diff options
Diffstat (limited to 'drivers/accel')
74 files changed, 9703 insertions, 622 deletions
diff --git a/drivers/accel/Kconfig b/drivers/accel/Kconfig index 64065fb8922b..5b9490367a39 100644 --- a/drivers/accel/Kconfig +++ b/drivers/accel/Kconfig @@ -24,6 +24,7 @@ menuconfig DRM_ACCEL different device files, called accel/accel* (in /dev, sysfs and debugfs). +source "drivers/accel/amdxdna/Kconfig" source "drivers/accel/habanalabs/Kconfig" source "drivers/accel/ivpu/Kconfig" source "drivers/accel/qaic/Kconfig" diff --git a/drivers/accel/Makefile b/drivers/accel/Makefile index ab3df932937f..a301fb6089d4 100644 --- a/drivers/accel/Makefile +++ b/drivers/accel/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DRM_ACCEL_AMDXDNA) += amdxdna/ obj-$(CONFIG_DRM_ACCEL_HABANALABS) += habanalabs/ obj-$(CONFIG_DRM_ACCEL_IVPU) += ivpu/ obj-$(CONFIG_DRM_ACCEL_QAIC) += qaic/ diff --git a/drivers/accel/amdxdna/Kconfig b/drivers/accel/amdxdna/Kconfig new file mode 100644 index 000000000000..f39d7a87296c --- /dev/null +++ b/drivers/accel/amdxdna/Kconfig @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config DRM_ACCEL_AMDXDNA + tristate "AMD AI Engine" + depends on AMD_IOMMU + depends on DRM_ACCEL + depends on PCI && HAS_IOMEM + depends on X86_64 + select DRM_SCHED + select DRM_GEM_SHMEM_HELPER + select FW_LOADER + select HMM_MIRROR + help + Choose this option to enable support for NPU integrated into AMD + client CPUs like AMD Ryzen AI 300 Series. AMD NPU can be used to + accelerate machine learning applications. + + If "M" is selected, the driver module will be amdxdna. diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile new file mode 100644 index 000000000000..0e9adf6890a0 --- /dev/null +++ b/drivers/accel/amdxdna/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0-only + +amdxdna-y := \ + aie2_ctx.o \ + aie2_error.o \ + aie2_message.o \ + aie2_pci.o \ + aie2_pm.o \ + aie2_psp.o \ + aie2_smu.o \ + aie2_solver.o \ + amdxdna_ctx.o \ + amdxdna_gem.o \ + amdxdna_mailbox.o \ + amdxdna_mailbox_helper.o \ + amdxdna_pci_drv.o \ + amdxdna_sysfs.o \ + npu1_regs.o \ + npu2_regs.o \ + npu4_regs.o \ + npu5_regs.o \ + npu6_regs.o +obj-$(CONFIG_DRM_ACCEL_AMDXDNA) = amdxdna.o diff --git a/drivers/accel/amdxdna/TODO b/drivers/accel/amdxdna/TODO new file mode 100644 index 000000000000..5119bccd1917 --- /dev/null +++ b/drivers/accel/amdxdna/TODO @@ -0,0 +1,3 @@ +- Add import and export BO support +- Add debugfs support +- Add debug BO support diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c new file mode 100644 index 000000000000..00d215ac866e --- /dev/null +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -0,0 +1,919 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_print.h> +#include <drm/drm_syncobj.h> +#include <linux/hmm.h> +#include <linux/types.h> +#include <linux/xarray.h> +#include <trace/events/amdxdna.h> + +#include "aie2_msg_priv.h" +#include "aie2_pci.h" +#include "aie2_solver.h" +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +static bool force_cmdlist; +module_param(force_cmdlist, bool, 0600); +MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)"); + +#define HWCTX_MAX_TIMEOUT 60000 /* milliseconds */ + +static void aie2_job_release(struct kref *ref) +{ + struct amdxdna_sched_job *job; + + job = container_of(ref, struct amdxdna_sched_job, refcnt); + amdxdna_sched_job_cleanup(job); + atomic64_inc(&job->hwctx->job_free_cnt); + wake_up(&job->hwctx->priv->job_free_wq); + if (job->out_fence) + dma_fence_put(job->out_fence); + kfree(job); +} + +static void aie2_job_put(struct amdxdna_sched_job *job) +{ + kref_put(&job->refcnt, aie2_job_release); +} + +/* The bad_job is used in aie2_sched_job_timedout, otherwise, set it to NULL */ +static void aie2_hwctx_stop(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx, + struct drm_sched_job *bad_job) +{ + drm_sched_stop(&hwctx->priv->sched, bad_job); + aie2_destroy_context(xdna->dev_handle, hwctx); +} + +static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_gem_obj *heap = hwctx->priv->heap; + int ret; + + ret = aie2_create_context(xdna->dev_handle, hwctx); + if (ret) { + XDNA_ERR(xdna, "Create hwctx failed, ret %d", ret); + goto out; + } + + ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id, + heap->mem.userptr, heap->mem.size); + if (ret) { + XDNA_ERR(xdna, "Map host buf failed, ret %d", ret); + goto out; + } + + if (hwctx->status != HWCTX_STAT_READY) { + XDNA_DBG(xdna, "hwctx is not ready, status %d", hwctx->status); + goto out; + } + + ret = aie2_config_cu(hwctx); + if (ret) { + XDNA_ERR(xdna, "Config cu failed, ret %d", ret); + goto out; + } + +out: + drm_sched_start(&hwctx->priv->sched, 0); + XDNA_DBG(xdna, "%s restarted, ret %d", hwctx->name, ret); + return ret; +} + +void aie2_restart_ctx(struct amdxdna_client *client) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + mutex_lock(&client->hwctx_lock); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) { + if (hwctx->status != HWCTX_STAT_STOP) + continue; + + hwctx->status = hwctx->old_status; + XDNA_DBG(xdna, "Resetting %s", hwctx->name); + aie2_hwctx_restart(xdna, hwctx); + } + mutex_unlock(&client->hwctx_lock); +} + +static struct dma_fence *aie2_cmd_get_out_fence(struct amdxdna_hwctx *hwctx, u64 seq) +{ + struct dma_fence *fence, *out_fence = NULL; + int ret; + + fence = drm_syncobj_fence_get(hwctx->priv->syncobj); + if (!fence) + return NULL; + + ret = dma_fence_chain_find_seqno(&fence, seq); + if (ret) + goto out; + + out_fence = dma_fence_get(dma_fence_chain_contained(fence)); + +out: + dma_fence_put(fence); + return out_fence; +} + +static void aie2_hwctx_wait_for_idle(struct amdxdna_hwctx *hwctx) +{ + struct dma_fence *fence; + + fence = aie2_cmd_get_out_fence(hwctx, hwctx->priv->seq - 1); + if (!fence) + return; + + /* Wait up to 2 seconds for fw to finish all pending requests */ + dma_fence_wait_timeout(fence, false, msecs_to_jiffies(2000)); + dma_fence_put(fence); +} + +void aie2_hwctx_suspend(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + + /* + * Command timeout is unlikely. But if it happens, it doesn't + * break the system. aie2_hwctx_stop() will destroy mailbox + * and abort all commands. + */ + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + aie2_hwctx_wait_for_idle(hwctx); + aie2_hwctx_stop(xdna, hwctx, NULL); + hwctx->old_status = hwctx->status; + hwctx->status = HWCTX_STAT_STOP; +} + +void aie2_hwctx_resume(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + + /* + * The resume path cannot guarantee that mailbox channel can be + * regenerated. If this happen, when submit message to this + * mailbox channel, error will return. + */ + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + hwctx->status = hwctx->old_status; + aie2_hwctx_restart(xdna, hwctx); +} + +static void +aie2_sched_notify(struct amdxdna_sched_job *job) +{ + struct dma_fence *fence = job->fence; + + trace_xdna_job(&job->base, job->hwctx->name, "signaled fence", job->seq); + job->hwctx->priv->completed++; + dma_fence_signal(fence); + + up(&job->hwctx->priv->job_sem); + job->job_done = true; + dma_fence_put(fence); + mmput_async(job->mm); + aie2_job_put(job); +} + +static int +aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size) +{ + struct amdxdna_sched_job *job = handle; + struct amdxdna_gem_obj *cmd_abo; + u32 ret = 0; + u32 status; + + cmd_abo = job->cmd_bo; + + if (unlikely(!data)) + goto out; + + if (unlikely(size != sizeof(u32))) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + ret = -EINVAL; + goto out; + } + + status = readl(data); + XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status); + if (status == AIE2_STATUS_SUCCESS) + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED); + else + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR); + +out: + aie2_sched_notify(job); + return ret; +} + +static int +aie2_sched_nocmd_resp_handler(void *handle, void __iomem *data, size_t size) +{ + struct amdxdna_sched_job *job = handle; + u32 ret = 0; + u32 status; + + if (unlikely(!data)) + goto out; + + if (unlikely(size != sizeof(u32))) { + ret = -EINVAL; + goto out; + } + + status = readl(data); + XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status); + +out: + aie2_sched_notify(job); + return ret; +} + +static int +aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size) +{ + struct amdxdna_sched_job *job = handle; + struct amdxdna_gem_obj *cmd_abo; + struct amdxdna_dev *xdna; + u32 fail_cmd_status; + u32 fail_cmd_idx; + u32 cmd_status; + u32 ret = 0; + + cmd_abo = job->cmd_bo; + if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + ret = -EINVAL; + goto out; + } + + cmd_status = readl(data + offsetof(struct cmd_chain_resp, status)); + xdna = job->hwctx->client->xdna; + XDNA_DBG(xdna, "Status 0x%x", cmd_status); + if (cmd_status == AIE2_STATUS_SUCCESS) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED); + goto out; + } + + /* Slow path to handle error, read from ringbuf on BAR */ + fail_cmd_idx = readl(data + offsetof(struct cmd_chain_resp, fail_cmd_idx)); + fail_cmd_status = readl(data + offsetof(struct cmd_chain_resp, fail_cmd_status)); + XDNA_DBG(xdna, "Failed cmd idx %d, status 0x%x", + fail_cmd_idx, fail_cmd_status); + + if (fail_cmd_status == AIE2_STATUS_SUCCESS) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + ret = -EINVAL; + goto out; + } + amdxdna_cmd_set_state(cmd_abo, fail_cmd_status); + + if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) { + struct amdxdna_cmd_chain *cc = amdxdna_cmd_get_payload(cmd_abo, NULL); + + cc->error_index = fail_cmd_idx; + if (cc->error_index >= cc->command_count) + cc->error_index = 0; + } +out: + aie2_sched_notify(job); + return ret; +} + +static struct dma_fence * +aie2_sched_job_run(struct drm_sched_job *sched_job) +{ + struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job); + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + struct amdxdna_hwctx *hwctx = job->hwctx; + struct dma_fence *fence; + int ret; + + if (!mmget_not_zero(job->mm)) + return ERR_PTR(-ESRCH); + + kref_get(&job->refcnt); + fence = dma_fence_get(job->fence); + + if (unlikely(!cmd_abo)) { + ret = aie2_sync_bo(hwctx, job, aie2_sched_nocmd_resp_handler); + goto out; + } + + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_NEW); + + if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) + ret = aie2_cmdlist_multi_execbuf(hwctx, job, aie2_sched_cmdlist_resp_handler); + else if (force_cmdlist) + ret = aie2_cmdlist_single_execbuf(hwctx, job, aie2_sched_cmdlist_resp_handler); + else + ret = aie2_execbuf(hwctx, job, aie2_sched_resp_handler); + +out: + if (ret) { + dma_fence_put(job->fence); + aie2_job_put(job); + mmput(job->mm); + fence = ERR_PTR(ret); + } + trace_xdna_job(sched_job, hwctx->name, "sent to device", job->seq); + + return fence; +} + +static void aie2_sched_job_free(struct drm_sched_job *sched_job) +{ + struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job); + struct amdxdna_hwctx *hwctx = job->hwctx; + + trace_xdna_job(sched_job, hwctx->name, "job free", job->seq); + if (!job->job_done) + up(&hwctx->priv->job_sem); + + drm_sched_job_cleanup(sched_job); + aie2_job_put(job); +} + +static enum drm_gpu_sched_stat +aie2_sched_job_timedout(struct drm_sched_job *sched_job) +{ + struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job); + struct amdxdna_hwctx *hwctx = job->hwctx; + struct amdxdna_dev *xdna; + + xdna = hwctx->client->xdna; + trace_xdna_job(sched_job, hwctx->name, "job timedout", job->seq); + mutex_lock(&xdna->dev_lock); + aie2_hwctx_stop(xdna, hwctx, sched_job); + + aie2_hwctx_restart(xdna, hwctx); + mutex_unlock(&xdna->dev_lock); + + return DRM_GPU_SCHED_STAT_NOMINAL; +} + +static const struct drm_sched_backend_ops sched_ops = { + .run_job = aie2_sched_job_run, + .free_job = aie2_sched_job_free, + .timedout_job = aie2_sched_job_timedout, +}; + +static int aie2_hwctx_col_list(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct amdxdna_dev_hdl *ndev; + int start, end, first, last; + u32 width = 1, entries = 0; + int i; + + if (!hwctx->num_tiles) { + XDNA_ERR(xdna, "Number of tiles is zero"); + return -EINVAL; + } + + ndev = xdna->dev_handle; + if (unlikely(!ndev->metadata.core.row_count)) { + XDNA_WARN(xdna, "Core tile row count is zero"); + return -EINVAL; + } + + hwctx->num_col = hwctx->num_tiles / ndev->metadata.core.row_count; + if (!hwctx->num_col || hwctx->num_col > ndev->total_col) { + XDNA_ERR(xdna, "Invalid num_col %d", hwctx->num_col); + return -EINVAL; + } + + if (ndev->priv->col_align == COL_ALIGN_NATURE) + width = hwctx->num_col; + + /* + * In range [start, end], find out columns that is multiple of width. + * 'first' is the first column, + * 'last' is the last column, + * 'entries' is the total number of columns. + */ + start = xdna->dev_info->first_col; + end = ndev->total_col - hwctx->num_col; + if (start > 0 && end == 0) { + XDNA_DBG(xdna, "Force start from col 0"); + start = 0; + } + first = start + (width - start % width) % width; + last = end - end % width; + if (last >= first) + entries = (last - first) / width + 1; + XDNA_DBG(xdna, "start %d end %d first %d last %d", + start, end, first, last); + + if (unlikely(!entries)) { + XDNA_ERR(xdna, "Start %d end %d width %d", + start, end, width); + return -EINVAL; + } + + hwctx->col_list = kmalloc_array(entries, sizeof(*hwctx->col_list), GFP_KERNEL); + if (!hwctx->col_list) + return -ENOMEM; + + hwctx->col_list_len = entries; + hwctx->col_list[0] = first; + for (i = 1; i < entries; i++) + hwctx->col_list[i] = hwctx->col_list[i - 1] + width; + + print_hex_dump_debug("col_list: ", DUMP_PREFIX_OFFSET, 16, 4, hwctx->col_list, + entries * sizeof(*hwctx->col_list), false); + return 0; +} + +static int aie2_alloc_resource(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct alloc_requests *xrs_req; + int ret; + + xrs_req = kzalloc(sizeof(*xrs_req), GFP_KERNEL); + if (!xrs_req) + return -ENOMEM; + + xrs_req->cdo.start_cols = hwctx->col_list; + xrs_req->cdo.cols_len = hwctx->col_list_len; + xrs_req->cdo.ncols = hwctx->num_col; + xrs_req->cdo.qos_cap.opc = hwctx->max_opc; + + xrs_req->rqos.gops = hwctx->qos.gops; + xrs_req->rqos.fps = hwctx->qos.fps; + xrs_req->rqos.dma_bw = hwctx->qos.dma_bandwidth; + xrs_req->rqos.latency = hwctx->qos.latency; + xrs_req->rqos.exec_time = hwctx->qos.frame_exec_time; + xrs_req->rqos.priority = hwctx->qos.priority; + + xrs_req->rid = (uintptr_t)hwctx; + + ret = xrs_allocate_resource(xdna->xrs_hdl, xrs_req, hwctx); + if (ret) + XDNA_ERR(xdna, "Allocate AIE resource failed, ret %d", ret); + + kfree(xrs_req); + return ret; +} + +static void aie2_release_resource(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + int ret; + + ret = xrs_release_resource(xdna->xrs_hdl, (uintptr_t)hwctx); + if (ret) + XDNA_ERR(xdna, "Release AIE resource failed, ret %d", ret); +} + +static int aie2_ctx_syncobj_create(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct drm_file *filp = hwctx->client->filp; + struct drm_syncobj *syncobj; + u32 hdl; + int ret; + + hwctx->syncobj_hdl = AMDXDNA_INVALID_FENCE_HANDLE; + + ret = drm_syncobj_create(&syncobj, 0, NULL); + if (ret) { + XDNA_ERR(xdna, "Create ctx syncobj failed, ret %d", ret); + return ret; + } + ret = drm_syncobj_get_handle(filp, syncobj, &hdl); + if (ret) { + drm_syncobj_put(syncobj); + XDNA_ERR(xdna, "Create ctx syncobj handle failed, ret %d", ret); + return ret; + } + hwctx->priv->syncobj = syncobj; + hwctx->syncobj_hdl = hdl; + + return 0; +} + +static void aie2_ctx_syncobj_destroy(struct amdxdna_hwctx *hwctx) +{ + /* + * The syncobj_hdl is owned by user space and will be cleaned up + * separately. + */ + drm_syncobj_put(hwctx->priv->syncobj); +} + +int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_client *client = hwctx->client; + struct amdxdna_dev *xdna = client->xdna; + const struct drm_sched_init_args args = { + .ops = &sched_ops, + .num_rqs = DRM_SCHED_PRIORITY_COUNT, + .credit_limit = HWCTX_MAX_CMDS, + .timeout = msecs_to_jiffies(HWCTX_MAX_TIMEOUT), + .name = hwctx->name, + .dev = xdna->ddev.dev, + }; + struct drm_gpu_scheduler *sched; + struct amdxdna_hwctx_priv *priv; + struct amdxdna_gem_obj *heap; + struct amdxdna_dev_hdl *ndev; + int i, ret; + + priv = kzalloc(sizeof(*hwctx->priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + hwctx->priv = priv; + + mutex_lock(&client->mm_lock); + heap = client->dev_heap; + if (!heap) { + XDNA_ERR(xdna, "The client dev heap object not exist"); + mutex_unlock(&client->mm_lock); + ret = -ENOENT; + goto free_priv; + } + drm_gem_object_get(to_gobj(heap)); + mutex_unlock(&client->mm_lock); + priv->heap = heap; + sema_init(&priv->job_sem, HWCTX_MAX_CMDS); + + ret = amdxdna_gem_pin(heap); + if (ret) { + XDNA_ERR(xdna, "Dev heap pin failed, ret %d", ret); + goto put_heap; + } + + for (i = 0; i < ARRAY_SIZE(priv->cmd_buf); i++) { + struct amdxdna_gem_obj *abo; + struct amdxdna_drm_create_bo args = { + .flags = 0, + .type = AMDXDNA_BO_DEV, + .vaddr = 0, + .size = MAX_CHAIN_CMDBUF_SIZE, + }; + + abo = amdxdna_drm_alloc_dev_bo(&xdna->ddev, &args, client->filp, true); + if (IS_ERR(abo)) { + ret = PTR_ERR(abo); + goto free_cmd_bufs; + } + + XDNA_DBG(xdna, "Command buf %d addr 0x%llx size 0x%lx", + i, abo->mem.dev_addr, abo->mem.size); + priv->cmd_buf[i] = abo; + } + + sched = &priv->sched; + mutex_init(&priv->io_lock); + + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&priv->io_lock); + fs_reclaim_release(GFP_KERNEL); + + ret = drm_sched_init(sched, &args); + if (ret) { + XDNA_ERR(xdna, "Failed to init DRM scheduler. ret %d", ret); + goto free_cmd_bufs; + } + + ret = drm_sched_entity_init(&priv->entity, DRM_SCHED_PRIORITY_NORMAL, + &sched, 1, NULL); + if (ret) { + XDNA_ERR(xdna, "Failed to initial sched entiry. ret %d", ret); + goto free_sched; + } + + ret = aie2_hwctx_col_list(hwctx); + if (ret) { + XDNA_ERR(xdna, "Create col list failed, ret %d", ret); + goto free_entity; + } + + ret = aie2_alloc_resource(hwctx); + if (ret) { + XDNA_ERR(xdna, "Alloc hw resource failed, ret %d", ret); + goto free_col_list; + } + + ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id, + heap->mem.userptr, heap->mem.size); + if (ret) { + XDNA_ERR(xdna, "Map host buffer failed, ret %d", ret); + goto release_resource; + } + + ret = aie2_ctx_syncobj_create(hwctx); + if (ret) { + XDNA_ERR(xdna, "Create syncobj failed, ret %d", ret); + goto release_resource; + } + + hwctx->status = HWCTX_STAT_INIT; + ndev = xdna->dev_handle; + ndev->hwctx_num++; + init_waitqueue_head(&priv->job_free_wq); + + XDNA_DBG(xdna, "hwctx %s init completed", hwctx->name); + + return 0; + +release_resource: + aie2_release_resource(hwctx); +free_col_list: + kfree(hwctx->col_list); +free_entity: + drm_sched_entity_destroy(&priv->entity); +free_sched: + drm_sched_fini(&priv->sched); +free_cmd_bufs: + for (i = 0; i < ARRAY_SIZE(priv->cmd_buf); i++) { + if (!priv->cmd_buf[i]) + continue; + drm_gem_object_put(to_gobj(priv->cmd_buf[i])); + } + amdxdna_gem_unpin(heap); +put_heap: + drm_gem_object_put(to_gobj(heap)); +free_priv: + kfree(priv); + return ret; +} + +void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev_hdl *ndev; + struct amdxdna_dev *xdna; + int idx; + + xdna = hwctx->client->xdna; + ndev = xdna->dev_handle; + ndev->hwctx_num--; + + XDNA_DBG(xdna, "%s sequence number %lld", hwctx->name, hwctx->priv->seq); + drm_sched_entity_destroy(&hwctx->priv->entity); + + aie2_hwctx_wait_for_idle(hwctx); + + /* Request fw to destroy hwctx and cancel the rest pending requests */ + aie2_release_resource(hwctx); + + /* Wait for all submitted jobs to be completed or canceled */ + wait_event(hwctx->priv->job_free_wq, + atomic64_read(&hwctx->job_submit_cnt) == + atomic64_read(&hwctx->job_free_cnt)); + + drm_sched_fini(&hwctx->priv->sched); + aie2_ctx_syncobj_destroy(hwctx); + + for (idx = 0; idx < ARRAY_SIZE(hwctx->priv->cmd_buf); idx++) + drm_gem_object_put(to_gobj(hwctx->priv->cmd_buf[idx])); + amdxdna_gem_unpin(hwctx->priv->heap); + drm_gem_object_put(to_gobj(hwctx->priv->heap)); + + mutex_destroy(&hwctx->priv->io_lock); + kfree(hwctx->col_list); + kfree(hwctx->priv); + kfree(hwctx->cus); +} + +static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size) +{ + struct amdxdna_hwctx_param_config_cu *config = buf; + struct amdxdna_dev *xdna = hwctx->client->xdna; + u32 total_size; + int ret; + + XDNA_DBG(xdna, "Config %d CU to %s", config->num_cus, hwctx->name); + if (XDNA_MBZ_DBG(xdna, config->pad, sizeof(config->pad))) + return -EINVAL; + + if (hwctx->status != HWCTX_STAT_INIT) { + XDNA_ERR(xdna, "Not support re-config CU"); + return -EINVAL; + } + + if (!config->num_cus) { + XDNA_ERR(xdna, "Number of CU is zero"); + return -EINVAL; + } + + total_size = struct_size(config, cu_configs, config->num_cus); + if (total_size > size) { + XDNA_ERR(xdna, "CU config larger than size"); + return -EINVAL; + } + + hwctx->cus = kmemdup(config, total_size, GFP_KERNEL); + if (!hwctx->cus) + return -ENOMEM; + + ret = aie2_config_cu(hwctx); + if (ret) { + XDNA_ERR(xdna, "Config CU to firmware failed, ret %d", ret); + goto free_cus; + } + + wmb(); /* To avoid locking in command submit when check status */ + hwctx->status = HWCTX_STAT_READY; + + return 0; + +free_cus: + kfree(hwctx->cus); + hwctx->cus = NULL; + return ret; +} + +int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + switch (type) { + case DRM_AMDXDNA_HWCTX_CONFIG_CU: + return aie2_hwctx_cu_config(hwctx, buf, size); + case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF: + case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF: + return -EOPNOTSUPP; + default: + XDNA_DBG(xdna, "Not supported type %d", type); + return -EOPNOTSUPP; + } +} + +static int aie2_populate_range(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + struct mm_struct *mm = abo->mem.notifier.mm; + struct hmm_range range = { 0 }; + unsigned long timeout; + int ret; + + XDNA_INFO_ONCE(xdna, "populate memory range %llx size %lx", + abo->mem.userptr, abo->mem.size); + range.notifier = &abo->mem.notifier; + range.start = abo->mem.userptr; + range.end = abo->mem.userptr + abo->mem.size; + range.hmm_pfns = abo->mem.pfns; + range.default_flags = HMM_PFN_REQ_FAULT; + + if (!mmget_not_zero(mm)) + return -EFAULT; + + timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); +again: + range.notifier_seq = mmu_interval_read_begin(&abo->mem.notifier); + mmap_read_lock(mm); + ret = hmm_range_fault(&range); + mmap_read_unlock(mm); + if (ret) { + if (time_after(jiffies, timeout)) { + ret = -ETIME; + goto put_mm; + } + + if (ret == -EBUSY) + goto again; + + goto put_mm; + } + + down_read(&xdna->notifier_lock); + if (mmu_interval_read_retry(&abo->mem.notifier, range.notifier_seq)) { + up_read(&xdna->notifier_lock); + goto again; + } + abo->mem.map_invalid = false; + up_read(&xdna->notifier_lock); + +put_mm: + mmput(mm); + return ret; +} + +int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct ww_acquire_ctx acquire_ctx; + struct dma_fence_chain *chain; + struct amdxdna_gem_obj *abo; + unsigned long timeout = 0; + int ret, i; + + ret = down_interruptible(&hwctx->priv->job_sem); + if (ret) { + XDNA_ERR(xdna, "Grab job sem failed, ret %d", ret); + return ret; + } + + chain = dma_fence_chain_alloc(); + if (!chain) { + XDNA_ERR(xdna, "Alloc fence chain failed"); + ret = -ENOMEM; + goto up_sem; + } + + ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx); + if (ret) { + XDNA_ERR(xdna, "DRM job init failed, ret %d", ret); + goto free_chain; + } + +retry: + ret = drm_gem_lock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + if (ret) { + XDNA_WARN(xdna, "Failed to lock BOs, ret %d", ret); + goto cleanup_job; + } + + for (i = 0; i < job->bo_cnt; i++) { + ret = dma_resv_reserve_fences(job->bos[i]->resv, 1); + if (ret) { + XDNA_WARN(xdna, "Failed to reserve fences %d", ret); + drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + goto cleanup_job; + } + } + + down_read(&xdna->notifier_lock); + for (i = 0; i < job->bo_cnt; i++) { + abo = to_xdna_obj(job->bos[i]); + if (abo->mem.map_invalid) { + up_read(&xdna->notifier_lock); + drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + if (!timeout) { + timeout = jiffies + + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + } else if (time_after(jiffies, timeout)) { + ret = -ETIME; + goto cleanup_job; + } + + ret = aie2_populate_range(abo); + if (ret) + goto cleanup_job; + goto retry; + } + } + + mutex_lock(&hwctx->priv->io_lock); + drm_sched_job_arm(&job->base); + job->out_fence = dma_fence_get(&job->base.s_fence->finished); + for (i = 0; i < job->bo_cnt; i++) + dma_resv_add_fence(job->bos[i]->resv, job->out_fence, DMA_RESV_USAGE_WRITE); + job->seq = hwctx->priv->seq++; + kref_get(&job->refcnt); + drm_sched_entity_push_job(&job->base); + + *seq = job->seq; + drm_syncobj_add_point(hwctx->priv->syncobj, chain, job->out_fence, *seq); + mutex_unlock(&hwctx->priv->io_lock); + + up_read(&xdna->notifier_lock); + drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + + aie2_job_put(job); + atomic64_inc(&hwctx->job_submit_cnt); + + return 0; + +cleanup_job: + drm_sched_job_cleanup(&job->base); +free_chain: + dma_fence_chain_free(chain); +up_sem: + up(&hwctx->priv->job_sem); + job->job_done = true; + return ret; +} + +void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo, + unsigned long cur_seq) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + struct drm_gem_object *gobj = to_gobj(abo); + long ret; + + down_write(&xdna->notifier_lock); + abo->mem.map_invalid = true; + mmu_interval_set_seq(&abo->mem.notifier, cur_seq); + up_write(&xdna->notifier_lock); + ret = dma_resv_wait_timeout(gobj->resv, DMA_RESV_USAGE_BOOKKEEP, + true, MAX_SCHEDULE_TIMEOUT); + if (!ret || ret == -ERESTARTSYS) + XDNA_ERR(xdna, "Failed to wait for bo, ret %ld", ret); +} diff --git a/drivers/accel/amdxdna/aie2_error.c b/drivers/accel/amdxdna/aie2_error.c new file mode 100644 index 000000000000..5ee905632a39 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_error.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/drm_cache.h> +#include <drm/drm_device.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/dma-mapping.h> +#include <linux/kthread.h> +#include <linux/kernel.h> + +#include "aie2_msg_priv.h" +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +struct async_event { + struct amdxdna_dev_hdl *ndev; + struct async_event_msg_resp resp; + struct workqueue_struct *wq; + struct work_struct work; + u8 *buf; + dma_addr_t addr; + u32 size; +}; + +struct async_events { + struct workqueue_struct *wq; + u8 *buf; + dma_addr_t addr; + u32 size; + u32 event_cnt; + struct async_event event[] __counted_by(event_cnt); +}; + +/* + * Below enum, struct and lookup tables are porting from XAIE util header file. + * + * Below data is defined by AIE device and it is used for decode error message + * from the device. + */ + +enum aie_module_type { + AIE_MEM_MOD = 0, + AIE_CORE_MOD, + AIE_PL_MOD, +}; + +enum aie_error_category { + AIE_ERROR_SATURATION = 0, + AIE_ERROR_FP, + AIE_ERROR_STREAM, + AIE_ERROR_ACCESS, + AIE_ERROR_BUS, + AIE_ERROR_INSTRUCTION, + AIE_ERROR_ECC, + AIE_ERROR_LOCK, + AIE_ERROR_DMA, + AIE_ERROR_MEM_PARITY, + /* Unknown is not from XAIE, added for better category */ + AIE_ERROR_UNKNOWN, +}; + +/* Don't pack, unless XAIE side changed */ +struct aie_error { + __u8 row; + __u8 col; + __u32 mod_type; + __u8 event_id; +}; + +struct aie_err_info { + u32 err_cnt; + u32 ret_code; + u32 rsvd; + struct aie_error payload[] __counted_by(err_cnt); +}; + +struct aie_event_category { + u8 event_id; + enum aie_error_category category; +}; + +#define EVENT_CATEGORY(id, cat) { id, cat } +static const struct aie_event_category aie_ml_mem_event_cat[] = { + EVENT_CATEGORY(88U, AIE_ERROR_ECC), + EVENT_CATEGORY(90U, AIE_ERROR_ECC), + EVENT_CATEGORY(91U, AIE_ERROR_MEM_PARITY), + EVENT_CATEGORY(92U, AIE_ERROR_MEM_PARITY), + EVENT_CATEGORY(93U, AIE_ERROR_MEM_PARITY), + EVENT_CATEGORY(94U, AIE_ERROR_MEM_PARITY), + EVENT_CATEGORY(95U, AIE_ERROR_MEM_PARITY), + EVENT_CATEGORY(96U, AIE_ERROR_MEM_PARITY), + EVENT_CATEGORY(97U, AIE_ERROR_DMA), + EVENT_CATEGORY(98U, AIE_ERROR_DMA), + EVENT_CATEGORY(99U, AIE_ERROR_DMA), + EVENT_CATEGORY(100U, AIE_ERROR_DMA), + EVENT_CATEGORY(101U, AIE_ERROR_LOCK), +}; + +static const struct aie_event_category aie_ml_core_event_cat[] = { + EVENT_CATEGORY(55U, AIE_ERROR_ACCESS), + EVENT_CATEGORY(56U, AIE_ERROR_STREAM), + EVENT_CATEGORY(57U, AIE_ERROR_STREAM), + EVENT_CATEGORY(58U, AIE_ERROR_BUS), + EVENT_CATEGORY(59U, AIE_ERROR_INSTRUCTION), + EVENT_CATEGORY(60U, AIE_ERROR_ACCESS), + EVENT_CATEGORY(62U, AIE_ERROR_ECC), + EVENT_CATEGORY(64U, AIE_ERROR_ECC), + EVENT_CATEGORY(65U, AIE_ERROR_ACCESS), + EVENT_CATEGORY(66U, AIE_ERROR_ACCESS), + EVENT_CATEGORY(67U, AIE_ERROR_LOCK), + EVENT_CATEGORY(70U, AIE_ERROR_INSTRUCTION), + EVENT_CATEGORY(71U, AIE_ERROR_STREAM), + EVENT_CATEGORY(72U, AIE_ERROR_BUS), +}; + +static const struct aie_event_category aie_ml_mem_tile_event_cat[] = { + EVENT_CATEGORY(130U, AIE_ERROR_ECC), + EVENT_CATEGORY(132U, AIE_ERROR_ECC), + EVENT_CATEGORY(133U, AIE_ERROR_DMA), + EVENT_CATEGORY(134U, AIE_ERROR_DMA), + EVENT_CATEGORY(135U, AIE_ERROR_STREAM), + EVENT_CATEGORY(136U, AIE_ERROR_STREAM), + EVENT_CATEGORY(137U, AIE_ERROR_STREAM), + EVENT_CATEGORY(138U, AIE_ERROR_BUS), + EVENT_CATEGORY(139U, AIE_ERROR_LOCK), +}; + +static const struct aie_event_category aie_ml_shim_tile_event_cat[] = { + EVENT_CATEGORY(64U, AIE_ERROR_BUS), + EVENT_CATEGORY(65U, AIE_ERROR_STREAM), + EVENT_CATEGORY(66U, AIE_ERROR_STREAM), + EVENT_CATEGORY(67U, AIE_ERROR_BUS), + EVENT_CATEGORY(68U, AIE_ERROR_BUS), + EVENT_CATEGORY(69U, AIE_ERROR_BUS), + EVENT_CATEGORY(70U, AIE_ERROR_BUS), + EVENT_CATEGORY(71U, AIE_ERROR_BUS), + EVENT_CATEGORY(72U, AIE_ERROR_DMA), + EVENT_CATEGORY(73U, AIE_ERROR_DMA), + EVENT_CATEGORY(74U, AIE_ERROR_LOCK), +}; + +static enum aie_error_category +aie_get_error_category(u8 row, u8 event_id, enum aie_module_type mod_type) +{ + const struct aie_event_category *lut; + int num_entry; + int i; + + switch (mod_type) { + case AIE_PL_MOD: + lut = aie_ml_shim_tile_event_cat; + num_entry = ARRAY_SIZE(aie_ml_shim_tile_event_cat); + break; + case AIE_CORE_MOD: + lut = aie_ml_core_event_cat; + num_entry = ARRAY_SIZE(aie_ml_core_event_cat); + break; + case AIE_MEM_MOD: + if (row == 1) { + lut = aie_ml_mem_tile_event_cat; + num_entry = ARRAY_SIZE(aie_ml_mem_tile_event_cat); + } else { + lut = aie_ml_mem_event_cat; + num_entry = ARRAY_SIZE(aie_ml_mem_event_cat); + } + break; + default: + return AIE_ERROR_UNKNOWN; + } + + for (i = 0; i < num_entry; i++) { + if (event_id != lut[i].event_id) + continue; + + return lut[i].category; + } + + return AIE_ERROR_UNKNOWN; +} + +static u32 aie2_error_backtrack(struct amdxdna_dev_hdl *ndev, void *err_info, u32 num_err) +{ + struct aie_error *errs = err_info; + u32 err_col = 0; /* assume that AIE has less than 32 columns */ + int i; + + /* Get err column bitmap */ + for (i = 0; i < num_err; i++) { + struct aie_error *err = &errs[i]; + enum aie_error_category cat; + + cat = aie_get_error_category(err->row, err->event_id, err->mod_type); + XDNA_ERR(ndev->xdna, "Row: %d, Col: %d, module %d, event ID %d, category %d", + err->row, err->col, err->mod_type, + err->event_id, cat); + + if (err->col >= 32) { + XDNA_WARN(ndev->xdna, "Invalid column number"); + break; + } + + err_col |= (1 << err->col); + } + + return err_col; +} + +static int aie2_error_async_cb(void *handle, void __iomem *data, size_t size) +{ + struct async_event *e = handle; + + if (data) { + e->resp.type = readl(data + offsetof(struct async_event_msg_resp, type)); + wmb(); /* Update status in the end, so that no lock for here */ + e->resp.status = readl(data + offsetof(struct async_event_msg_resp, status)); + } + queue_work(e->wq, &e->work); + return 0; +} + +static int aie2_error_event_send(struct async_event *e) +{ + drm_clflush_virt_range(e->buf, e->size); /* device can access */ + return aie2_register_asyn_event_msg(e->ndev, e->addr, e->size, e, + aie2_error_async_cb); +} + +static void aie2_error_worker(struct work_struct *err_work) +{ + struct aie_err_info *info; + struct amdxdna_dev *xdna; + struct async_event *e; + u32 max_err; + u32 err_col; + + e = container_of(err_work, struct async_event, work); + + xdna = e->ndev->xdna; + + if (e->resp.status == MAX_AIE2_STATUS_CODE) + return; + + e->resp.status = MAX_AIE2_STATUS_CODE; + + print_hex_dump_debug("AIE error: ", DUMP_PREFIX_OFFSET, 16, 4, + e->buf, 0x100, false); + + info = (struct aie_err_info *)e->buf; + XDNA_DBG(xdna, "Error count %d return code %d", info->err_cnt, info->ret_code); + + max_err = (e->size - sizeof(*info)) / sizeof(struct aie_error); + if (unlikely(info->err_cnt > max_err)) { + WARN_ONCE(1, "Error count too large %d\n", info->err_cnt); + return; + } + err_col = aie2_error_backtrack(e->ndev, info->payload, info->err_cnt); + if (!err_col) { + XDNA_WARN(xdna, "Did not get error column"); + return; + } + + mutex_lock(&xdna->dev_lock); + /* Re-sent this event to firmware */ + if (aie2_error_event_send(e)) + XDNA_WARN(xdna, "Unable to register async event"); + mutex_unlock(&xdna->dev_lock); +} + +int aie2_error_async_events_send(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->xdna; + struct async_event *e; + int i, ret; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + for (i = 0; i < ndev->async_events->event_cnt; i++) { + e = &ndev->async_events->event[i]; + ret = aie2_error_event_send(e); + if (ret) + return ret; + } + + return 0; +} + +void aie2_error_async_events_free(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->xdna; + struct async_events *events; + + events = ndev->async_events; + + mutex_unlock(&xdna->dev_lock); + destroy_workqueue(events->wq); + mutex_lock(&xdna->dev_lock); + + dma_free_noncoherent(xdna->ddev.dev, events->size, events->buf, + events->addr, DMA_FROM_DEVICE); + kfree(events); +} + +int aie2_error_async_events_alloc(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->xdna; + u32 total_col = ndev->total_col; + u32 total_size = ASYNC_BUF_SIZE * total_col; + struct async_events *events; + int i, ret; + + events = kzalloc(struct_size(events, event, total_col), GFP_KERNEL); + if (!events) + return -ENOMEM; + + events->buf = dma_alloc_noncoherent(xdna->ddev.dev, total_size, &events->addr, + DMA_FROM_DEVICE, GFP_KERNEL); + if (!events->buf) { + ret = -ENOMEM; + goto free_events; + } + events->size = total_size; + events->event_cnt = total_col; + + events->wq = alloc_ordered_workqueue("async_wq", 0); + if (!events->wq) { + ret = -ENOMEM; + goto free_buf; + } + + for (i = 0; i < events->event_cnt; i++) { + struct async_event *e = &events->event[i]; + u32 offset = i * ASYNC_BUF_SIZE; + + e->ndev = ndev; + e->wq = events->wq; + e->buf = &events->buf[offset]; + e->addr = events->addr + offset; + e->size = ASYNC_BUF_SIZE; + e->resp.status = MAX_AIE2_STATUS_CODE; + INIT_WORK(&e->work, aie2_error_worker); + } + + ndev->async_events = events; + + XDNA_DBG(xdna, "Async event count %d, buf total size 0x%x", + events->event_cnt, events->size); + return 0; + +free_buf: + dma_free_noncoherent(xdna->ddev.dev, events->size, events->buf, + events->addr, DMA_FROM_DEVICE); +free_events: + kfree(events); + return ret; +} diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c new file mode 100644 index 000000000000..82412eec9a4b --- /dev/null +++ b/drivers/accel/amdxdna/aie2_message.c @@ -0,0 +1,776 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_cache.h> +#include <drm/drm_device.