From: Mikko Perttunen mperttunen@nvidia.com
*** New in v5:
Rebased Renamed host1x_context to host1x_memory_context Small change in DRM side client driver ops to reduce churn with some upcoming changes Add NVDEC support
***
*** New in v4:
Addressed review comments. See individual patches. ***
*** New in v3:
Added device tree bindings for new property. ***
*** New in v2:
Added support for Tegra194 Use standard iommu-map property instead of custom mechanism ***
This series adds support for Host1x 'context isolation'. Since when programming engines through Host1x, userspace can program in any addresses it wants, we need some way to isolate the engines' memory spaces. Traditionally this has either been done imperfectly with a single shared IOMMU domain, or by copying and verifying the programming command stream at submit time (Host1x firewall).
Since Tegra186 there is a privileged (only usable by kernel) Host1x opcode that allows setting the stream ID sent by the engine to the SMMU. So, by allocating a number of context banks and stream IDs for this purpose, and using this opcode at the beginning of each job, we can implement isolation. Due to the limited number of context banks only each process gets its own context, and not each channel.
This feature also allows sharing engines among multiple VMs when used with Host1x's hardware virtualization support - up to 8 VMs can be configured with a subset of allowed stream IDs, enforced at hardware level.
To implement this, this series adds a new host1x context bus, which will contain the 'struct device's corresponding to each context bank / stream ID, changes to device tree and SMMU code to allow registering the devices and using the bus, as well as the Host1x stream ID programming code and support in TegraDRM.
------------- Merging notes -------------
The changes to DT bindings should be applied on top of Thierry's patch 'dt-bindings: display: tegra: Convert to json-schema'.
Thanks, Mikko
Mikko Perttunen (9): dt-bindings: host1x: Add iommu-map property gpu: host1x: Add context bus gpu: host1x: Add context device management code gpu: host1x: Program context stream ID on submission iommu/arm-smmu: Attach to host1x context device bus arm64: tegra: Add Host1x context stream IDs on Tegra186+ drm/tegra: falcon: Set DMACTX field on DMA transactions drm/tegra: Support context isolation drm/tegra: Implement stream ID related callbacks on engines
.../display/tegra/nvidia,tegra20-host1x.yaml | 5 + arch/arm64/boot/dts/nvidia/tegra186.dtsi | 11 ++ arch/arm64/boot/dts/nvidia/tegra194.dtsi | 11 ++ drivers/gpu/Makefile | 3 +- drivers/gpu/drm/tegra/drm.h | 11 ++ drivers/gpu/drm/tegra/falcon.c | 8 + drivers/gpu/drm/tegra/falcon.h | 1 + drivers/gpu/drm/tegra/nvdec.c | 9 + drivers/gpu/drm/tegra/submit.c | 48 +++++- drivers/gpu/drm/tegra/uapi.c | 43 ++++- drivers/gpu/drm/tegra/vic.c | 67 +++++++- drivers/gpu/host1x/Kconfig | 5 + drivers/gpu/host1x/Makefile | 2 + drivers/gpu/host1x/context.c | 160 ++++++++++++++++++ drivers/gpu/host1x/context.h | 27 +++ drivers/gpu/host1x/context_bus.c | 31 ++++ drivers/gpu/host1x/dev.c | 12 +- drivers/gpu/host1x/dev.h | 2 + drivers/gpu/host1x/hw/channel_hw.c | 52 +++++- drivers/gpu/host1x/hw/host1x06_hardware.h | 10 ++ drivers/gpu/host1x/hw/host1x07_hardware.h | 10 ++ drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 ++ include/linux/host1x.h | 26 +++ include/linux/host1x_context_bus.h | 15 ++ 24 files changed, 564 insertions(+), 18 deletions(-) create mode 100644 drivers/gpu/host1x/context.c create mode 100644 drivers/gpu/host1x/context.h create mode 100644 drivers/gpu/host1x/context_bus.c create mode 100644 include/linux/host1x_context_bus.h
From: Mikko Perttunen mperttunen@nvidia.com
Add schema information for specifying context stream IDs. This uses the standard iommu-map property.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com Reviewed-by: Robin Murphy robin.murphy@arm.com --- v3: * New patch v4: * Remove memory-contexts subnode. --- .../bindings/display/tegra/nvidia,tegra20-host1x.yaml | 5 +++++ 1 file changed, 5 insertions(+)
diff --git a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.yaml b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.yaml index 4fd513efb0f7..0adeb03b9e3a 100644 --- a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.yaml +++ b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.yaml @@ -144,6 +144,11 @@ allOf: reset-names: maxItems: 1
+ iommu-map: + description: Specification of stream IDs available for memory context device + use. Should be a mapping of IDs 0..n to IOMMU entries corresponding to + usable stream IDs. + required: - reg-names
On Mon, 16 May 2022 11:52:50 +0300, cyndis@kapsi.fi wrote:
From: Mikko Perttunen mperttunen@nvidia.com
Add schema information for specifying context stream IDs. This uses the standard iommu-map property.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com Reviewed-by: Robin Murphy robin.murphy@arm.com
v3:
- New patch
v4:
- Remove memory-contexts subnode.
.../bindings/display/tegra/nvidia,tegra20-host1x.yaml | 5 +++++ 1 file changed, 5 insertions(+)
Acked-by: Rob Herring robh@kernel.org
From: Mikko Perttunen mperttunen@nvidia.com
The context bus is a "dummy" bus that contains struct devices that correspond to IOMMU contexts assigned through Host1x to processes.
