On Mon, Jun 29, 2020 at 09:49:22PM -0500, Suman Anna wrote:
> The K3 SoCs has various internal on-chip SRAM memories like the SRAM
> within the MCU domain or the shared MSMC RAM within NavSS that can be
> used for multiple purposes. One such purpose is to have the R5F cores
> use a portion of such on-chip SRAM for fast-access data or to directly
> execute code.
>
> Add support to the K3 R5 remoteproc driver to parse and support
> loading into such memories. The SRAM regions need to be mapped as
> normal non-cacheable memory to avoid kernel crashes when the remoteproc
> loader code uses the Arm64 memset library function (the "DC ZVA"
> instruction throws a alignment fault on device type memory).
>
> These SRAM regions are completely optional as not all firmware images
> require these memories, and any such memory has to be reserved as such
> in the DTS files.
>
> Signed-off-by: Suman Anna <s-a...@ti.com>
> ---
> v2:
> - Adapted to use various devm_ functions resulting in a smaller patch
> - Failure path code is dropped as a result in k3_r5_core_of_exit() and
> k3_r5_core_of_get_sram_memories()
> - Dropped unneeded whitespaces in a debug trace
> - Revised the patch title to move away from remoteproc/k3-r5
> - Dropped Mathieu's Acked-by because of the changes
> v1: https://patchwork.kernel.org/patch/11456373/
>
> drivers/remoteproc/ti_k3_r5_remoteproc.c | 79 ++++++++++++++++++++++++
> 1 file changed, 79 insertions(+)
>
> diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c
> b/drivers/remoteproc/ti_k3_r5_remoteproc.c
> index aca0eaf42a38..ac8ae29f38aa 100644
> --- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
> +++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
> @@ -86,7 +86,9 @@ struct k3_r5_cluster {
> * @dev: cached device pointer
> * @rproc: rproc handle representing this core
> * @mem: internal memory regions data
> + * @sram: on-chip SRAM memory regions data
> * @num_mems: number of internal memory regions
> + * @num_sram: number of on-chip SRAM memory regions
> * @reset: reset control handle
> * @tsp: TI-SCI processor control handle
> * @ti_sci: TI-SCI handle
> @@ -100,7 +102,9 @@ struct k3_r5_core {
> struct device *dev;
> struct rproc *rproc;
> struct k3_r5_mem *mem;
> + struct k3_r5_mem *sram;
> int num_mems;
> + int num_sram;
> struct reset_control *reset;
> struct ti_sci_proc *tsp;
> const struct ti_sci_handle *ti_sci;
> @@ -588,6 +592,18 @@ static void *k3_r5_rproc_da_to_va(struct rproc *rproc,
> u64 da, size_t len)
> }
> }
>
> + /* handle any SRAM regions using SoC-view addresses */
> + for (i = 0; i < core->num_sram; i++) {
> + dev_addr = core->sram[i].dev_addr;
> + size = core->sram[i].size;
> +
> + if (da >= dev_addr && ((da + len) <= (dev_addr + size))) {
> + offset = da - dev_addr;
> + va = core->sram[i].cpu_addr + offset;
> + return (__force void *)va;
> + }
> + }
> +
> /* handle static DDR reserved memory regions */
> for (i = 0; i < kproc->num_rmems; i++) {
> dev_addr = kproc->rmem[i].dev_addr;
> @@ -1030,6 +1046,63 @@ static int k3_r5_core_of_get_internal_memories(struct
> platform_device *pdev,
> return 0;
> }
>
> +static int k3_r5_core_of_get_sram_memories(struct platform_device *pdev,
> + struct k3_r5_core *core)
> +{
> + struct device_node *np = pdev->dev.of_node;
> + struct device *dev = &pdev->dev;
> + struct device_node *sram_np;
> + struct resource res;
> + int num_sram;
> + int i, ret;
> +
> + num_sram = of_property_count_elems_of_size(np, "sram", sizeof(phandle));
> + if (num_sram <= 0) {
> + dev_dbg(dev, "device does not use reserved on-chip memories,
> num_sram = %d\n",
> + num_sram);
> + return 0;
> + }
> +
> + core->sram = devm_kcalloc(dev, num_sram, sizeof(*core->sram),
> GFP_KERNEL);
> + if (!core->sram)
> + return -ENOMEM;
> +
> + for (i = 0; i < num_sram; i++) {
> + sram_np = of_parse_phandle(np, "sram", i);
> + if (!sram_np)
> + return -EINVAL;
> +
> + if (!of_device_is_available(sram_np)) {
> + of_node_put(sram_np);
> + return -EINVAL;
> + }
> +
> + ret = of_address_to_resource(sram_np, 0, &res);
> + of_node_put(sram_np);
> + if (ret)
> + return -EINVAL;
> +
> + core->sram[i].bus_addr = res.start;
> + core->sram[i].dev_addr = res.start;
> + core->sram[i].size = resource_size(&res);
> + core->sram[i].cpu_addr = devm_ioremap_wc(dev, res.start,
> + resource_size(&res));
> + if (!core->sram[i].cpu_addr) {
> + dev_err(dev, "failed to parse and map sram%d memory at
> %pad\n",
> + i, &res.start);
> + return -ENOMEM;
> + }
> +
> + dev_dbg(dev, "memory sram%d: bus addr %pa size 0x%zx va %pK da
> 0x%x\n",
> + i, &core->sram[i].bus_addr,
> + core->sram[i].size, core->sram[i].cpu_addr,
> + core->sram[i].dev_addr);
> + }
> + core->num_sram = num_sram;
> +
> + return 0;
> +}
> +
> static
> struct ti_sci_proc *k3_r5_core_of_get_tsp(struct device *dev,
> const struct ti_sci_handle *sci)
> @@ -1143,6 +1216,12 @@ static int k3_r5_core_of_init(struct platform_device
> *pdev)
> goto err;
> }
>
> + ret = k3_r5_core_of_get_sram_memories(pdev, core);
> + if (ret) {
> + dev_err(dev, "failed to get sram memories, ret = %d\n", ret);
> + goto err;
> + }
> +
Reviewed-by: Mathieu Poirier <mathieu.poir...@linaro.org>
> ret = ti_sci_proc_request(core->tsp);
> if (ret < 0) {
> dev_err(dev, "ti_sci_proc_request failed, ret = %d\n", ret);
> --
> 2.26.0
>