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/bitfield.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/types.h> +#include <linux/xarray.h> + +#include "aie2_msg_priv.h" +#include "aie2_pci.h" +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_mailbox_helper.h" +#include "amdxdna_pci_drv.h" + +#define DECLARE_AIE2_MSG(name, op) \ + DECLARE_XDNA_MSG_COMMON(name, op, MAX_AIE2_STATUS_CODE) + +static int aie2_send_mgmt_msg_wait(struct amdxdna_dev_hdl *ndev, + struct xdna_mailbox_msg *msg) +{ + struct amdxdna_dev *xdna = ndev->xdna; + struct xdna_notify *hdl = msg->handle; + int ret; + + if (!ndev->mgmt_chann) + return -ENODEV; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + ret = xdna_send_msg_wait(xdna, ndev->mgmt_chann, msg); + if (ret == -ETIME) { + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_destroy_channel(ndev->mgmt_chann); + ndev->mgmt_chann = NULL; + } + + if (!ret && *hdl->data != AIE2_STATUS_SUCCESS) { + XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x", + msg->opcode, *hdl->data); + ret = -EINVAL; + } + + return ret; +} + +int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev) +{ + DECLARE_AIE2_MSG(suspend, MSG_OP_SUSPEND); + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_resume_fw(struct amdxdna_dev_hdl *ndev) +{ + DECLARE_AIE2_MSG(suspend, MSG_OP_RESUME); + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value) +{ + DECLARE_AIE2_MSG(set_runtime_cfg, MSG_OP_SET_RUNTIME_CONFIG); + int ret; + + req.type = type; + req.value = value; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) { + XDNA_ERR(ndev->xdna, "Failed to set runtime config, ret %d", ret); + return ret; + } + + return 0; +} + +int aie2_get_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 *value) +{ + DECLARE_AIE2_MSG(get_runtime_cfg, MSG_OP_GET_RUNTIME_CONFIG); + int ret; + + req.type = type; + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) { + XDNA_ERR(ndev->xdna, "Failed to get runtime config, ret %d", ret); + return ret; + } + + *value = resp.value; + return 0; +} + +int aie2_assign_mgmt_pasid(struct amdxdna_dev_hdl *ndev, u16 pasid) +{ + DECLARE_AIE2_MSG(assign_mgmt_pasid, MSG_OP_ASSIGN_MGMT_PASID); + + req.pasid = pasid; + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *version) +{ + DECLARE_AIE2_MSG(aie_version_info, MSG_OP_QUERY_AIE_VERSION); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + XDNA_DBG(xdna, "Query AIE version - major: %u minor: %u completed", + resp.major, resp.minor); + + version->major = resp.major; + version->minor = resp.minor; + + return 0; +} + +int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata) +{ + DECLARE_AIE2_MSG(aie_tile_info, MSG_OP_QUERY_AIE_TILE_INFO); + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + metadata->size = resp.info.size; + metadata->cols = resp.info.cols; + metadata->rows = resp.info.rows; + + metadata->version.major = resp.info.major; + metadata->version.minor = resp.info.minor; + + metadata->core.row_count = resp.info.core_rows; + metadata->core.row_start = resp.info.core_row_start; + metadata->core.dma_channel_count = resp.info.core_dma_channels; + metadata->core.lock_count = resp.info.core_locks; + metadata->core.event_reg_count = resp.info.core_events; + + metadata->mem.row_count = resp.info.mem_rows; + metadata->mem.row_start = resp.info.mem_row_start; + metadata->mem.dma_channel_count = resp.info.mem_dma_channels; + metadata->mem.lock_count = resp.info.mem_locks; + metadata->mem.event_reg_count = resp.info.mem_events; + + metadata->shim.row_count = resp.info.shim_rows; + metadata->shim.row_start = resp.info.shim_row_start; + metadata->shim.dma_channel_count = resp.info.shim_dma_channels; + metadata->shim.lock_count = resp.info.shim_locks; + metadata->shim.event_reg_count = resp.info.shim_events; + + return 0; +} + +int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, + struct amdxdna_fw_ver *fw_ver) +{ + DECLARE_AIE2_MSG(firmware_version, MSG_OP_GET_FIRMWARE_VERSION); + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + fw_ver->major = resp.major; + fw_ver->minor = resp.minor; + fw_ver->sub = resp.sub; + fw_ver->build = resp.build; + + return 0; +} + +int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx) +{ + DECLARE_AIE2_MSG(create_ctx, MSG_OP_CREATE_CONTEXT); + struct amdxdna_dev *xdna = ndev->xdna; + struct xdna_mailbox_chann_res x2i; + struct xdna_mailbox_chann_res i2x; + struct cq_pair *cq_pair; + u32 intr_reg; + int ret; + + req.aie_type = 1; + req.start_col = hwctx->start_col; + req.num_col = hwctx->num_col; + req.num_cq_pairs_requested = 1; + req.pasid = hwctx->client->pasid; + req.context_priority = 2; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + hwctx->fw_ctx_id = resp.context_id; + WARN_ONCE(hwctx->fw_ctx_id == -1, "Unexpected context id"); + + cq_pair = &resp.cq_pair[0]; + x2i.mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->x2i_q.head_addr); + x2i.mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->x2i_q.tail_addr); + x2i.rb_start_addr = AIE2_SRAM_OFF(ndev, cq_pair->x2i_q.buf_addr); + x2i.rb_size = cq_pair->x2i_q.buf_size; + + i2x.mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->i2x_q.head_addr); + i2x.mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->i2x_q.tail_addr); + i2x.rb_start_addr = AIE2_SRAM_OFF(ndev, cq_pair->i2x_q.buf_addr); + i2x.rb_size = cq_pair->i2x_q.buf_size; + + ret = pci_irq_vector(to_pci_dev(xdna->ddev.dev), resp.msix_id); + if (ret == -EINVAL) { + XDNA_ERR(xdna, "not able to create channel"); + goto out_destroy_context; + } + + intr_reg = i2x.mb_head_ptr_reg + 4; + hwctx->priv->mbox_chann = xdna_mailbox_create_channel(ndev->mbox, &x2i, &i2x, + intr_reg, ret); + if (!hwctx->priv->mbox_chann) { + XDNA_ERR(xdna, "not able to create channel"); + ret = -EINVAL; + goto out_destroy_context; + } + + XDNA_DBG(xdna, "%s mailbox channel irq: %d, msix_id: %d", + hwctx->name, ret, resp.msix_id); + XDNA_DBG(xdna, "%s created fw ctx %d pasid %d", hwctx->name, + hwctx->fw_ctx_id, hwctx->client->pasid); + + return 0; + +out_destroy_context: + aie2_destroy_context(ndev, hwctx); + return ret; +} + +int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx) +{ + DECLARE_AIE2_MSG(destroy_ctx, MSG_OP_DESTROY_CONTEXT); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + if (hwctx->fw_ctx_id == -1) + return 0; + + xdna_mailbox_stop_channel(hwctx->priv->mbox_chann); + + req.context_id = hwctx->fw_ctx_id; + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + XDNA_WARN(xdna, "%s destroy context failed, ret %d", hwctx->name, ret); + + xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann); + XDNA_DBG(xdna, "%s destroyed fw ctx %d", hwctx->name, + hwctx->fw_ctx_id); + hwctx->priv->mbox_chann = NULL; + hwctx->fw_ctx_id = -1; + + return ret; +} + +int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size) +{ + DECLARE_AIE2_MSG(map_host_buffer, MSG_OP_MAP_HOST_BUFFER); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + req.context_id = context_id; + req.buf_addr = addr; + req.buf_size = size; + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + XDNA_DBG(xdna, "fw ctx %d map host buf addr 0x%llx size 0x%llx", + context_id, addr, size); + + return 0; +} + +int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, + u32 size, u32 *cols_filled) +{ + DECLARE_AIE2_MSG(aie_column_info, MSG_OP_QUERY_COL_STATUS); + struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_client *client; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + dma_addr_t dma_addr; + u32 aie_bitmap = 0; + u8 *buff_addr; + int ret, idx; + + buff_addr = dma_alloc_noncoherent(xdna->ddev.dev, size, &dma_addr, + DMA_FROM_DEVICE, GFP_KERNEL); + if (!buff_addr) + return -ENOMEM; + + /* Go through each hardware context and mark the AIE columns that are active */ + list_for_each_entry(client, &xdna->client_list, node) { + idx = srcu_read_lock(&client->hwctx_srcu); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) + aie_bitmap |= amdxdna_hwctx_col_map(hwctx); + srcu_read_unlock(&client->hwctx_srcu, idx); + } + + *cols_filled = 0; + req.dump_buff_addr = dma_addr; + req.dump_buff_size = size; + req.num_cols = hweight32(aie_bitmap); + req.aie_bitmap = aie_bitmap; + + drm_clflush_virt_range(buff_addr, size); /* device can access */ + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) { + XDNA_ERR(xdna, "Error during NPU query, status %d", ret); + goto fail; + } + + if (resp.status != AIE2_STATUS_SUCCESS) { + XDNA_ERR(xdna, "Query NPU status failed, status 0x%x", resp.status); + ret = -EINVAL; + goto fail; + } + XDNA_DBG(xdna, "Query NPU status completed"); + + if (size < resp.size) { + ret = -EINVAL; + XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", size, resp.size); + goto fail; + } + + if (copy_to_user(buf, buff_addr, resp.size)) { + ret = -EFAULT; + XDNA_ERR(xdna, "Failed to copy NPU status to user space"); + goto fail; + } + + *cols_filled = aie_bitmap; + +fail: + dma_free_noncoherent(xdna->ddev.dev, size, buff_addr, dma_addr, DMA_FROM_DEVICE); + return ret; +} + +int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size, + void *handle, int (*cb)(void*, void __iomem *, size_t)) +{ + struct async_event_msg_req req = { 0 }; + struct xdna_mailbox_msg msg = { + .send_data = (u8 *)&req, + .send_size = sizeof(req), + .handle = handle, + .opcode = MSG_OP_REGISTER_ASYNC_EVENT_MSG, + .notify_cb = cb, + }; + + req.buf_addr = addr; + req.buf_size = size; + + XDNA_DBG(ndev->xdna, "Register addr 0x%llx size 0x%x", addr, size); + return xdna_mailbox_send_msg(ndev->mgmt_chann, &msg, TX_TIMEOUT); +} + +int aie2_config_cu(struct amdxdna_hwctx *hwctx) +{ + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_dev *xdna = hwctx->client->xdna; + u32 shift = xdna->dev_info->dev_mem_buf_shift; + DECLARE_AIE2_MSG(config_cu, MSG_OP_CONFIG_CU); + struct drm_gem_object *gobj; + struct amdxdna_gem_obj *abo; + int ret, i; + + if (!chann) + return -ENODEV; + + if (hwctx->cus->num_cus > MAX_NUM_CUS) { + XDNA_DBG(xdna, "Exceed maximum CU %d", MAX_NUM_CUS); + return -EINVAL; + } + + for (i = 0; i < hwctx->cus->num_cus; i++) { + struct amdxdna_cu_config *cu = &hwctx->cus->cu_configs[i]; + + if (XDNA_MBZ_DBG(xdna, cu->pad, sizeof(cu->pad))) + return -EINVAL; + + gobj = drm_gem_object_lookup(hwctx->client->filp, cu->cu_bo); + if (!gobj) { + XDNA_ERR(xdna, "Lookup GEM object failed"); + return -EINVAL; + } + abo = to_xdna_obj(gobj); + + if (abo->type != AMDXDNA_BO_DEV) { + drm_gem_object_put(gobj); + XDNA_ERR(xdna, "Invalid BO type"); + return -EINVAL; + } + + req.cfgs[i] = FIELD_PREP(AIE2_MSG_CFG_CU_PDI_ADDR, + abo->mem.dev_addr >> shift); + req.cfgs[i] |= FIELD_PREP(AIE2_MSG_CFG_CU_FUNC, cu->cu_func); + XDNA_DBG(xdna, "CU %d full addr 0x%llx, cfg 0x%x", i, + abo->mem.dev_addr, req.cfgs[i]); + drm_gem_object_put(gobj); + } + req.num_cus = hwctx->cus->num_cus; + + ret = xdna_send_msg_wait(xdna, chann, &msg); + if (ret == -ETIME) + aie2_destroy_context(xdna->dev_handle, hwctx); + + if (resp.status == AIE2_STATUS_SUCCESS) { + XDNA_DBG(xdna, "Configure %d CUs, ret %d", req.num_cus, ret); + return 0; + } + + XDNA_ERR(xdna, "Command opcode 0x%x failed, status 0x%x ret %d", + msg.opcode, resp.status, ret); + return ret; +} + +int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)) +{ + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + union { + struct execute_buffer_req ebuf; + struct exec_dpu_req dpu; + } req; + struct xdna_mailbox_msg msg; + u32 payload_len; + void *payload; + int cu_idx; + int ret; + u32 op; + + if (!chann) + return -ENODEV; + + payload = amdxdna_cmd_get_payload(cmd_abo, &payload_len); + if (!payload) { + XDNA_ERR(xdna, "Invalid command, cannot get payload"); + return -EINVAL; + } + + cu_idx = amdxdna_cmd_get_cu_idx(cmd_abo); + if (cu_idx < 0) { + XDNA_DBG(xdna, "Invalid cu idx"); + return -EINVAL; + } + + op = amdxdna_cmd_get_op(cmd_abo); + switch (op) { + case ERT_START_CU: + if (unlikely(payload_len > sizeof(req.ebuf.payload))) + XDNA_DBG(xdna, "Invalid ebuf payload len: %d", payload_len); + req.ebuf.cu_idx = cu_idx; + memcpy(req.ebuf.payload, payload, sizeof(req.ebuf.payload)); + msg.send_size = sizeof(req.ebuf); + msg.opcode = MSG_OP_EXECUTE_BUFFER_CF; + break; + case ERT_START_NPU: { + struct amdxdna_cmd_start_npu *sn = payload; + + if (unlikely(payload_len - sizeof(*sn) > sizeof(req.dpu.payload))) + XDNA_DBG(xdna, "Invalid dpu payload len: %d", payload_len); + req.dpu.inst_buf_addr = sn->buffer; + req.dpu.inst_size = sn->buffer_size; + req.dpu.inst_prop_cnt = sn->prop_count; + req.dpu.cu_idx = cu_idx; + memcpy(req.dpu.payload, sn->prop_args, sizeof(req.dpu.payload)); + msg.send_size = sizeof(req.dpu); + msg.opcode = MSG_OP_EXEC_DPU; + break; + } + default: + XDNA_DBG(xdna, "Invalid ERT cmd op code: %d", op); + return -EINVAL; + } + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + print_hex_dump_debug("cmd: ", DUMP_PREFIX_OFFSET, 16, 4, &req, + 0x40, false); + + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(xdna, "Send message failed"); + return ret; + } + + return 0; +} + +static int +aie2_cmdlist_fill_one_slot_cf(void *cmd_buf, u32 offset, + struct amdxdna_gem_obj *abo, u32 *size) +{ + struct cmd_chain_slot_execbuf_cf *buf = cmd_buf + offset; + int cu_idx = amdxdna_cmd_get_cu_idx(abo); + u32 payload_len; + void *payload; + + if (cu_idx < 0) + return -EINVAL; + + payload = amdxdna_cmd_get_payload(abo, &payload_len); + if (!payload) + return -EINVAL; + + if (!slot_has_space(*buf, offset, payload_len)) + return -ENOSPC; + + buf->cu_idx = cu_idx; + buf->arg_cnt = payload_len / sizeof(u32); + memcpy(buf->args, payload, payload_len); + /* Accurate buf size to hint firmware to do necessary copy */ + *size = sizeof(*buf) + payload_len; + return 0; +} + +static int +aie2_cmdlist_fill_one_slot_dpu(void *cmd_buf, u32 offset, + struct amdxdna_gem_obj *abo, u32 *size) +{ + struct cmd_chain_slot_dpu *buf = cmd_buf + offset; + int cu_idx = amdxdna_cmd_get_cu_idx(abo); + struct amdxdna_cmd_start_npu *sn; + u32 payload_len; + void *payload; + u32 arg_sz; + + if (cu_idx < 0) + return -EINVAL; + + payload = amdxdna_cmd_get_payload(abo, &payload_len); + if (!payload) + return -EINVAL; + sn = payload; + arg_sz = payload_len - sizeof(*sn); + if (payload_len < sizeof(*sn) || arg_sz > MAX_DPU_ARGS_SIZE) + return -EINVAL; + + if (!slot_has_space(*buf, offset, arg_sz)) + return -ENOSPC; + + buf->inst_buf_addr = sn->buffer; + buf->inst_size = sn->buffer_size; + buf->inst_prop_cnt = sn->prop_count; + buf->cu_idx = cu_idx; + buf->arg_cnt = arg_sz / sizeof(u32); + memcpy(buf->args, sn->prop_args, arg_sz); + + /* Accurate buf size to hint firmware to do necessary copy */ + *size = sizeof(*buf) + arg_sz; + return 0; +} + +static int +aie2_cmdlist_fill_one_slot(u32 op, struct amdxdna_gem_obj *cmdbuf_abo, u32 offset, + struct amdxdna_gem_obj *abo, u32 *size) +{ + u32 this_op = amdxdna_cmd_get_op(abo); + void *cmd_buf = cmdbuf_abo->mem.kva; + int ret; + + if (this_op != op) { + ret = -EINVAL; + goto done; + } + + switch (op) { + case ERT_START_CU: + ret = aie2_cmdlist_fill_one_slot_cf(cmd_buf, offset, abo, size); + break; + case ERT_START_NPU: + ret = aie2_cmdlist_fill_one_slot_dpu(cmd_buf, offset, abo, size); + break; + default: + ret = -EOPNOTSUPP; + } + +done: + if (ret) { + XDNA_ERR(abo->client->xdna, "Can't fill slot for cmd op %d ret %d", + op, ret); + } + return ret; +} + +static inline struct amdxdna_gem_obj * +aie2_cmdlist_get_cmd_buf(struct amdxdna_sched_job *job) +{ + int idx = get_job_idx(job->seq); + + return job->hwctx->priv->cmd_buf[idx]; +} + +static void +aie2_cmdlist_prepare_request(struct cmd_chain_req *req, + struct amdxdna_gem_obj *cmdbuf_abo, u32 size, u32 cnt) +{ + req->buf_addr = cmdbuf_abo->mem.dev_addr; + req->buf_size = size; + req->count = cnt; + drm_clflush_virt_range(cmdbuf_abo->mem.kva, size); + XDNA_DBG(cmdbuf_abo->client->xdna, "Command buf addr 0x%llx size 0x%x count %d", + req->buf_addr, size, cnt); +} + +static inline u32 +aie2_cmd_op_to_msg_op(u32 op) +{ + switch (op) { + case ERT_START_CU: + return MSG_OP_CHAIN_EXEC_BUFFER_CF; + case ERT_START_NPU: + return MSG_OP_CHAIN_EXEC_DPU; + default: + return MSG_OP_MAX_OPCODE; + } +} + +int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)) +{ + struct amdxdna_gem_obj *cmdbuf_abo = aie2_cmdlist_get_cmd_buf(job); + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_client *client = hwctx->client; + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + struct amdxdna_cmd_chain *payload; + struct xdna_mailbox_msg msg; + struct cmd_chain_req req; + u32 payload_len; + u32 offset = 0; + u32 size; + int ret; + u32 op; + u32 i; + + op = amdxdna_cmd_get_op(cmd_abo); + payload = amdxdna_cmd_get_payload(cmd_abo, &payload_len); + if (op != ERT_CMD_CHAIN || !payload || + payload_len < struct_size(payload, data, payload->command_count)) + return -EINVAL; + + for (i = 0; i < payload->command_count; i++) { + u32 boh = (u32)(payload->data[i]); + struct amdxdna_gem_obj *abo; + + abo = amdxdna_gem_get_obj(client, boh, AMDXDNA_BO_CMD); + if (!abo) { + XDNA_ERR(client->xdna, "Failed to find cmd BO %d", boh); + return -ENOENT; + } + + /* All sub-cmd should have same op, use the first one. */ + if (i == 0) + op = amdxdna_cmd_get_op(abo); + + ret = aie2_cmdlist_fill_one_slot(op, cmdbuf_abo, offset, abo, &size); + amdxdna_gem_put_obj(abo); + if (ret) + return -EINVAL; + + offset += size; + } + + /* The offset is the accumulated total size of the cmd buffer */ + aie2_cmdlist_prepare_request(&req, cmdbuf_abo, offset, payload->command_count); + + msg.opcode = aie2_cmd_op_to_msg_op(op); + if (msg.opcode == MSG_OP_MAX_OPCODE) + return -EOPNOTSUPP; + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + msg.send_size = sizeof(req); + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(hwctx->client->xdna, "Send message failed"); + return ret; + } + + return 0; +} + +int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)) +{ + struct amdxdna_gem_obj *cmdbuf_abo = aie2_cmdlist_get_cmd_buf(job); + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + struct xdna_mailbox_msg msg; + struct cmd_chain_req req; + u32 size; + int ret; + u32 op; + + op = amdxdna_cmd_get_op(cmd_abo); + ret = aie2_cmdlist_fill_one_slot(op, cmdbuf_abo, 0, cmd_abo, &size); + if (ret) + return ret; + + aie2_cmdlist_prepare_request(&req, cmdbuf_abo, size, 1); + + msg.opcode = aie2_cmd_op_to_msg_op(op); + if (msg.opcode == MSG_OP_MAX_OPCODE) + return -EOPNOTSUPP; + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + msg.send_size = sizeof(req); + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(hwctx->client->xdna, "Send message failed"); + return ret; + } + + return 0; +} + +int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)) +{ + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_gem_obj *abo = to_xdna_obj(job->bos[0]); + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct xdna_mailbox_msg msg; + struct sync_bo_req req; + int ret = 0; + + req.src_addr = 0; + req.dst_addr = abo->mem.dev_addr - hwctx->client->dev_heap->mem.dev_addr; + req.size = abo->mem.size; + + /* Device to Host */ + req.type = FIELD_PREP(AIE2_MSG_SYNC_BO_SRC_TYPE, SYNC_BO_DEV_MEM) | + FIELD_PREP(AIE2_MSG_SYNC_BO_DST_TYPE, SYNC_BO_HOST_MEM); + + XDNA_DBG(xdna, "sync %d bytes src(0x%llx) to dst(0x%llx) completed", + req.size, req.src_addr, req.dst_addr); + + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + msg.send_size = sizeof(req); + msg.opcode = MSG_OP_SYNC_BO; + + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(xdna, "Send message failed"); + return ret; + } + + return 0; +} diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h b/drivers/accel/amdxdna/aie2_msg_priv.h new file mode 100644 index 000000000000..6df9065b13f6 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_msg_priv.h @@ -0,0 +1,368 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_MSG_PRIV_H_ +#define _AIE2_MSG_PRIV_H_ + +enum aie2_msg_opcode { + MSG_OP_CREATE_CONTEXT = 0x2, + MSG_OP_DESTROY_CONTEXT = 0x3, + MSG_OP_SYNC_BO = 0x7, + MSG_OP_EXECUTE_BUFFER_CF = 0xC, + MSG_OP_QUERY_COL_STATUS = 0xD, + MSG_OP_QUERY_AIE_TILE_INFO = 0xE, + MSG_OP_QUERY_AIE_VERSION = 0xF, + MSG_OP_EXEC_DPU = 0x10, + MSG_OP_CONFIG_CU = 0x11, + MSG_OP_CHAIN_EXEC_BUFFER_CF = 0x12, + MSG_OP_CHAIN_EXEC_DPU = 0x13, + MSG_OP_MAX_XRT_OPCODE, + MSG_OP_SUSPEND = 0x101, + MSG_OP_RESUME = 0x102, + MSG_OP_ASSIGN_MGMT_PASID = 0x103, + MSG_OP_INVOKE_SELF_TEST = 0x104, + MSG_OP_MAP_HOST_BUFFER = 0x106, + MSG_OP_GET_FIRMWARE_VERSION = 0x108, + MSG_OP_SET_RUNTIME_CONFIG = 0x10A, + MSG_OP_GET_RUNTIME_CONFIG = 0x10B, + MSG_OP_REGISTER_ASYNC_EVENT_MSG = 0x10C, + MSG_OP_MAX_DRV_OPCODE, + MSG_OP_GET_PROTOCOL_VERSION = 0x301, + MSG_OP_MAX_OPCODE +}; + +enum aie2_msg_status { + AIE2_STATUS_SUCCESS = 0x0, + /* AIE Error codes */ + AIE2_STATUS_AIE_SATURATION_ERROR = 0x1000001, + AIE2_STATUS_AIE_FP_ERROR = 0x1000002, + AIE2_STATUS_AIE_STREAM_ERROR = 0x1000003, + AIE2_STATUS_AIE_ACCESS_ERROR = 0x1000004, + AIE2_STATUS_AIE_BUS_ERROR = 0x1000005, + AIE2_STATUS_AIE_INSTRUCTION_ERROR = 0x1000006, + AIE2_STATUS_AIE_ECC_ERROR = 0x1000007, + AIE2_STATUS_AIE_LOCK_ERROR = 0x1000008, + AIE2_STATUS_AIE_DMA_ERROR = 0x1000009, + AIE2_STATUS_AIE_MEM_PARITY_ERROR = 0x100000a, + AIE2_STATUS_AIE_PWR_CFG_ERROR = 0x100000b, + AIE2_STATUS_AIE_BACKTRACK_ERROR = 0x100000c, + AIE2_STATUS_MAX_AIE_STATUS_CODE, + /* MGMT ERT Error codes */ + AIE2_STATUS_MGMT_ERT_SELF_TEST_FAILURE = 0x2000001, + AIE2_STATUS_MGMT_ERT_HASH_MISMATCH, + AIE2_STATUS_MGMT_ERT_NOAVAIL, + AIE2_STATUS_MGMT_ERT_INVALID_PARAM, + AIE2_STATUS_MGMT_ERT_ENTER_SUSPEND_FAILURE, + AIE2_STATUS_MGMT_ERT_BUSY, + AIE2_STATUS_MGMT_ERT_APPLICATION_ACTIVE, + MAX_MGMT_ERT_STATUS_CODE, + /* APP ERT Error codes */ + AIE2_STATUS_APP_ERT_FIRST_ERROR = 0x3000001, + AIE2_STATUS_APP_INVALID_INSTR, + AIE2_STATUS_APP_LOAD_PDI_FAIL, + MAX_APP_ERT_STATUS_CODE, + /* NPU RTOS Error Codes */ + AIE2_STATUS_INVALID_INPUT_BUFFER = 0x4000001, + AIE2_STATUS_INVALID_COMMAND, + AIE2_STATUS_INVALID_PARAM, + AIE2_STATUS_INVALID_OPERATION = 0x4000006, + AIE2_STATUS_ASYNC_EVENT_MSGS_FULL, + AIE2_STATUS_MAX_RTOS_STATUS_CODE, + MAX_AIE2_STATUS_CODE +}; + +struct assign_mgmt_pasid_req { + __u16 pasid; + __u16 reserved; +} __packed; + +struct assign_mgmt_pasid_resp { + enum aie2_msg_status status; +} __packed; + +struct map_host_buffer_req { + __u32 context_id; + __u64 buf_addr; + __u64 buf_size; +} __packed; + +struct map_host_buffer_resp { + enum aie2_msg_status status; +} __packed; + +#define MAX_CQ_PAIRS 2 +struct cq_info { + __u32 head_addr; + __u32 tail_addr; + __u32 buf_addr; + __u32 buf_size; +}; + +struct cq_pair { + struct cq_info x2i_q; + struct cq_info i2x_q; +}; + +struct create_ctx_req { + __u32 aie_type; + __u8 start_col; + __u8 num_col; + __u16 reserved; + __u8 num_cq_pairs_requested; + __u8 reserved1; + __u16 pasid; + __u32 pad[2]; + __u32 sec_comm_target_type; + __u32 context_priority; +} __packed; + +struct create_ctx_resp { + enum aie2_msg_status status; + __u32 context_id; + __u16 msix_id; + __u8 num_cq_pairs_allocated; + __u8 reserved; + struct cq_pair cq_pair[MAX_CQ_PAIRS]; +} __packed; + +struct destroy_ctx_req { + __u32 context_id; +} __packed; + +struct destroy_ctx_resp { + enum aie2_msg_status status; +} __packed; + +struct execute_buffer_req { + __u32 cu_idx; + __u32 payload[19]; +} __packed; + +struct exec_dpu_req { + __u64 inst_buf_addr; + __u32 inst_size; + __u32 inst_prop_cnt; + __u32 cu_idx; + __u32 payload[35]; +} __packed; + +struct execute_buffer_resp { + enum aie2_msg_status status; +} __packed; + +struct aie_tile_info { + __u32 size; + __u16 major; + __u16 minor; + __u16 cols; + __u16 rows; + __u16 core_rows; + __u16 mem_rows; + __u16 shim_rows; + __u16 core_row_start; + __u16 mem_row_start; + __u16 shim_row_start; + __u16 core_dma_channels; + __u16 mem_dma_channels; + __u16 shim_dma_channels; + __u16 core_locks; + __u16 mem_locks; + __u16 shim_locks; + __u16 core_events; + __u16 mem_events; + __u16 shim_events; + __u16 reserved; +}; + +struct aie_tile_info_req { + __u32 reserved; +} __packed; + +struct aie_tile_info_resp { + enum aie2_msg_status status; + struct aie_tile_info info; +} __packed; + +struct aie_version_info_req { + __u32 reserved; +} __packed; + +struct aie_version_info_resp { + enum aie2_msg_status status; + __u16 major; + __u16 minor; +} __packed; + +struct aie_column_info_req { + __u64 dump_buff_addr; + __u32 dump_buff_size; + __u32 num_cols; + __u32 aie_bitmap; +} __packed; + +struct aie_column_info_resp { + enum aie2_msg_status status; + __u32 size; +} __packed; + +struct suspend_req { + __u32 place_holder; +} __packed; + +struct suspend_resp { + enum aie2_msg_status status; +} __packed; + +struct resume_req { + __u32 place_holder; +} __packed; + +struct resume_resp { + enum aie2_msg_status status; +} __packed; + +struct check_header_hash_req { + __u64 hash_high; + __u64 hash_low; +} __packed; + +struct check_header_hash_resp { + enum aie2_msg_status status; +} __packed; + +struct query_error_req { + __u64 buf_addr; + __u32 buf_size; + __u32 next_row; + __u32 next_column; + __u32 next_module; +} __packed; + +struct query_error_resp { + enum aie2_msg_status status; + __u32 num_err; + __u32 has_next_err; + __u32 next_row; + __u32 next_column; + __u32 next_module; +} __packed; + +struct protocol_version_req { + __u32 reserved; +} __packed; + +struct protocol_version_resp { + enum aie2_msg_status status; + __u32 major; + __u32 minor; +} __packed; + +struct firmware_version_req { + __u32 reserved; +} __packed; + +struct firmware_version_resp { + enum aie2_msg_status status; + __u32 major; + __u32 minor; + __u32 sub; + __u32 build; +} __packed; + +#define MAX_NUM_CUS 32 +#define AIE2_MSG_CFG_CU_PDI_ADDR GENMASK(16, 0) +#define AIE2_MSG_CFG_CU_FUNC GENMASK(24, 17) +struct config_cu_req { + __u32 num_cus; + __u32 cfgs[MAX_NUM_CUS]; +} __packed; + +struct config_cu_resp { + enum aie2_msg_status status; +} __packed; + +struct set_runtime_cfg_req { + __u32 type; + __u64 value; +} __packed; + +struct set_runtime_cfg_resp { + enum aie2_msg_status status; +} __packed; + +struct get_runtime_cfg_req { + __u32 type; +} __packed; + +struct get_runtime_cfg_resp { + enum aie2_msg_status status; + __u64 value; +} __packed; + +enum async_event_type { + ASYNC_EVENT_TYPE_AIE_ERROR, + ASYNC_EVENT_TYPE_EXCEPTION, + MAX_ASYNC_EVENT_TYPE +}; + +#define ASYNC_BUF_SIZE SZ_8K +struct async_event_msg_req { + __u64 buf_addr; + __u32 buf_size; +} __packed; + +struct async_event_msg_resp { + enum aie2_msg_status status; + enum async_event_type type; +} __packed; + +#define MAX_CHAIN_CMDBUF_SIZE SZ_4K +#define slot_has_space(slot, offset, payload_size) \ + (MAX_CHAIN_CMDBUF_SIZE >= (offset) + (payload_size) + \ + sizeof(typeof(slot))) + +struct cmd_chain_slot_execbuf_cf { + __u32 cu_idx; + __u32 arg_cnt; + __u32 args[] __counted_by(arg_cnt); +}; + +struct cmd_chain_slot_dpu { + __u64 inst_buf_addr; + __u32 inst_size; + __u32 inst_prop_cnt; + __u32 cu_idx; + __u32 arg_cnt; +#define MAX_DPU_ARGS_SIZE (34 * sizeof(__u32)) + __u32 args[] __counted_by(arg_cnt); +}; + +struct cmd_chain_req { + __u64 buf_addr; + __u32 buf_size; + __u32 count; +} __packed; + +struct cmd_chain_resp { + enum aie2_msg_status status; + __u32 fail_cmd_idx; + enum aie2_msg_status fail_cmd_status; +} __packed; + +#define AIE2_MSG_SYNC_BO_SRC_TYPE GENMASK(3, 0) +#define AIE2_MSG_SYNC_BO_DST_TYPE GENMASK(7, 4) +struct sync_bo_req { + __u64 src_addr; + __u64 dst_addr; + __u32 size; +#define SYNC_BO_DEV_MEM 0 +#define SYNC_BO_HOST_MEM 2 + __u32 type; +} __packed; + +struct sync_bo_resp { + enum aie2_msg_status status; +} __packed; +#endif /* _AIE2_MSG_PRIV_H_ */ diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c new file mode 100644 index 000000000000..5a058e565b01 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -0,0 +1,928 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/drm_drv.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_managed.