Even when host1x itself is built as a module, the bus is registered in built-in code so that the built-in ARM SMMU driver is able to reference it.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- v4: * Export bus as GPL --- drivers/gpu/Makefile | 3 +-- drivers/gpu/host1x/Kconfig | 5 +++++ drivers/gpu/host1x/Makefile | 1 + drivers/gpu/host1x/context_bus.c | 31 ++++++++++++++++++++++++++++++ include/linux/host1x_context_bus.h | 15 +++++++++++++++ 5 files changed, 53 insertions(+), 2 deletions(-) create mode 100644 drivers/gpu/host1x/context_bus.c create mode 100644 include/linux/host1x_context_bus.h
diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile index 835c88318cec..8997f0096545 100644 --- a/drivers/gpu/Makefile +++ b/drivers/gpu/Makefile @@ -2,7 +2,6 @@ # drm/tegra depends on host1x, so if both drivers are built-in care must be # taken to initialize them in the correct order. Link order is the only way # to ensure this currently. -obj-$(CONFIG_TEGRA_HOST1X) += host1x/ -obj-y += drm/ vga/ +obj-y += host1x/ drm/ vga/ obj-$(CONFIG_IMX_IPUV3_CORE) += ipu-v3/ obj-$(CONFIG_TRACE_GPU_MEM) += trace/ diff --git a/drivers/gpu/host1x/Kconfig b/drivers/gpu/host1x/Kconfig index 6815b4db17c1..1861a8180d3f 100644 --- a/drivers/gpu/host1x/Kconfig +++ b/drivers/gpu/host1x/Kconfig @@ -1,8 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only + +config TEGRA_HOST1X_CONTEXT_BUS + bool + config TEGRA_HOST1X tristate "NVIDIA Tegra host1x driver" depends on ARCH_TEGRA || (ARM && COMPILE_TEST) select DMA_SHARED_BUFFER + select TEGRA_HOST1X_CONTEXT_BUS select IOMMU_IOVA help Driver for the NVIDIA Tegra host1x hardware. diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile index d2b6f7de0498..c891a3e33844 100644 --- a/drivers/gpu/host1x/Makefile +++ b/drivers/gpu/host1x/Makefile @@ -18,3 +18,4 @@ host1x-y = \ hw/host1x07.o
obj-$(CONFIG_TEGRA_HOST1X) += host1x.o +obj-$(CONFIG_TEGRA_HOST1X_CONTEXT_BUS) += context_bus.o diff --git a/drivers/gpu/host1x/context_bus.c b/drivers/gpu/host1x/context_bus.c new file mode 100644 index 000000000000..b0d35b2bbe89 --- /dev/null +++ b/drivers/gpu/host1x/context_bus.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, NVIDIA Corporation. + */ + +#include <linux/device.h> +#include <linux/of.h> + +struct bus_type host1x_context_device_bus_type = { + .name = "host1x-context", +}; +EXPORT_SYMBOL_GPL(host1x_context_device_bus_type); + +static int __init host1x_context_device_bus_init(void) +{ + int err; + + if (!of_machine_is_compatible("nvidia,tegra186") && + !of_machine_is_compatible("nvidia,tegra194") && + !of_machine_is_compatible("nvidia,tegra234")) + return 0; + + err = bus_register(&host1x_context_device_bus_type); + if (err < 0) { + pr_err("bus type registration failed: %d\n", err); + return err; + } + + return 0; +} +postcore_initcall(host1x_context_device_bus_init); diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h new file mode 100644 index 000000000000..72462737a6db --- /dev/null +++ b/include/linux/host1x_context_bus.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021, NVIDIA Corporation. All rights reserved. + */ + +#ifndef __LINUX_HOST1X_CONTEXT_BUS_H +#define __LINUX_HOST1X_CONTEXT_BUS_H + +#include <linux/device.h> + +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS +extern struct bus_type host1x_context_device_bus_type; +#endif + +#endif
From: Mikko Perttunen mperttunen@nvidia.com
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. v4: * Use u64 instead of dma_addr_t for DMA mask * Use unsigned ints for indexes and adjust error handling flow * Parse iommu-map property at top level host1x DT node * Use separate DMA mask per device * Export symbols as GPL v5: * Rename host1x_context to host1x_memory_context --- drivers/gpu/host1x/Makefile | 1 + drivers/gpu/host1x/context.c | 160 +++++++++++++++++++++++++++++++++++ drivers/gpu/host1x/context.h | 27 ++++++ drivers/gpu/host1x/dev.c | 12 ++- drivers/gpu/host1x/dev.h | 2 + include/linux/host1x.h | 18 ++++ 6 files changed, 219 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/host1x/context.c create mode 100644 drivers/gpu/host1x/context.h
diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile index c891a3e33844..8a65e13d113a 100644 --- a/drivers/gpu/host1x/Makefile +++ b/drivers/gpu/host1x/Makefile @@ -10,6 +10,7 @@ host1x-y = \ debug.o \ mipi.o \ fence.o \ + context.o \ hw/host1x01.o \ hw/host1x02.o \ hw/host1x04.o \ diff --git a/drivers/gpu/host1x/context.c b/drivers/gpu/host1x/context.c new file mode 100644 index 000000000000..d7d95b69a72a --- /dev/null +++ b/drivers/gpu/host1x/context.c @@ -0,0 +1,160 @@ +// 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" + +int host1x_memory_context_list_init(struct host1x *host1x) +{ + struct host1x_memory_context_list *cdl = &host1x->context_list; + struct device_node *node = host1x->dev->of_node; + struct host1x_memory_context *ctx; + unsigned int i; + int err; + + cdl->devs = NULL; + cdl->len = 0; + mutex_init(&cdl->lock); + + err = of_property_count_u32_elems(node, "iommu-map"); + if (err < 0) + return 0; + + cdl->devs = kcalloc(err, sizeof(*cdl->devs), GFP_KERNEL); + if (!cdl->devs) + return -ENOMEM; + cdl->len = err / 4; + + for (i = 0; i < cdl->len; i++) { + struct iommu_fwspec *fwspec; + + ctx = &cdl->devs[i]; + + ctx->host = host1x; + + device_initialize(&ctx->dev); + + /* + * Due to an issue with T194 NVENC, only 38 bits can be used. + * Anyway, 256GiB of IOVA ought to be enough for anyone. + */ + ctx->dma_mask = DMA_BIT_MASK(38); + ctx->dev.dma_mask = &ctx->dma_mask; + ctx->dev.coherent_dma_mask = ctx->dma_mask; + dev_set_name(&ctx->dev, "host1x-ctx.