = &cd->host->context_list;
+
+ if (refcount_dec_and_mutex_lock(&cd->ref, &cdl->lock)) {
+ put_pid(cd->owner);
+ cd->owner = NULL;
+ mutex_unlock(&cdl->lock);
+ }
+}
+EXPORT_SYMBOL(host1x_context_put);
new file mode 100644
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Host1x context devices
+ *
+ * Copyright (c) 2020, NVIDIA Corporation.
+ */
+
+#ifndef __HOST1X_CONTEXT_H
+#define __HOST1X_CONTEXT_H
+
+#include <linux/mutex.h>
+#include <linux/refcount.h>
+
+struct host1x;
+
+extern struct bus_type host1x_context_device_bus_type;
+
+struct host1x_context_list {
+ struct mutex lock;
+ struct host1x_context *devs;
+ unsigned int len;
+};
+
+int host1x_context_list_init(struct host1x *host1x);
+void host1x_context_list_free(struct host1x_context_list *cdl);
+
+#endif
@@ -20,6 +20,7 @@
#include "bus.h"
#include "channel.h"
+#include "context.h"
#include "debug.h"
#include "dev.h"
#include "intr.h"
@@ -461,10 +462,16 @@ static int host1x_probe(struct platform_device *pdev)
goto iommu_exit;
}
+ err = host1x_context_list_init(host);
+ if (err) {
+ dev_err(&pdev->dev, "failed to initialize context list\n");
+ goto free_channels;
+ }
+
err = clk_prepare_enable(host->clk);
if (err < 0) {
dev_err(&pdev->dev, "failed to enable clock\n");
- goto free_channels;
+ goto free_contexts;
}
err = reset_control_deassert(host->rst);
@@ -511,6 +518,8 @@ static int host1x_probe(struct platform_device *pdev)
reset_control_assert(host->rst);
unprepare_disable:
clk_disable_unprepare(host->clk);
+free_contexts:
+ host1x_context_list_free(&host->context_list);
free_channels:
host1x_channel_list_free(&host->channel_list);
iommu_exit:
@@ -529,6 +538,7 @@ static int host1x_remove(struct platform_device *pdev)
host1x_syncpt_deinit(host);
reset_control_assert(host->rst);
clk_disable_unprepare(host->clk);
+ host1x_context_list_free(&host->context_list);
host1x_iommu_exit(host);
return 0;
@@ -14,6 +14,7 @@
#include "cdma.h"
#include "channel.h"
+#include "context.h"
#include "intr.h"
#include "job.h"
#include "syncpt.h"
@@ -140,6 +141,7 @@ struct host1x {
struct mutex syncpt_mutex;
struct host1x_channel_list channel_list;
+ struct host1x_context_list context_list;
struct dentry *debugfs;
@@ -396,4 +396,21 @@ int tegra_mipi_disable(struct tegra_mipi_device *device);
int tegra_mipi_start_calibration(struct tegra_mipi_device *device);
int tegra_mipi_finish_calibration(struct tegra_mipi_device *device);
+/* host1x context devices */
+
+struct host1x_context {
+ struct host1x *host;
+
+ refcount_t ref;
+ struct pid *owner;
+
+ struct device dev;
+ u32 stream_id;
+};
+
+struct host1x_context *host1x_context_alloc(struct host1x *host1x,
+ struct pid *pid);
+void host1x_context_get(struct host1x_context *cd);
+void host1x_context_put(struct host1x_context *cd);
+
#endif
Add code to register context devices from device tree, allocate them out and manage their refcounts. Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com> --- v2: * Directly set DMA mask instead of inheriting from Host1x. * Use iommu-map instead of custom DT property. --- drivers/gpu/host1x/Makefile | 1 + drivers/gpu/host1x/context.c | 174 +++++++++++++++++++++++++++++++++++ drivers/gpu/host1x/context.h | 27 ++++++ drivers/gpu/host1x/dev.c | 12 ++- drivers/gpu/host1x/dev.h | 2 + include/linux/host1x.h | 17 ++++ 6 files changed, 232 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/host1x/context.c create mode 100644 drivers/gpu/host1x/context.h