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/errno.h> +#include <linux/firmware.h> +#include <linux/iommu.h> +#include <linux/iopoll.h> +#include <linux/pci.h> +#include <linux/xarray.h> + +#include "aie2_msg_priv.h" +#include "aie2_pci.h" +#include "aie2_solver.h" +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +static int aie2_max_col = XRS_MAX_COL; +module_param(aie2_max_col, uint, 0600); +MODULE_PARM_DESC(aie2_max_col, "Maximum column could be used"); + +/* + * The management mailbox channel is allocated by firmware. + * The related register and ring buffer information is on SRAM BAR. + * This struct is the register layout. + */ +#define MGMT_MBOX_MAGIC 0x55504e5f /* _NPU */ +struct mgmt_mbox_chann_info { + __u32 x2i_tail; + __u32 x2i_head; + __u32 x2i_buf; + __u32 x2i_buf_sz; + __u32 i2x_tail; + __u32 i2x_head; + __u32 i2x_buf; + __u32 i2x_buf_sz; + __u32 magic; + __u32 msi_id; + __u32 prot_major; + __u32 prot_minor; + __u32 rsvd[4]; +}; + +static int aie2_check_protocol(struct amdxdna_dev_hdl *ndev, u32 fw_major, u32 fw_minor) +{ + struct amdxdna_dev *xdna = ndev->xdna; + + /* + * The driver supported mailbox behavior is defined by + * ndev->priv->protocol_major and protocol_minor. + * + * When protocol_major and fw_major are different, it means driver + * and firmware are incompatible. + */ + if (ndev->priv->protocol_major != fw_major) { + XDNA_ERR(xdna, "Incompatible firmware protocol major %d minor %d", + fw_major, fw_minor); + return -EINVAL; + } + + /* + * When protocol_minor is greater then fw_minor, that means driver + * relies on operation the installed firmware does not support. + */ + if (ndev->priv->protocol_minor > fw_minor) { + XDNA_ERR(xdna, "Firmware minor version smaller than supported"); + return -EINVAL; + } + return 0; +} + +static void aie2_dump_chann_info_debug(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->xdna; + + XDNA_DBG(xdna, "i2x tail 0x%x", ndev->mgmt_i2x.mb_tail_ptr_reg); + XDNA_DBG(xdna, "i2x head 0x%x", ndev->mgmt_i2x.mb_head_ptr_reg); + XDNA_DBG(xdna, "i2x ringbuf 0x%x", ndev->mgmt_i2x.rb_start_addr); + XDNA_DBG(xdna, "i2x rsize 0x%x", ndev->mgmt_i2x.rb_size); + XDNA_DBG(xdna, "x2i tail 0x%x", ndev->mgmt_x2i.mb_tail_ptr_reg); + XDNA_DBG(xdna, "x2i head 0x%x", ndev->mgmt_x2i.mb_head_ptr_reg); + XDNA_DBG(xdna, "x2i ringbuf 0x%x", ndev->mgmt_x2i.rb_start_addr); + XDNA_DBG(xdna, "x2i rsize 0x%x", ndev->mgmt_x2i.rb_size); + XDNA_DBG(xdna, "x2i chann index 0x%x", ndev->mgmt_chan_idx); + XDNA_DBG(xdna, "mailbox protocol major 0x%x", ndev->mgmt_prot_major); + XDNA_DBG(xdna, "mailbox protocol minor 0x%x", ndev->mgmt_prot_minor); +} + +static int aie2_get_mgmt_chann_info(struct amdxdna_dev_hdl *ndev) +{ + struct mgmt_mbox_chann_info info_regs; + struct xdna_mailbox_chann_res *i2x; + struct xdna_mailbox_chann_res *x2i; + u32 addr, off; + u32 *reg; + int ret; + int i; + + /* + * Once firmware is alive, it will write management channel + * information in SRAM BAR and write the address of that information + * at FW_ALIVE_OFF offset in SRMA BAR. + * + * Read a non-zero value from FW_ALIVE_OFF implies that firmware + * is alive. + */ + ret = readx_poll_timeout(readl, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF), + addr, addr, AIE2_INTERVAL, AIE2_TIMEOUT); + if (ret || !addr) + return -ETIME; + + off = AIE2_SRAM_OFF(ndev, addr); + reg = (u32 *)&info_regs; + for (i = 0; i < sizeof(info_regs) / sizeof(u32); i++) + reg[i] = readl(ndev->sram_base + off + i * sizeof(u32)); + + if (info_regs.magic != MGMT_MBOX_MAGIC) { + XDNA_ERR(ndev->xdna, "Invalid mbox magic 0x%x", info_regs.magic); + ret = -EINVAL; + goto done; + } + + i2x = &ndev->mgmt_i2x; + x2i = &ndev->mgmt_x2i; + + i2x->mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.i2x_head); + i2x->mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.i2x_tail); + i2x->rb_start_addr = AIE2_SRAM_OFF(ndev, info_regs.i2x_buf); + i2x->rb_size = info_regs.i2x_buf_sz; + + x2i->mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.x2i_head); + x2i->mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.x2i_tail); + x2i->rb_start_addr = AIE2_SRAM_OFF(ndev, info_regs.x2i_buf); + x2i->rb_size = info_regs.x2i_buf_sz; + + ndev->mgmt_chan_idx = info_regs.msi_id; + ndev->mgmt_prot_major = info_regs.prot_major; + ndev->mgmt_prot_minor = info_regs.prot_minor; + + ret = aie2_check_protocol(ndev, ndev->mgmt_prot_major, ndev->mgmt_prot_minor); + +done: + aie2_dump_chann_info_debug(ndev); + + /* Must clear address at FW_ALIVE_OFF */ + writel(0, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF)); + + return ret; +} + +int aie2_runtime_cfg(struct amdxdna_dev_hdl *ndev, + enum rt_config_category category, u32 *val) +{ + const struct rt_config *cfg; + u32 value; + int ret; + + for (cfg = ndev->priv->rt_config; cfg->type; cfg++) { + if (cfg->category != category) + continue; + + value = val ? *val : cfg->value; + ret = aie2_set_runtime_cfg(ndev, cfg->type, value); + if (ret) { + XDNA_ERR(ndev->xdna, "Set type %d value %d failed", + cfg->type, value); + return ret; + } + } + + return 0; +} + +static int aie2_xdna_reset(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_suspend_fw(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Suspend firmware failed"); + return ret; + } + + ret = aie2_resume_fw(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Resume firmware failed"); + return ret; + } + + return 0; +} + +static int aie2_mgmt_fw_init(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_runtime_cfg(ndev, AIE2_RT_CFG_INIT, NULL); + if (ret) { + XDNA_ERR(ndev->xdna, "Runtime config failed"); + return ret; + } + + ret = aie2_assign_mgmt_pasid(ndev, 0); + if (ret) { + XDNA_ERR(ndev->xdna, "Can not assign PASID"); + return ret; + } + + ret = aie2_xdna_reset(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Reset firmware failed"); + return ret; + } + + if (!ndev->async_events) + return 0; + + ret = aie2_error_async_events_send(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Send async events failed"); + return ret; + } + + return 0; +} + +static int aie2_mgmt_fw_query(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_query_firmware_version(ndev, &ndev->xdna->fw_ver); + if (ret) { + XDNA_ERR(ndev->xdna, "query firmware version failed"); + return ret; + } + + ret = aie2_query_aie_version(ndev, &ndev->version); + if (ret) { + XDNA_ERR(ndev->xdna, "Query AIE version failed"); + return ret; + } + + ret = aie2_query_aie_metadata(ndev, &ndev->metadata); + if (ret) { + XDNA_ERR(ndev->xdna, "Query AIE metadata failed"); + return ret; + } + + return 0; +} + +static void aie2_mgmt_fw_fini(struct amdxdna_dev_hdl *ndev) +{ + if (aie2_suspend_fw(ndev)) + XDNA_ERR(ndev->xdna, "Suspend_fw failed"); + XDNA_DBG(ndev->xdna, "Firmware suspended"); +} + +static int aie2_xrs_load(void *cb_arg, struct xrs_action_load *action) +{ + struct amdxdna_hwctx *hwctx = cb_arg; + struct amdxdna_dev *xdna; + int ret; + + xdna = hwctx->client->xdna; + + hwctx->start_col = action->part.start_col; + hwctx->num_col = action->part.ncols; + ret = aie2_create_context(xdna->dev_handle, hwctx); + if (ret) + XDNA_ERR(xdna, "create context failed, ret %d", ret); + + return ret; +} + +static int aie2_xrs_unload(void *cb_arg) +{ + struct amdxdna_hwctx *hwctx = cb_arg; + struct amdxdna_dev *xdna; + int ret; + + xdna = hwctx->client->xdna; + + ret = aie2_destroy_context(xdna->dev_handle, hwctx); + if (ret) + XDNA_ERR(xdna, "destroy context failed, ret %d", ret); + + return ret; +} + +static int aie2_xrs_set_dft_dpm_level(struct drm_device *ddev, u32 dpm_level) +{ + struct amdxdna_dev *xdna = to_xdna_dev(ddev); + struct amdxdna_dev_hdl *ndev; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + ndev = xdna->dev_handle; + ndev->dft_dpm_level = dpm_level; + if (ndev->pw_mode != POWER_MODE_DEFAULT || ndev->dpm_level == dpm_level) + return 0; + + return ndev->priv->hw_ops.set_dpm(ndev, dpm_level); +} + +static struct xrs_action_ops aie2_xrs_actions = { + .load = aie2_xrs_load, + .unload = aie2_xrs_unload, + .set_dft_dpm_level = aie2_xrs_set_dft_dpm_level, +}; + +static void aie2_hw_stop(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + + if (ndev->dev_status <= AIE2_DEV_INIT) { + XDNA_ERR(xdna, "device is already stopped"); + return; + } + + aie2_mgmt_fw_fini(ndev); + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_destroy_channel(ndev->mgmt_chann); + ndev->mgmt_chann = NULL; + drmm_kfree(&xdna->ddev, ndev->mbox); + ndev->mbox = NULL; + aie2_psp_stop(ndev->psp_hdl); + aie2_smu_fini(ndev); + pci_disable_device(pdev); + + ndev->dev_status = AIE2_DEV_INIT; +} + +static int aie2_hw_start(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct xdna_mailbox_res mbox_res; + u32 xdna_mailbox_intr_reg; + int mgmt_mb_irq, ret; + + if (ndev->dev_status >= AIE2_DEV_START) { + XDNA_INFO(xdna, "device is already started"); + return 0; + } + + ret = pci_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "failed to enable device, ret %d", ret); + return ret; + } + pci_set_master(pdev); + + ret = aie2_smu_init(ndev); + if (ret) { + XDNA_ERR(xdna, "failed to init smu, ret %d", ret); + goto disable_dev; + } + + ret = aie2_psp_start(ndev->psp_hdl); + if (ret) { + XDNA_ERR(xdna, "failed to start psp, ret %d", ret); + goto fini_smu; + } + + ret = aie2_get_mgmt_chann_info(ndev); + if (ret) { + XDNA_ERR(xdna, "firmware is not alive"); + goto stop_psp; + } + + mbox_res.ringbuf_base = ndev->sram_base; + mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar); + mbox_res.mbox_base = ndev->mbox_base; + mbox_res.mbox_size = MBOX_SIZE(ndev); + mbox_res.name = "xdna_mailbox"; + ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res); + if (!ndev->mbox) { + XDNA_ERR(xdna, "failed to create mailbox device"); + ret = -ENODEV; + goto stop_psp; + } + + mgmt_mb_irq = pci_irq_vector(pdev, ndev->mgmt_chan_idx); + if (mgmt_mb_irq < 0) { + ret = mgmt_mb_irq; + XDNA_ERR(xdna, "failed to alloc irq vector, ret %d", ret); + goto stop_psp; + } + + xdna_mailbox_intr_reg = ndev->mgmt_i2x.mb_head_ptr_reg + 4; + ndev->mgmt_chann = xdna_mailbox_create_channel(ndev->mbox, + &ndev->mgmt_x2i, + &ndev->mgmt_i2x, + xdna_mailbox_intr_reg, + mgmt_mb_irq); + if (!ndev->mgmt_chann) { + XDNA_ERR(xdna, "failed to create management mailbox channel"); + ret = -EINVAL; + goto stop_psp; + } + + ret = aie2_pm_init(ndev); + if (ret) { + XDNA_ERR(xdna, "failed to init pm, ret %d", ret); + goto destroy_mgmt_chann; + } + + ret = aie2_mgmt_fw_init(ndev); + if (ret) { + XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret); + goto destroy_mgmt_chann; + } + + ndev->dev_status = AIE2_DEV_START; + + return 0; + +destroy_mgmt_chann: + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_destroy_channel(ndev->mgmt_chann); +stop_psp: + aie2_psp_stop(ndev->psp_hdl); +fini_smu: + aie2_smu_fini(ndev); +disable_dev: + pci_disable_device(pdev); + + return ret; +} + +static int aie2_init(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + void __iomem *tbl[PCI_NUM_RESOURCES] = {0}; + struct init_config xrs_cfg = { 0 }; + struct amdxdna_dev_hdl *ndev; + struct psp_config psp_conf; + const struct firmware *fw; + unsigned long bars = 0; + int i, nvec, ret; + + ndev = drmm_kzalloc(&xdna->ddev, sizeof(*ndev), GFP_KERNEL); + if (!ndev) + return -ENOMEM; + + ndev->priv = xdna->dev_info->dev_priv; + ndev->xdna = xdna; + + ret = request_firmware(&fw, ndev->priv->fw_path, &pdev->dev); + if (ret) { + XDNA_ERR(xdna, "failed to request_firmware %s, ret %d", + ndev->priv->fw_path, ret); + return ret; + } + + ret = pcim_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "pcim enable device failed, ret %d", ret); + goto release_fw; + } + + for (i = 0; i < PSP_MAX_REGS; i++) + set_bit(PSP_REG_BAR(ndev, i), &bars); + + set_bit(xdna->dev_info->sram_bar, &bars); + set_bit(xdna->dev_info->smu_bar, &bars); + set_bit(xdna->dev_info->mbox_bar, &bars); + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + if (!test_bit(i, &bars)) + continue; + tbl[i] = pcim_iomap(pdev, i, 0); + if (!tbl[i]) { + XDNA_ERR(xdna, "map bar %d failed", i); + ret = -ENOMEM; + goto release_fw; + } + } + + ndev->sram_base = tbl[xdna->dev_info->sram_bar]; + ndev->smu_base = tbl[xdna->dev_info->smu_bar]; + ndev->mbox_base = tbl[xdna->dev_info->mbox_bar]; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + XDNA_ERR(xdna, "Failed to set DMA mask: %d", ret); + goto release_fw; + } + + nvec = pci_msix_vec_count(pdev); + if (nvec <= 0) { + XDNA_ERR(xdna, "does not get number of interrupt vector"); + ret = -EINVAL; + goto release_fw; + } + + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX); + if (ret < 0) { + XDNA_ERR(xdna, "failed to alloc irq vectors, ret %d", ret); + goto release_fw; + } + + ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + if (ret) { + XDNA_ERR(xdna, "Enable PASID failed, ret %d", ret); + goto free_irq; + } + + psp_conf.fw_size = fw->size; + psp_conf.fw_buf = fw->data; + for (i = 0; i < PSP_MAX_REGS; i++) + psp_conf.psp_regs[i] = tbl[PSP_REG_BAR(ndev, i)] + PSP_REG_OFF(ndev, i); + ndev->psp_hdl = aie2m_psp_create(&xdna->ddev, &psp_conf); + if (!ndev->psp_hdl) { + XDNA_ERR(xdna, "failed to create psp"); + ret = -ENOMEM; + goto disable_sva; + } + xdna->dev_handle = ndev; + + ret = aie2_hw_start(xdna); + if (ret) { + XDNA_ERR(xdna, "start npu failed, ret %d", ret); + goto disable_sva; + } + + ret = aie2_mgmt_fw_query(ndev); + if (ret) { + XDNA_ERR(xdna, "Query firmware failed, ret %d", ret); + goto stop_hw; + } + ndev->total_col = min(aie2_max_col, ndev->metadata.cols); + + xrs_cfg.clk_list.num_levels = ndev->max_dpm_level + 1; + for (i = 0; i < xrs_cfg.clk_list.num_levels; i++) + xrs_cfg.clk_list.cu_clk_list[i] = ndev->priv->dpm_clk_tbl[i].hclk; + xrs_cfg.sys_eff_factor = 1; + xrs_cfg.ddev = &xdna->ddev; + xrs_cfg.actions = &aie2_xrs_actions; + xrs_cfg.total_col = ndev->total_col; + + xdna->xrs_hdl = xrsm_init(&xrs_cfg); + if (!xdna->xrs_hdl) { + XDNA_ERR(xdna, "Initialize resolver failed"); + ret = -EINVAL; + goto stop_hw; + } + + ret = aie2_error_async_events_alloc(ndev); + if (ret) { + XDNA_ERR(xdna, "Allocate async events failed, ret %d", ret); + goto stop_hw; + } + + ret = aie2_error_async_events_send(ndev); + if (ret) { + XDNA_ERR(xdna, "Send async events failed, ret %d", ret); + goto async_event_free; + } + + /* Issue a command to make sure firmware handled async events */ + ret = aie2_query_firmware_version(ndev, &ndev->xdna->fw_ver); + if (ret) { + XDNA_ERR(xdna, "Re-query firmware version failed"); + goto async_event_free; + } + + release_firmware(fw); + return 0; + +async_event_free: + aie2_error_async_events_free(ndev); +stop_hw: + aie2_hw_stop(xdna); +disable_sva: + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); +free_irq: + pci_free_irq_vectors(pdev); +release_fw: + release_firmware(fw); + + return ret; +} + +static void aie2_fini(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + + aie2_hw_stop(xdna); + aie2_error_async_events_free(ndev); + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + pci_free_irq_vectors(pdev); +} + +static int aie2_get_aie_status(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_aie_status status; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + int ret; + + ndev = xdna->dev_handle; + if (copy_from_user(&status, u64_to_user_ptr(args->buffer), sizeof(status))) { + XDNA_ERR(xdna, "Failed to copy AIE request into kernel"); + return -EFAULT; + } + + if (ndev->metadata.cols * ndev->metadata.size < status.buffer_size) { + XDNA_ERR(xdna, "Invalid buffer size. Given Size: %u. Need Size: %u.", + status.buffer_size, ndev->metadata.cols * ndev->metadata.size); + return -EINVAL; + } + + ret = aie2_query_status(ndev, u64_to_user_ptr(status.buffer), + status.buffer_size, &status.cols_filled); + if (ret) { + XDNA_ERR(xdna, "Failed to get AIE status info. Ret: %d", ret); + return ret; + } + + if (copy_to_user(u64_to_user_ptr(args->buffer), &status, sizeof(status))) { + XDNA_ERR(xdna, "Failed to copy AIE request info to user space"); + return -EFAULT; + } + + return 0; +} + +static int aie2_get_aie_metadata(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_aie_metadata *meta; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + int ret = 0; + + ndev = xdna->dev_handle; + meta = kzalloc(sizeof(*meta), GFP_KERNEL); + if (!meta) + return -ENOMEM; + + meta->col_size = ndev->metadata.size; + meta->cols = ndev->metadata.cols; + meta->rows = ndev->metadata.rows; + + meta->version.major = ndev->metadata.version.major; + meta->version.minor = ndev->metadata.version.minor; + + meta->core.row_count = ndev->metadata.core.row_count; + meta->core.row_start = ndev->metadata.core.row_start; + meta->core.dma_channel_count = ndev->metadata.core.dma_channel_count; + meta->core.lock_count = ndev->metadata.core.lock_count; + meta->core.event_reg_count = ndev->metadata.core.event_reg_count; + + meta->mem.row_count = ndev->metadata.mem.row_count; + meta->mem.row_start = ndev->metadata.mem.row_start; + meta->mem.dma_channel_count = ndev->metadata.mem.dma_channel_count; + meta->mem.lock_count = ndev->metadata.mem.lock_count; + meta->mem.event_reg_count = ndev->metadata.mem.event_reg_count; + + meta->shim.row_count = ndev->metadata.shim.row_count; + meta->shim.row_start = ndev->metadata.shim.row_start; + meta->shim.dma_channel_count = ndev->metadata.shim.dma_channel_count; + meta->shim.lock_count = ndev->metadata.shim.lock_count; + meta->shim.event_reg_count = ndev->metadata.shim.event_reg_count; + + if (copy_to_user(u64_to_user_ptr(args->buffer), meta, sizeof(*meta))) + ret = -EFAULT; + + kfree(meta); + return ret; +} + +static int aie2_get_aie_version(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_aie_version version; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + + ndev = xdna->dev_handle; + version.major = ndev->version.major; + version.minor = ndev->version.minor; + + if (copy_to_user(u64_to_user_ptr(args->buffer), &version, sizeof(version))) + return -EFAULT; + + return 0; +} + +static int aie2_get_firmware_version(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_firmware_version version; + struct amdxdna_dev *xdna = client->xdna; + + version.major = xdna->fw_ver.major; + version.minor = xdna->fw_ver.minor; + version.patch = xdna->fw_ver.sub; + version.build = xdna->fw_ver.build; + + if (copy_to_user(u64_to_user_ptr(args->buffer), &version, sizeof(version))) + return -EFAULT; + + return 0; +} + +static int aie2_get_power_mode(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_get_power_mode mode = {}; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + + ndev = xdna->dev_handle; + mode.power_mode = ndev->pw_mode; + + if (copy_to_user(u64_to_user_ptr(args->buffer), &mode, sizeof(mode))) + return -EFAULT; + + return 0; +} + +static int aie2_get_clock_metadata(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_clock_metadata *clock; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + int ret = 0; + + ndev = xdna->dev_handle; + clock = kzalloc(sizeof(*clock), GFP_KERNEL); + if (!clock) + return -ENOMEM; + + snprintf(clock->mp_npu_clock.name, sizeof(clock->mp_npu_clock.name), + "MP-NPU Clock"); + clock->mp_npu_clock.freq_mhz = ndev->npuclk_freq; + snprintf(clock->h_clock.name, sizeof(clock->h_clock.name), "H Clock"); + clock->h_clock.freq_mhz = ndev->hclk_freq; + + if (copy_to_user(u64_to_user_ptr(args->buffer), clock, sizeof(*clock))) + ret = -EFAULT; + + kfree(clock); + return ret; +} + +static int aie2_get_hwctx_status(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_hwctx __user *buf; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_drm_query_hwctx *tmp; + struct amdxdna_client *tmp_client; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + bool overflow = false; + u32 req_bytes = 0; + u32 hw_i = 0; + int ret = 0; + int idx; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + buf = u64_to_user_ptr(args->buffer); + list_for_each_entry(tmp_client, &xdna->client_list, node) { + idx = srcu_read_lock(&tmp_client->hwctx_srcu); + amdxdna_for_each_hwctx(tmp_client, hwctx_id, hwctx) { + req_bytes += sizeof(*tmp); + if (args->buffer_size < req_bytes) { + /* Continue iterating to get the required size */ + overflow = true; + continue; + } + + memset(tmp, 0, sizeof(*tmp)); + tmp->pid = tmp_client->pid; + tmp->context_id = hwctx->id; + tmp->start_col = hwctx->start_col; + tmp->num_col = hwctx->num_col; + tmp->command_submissions = hwctx->priv->seq; + tmp->command_completions = hwctx->priv->completed; + + if (copy_to_user(&buf[hw_i], tmp, sizeof(*tmp))) { + ret = -EFAULT; + srcu_read_unlock(&tmp_client->hwctx_srcu, idx); + goto out; + } + hw_i++; + } + srcu_read_unlock(&tmp_client->hwctx_srcu, idx); + } + + if (overflow) { + XDNA_ERR(xdna, "Invalid buffer size. Given: %u Need: %u.", + args->buffer_size, req_bytes); + ret = -EINVAL; + } + +out: + kfree(tmp); + args->buffer_size = req_bytes; + return ret; +} + +static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_info *args) +{ + struct amdxdna_dev *xdna = client->xdna; + int ret, idx; + + if (!drm_dev_enter(&xdna->ddev, &idx)) + return -ENODEV; + + switch (args->param) { + case DRM_AMDXDNA_QUERY_AIE_STATUS: + ret = aie2_get_aie_status(client, args); + break; + case DRM_AMDXDNA_QUERY_AIE_METADATA: + ret = aie2_get_aie_metadata(client, args); + break; + case DRM_AMDXDNA_QUERY_AIE_VERSION: + ret = aie2_get_aie_version(client, args); + break; + case DRM_AMDXDNA_QUERY_CLOCK_METADATA: + ret = aie2_get_clock_metadata(client, args); + break; + case DRM_AMDXDNA_QUERY_HW_CONTEXTS: + ret = aie2_get_hwctx_status(client, args); + break; + case DRM_AMDXDNA_QUERY_FIRMWARE_VERSION: + ret = aie2_get_firmware_version(client, args); + break; + case DRM_AMDXDNA_GET_POWER_MODE: + ret = aie2_get_power_mode(client, args); + break; + default: + XDNA_ERR(xdna, "Not supported request parameter %u", args->param); + ret = -EOPNOTSUPP; + } + XDNA_DBG(xdna, "Got param %d", args->param); + + drm_dev_exit(idx); + return ret; +} + +static int aie2_set_power_mode(struct amdxdna_client *client, + struct amdxdna_drm_set_state *args) +{ + struct amdxdna_drm_set_power_mode power_state; + enum amdxdna_power_mode_type power_mode; + struct amdxdna_dev *xdna = client->xdna; + + if (copy_from_user(&power_state, u64_to_user_ptr(args->buffer), + sizeof(power_state))) { + XDNA_ERR(xdna, "Failed to copy power mode request into kernel"); + return -EFAULT; + } + + if (XDNA_MBZ_DBG(xdna, power_state.pad, sizeof(power_state.pad))) + return -EINVAL; + + power_mode = power_state.power_mode; + if (power_mode > POWER_MODE_TURBO) { + XDNA_ERR(xdna, "Invalid power mode %d", power_mode); + return -EINVAL; + } + + return aie2_pm_set_mode(xdna->dev_handle, power_mode); +} + +static int aie2_set_state(struct amdxdna_client *client, + struct amdxdna_drm_set_state *args) +{ + struct amdxdna_dev *xdna = client->xdna; + int ret, idx; + + if (!drm_dev_enter(&xdna->ddev, &idx)) + return -ENODEV; + + switch (args->param) { + case DRM_AMDXDNA_SET_POWER_MODE: + ret = aie2_set_power_mode(client, args); + break; + default: + XDNA_ERR(xdna, "Not supported request parameter %u", args->param); + ret = -EOPNOTSUPP; + break; + } + + drm_dev_exit(idx); + return ret; +} + +const struct amdxdna_dev_ops aie2_ops = { + .init = aie2_init, + .fini = aie2_fini, + .resume = aie2_hw_start, + .suspend = aie2_hw_stop, + .get_aie_info = aie2_get_info, + .set_aie_state = aie2_set_state, + .hwctx_init = aie2_hwctx_init, + .hwctx_fini = aie2_hwctx_fini, + .hwctx_config = aie2_hwctx_config, + .cmd_submit = aie2_cmd_submit, + .hmm_invalidate = aie2_hmm_invalidate, + .hwctx_suspend = aie2_hwctx_suspend, + .hwctx_resume = aie2_hwctx_resume, +}; diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h new file mode 100644 index 000000000000..385914840eaa --- /dev/null +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_PCI_H_ +#define _AIE2_PCI_H_ + +#include <drm/amdxdna_accel.h> +#include <linux/semaphore.h> + +#include "amdxdna_mailbox.h" + +#define AIE2_INTERVAL 20000 /* us */ +#define AIE2_TIMEOUT 1000000 /* us */ + +/* Firmware determines device memory base address and size */ +#define AIE2_DEVM_BASE 0x4000000 +#define AIE2_DEVM_SIZE SZ_64M + +#define NDEV2PDEV(ndev) (to_pci_dev((ndev)->xdna->ddev.dev)) + +#define AIE2_SRAM_OFF(ndev, addr) ((addr) - (ndev)->priv->sram_dev_addr) +#define AIE2_MBOX_OFF(ndev, addr) ((addr) - (ndev)->priv->mbox_dev_addr) + +#define PSP_REG_BAR(ndev, idx) ((ndev)->priv->psp_regs_off[(idx)].bar_idx) +#define PSP_REG_OFF(ndev, idx) ((ndev)->priv->psp_regs_off[(idx)].offset) +#define SRAM_REG_OFF(ndev, idx) ((ndev)->priv->sram_offs[(idx)].offset) + +#define SMU_REG(ndev, idx) \ +({ \ + typeof(ndev) _ndev = ndev; \ + ((_ndev)->smu_base + (_ndev)->priv->smu_regs_off[(idx)].offset); \ +}) +#define SRAM_GET_ADDR(ndev, idx) \ +({ \ + typeof(ndev) _ndev = ndev; \ + ((_ndev)->sram_base + SRAM_REG_OFF((_ndev), (idx))); \ +}) + +#define CHAN_SLOT_SZ SZ_8K +#define MBOX_SIZE(ndev) \ +({ \ + typeof(ndev) _ndev = (ndev); \ + ((_ndev)->priv->mbox_size) ? (_ndev)->priv->mbox_size : \ + pci_resource_len(NDEV2PDEV(_ndev), (_ndev)->xdna->dev_info->mbox_bar); \ +}) + +enum aie2_smu_reg_idx { + SMU_CMD_REG = 0, + SMU_ARG_REG, + SMU_INTR_REG, + SMU_RESP_REG, + SMU_OUT_REG, + SMU_MAX_REGS /* Keep this at the end */ +}; + +enum aie2_sram_reg_idx { + MBOX_CHANN_OFF = 0, + FW_ALIVE_OFF, + SRAM_MAX_INDEX /* Keep this at the end */ +}; + +enum psp_reg_idx { + PSP_CMD_REG = 0, + PSP_ARG0_REG, + PSP_ARG1_REG, + PSP_ARG2_REG, + PSP_NUM_IN_REGS, /* number of input registers */ + PSP_INTR_REG = PSP_NUM_IN_REGS, + PSP_STATUS_REG, + PSP_RESP_REG, + PSP_MAX_REGS /* Keep this at the end */ +}; + +struct amdxdna_client; +struct amdxdna_fw_ver; +struct amdxdna_hwctx; +struct amdxdna_sched_job; + +struct psp_config { + const void *fw_buf; + u32 fw_size; + void __iomem *psp_regs[PSP_MAX_REGS]; +}; + +struct aie_version { + u16 major; + u16 minor; +}; + +struct aie_tile_metadata { + u16 row_count; + u16 row_start; + u16 dma_channel_count; + u16 lock_count; + u16 event_reg_count; +}; + +struct aie_metadata { + u32 size; + u16 cols; + u16 rows; + struct aie_version version; + struct aie_tile_metadata core; + struct aie_tile_metadata mem; + struct aie_tile_metadata shim; +}; + +enum rt_config_category { + AIE2_RT_CFG_INIT, + AIE2_RT_CFG_CLK_GATING, +}; + +struct rt_config { + u32 type; + u32 value; + u32 category; +}; + +struct dpm_clk_freq { + u32 npuclk; + u32 hclk; +}; + +/* + * Define the maximum number of pending commands in a hardware context. + * Must be power of 2! + */ +#define HWCTX_MAX_CMDS 4 +#define get_job_idx(seq) ((seq) & (HWCTX_MAX_CMDS - 1)) +struct amdxdna_hwctx_priv { + struct amdxdna_gem_obj *heap; + void *mbox_chann; + + struct drm_gpu_scheduler sched; + struct drm_sched_entity entity; + + struct mutex io_lock; /* protect seq and cmd order */ + struct wait_queue_head job_free_wq; + u32 num_pending; + u64 seq; + struct semaphore job_sem; + bool job_done; + + /* Completed job counter */ + u64 completed; + + struct amdxdna_gem_obj *cmd_buf[HWCTX_MAX_CMDS]; + struct drm_syncobj *syncobj; +}; + +enum aie2_dev_status { + AIE2_DEV_UNINIT, + AIE2_DEV_INIT, + AIE2_DEV_START, +}; + +struct amdxdna_dev_hdl { + struct amdxdna_dev *xdna; + const struct amdxdna_dev_priv *priv; + void __iomem *sram_base; + void __iomem *smu_base; + void __iomem *mbox_base; + struct psp_device *psp_hdl; + + struct xdna_mailbox_chann_res mgmt_x2i; + struct xdna_mailbox_chann_res mgmt_i2x; + u32 mgmt_chan_idx; + u32 mgmt_prot_major; + u32 mgmt_prot_minor; + + u32 total_col; + struct aie_version version; + struct aie_metadata metadata; + + /* power management and clock*/ + enum amdxdna_power_mode_type pw_mode; + u32 dpm_level; + u32 dft_dpm_level; + u32 max_dpm_level; + u32 clk_gating; + u32 npuclk_freq; + u32 hclk_freq; + + /* Mailbox and the management channel */ + struct mailbox *mbox; + struct mailbox_channel *mgmt_chann; + struct async_events *async_events; + + enum aie2_dev_status dev_status; + u32 hwctx_num; +}; + +#define DEFINE_BAR_OFFSET(reg_name, bar, reg_addr) \ + [reg_name] = {bar##_BAR_INDEX, (reg_addr) - bar##_BAR_BASE} + +struct aie2_bar_off_pair { + int bar_idx; + u32 offset; +}; + +struct aie2_hw_ops { + int (*set_dpm)(struct amdxdna_dev_hdl *ndev, u32 dpm_level); +}; + +struct amdxdna_dev_priv { + const char *fw_path; + u64 protocol_major; + u64 protocol_minor; + const struct rt_config *rt_config; + const struct dpm_clk_freq *dpm_clk_tbl; + +#define COL_ALIGN_NONE 0 +#define COL_ALIGN_NATURE 1 + u32 col_align; + u32 mbox_dev_addr; + /* If mbox_size is 0, use BAR size. See MBOX_SIZE macro */ + u32 mbox_size; + u32 sram_dev_addr; + struct aie2_bar_off_pair sram_offs[SRAM_MAX_INDEX]; + struct aie2_bar_off_pair psp_regs_off[PSP_MAX_REGS]; + struct aie2_bar_off_pair smu_regs_off[SMU_MAX_REGS]; + struct aie2_hw_ops hw_ops; +}; + +extern const struct amdxdna_dev_ops aie2_ops; + +int aie2_runtime_cfg(struct amdxdna_dev_hdl *ndev, + enum rt_config_category category, u32 *val); + +/* aie2 npu hw config */ +extern const struct dpm_clk_freq npu1_dpm_clk_table[]; +extern const struct dpm_clk_freq npu4_dpm_clk_table[]; +extern const struct rt_config npu1_default_rt_cfg[]; +extern const struct rt_config npu4_default_rt_cfg[]; + +/* aie2_smu.c */ +int aie2_smu_init(struct amdxdna_dev_hdl *ndev); +void aie2_smu_fini(struct amdxdna_dev_hdl *ndev); +int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level); +int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level); + +/* aie2_pm.c */ +int aie2_pm_init(struct amdxdna_dev_hdl *ndev); +int aie2_pm_set_mode(struct amdxdna_dev_hdl *ndev, enum amdxdna_power_mode_type target); + +/* aie2_psp.c */ +struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *conf); +int aie2_psp_start(struct psp_device *psp); +void aie2_psp_stop(struct psp_device *psp); + +/* aie2_error.c */ +int aie2_error_async_events_alloc(struct amdxdna_dev_hdl *ndev); +void aie2_error_async_events_free(struct amdxdna_dev_hdl *ndev); +int aie2_error_async_events_send(struct amdxdna_dev_hdl *ndev); +int aie2_error_async_msg_thread(void *data); + +/* aie2_message.c */ +int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev); +int aie2_resume_fw(struct amdxdna_dev_hdl *ndev); +int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value); +int aie2_get_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 *value); +int aie2_assign_mgmt_pasid(struct amdxdna_dev_hdl *ndev, u16 pasid); +int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *version); +int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata); +int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, + struct amdxdna_fw_ver *fw_ver); +int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); +int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); +int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size); +int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, u32 size, u32 *cols_filled); +int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size, + void *handle, int (*cb)(void*, void __iomem *, size_t)); +int aie2_config_cu(struct amdxdna_hwctx *hwctx); +int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)); +int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)); +int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)); +int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, void __iomem *, size_t)); + +/* aie2_hwctx.c */ +int aie2_hwctx_init(struct amdxdna_hwctx *hwctx); +void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx); +int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); +void aie2_hwctx_suspend(struct amdxdna_hwctx *hwctx); +void aie2_hwctx_resume(struct amdxdna_hwctx *hwctx); +int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq); +void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo, unsigned long cur_seq); +void aie2_restart_ctx(struct amdxdna_client *client); + +#endif /* _AIE2_PCI_H_ */ diff --git a/drivers/accel/amdxdna/aie2_pm.c b/drivers/accel/amdxdna/aie2_pm.c new file mode 100644 index 000000000000..426c38fce848 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_pm.