%d", i); + 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", i, err); + goto del_devices; + } + + err = of_dma_configure_id(&ctx->dev, node, true, &i); + if (err) { + dev_err(host1x->dev, "IOMMU configuration failed for context device %d: %d\n", + i, 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", i); + device_del(&ctx->dev); + goto del_devices; + } + + ctx->stream_id = fwspec->ids[0] & 0xffff; + } + + return 0; + +del_devices: + while (i--) + device_del(&cdl->devs[i].dev); + + kfree(cdl->devs); + cdl->len = 0; + + return err; +} + +void host1x_memory_context_list_free(struct host1x_memory_context_list *cdl) +{ + unsigned int i; + + for (i = 0; i < cdl->len; i++) + device_del(&cdl->devs[i].dev); + + kfree(cdl->devs); + cdl->len = 0; +} + +struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x, + struct pid *pid) +{ + struct host1x_memory_context_list *cdl = &host1x->context_list; + struct host1x_memory_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_memory_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_GPL(host1x_memory_context_alloc); + +void host1x_memory_context_get(struct host1x_memory_context *cd) +{ + refcount_inc(&cd->ref); +} +EXPORT_SYMBOL_GPL(host1x_memory_context_get); + +void host1x_memory_context_put(struct host1x_memory_context *cd) +{ + struct host1x_memory_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_GPL(host1x_memory_context_put); diff --git a/drivers/gpu/host1x/context.h b/drivers/gpu/host1x/context.h new file mode 100644 index 000000000000..db8ff0a1f4f3 --- /dev/null +++ b/drivers/gpu/host1x/context.h @@ -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_memory_context_list { + struct mutex lock; + struct host1x_memory_context *devs; + unsigned int len; +}; + +int host1x_memory_context_list_init(struct host1x *host1x); +void host1x_memory_context_list_free(struct host1x_memory_context_list *cdl); + +#endif diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 80c685ab3e30..89cc79a48eab 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -28,6 +28,7 @@
#include "bus.h" #include "channel.h" +#include "context.h" #include "debug.h" #include "dev.h" #include "intr.h" @@ -503,10 +504,16 @@ static int host1x_probe(struct platform_device *pdev) goto iommu_exit; }
+ err = host1x_memory_context_list_init(host); + if (err) { + dev_err(&pdev->dev, "failed to initialize context list\n"); + goto free_channels; + } + err = host1x_syncpt_init(host); if (err) { dev_err(&pdev->dev, "failed to initialize syncpts\n"); - goto free_channels; + goto free_contexts; }
err = host1x_intr_init(host, syncpt_irq); @@ -550,6 +557,8 @@ static int host1x_probe(struct platform_device *pdev) host1x_intr_deinit(host); deinit_syncpt: host1x_syncpt_deinit(host); +free_contexts: + host1x_memory_context_list_free(&host->context_list); free_channels: host1x_channel_list_free(&host->channel_list); iommu_exit: @@ -571,6 +580,7 @@ static int host1x_remove(struct platform_device *pdev)
host1x_intr_deinit(host); host1x_syncpt_deinit(host); + host1x_memory_context_list_free(&host->context_list); host1x_channel_list_free(&host->channel_list); host1x_iommu_exit(host); host1x_bo_cache_destroy(&host->cache); diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index ca4b082f0cd4..7552a4554534 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -14,6 +14,7 @@
#include "cdma.h" #include "channel.h" +#include "context.h" #include "intr.h" #include "job.h" #include "syncpt.h" @@ -141,6 +142,7 @@ struct host1x { struct mutex syncpt_mutex;
struct host1x_channel_list channel_list; + struct host1x_memory_context_list context_list;
struct dentry *debugfs;
diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e8dc5bc41f79..75cf996b0087 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -440,4 +440,22 @@ 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 memory contexts */ + +struct host1x_memory_context { + struct host1x *host; + + refcount_t ref; + struct pid *owner; + + struct device dev; + u64 dma_mask; + u32 stream_id; +}; + +struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x, + struct pid *pid); +void host1x_memory_context_get(struct host1x_memory_context *cd); +void host1x_memory_context_put(struct host1x_memory_context *cd); + #endif
From: Mikko Perttunen mperttunen@nvidia.com
Add code to do stream ID switching at the beginning of a job. The stream ID is switched to the stream ID specified by the context passed in the job structure.
Before switching the stream ID, an OP_DONE wait is done on the channel's engine to ensure that there is no residual ongoing work that might do DMA using the new stream ID.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- v5: * Add fallback stream ID. Not used yet, will be needed for full featured opcode sequence. * Rename host1x_context to host1x_memory_context v4: * Rename job->context to job->memory_context for clarity --- drivers/gpu/host1x/hw/channel_hw.c | 52 +++++++++++++++++++++-- drivers/gpu/host1x/hw/host1x06_hardware.h | 10 +++++ drivers/gpu/host1x/hw/host1x07_hardware.h | 10 +++++ include/linux/host1x.h | 8 ++++ 4 files changed, 76 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 6b40e9af1e88..f84caf06621a 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -180,6 +180,45 @@ static void host1x_enable_gather_filter(struct host1x_channel *ch) #endif }
+static void host1x_channel_program_engine_streamid(struct host1x_job *job) +{ +#if HOST1X_HW >= 6 + u32 fence; + + if (!job->memory_context) + return; + + fence = host1x_syncpt_incr_max(job->syncpt, 1); + + /* First, increment a syncpoint on OP_DONE condition.. */ + + host1x_cdma_push(&job->channel->cdma, + host1x_opcode_nonincr(HOST1X_UCLASS_INCR_SYNCPT, 1), + HOST1X_UCLASS_INCR_SYNCPT_INDX_F(job->syncpt->id) | + HOST1X_UCLASS_INCR_SYNCPT_COND_F(1)); + + /* Wait for syncpoint to increment */ + + host1x_cdma_push(&job->channel->cdma, + host1x_opcode_setclass(HOST1X_CLASS_HOST1X, + host1x_uclass_wait_syncpt_r(), 1), + host1x_class_host_wait_syncpt(job->syncpt->id, fence)); + + /* + * Now that we know the engine is idle, return to class and + * change stream ID. + */ + + host1x_cdma_push(&job->channel->cdma, + host1x_opcode_setclass(job->class, 0, 0), + HOST1X_OPCODE_NOP); + + host1x_cdma_push(&job->channel->cdma, + host1x_opcode_setpayload(job->memory_context->stream_id), + host1x_opcode_setstreamid(job->engine_streamid_offset / 4)); +#endif +} + static int channel_submit(struct host1x_job *job) { struct host1x_channel *ch = job->channel; @@ -236,18 +275,23 @@ static int channel_submit(struct host1x_job *job) if (sp->base) synchronize_syncpt_base(job);