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +#define AIE2_CLK_GATING_ENABLE 1 +#define AIE2_CLK_GATING_DISABLE 0 + +static int aie2_pm_set_clk_gating(struct amdxdna_dev_hdl *ndev, u32 val) +{ + int ret; + + ret = aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, &val); + if (ret) + return ret; + + ndev->clk_gating = val; + return 0; +} + +int aie2_pm_init(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + if (ndev->dev_status != AIE2_DEV_UNINIT) { + /* Resume device */ + ret = ndev->priv->hw_ops.set_dpm(ndev, ndev->dpm_level); + if (ret) + return ret; + + ret = aie2_pm_set_clk_gating(ndev, ndev->clk_gating); + if (ret) + return ret; + + return 0; + } + + while (ndev->priv->dpm_clk_tbl[ndev->max_dpm_level].hclk) + ndev->max_dpm_level++; + ndev->max_dpm_level--; + + ret = ndev->priv->hw_ops.set_dpm(ndev, ndev->max_dpm_level); + if (ret) + return ret; + + ret = aie2_pm_set_clk_gating(ndev, AIE2_CLK_GATING_ENABLE); + if (ret) + return ret; + + ndev->pw_mode = POWER_MODE_DEFAULT; + ndev->dft_dpm_level = ndev->max_dpm_level; + + return 0; +} + +int aie2_pm_set_mode(struct amdxdna_dev_hdl *ndev, enum amdxdna_power_mode_type target) +{ + struct amdxdna_dev *xdna = ndev->xdna; + u32 clk_gating, dpm_level; + int ret; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + if (ndev->pw_mode == target) + return 0; + + switch (target) { + case POWER_MODE_TURBO: + if (ndev->hwctx_num) { + XDNA_ERR(xdna, "Can not set turbo when there is active hwctx"); + return -EINVAL; + } + + clk_gating = AIE2_CLK_GATING_DISABLE; + dpm_level = ndev->max_dpm_level; + break; + case POWER_MODE_HIGH: + clk_gating = AIE2_CLK_GATING_ENABLE; + dpm_level = ndev->max_dpm_level; + break; + case POWER_MODE_DEFAULT: + clk_gating = AIE2_CLK_GATING_ENABLE; + dpm_level = ndev->dft_dpm_level; + break; + default: + return -EOPNOTSUPP; + } + + ret = ndev->priv->hw_ops.set_dpm(ndev, dpm_level); + if (ret) + return ret; + + ret = aie2_pm_set_clk_gating(ndev, clk_gating); + if (ret) + return ret; + + ndev->pw_mode = target; + + return 0; +} diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c new file mode 100644 index 000000000000..f28a060a8810 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_psp.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/drm_device.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_managed.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/bitfield.h> +#include <linux/iopoll.h> + +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +#define PSP_STATUS_READY BIT(31) + +/* PSP commands */ +#define PSP_VALIDATE 1 +#define PSP_START 2 +#define PSP_RELEASE_TMR 3 + +/* PSP special arguments */ +#define PSP_START_COPY_FW 1 + +/* PSP response error code */ +#define PSP_ERROR_CANCEL 0xFFFF0002 +#define PSP_ERROR_BAD_STATE 0xFFFF0007 + +#define PSP_FW_ALIGN 0x10000 +#define PSP_POLL_INTERVAL 20000 /* us */ +#define PSP_POLL_TIMEOUT 1000000 /* us */ + +#define PSP_REG(p, reg) ((p)->psp_regs[reg]) + +struct psp_device { + struct drm_device *ddev; + struct psp_config conf; + u32 fw_buf_sz; + u64 fw_paddr; + void *fw_buffer; + void __iomem *psp_regs[PSP_MAX_REGS]; +}; + +static int psp_exec(struct psp_device *psp, u32 *reg_vals) +{ + u32 resp_code; + int ret, i; + u32 ready; + + /* Write command and argument registers */ + for (i = 0; i < PSP_NUM_IN_REGS; i++) + writel(reg_vals[i], PSP_REG(psp, i)); + + /* clear and set PSP INTR register to kick off */ + writel(0, PSP_REG(psp, PSP_INTR_REG)); + writel(1, PSP_REG(psp, PSP_INTR_REG)); + + /* PSP should be busy. Wait for ready, so we know task is done. */ + ret = readx_poll_timeout(readl, PSP_REG(psp, PSP_STATUS_REG), ready, + FIELD_GET(PSP_STATUS_READY, ready), + PSP_POLL_INTERVAL, PSP_POLL_TIMEOUT); + if (ret) { + drm_err(psp->ddev, "PSP is not ready, ret 0x%x", ret); + return ret; + } + + resp_code = readl(PSP_REG(psp, PSP_RESP_REG)); + if (resp_code) { + drm_err(psp->ddev, "fw return error 0x%x", resp_code); + return -EIO; + } + + return 0; +} + +void aie2_psp_stop(struct psp_device *psp) +{ + u32 reg_vals[PSP_NUM_IN_REGS] = { PSP_RELEASE_TMR, }; + int ret; + + ret = psp_exec(psp, reg_vals); + if (ret) + drm_err(psp->ddev, "release tmr failed, ret %d", ret); +} + +int aie2_psp_start(struct psp_device *psp) +{ + u32 reg_vals[PSP_NUM_IN_REGS]; + int ret; + + reg_vals[0] = PSP_VALIDATE; + reg_vals[1] = lower_32_bits(psp->fw_paddr); + reg_vals[2] = upper_32_bits(psp->fw_paddr); + reg_vals[3] = psp->fw_buf_sz; + + ret = psp_exec(psp, reg_vals); + if (ret) { + drm_err(psp->ddev, "failed to validate fw, ret %d", ret); + return ret; + } + + memset(reg_vals, 0, sizeof(reg_vals)); + reg_vals[0] = PSP_START; + reg_vals[1] = PSP_START_COPY_FW; + ret = psp_exec(psp, reg_vals); + if (ret) { + drm_err(psp->ddev, "failed to start fw, ret %d", ret); + return ret; + } + + return 0; +} + +struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *conf) +{ + struct psp_device *psp; + u64 offset; + + psp = drmm_kzalloc(ddev, sizeof(*psp), GFP_KERNEL); + if (!psp) + return NULL; + + psp->ddev = ddev; + memcpy(psp->psp_regs, conf->psp_regs, sizeof(psp->psp_regs)); + + psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN); + psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz + PSP_FW_ALIGN, GFP_KERNEL); + if (!psp->fw_buffer) { + drm_err(ddev, "no memory for fw buffer"); + return NULL; + } + + /* + * AMD Platform Security Processor(PSP) requires host physical + * address to load NPU firmware. + */ + psp->fw_paddr = virt_to_phys(psp->fw_buffer); + offset = ALIGN(psp->fw_paddr, PSP_FW_ALIGN) - psp->fw_paddr; + psp->fw_paddr += offset; + memcpy(psp->fw_buffer + offset, conf->fw_buf, conf->fw_size); + + return psp; +} diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/amdxdna/aie2_smu.c new file mode 100644 index 000000000000..d303701b0ded --- /dev/null +++ b/drivers/accel/amdxdna/aie2_smu.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/drm_device.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/iopoll.h> + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +#define SMU_RESULT_OK 1 + +/* SMU commands */ +#define AIE2_SMU_POWER_ON 0x3 +#define AIE2_SMU_POWER_OFF 0x4 +#define AIE2_SMU_SET_MPNPUCLK_FREQ 0x5 +#define AIE2_SMU_SET_HCLK_FREQ 0x6 +#define AIE2_SMU_SET_SOFT_DPMLEVEL 0x7 +#define AIE2_SMU_SET_HARD_DPMLEVEL 0x8 + +static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd, + u32 reg_arg, u32 *out) +{ + u32 resp; + int ret; + + writel(0, SMU_REG(ndev, SMU_RESP_REG)); + writel(reg_arg, SMU_REG(ndev, SMU_ARG_REG)); + writel(reg_cmd, SMU_REG(ndev, SMU_CMD_REG)); + + /* Clear and set SMU_INTR_REG to kick off */ + writel(0, SMU_REG(ndev, SMU_INTR_REG)); + writel(1, SMU_REG(ndev, SMU_INTR_REG)); + + ret = readx_poll_timeout(readl, SMU_REG(ndev, SMU_RESP_REG), resp, + resp, AIE2_INTERVAL, AIE2_TIMEOUT); + if (ret) { + XDNA_ERR(ndev->xdna, "smu cmd %d timed out", reg_cmd); + return ret; + } + + if (out) + *out = readl(SMU_REG(ndev, SMU_OUT_REG)); + + if (resp != SMU_RESULT_OK) { + XDNA_ERR(ndev->xdna, "smu cmd %d failed, 0x%x", reg_cmd, resp); + return -EINVAL; + } + + return 0; +} + +int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) +{ + u32 freq; + int ret; + + ret = aie2_smu_exec(ndev, AIE2_SMU_SET_MPNPUCLK_FREQ, + ndev->priv->dpm_clk_tbl[dpm_level].npuclk, &freq); + if (ret) { + XDNA_ERR(ndev->xdna, "Set npu clock to %d failed, ret %d\n", + ndev->priv->dpm_clk_tbl[dpm_level].npuclk, ret); + return ret; + } + ndev->npuclk_freq = freq; + + ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HCLK_FREQ, + ndev->priv->dpm_clk_tbl[dpm_level].hclk, &freq); + if (ret) { + XDNA_ERR(ndev->xdna, "Set h clock to %d failed, ret %d\n", + ndev->priv->dpm_clk_tbl[dpm_level].hclk, ret); + return ret; + } + ndev->hclk_freq = freq; + ndev->dpm_level = dpm_level; + + XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n", + ndev->npuclk_freq, ndev->hclk_freq); + + return 0; +} + +int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) +{ + int ret; + + ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HARD_DPMLEVEL, dpm_level, NULL); + if (ret) { + XDNA_ERR(ndev->xdna, "Set hard dpm level %d failed, ret %d ", + dpm_level, ret); + return ret; + } + + ret = aie2_smu_exec(ndev, AIE2_SMU_SET_SOFT_DPMLEVEL, dpm_level, NULL); + if (ret) { + XDNA_ERR(ndev->xdna, "Set soft dpm level %d failed, ret %d", + dpm_level, ret); + return ret; + } + + ndev->npuclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].npuclk; + ndev->hclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].hclk; + ndev->dpm_level = dpm_level; + + XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n", + ndev->npuclk_freq, ndev->hclk_freq); + + return 0; +} + +int aie2_smu_init(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_ON, 0, NULL); + if (ret) { + XDNA_ERR(ndev->xdna, "Power on failed, ret %d", ret); + return ret; + } + + return 0; +} + +void aie2_smu_fini(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ndev->priv->hw_ops.set_dpm(ndev, 0); + ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_OFF, 0, NULL); + if (ret) + XDNA_ERR(ndev->xdna, "Power off failed, ret %d", ret); +} diff --git a/drivers/accel/amdxdna/aie2_solver.c b/drivers/accel/amdxdna/aie2_solver.c new file mode 100644 index 000000000000..2013d1f13aae --- /dev/null +++ b/drivers/accel/amdxdna/aie2_solver.c @@ -0,0 +1,380 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/drm_device.h> +#include <drm/drm_managed.h> +#include <drm/drm_print.h> +#include <linux/bitops.h> +#include <linux/bitmap.h> +#include <linux/slab.h> + +#include "aie2_solver.h" + +struct partition_node { + struct list_head list; + u32 nshared; /* # shared requests */ + u32 start_col; /* start column */ + u32 ncols; /* # columns */ + bool exclusive; /* can not be shared if set */ +}; + +struct solver_node { + struct list_head list; + u64 rid; /* Request ID from consumer */ + + struct partition_node *pt_node; + void *cb_arg; + u32 dpm_level; + u32 cols_len; + u32 start_cols[] __counted_by(cols_len); +}; + +struct solver_rgroup { + u32 rgid; + u32 nnode; + u32 npartition_node; + + DECLARE_BITMAP(resbit, XRS_MAX_COL); + struct list_head node_list; + struct list_head pt_node_list; +}; + +struct solver_state { + struct solver_rgroup rgp; + struct init_config cfg; + struct xrs_action_ops *actions; +}; + +static u32 calculate_gops(struct aie_qos *rqos) +{ + u32 service_rate = 0; + + if (rqos->latency) + service_rate = (1000 / rqos->latency); + + if (rqos->fps > service_rate) + return rqos->fps * rqos->gops; + + return service_rate * rqos->gops; +} + +/* + * qos_meet() - Check the QOS request can be met. + */ +static int qos_meet(struct solver_state *xrs, struct aie_qos *rqos, u32 cgops) +{ + u32 request_gops = calculate_gops(rqos) * xrs->cfg.sys_eff_factor; + + if (request_gops <= cgops) + return 0; + + return -EINVAL; +} + +/* + * sanity_check() - Do a basic sanity check on allocation request. + */ +static int sanity_check(struct solver_state *xrs, struct alloc_requests *req) +{ + struct cdo_parts *cdop = &req->cdo; + struct aie_qos *rqos = &req->rqos; + u32 cu_clk_freq; + + if (cdop->ncols > xrs->cfg.total_col) + return -EINVAL; + + /* + * We can find at least one CDOs groups that meet the + * GOPs requirement. + */ + cu_clk_freq = xrs->cfg.clk_list.cu_clk_list[xrs->cfg.clk_list.num_levels - 1]; + + if (qos_meet(xrs, rqos, cdop->qos_cap.opc * cu_clk_freq / 1000)) + return -EINVAL; + + return 0; +} + +static bool is_valid_qos_dpm_params(struct aie_qos *rqos) +{ + /* + * gops is retrieved from the xmodel, so it's always set + * fps and latency are the configurable params from the application + */ + if (rqos->gops > 0 && (rqos->fps > 0 || rqos->latency > 0)) + return true; + + return false; +} + +static int set_dpm_level(struct solver_state *xrs, struct alloc_requests *req, u32 *dpm_level) +{ + struct solver_rgroup *rgp = &xrs->rgp; + struct cdo_parts *cdop = &req->cdo; + struct aie_qos *rqos = &req->rqos; + u32 freq, max_dpm_level, level; + struct solver_node *node; + + max_dpm_level = xrs->cfg.clk_list.num_levels - 1; + /* If no QoS parameters are passed, set it to the max DPM level */ + if (!is_valid_qos_dpm_params(rqos)) { + level = max_dpm_level; + goto set_dpm; + } + + /* Find one CDO group that meet the GOPs requirement. */ + for (level = 0; level < max_dpm_level; level++) { + freq = xrs->cfg.clk_list.cu_clk_list[level]; + if (!qos_meet(xrs, rqos, cdop->qos_cap.opc * freq / 1000)) + break; + } + + /* set the dpm level which fits all the sessions */ + list_for_each_entry(node, &rgp->node_list, list) { + if (node->dpm_level > level) + level = node->dpm_level; + } + +set_dpm: + *dpm_level = level; + return xrs->cfg.actions->set_dft_dpm_level(xrs->cfg.ddev, level); +} + +static struct solver_node *rg_search_node(struct solver_rgroup *rgp, u64 rid) +{ + struct solver_node *node; + + list_for_each_entry(node, &rgp->node_list, list) { + if (node->rid == rid) + return node; + } + + return NULL; +} + +static void remove_partition_node(struct solver_rgroup *rgp, + struct partition_node *pt_node) +{ + pt_node->nshared--; + if (pt_node->nshared > 0) + return; + + list_del(&pt_node->list); + rgp->npartition_node--; + + bitmap_clear(rgp->resbit, pt_node->start_col, pt_node->ncols); + kfree(pt_node); +} + +static void remove_solver_node(struct solver_rgroup *rgp, + struct solver_node *node) +{ + list_del(&node->list); + rgp->nnode--; + + if (node->pt_node) + remove_partition_node(rgp, node->pt_node); + + kfree(node); +} + +static int get_free_partition(struct solver_state *xrs, + struct solver_node *snode, + struct alloc_requests *req) +{ + struct partition_node *pt_node; + u32 ncols = req->cdo.ncols; + u32 col, i; + + for (i = 0; i < snode->cols_len; i++) { + col = snode->start_cols[i]; + if (find_next_bit(xrs->rgp.resbit, XRS_MAX_COL, col) >= col + ncols) + break; + } + + if (i == snode->cols_len) + return -ENODEV; + + pt_node = kzalloc(sizeof(*pt_node), GFP_KERNEL); + if (!pt_node) + return -ENOMEM; + + pt_node->nshared = 1; + pt_node->start_col = col; + pt_node->ncols = ncols; + + /* + * Always set exclusive to false for now. + */ + pt_node->exclusive = false; + + list_add_tail(&pt_node->list, &xrs->rgp.pt_node_list); + xrs->rgp.npartition_node++; + bitmap_set(xrs->rgp.resbit, pt_node->start_col, pt_node->ncols); + + snode->pt_node = pt_node; + + return 0; +} + +static int allocate_partition(struct solver_state *xrs, + struct solver_node *snode, + struct alloc_requests *req) +{ + struct partition_node *pt_node, *rpt_node = NULL; + int idx, ret; + + ret = get_free_partition(xrs, snode, req); + if (!ret) + return ret; + + /* try to get a share-able partition */ + list_for_each_entry(pt_node, &xrs->rgp.pt_node_list, list) { + if (pt_node->exclusive) + continue; + + if (rpt_node && pt_node->nshared >= rpt_node->nshared) + continue; + + for (idx = 0; idx < snode->cols_len; idx++) { + if (snode->start_cols[idx] != pt_node->start_col) + continue; + + if (req->cdo.ncols != pt_node->ncols) + continue; + + rpt_node = pt_node; + break; + } + } + + if (!rpt_node) + return -ENODEV; + + rpt_node->nshared++; + snode->pt_node = rpt_node; + + return 0; +} + +static struct solver_node *create_solver_node(struct solver_state *xrs, + struct alloc_requests *req) +{ + struct cdo_parts *cdop = &req->cdo; + struct solver_node *node; + int ret; + + node = kzalloc(struct_size(node, start_cols, cdop->cols_len), GFP_KERNEL); + if (!node) + return ERR_PTR(-ENOMEM); + + node->rid = req->rid; + node->cols_len = cdop->cols_len; + memcpy(node->start_cols, cdop->start_cols, cdop->cols_len * sizeof(u32)); + + ret = allocate_partition(xrs, node, req); + if (ret) + goto free_node; + + list_add_tail(&node->list, &xrs->rgp.node_list); + xrs->rgp.nnode++; + return node; + +free_node: + kfree(node); + return ERR_PTR(ret); +} + +static void fill_load_action(struct solver_state *xrs, + struct solver_node *snode, + struct xrs_action_load *action) +{ + action->rid = snode->rid; + action->part.start_col = snode->pt_node->start_col; + action->part.ncols = snode->pt_node->ncols; +} + +int xrs_allocate_resource(void *hdl, struct alloc_requests *req, void *cb_arg) +{ + struct xrs_action_load load_act; + struct solver_node *snode; + struct solver_state *xrs; + u32 dpm_level; + int ret; + + xrs = (struct solver_state *)hdl; + + ret = sanity_check(xrs, req); + if (ret) { + drm_err(xrs->cfg.ddev, "invalid request"); + return ret; + } + + if (rg_search_node(&xrs->rgp, req->rid)) { + drm_err(xrs->cfg.ddev, "rid %lld is in-use", req->rid); + return -EEXIST; + } + + snode = create_solver_node(xrs, req); + if (IS_ERR(snode)) + return PTR_ERR(snode); + + fill_load_action(xrs, snode, &load_act); + ret = xrs->cfg.actions->load(cb_arg, &load_act); + if (ret) + goto free_node; + + ret = set_dpm_level(xrs, req, &dpm_level); + if (ret) + goto free_node; + + snode->dpm_level = dpm_level; + snode->cb_arg = cb_arg; + + drm_dbg(xrs->cfg.ddev, "start col %d ncols %d\n", + snode->pt_node->start_col, snode->pt_node->ncols); + + return 0; + +free_node: + remove_solver_node(&xrs->rgp, snode); + + return ret; +} + +int xrs_release_resource(void *hdl, u64 rid) +{ + struct solver_state *xrs = hdl; + struct solver_node *node; + + node = rg_search_node(&xrs->rgp, rid); + if (!node) { + drm_err(xrs->cfg.ddev, "node not exist"); + return -ENODEV; + } + + xrs->cfg.actions->unload(node->cb_arg); + remove_solver_node(&xrs->rgp, node); + + return 0; +} + +void *xrsm_init(struct init_config *cfg) +{ + struct solver_rgroup *rgp; + struct solver_state *xrs; + + xrs = drmm_kzalloc(cfg->ddev, sizeof(*xrs), GFP_KERNEL); + if (!xrs) + return NULL; + + memcpy(&xrs->cfg, cfg, sizeof(*cfg)); + + rgp = &xrs->rgp; + INIT_LIST_HEAD(&rgp->node_list); + INIT_LIST_HEAD(&rgp->pt_node_list); + + return xrs; +} diff --git a/drivers/accel/amdxdna/aie2_solver.h b/drivers/accel/amdxdna/aie2_solver.h new file mode 100644 index 000000000000..a2e3c52229e9 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_solver.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_SOLVER_H +#define _AIE2_SOLVER_H + +#define XRS_MAX_COL 128 + +/* + * Structure used to describe a partition. A partition is column based + * allocation unit described by its start column and number of columns. + */ +struct aie_part { + u32 start_col; + u32 ncols; +}; + +/* + * The QoS capabilities of a given AIE partition. + */ +struct aie_qos_cap { + u32 opc; /* operations per cycle */ + u32 dma_bw; /* DMA bandwidth */ +}; + +/* + * QoS requirement of a resource allocation. + */ +struct aie_qos { + u32 gops; /* Giga operations */ + u32 fps; /* Frames per second */ + u32 dma_bw; /* DMA bandwidth */ + u32 latency; /* Frame response latency */ + u32 exec_time; /* Frame execution time */ + u32 priority; /* Request priority */ +}; + +/* + * Structure used to describe a relocatable CDO (Configuration Data Object). + */ +struct cdo_parts { + u32 *start_cols; /* Start column array */ + u32 cols_len; /* Length of start column array */ + u32 ncols; /* # of column */ + struct aie_qos_cap qos_cap; /* CDO QoS capabilities */ +}; + +/* + * Structure used to describe a request to allocate. + */ +struct alloc_requests { + u64 rid; + struct cdo_parts cdo; + struct aie_qos rqos; /* Requested QoS */ +}; + +/* + * Load callback argument + */ +struct xrs_action_load { + u32 rid; + struct aie_part part; +}; + +/* + * Define the power level available + * + * POWER_LEVEL_MIN: + * Lowest power level. Usually set when all actions are unloaded. + * + * POWER_LEVEL_n + * Power levels 0 - n, is a step increase in system frequencies + */ +enum power_level { + POWER_LEVEL_MIN = 0x0, + POWER_LEVEL_0 = 0x1, + POWER_LEVEL_1 = 0x2, + POWER_LEVEL_2 = 0x3, + POWER_LEVEL_3 = 0x4, + POWER_LEVEL_4 = 0x5, + POWER_LEVEL_5 = 0x6, + POWER_LEVEL_6 = 0x7, + POWER_LEVEL_7 = 0x8, + POWER_LEVEL_NUM, +}; + +/* + * Structure used to describe the frequency table. + * Resource solver chooses the frequency from the table + * to meet the QOS requirements. + */ +struct clk_list_info { + u32 num_levels; /* available power levels */ + u32 cu_clk_list[POWER_LEVEL_NUM]; /* available aie clock frequencies in Mhz*/ +}; + +struct xrs_action_ops { + int (*load)(void *cb_arg, struct xrs_action_load *action); + int (*unload)(void *cb_arg); + int (*set_dft_dpm_level)(struct drm_device *ddev, u32 level); +}; + +/* + * Structure used to describe information for solver during initialization. + */ +struct init_config { + u32 total_col; + u32 sys_eff_factor; /* system efficiency factor */ + u32 latency_adj; /* latency adjustment in ms */ + struct clk_list_info clk_list; /* List of frequencies available in system */ + struct drm_device *ddev; + struct xrs_action_ops *actions; +}; + +/* + * xrsm_init() - Register resource solver. Resource solver client needs + * to call this function to register itself. + * + * @cfg: The system metrics for resource solver to use + * + * Return: A resource solver handle + * + * Note: We should only create one handle per AIE array to be managed. + */ +void *xrsm_init(struct init_config *cfg); + +/* + * xrs_allocate_resource() - Request to allocate resources for a given context + * and a partition metadata. (See struct part_meta) + * + * @hdl: Resource solver handle obtained from xrs_init() + * @req: Input to the Resource solver including request id + * and partition metadata. + * @cb_arg: callback argument pointer + * + * Return: 0 when successful. + * Or standard error number when failing + * + * Note: + * There is no lock mechanism inside resource solver. So it is + * the caller's responsibility to lock down XCLBINs and grab + * necessary lock. + */ +int xrs_allocate_resource(void *hdl, struct alloc_requests *req, void *cb_arg); + +/* + * xrs_release_resource() - Request to free resources for a given context. + * + * @hdl: Resource solver handle obtained from xrs_init() + * @rid: The Request ID to identify the requesting context + */ +int xrs_release_resource(void *hdl, u64 rid); +#endif /* _AIE2_SOLVER_H */ diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c new file mode 100644 index 000000000000..43442b9e273b --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -0,0 +1,552 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/drm_drv.h> +#include <drm/drm_file.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/xarray.h> +#include <trace/events/amdxdna.h> + +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_pci_drv.h" + +#define MAX_HWCTX_ID 255 +#define MAX_ARG_COUNT 4095 + +struct amdxdna_fence { + struct dma_fence base; + spinlock_t lock; /* for base */ + struct amdxdna_hwctx *hwctx; +}; + +static const char *amdxdna_fence_get_driver_name(struct dma_fence *fence) +{ + return KBUILD_MODNAME; +} + +static const char *amdxdna_fence_get_timeline_name(struct dma_fence *fence) +{ + struct amdxdna_fence *xdna_fence; + + xdna_fence = container_of(fence, struct amdxdna_fence, base); + + return xdna_fence->hwctx->name; +} + +static const struct dma_fence_ops fence_ops = { + .get_driver_name = amdxdna_fence_get_driver_name, + .get_timeline_name = amdxdna_fence_get_timeline_name, +}; + +static struct dma_fence *amdxdna_fence_create(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_fence *fence; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) + return NULL; + + fence->hwctx = hwctx; + spin_lock_init(&fence->lock); + dma_fence_init(&fence->base, &fence_ops, &fence->lock, hwctx->id, 0); + return &fence->base; +} + +void amdxdna_hwctx_suspend(struct amdxdna_client *client) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + mutex_lock(&client->hwctx_lock); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) + xdna->dev_info->ops->hwctx_suspend(hwctx); + mutex_unlock(&client->hwctx_lock); +} + +void amdxdna_hwctx_resume(struct amdxdna_client *client) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + mutex_lock(&client->hwctx_lock); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) + xdna->dev_info->ops->hwctx_resume(hwctx); + mutex_unlock(&client->hwctx_lock); +} + +static void amdxdna_hwctx_destroy_rcu(struct amdxdna_hwctx *hwctx, + struct srcu_struct *ss) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + + synchronize_srcu(ss); + + /* At this point, user is not able to submit new commands */ + mutex_lock(&xdna->dev_lock); + xdna->dev_info->ops->hwctx_fini(hwctx); + mutex_unlock(&xdna->dev_lock); + + kfree(hwctx->name); + kfree(hwctx); +} + +void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + u32 num_masks, count; + + if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN) + num_masks = 0; + else + num_masks = 1 + FIELD_GET(AMDXDNA_CMD_EXTRA_CU_MASK, cmd->header); + + if (size) { + count = FIELD_GET(AMDXDNA_CMD_COUNT, cmd->header); + if (unlikely(count <= num_masks)) { + *size = 0; + return NULL; + } + *size = (count - num_masks) * sizeof(u32); + } + return &cmd->data[num_masks]; +} + +int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + u32 num_masks, i; + u32 *cu_mask; + + if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN) + return -1; + + num_masks = 1 + FIELD_GET(AMDXDNA_CMD_EXTRA_CU_MASK, cmd->header); + cu_mask = cmd->data; + for (i = 0; i < num_masks; i++) { + if (cu_mask[i]) + return ffs(cu_mask[i]) - 1; + } + + return -1; +} + +/* + * This should be called in close() and remove(). DO NOT call in other syscalls. + * This guarantee that when hwctx and resources will be released, if user + * doesn't call amdxdna_drm_destroy_hwctx_ioctl. + */ +void amdxdna_hwctx_remove_all(struct amdxdna_client *client) +{ + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + + mutex_lock(&client->hwctx_lock); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) { + XDNA_DBG(client->xdna, "PID %d close HW context %d", + client->pid, hwctx->id); + xa_erase(&client->hwctx_xa, hwctx->id); + mutex_unlock(&client->hwctx_lock); + amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu); + mutex_lock(&client->hwctx_lock); + } + mutex_unlock(&client->hwctx_lock); +} + +int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_create_hwctx *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_hwctx *hwctx; + int ret, idx; + + if (args->ext || args->ext_flags) + return -EINVAL; + + if (!drm_dev_enter(dev, &idx)) + return -ENODEV; + + hwctx = kzalloc(sizeof(*hwctx), GFP_KERNEL); + if (!hwctx) { + ret = -ENOMEM; + goto exit; + } + + if (copy_from_user(&hwctx->qos, u64_to_user_ptr(args->qos_p), sizeof(hwctx->qos))) { + XDNA_ERR(xdna, "Access QoS info failed"); + ret = -EFAULT; + goto free_hwctx; + } + + hwctx->client = client; + hwctx->fw_ctx_id = -1; + hwctx->num_tiles = args->num_tiles; + hwctx->mem_size = args->mem_size; + hwctx->max_opc = args->max_opc; + ret = xa_alloc_cyclic(&client->hwctx_xa, &hwctx->id, hwctx, + XA_LIMIT(AMDXDNA_INVALID_CTX_HANDLE + 1, MAX_HWCTX_ID), + &client->next_hwctxid, GFP_KERNEL); + if (ret < 0) { + XDNA_ERR(xdna, "Allocate hwctx ID failed, ret %d", ret); + goto free_hwctx; + } + + hwctx->name = kasprintf(GFP_KERNEL, "hwctx.%d.%d", client->pid, hwctx->id); + if (!hwctx->name) { + ret = -ENOMEM; + goto rm_id; + } + + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->hwctx_init(hwctx); + if (ret) { + mutex_unlock(&xdna->dev_lock); + XDNA_ERR(xdna, "Init hwctx failed, ret %d", ret); + goto free_name; + } + args->handle = hwctx->id; + args->syncobj_handle = hwctx->syncobj_hdl; + mutex_unlock(&xdna->dev_lock); + + atomic64_set(&hwctx->job_submit_cnt, 0); + atomic64_set(&hwctx->job_free_cnt, 0); + XDNA_DBG(xdna, "PID %d create HW context %d, ret %d", client->pid, args->handle, ret); + drm_dev_exit(idx); + return 0; + +free_name: + kfree(hwctx->name); +rm_id: + xa_erase(&client->hwctx_xa, hwctx->id); +free_hwctx: + kfree(hwctx); +exit: + drm_dev_exit(idx); + return ret; +} + +int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_destroy_hwctx *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_hwctx *hwctx; + int ret = 0, idx; + + if (XDNA_MBZ_DBG(xdna, &args->pad, sizeof(args->pad))) + return -EINVAL; + + if (!drm_dev_enter(dev, &idx)) + return -ENODEV; + + hwctx = xa_erase(&client->hwctx_xa, args->handle); + if (!hwctx) { + ret = -EINVAL; + XDNA_DBG(xdna, "PID %d HW context %d not exist", + client->pid, args->handle); + goto out; + } + + /* + * The pushed jobs are handled by DRM scheduler during destroy. + * SRCU to synchronize with exec command ioctls. + */ + amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu); + + XDNA_DBG(xdna, "PID %d destroyed HW context %d", client->pid, args->handle); +out: + drm_dev_exit(idx); + return ret; +} + +int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_config_hwctx *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_hwctx *hwctx; + int ret, idx; + u32 buf_size; + void *buf; + u64 val; + + if (XDNA_MBZ_DBG(xdna, &args->pad, sizeof(args->pad))) + return -EINVAL; + + if (!xdna->dev_info->ops->hwctx_config) + return -EOPNOTSUPP; + + val = args->param_val; + buf_size = args->param_val_size; + + switch (args->param_type) { + case DRM_AMDXDNA_HWCTX_CONFIG_CU: + /* For those types that param_val is pointer */ + if (buf_size > PAGE_SIZE) { + XDNA_ERR(xdna, "Config CU param buffer too large"); + return -E2BIG; + } + + /* Hwctx needs to keep buf */ + buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, u64_to_user_ptr(val), buf_size)) { + kfree(buf); + return -EFAULT; + } + + break; + case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF: + case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF: + /* For those types that param_val is a value */ + buf = NULL; + buf_size = 0; + break; + default: + XDNA_DBG(xdna, "Unknown HW context config type %d", args->param_type); + return -EINVAL; + } + + mutex_lock(&xdna->dev_lock); + idx = srcu_read_lock(&client->hwctx_srcu); + hwctx = xa_load(&client->hwctx_xa, args->handle); + if (!hwctx) { + XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle); + ret = -EINVAL; + goto unlock_srcu; + } + + ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size); + +unlock_srcu: + srcu_read_unlock(&client->hwctx_srcu, idx); + mutex_unlock(&xdna->dev_lock); + kfree(buf); + return ret; +} + +static void +amdxdna_arg_bos_put(struct amdxdna_sched_job *job) +{ + int i; + + for (i = 0; i < job->bo_cnt; i++) { + if (!job->bos[i]) + break; + drm_gem_object_put(job->bos[i]); + } +} + +static int +amdxdna_arg_bos_lookup(struct amdxdna_client *client, + struct amdxdna_sched_job *job, + u32 *bo_hdls, u32 bo_cnt) +{ + struct drm_gem_object *gobj; + int i, ret; + + job->bo_cnt = bo_cnt; + for (i = 0; i < job->bo_cnt; i++) { + struct amdxdna_gem_obj *abo; + + gobj = drm_gem_object_lookup(client->filp, bo_hdls[i]); + if (!gobj) { + ret = -ENOENT; + goto put_shmem_bo; + } + abo = to_xdna_obj(gobj); + + mutex_lock(&abo->lock); + if (abo->pinned) { + mutex_unlock(&abo->lock); + job->bos[i] = gobj; + continue; + } + + ret = amdxdna_gem_pin_nolock(abo); + if (ret) { + mutex_unlock(&abo->lock); + drm_gem_object_put(gobj); + goto put_shmem_bo; + } + abo->pinned = true; + mutex_unlock(&abo->lock); + + job->bos[i] = gobj; + } + + return 0; + +put_shmem_bo: + amdxdna_arg_bos_put(job); + return ret; +} + +void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job) +{ + trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release"); + amdxdna_arg_bos_put(job); + amdxdna_gem_put_obj(job->cmd_bo); +} + +int amdxdna_cmd_submit(struct amdxdna_client *client, + u32 cmd_bo_hdl, u32 *arg_bo_hdls, u32 arg_bo_cnt, + u32 hwctx_hdl, u64 *seq) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_sched_job *job; + struct amdxdna_hwctx *hwctx; + int ret, idx; + + XDNA_DBG(xdna, "Command BO hdl %d, Arg BO count %d", cmd_bo_hdl, arg_bo_cnt); + job = kzalloc(struct_size(job, bos, arg_bo_cnt), GFP_KERNEL); + if (!job) + return -ENOMEM; + + if (cmd_bo_hdl != AMDXDNA_INVALID_BO_HANDLE) { + job->cmd_bo = amdxdna_gem_get_obj(client, cmd_bo_hdl, AMDXDNA_BO_CMD); + if (!job->cmd_bo) { + XDNA_ERR(xdna, "Failed to get cmd bo from %d", cmd_bo_hdl); + ret = -EINVAL; + goto free_job; + } + } else { + job->cmd_bo = NULL; + } + + ret = amdxdna_arg_bos_lookup(client, job, arg_bo_hdls, arg_bo_cnt); + if (ret) { + XDNA_ERR(xdna, "Argument BOs lookup failed, ret %d", ret); + goto cmd_put; + } + + idx = srcu_read_lock(&client->hwctx_srcu); + hwctx = xa_load(&client->hwctx_xa, hwctx_hdl); + if (!hwctx) { + XDNA_DBG(xdna, "PID %d failed to get hwctx %d", + client->pid, hwctx_hdl); + ret = -EINVAL; + goto unlock_srcu; + } + + if (hwctx->status != HWCTX_STAT_READY) { + XDNA_ERR(xdna, "HW Context is not ready"); + ret = -EINVAL; + goto unlock_srcu; + } + + job->hwctx = hwctx; + job->mm = current->mm; + + job->fence = amdxdna_fence_create(hwctx); + if (!job->fence) { + XDNA_ERR(xdna, "Failed to create fence"); + ret = -ENOMEM; + goto unlock_srcu; + } + kref_init(&job->refcnt); + + ret = xdna->dev_info->ops->cmd_submit(hwctx, job, seq); + if (ret) + goto put_fence; + + /* + * The amdxdna_hwctx_destroy_rcu() will release hwctx and associated + * resource after synchronize_srcu(). The submitted jobs should be + * handled by the queue, for example DRM scheduler, in device layer. + * For here we can unlock SRCU. + */ + srcu_read_unlock(&client->hwctx_srcu, idx); + trace_amdxdna_debug_point(hwctx->name, *seq, "job pushed"); + + return 0; + +put_fence: + dma_fence_put(job->fence); +unlock_srcu: + srcu_read_unlock(&client->hwctx_srcu, idx); + amdxdna_arg_bos_put(job); +cmd_put: + amdxdna_gem_put_obj(job->cmd_bo); +free_job: + kfree(job); + return ret; +} + +/* + * The submit command ioctl submits a command to firmware. One firmware command + * may contain multiple command BOs for processing as a whole. + * The command sequence number is returned which can be used for wait command ioctl. + */ +static int amdxdna_drm_submit_execbuf(struct amdxdna_client *client, + struct amdxdna_drm_exec_cmd *args) +{ + struct amdxdna_dev *xdna = client->xdna; + u32 *arg_bo_hdls; + u32 cmd_bo_hdl; + int ret; + + if (!args->arg_count || args->arg_count > MAX_ARG_COUNT) { + XDNA_ERR(xdna, "Invalid arg bo count %d", args->arg_count); + return -EINVAL; + } + + /* Only support single command for now. */ + if (args->cmd_count != 1) { + XDNA_ERR(xdna, "Invalid cmd bo count %d", args->cmd_count); + return -EINVAL; + } + + cmd_bo_hdl = (u32)args->cmd_handles; + arg_bo_hdls = kcalloc(args->arg_count, sizeof(u32), GFP_KERNEL); + if (!arg_bo_hdls) + return -ENOMEM; + ret = copy_from_user(arg_bo_hdls, u64_to_user_ptr(args->args), + args->arg_count * sizeof(u32)); + if (ret) { + ret = -EFAULT; + goto free_cmd_bo_hdls; + } + + ret = amdxdna_cmd_submit(client, cmd_bo_hdl, arg_bo_hdls, + args->arg_count, args->hwctx, &args->seq); + if (ret) + XDNA_DBG(xdna, "Submit cmds failed, ret %d", ret); + +free_cmd_bo_hdls: + kfree(arg_bo_hdls); + if (!ret) + XDNA_DBG(xdna, "Pushed cmd %lld to scheduler", args->seq); + return ret; +} + +int amdxdna_drm_submit_cmd_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_exec_cmd *args = data; + + if (args->ext || args->ext_flags) + return -EINVAL; + + switch (args->type) { + case AMDXDNA_CMD_SUBMIT_EXEC_BUF: + return amdxdna_drm_submit_execbuf(client, args); + } + + XDNA_ERR(client->xdna, "Invalid command type %d", args->type); + return -EINVAL; +} diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h new file mode 100644 index 000000000000..f0a4a8586d85 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_CTX_H_ +#define _AMDXDNA_CTX_H_ + +#include <linux/bitfield.h> + +#include "amdxdna_gem.h" + +struct amdxdna_hwctx_priv; + +enum ert_cmd_opcode { + ERT_START_CU = 0, + ERT_CMD_CHAIN = 19, + ERT_START_NPU = 20, +}; + +enum ert_cmd_state { + ERT_CMD_STATE_INVALID, + ERT_CMD_STATE_NEW, + ERT_CMD_STATE_QUEUED, + ERT_CMD_STATE_RUNNING, + ERT_CMD_STATE_COMPLETED, + ERT_CMD_STATE_ERROR, + ERT_CMD_STATE_ABORT, + ERT_CMD_STATE_SUBMITTED, + ERT_CMD_STATE_TIMEOUT, + ERT_CMD_STATE_NORESPONSE, +}; + +/* + * Interpretation of the beginning of data payload for ERT_START_NPU in + * amdxdna_cmd. The rest of the payload in amdxdna_cmd is regular kernel args. + */ +struct amdxdna_cmd_start_npu { + u64 buffer; /* instruction buffer address */ + u32 buffer_size; /* size of buffer in bytes */ + u32 prop_count; /* properties count */ + u32 prop_args[]; /* properties and regular kernel arguments */ +}; + +/* + * Interpretation of the beginning of data payload for ERT_CMD_CHAIN in + * amdxdna_cmd. The rest of the payload in amdxdna_cmd is cmd BO handles. + */ +struct amdxdna_cmd_chain { + u32 command_count; + u32 submit_index; + u32 error_index; + u32 reserved[3]; + u64 data[] __counted_by(command_count); +}; + +/* Exec buffer command header format */ +#define AMDXDNA_CMD_STATE GENMASK(3, 0) +#define AMDXDNA_CMD_EXTRA_CU_MASK GENMASK(11, 10) +#define AMDXDNA_CMD_COUNT GENMASK(22, 12) +#define AMDXDNA_CMD_OPCODE GENMASK(27, 23) +struct amdxdna_cmd { + u32 header; + u32 data[]; +}; + +struct amdxdna_hwctx { + struct amdxdna_client *client; + struct amdxdna_hwctx_priv *priv; + char *name; + + u32 id; + u32 max_opc; + u32 num_tiles; + u32 mem_size; + u32 fw_ctx_id; + u32 col_list_len; + u32 *col_list; + u32 start_col; + u32 num_col; +#define HWCTX_STAT_INIT 0 +#define HWCTX_STAT_READY 1 +#define HWCTX_STAT_STOP 2 + u32 status; + u32 old_status; + + struct amdxdna_qos_info qos; + struct amdxdna_hwctx_param_config_cu *cus; + u32 syncobj_hdl; + + atomic64_t job_submit_cnt; + atomic64_t job_free_cnt ____cacheline_aligned_in_smp; +}; + +#define drm_job_to_xdna_job(j) \ + container_of(j, struct amdxdna_sched_job, base) + +struct amdxdna_sched_job { + struct drm_sched_job base; + struct kref refcnt; + struct amdxdna_hwctx *hwctx; + struct mm_struct *mm; + /* The fence to notice DRM scheduler that job is done by hardware */ + struct dma_fence *fence; + /* user can wait on this fence */ + struct dma_fence *out_fence; + bool job_done; + u64 seq; + struct amdxdna_gem_obj *cmd_bo; + size_t bo_cnt; + struct drm_gem_object *bos[] __counted_by(bo_cnt); +}; + +static inline u32 +amdxdna_cmd_get_op(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + + return FIELD_GET(AMDXDNA_CMD_OPCODE, cmd->header); +} + +static inline void +amdxdna_cmd_set_state(struct amdxdna_gem_obj *abo, enum ert_cmd_state s) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + + cmd->header &= ~AMDXDNA_CMD_STATE; + cmd->header |= FIELD_PREP(AMDXDNA_CMD_STATE, s); +} + +static inline enum ert_cmd_state +amdxdna_cmd_get_state(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + + return FIELD_GET(AMDXDNA_CMD_STATE, cmd->header); +} + +void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size); +int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo); + +static inline u32 amdxdna_hwctx_col_map(struct amdxdna_hwctx *hwctx) +{ + return GENMASK(hwctx->start_col + hwctx->num_col - 1, + hwctx->start_col); +} + +void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job); +void amdxdna_hwctx_remove_all(struct amdxdna_client *client); +void amdxdna_hwctx_suspend(struct amdxdna_client *client); +void amdxdna_hwctx_resume(struct amdxdna_client *client); + +int amdxdna_cmd_submit(struct amdxdna_client *client, + u32 cmd_bo_hdls, u32 *arg_bo_hdls, u32 arg_bo_cnt, + u32 hwctx_hdl, u64 *seq); + +int amdxdna_cmd_wait(struct amdxdna_client *client, u32 hwctx_hdl, + u64 seq, u32 timeout); + +int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_submit_cmd_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); + +#endif /* _AMDXDNA_CTX_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c new file mode 100644 index 000000000000..606433d73236 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -0,0 +1,622 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_cache.h> +#include <drm/drm_device.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/gpu_scheduler.h> +#include <linux/iosys-map.h> +#include <linux/vmalloc.h> + +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_pci_drv.h" + +#define XDNA_MAX_CMD_BO_SIZE SZ_32K + +static int +amdxdna_gem_insert_node_locked(struct amdxdna_gem_obj *abo, bool use_vmap) +{ + struct amdxdna_client *client = abo->client; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_mem *mem = &abo->mem; + u64 offset; + u32 align; + int ret; + + align = 1 << max(PAGE_SHIFT, xdna->dev_info->dev_mem_buf_shift); + ret = drm_mm_insert_node_generic(&abo->dev_heap->mm, &abo->mm_node, + mem->size, align, + 0, DRM_MM_INSERT_BEST); + if (ret) { + XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret); + return ret; + } + + mem->dev_addr = abo->mm_node.start; + offset = mem->dev_addr - abo->dev_heap->mem.dev_addr; + mem->userptr = abo->dev_heap->mem.userptr + offset; + mem->pages = &abo->dev_heap->base.pages[offset >> PAGE_SHIFT]; + mem->nr_pages = mem->size >> PAGE_SHIFT; + + if (use_vmap) { + mem->kva = vmap(mem->pages, mem->nr_pages, VM_MAP, PAGE_KERNEL); + if (!mem->kva) { + XDNA_ERR(xdna, "Failed to vmap"); + drm_mm_remove_node(&abo->mm_node); + return -EFAULT; + } + } + + return 0; +} + +static void amdxdna_gem_obj_free(struct drm_gem_object *gobj) +{ + struct amdxdna_dev *xdna = to_xdna_dev(gobj->dev); + struct amdxdna_gem_obj *abo = to_xdna_obj(gobj); + struct iosys_map map = IOSYS_MAP_INIT_VADDR(abo->mem.kva); + + XDNA_DBG(xdna, "BO type %d xdna_addr 0x%llx", abo->type, abo->mem.dev_addr); + if (abo->pinned) + amdxdna_gem_unpin(abo); + + if (abo->type == AMDXDNA_BO_DEV) { + mutex_lock(&abo->client->mm_lock); + drm_mm_remove_node(&abo->mm_node); + mutex_unlock(&abo->client->mm_lock); + + vunmap(abo->mem.kva); + drm_gem_object_put(to_gobj(abo->dev_heap)); + drm_gem_object_release(gobj); + mutex_destroy(&abo->lock); + kfree(abo); + return; + } + + if (abo->type == AMDXDNA_BO_DEV_HEAP) + drm_mm_takedown(&abo->mm); + + drm_gem_vunmap_unlocked(gobj, &map); + mutex_destroy(&abo->lock); + drm_gem_shmem_free(&abo->base); +} + +static const struct drm_gem_object_funcs amdxdna_gem_dev_obj_funcs = { + .free = amdxdna_gem_obj_free, +}; + +static bool amdxdna_hmm_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) +{ + struct amdxdna_gem_obj *abo = container_of(mni, struct amdxdna_gem_obj, + mem.notifier); + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + + XDNA_DBG(xdna, "Invalid range 0x%llx, 0x%lx, type %d", + abo->mem.userptr, abo->mem.size, abo->type); + + if (!mmu_notifier_range_blockable(range)) + return false; + + xdna->dev_info->ops->hmm_invalidate(abo, cur_seq); + + return true; +} + +static const struct mmu_interval_notifier_ops amdxdna_hmm_ops = { + .invalidate = amdxdna_hmm_invalidate, +}; + +static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + + if (!xdna->dev_info->ops->hmm_invalidate) + return; + + mmu_interval_notifier_remove(&abo->mem.notifier); + kvfree(abo->mem.pfns); + abo->mem.pfns = NULL; +} + +static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, unsigned long addr, + size_t len) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + u32 nr_pages; + int ret; + + if (!xdna->dev_info->ops->hmm_invalidate) + return 0; + + if (abo->mem.pfns) + return -EEXIST; + + nr_pages = (PAGE_ALIGN(addr + len) - (addr & PAGE_MASK)) >> PAGE_SHIFT; + abo->mem.pfns = kvcalloc(nr_pages, sizeof(*abo->mem.pfns), + GFP_KERNEL); + if (!abo->mem.pfns) + return -ENOMEM; + + ret = mmu_interval_notifier_insert_locked(&abo->mem.notifier, + current->mm, + addr, + len, + &amdxdna_hmm_ops); + if (ret) { + XDNA_ERR(xdna, "Insert mmu notifier failed, ret %d", ret); + kvfree(abo->mem.pfns); + } + abo->mem.userptr = addr; + + return ret; +} + +static int amdxdna_gem_obj_mmap(struct drm_gem_object *gobj, + struct vm_area_struct *vma) +{ + struct amdxdna_gem_obj *abo = to_xdna_obj(gobj); + unsigned long num_pages; + int ret; + + ret = amdxdna_hmm_register(abo, vma->vm_start, gobj->size); + if (ret) + return ret; + + ret = drm_gem_shmem_mmap(&abo->base, vma); + if (ret) + goto hmm_unreg; + + num_pages = gobj->size >> PAGE_SHIFT; + /* Try to insert the pages */ + vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP); + ret = vm_insert_pages(vma, vma->vm_start, abo->base.pages, &num_pages); + if (ret) + XDNA_ERR(abo->client->xdna, "Failed insert pages, ret %d", ret); + + return 0; + +hmm_unreg: + amdxdna_hmm_unregister(abo); + return ret; +} + +static vm_fault_t amdxdna_gem_vm_fault(struct vm_fault *vmf) +{ + return drm_gem_shmem_vm_ops.fault(vmf); +} + +static void amdxdna_gem_vm_open(struct vm_area_struct *vma) +{ + drm_gem_shmem_vm_ops.open(vma); +} + +static void amdxdna_gem_vm_close(struct vm_area_struct *vma) +{ + struct drm_gem_object *gobj = vma->vm_private_data; + + amdxdna_hmm_unregister(to_xdna_obj(gobj)); + drm_gem_shmem_vm_ops.close(vma); +} + +static const struct vm_operations_struct amdxdna_gem_vm_ops = { + .fault = amdxdna_gem_vm_fault, + .open = amdxdna_gem_vm_open, + .close = amdxdna_gem_vm_close, +}; + +static const struct drm_gem_object_funcs amdxdna_gem_shmem_funcs = { + .free = amdxdna_gem_obj_free, + .print_info = drm_gem_shmem_object_print_info, + .pin = drm_gem_shmem_object_pin, + .unpin = drm_gem_shmem_object_unpin, + .get_sg_table = drm_gem_shmem_object_get_sg_table, + .vmap = drm_gem_shmem_object_vmap, + .vunmap = drm_gem_shmem_object_vunmap, + .mmap = amdxdna_gem_obj_mmap, + .vm_ops = &amdxdna_gem_vm_ops, +}; + +static struct amdxdna_gem_obj * +amdxdna_gem_create_obj(struct drm_device *dev, size_t size) +{ + struct amdxdna_gem_obj *abo; + + abo = kzalloc(sizeof(*abo), GFP_KERNEL); + if (!abo) + return ERR_PTR(-ENOMEM); + + abo->pinned = false; + abo->assigned_hwctx = AMDXDNA_INVALID_CTX_HANDLE; + mutex_init(&abo->lock); + + abo->mem.userptr = AMDXDNA_INVALID_ADDR; + abo->mem.dev_addr = AMDXDNA_INVALID_ADDR; + abo->mem.size = size; + + return abo; +} + +/* For drm_driver->gem_create_object callback */ +struct drm_gem_object * +amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size) +{ + struct amdxdna_gem_obj *abo; + + abo = amdxdna_gem_create_obj(dev, size); + if (IS_ERR(abo)) + return ERR_CAST(abo); + + to_gobj(abo)->funcs = &amdxdna_gem_shmem_funcs; + + return to_gobj(abo); +} + +static struct amdxdna_gem_obj * +amdxdna_drm_alloc_shmem(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct drm_gem_shmem_object *shmem; + struct amdxdna_gem_obj *abo; + + shmem = drm_gem_shmem_create(dev, args->size); + if (IS_ERR(shmem)) + return ERR_CAST(shmem); + + shmem->map_wc = false; + + abo = to_xdna_obj(&shmem->base); + abo->client = client; + abo->type = AMDXDNA_BO_SHMEM; + + return abo; +} + +static struct amdxdna_gem_obj * +amdxdna_drm_create_dev_heap(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct drm_gem_shmem_object *shmem; + struct amdxdna_gem_obj *abo; + int ret; + + if (args->size > xdna->dev_info->dev_mem_size) { + XDNA_DBG(xdna, "Invalid dev heap size 0x%llx, limit 0x%lx", + args->size, xdna->dev_info->dev_mem_size); + return ERR_PTR(-EINVAL); + } + + mutex_lock(&client->mm_lock); + if (client->dev_heap) { + XDNA_DBG(client->xdna, "dev heap is already created"); + ret = -EBUSY; + goto mm_unlock; + } + + shmem = drm_gem_shmem_create(dev, args->size); + if (IS_ERR(shmem)) { + ret = PTR_ERR(shmem); + goto mm_unlock; + } + + shmem->map_wc = false; + abo = to_xdna_obj(&shmem->base); + + abo->type = AMDXDNA_BO_DEV_HEAP; + abo->client = client; + abo->mem.dev_addr = client->xdna->dev_info->dev_mem_base; + drm_mm_init(&abo->mm, abo->mem.dev_addr, abo->mem.size); + + client->dev_heap = abo; + drm_gem_object_get(to_gobj(abo)); + mutex_unlock(&client->mm_lock); + + return abo; + +mm_unlock: + mutex_unlock(&client->mm_lock); + return ERR_PTR(ret); +} + +struct amdxdna_gem_obj * +amdxdna_drm_alloc_dev_bo(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp, bool use_vmap) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + size_t aligned_sz = PAGE_ALIGN(args->size); + struct amdxdna_gem_obj *abo, *heap; + int ret; + + mutex_lock(&client->mm_lock); + heap = client->dev_heap; + if (!heap) { + ret = -EINVAL; + goto mm_unlock; + } + + if (heap->mem.userptr == AMDXDNA_INVALID_ADDR) { + XDNA_ERR(xdna, "Invalid dev heap userptr"); + ret = -EINVAL; + goto mm_unlock; + } + + if (args->size > heap->mem.size) { + XDNA_ERR(xdna, "Invalid dev bo size 0x%llx, limit 0x%lx", + args->size, heap->mem.size); + ret = -EINVAL; + goto mm_unlock; + } + + abo = amdxdna_gem_create_obj(&xdna->ddev, aligned_sz); + if (IS_ERR(abo)) { + ret = PTR_ERR(abo); + goto mm_unlock; + } + to_gobj(abo)->funcs = &amdxdna_gem_dev_obj_funcs; + abo->type = AMDXDNA_BO_DEV; + abo->client = client; + abo->dev_heap = heap; + ret = amdxdna_gem_insert_node_locked(abo, use_vmap); + if (ret) { + XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret); + goto mm_unlock; + } + + drm_gem_object_get(to_gobj(heap)); + drm_gem_private_object_init(&xdna->ddev, to_gobj(abo), aligned_sz); + + mutex_unlock(&client->mm_lock); + return abo; + +mm_unlock: + mutex_unlock(&client->mm_lock); + return ERR_PTR(ret); +} + +static struct amdxdna_gem_obj * +amdxdna_drm_create_cmd_bo(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct drm_gem_shmem_object *shmem; + struct amdxdna_gem_obj *abo; + struct iosys_map map; + int ret; + + if (args->size > XDNA_MAX_CMD_BO_SIZE) { + XDNA_ERR(xdna, "Command bo size 0x%llx too large", args->size); + return ERR_PTR(-EINVAL); + } + + if (args->size < sizeof(struct amdxdna_cmd)) { + XDNA_DBG(xdna, "Command BO size 0x%llx too small", args->size); + return ERR_PTR(-EINVAL); + } + + shmem = drm_gem_shmem_create(dev, args->size); + if (IS_ERR(shmem)) + return ERR_CAST(shmem); + + shmem->map_wc = false; + abo = to_xdna_obj(&shmem->base); + + abo->type = AMDXDNA_BO_CMD; + abo->client = filp->driver_priv; + + ret = drm_gem_vmap_unlocked(to_gobj(abo), &map); + if (ret) { + XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret); + goto release_obj; + } + abo->mem.kva = map.vaddr; + + return abo; + +release_obj: + drm_gem_shmem_free(shmem); + return ERR_PTR(ret); +} + +int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_create_bo *args = data; + struct amdxdna_gem_obj *abo; + int ret; + + if (args->flags || args->vaddr || !args->size) + return -EINVAL; + + XDNA_DBG(xdna, "BO arg type %d vaddr 0x%llx size 0x%llx flags 0x%llx", + args->type, args->vaddr, args->size, args->flags); + switch (args->type) { + case AMDXDNA_BO_SHMEM: + abo = amdxdna_drm_alloc_shmem(dev, args, filp); + break; + case AMDXDNA_BO_DEV_HEAP: + abo = amdxdna_drm_create_dev_heap(dev, args, filp); + break; + case AMDXDNA_BO_DEV: + abo = amdxdna_drm_alloc_dev_bo(dev, args, filp, false); + break; + case AMDXDNA_BO_CMD: + abo = amdxdna_drm_create_cmd_bo(dev, args, filp); + break; + default: + return -EINVAL; + } + if (IS_ERR(abo)) + return PTR_ERR(abo); + + /* ready to publish object to userspace */ + ret = drm_gem_handle_create(filp, to_gobj(abo), &args->handle); + if (ret) { + XDNA_ERR(xdna, "Create handle failed"); + goto put_obj; + } + + XDNA_DBG(xdna, "BO hdl %d type %d userptr 0x%llx xdna_addr 0x%llx size 0x%lx", + args->handle, args->type, abo->mem.userptr, + abo->mem.dev_addr, abo->mem.size); +put_obj: + /* Dereference object reference. Handle holds it now. */ + drm_gem_object_put(to_gobj(abo)); + return ret; +} + +int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + int ret; + + switch (abo->type) { + case AMDXDNA_BO_SHMEM: + case AMDXDNA_BO_DEV_HEAP: + ret = drm_gem_shmem_pin(&abo->base); + break; + case AMDXDNA_BO_DEV: + ret = drm_gem_shmem_pin(&abo->dev_heap->base); + break; + default: + ret = -EOPNOTSUPP; + } + + XDNA_DBG(xdna, "BO type %d ret %d", abo->type, ret); + return ret; +} + +int amdxdna_gem_pin(struct amdxdna_gem_obj *abo) +{ + int ret; + + if (abo->type == AMDXDNA_BO_DEV) + abo = abo->dev_heap; + + mutex_lock(&abo->lock); + ret = amdxdna_gem_pin_nolock(abo); + mutex_unlock(&abo->lock); + + return ret; +} + +void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo) +{ + if (abo->type == AMDXDNA_BO_DEV) + abo = abo->dev_heap; + + mutex_lock(&abo->lock); + drm_gem_shmem_unpin(&abo->base); + mutex_unlock(&abo->lock); +} + +struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client, + u32 bo_hdl, u8 bo_type) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_gem_obj *abo; + struct drm_gem_object *gobj; + + gobj = drm_gem_object_lookup(client->filp, bo_hdl); + if (!gobj) { + XDNA_DBG(xdna, "Can not find bo %d", bo_hdl); + return NULL; + } + + abo = to_xdna_obj(gobj); + if (bo_type == AMDXDNA_BO_INVALID || abo->type == bo_type) + return abo; + + drm_gem_object_put(gobj); + return NULL; +} + +int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_drm_get_bo_info *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_gem_obj *abo; + struct drm_gem_object *gobj; + int ret = 0; + + if (args->ext || args->ext_flags || args->pad) + return -EINVAL; + + gobj = drm_gem_object_lookup(filp, args->handle); + if (!gobj) { + XDNA_DBG(xdna, "Lookup GEM object %d failed", args->handle); + return -ENOENT; + } + + abo = to_xdna_obj(gobj); + args->vaddr = abo->mem.userptr; + args->xdna_addr = abo->mem.dev_addr; + + if (abo->type != AMDXDNA_BO_DEV) + args->map_offset = drm_vma_node_offset_addr(&gobj->vma_node); + else + args->map_offset = AMDXDNA_INVALID_ADDR; + + XDNA_DBG(xdna, "BO hdl %d map_offset 0x%llx vaddr 0x%llx xdna_addr 0x%llx", + args->handle, args->map_offset, args->vaddr, args->xdna_addr); + + drm_gem_object_put(gobj); + return ret; +} + +/* + * The sync bo ioctl is to make sure the CPU cache is in sync with memory. + * This is required because NPU is not cache coherent device. CPU cache + * flushing/invalidation is expensive so it is best to handle this outside + * of the command submission path. This ioctl allows explicit cache + * flushing/invalidation outside of the critical path. + */ +int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, + void *data, struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_sync_bo *args = data; + struct amdxdna_gem_obj *abo; + struct drm_gem_object *gobj; + int ret; + + gobj = drm_gem_object_lookup(filp, args->handle); + if (!gobj) { + XDNA_ERR(xdna, "Lookup GEM object failed"); + return -ENOENT; + } + abo = to_xdna_obj(gobj); + + ret = amdxdna_gem_pin(abo); + if (ret) { + XDNA_ERR(xdna, "Pin BO %d failed, ret %d", args->handle, ret); + goto put_obj; + } + + if (abo->type == AMDXDNA_BO_DEV) + drm_clflush_pages(abo->mem.pages, abo->mem.nr_pages); + else + drm_clflush_pages(abo->base.pages, gobj->size >> PAGE_SHIFT); + + amdxdna_gem_unpin(abo); + + XDNA_DBG(xdna, "Sync bo %d offset 0x%llx, size 0x%llx\n", + args->handle, args->offset, args->size); + +put_obj: + drm_gem_object_put(gobj); + return ret; +} diff --git a/drivers/accel/amdxdna/amdxdna_gem.h b/drivers/accel/amdxdna/amdxdna_gem.h new file mode 100644 index 000000000000..8ccc0375dd9d --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_gem.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_GEM_H_ +#define _AMDXDNA_GEM_H_ + +struct amdxdna_mem { + u64 userptr; + void *kva; + u64 dev_addr; + size_t size; + struct page **pages; + u32 nr_pages; + struct mmu_interval_notifier notifier; + unsigned long *pfns; + bool map_invalid; +}; + +struct amdxdna_gem_obj { + struct drm_gem_shmem_object base; + struct amdxdna_client *client; + u8 type; + bool pinned; + struct mutex lock; /* Protects: pinned */ + struct amdxdna_mem mem; + + /* Below members is uninitialized when needed */ + struct drm_mm mm; /* For AMDXDNA_BO_DEV_HEAP */ + struct amdxdna_gem_obj *dev_heap; /* For AMDXDNA_BO_DEV */ + struct drm_mm_node mm_node; /* For AMDXDNA_BO_DEV */ + u32 assigned_hwctx; +}; + +#define to_gobj(obj) (&(obj)->base.base) + +static inline struct amdxdna_gem_obj *to_xdna_obj(struct drm_gem_object *gobj) +{ + return container_of(gobj, struct amdxdna_gem_obj, base.base); +} + +struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client, + u32 bo_hdl, u8 bo_type); +static inline void amdxdna_gem_put_obj(struct amdxdna_gem_obj *abo) +{ + drm_gem_object_put(to_gobj(abo)); +} + +struct drm_gem_object * +amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size); +struct amdxdna_gem_obj * +amdxdna_drm_alloc_dev_bo(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp, bool use_vmap); + +int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo); +int amdxdna_gem_pin(struct amdxdna_gem_obj *abo); +void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo); + +int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); + +#endif /* _AMDXDNA_GEM_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c new file mode 100644 index 000000000000..da1ac89bb78f --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/drm_device.h> +#include <drm/drm_managed.h> +#include <linux/bitfield.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/slab.h> +#include <linux/xarray.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/amdxdna.h> + +#include "amdxdna_mailbox.h" + +#define MB_ERR(chann, fmt, args...) \ +({ \ + typeof(chann) _chann = chann; \ + dev_err((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \ + (_chann)->msix_irq, ##args); \ +}) +#define MB_DBG(chann, fmt, args...) \ +({ \ + typeof(chann) _chann = chann; \ + dev_dbg((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \ + (_chann)->msix_irq, ##args); \ +}) +#define MB_WARN_ONCE(chann, fmt, args...) \ +({ \ + typeof(chann) _chann = chann; \ + dev_warn_once((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \ + (_chann)->msix_irq, ##args); \ +}) + +#define MAGIC_VAL 0x1D000000U +#define MAGIC_VAL_MASK 0xFF000000 +#define MAX_MSG_ID_ENTRIES 256 +#define MSG_RX_TIMER 200 /* milliseconds */ +#define MAILBOX_NAME "xdna_mailbox" + +enum channel_res_type { + CHAN_RES_X2I, + CHAN_RES_I2X, + CHAN_RES_NUM +}; + +struct mailbox { + struct device *dev; + struct xdna_mailbox_res res; +}; + +struct mailbox_channel { + struct mailbox *mb; + struct xdna_mailbox_chann_res res[CHAN_RES_NUM]; + int msix_irq; + u32 iohub_int_addr; + struct xarray chan_xa; + u32 next_msgid; + u32 x2i_tail; + + /* Received msg related fields */ + struct workqueue_struct *work_q; + struct work_struct rx_work; + u32 i2x_head; + bool bad_state; +}; + +#define MSG_BODY_SZ GENMASK(10, 0) +#define MSG_PROTO_VER GENMASK(23, 16) +struct xdna_msg_header { + __u32 total_size; + __u32 sz_ver; + __u32 id; + __u32 opcode; +} __packed; + +static_assert(sizeof(struct xdna_msg_header) == 16); + +struct mailbox_pkg { + struct xdna_msg_header header; + __u32 payload[]; +}; + +/* The protocol version. */ +#define MSG_PROTOCOL_VERSION 0x1 +/* The tombstone value. */ +#define TOMBSTONE 0xDEADFACE + +struct mailbox_msg { + void *handle; + int (*notify_cb)(void *handle, void __iomem *data, size_t size); + size_t pkg_size; /* package size in bytes */ + struct mailbox_pkg pkg; +}; + +static void mailbox_reg_write(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 data) +{ + struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; + void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg; + + writel(data, ringbuf_addr); +} + +static u32 mailbox_reg_read(struct mailbox_channel *mb_chann, u32 mbox_reg) +{ + struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; + void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg; + + return readl(ringbuf_addr); +} + +static int mailbox_reg_read_non_zero(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 *val) +{ + struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; + void __iomem *ringbuf_addr = mb_res->mbox_base + mbox_reg; + int ret, value; + + /* Poll till value is not zero */ + ret = readx_poll_timeout(readl, ringbuf_addr, value, + value, 1 /* us */, 100); + if (ret < 0) + return ret; + + *val = value; + return 0; +} + +static inline void +mailbox_set_headptr(struct mailbox_channel *mb_chann, u32 headptr_val) +{ + mailbox_reg_write(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_head_ptr_reg, headptr_val); + mb_chann->i2x_head = headptr_val; +} + +static inline void +mailbox_set_tailptr(struct mailbox_channel *mb_chann, u32 tailptr_val) +{ + mailbox_reg_write(mb_chann, mb_chann->res[CHAN_RES_X2I].mb_tail_ptr_reg, tailptr_val); + mb_chann->x2i_tail = tailptr_val; +} + +static inline u32 +mailbox_get_headptr(struct mailbox_channel *mb_chann, enum channel_res_type type) +{ + return mailbox_reg_read(mb_chann, mb_chann->res[type].mb_head_ptr_reg); +} + +static inline u32 +mailbox_get_tailptr(struct mailbox_channel *mb_chann, enum channel_res_type type) +{ + return mailbox_reg_read(mb_chann, mb_chann->res[type].mb_tail_ptr_reg); +} + +static inline u32 +mailbox_get_ringbuf_size(struct mailbox_channel *mb_chann, enum channel_res_type type) +{ + return mb_chann->res[type].rb_size; +} + +static inline int mailbox_validate_msgid(int msg_id) +{ + return (msg_id & MAGIC_VAL_MASK) == MAGIC_VAL; +} + +static int mailbox_acquire_msgid(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) +{ + u32 msg_id; + int ret; + + ret = xa_alloc_cyclic_irq(&mb_chann->chan_xa, &msg_id, mb_msg, + XA_LIMIT(0, MAX_MSG_ID_ENTRIES - 1), + &mb_chann->next_msgid, GFP_NOWAIT); + if (ret < 0) + return ret; + + /* + * Add MAGIC_VAL to the higher bits. + */ + msg_id |= MAGIC_VAL; + return msg_id; +} + +static void mailbox_release_msgid(struct mailbox_channel *mb_chann, int msg_id) +{ + msg_id &= ~MAGIC_VAL_MASK; + xa_erase_irq(&mb_chann->chan_xa, msg_id); +} + +static void mailbox_release_msg(struct mailbox_channel *mb_chann, + struct mailbox_msg *mb_msg) +{ + MB_DBG(mb_chann, "msg_id 0x%x msg opcode 0x%x", + mb_msg->pkg.header.id, mb_msg->pkg.header.opcode); + mb_msg->notify_cb(mb_msg->handle, NULL, 0); + kfree(mb_msg); +} + +static int +mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) +{ + void __iomem *write_addr; + u32 ringbuf_size; + u32 head, tail; + u32 start_addr; + u32 tmp_tail; + + head = mailbox_get_headptr(mb_chann, CHAN_RES_X2I); + tail = mb_chann->x2i_tail; + ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I); + start_addr = mb_chann->res[CHAN_RES_X2I].rb_start_addr; + tmp_tail = tail + mb_msg->pkg_size; + + if (tail < head && tmp_tail >= head) + goto no_space; + + if (tail >= head && (tmp_tail > ringbuf_size - sizeof(u32) && + mb_msg->pkg_size >= head)) + goto no_space; + + if (tail >= head && tmp_tail > ringbuf_size - sizeof(u32)) { + write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; + writel(TOMBSTONE, write_addr); + + /* tombstone is set. Write from the start of the ringbuf */ + tail = 0; + } + + write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; + memcpy_toio(write_addr, &mb_msg->pkg, mb_msg->pkg_size); + mailbox_set_tailptr(mb_chann, tail + mb_msg->pkg_size); + + trace_mbox_set_tail(MAILBOX_NAME, mb_chann->msix_irq, + mb_msg->pkg.header.opcode, + mb_msg->pkg.header.id); + + return 0; + +no_space: + return -ENOSPC; +} + +static int +mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *header, + void __iomem *data) +{ + struct mailbox_msg *mb_msg; + int msg_id; + int ret; + + msg_id = header->id; + if (!mailbox_validate_msgid(msg_id)) { + MB_ERR(mb_chann, "Bad message ID 0x%x", msg_id); + return -EINVAL; + } + + msg_id &= ~MAGIC_VAL_MASK; + mb_msg = xa_erase_irq(&mb_chann->chan_xa, msg_id); + if (!mb_msg) { + MB_ERR(mb_chann, "Cannot find msg 0x%x", msg_id); + return -EINVAL; + } + + MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x", + header->opcode, header->total_size, header->id); + ret = mb_msg->notify_cb(mb_msg->handle, data, header->total_size); + if (unlikely(ret)) + MB_ERR(mb_chann, "Message callback ret %d", ret); + + kfree(mb_msg); + return ret; +} + +static int mailbox_get_msg(struct mailbox_channel *mb_chann) +{ + struct xdna_msg_header header; + void __iomem *read_addr; + u32 msg_size, rest; + u32 ringbuf_size; + u32 head, tail; + u32 start_addr; + int ret; + + if (mailbox_reg_read_non_zero(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_tail_ptr_reg, &tail)) + return -EINVAL; + head = mb_chann->i2x_head; + ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_I2X); + start_addr = mb_chann->res[CHAN_RES_I2X].rb_start_addr; + + if (unlikely(tail > ringbuf_size || !IS_ALIGNED(tail, 4))) { + MB_WARN_ONCE(mb_chann, "Invalid tail 0x%x", tail); + return -EINVAL; + } + + /* ringbuf empty */ + if (head == tail) + return -ENOENT; + + if (head == ringbuf_size) + head = 0; + + /* Peek size of the message or TOMBSTONE */ + read_addr = mb_chann->mb->res.ringbuf_base + start_addr + head; + header.total_size = readl(read_addr); + /* size is TOMBSTONE, set next read from 0 */ + if (header.total_size == TOMBSTONE) { + if (head < tail) { + MB_WARN_ONCE(mb_chann, "Tombstone, head 0x%x tail 0x%x", + head, tail); + return -EINVAL; + } + mailbox_set_headptr(mb_chann, 0); + return 0; + } + + if (unlikely(!header.total_size || !IS_ALIGNED(header.total_size, 4))) { + MB_WARN_ONCE(mb_chann, "Invalid total size 0x%x", header.total_size); + return -EINVAL; + } + msg_size = sizeof(header) + header.total_size; + + if (msg_size > ringbuf_size - head || msg_size > tail - head) { + MB_WARN_ONCE(mb_chann, "Invalid message size %d, tail %d, head %d", + msg_size, tail, head); + return -EINVAL; + } + + rest = sizeof(header) - sizeof(u32); + read_addr += sizeof(u32); + memcpy_fromio((u32 *)&header + 1, read_addr, rest); + read_addr += rest; + + ret = mailbox_get_resp(mb_chann, &header, read_addr); + + mailbox_set_headptr(mb_chann, head + msg_size); + /* After update head, it can equal to ringbuf_size. This is expected. */ + trace_mbox_set_head(MAILBOX_NAME, mb_chann->msix_irq, + header.opcode, header.id); + + return ret; +} + +static irqreturn_t mailbox_irq_handler(int irq, void *p) +{ + struct mailbox_channel *mb_chann = p; + + trace_mbox_irq_handle(MAILBOX_NAME, irq); + /* Schedule a rx_work to call the callback functions */ + queue_work(mb_chann->work_q, &mb_chann->rx_work); + + return IRQ_HANDLED; +} + +static void mailbox_rx_worker(struct work_struct *rx_work) +{ + struct mailbox_channel *mb_chann; + int ret; + + mb_chann = container_of(rx_work, struct mailbox_channel, rx_work); + + if (READ_ONCE(mb_chann->bad_state)) { + MB_ERR(mb_chann, "Channel in bad state, work aborted"); + return; + } + +again: + mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0); + + while (1) { + /* + * If return is 0, keep consuming next message, until there is + * no messages or an error happened. + */ + ret = mailbox_get_msg(mb_chann); + if (ret == -ENOENT) + break; + + /* Other error means device doesn't look good, disable irq. */ + if (unlikely(ret)) { + MB_ERR(mb_chann, "Unexpected ret %d, disable irq", ret); + WRITE_ONCE(mb_chann->bad_state, true); + return; + } + } + + /* + * The hardware will not generate interrupt if firmware creates a new + * response right after driver clears interrupt register. Check + * the interrupt register to make sure there is not any new response + * before exiting. + */ + if (mailbox_reg_read(mb_chann, mb_chann->iohub_int_addr)) + goto again; +} + +int xdna_mailbox_send_msg(struct mailbox_channel *mb_chann, + const struct xdna_mailbox_msg *msg, u64 tx_timeout) +{ + struct xdna_msg_header *header; + struct mailbox_msg *mb_msg; + size_t pkg_size; + int ret; + + pkg_size = sizeof(*header) + msg->send_size; + if (pkg_size > mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I)) { + MB_ERR(mb_chann, "Message size larger than ringbuf size"); + return -EINVAL; + } + + if (unlikely(!IS_ALIGNED(msg->send_size, 4))) { + MB_ERR(mb_chann, "Message must be 4 bytes align"); + return -EINVAL; + } + + /* The fist word in payload can NOT be TOMBSTONE */ + if (unlikely(((u32 *)msg->send_data)[0] == TOMBSTONE)) { + MB_ERR(mb_chann, "Tomb stone in data"); + return -EINVAL; + } + + if (READ_ONCE(mb_chann->bad_state)) { + MB_ERR(mb_chann, "Channel in bad state"); + return -EPIPE; + } + + mb_msg = kzalloc(sizeof(*mb_msg) + pkg_size, GFP_KERNEL); + if (!mb_msg) + return -ENOMEM; + + mb_msg->handle = msg->handle; + mb_msg->notify_cb = msg->notify_cb; + mb_msg->pkg_size = pkg_size; + + header = &mb_msg->pkg.header; + /* + * Hardware use total_size and size to split huge message. + * We do not support it here. Thus the values are the same. + */ + header->total_size = msg->send_size; + header->sz_ver = FIELD_PREP(MSG_BODY_SZ, msg->send_size) | + FIELD_PREP(MSG_PROTO_VER, MSG_PROTOCOL_VERSION); + header->opcode = msg->opcode; + memcpy(mb_msg->pkg.payload, msg->send_data, msg->send_size); + + ret = mailbox_acquire_msgid(mb_chann, mb_msg); + if (unlikely(ret < 0)) { + MB_ERR(mb_chann, "mailbox_acquire_msgid failed"); + goto msg_id_failed; + } + header->id = ret; + + MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x", + header->opcode, header->total_size, header->id); + + ret = mailbox_send_msg(mb_chann, mb_msg); + if (ret) { + MB_DBG(mb_chann, "Error in mailbox send msg, ret %d", ret); + goto release_id; + } + + return 0; + +release_id: + mailbox_release_msgid(mb_chann, header->id); +msg_id_failed: + kfree(mb_msg); + return ret; +} + +struct mailbox_channel * +xdna_mailbox_create_channel(struct mailbox *mb, + const struct xdna_mailbox_chann_res *x2i, + const struct xdna_mailbox_chann_res *i2x, + u32 iohub_int_addr, + int mb_irq) +{ + struct mailbox_channel *mb_chann; + int ret; + + if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) { + pr_err("Ring buf size must be power of 2"); + return NULL; + } + + mb_chann = kzalloc(sizeof(*mb_chann), GFP_KERNEL); + if (!mb_chann) + return NULL; + + mb_chann->mb = mb; + mb_chann->msix_irq = mb_irq; + mb_chann->iohub_int_addr = iohub_int_addr; + memcpy(&mb_chann->res[CHAN_RES_X2I], x2i, sizeof(*x2i)); + memcpy(&mb_chann->res[CHAN_RES_I2X], i2x, sizeof(*i2x)); + + xa_init_flags(&mb_chann->chan_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); + mb_chann->x2i_tail = mailbox_get_tailptr(mb_chann, CHAN_RES_X2I); + mb_chann->i2x_head = mailbox_get_headptr(mb_chann, CHAN_RES_I2X); + + INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker); + mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME); + if (!mb_chann->work_q) { + MB_ERR(mb_chann, "Create workqueue failed"); + goto free_and_out; + } + + /* Everything look good. Time to enable irq handler */ + ret = request_irq(mb_irq, mailbox_irq_handler, 0, MAILBOX_NAME, mb_chann); + if (ret) { + MB_ERR(mb_chann, "Failed to request irq %d ret %d", mb_irq, ret); + goto destroy_wq; + } + + mb_chann->bad_state = false; + + MB_DBG(mb_chann, "Mailbox channel created (irq: %d)", mb_chann->msix_irq); + return mb_chann; + +destroy_wq: + destroy_workqueue(mb_chann->work_q); +free_and_out: + kfree(mb_chann); + return NULL; +} + +int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann) +{ + struct mailbox_msg *mb_msg; + unsigned long msg_id; + + MB_DBG(mb_chann, "IRQ disabled and RX work cancelled"); + free_irq(mb_chann->msix_irq, mb_chann); + destroy_workqueue(mb_chann->work_q); + /* We can clean up and release resources */ + + xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg) + mailbox_release_msg(mb_chann, mb_msg); + + xa_destroy(&mb_chann->chan_xa); + + MB_DBG(mb_chann, "Mailbox channel destroyed, irq: %d", mb_chann->msix_irq); + kfree(mb_chann); + return 0; +} + +void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann) +{ + /* Disable an irq and wait. This might sleep. */ + disable_irq(mb_chann->msix_irq); + + /* Cancel RX work and wait for it to finish */ + cancel_work_sync(&mb_chann->rx_work); + MB_DBG(mb_chann, "IRQ disabled and RX work cancelled"); +} + +struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, + const struct xdna_mailbox_res *res) +{ + struct mailbox *mb; + + mb = drmm_kzalloc(ddev, sizeof(*mb), GFP_KERNEL); + if (!mb) + return NULL; + mb->dev = ddev->dev; + + /* mailbox and ring buf base and size information */ + memcpy(&mb->res, res, sizeof(*res)); + + return mb; +} diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h new file mode 100644 index 000000000000..ea367f2fb738 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_MAILBOX_H_ +#define _AIE2_MAILBOX_H_ + +struct mailbox; +struct mailbox_channel; + +/* + * xdna_mailbox_msg - message struct + * + * @opcode: opcode for firmware + * @handle: handle used for the notify callback + * @notify_cb: callback function to notify the sender when there is response + * @send_data: pointing to sending data + * @send_size: size of the sending data + * + * The mailbox will split the sending data in to multiple firmware message if + * the size of the data is too big. This is transparent to the sender. The + * sender will receive one notification. + */ +struct xdna_mailbox_msg { + u32 opcode; + void *handle; + int (*notify_cb)(void *handle, void __iomem *data, size_t size); + u8 *send_data; + size_t send_size; +}; + +/* + * xdna_mailbox_res - mailbox hardware resource + * + * @ringbuf_base: ring buffer base address + * @ringbuf_size: ring buffer size + * @mbox_base: mailbox base address + * @mbox_size: mailbox size + */ +struct xdna_mailbox_res { + void __iomem *ringbuf_base; + size_t ringbuf_size; + void __iomem *mbox_base; + size_t mbox_size; + const char *name; +}; + +/* + * xdna_mailbox_chann_res - resources + * + * @rb_start_addr: ring buffer start address + * @rb_size: ring buffer size + * @mb_head_ptr_reg: mailbox head pointer register + * @mb_tail_ptr_reg: mailbox tail pointer register + */ +struct xdna_mailbox_chann_res { + u32 rb_start_addr; + u32 rb_size; + u32 mb_head_ptr_reg; + u32 mb_tail_ptr_reg; +}; + +/* + * xdna_mailbox_create() -- create mailbox subsystem and initialize + * + * @ddev: device pointer + * @res: SRAM and mailbox resources + * + * Return: If success, return a handle of mailbox subsystem. + * Otherwise, return NULL pointer. + */ +struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, + const struct xdna_mailbox_res *res); + +/* + * xdna_mailbox_create_channel() -- Create a mailbox channel instance + * + * @mailbox: the handle return from xdna_mailbox_create() + * @x2i: host to firmware mailbox resources + * @i2x: firmware to host mailbox resources + * @xdna_mailbox_intr_reg: register addr of MSI-X interrupt + * @mb_irq: Linux IRQ number associated with mailbox MSI-X interrupt vector index + * + * Return: If success, return a handle of mailbox channel. Otherwise, return NULL. + */ +struct mailbox_channel * +xdna_mailbox_create_channel(struct mailbox *mailbox, + const struct xdna_mailbox_chann_res *x2i, + const struct xdna_mailbox_chann_res *i2x, + u32 xdna_mailbox_intr_reg, + int mb_irq); + +/* + * xdna_mailbox_destroy_channel() -- destroy mailbox channel + * + * @mailbox_chann: the handle return from xdna_mailbox_create_channel() + * + * Return: if success, return 0. otherwise return error code + */ +int xdna_mailbox_destroy_channel(struct mailbox_channel *mailbox_chann); + +/* + * xdna_mailbox_stop_channel() -- stop mailbox channel + * + * @mailbox_chann: the handle return from xdna_mailbox_create_channel() + * + * Return: if success, return 0. otherwise return error code + */ +void xdna_mailbox_stop_channel(struct mailbox_channel *mailbox_chann); + +/* + * xdna_mailbox_send_msg() -- Send a message + * + * @mailbox_chann: Mailbox channel handle + * @msg: message struct for message information + * @tx_timeout: the timeout value for sending the message in ms. + * + * Return: If success return 0, otherwise, return error code + */ +int xdna_mailbox_send_msg(struct mailbox_channel *mailbox_chann, + const struct xdna_mailbox_msg *msg, u64 tx_timeout); + +#endif /* _AIE2_MAILBOX_ */ diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c new file mode 100644 index 000000000000..6d0c24513476 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/drm_print.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/gpu_scheduler.h> +#include <linux/completion.h> + +#include "amdxdna_gem.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_mailbox_helper.h" +#include "amdxdna_pci_drv.h" + +int xdna_msg_cb(void *handle, void __iomem *data, size_t size) +{ + struct xdna_notify *cb_arg = handle; + int ret; + + if (unlikely(!data)) + goto out; + + if (unlikely(cb_arg->size != size)) { + cb_arg->error = -EINVAL; + goto out; + } + + memcpy_fromio(cb_arg->data, data, cb_arg->size); + print_hex_dump_debug("resp data: ", DUMP_PREFIX_OFFSET, + 16, 4, cb_arg->data, cb_arg->size, true); +out: + ret = cb_arg->error; + complete(&cb_arg->comp); + return ret; +} + +int xdna_send_msg_wait(struct amdxdna_dev *xdna, struct mailbox_channel *chann, + struct xdna_mailbox_msg *msg) +{ + struct xdna_notify *hdl = msg->handle; + int ret; + + ret = xdna_mailbox_send_msg(chann, msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(xdna, "Send message failed, ret %d", ret); + return ret; + } + + ret = wait_for_completion_timeout(&hdl->comp, + msecs_to_jiffies(RX_TIMEOUT)); + if (!ret) { + XDNA_ERR(xdna, "Wait for completion timeout"); + return -ETIME; + } + + return hdl->error; +} diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.h b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h new file mode 100644 index 000000000000..710ff8873d61 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_MAILBOX_HELPER_H +#define _AMDXDNA_MAILBOX_HELPER_H + +#define TX_TIMEOUT 2000 /* milliseconds */ +#define RX_TIMEOUT 5000 /* milliseconds */ + +struct amdxdna_dev; + +struct xdna_notify { + struct completion comp; + u32 *data; + size_t size; + int error; +}; + +#define DECLARE_XDNA_MSG_COMMON(name, op, status) \ + struct name##_req req = { 0 }; \ + struct name##_resp resp = { status }; \ + struct xdna_notify hdl = { \ + .error = 0, \ + .data = (u32 *)&resp, \ + .size = sizeof(resp), \ + .comp = COMPLETION_INITIALIZER_ONSTACK(hdl.comp), \ + }; \ + struct xdna_mailbox_msg msg = { \ + .send_data = (u8 *)&req, \ + .send_size = sizeof(req), \ + .handle = &hdl, \ + .opcode = op, \ + .notify_cb = xdna_msg_cb, \ + } + +int xdna_msg_cb(void *handle, void __iomem *data, size_t size); +int xdna_send_msg_wait(struct amdxdna_dev *xdna, struct mailbox_channel *chann, + struct xdna_mailbox_msg *msg); + +#endif /* _AMDXDNA_MAILBOX_HELPER_H */ diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c new file mode 100644 index 000000000000..f5b8497cf5ad --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -0,0 +1,434 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_accel.h> +#include <drm/drm_drv.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_ioctl.h> +#include <drm/drm_managed.h> +#include <drm/gpu_scheduler.h> +#include <linux/iommu.h> +#include <linux/pci.h> +#include <linux/pm_runtime.h> + +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_pci_drv.h" + +#define AMDXDNA_AUTOSUSPEND_DELAY 5000 /* milliseconds */ + +MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin"); + +/* + * Bind the driver base on (vendor_id, device_id) pair and later use the + * (device_id, rev_id) pair as a key to select the devices. The devices with + * same device_id have very similar interface to host driver. + */ +static const struct pci_device_id pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1502) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x17f0) }, + {0} +}; + +MODULE_DEVICE_TABLE(pci, pci_ids); + +static const struct amdxdna_device_id amdxdna_ids[] = { + { 0x1502, 0x0, &dev_npu1_info }, + { 0x17f0, 0x0, &dev_npu2_info }, + { 0x17f0, 0x10, &dev_npu4_info }, + { 0x17f0, 0x11, &dev_npu5_info }, + { 0x17f0, 0x20, &dev_npu6_info }, + {0} +}; + +static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(ddev); + struct amdxdna_client *client; + int ret; + + ret = pm_runtime_resume_and_get(ddev->dev); + if (ret) { + XDNA_ERR(xdna, "Failed to get rpm, ret %d", ret); + return ret; + } + + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) { + ret = -ENOMEM; + goto put_rpm; + } + + client->pid = pid_nr(rcu_access_pointer(filp->pid)); + client->xdna = xdna; + + client->sva = iommu_sva_bind_device(xdna->ddev.dev, current->mm); + if (IS_ERR(client->sva)) { + ret = PTR_ERR(client->sva); + XDNA_ERR(xdna, "SVA bind device failed, ret %d", ret); + goto failed; + } + client->pasid = iommu_sva_get_pasid(client->sva); + if (client->pasid == IOMMU_PASID_INVALID) { + XDNA_ERR(xdna, "SVA get pasid failed"); + ret = -ENODEV; + goto unbind_sva; + } + mutex_init(&client->hwctx_lock); + init_srcu_struct(&client->hwctx_srcu); + xa_init_flags(&client->hwctx_xa, XA_FLAGS_ALLOC); + mutex_init(&client->mm_lock); + + mutex_lock(&xdna->dev_lock); + list_add_tail(&client->node, &xdna->client_list); + mutex_unlock(&xdna->dev_lock); + + filp->driver_priv = client; + client->filp = filp; + + XDNA_DBG(xdna, "pid %d opened", client->pid); + return 0; + +unbind_sva: + iommu_sva_unbind_device(client->sva); +failed: + kfree(client); +put_rpm: + pm_runtime_mark_last_busy(ddev->dev); + pm_runtime_put_autosuspend(ddev->dev); + + return ret; +} + +static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(ddev); + + XDNA_DBG(xdna, "closing pid %d", client->pid); + + xa_destroy(&client->hwctx_xa); + cleanup_srcu_struct(&client->hwctx_srcu); + mutex_destroy(&client->hwctx_lock); + mutex_destroy(&client->mm_lock); + if (client->dev_heap) + drm_gem_object_put(to_gobj(client->dev_heap)); + + iommu_sva_unbind_device(client->sva); + + XDNA_DBG(xdna, "pid %d closed", client->pid); + kfree(client); + pm_runtime_mark_last_busy(ddev->dev); + pm_runtime_put_autosuspend(ddev->dev); +} + +static int amdxdna_flush(struct file *f, fl_owner_t id) +{ + struct drm_file *filp = f->private_data; + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = client->xdna; + int idx; + + XDNA_DBG(xdna, "PID %d flushing...", client->pid); + if (!drm_dev_enter(&xdna->ddev, &idx)) + return 0; + + mutex_lock(&xdna->dev_lock); + list_del_init(&client->node); + mutex_unlock(&xdna->dev_lock); + amdxdna_hwctx_remove_all(client); + + drm_dev_exit(idx); + return 0; +} + +static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_get_info *args = data; + int ret; + + if (!xdna->dev_info->ops->get_aie_info) + return -EOPNOTSUPP; + + XDNA_DBG(xdna, "Request parameter %u", args->param); + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->get_aie_info(client, args); + mutex_unlock(&xdna->dev_lock); + return ret; +} + +static int amdxdna_drm_set_state_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_set_state *args = data; + int ret; + + if (!xdna->dev_info->ops->set_aie_state) + return -EOPNOTSUPP; + + XDNA_DBG(xdna, "Request parameter %u", args->param); + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->set_aie_state(client, args); + mutex_unlock(&xdna->dev_lock); + + return ret; +} + +static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = { + /* Context */ + DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX, amdxdna_drm_create_hwctx_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_DESTROY_HWCTX, amdxdna_drm_destroy_hwctx_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_CONFIG_HWCTX, amdxdna_drm_config_hwctx_ioctl, 0), + /* BO */ + DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_BO, amdxdna_drm_create_bo_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_GET_BO_INFO, amdxdna_drm_get_bo_info_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_SYNC_BO, amdxdna_drm_sync_bo_ioctl, 0), + /* Execution */ + DRM_IOCTL_DEF_DRV(AMDXDNA_EXEC_CMD, amdxdna_drm_submit_cmd_ioctl, 0), + /* AIE hardware */ + DRM_IOCTL_DEF_DRV(AMDXDNA_GET_INFO, amdxdna_drm_get_info_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_SET_STATE, amdxdna_drm_set_state_ioctl, DRM_ROOT_ONLY), +}; + +static const struct file_operations amdxdna_fops = { + .owner = THIS_MODULE, + .open = accel_open, + .release = drm_release, + .flush = amdxdna_flush, + .unlocked_ioctl = drm_ioctl, + .compat_ioctl = drm_compat_ioctl, + .poll = drm_poll, + .read = drm_read, + .llseek = noop_llseek, + .mmap = drm_gem_mmap, + .fop_flags = FOP_UNSIGNED_OFFSET, +}; + +const struct drm_driver amdxdna_drm_drv = { + .driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL | + DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE, + .fops = &amdxdna_fops, + .name = "amdxdna_accel_driver", + .desc = "AMD XDNA DRM implementation", + .open = amdxdna_drm_open, + .postclose = amdxdna_drm_close, + .ioctls = amdxdna_drm_ioctls, + .num_ioctls = ARRAY_SIZE(amdxdna_drm_ioctls), + + .gem_create_object = amdxdna_gem_create_object_cb, +}; + +static const struct amdxdna_dev_info * +amdxdna_get_dev_info(struct pci_dev *pdev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(amdxdna_ids); i++) { + if (pdev->device == amdxdna_ids[i].device && + pdev->revision == amdxdna_ids[i].revision) + return amdxdna_ids[i].dev_info; + } + return NULL; +} + +static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct amdxdna_dev *xdna; + int ret; + + xdna = devm_drm_dev_alloc(dev, &amdxdna_drm_drv, typeof(*xdna), ddev); + if (IS_ERR(xdna)) + return PTR_ERR(xdna); + + xdna->dev_info = amdxdna_get_dev_info(pdev); + if (!xdna->dev_info) + return -ENODEV; + + drmm_mutex_init(&xdna->ddev, &xdna->dev_lock); + init_rwsem(&xdna->notifier_lock); + INIT_LIST_HEAD(&xdna->client_list); + pci_set_drvdata(pdev, xdna); + + if (IS_ENABLED(CONFIG_LOCKDEP)) { + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&xdna->notifier_lock); + fs_reclaim_release(GFP_KERNEL); + } + + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->init(xdna); + mutex_unlock(&xdna->dev_lock); + if (ret) { + XDNA_ERR(xdna, "Hardware init failed, ret %d", ret); + return ret; + } + + ret = amdxdna_sysfs_init(xdna); + if (ret) { + XDNA_ERR(xdna, "Create amdxdna attrs failed: %d", ret); + goto failed_dev_fini; + } + + pm_runtime_set_autosuspend_delay(dev, AMDXDNA_AUTOSUSPEND_DELAY); + pm_runtime_use_autosuspend(dev); + pm_runtime_allow(dev); + + ret = drm_dev_register(&xdna->ddev, 0); + if (ret) { + XDNA_ERR(xdna, "DRM register failed, ret %d", ret); + pm_runtime_forbid(dev); + goto failed_sysfs_fini; + } + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + return 0; + +failed_sysfs_fini: + amdxdna_sysfs_fini(xdna); +failed_dev_fini: + mutex_lock(&xdna->dev_lock); + xdna->dev_info->ops->fini(xdna); + mutex_unlock(&xdna->dev_lock); + return ret; +} + +static void amdxdna_remove(struct pci_dev *pdev) +{ + struct amdxdna_dev *xdna = pci_get_drvdata(pdev); + struct device *dev = &pdev->dev; + struct amdxdna_client *client; + + pm_runtime_get_noresume(dev); + pm_runtime_forbid(dev); + + drm_dev_unplug(&xdna->ddev); + amdxdna_sysfs_fini(xdna); + + mutex_lock(&xdna->dev_lock); + client = list_first_entry_or_null(&xdna->client_list, + struct amdxdna_client, node); + while (client) { + list_del_init(&client->node); + mutex_unlock(&xdna->dev_lock); + + amdxdna_hwctx_remove_all(client); + + mutex_lock(&xdna->dev_lock); + client = list_first_entry_or_null(&xdna->client_list, + struct amdxdna_client, node); + } + + xdna->dev_info->ops->fini(xdna); + mutex_unlock(&xdna->dev_lock); +} + +static int amdxdna_dev_suspend_nolock(struct amdxdna_dev *xdna) +{ + if (xdna->dev_info->ops->suspend) + xdna->dev_info->ops->suspend(xdna); + + return 0; +} + +static int amdxdna_dev_resume_nolock(struct amdxdna_dev *xdna) +{ + if (xdna->dev_info->ops->resume) + return xdna->dev_info->ops->resume(xdna); + + return 0; +} + +static int amdxdna_pmops_suspend(struct device *dev) +{ + struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev)); + struct amdxdna_client *client; + + mutex_lock(&xdna->dev_lock); + list_for_each_entry(client, &xdna->client_list, node) + amdxdna_hwctx_suspend(client); + + amdxdna_dev_suspend_nolock(xdna); + mutex_unlock(&xdna->dev_lock); + + return 0; +} + +static int amdxdna_pmops_resume(struct device *dev) +{ + struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev)); + struct amdxdna_client *client; + int ret; + + XDNA_INFO(xdna, "firmware resuming..."); + mutex_lock(&xdna->dev_lock); + ret = amdxdna_dev_resume_nolock(xdna); + if (ret) { + XDNA_ERR(xdna, "resume NPU firmware failed"); + mutex_unlock(&xdna->dev_lock); + return ret; + } + + XDNA_INFO(xdna, "hardware context resuming..."); + list_for_each_entry(client, &xdna->client_list, node) + amdxdna_hwctx_resume(client); + mutex_unlock(&xdna->dev_lock); + + return 0; +} + +static int amdxdna_rpmops_suspend(struct device *dev) +{ + struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev)); + int ret; + + mutex_lock(&xdna->dev_lock); + ret = amdxdna_dev_suspend_nolock(xdna); + mutex_unlock(&xdna->dev_lock); + + XDNA_DBG(xdna, "Runtime suspend done ret: %d", ret); + return ret; +} + +static int amdxdna_rpmops_resume(struct device *dev) +{ + struct amdxdna_dev *xdna = pci_get_drvdata(to_pci_dev(dev)); + int ret; + + mutex_lock(&xdna->dev_lock); + ret = amdxdna_dev_resume_nolock(xdna); + mutex_unlock(&xdna->dev_lock); + + XDNA_DBG(xdna, "Runtime resume done ret: %d", ret); + return ret; +} + +static const struct dev_pm_ops amdxdna_pm_ops = { + SYSTEM_SLEEP_PM_OPS(amdxdna_pmops_suspend, amdxdna_pmops_resume) + RUNTIME_PM_OPS(amdxdna_rpmops_suspend, amdxdna_rpmops_resume, NULL) +}; + +static struct pci_driver amdxdna_pci_driver = { + .name = KBUILD_MODNAME, + .id_table = pci_ids, + .probe = amdxdna_probe, + .remove = amdxdna_remove, + .driver.pm = &amdxdna_pm_ops, +}; + +module_pci_driver(amdxdna_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("XRT Team <runtimeca39d@amd.com>"); +MODULE_DESCRIPTION("amdxdna driver"); diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h new file mode 100644 index 000000000000..37848a8d8031 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_PCI_DRV_H_ +#define _AMDXDNA_PCI_DRV_H_ + +#include <linux/xarray.h> + +#define XDNA_INFO(xdna, fmt, args...) drm_info(&(xdna)->ddev, fmt, ##args) +#define XDNA_WARN(xdna, fmt, args...) drm_warn(&(xdna)->ddev, "%s: "fmt, __func__, ##args) +#define XDNA_ERR(xdna, fmt, args...) drm_err(&(xdna)->ddev, "%s: "fmt, __func__, ##args) +#define XDNA_DBG(xdna, fmt, args...) drm_dbg(&(xdna)->ddev, fmt, ##args) +#define XDNA_INFO_ONCE(xdna, fmt, args...) drm_info_once(&(xdna)->ddev, fmt, ##args) + +#define XDNA_MBZ_DBG(xdna, ptr, sz) \ + ({ \ + int __i; \ + int __ret = 0; \ + u8 *__ptr = (u8 *)(ptr); \ + for (__i = 0; __i < (sz); __i++) { \ + if (__ptr[__i]) { \ + XDNA_DBG(xdna, "MBZ check failed"); \ + __ret = -EINVAL; \ + break; \ + } \ + } \ + __ret; \ + }) + +#define to_xdna_dev(drm_dev) \ + ((struct amdxdna_dev *)container_of(drm_dev, struct amdxdna_dev, ddev)) + +extern const struct drm_driver amdxdna_drm_drv; + +struct amdxdna_client; +struct amdxdna_dev; +struct amdxdna_drm_get_info; +struct amdxdna_drm_set_state; +struct amdxdna_gem_obj; +struct amdxdna_hwctx; +struct amdxdna_sched_job; + +/* + * struct amdxdna_dev_ops - Device hardware operation callbacks + */ +struct amdxdna_dev_ops { + int (*init)(struct amdxdna_dev *xdna); + void (*fini)(struct amdxdna_dev *xdna); + int (*resume)(struct amdxdna_dev *xdna); + void (*suspend)(struct amdxdna_dev *xdna); + int (*hwctx_init)(struct amdxdna_hwctx *hwctx); + void (*hwctx_fini)(struct amdxdna_hwctx *hwctx); + int (*hwctx_config)(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); + void (*hmm_invalidate)(struct amdxdna_gem_obj *abo, unsigned long cur_seq); + void (*hwctx_suspend)(struct amdxdna_hwctx *hwctx); + void (*hwctx_resume)(struct amdxdna_hwctx *hwctx); + int (*cmd_submit)(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq); + int (*get_aie_info)(struct amdxdna_client *client, struct amdxdna_drm_get_info *args); + int (*set_aie_state)(struct amdxdna_client *client, struct amdxdna_drm_set_state *args); +}; + +/* + * struct amdxdna_dev_info - Device hardware information + * Record device static information, like reg, mbox, PSP, SMU bar index + */ +struct amdxdna_dev_info { + int reg_bar; + int mbox_bar; + int sram_bar; + int psp_bar; + int smu_bar; + int device_type; + int first_col; + u32 dev_mem_buf_shift; + u64 dev_mem_base; + size_t dev_mem_size; + char *vbnv; + const struct amdxdna_dev_priv *dev_priv; + const struct amdxdna_dev_ops *ops; +}; + +struct amdxdna_fw_ver { + u32 major; + u32 minor; + u32 sub; + u32 build; +}; + +struct amdxdna_dev { + struct drm_device ddev; + struct amdxdna_dev_hdl *dev_handle; + const struct amdxdna_dev_info *dev_info; + void *xrs_hdl; + + struct mutex dev_lock; /* per device lock */ + struct list_head client_list; + struct amdxdna_fw_ver fw_ver; + struct rw_semaphore notifier_lock; /* for mmu notifier*/ +}; + +/* + * struct amdxdna_device_id - PCI device info + */ +struct amdxdna_device_id { + unsigned short device; + u8 revision; + const struct amdxdna_dev_info *dev_info; +}; + +/* + * struct amdxdna_client - amdxdna client + * A per fd data structure for managing context and other user process stuffs. + */ +struct amdxdna_client { + struct list_head node; + pid_t pid; + struct mutex hwctx_lock; /* protect hwctx */ + /* do NOT wait this srcu when hwctx_lock is held */ + struct srcu_struct hwctx_srcu; + struct xarray hwctx_xa; + u32 next_hwctxid; + struct amdxdna_dev *xdna; + struct drm_file *filp; + + struct mutex mm_lock; /* protect memory related */ + struct amdxdna_gem_obj *dev_heap; + + struct iommu_sva *sva; + int pasid; +}; + +#define amdxdna_for_each_hwctx(client, hwctx_id, entry) \ + xa_for_each(&(client)->hwctx_xa, hwctx_id, entry) + +/* Add device info below */ +extern const struct amdxdna_dev_info dev_npu1_info; +extern const struct amdxdna_dev_info dev_npu2_info; +extern const struct amdxdna_dev_info dev_npu4_info; +extern const struct amdxdna_dev_info dev_npu5_info; +extern const struct amdxdna_dev_info dev_npu6_info; + +int amdxdna_sysfs_init(struct amdxdna_dev *xdna); +void amdxdna_sysfs_fini(struct amdxdna_dev *xdna); + +#endif /* _AMDXDNA_PCI_DRV_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_sysfs.c b/drivers/accel/amdxdna/amdxdna_sysfs.c new file mode 100644 index 000000000000..f27e4ee960a0 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_sysfs.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_print.h> +#include <drm/gpu_scheduler.h> +#include <linux/types.h> + +#include "amdxdna_gem.h" +#include "amdxdna_pci_drv.h" + +static ssize_t vbnv_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct amdxdna_dev *xdna = dev_get_drvdata(dev); + + return sprintf(buf, "%s\n", xdna->dev_info->vbnv); +} +static DEVICE_ATTR_RO(vbnv); + +static ssize_t device_type_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct amdxdna_dev *xdna = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", xdna->dev_info->device_type); +} +static DEVICE_ATTR_RO(device_type); + +static ssize_t fw_version_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct amdxdna_dev *xdna = dev_get_drvdata(dev); + + return sprintf(buf, "%d.%d.%d.%d\n", xdna->fw_ver.major, + xdna->fw_ver.minor, xdna->fw_ver.sub, + xdna->fw_ver.build); +} +static DEVICE_ATTR_RO(fw_version); + +static struct attribute *amdxdna_attrs[] = { + &dev_attr_device_type.attr, + &dev_attr_vbnv.attr, + &dev_attr_fw_version.attr, + NULL, +}; + +static struct attribute_group amdxdna_attr_group = { + .attrs = amdxdna_attrs, +}; + +int amdxdna_sysfs_init(struct amdxdna_dev *xdna) +{ + int ret; + + ret = sysfs_create_group(&xdna->ddev.dev->kobj, &amdxdna_attr_group); + if (ret) + XDNA_ERR(xdna, "Create attr group failed"); + + return ret; +} + +void amdxdna_sysfs_fini(struct amdxdna_dev *xdna) +{ + sysfs_remove_group(&xdna->ddev.dev->kobj, &amdxdna_attr_group); +} diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c new file mode 100644 index 000000000000..e4f6dac7d00f --- /dev/null +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/gpu_scheduler.h> +#include <linux/sizes.h> + +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +/* Address definition from NPU1 docs */ +#define MPNPU_PUB_SEC_INTR 0x3010090 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010094 +#define MPNPU_PUB_SCRATCH2 0x30100A0 +#define MPNPU_PUB_SCRATCH3 0x30100A4 +#define MPNPU_PUB_SCRATCH4 0x30100A8 +#define MPNPU_PUB_SCRATCH5 0x30100AC +#define MPNPU_PUB_SCRATCH6 0x30100B0 +#define MPNPU_PUB_SCRATCH7 0x30100B4 +#define MPNPU_PUB_SCRATCH9 0x30100BC + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x30A0000 +#define MPNPU_SRAM_X2I_MAILBOX_1 0x30A2000 +#define MPNPU_SRAM_I2X_MAILBOX_15 0x30BF000 + +#define MPNPU_APERTURE0_BASE 0x3000000 +#define MPNPU_APERTURE1_BASE 0x3080000 +#define MPNPU_APERTURE2_BASE 0x30C0000 + +/* PCIe BAR Index for NPU1 */ +#define NPU1_REG_BAR_INDEX 0 +#define NPU1_MBOX_BAR_INDEX 4 +#define NPU1_PSP_BAR_INDEX 0 +#define NPU1_SMU_BAR_INDEX 0 +#define NPU1_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU1_REG_BAR_BASE MPNPU_APERTURE0_BASE +#define NPU1_MBOX_BAR_BASE MPNPU_APERTURE2_BASE +#define NPU1_PSP_BAR_BASE MPNPU_APERTURE0_BASE +#define NPU1_SMU_BAR_BASE MPNPU_APERTURE0_BASE +#define NPU1_SRAM_BAR_BASE MPNPU_APERTURE1_BASE + +const struct rt_config npu1_default_rt_cfg[] = { + { 2, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */ + { 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */ + { 0 }, +}; + +const struct dpm_clk_freq npu1_dpm_clk_table[] = { + {400, 800}, + {600, 1024}, + {600, 1024}, + {600, 1024}, + {600, 1024}, + {720, 1309}, + {720, 1309}, + {847, 1600}, + { 0 } +}; + +static const struct amdxdna_dev_priv npu1_dev_priv = { + .fw_path = "amdnpu/1502_00/npu.sbin", + .protocol_major = 0x5, + .protocol_minor = 0x7, + .rt_config = npu1_default_rt_cfg, + .dpm_clk_tbl = npu1_dpm_clk_table, + .col_align = COL_ALIGN_NONE, + .mbox_dev_addr = NPU1_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU1_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU1_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU1_SRAM, MPNPU_SRAM_I2X_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU1_PSP, MPNPU_PUB_SCRATCH2), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU1_PSP, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU1_PSP, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU1_PSP, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU1_PSP, MPNPU_PUB_SEC_INTR), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU1_PSP, MPNPU_PUB_SCRATCH2), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU1_PSP, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU1_SMU, MPNPU_PUB_SCRATCH5), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU1_SMU, MPNPU_PUB_SCRATCH7), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU1_SMU, MPNPU_PUB_PWRMGMT_INTR), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU1_SMU, MPNPU_PUB_SCRATCH6), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU1_SMU, MPNPU_PUB_SCRATCH7), + }, + .hw_ops = { + .set_dpm = npu1_set_dpm, + }, +}; + +const struct amdxdna_dev_info dev_npu1_info = { + .reg_bar = NPU1_REG_BAR_INDEX, + .mbox_bar = NPU1_MBOX_BAR_INDEX, + .sram_bar = NPU1_SRAM_BAR_INDEX, + .psp_bar = NPU1_PSP_BAR_INDEX, + .smu_bar = NPU1_SMU_BAR_INDEX, + .first_col = 1, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu1", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu1_dev_priv, + .ops = &aie2_ops, +}; diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/amdxdna/npu2_regs.c new file mode 100644 index 000000000000..a081cac75ee0 --- /dev/null +++ b/drivers/accel/amdxdna/npu2_regs.