- syncval = host1x_syncpt_incr_max(sp, user_syncpt_incrs); - host1x_hw_syncpt_assign_to_channel(host, sp, ch);
- job->syncpt_end = syncval; - /* add a setclass for modules that require it */ if (job->class) host1x_cdma_push(&ch->cdma, host1x_opcode_setclass(job->class, 0, 0), HOST1X_OPCODE_NOP);
+ /* + * Ensure engine DMA is idle and set new stream ID. May increment + * syncpt max. + */ + host1x_channel_program_engine_streamid(job); + + syncval = host1x_syncpt_incr_max(sp, user_syncpt_incrs); + job->syncpt_end = syncval; + submit_gathers(job, syncval - user_syncpt_incrs);
/* end CDMA submit & stash pinned hMems into sync queue */ diff --git a/drivers/gpu/host1x/hw/host1x06_hardware.h b/drivers/gpu/host1x/hw/host1x06_hardware.h index 01a142a09800..5d515745eee7 100644 --- a/drivers/gpu/host1x/hw/host1x06_hardware.h +++ b/drivers/gpu/host1x/hw/host1x06_hardware.h @@ -127,6 +127,16 @@ static inline u32 host1x_opcode_gather_incr(unsigned offset, unsigned count) return (6 << 28) | (offset << 16) | BIT(15) | BIT(14) | count; }
+static inline u32 host1x_opcode_setstreamid(unsigned streamid) +{ + return (7 << 28) | streamid; +} + +static inline u32 host1x_opcode_setpayload(unsigned payload) +{ + return (9 << 28) | payload; +} + static inline u32 host1x_opcode_gather_wide(unsigned count) { return (12 << 28) | count; diff --git a/drivers/gpu/host1x/hw/host1x07_hardware.h b/drivers/gpu/host1x/hw/host1x07_hardware.h index e6582172ebfd..82c0cc9bb0b5 100644 --- a/drivers/gpu/host1x/hw/host1x07_hardware.h +++ b/drivers/gpu/host1x/hw/host1x07_hardware.h @@ -127,6 +127,16 @@ static inline u32 host1x_opcode_gather_incr(unsigned offset, unsigned count) return (6 << 28) | (offset << 16) | BIT(15) | BIT(14) | count; }
+static inline u32 host1x_opcode_setstreamid(unsigned streamid) +{ + return (7 << 28) | streamid; +} + +static inline u32 host1x_opcode_setpayload(unsigned payload) +{ + return (9 << 28) | payload; +} + static inline u32 host1x_opcode_gather_wide(unsigned count) { return (12 << 28) | count; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 75cf996b0087..1b7dd67c7801 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -321,6 +321,14 @@ struct host1x_job {
/* Whether host1x-side firewall should be ran for this job or not */ bool enable_firewall; + + /* Options for configuring engine data stream ID */ + /* Context device to use for job */ + struct host1x_memory_context *memory_context; + /* Stream ID to use if context isolation is disabled (!memory_context) */ + u32 engine_fallback_streamid; + /* Engine offset to program stream ID to */ + u32 engine_streamid_offset; };
struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
From: Mikko Perttunen mperttunen@nvidia.com
Set itself as the IOMMU for the host1x context device bus, containing "dummy" devices used for Host1x context isolation.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 568cce590ccc..9ff54eaecf81 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -39,6 +39,7 @@
#include <linux/amba/bus.h> #include <linux/fsl/mc.h> +#include <linux/host1x_context_bus.h>
#include "arm-smmu.h"
@@ -2053,8 +2054,20 @@ static int arm_smmu_bus_init(struct iommu_ops *ops) goto err_reset_pci_ops; } #endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS + if (!iommu_present(&host1x_context_device_bus_type)) { + err = bus_set_iommu(&host1x_context_device_bus_type, ops); + if (err) + goto err_reset_fsl_mc_ops; + } +#endif + return 0;
+err_reset_fsl_mc_ops: __maybe_unused; +#ifdef CONFIG_FSL_MC_BUS + bus_set_iommu(&fsl_mc_bus_type, NULL); +#endif err_reset_pci_ops: __maybe_unused; #ifdef CONFIG_PCI bus_set_iommu(&pci_bus_type, NULL);
On Mon, May 16, 2022 at 11:52:54AM +0300, cyndis@kapsi.fi wrote:
From: Mikko Perttunen mperttunen@nvidia.com
Set itself as the IOMMU for the host1x context device bus, containing "dummy" devices used for Host1x context isolation.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com
drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 568cce590ccc..9ff54eaecf81 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -39,6 +39,7 @@
#include <linux/amba/bus.h> #include <linux/fsl/mc.h> +#include <linux/host1x_context_bus.h>
#include "arm-smmu.h"
@@ -2053,8 +2054,20 @@ static int arm_smmu_bus_init(struct iommu_ops *ops) goto err_reset_pci_ops; } #endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS
- if (!iommu_present(&host1x_context_device_bus_type)) {
err = bus_set_iommu(&host1x_context_device_bus_type, ops);if (err)goto err_reset_fsl_mc_ops;- }
+#endif
- return 0;
+err_reset_fsl_mc_ops: __maybe_unused; +#ifdef CONFIG_FSL_MC_BUS
- bus_set_iommu(&fsl_mc_bus_type, NULL);
+#endif
bus_set_iommu() is going away:
https://lore.kernel.org/r/cover.1650890638.git.robin.murphy@arm.com
Will
On 5/16/22 13:07, Will Deacon wrote:
On Mon, May 16, 2022 at 11:52:54AM +0300, cyndis@kapsi.fi wrote:
From: Mikko Perttunen mperttunen@nvidia.com
Set itself as the IOMMU for the host1x context device bus, containing "dummy" devices used for Host1x context isolation.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com
drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 568cce590ccc..9ff54eaecf81 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -39,6 +39,7 @@
#include <linux/amba/bus.h> #include <linux/fsl/mc.h> +#include <linux/host1x_context_bus.h>
#include "arm-smmu.h"
@@ -2053,8 +2054,20 @@ static int arm_smmu_bus_init(struct iommu_ops *ops) goto err_reset_pci_ops; } #endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS
- if (!iommu_present(&host1x_context_device_bus_type)) {
err = bus_set_iommu(&host1x_context_device_bus_type, ops);if (err)goto err_reset_fsl_mc_ops;- }
+#endif
- return 0;
+err_reset_fsl_mc_ops: __maybe_unused; +#ifdef CONFIG_FSL_MC_BUS
- bus_set_iommu(&fsl_mc_bus_type, NULL);
+#endif
bus_set_iommu() is going away:
https://lore.kernel.org/r/cover.1650890638.git.robin.murphy@arm.com
Will
Thanks for the heads-up. Robin had pointed out that this work was ongoing but I hadn't seen the patches yet. I'll look into it.
Mikko
On 2022-05-16 11:13, Mikko Perttunen wrote:
On 5/16/22 13:07, Will Deacon wrote:
On Mon, May 16, 2022 at 11:52:54AM +0300, cyndis@kapsi.fi wrote:
From: Mikko Perttunen mperttunen@nvidia.com
Set itself as the IOMMU for the host1x context device bus, containing "dummy" devices used for Host1x context isolation.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com
drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 568cce590ccc..9ff54eaecf81 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -39,6 +39,7 @@ #include <linux/amba/bus.h> #include <linux/fsl/mc.h> +#include <linux/host1x_context_bus.h> #include "arm-smmu.h" @@ -2053,8 +2054,20 @@ static int arm_smmu_bus_init(struct iommu_ops *ops) goto err_reset_pci_ops; } #endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS + if (!iommu_present(&host1x_context_device_bus_type)) { + err = bus_set_iommu(&host1x_context_device_bus_type, ops); + if (err) + goto err_reset_fsl_mc_ops; + } +#endif
return 0; +err_reset_fsl_mc_ops: __maybe_unused; +#ifdef CONFIG_FSL_MC_BUS + bus_set_iommu(&fsl_mc_bus_type, NULL); +#endif
bus_set_iommu() is going away:
https://lore.kernel.org/r/cover.1650890638.git.robin.murphy@arm.com
Will
Thanks for the heads-up. Robin had pointed out that this work was ongoing but I hadn't seen the patches yet. I'll look into it.
Although that *is* currently blocked on the mystery intel-iommu problem that I can't reproduce... If this series is ready to land right now for 5.19 then in principle that might be the easiest option overall. Hopefully at least patch #2 could sneak in so that the compile-time dependencies are ready for me to roll up host1x into the next rebase of "iommu: Always register bus notifiers".
Cheers, Robin.
On 5/16/22 13:44, Robin Murphy wrote:
On 2022-05-16 11:13, Mikko Perttunen wrote:
On 5/16/22 13:07, Will Deacon wrote:
On Mon, May 16, 2022 at 11:52:54AM +0300, cyndis@kapsi.fi wrote:
From: Mikko Perttunen mperttunen@nvidia.com
Set itself as the IOMMU for the host1x context device bus, containing "dummy" devices used for Host1x context isolation.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com
drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 568cce590ccc..9ff54eaecf81 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -39,6 +39,7 @@ #include <linux/amba/bus.h> #include <linux/fsl/mc.h> +#include <linux/host1x_context_bus.h> #include "arm-smmu.h" @@ -2053,8 +2054,20 @@ static int arm_smmu_bus_init(struct iommu_ops *ops) goto err_reset_pci_ops; } #endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS + if (!iommu_present(&host1x_context_device_bus_type)) { + err = bus_set_iommu(&host1x_context_device_bus_type, ops); + if (err) + goto err_reset_fsl_mc_ops; + } +#endif
return 0; +err_reset_fsl_mc_ops: __maybe_unused; +#ifdef CONFIG_FSL_MC_BUS + bus_set_iommu(&fsl_mc_bus_type, NULL); +#endif
bus_set_iommu() is going away:
https://lore.kernel.org/r/cover.1650890638.git.robin.murphy@arm.com
Will
Thanks for the heads-up. Robin had pointed out that this work was ongoing but I hadn't seen the patches yet. I'll look into it.
Although that *is* currently blocked on the mystery intel-iommu problem that I can't reproduce... If this series is ready to land right now for 5.19 then in principle that might be the easiest option overall. Hopefully at least patch #2 could sneak in so that the compile-time dependencies are ready for me to roll up host1x into the next rebase of "iommu: Always register bus notifiers".
Cheers, Robin.
My guess is that the series as a whole is not ready to land in the 5.19 timeframe, but #2 could be possible.
Thierry, any opinion?
Thanks, Mikko
On Mon, May 16, 2022 at 02:20:18PM +0300, Mikko Perttunen wrote:
On 5/16/22 13:44, Robin Murphy wrote:
On 2022-05-16 11:13, Mikko Perttunen wrote:
On 5/16/22 13:07, Will Deacon wrote:
On Mon, May 16, 2022 at 11:52:54AM +0300, cyndis@kapsi.fi wrote:
From: Mikko Perttunen mperttunen@nvidia.com
Set itself as the IOMMU for the host1x context device bus, containing "dummy" devices used for Host1x context isolation.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com
drivers/iommu/arm/arm-smmu/arm-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 568cce590ccc..9ff54eaecf81 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -39,6 +39,7 @@ #include <linux/amba/bus.h> #include <linux/fsl/mc.h> +#include <linux/host1x_context_bus.h> #include "arm-smmu.h" @@ -2053,8 +2054,20 @@ static int arm_smmu_bus_init(struct iommu_ops *ops) goto err_reset_pci_ops; } #endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS + if (!iommu_present(&host1x_context_device_bus_type)) { + err = bus_set_iommu(&host1x_context_device_bus_type, ops); + if (err) + goto err_reset_fsl_mc_ops; + } +#endif
return 0; +err_reset_fsl_mc_ops: __maybe_unused; +#ifdef CONFIG_FSL_MC_BUS + bus_set_iommu(&fsl_mc_bus_type, NULL); +#endif
bus_set_iommu() is going away:
https://lore.kernel.org/r/cover.1650890638.git.robin.murphy@arm.com
Will
Thanks for the heads-up. Robin had pointed out that this work was ongoing but I hadn't seen the patches yet. I'll look into it.
Although that *is* currently blocked on the mystery intel-iommu problem that I can't reproduce... If this series is ready to land right now for 5.19 then in principle that might be the easiest option overall. Hopefully at least patch #2 could sneak in so that the compile-time dependencies are ready for me to roll up host1x into the next rebase of "iommu: Always register bus notifiers".
Cheers, Robin.
My guess is that the series as a whole is not ready to land in the 5.19 timeframe, but #2 could be possible.
Thierry, any opinion?
Dave and Daniel typically want new material to be in by -rc6 and I've already sent the PR for this cycle. I can ask them if they'd take another one, though, if it make things simpler for the next cycle.
Thierry
From: Mikko Perttunen mperttunen@nvidia.com
Add Host1x context stream IDs on systems that support Host1x context isolation. Host1x and attached engines can use these stream IDs to allow isolation between memory used by different processes.
The specified stream IDs must match those configured by the hypervisor, if one is present.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- v2: * Added context devices on T194. * Use iommu-map instead of custom property. v4: * Remove memory-contexts subnode. --- arch/arm64/boot/dts/nvidia/tegra186.dtsi | 11 +++++++++++ arch/arm64/boot/dts/nvidia/tegra194.dtsi | 11 +++++++++++ 2 files changed, 22 insertions(+)
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index 0e9afc3e2f26..5f560f13ed93 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -1461,6 +1461,17 @@ host1x@13e00000 {
iommus = <&smmu TEGRA186_SID_HOST1X>;
+ /* Context isolation domains */ + iommu-map = < + 0 &smmu TEGRA186_SID_HOST1X_CTX0 1 + 1 &smmu TEGRA186_SID_HOST1X_CTX1 1 + 2 &smmu TEGRA186_SID_HOST1X_CTX2 1 + 3 &smmu TEGRA186_SID_HOST1X_CTX3 1 + 4 &smmu TEGRA186_SID_HOST1X_CTX4 1 + 5 &smmu TEGRA186_SID_HOST1X_CTX5 1 + 6 &smmu TEGRA186_SID_HOST1X_CTX6 1 + 7 &smmu TEGRA186_SID_HOST1X_CTX7 1>; + dpaux1: dpaux@15040000 { compatible = "nvidia,tegra186-dpaux"; reg = <0x15040000 0x10000>; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index d1f8248c00f4..613fd71dec25 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1769,6 +1769,17 @@ host1x@13e00000 { interconnect-names = "dma-mem"; iommus = <&smmu TEGRA194_SID_HOST1X>;
+ /* Context isolation domains */ + iommu-map = < + 0 &smmu TEGRA194_SID_HOST1X_CTX0 1 + 1 &smmu TEGRA194_SID_HOST1X_CTX1 1 + 2 &smmu TEGRA194_SID_HOST1X_CTX2 1 + 3 &smmu TEGRA194_SID_HOST1X_CTX3 1 + 4 &smmu TEGRA194_SID_HOST1X_CTX4 1 + 5 &smmu TEGRA194_SID_HOST1X_CTX5 1 + 6 &smmu TEGRA194_SID_HOST1X_CTX6 1 + 7 &smmu TEGRA194_SID_HOST1X_CTX7 1>; + nvdec@15140000 { compatible = "nvidia,tegra194-nvdec"; reg = <0x15140000 0x00040000>;
From: Mikko Perttunen mperttunen@nvidia.com
The DMACTX field determines which context, as specified in the TRANSCFG register, is used. While during boot it doesn't matter which is used, later on it matters and this value is reused by the firmware.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- drivers/gpu/drm/tegra/falcon.c | 8 ++++++++ drivers/gpu/drm/tegra/falcon.h | 1 + 2 files changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/tegra/falcon.c b/drivers/gpu/drm/tegra/falcon.c index 3762d87759d9..c0d85463eb1a 100644 --- a/drivers/gpu/drm/tegra/falcon.c +++ b/drivers/gpu/drm/tegra/falcon.c @@ -48,6 +48,14 @@ static int falcon_copy_chunk(struct falcon *falcon, if (target == FALCON_MEMORY_IMEM) cmd |= FALCON_DMATRFCMD_IMEM;
+ /* + * Use second DMA context (i.e. the one for firmware). Strictly + * speaking, at this point both DMA contexts point to the firmware + * stream ID, but this register's value will be reused by the firmware + * for later DMA transactions, so we need to use the correct value. + */ + cmd |= FALCON_DMATRFCMD_DMACTX(1); + falcon_writel(falcon, offset, FALCON_DMATRFMOFFS); falcon_writel(falcon, base, FALCON_DMATRFFBOFFS); falcon_writel(falcon, cmd, FALCON_DMATRFCMD); diff --git a/drivers/gpu/drm/tegra/falcon.h b/drivers/gpu/drm/tegra/falcon.h index c56ee32d92ee..1955cf11a8a6 100644 --- a/drivers/gpu/drm/tegra/falcon.h +++ b/drivers/gpu/drm/tegra/falcon.h @@ -50,6 +50,7 @@ #define FALCON_DMATRFCMD_IDLE (1 << 1) #define FALCON_DMATRFCMD_IMEM (1 << 4) #define FALCON_DMATRFCMD_SIZE_256B (6 << 8) +#define FALCON_DMATRFCMD_DMACTX(v) (((v) & 0x7) << 12)
#define FALCON_DMATRFFBOFFS 0x0000111c
From: Mikko Perttunen mperttunen@nvidia.com
For engines that support context isolation, allocate a context when opening a channel, and set up stream ID offset and context fields when submitting a job.
As of this commit, the stream ID offset and fallback stream ID are not used when context isolation is disabled. However, with upcoming patches that enable a full featured job opcode sequence, these will be necessary.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- v5: * On supporting engines, always program stream ID offset and new fallback stream ID. * Rename host1x_context to host1x_memory_context v4: * Separate error and output values in get_streamid_offset API * Improve error handling * Rename job->context to job->memory_context for clarity --- drivers/gpu/drm/tegra/drm.h | 3 +++ drivers/gpu/drm/tegra/submit.c | 48 +++++++++++++++++++++++++++++++++- drivers/gpu/drm/tegra/uapi.c | 43 ++++++++++++++++++++++++++++-- 3 files changed, 91 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index fc0a19554eac..2acc8f2948ad 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -80,6 +80,7 @@ struct tegra_drm_context {
/* Only used by new UAPI. */ struct xarray mappings; + struct host1x_memory_context *memory_context; };
struct tegra_drm_client_ops { @@ -91,6 +92,8 @@ struct tegra_drm_client_ops { int (*submit)(struct tegra_drm_context *context, struct drm_tegra_submit *args, struct drm_device *drm, struct drm_file *file); + int (*get_streamid_offset)(struct tegra_drm_client *client, u32 *offset); + int (*can_use_memory_ctx)(struct tegra_drm_client *client, bool *supported); };
int tegra_drm_submit(struct tegra_drm_context *context, diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c index 6d6dd8c35475..b24738bdf3df 100644 --- a/drivers/gpu/drm/tegra/submit.c +++ b/drivers/gpu/drm/tegra/submit.c @@ -498,6 +498,9 @@ static void release_job(struct host1x_job *job) struct tegra_drm_submit_data *job_data = job->user_data; u32 i;
+ if (job->memory_context) + host1x_memory_context_put(job->memory_context); + for (i = 0; i < job_data->num_used_mappings; i++) tegra_drm_mapping_put(job_data->used_mappings[i].mapping);
@@ -588,11 +591,51 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data, goto put_job; }
+ if (context->client->ops->get_streamid_offset) { + err = context->client->ops->get_streamid_offset( + context->client, &job->engine_streamid_offset); + if (err) { + SUBMIT_ERR(context, "failed to get streamid offset: %d", err); + goto unpin_job; + } + } + + if (context->memory_context && context->client->ops->can_use_memory_ctx) { + bool supported; + + err = context->client->ops->can_use_memory_ctx(context->client, &supported); + if (err) { + SUBMIT_ERR(context, "failed to detect if engine can use memory context: %d", err); + goto unpin_job; + } + + if (supported) { + job->memory_context = context->memory_context; + host1x_memory_context_get(job->memory_context); + } + } else if (context->client->ops->get_streamid_offset) { +#ifdef CONFIG_IOMMU_API + struct iommu_fwspec *spec; + + /* + * Job submission will need to temporarily change stream ID, + * so need to tell it what to change it back to. + */ + spec = dev_iommu_fwspec_get(context->client->base.dev); + if (spec && spec->num_ids > 0) + job->engine_fallback_streamid = spec->ids[0] & 0xffff; + else + job->engine_fallback_streamid = 0x7f; +#else + job->engine_fallback_streamid = 0x7f; +#endif + } + /* Boot engine. */ err = pm_runtime_resume_and_get(context->client->base.dev); if (err < 0) { SUBMIT_ERR(context, "could not power up engine: %d", err); - goto unpin_job; + goto put_memory_context; }
job->user_data = job_data; @@ -627,6 +670,9 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data,
goto put_job;
+put_memory_context: + if (job->memory_context) + host1x_memory_context_put(job->memory_context); unpin_job: host1x_job_unpin(job); put_job: diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index 9ab9179d2026..a98239cb0e29 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -33,6 +33,9 @@ static void tegra_drm_channel_context_close(struct tegra_drm_context *context) struct tegra_drm_mapping *mapping; unsigned long id;
+ if (context->memory_context) + host1x_memory_context_put(context->memory_context); + xa_for_each(&context->mappings, id, mapping) tegra_drm_mapping_put(mapping);
@@ -72,6 +75,7 @@ static struct tegra_drm_client *tegra_drm_find_client(struct tegra_drm *tegra, u
int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_file *file) { + struct host1x *host = tegra_drm_to_host1x(drm->dev_private); struct tegra_drm_file *fpriv = file->driver_priv; struct tegra_drm *tegra = drm->dev_private; struct drm_tegra_channel_open *args = data; @@ -102,10 +106,36 @@ int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_ } }
+ /* Only allocate context if the engine supports context isolation. */ + if (device_iommu_mapped(client->base.dev) && client->ops->can_use_memory_ctx) { + bool supported; + + err = client->ops->can_use_memory_ctx(client, &supported); + if (err) + goto put_channel; + + if (supported) + context->memory_context = host1x_memory_context_alloc( + host, get_task_pid(current, PIDTYPE_TGID)); + + if (IS_ERR(context->memory_context)) { + if (PTR_ERR(context->memory_context) != -EOPNOTSUPP) { + err = PTR_ERR(context->memory_context); + goto put_channel; + } else { + /* + * OK, HW does not support contexts or contexts + * are disabled. + */ + context->memory_context = NULL; + } + } + } + err = xa_alloc(&fpriv->contexts, &args->context, context, XA_LIMIT(1, U32_MAX), GFP_KERNEL); if (err < 0) - goto put_channel; + goto put_memctx;
context->client = client; xa_init_flags(&context->mappings, XA_FLAGS_ALLOC1); @@ -118,6 +148,9 @@ int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_
return 0;
+put_memctx: + if (context->memory_context) + host1x_memory_context_put(context->memory_context); put_channel: host1x_channel_put(context->channel); free: @@ -156,6 +189,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f struct tegra_drm_mapping *mapping; struct tegra_drm_context *context; enum dma_data_direction direction; + struct device *mapping_dev; int err = 0;
if (args->flags & ~DRM_TEGRA_CHANNEL_MAP_READ_WRITE) @@ -177,6 +211,11 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f
kref_init(&mapping->ref);
+ if (context->memory_context) + mapping_dev = &context->memory_context->dev; + else + mapping_dev = context->client->base.dev; + mapping->bo = tegra_gem_lookup(file, args->handle); if (!mapping->bo) { err = -EINVAL; @@ -201,7 +240,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f goto put_gem; }
- mapping->map = host1x_bo_pin(context->client->base.dev, mapping->bo, direction, NULL); + mapping->map = host1x_bo_pin(mapping_dev, mapping->bo, direction, NULL); if (IS_ERR(mapping->map)) { err = PTR_ERR(mapping->map); goto put_gem;
From: Mikko Perttunen mperttunen@nvidia.com
Implement the get_streamid_offset and can_use_memory_ctx callbacks required for supporting context isolation. Since old firmware on VIC cannot support context isolation without hacks that we don't want to implement, check the firmware binary to see if context isolation should be enabled.
Signed-off-by: Mikko Perttunen mperttunen@nvidia.com --- v5: * Split into two callbacks * Add NVDEC support v4: * Add locking in vic_load_firmware * Return -EOPNOTSUPP if context isolation is not available * Update for changed get_streamid_offset declaration * Add comment noting that vic_load_firmware is safe to call without the hardware being powered on
Implement context isolation related callbacks in VIC, NVDEC --- drivers/gpu/drm/tegra/drm.h | 8 +++++ drivers/gpu/drm/tegra/nvdec.c | 9 +++++ drivers/gpu/drm/tegra/vic.c | 67 ++++++++++++++++++++++++++++++----- 3 files changed, 76 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index 2acc8f2948ad..845e60f144c7 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -100,6 +100,14 @@ int tegra_drm_submit(struct tegra_drm_context *context, struct drm_tegra_submit *args, struct drm_device *drm, struct drm_file *file);
+static inline int +tegra_drm_get_streamid_offset_thi(struct tegra_drm_client *client, u32 *offset) +{ + *offset = 0x30; + + return 0; +} + struct tegra_drm_client { struct host1x_client base; struct list_head list; diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c index 79e1e88203cf..f1210cfb3708 100644 --- a/drivers/gpu/drm/tegra/nvdec.c +++ b/drivers/gpu/drm/tegra/nvdec.c @@ -304,10 +304,19 @@ static void nvdec_close_channel(struct tegra_drm_context *context) host1x_channel_put(context->channel); }
+static int nvdec_can_use_memory_ctx(struct tegra_drm_client *client, bool *supported) +{ + *supported = true; + + return 0; +} + static const struct tegra_drm_client_ops nvdec_ops = { .open_channel = nvdec_open_channel, .close_channel = nvdec_close_channel, .submit = tegra_drm_submit, + .get_streamid_offset = tegra_drm_get_streamid_offset_thi, + .can_use_memory_ctx = nvdec_can_use_memory_ctx, };
#define NVIDIA_TEGRA_210_NVDEC_FIRMWARE "nvidia/tegra210/nvdec.bin" diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c index 1e342fa3d27b..2c0d554bd13c 100644 --- a/drivers/gpu/drm/tegra/vic.c +++ b/drivers/gpu/drm/tegra/vic.c @@ -38,6 +38,8 @@ struct vic { struct clk *clk; struct reset_control *rst;
+ bool can_use_context; + /* Platform configuration */ const struct vic_config *config; }; @@ -229,28 +231,38 @@ static int vic_load_firmware(struct vic *vic) { struct host1x_client *client = &vic->client.base; struct tegra_drm *tegra = vic->client.drm; + static DEFINE_MUTEX(lock); + u32 fce_bin_data_offset; dma_addr_t iova; size_t size; void *virt; int err;
- if (vic->falcon.firmware.virt) - return 0; + mutex_lock(&lock); + + if (vic->falcon.firmware.virt) { + err = 0; + goto unlock; + }
err = falcon_read_firmware(&vic->falcon, vic->config->firmware); if (err < 0) - return err; + goto unlock;
size = vic->falcon.firmware.size;
if (!client->group) { virt = dma_alloc_coherent(vic->dev, size, &iova, GFP_KERNEL); - if (!virt) - return -ENOMEM; + if (!virt) { + err = -ENOMEM; + goto unlock; + } } else { virt = tegra_drm_alloc(tegra, size, &iova); - if (IS_ERR(virt)) - return PTR_ERR(virt); + if (IS_ERR(virt)) { + err = PTR_ERR(virt); + goto unlock; + } }
vic->falcon.firmware.virt = virt; @@ -277,7 +289,28 @@ static int vic_load_firmware(struct vic *vic) vic->falcon.firmware.phys = phys; }
- return 0; + /* + * Check if firmware is new enough to not require mapping firmware + * to data buffer domains. + */ + fce_bin_data_offset = *(u32 *)(virt + VIC_UCODE_FCE_DATA_OFFSET); + + if (!vic->config->supports_sid) { + vic->can_use_context = false; + } else if (fce_bin_data_offset != 0x0 && fce_bin_data_offset != 0xa5a5a5a5) { + /* + * Firmware will access FCE through STREAMID0, so context + * isolation cannot be used. + */ + vic->can_use_context = false; + dev_warn_once(vic->dev, "context isolation disabled due to old firmware\n"); + } else { + vic->can_use_context = true; + } + +unlock: + mutex_unlock(&lock); + return err;
cleanup: if (!client->group) @@ -285,6 +318,7 @@ static int vic_load_firmware(struct vic *vic) else tegra_drm_free(tegra, size, virt, iova);
+ mutex_unlock(&lock); return err; }
@@ -358,10 +392,27 @@ static void vic_close_channel(struct tegra_drm_context *context) host1x_channel_put(context->channel); }
+static int vic_can_use_memory_ctx(struct tegra_drm_client *client, bool *supported) +{ + struct vic *vic = to_vic(client); + int err; + + /* This doesn't access HW so it's safe to call without powering up. */ + err = vic_load_firmware(vic); + if (err < 0) + return err; + + *supported = vic->can_use_context; + + return 0; +} + static const struct tegra_drm_client_ops vic_ops = { .open_channel = vic_open_channel, .close_channel = vic_close_channel, .submit = tegra_drm_submit, + .get_streamid_offset = tegra_drm_get_streamid_offset_thi, + .can_use_memory_ctx = vic_can_use_memory_ctx, };
#define NVIDIA_TEGRA_124_VIC_FIRMWARE "nvidia/tegra124/vic03_ucode.bin"
dri-devel@lists.freedesktop.org
-
cyndis＠kapsi.fi -
Mikko Perttunen
-
Rob Herring -
Robin Murphy -
Thierry Reding -
Will Deacon