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/gpu_scheduler.h> +#include <linux/sizes.h> + +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU2 */ +#define NPU2_REG_BAR_INDEX 0 +#define NPU2_MBOX_BAR_INDEX 0 +#define NPU2_PSP_BAR_INDEX 4 +#define NPU2_SMU_BAR_INDEX 5 +#define NPU2_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU2_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU2_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU2_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU2_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU2_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +static const struct amdxdna_dev_priv npu2_dev_priv = { + .fw_path = "amdnpu/17f0_00/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 0x6, + .rt_config = npu4_default_rt_cfg, + .dpm_clk_tbl = npu4_dpm_clk_table, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU2_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU2_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU2_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU2_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU2_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU2_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU2_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU2_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU2_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU2_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU2_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU2_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU2_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU2_SMU, MP1_C2PMSG_60), + }, + .hw_ops = { + .set_dpm = npu4_set_dpm, + }, +}; + +const struct amdxdna_dev_info dev_npu2_info = { + .reg_bar = NPU2_REG_BAR_INDEX, + .mbox_bar = NPU2_MBOX_BAR_INDEX, + .sram_bar = NPU2_SRAM_BAR_INDEX, + .psp_bar = NPU2_PSP_BAR_INDEX, + .smu_bar = NPU2_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu2", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu2_dev_priv, + .ops = &aie2_ops, /* NPU2 can share NPU1's callback */ +}; diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c new file mode 100644 index 000000000000..9f2e33182ec6 --- /dev/null +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/gpu_scheduler.h> +#include <linux/sizes.h> + +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU4 */ +#define NPU4_REG_BAR_INDEX 0 +#define NPU4_MBOX_BAR_INDEX 0 +#define NPU4_PSP_BAR_INDEX 4 +#define NPU4_SMU_BAR_INDEX 5 +#define NPU4_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU4_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU4_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU4_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU4_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU4_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +const struct rt_config npu4_default_rt_cfg[] = { + { 5, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */ + { 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */ + { 2, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */ + { 3, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */ + { 4, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */ + { 0 }, +}; + +const struct dpm_clk_freq npu4_dpm_clk_table[] = { + {396, 792}, + {600, 1056}, + {792, 1152}, + {975, 1267}, + {975, 1267}, + {1056, 1408}, + {1152, 1584}, + {1267, 1800}, + { 0 } +}; + +static const struct amdxdna_dev_priv npu4_dev_priv = { + .fw_path = "amdnpu/17f0_10/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 12, + .rt_config = npu4_default_rt_cfg, + .dpm_clk_tbl = npu4_dpm_clk_table, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU4_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU4_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU4_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU4_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU4_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU4_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU4_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU4_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU4_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU4_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU4_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU4_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU4_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU4_SMU, MP1_C2PMSG_60), + }, + .hw_ops = { + .set_dpm = npu4_set_dpm, + }, +}; + +const struct amdxdna_dev_info dev_npu4_info = { + .reg_bar = NPU4_REG_BAR_INDEX, + .mbox_bar = NPU4_MBOX_BAR_INDEX, + .sram_bar = NPU4_SRAM_BAR_INDEX, + .psp_bar = NPU4_PSP_BAR_INDEX, + .smu_bar = NPU4_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu4", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu4_dev_priv, + .ops = &aie2_ops, /* NPU4 can share NPU1's callback */ +}; diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c new file mode 100644 index 000000000000..5f1cf83461c4 --- /dev/null +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/gpu_scheduler.h> +#include <linux/sizes.h> + +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU5 */ +#define NPU5_REG_BAR_INDEX 0 +#define NPU5_MBOX_BAR_INDEX 0 +#define NPU5_PSP_BAR_INDEX 4 +#define NPU5_SMU_BAR_INDEX 5 +#define NPU5_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU5_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU5_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU5_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU5_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU5_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +static const struct amdxdna_dev_priv npu5_dev_priv = { + .fw_path = "amdnpu/17f0_11/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 12, + .rt_config = npu4_default_rt_cfg, + .dpm_clk_tbl = npu4_dpm_clk_table, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU5_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU5_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU5_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU5_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU5_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU5_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU5_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU5_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU5_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU5_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU5_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU5_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU5_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU5_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU5_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU5_SMU, MP1_C2PMSG_60), + }, + .hw_ops = { + .set_dpm = npu4_set_dpm, + }, +}; + +const struct amdxdna_dev_info dev_npu5_info = { + .reg_bar = NPU5_REG_BAR_INDEX, + .mbox_bar = NPU5_MBOX_BAR_INDEX, + .sram_bar = NPU5_SRAM_BAR_INDEX, + .psp_bar = NPU5_PSP_BAR_INDEX, + .smu_bar = NPU5_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu5", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu5_dev_priv, + .ops = &aie2_ops, +}; diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/amdxdna/npu6_regs.c new file mode 100644 index 000000000000..94a7005685a7 --- /dev/null +++ b/drivers/accel/amdxdna/npu6_regs.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include <drm/amdxdna_accel.h> +#include <drm/drm_device.h> +#include <drm/gpu_scheduler.h> +#include <linux/sizes.h> + +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU6 */ +#define NPU6_REG_BAR_INDEX 0 +#define NPU6_MBOX_BAR_INDEX 0 +#define NPU6_PSP_BAR_INDEX 4 +#define NPU6_SMU_BAR_INDEX 5 +#define NPU6_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU6_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU6_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU6_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU6_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU6_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +static const struct amdxdna_dev_priv npu6_dev_priv = { + .fw_path = "amdnpu/17f0_10/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 12, + .rt_config = npu4_default_rt_cfg, + .dpm_clk_tbl = npu4_dpm_clk_table, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU6_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU6_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU6_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU6_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU6_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU6_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU6_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU6_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU6_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU6_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU6_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU6_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU6_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU6_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU6_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU6_SMU, MP1_C2PMSG_60), + }, + .hw_ops = { + .set_dpm = npu4_set_dpm, + }, + +}; + +const struct amdxdna_dev_info dev_npu6_info = { + .reg_bar = NPU6_REG_BAR_INDEX, + .mbox_bar = NPU6_MBOX_BAR_INDEX, + .sram_bar = NPU6_SRAM_BAR_INDEX, + .psp_bar = NPU6_PSP_BAR_INDEX, + .smu_bar = NPU6_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu6", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu6_dev_priv, + .ops = &aie2_ops, +}; diff --git a/drivers/accel/habanalabs/common/command_submission.c b/drivers/accel/habanalabs/common/command_submission.c index 59823e3c3bf7..dee487724918 100644 --- a/drivers/accel/habanalabs/common/command_submission.c +++ b/drivers/accel/habanalabs/common/command_submission.c @@ -2586,7 +2586,7 @@ int hl_cs_ioctl(struct drm_device *ddev, void *data, struct drm_file *file_priv) cs_seq = args->in.seq; timeout = flags & HL_CS_FLAGS_CUSTOM_TIMEOUT - ? msecs_to_jiffies(args->in.timeout * 1000) + ? secs_to_jiffies(args->in.timeout) : hpriv->hdev->timeout_jiffies; switch (cs_type) { diff --git a/drivers/accel/habanalabs/common/context.c b/drivers/accel/habanalabs/common/context.c index b83141f58319..9f212b17611a 100644 --- a/drivers/accel/habanalabs/common/context.c +++ b/drivers/accel/habanalabs/common/context.c @@ -199,7 +199,6 @@ out_err: int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx) { - char task_comm[TASK_COMM_LEN]; int rc = 0, i; ctx->hdev = hdev; @@ -272,7 +271,7 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx) mutex_init(&ctx->ts_reg_lock); dev_dbg(hdev->dev, "create user context, comm=\"%s\", asid=%u\n", - get_task_comm(task_comm, current), ctx->asid); + current->comm, ctx->asid); } return 0; diff --git a/drivers/accel/habanalabs/common/debugfs.c b/drivers/accel/habanalabs/common/debugfs.c index ca7677293a55..4b391807e5f2 100644 --- a/drivers/accel/habanalabs/common/debugfs.c +++ b/drivers/accel/habanalabs/common/debugfs.c @@ -1403,7 +1403,7 @@ static ssize_t hl_timeout_locked_write(struct file *f, const char __user *buf, return rc; if (value) - hdev->timeout_jiffies = msecs_to_jiffies(value * 1000); + hdev->timeout_jiffies = secs_to_jiffies(value); else hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT; diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index e0cf3b4343bb..68eebed3b050 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -817,7 +817,7 @@ static void device_hard_reset_pending(struct work_struct *work) } queue_delayed_work(hdev->reset_wq, &device_reset_work->reset_work, - msecs_to_jiffies(HL_PENDING_RESET_PER_SEC * 1000)); + secs_to_jiffies(HL_PENDING_RESET_PER_SEC)); } } @@ -2091,7 +2091,7 @@ int hl_device_cond_reset(struct hl_device *hdev, u32 flags, u64 event_mask) dev_dbg(hdev->dev, "Device is going to be hard-reset in %u sec unless being released\n", hdev->device_release_watchdog_timeout_sec); schedule_delayed_work(&hdev->device_release_watchdog_work.reset_work, - msecs_to_jiffies(hdev->device_release_watchdog_timeout_sec * 1000)); + secs_to_jiffies(hdev->device_release_watchdog_timeout_sec)); hdev->reset_info.watchdog_active = 1; out: spin_unlock(&hdev->reset_info.lock); diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c index 708dfd10f39c..0035748f3228 100644 --- a/drivers/accel/habanalabs/common/habanalabs_drv.c +++ b/drivers/accel/habanalabs/common/habanalabs_drv.c @@ -101,7 +101,6 @@ static const struct drm_driver hl_driver = { .major = LINUX_VERSION_MAJOR, .minor = LINUX_VERSION_PATCHLEVEL, .patchlevel = LINUX_VERSION_SUBLEVEL, - .date = "20190505", .fops = &hl_fops, .open = hl_device_open, @@ -362,8 +361,7 @@ static void fixup_device_params_per_asic(struct hl_device *hdev, int timeout) * a different default timeout for Gaudi */ if (timeout == HL_DEFAULT_TIMEOUT_LOCKED) - hdev->timeout_jiffies = msecs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED * - MSEC_PER_SEC); + hdev->timeout_jiffies = secs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED); hdev->reset_upon_device_release = 0; break; @@ -388,7 +386,7 @@ static int fixup_device_params(struct hl_device *hdev) hdev->fw_comms_poll_interval_usec = HL_FW_STATUS_POLL_INTERVAL_USEC; if (tmp_timeout) - hdev->timeout_jiffies = msecs_to_jiffies(tmp_timeout * MSEC_PER_SEC); + hdev->timeout_jiffies = secs_to_jiffies(tmp_timeout); else hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT; diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c index 1dd6e23172ca..8729a0c57d78 100644 --- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c @@ -1279,13 +1279,10 @@ static long _hl_ioctl(struct hl_fpriv *hpriv, unsigned int cmd, unsigned long ar retcode = -EFAULT; out_err: - if (retcode) { - char task_comm[TASK_COMM_LEN]; - + if (retcode) dev_dbg_ratelimited(dev, "error in ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n", - task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr); - } + task_pid_nr(current), current->comm, cmd, nr); if (kdata != stack_kdata) kfree(kdata); @@ -1308,11 +1305,9 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg) if (nr == _IOC_NR(DRM_IOCTL_HL_INFO)) { ioctl = &hl_ioctls_control[nr - HL_COMMAND_START]; } else { - char task_comm[TASK_COMM_LEN]; - dev_dbg_ratelimited(hdev->dev_ctrl, "invalid ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n", - task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr); + task_pid_nr(current), current->comm, cmd, nr); return -ENOTTY; } diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c index e9f8ccc0bbf9..9d58efa2ff38 100644 --- a/drivers/accel/habanalabs/common/sysfs.c +++ b/drivers/accel/habanalabs/common/sysfs.c @@ -368,7 +368,7 @@ out: } static ssize_t eeprom_read_handler(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t offset, + const struct bin_attribute *attr, char *buf, loff_t offset, size_t max_size) { struct device *dev = kobj_to_dev(kobj); @@ -443,10 +443,10 @@ static DEVICE_ATTR_RO(security_enabled); static DEVICE_ATTR_RO(module_id); static DEVICE_ATTR_RO(parent_device); -static struct bin_attribute bin_attr_eeprom = { +static const struct bin_attribute bin_attr_eeprom = { .attr = {.name = "eeprom", .mode = (0444)}, .size = PAGE_SIZE, - .read = eeprom_read_handler + .read_new = eeprom_read_handler }; static struct attribute *hl_dev_attrs[] = { @@ -472,14 +472,14 @@ static struct attribute *hl_dev_attrs[] = { NULL, }; -static struct bin_attribute *hl_dev_bin_attrs[] = { +static const struct bin_attribute *const hl_dev_bin_attrs[] = { &bin_attr_eeprom, NULL }; static struct attribute_group hl_dev_attr_group = { .attrs = hl_dev_attrs, - .bin_attrs = hl_dev_bin_attrs, + .bin_attrs_new = hl_dev_bin_attrs, }; static struct attribute_group hl_dev_clks_attr_group; diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c index 8180b95ed69d..cd24ccd20ba6 100644 --- a/drivers/accel/ivpu/ivpu_debugfs.c +++ b/drivers/accel/ivpu/ivpu_debugfs.c @@ -4,6 +4,7 @@ */ #include <linux/debugfs.h> +#include <linux/fault-inject.h> #include <drm/drm_debugfs.h> #include <drm/drm_file.h> @@ -331,7 +332,7 @@ ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t si return -EINVAL; ret = ivpu_rpm_get(vdev); - if (ret) + if (ret < 0) return ret; ivpu_pm_trigger_recovery(vdev, "debugfs"); @@ -382,7 +383,7 @@ static int dct_active_set(void *data, u64 active_percent) return -EINVAL; ret = ivpu_rpm_get(vdev); - if (ret) + if (ret < 0) return ret; if (active_percent) @@ -397,6 +398,88 @@ static int dct_active_set(void *data, u64 active_percent) DEFINE_DEBUGFS_ATTRIBUTE(ivpu_dct_fops, dct_active_get, dct_active_set, "%llu\n"); +static int priority_bands_show(struct seq_file *s, void *v) +{ + struct ivpu_device *vdev = s->private; + struct ivpu_hw_info *hw = vdev->hw; + + for (int band = VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE; + band < VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT; band++) { + switch (band) { + case VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE: + seq_puts(s, "Idle: "); + break; + + case VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL: + seq_puts(s, "Normal: "); + break; + + case VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS: + seq_puts(s, "Focus: "); + break; + + case VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME: + seq_puts(s, "Realtime: "); + break; + } + + seq_printf(s, "grace_period %9u process_grace_period %9u process_quantum %9u\n", + hw->hws.grace_period[band], hw->hws.process_grace_period[band], + hw->hws.process_quantum[band]); + } + + return 0; +} + +static int priority_bands_fops_open(struct inode *inode, struct file *file) +{ + return single_open(file, priority_bands_show, inode->i_private); +} + +static ssize_t +priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos) +{ + struct seq_file *s = file->private_data; + struct ivpu_device *vdev = s->private; + char buf[64]; + u32 grace_period; + u32 process_grace_period; + u32 process_quantum; + u32 band; + int ret; + + if (size >= sizeof(buf)) + return -EINVAL; + + ret = simple_write_to_buffer(buf, sizeof(buf) - 1, pos, user_buf, size); + if (ret < 0) + return ret; + + buf[ret] = '\0'; + ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period, + &process_quantum); + if (ret != 4) + return -EINVAL; + + if (band >= VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT) + return -EINVAL; + + vdev->hw->hws.grace_period[band] = grace_period; + vdev->hw->hws.process_grace_period[band] = process_grace_period; + vdev->hw->hws.process_quantum[band] = process_quantum; + + return size; +} + +static const struct file_operations ivpu_hws_priority_bands_fops = { + .owner = THIS_MODULE, + .open = priority_bands_fops_open, + .write = priority_bands_fops_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + void ivpu_debugfs_init(struct ivpu_device *vdev) { struct dentry *debugfs_root = vdev->drm.debugfs_root; @@ -419,6 +502,8 @@ void ivpu_debugfs_init(struct ivpu_device *vdev) &fw_trace_hw_comp_mask_fops); debugfs_create_file("fw_trace_level", 0200, debugfs_root, vdev, &fw_trace_level_fops); + debugfs_create_file("hws_priority_bands", 0200, debugfs_root, vdev, + &ivpu_hws_priority_bands_fops); debugfs_create_file("reset_engine", 0200, debugfs_root, vdev, &ivpu_reset_engine_fops); @@ -430,4 +515,8 @@ void ivpu_debugfs_init(struct ivpu_device *vdev) debugfs_root, vdev, &fw_profiling_freq_fops); debugfs_create_file("dct", 0644, debugfs_root, vdev, &ivpu_dct_fops); } + +#ifdef CONFIG_FAULT_INJECTION + fault_create_debugfs_attr("fail_hw", debugfs_root, &ivpu_hw_failure); +#endif } diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 0c4a82271c26..eff1d3ca075f 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -1,12 +1,13 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #include <linux/firmware.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/pm_runtime.h> +#include <linux/workqueue.h> #include <generated/utsrelease.h> #include <drm/drm_accel.h> @@ -36,8 +37,6 @@ #define DRIVER_VERSION_STR "1.0.0 " UTS_RELEASE #endif -static struct lock_class_key submitted_jobs_xa_lock_class_key; - int ivpu_dbg_mask; module_param_named(dbg_mask, ivpu_dbg_mask, int, 0644); MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros."); @@ -128,20 +127,18 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link) kref_put(&file_priv->ref, file_priv_release); } -static int ivpu_get_capabilities(struct ivpu_device *vdev, struct drm_ivpu_param *args) +bool ivpu_is_capable(struct ivpu_device *vdev, u32 capability) { - switch (args->index) { + switch (capability) { case DRM_IVPU_CAP_METRIC_STREAMER: - args->value = 1; - break; + return true; case DRM_IVPU_CAP_DMA_MEMORY_RANGE: - args->value = 1; - break; + return true; + case DRM_IVPU_CAP_MANAGE_CMDQ: + return vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW; default: - return -EINVAL; + return false; } - - return 0; } static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file) @@ -167,7 +164,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f args->value = vdev->platform; break; case DRM_IVPU_PARAM_CORE_CLOCK_RATE: - args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio); + args->value = ivpu_hw_dpu_max_freq_get(vdev); break; case DRM_IVPU_PARAM_NUM_CONTEXTS: args->value = ivpu_get_context_count(vdev); @@ -201,7 +198,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f args->value = vdev->hw->sku; break; case DRM_IVPU_PARAM_CAPABILITIES: - ret = ivpu_get_capabilities(vdev, args); + args->value = ivpu_is_capable(vdev, args->index); break; default: ret = -EINVAL; @@ -310,6 +307,9 @@ static const struct drm_ioctl_desc ivpu_drm_ioctls[] = { DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_GET_DATA, ivpu_ms_get_data_ioctl, 0), DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_STOP, ivpu_ms_stop_ioctl, 0), DRM_IOCTL_DEF_DRV(IVPU_METRIC_STREAMER_GET_INFO, ivpu_ms_get_info_ioctl, 0), + DRM_IOCTL_DEF_DRV(IVPU_CMDQ_CREATE, ivpu_cmdq_create_ioctl, 0), + DRM_IOCTL_DEF_DRV(IVPU_CMDQ_DESTROY, ivpu_cmdq_destroy_ioctl, 0), + DRM_IOCTL_DEF_DRV(IVPU_CMDQ_SUBMIT, ivpu_cmdq_submit_ioctl, 0), }; static int ivpu_wait_for_ready(struct ivpu_device *vdev) @@ -421,6 +421,9 @@ void ivpu_prepare_for_reset(struct ivpu_device *vdev) { ivpu_hw_irq_disable(vdev); disable_irq(vdev->irq); + flush_work(&vdev->irq_ipc_work); + flush_work(&vdev->irq_dct_work); + flush_work(&vdev->context_abort_work); ivpu_ipc_disable(vdev); ivpu_mmu_disable(vdev); } @@ -453,7 +456,7 @@ static const struct drm_driver driver = { .postclose = ivpu_postclose, .gem_create_object = ivpu_gem_create_object, - .gem_prime_import_sg_table = drm_gem_shmem_prime_import_sg_table, + .gem_prime_import = ivpu_gem_prime_import, .ioctls = ivpu_drm_ioctls, .num_ioctls = ARRAY_SIZE(ivpu_drm_ioctls), @@ -462,65 +465,9 @@ static const struct drm_driver driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, -#ifdef DRIVER_DATE - .date = DRIVER_DATE, - .major = DRIVER_MAJOR, - .minor = DRIVER_MINOR, - .patchlevel = DRIVER_PATCHLEVEL, -#else - .date = UTS_RELEASE, .major = 1, -#endif }; -static void ivpu_context_abort_invalid(struct ivpu_device *vdev) -{ - struct ivpu_file_priv *file_priv; - unsigned long ctx_id; - - mutex_lock(&vdev->context_list_lock); - - xa_for_each(&vdev->context_xa, ctx_id, file_priv) { - if (!file_priv->has_mmu_faults || file_priv->aborted) - continue; - - mutex_lock(&file_priv->lock); - ivpu_context_abort_locked(file_priv); - file_priv->aborted = true; - mutex_unlock(&file_priv->lock); - } - - mutex_unlock(&vdev->context_list_lock); -} - -static irqreturn_t ivpu_irq_thread_handler(int irq, void *arg) -{ - struct ivpu_device *vdev = arg; - u8 irq_src; - - if (kfifo_is_empty(&vdev->hw->irq.fifo)) - return IRQ_NONE; - - while (kfifo_get(&vdev->hw->irq.fifo, &irq_src)) { - switch (irq_src) { - case IVPU_HW_IRQ_SRC_IPC: - ivpu_ipc_irq_thread_handler(vdev); - break; - case IVPU_HW_IRQ_SRC_MMU_EVTQ: - ivpu_context_abort_invalid(vdev); - break; - case IVPU_HW_IRQ_SRC_DCT: - ivpu_pm_dct_irq_thread_handler(vdev); - break; - default: - ivpu_err_ratelimited(vdev, "Unknown IRQ source: %u\n", irq_src); - break; - } - } - - return IRQ_HANDLED; -} - static int ivpu_irq_init(struct ivpu_device *vdev) { struct pci_dev *pdev = to_pci_dev(vdev->drm.dev); @@ -532,12 +479,16 @@ static int ivpu_irq_init(struct ivpu_device *vdev) return ret; } + INIT_WORK(&vdev->irq_ipc_work, ivpu_ipc_irq_work_fn); + INIT_WORK(&vdev->irq_dct_work, ivpu_pm_irq_dct_work_fn); + INIT_WORK(&vdev->context_abort_work, ivpu_context_abort_work_fn); + ivpu_irq_handlers_init(vdev); vdev->irq = pci_irq_vector(pdev, 0); - ret = devm_request_threaded_irq(vdev->drm.dev, vdev->irq, ivpu_hw_irq_handler, - ivpu_irq_thread_handler, IRQF_NO_AUTOEN, DRIVER_NAME, vdev); + ret = devm_request_irq(vdev->drm.dev, vdev->irq, ivpu_hw_irq_handler, + IRQF_NO_AUTOEN, DRIVER_NAME, vdev); if (ret) ivpu_err(vdev, "Failed to request an IRQ %d\n", ret); @@ -625,7 +576,6 @@ static int ivpu_dev_init(struct ivpu_device *vdev) xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1); xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1); - lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key); INIT_LIST_HEAD(&vdev->bo_list); vdev->db_limit.min = IVPU_MIN_DB; @@ -635,6 +585,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev) if (ret) goto err_xa_destroy; + ret = drmm_mutex_init(&vdev->drm, &vdev->submitted_jobs_lock); + if (ret) + goto err_xa_destroy; + ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock); if (ret) goto err_xa_destroy; diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 3fdff3f6cffd..92753effb1c9 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -58,6 +58,7 @@ #define IVPU_PLATFORM_SILICON 0 #define IVPU_PLATFORM_SIMICS 2 #define IVPU_PLATFORM_FPGA 3 +#define IVPU_PLATFORM_HSLE 4 #define IVPU_PLATFORM_INVALID 8 #define IVPU_SCHED_MODE_AUTO -1 @@ -110,6 +111,7 @@ struct ivpu_wa_table { bool disable_clock_relinquish; bool disable_d0i3_msg; bool wp0_during_power_up; + bool disable_d0i2; }; struct ivpu_hw_info; @@ -142,9 +144,14 @@ struct ivpu_device { struct xa_limit db_limit; u32 db_next; + struct work_struct irq_ipc_work; + struct work_struct irq_dct_work; + struct work_struct context_abort_work; + struct mutex bo_list_lock; /* Protects bo_list */ struct list_head bo_list; + struct mutex submitted_jobs_lock; /* Protects submitted_jobs */ struct xarray submitted_jobs_xa; struct ivpu_ipc_consumer job_done_consumer; @@ -200,6 +207,9 @@ extern bool ivpu_force_snoop; #define IVPU_TEST_MODE_MIP_DISABLE BIT(6) #define IVPU_TEST_MODE_DISABLE_TIMEOUTS BIT(8) #define IVPU_TEST_MODE_TURBO BIT(9) +#define IVPU_TEST_MODE_CLK_RELINQ_DISABLE BIT(10) +#define IVPU_TEST_MODE_CLK_RELINQ_ENABLE BIT(11) +#define IVPU_TEST_MODE_D0I2_DISABLE BIT(12) extern int ivpu_test_mode; struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv); @@ -208,6 +218,7 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link); int ivpu_boot(struct ivpu_device *vdev); int ivpu_shutdown(struct ivpu_device *vdev); void ivpu_prepare_for_reset(struct ivpu_device *vdev); +bool ivpu_is_capable(struct ivpu_device *vdev, u32 capability); static inline u8 ivpu_revision(struct ivpu_device *vdev) { @@ -282,7 +293,8 @@ static inline bool ivpu_is_simics(struct ivpu_device *vdev) static inline bool ivpu_is_fpga(struct ivpu_device *vdev) { - return ivpu_get_platform(vdev) == IVPU_PLATFORM_FPGA; + return ivpu_get_platform(vdev) == IVPU_PLATFORM_FPGA || + ivpu_get_platform(vdev) == IVPU_PLATFORM_HSLE; } static inline bool ivpu_is_force_snoop_enabled(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index 6037ec0b3096..9db741695401 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #include <linux/firmware.h> @@ -55,18 +55,18 @@ static struct { int gen; const char *name; } fw_names[] = { - { IVPU_HW_IP_37XX, "vpu_37xx.bin" }, + { IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v1.bin" }, { IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v0.0.bin" }, - { IVPU_HW_IP_40XX, "vpu_40xx.bin" }, + { IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v1.bin" }, { IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v0.0.bin" }, - { IVPU_HW_IP_50XX, "vpu_50xx.bin" }, + { IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v1.bin" }, { IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v0.0.bin" }, }; /* Production fw_names from the table above */ -MODULE_FIRMWARE("intel/vpu/vpu_37xx_v0.0.bin"); -MODULE_FIRMWARE("intel/vpu/vpu_40xx_v0.0.bin"); -MODULE_FIRMWARE("intel/vpu/vpu_50xx_v0.0.bin"); +MODULE_FIRMWARE("intel/vpu/vpu_37xx_v1.bin"); +MODULE_FIRMWARE("intel/vpu/vpu_40xx_v1.bin"); +MODULE_FIRMWARE("intel/vpu/vpu_50xx_v1.bin"); static int ivpu_fw_request(struct ivpu_device *vdev) { @@ -145,7 +145,10 @@ ivpu_fw_sched_mode_select(struct ivpu_device *vdev, const struct vpu_firmware_he if (ivpu_sched_mode != IVPU_SCHED_MODE_AUTO) return ivpu_sched_mode; - return VPU_SCHEDULING_MODE_OS; + if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, JSM, 3, 24)) + return VPU_SCHEDULING_MODE_OS; + + return VPU_SCHEDULING_MODE_HW; } static int ivpu_fw_parse(struct ivpu_device *vdev) @@ -230,10 +233,20 @@ static int ivpu_fw_parse(struct ivpu_device *vdev) fw->dvfs_mode = 0; fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr); - fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size; - fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size; ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS"); + if (fw_hdr->preemption_buffer_1_max_size) + fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_max_size; + else + fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size; + + if (fw_hdr->preemption_buffer_2_max_size) + fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_max_size; + else + fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size; + ivpu_dbg(vdev, FW_BOOT, "Preemption buffer sizes: primary %u, secondary %u\n", + fw->primary_preempt_buf_size, fw->secondary_preempt_buf_size); + if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address, fw_hdr->ro_section_size, fw_hdr->image_load_address, @@ -531,6 +544,8 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_ boot_params->d0i3_entry_vpu_ts); ivpu_dbg(vdev, FW_BOOT, "boot_params.system_time_us = %llu\n", boot_params->system_time_us); + ivpu_dbg(vdev, FW_BOOT, "boot_params.power_profile = 0x%x\n", + boot_params->power_profile); } void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params) @@ -561,7 +576,6 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->magic = VPU_BOOT_PARAMS_MAGIC; boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number; - boot_params->frequency = ivpu_hw_pll_freq_get(vdev); /* * This param is a debug firmware feature. It switches default clock @@ -631,6 +645,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->d0i3_delayed_entry = 1; boot_params->d0i3_residency_time_us = 0; boot_params->d0i3_entry_vpu_ts = 0; + if (IVPU_WA(disable_d0i2)) + boot_params->power_profile |= BIT(1); boot_params->system_time_us = ktime_to_us(ktime_get_real()); wmb(); /* Flush WC buffers after writing bootparams */ diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index 16178054e629..248bfebeaa22 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -20,17 +20,29 @@ #include "ivpu_mmu.h" #include "ivpu_mmu_context.h" +MODULE_IMPORT_NS("DMA_BUF"); + static const struct drm_gem_object_funcs ivpu_gem_funcs; static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action) { ivpu_dbg(vdev, BO, "%6s: bo %8p vpu_addr %9llx size %8zu ctx %d has_pages %d dma_mapped %d mmu_mapped %d wc %d imported %d\n", - action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx ? bo->ctx->id : 0, + action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx_id, (bool)bo->base.pages, (bool)bo->base.sgt, bo->mmu_mapped, bo->base.map_wc, (bool)bo->base.base.import_attach); } +static inline int ivpu_bo_lock(struct ivpu_bo *bo) +{ + return dma_resv_lock(bo->base.base.resv, NULL); +} + +static inline void ivpu_bo_unlock(struct ivpu_bo *bo) +{ + dma_resv_unlock(bo->base.base.resv); +} + /* * ivpu_bo_pin() - pin the backing physical pages and map them to VPU. * @@ -41,22 +53,22 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con int __must_check ivpu_bo_pin(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); + struct sg_table *sgt; int ret = 0; - mutex_lock(&bo->lock); - ivpu_dbg_bo(vdev, bo, "pin"); - drm_WARN_ON(&vdev->drm, !bo->ctx); - if (!bo->mmu_mapped) { - struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); + return ret; + } - if (IS_ERR(sgt)) { - ret = PTR_ERR(sgt); - ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); - goto unlock; - } + ivpu_bo_lock(bo); + if (!bo->mmu_mapped) { + drm_WARN_ON(&vdev->drm, !bo->ctx); ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, sgt, ivpu_bo_is_snooped(bo)); if (ret) { @@ -67,7 +79,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo) } unlock: - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); return ret; } @@ -82,7 +94,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, if (!drm_dev_enter(&vdev->drm, &idx)) return -ENODEV; - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node); if (!ret) { @@ -92,9 +104,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret); } - ivpu_dbg_bo(vdev, bo, "alloc"); - - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); drm_dev_exit(idx); @@ -105,7 +115,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); - lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount)); + lockdep_assert(dma_resv_held(bo->base.base.resv) || !kref_read(&bo->base.base.refcount)); if (bo->mmu_mapped) { drm_WARN_ON(&vdev->drm, !bo->ctx); @@ -123,14 +133,12 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) if (bo->base.base.import_attach) return; - dma_resv_lock(bo->base.base.resv, NULL); if (bo->base.sgt) { dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(bo->base.sgt); kfree(bo->base.sgt); bo->base.sgt = NULL; } - dma_resv_unlock(bo->base.base.resv); } void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx) @@ -142,12 +150,12 @@ void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m mutex_lock(&vdev->bo_list_lock); list_for_each_entry(bo, &vdev->bo_list, bo_list_node) { - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); if (bo->ctx == ctx) { ivpu_dbg_bo(vdev, bo, "unbind"); ivpu_bo_unbind_locked(bo); } - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); } mutex_unlock(&vdev->bo_list_lock); } @@ -167,12 +175,52 @@ struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t siz bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */ INIT_LIST_HEAD(&bo->bo_list_node); - mutex_init(&bo->lock); return &bo->base.base; } -static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags) +struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct device *attach_dev = dev->dev; + struct dma_buf_attachment *attach; + struct sg_table *sgt; + struct drm_gem_object *obj; + int ret; + + attach = dma_buf_attach(dma_buf, attach_dev); + if (IS_ERR(attach)) + return ERR_CAST(attach); + + get_dma_buf(dma_buf); + + sgt = dma_buf_map_attachment_unlocked(attach, DMA_BIDIRECTIONAL); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + goto fail_detach; + } + + obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt); + if (IS_ERR(obj)) { + ret = PTR_ERR(obj); + goto fail_unmap; + } + + obj->import_attach = attach; + obj->resv = dma_buf->resv; + + return obj; + +fail_unmap: + dma_buf_unmap_attachment_unlocked(attach, sgt, DMA_BIDIRECTIONAL); +fail_detach: + dma_buf_detach(dma_buf, attach); + dma_buf_put(dma_buf); + + return ERR_PTR(ret); +} + +static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, u32 ctx_id) { struct drm_gem_shmem_object *shmem; struct ivpu_bo *bo; @@ -190,6 +238,7 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla return ERR_CAST(shmem); bo = to_ivpu_bo(&shmem->base); + bo->ctx_id = ctx_id; bo->base.map_wc = flags & DRM_IVPU_BO_WC; bo->flags = flags; @@ -197,6 +246,8 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla list_add_tail(&bo->bo_list_node, &vdev->bo_list); mutex_unlock(&vdev->bo_list_lock); + ivpu_dbg_bo(vdev, bo, "alloc"); + return bo; } @@ -234,10 +285,14 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj) list_del(&bo->bo_list_node); mutex_unlock(&vdev->bo_list_lock); - drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); + drm_WARN_ON(&vdev->drm, !drm_gem_is_imported(&bo->base.base) && + !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); + drm_WARN_ON(&vdev->drm, ivpu_bo_size(bo) == 0); + drm_WARN_ON(&vdev->drm, bo->base.vaddr); ivpu_bo_unbind_locked(bo); - mutex_destroy(&bo->lock); + drm_WARN_ON(&vdev->drm, bo->mmu_mapped); + drm_WARN_ON(&vdev->drm, bo->ctx); drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1); drm_gem_shmem_free(&bo->base); @@ -271,7 +326,7 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi if (size == 0) return -EINVAL; - bo = ivpu_bo_alloc(vdev, size, args->flags); + bo = ivpu_bo_alloc(vdev, size, args->flags, file_priv->ctx.id); if (IS_ERR(bo)) { ivpu_err(vdev, "Failed to allocate BO: %pe (ctx %u size %llu flags 0x%x)", bo, file_priv->ctx.id, args->size, args->flags); @@ -279,7 +334,10 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi } ret = drm_gem_handle_create(file, &bo->base.base, &args->handle); - if (!ret) + if (ret) + ivpu_err(vdev, "Failed to create handle for BO: %pe (ctx %u size %llu flags 0x%x)", + bo, file_priv->ctx.id, args->size, args->flags); + else args->vpu_addr = bo->vpu_addr; drm_gem_object_put(&bo->base.base); @@ -302,7 +360,7 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(range->end)); drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(size)); - bo = ivpu_bo_alloc(vdev, size, flags); + bo = ivpu_bo_alloc(vdev, size, flags, IVPU_GLOBAL_CONTEXT_MMU_SSID); if (IS_ERR(bo)) { ivpu_err(vdev, "Failed to allocate BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)", bo, range->start, size, flags); @@ -318,9 +376,9 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, goto err_put; if (flags & DRM_IVPU_BO_MAPPABLE) { - dma_resv_lock(bo->base.base.resv, NULL); + ivpu_bo_lock(bo); ret = drm_gem_shmem_vmap(&bo->base, &map); - dma_resv_unlock(bo->base.base.resv); + ivpu_bo_unlock(bo); if (ret) goto err_put; @@ -343,9 +401,9 @@ void ivpu_bo_free(struct ivpu_bo *bo) struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr); if (bo->flags & DRM_IVPU_BO_MAPPABLE) { - dma_resv_lock(bo->base.base.resv, NULL); + ivpu_bo_lock(bo); drm_gem_shmem_vunmap(&bo->base, &map); - dma_resv_unlock(bo->base.base.resv); + ivpu_bo_unlock(bo); } drm_gem_object_put(&bo->base.base); @@ -364,12 +422,12 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file bo = to_ivpu_bo(obj); - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); args->flags = bo->flags; args->mmap_offset = drm_vma_node_offset_addr(&obj->vma_node); args->vpu_addr = bo->vpu_addr; args->size = obj->size; - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); drm_gem_object_put(obj); return ret; @@ -406,10 +464,10 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) { - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u", - bo, bo->ctx ? bo->ctx->id : 0, bo->vpu_addr, bo->base.base.size, + bo, bo->ctx_id, bo->vpu_addr, bo->base.base.size, bo->flags, kref_read(&bo->base.base.refcount)); if (bo->base.pages) @@ -423,7 +481,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) drm_printf(p, "\n"); - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); } void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p) diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index d975000abd78..aa8ff14f7aae 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -17,10 +17,10 @@ struct ivpu_bo { struct list_head bo_list_node; struct drm_mm_node mm_node; - struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */ u64 vpu_addr; u32 flags; u32 job_status; /* Valid only for command buffer */ + u32 ctx_id; bool mmu_mapped; }; @@ -28,6 +28,7 @@ int ivpu_bo_pin(struct ivpu_bo *bo); void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx); struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size); +struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf); struct ivpu_bo *ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, struct ivpu_addr_range *range, u64 size, u32 flags); struct ivpu_bo *ivpu_bo_create_global(struct ivpu_device *vdev, u64 size, u32 flags); diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c index 4e1054f3466e..633160470c93 100644 --- a/drivers/accel/ivpu/ivpu_hw.c +++ b/drivers/accel/ivpu/ivpu_hw.c @@ -9,6 +9,16 @@ #include "ivpu_hw_ip.h" #include <linux/dmi.h> +#include <linux/fault-inject.h> +#include <linux/pm_runtime.h> + +#ifdef CONFIG_FAULT_INJECTION +DECLARE_FAULT_ATTR(ivpu_hw_failure); + +static char *ivpu_fail_hw; +module_param_named_unsafe(fail_hw, ivpu_fail_hw, charp, 0444); +MODULE_PARM_DESC(fail_hw, "<interval>,<probability>,<space>,<times>"); +#endif static char *platform_to_str(u32 platform) { @@ -19,43 +29,36 @@ static char *platform_to_str(u32 platform) return "SIMICS"; case IVPU_PLATFORM_FPGA: return "FPGA"; + case IVPU_PLATFORM_HSLE: + return "HSLE"; default: return "Invalid platform"; } } -static const struct dmi_system_id dmi_platform_simulation[] = { - { - .ident = "Intel Simics", - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "lnlrvp"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), - DMI_MATCH(DMI_BOARD_SERIAL, "123456789"), - }, - }, - { - .ident = "Intel Simics", - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "Simics"), - }, - }, - { } -}; - static void platform_init(struct ivpu_device *vdev) { - if (dmi_check_system(dmi_platform_simulation)) - vdev->platform = IVPU_PLATFORM_SIMICS; - else - vdev->platform = IVPU_PLATFORM_SILICON; + int platform = ivpu_hw_btrs_platform_read(vdev); - ivpu_dbg(vdev, MISC, "Platform type: %s (%d)\n", - platform_to_str(vdev->platform), vdev->platform); + ivpu_dbg(vdev, MISC, "Platform type: %s (%d)\n", platform_to_str(platform), platform); + + switch (platform) { + case IVPU_PLATFORM_SILICON: + case IVPU_PLATFORM_SIMICS: + case IVPU_PLATFORM_FPGA: + case IVPU_PLATFORM_HSLE: + vdev->platform = platform; + break; + + default: + ivpu_err(vdev, "Invalid platform type: %d\n", platform); + break; + } } static void wa_init(struct ivpu_device *vdev) { - vdev->wa.punit_disabled = ivpu_is_fpga(vdev); + vdev->wa.punit_disabled = false; vdev->wa.clear_runtime_mem = false; if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) @@ -65,14 +68,24 @@ static void wa_init(struct ivpu_device *vdev) ivpu_revision(vdev) < IVPU_HW_IP_REV_LNL_B0) vdev->wa.disable_clock_relinquish = true; + if (ivpu_test_mode & IVPU_TEST_MODE_CLK_RELINQ_ENABLE) + vdev->wa.disable_clock_relinquish = false; + + if (ivpu_test_mode & IVPU_TEST_MODE_CLK_RELINQ_DISABLE) + vdev->wa.disable_clock_relinquish = true; + if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) vdev->wa.wp0_during_power_up = true; + if (ivpu_test_mode & IVPU_TEST_MODE_D0I2_DISABLE) + vdev->wa.disable_d0i2 = true; + IVPU_PRINT_WA(punit_disabled); IVPU_PRINT_WA(clear_runtime_mem); IVPU_PRINT_WA(interrupt_clear_with_0); IVPU_PRINT_WA(disable_clock_relinquish); IVPU_PRINT_WA(wp0_during_power_up); + IVPU_PRINT_WA(disable_d0i2); } static void timeouts_init(struct ivpu_device *vdev) @@ -84,12 +97,12 @@ static void timeouts_init(struct ivpu_device *vdev) vdev->timeout.autosuspend = -1; vdev->timeout.d0i3_entry_msg = -1; } else if (ivpu_is_fpga(vdev)) { - vdev->timeout.boot = 100000; - vdev->timeout.jsm = 50000; - vdev->timeout.tdr = 2000000; + vdev->timeout.boot = 50; + vdev->timeout.jsm = 15000; + vdev->timeout.tdr = 30000; vdev->timeout.autosuspend = -1; vdev->timeout.d0i3_entry_msg = 500; - vdev->timeout.state_dump_msg = 10; + vdev->timeout.state_dump_msg = 10000; } else if (ivpu_is_simics(vdev)) { vdev->timeout.boot = 50; vdev->timeout.jsm = 500; @@ -106,10 +119,30 @@ static void timeouts_init(struct ivpu_device *vdev) else vdev->timeout.autosuspend = 100; vdev->timeout.d0i3_entry_msg = 5; - vdev->timeout.state_dump_msg = 10; + vdev->timeout.state_dump_msg = 100; } } +static void priority_bands_init(struct ivpu_device *vdev) +{ + /* Idle */ + vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 0; + vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 50000; + vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 160000; + /* Normal */ + vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 50000; + vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 50000; + vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 300000; + /* Focus */ + vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 50000; + vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 50000; + vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 200000; + /* Realtime */ + vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 0; + vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 50000; + vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 200000; +} + static void memory_ranges_init(struct ivpu_device *vdev) { if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) { @@ -248,12 +281,18 @@ int ivpu_hw_init(struct ivpu_device *vdev) { ivpu_hw_btrs_info_init(vdev); ivpu_hw_btrs_freq_ratios_init(vdev); + priority_bands_init(vdev); memory_ranges_init(vdev); platform_init(vdev); wa_init(vdev); timeouts_init(vdev); atomic_set(&vdev->hw->firewall_irq_counter, 0); +#ifdef CONFIG_FAULT_INJECTION + if (ivpu_fail_hw) + setup_fault_attr(&ivpu_hw_failure, ivpu_fail_hw); +#endif + return 0; } @@ -285,8 +324,6 @@ void ivpu_hw_profiling_freq_drive(struct ivpu_device *vdev, bool enable) void ivpu_irq_handlers_init(struct ivpu_device *vdev) { - INIT_KFIFO(vdev->hw->irq.fifo); - if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) vdev->hw->irq.ip_irq_handler = ivpu_hw_ip_irq_handler_37xx; else @@ -300,7 +337,6 @@ void ivpu_irq_handlers_init(struct ivpu_device *vdev) void ivpu_hw_irq_enable(struct ivpu_device *vdev) { - kfifo_reset(&vdev->hw->irq.fifo); ivpu_hw_ip_irq_enable(vdev); ivpu_hw_btrs_irq_enable(vdev); } @@ -327,9 +363,9 @@ irqreturn_t ivpu_hw_irq_handler(int irq, void *ptr) /* Re-enable global interrupts to re-trigger MSI for pending interrupts */ ivpu_hw_btrs_global_int_enable(vdev); - if (!kfifo_is_empty(&vdev->hw->irq.fifo)) - return IRQ_WAKE_THREAD; - if (ip_handled || btrs_handled) - return IRQ_HANDLED; - return IRQ_NONE; + if (!ip_handled && !btrs_handled) + return IRQ_NONE; + + pm_runtime_mark_last_busy(vdev->drm.dev); + return IRQ_HANDLED; } diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index fc4dbfc980c8..d79668fe1609 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -1,23 +1,15 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #ifndef __IVPU_HW_H__ #define __IVPU_HW_H__ -#include <linux/kfifo.h> - #include "ivpu_drv.h" #include "ivpu_hw_btrs.h" #include "ivpu_hw_ip.h" -#define IVPU_HW_IRQ_FIFO_LENGTH 1024 - -#define IVPU_HW_IRQ_SRC_IPC 1 -#define IVPU_HW_IRQ_SRC_MMU_EVTQ 2 -#define IVPU_HW_IRQ_SRC_DCT 3 - struct ivpu_addr_range { resource_size_t start; resource_size_t end; @@ -27,7 +19,6 @@ struct ivpu_hw_info { struct { bool (*btrs_irq_handler)(struct ivpu_device *vdev, int irq); bool (*ip_irq_handler)(struct ivpu_device *vdev, int irq); - DECLARE_KFIFO(fifo, u8, IVPU_HW_IRQ_FIFO_LENGTH); } irq; struct { struct ivpu_addr_range global; @@ -45,6 +36,11 @@ struct ivpu_hw_info { u8 pn_ratio; u32 profiling_freq; } pll; + struct { + u32 grace_period[VPU_HWS_NUM_PRIORITY_BANDS]; + u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS]; + u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS]; + } hws; u32 tile_fuse; u32 sku; u16 config; @@ -86,19 +82,19 @@ static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range) return range->end - range->start; } -static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) +static inline u32 ivpu_hw_dpu_max_freq_get(struct ivpu_device *vdev) { - return ivpu_hw_btrs_ratio_to_freq(vdev, ratio); + return ivpu_hw_btrs_dpu_max_freq_get(vdev); } -static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev) +static inline u32 ivpu_hw_dpu_freq_get(struct ivpu_device *vdev) { - ivpu_hw_ip_irq_clear(vdev); + return ivpu_hw_btrs_dpu_freq_get(vdev); } -static inline u32 ivpu_hw_pll_freq_get(struct ivpu_device *vdev) +static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev) { - return ivpu_hw_btrs_pll_freq_get(vdev); + ivpu_hw_ip_irq_clear(vdev); } static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c index 3212c99f3682..b236c7234daa 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.c +++ b/drivers/accel/ivpu/ivpu_hw_btrs.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ +#include <linux/units.h> + #include "ivpu_drv.h" #include "ivpu_hw.h" #include "ivpu_hw_btrs.h" @@ -28,17 +30,13 @@ #define BTRS_LNL_ALL_IRQ_MASK ((u32)-1) -#define BTRS_MTL_WP_CONFIG_1_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_5_3) -#define BTRS_MTL_WP_CONFIG_1_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_4_3) -#define BTRS_MTL_WP_CONFIG_2_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_5_3) -#define BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3) -#define BTRS_MTL_WP_CONFIG_0_TILE_PLL_OFF WP_CONFIG(0, 0) #define PLL_CDYN_DEFAULT 0x80 #define PLL_EPP_DEFAULT 0x80 #define PLL_CONFIG_DEFAULT 0x0 -#define PLL_SIMULATION_FREQ 10000000 -#define PLL_REF_CLK_FREQ 50000000 +#define PLL_REF_CLK_FREQ 50000000ull +#define PLL_RATIO_TO_FREQ(x) ((x) * PLL_REF_CLK_FREQ) + #define PLL_TIMEOUT_US (1500 * USEC_PER_MSEC) #define IDLE_TIMEOUT_US (5 * USEC_PER_MSEC) #define TIMEOUT_US (150 * USEC_PER_MSEC) @@ -62,6 +60,8 @@ #define DCT_ENABLE 0x1 #define DCT_DISABLE 0x0 +static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio); + int ivpu_hw_btrs_irqs_clear_with_0_mtl(struct ivpu_device *vdev) { REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, BTRS_MTL_ALL_IRQ_MASK); @@ -156,7 +156,7 @@ static int info_init_mtl(struct ivpu_device *vdev) hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH; hw->sku = BTRS_MTL_TILE_SKU_BOTH; - hw->config = BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO; + hw->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3); return 0; } @@ -334,8 +334,8 @@ int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable) prepare_wp_request(vdev, &wp, enable); - ivpu_dbg(vdev, PM, "PLL workpoint request: %u Hz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n", - PLL_RATIO_TO_FREQ(wp.target), wp.cfg, wp.epp, wp.cdyn); + ivpu_dbg(vdev, PM, "PLL workpoint request: %lu MHz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n", + pll_ratio_to_dpu_freq(vdev, wp.target) / HZ_PER_MHZ, wp.cfg, wp.epp, wp.cdyn); ret = wp_request_send(vdev, &wp); if (ret) { @@ -573,6 +573,47 @@ int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev) return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US); } +static u32 pll_config_get_mtl(struct ivpu_device *vdev) +{ + return REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL); +} + +static u32 pll_config_get_lnl(struct ivpu_device *vdev) +{ + return REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ); +} + +static u32 pll_ratio_to_dpu_freq_mtl(u16 ratio) +{ + return (PLL_RATIO_TO_FREQ(ratio) * 2) / 3; +} + +static u32 pll_ratio_to_dpu_freq_lnl(u16 ratio) +{ + return PLL_RATIO_TO_FREQ(ratio) / 2; +} + +static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio) +{ + if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) + return pll_ratio_to_dpu_freq_mtl(ratio); + else + return pll_ratio_to_dpu_freq_lnl(ratio); +} + +u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev) +{ + return pll_ratio_to_dpu_freq(vdev, vdev->hw->pll.max_ratio); +} + +u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev) +{ + if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) + return pll_ratio_to_dpu_freq_mtl(pll_config_get_mtl(vdev)); + else + return pll_ratio_to_dpu_freq_lnl(pll_config_get_lnl(vdev)); +} + /* Handler for IRQs from Buttress core (irqB) */ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq) { @@ -582,9 +623,12 @@ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq) if (!status) return false; - if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) - ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", - REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL)); + if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) { + u32 pll = pll_config_get_mtl(vdev); + + ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz", + pll, pll_ratio_to_dpu_freq_mtl(pll) / HZ_PER_MHZ); + } if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR, status)) { ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_HW_BTRS_MTL_ATS_ERR_LOG_0)); @@ -630,12 +674,15 @@ bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq) if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, SURV_ERR, status)) { ivpu_dbg(vdev, IRQ, "Survivability IRQ\n"); - if (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_DCT)) - ivpu_err_ratelimited(vdev, "IRQ FIFO full\n"); + queue_work(system_wq, &vdev->irq_dct_work); } - if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) - ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ)); + if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) { + u32 pll = pll_config_get_lnl(vdev); + + ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz", + pll, pll_ratio_to_dpu_freq_lnl(pll) / HZ_PER_MHZ); + } if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, status)) { ivpu_err(vdev, "ATS_ERR LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n", @@ -718,60 +765,6 @@ void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 acti REGB_WR32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, val); } -static u32 pll_ratio_to_freq_mtl(u32 ratio, u32 config) -{ - u32 pll_clock = PLL_REF_CLK_FREQ * ratio; - u32 cpu_clock; - - if ((config & 0xff) == MTL_PLL_RATIO_4_3) - cpu_clock = pll_clock * 2 / 4; - else - cpu_clock = pll_clock * 2 / 5; - - return cpu_clock; -} - -u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) -{ - struct ivpu_hw_info *hw = vdev->hw; - - if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) - return pll_ratio_to_freq_mtl(ratio, hw->config); - else - return PLL_RATIO_TO_FREQ(ratio); -} - -static u32 pll_freq_get_mtl(struct ivpu_device *vdev) -{ - u32 pll_curr_ratio; - - pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL); - pll_curr_ratio &= VPU_HW_BTRS_MTL_CURRENT_PLL_RATIO_MASK; - - if (!ivpu_is_silicon(vdev)) - return PLL_SIMULATION_FREQ; - - return pll_ratio_to_freq_mtl(pll_curr_ratio, vdev->hw->config); -} - -static u32 pll_freq_get_lnl(struct ivpu_device *vdev) -{ - u32 pll_curr_ratio; - - pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ); - pll_curr_ratio &= VPU_HW_BTRS_LNL_PLL_FREQ_RATIO_MASK; - - return PLL_RATIO_TO_FREQ(pll_curr_ratio); -} - -u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev) -{ - if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) - return pll_freq_get_mtl(vdev); - else - return pll_freq_get_lnl(vdev); -} - u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev) { if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) @@ -888,3 +881,10 @@ void ivpu_hw_btrs_diagnose_failure(struct ivpu_device *vdev) else return diagnose_failure_lnl(vdev); } + +int ivpu_hw_btrs_platform_read(struct ivpu_device *vdev) +{ + u32 reg = REGB_RD32(VPU_HW_BTRS_LNL_VPU_STATUS); + + return REG_GET_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, PLATFORM, reg); +} diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h index 04f14f50fed6..d2d82651976d 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.h +++ b/drivers/accel/ivpu/ivpu_hw_btrs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #ifndef __IVPU_HW_BTRS_H__ @@ -13,9 +13,8 @@ #define PLL_PROFILING_FREQ_DEFAULT 38400000 #define PLL_PROFILING_FREQ_HIGH 400000000 -#define PLL_RATIO_TO_FREQ(x) ((x) * PLL_REF_CLK_FREQ) -#define DCT_DEFAULT_ACTIVE_PERCENT 15u +#define DCT_DEFAULT_ACTIVE_PERCENT 30u #define DCT_PERIOD_US 35300u int ivpu_hw_btrs_info_init(struct ivpu_device *vdev); @@ -32,12 +31,12 @@ int ivpu_hw_btrs_ip_reset(struct ivpu_device *vdev); void ivpu_hw_btrs_profiling_freq_reg_set_lnl(struct ivpu_device *vdev); void ivpu_hw_btrs_ats_print_lnl(struct ivpu_device *vdev); void ivpu_hw_btrs_clock_relinquish_disable_lnl(struct ivpu_device *vdev); +u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev); +u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev); bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq); bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq); int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable); void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 dct_percent); -u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev); -u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio); u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev); u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev); u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev); @@ -46,5 +45,6 @@ void ivpu_hw_btrs_global_int_disable(struct ivpu_device *vdev); void ivpu_hw_btrs_irq_enable(struct ivpu_device *vdev); void ivpu_hw_btrs_irq_disable(struct ivpu_device *vdev); void ivpu_hw_btrs_diagnose_failure(struct ivpu_device *vdev); +int ivpu_hw_btrs_platform_read(struct ivpu_device *vdev); #endif /* __IVPU_HW_BTRS_H__ */ diff --git a/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h b/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h index fc51f3098f97..fff2ef2cada6 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h +++ b/drivers/accel/ivpu/ivpu_hw_btrs_lnl_reg.h @@ -86,6 +86,7 @@ #define VPU_HW_BTRS_LNL_VPU_STATUS_POWER_RESOURCE_OWN_ACK_MASK BIT_MASK(7) #define VPU_HW_BTRS_LNL_VPU_STATUS_PERF_CLK_MASK BIT_MASK(11) #define VPU_HW_BTRS_LNL_VPU_STATUS_DISABLE_CLK_RELINQUISH_MASK BIT_MASK(12) +#define VPU_HW_BTRS_LNL_VPU_STATUS_PLATFORM_MASK GENMASK(31, 29) #define VPU_HW_BTRS_LNL_IP_RESET 0x00000160u #define VPU_HW_BTRS_LNL_IP_RESET_TRIGGER_MASK BIT_MASK(0) diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c index 029dd065614b..823f6a57dc54 100644 --- a/drivers/accel/ivpu/ivpu_hw_ip.c +++ b/drivers/accel/ivpu/ivpu_hw_ip.c @@ -968,14 +968,14 @@ void ivpu_hw_ip_wdt_disable(struct ivpu_device *vdev) static u32 ipc_rx_count_get_37xx(struct ivpu_device *vdev) { - u32 count = REGV_RD32_SILENT(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT); + u32 count = readl(vdev->regv + VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT); return REG_GET_FLD(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count); } static u32 ipc_rx_count_get_40xx(struct ivpu_device *vdev) { - u32 count = REGV_RD32_SILENT(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT); + u32 count = readl(vdev->regv + VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT); return REG_GET_FLD(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count); } diff --git a/drivers/accel/ivpu/ivpu_hw_reg_io.h b/drivers/accel/ivpu/ivpu_hw_reg_io.h index 79b3f441eac4..66259b0ead02 100644 --- a/drivers/accel/ivpu/ivpu_hw_reg_io.h +++ b/drivers/accel/ivpu/ivpu_hw_reg_io.h @@ -7,6 +7,7 @@ #define __IVPU_HW_REG_IO_H__ #include <linux/bitfield.h> +#include <linux/fault-inject.h> #include <linux/io.h> #include <linux/iopoll.h> @@ -16,13 +17,11 @@ #define REG_IO_ERROR 0xffffffff #define REGB_RD32(reg) ivpu_hw_reg_rd32(vdev, vdev->regb, (reg), #reg, __func__) -#define REGB_RD32_SILENT(reg) readl(vdev->regb + (reg)) #define REGB_RD64(reg) ivpu_hw_reg_rd64(vdev, vdev->regb, (reg), #reg, __func__) #define REGB_WR32(reg, val) ivpu_hw_reg_wr32(vdev, vdev->regb, (reg), (val), #reg, __func__) #define REGB_WR64(reg, val) ivpu_hw_reg_wr64(vdev, vdev->regb, (reg), (val), #reg, __func__) #define REGV_RD32(reg) ivpu_hw_reg_rd32(vdev, vdev->regv, (reg), #reg, __func__) -#define REGV_RD32_SILENT(reg) readl(vdev->regv + (reg)) #define REGV_RD64(reg) ivpu_hw_reg_rd64(vdev, vdev->regv, (reg), #reg, __func__) #define REGV_WR32(reg, val) ivpu_hw_reg_wr32(vdev, vdev->regv, (reg), (val), #reg, __func__) #define REGV_WR64(reg, val) ivpu_hw_reg_wr64(vdev, vdev->regv, (reg), (val), #reg, __func__) @@ -47,31 +46,42 @@ #define REG_TEST_FLD_NUM(REG, FLD, num, val) \ ((num) == FIELD_GET(REG##_##FLD##_MASK, val)) -#define REGB_POLL_FLD(reg, fld, val, timeout_us) \ -({ \ - u32 var; \ - int r; \ - ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s started (expected 0x%x)\n", \ - __func__, #reg, reg, #fld, val); \ - r = read_poll_timeout(REGB_RD32_SILENT, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)),\ - REG_POLL_SLEEP_US, timeout_us, false, (reg)); \ - ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s %s (reg val 0x%08x)\n", \ - __func__, #reg, reg, #fld, r ? "ETIMEDOUT" : "OK", var); \ - r; \ -}) - -#define REGV_POLL_FLD(reg, fld, val, timeout_us) \ -({ \ - u32 var; \ - int r; \ - ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s started (expected 0x%x)\n", \ - __func__, #reg, reg, #fld, val); \ - r = read_poll_timeout(REGV_RD32_SILENT, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)),\ - REG_POLL_SLEEP_US, timeout_us, false, (reg)); \ - ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s %s (reg val 0x%08x)\n", \ - __func__, #reg, reg, #fld, r ? "ETIMEDOUT" : "OK", var); \ - r; \ -}) +#define REGB_POLL_FLD(reg, fld, exp_fld_val, timeout_us) \ + ivpu_hw_reg_poll_fld(vdev, vdev->regb, reg, reg##_##fld##_MASK, \ + FIELD_PREP(reg##_##fld##_MASK, exp_fld_val), timeout_us, \ + __func__, #reg, #fld) + +#define REGV_POLL_FLD(reg, fld, exp_fld_val, timeout_us) \ + ivpu_hw_reg_poll_fld(vdev, vdev->regv, reg, reg##_##fld##_MASK, \ + FIELD_PREP(reg##_##fld##_MASK, exp_fld_val), timeout_us, \ + __func__, #reg, #fld) + +extern struct fault_attr ivpu_hw_failure; + +static inline int __must_check +ivpu_hw_reg_poll_fld(struct ivpu_device *vdev, void __iomem *base, + u32 reg_offset, u32 reg_mask, u32 exp_masked_val, u32 timeout_us, + const char *func_name, const char *reg_name, const char *fld_name) +{ + u32 reg_val; + int ret; + + ivpu_dbg(vdev, REG, "%s : %s (0x%08x) POLL %s started (exp_val 0x%x)\n", + func_name, reg_name, reg_offset, fld_name, exp_masked_val); + + ret = read_poll_timeout(readl, reg_val, (reg_val & reg_mask) == exp_masked_val, + REG_POLL_SLEEP_US, timeout_us, false, base + reg_offset); + +#ifdef CONFIG_FAULT_INJECTION + if (should_fail(&ivpu_hw_failure, 1)) + ret = -ETIMEDOUT; +#endif + + ivpu_dbg(vdev, REG, "%s : %s (0x%08x) POLL %s %s (reg_val 0x%08x)\n", + func_name, reg_name, reg_offset, fld_name, ret ? "ETIMEDOUT" : "OK", reg_val); + + return ret; +} static inline u32 ivpu_hw_reg_rd32(struct ivpu_device *vdev, void __iomem *base, u32 reg, diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index 01ebf88fe6ef..39f83225c181 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -302,7 +302,8 @@ ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req struct ivpu_ipc_consumer cons; int ret; - drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev)); + drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev) && + pm_runtime_enabled(vdev->drm.dev)); ivpu_ipc_consumer_add(vdev, &cons, channel, NULL); @@ -459,13 +460,12 @@ void ivpu_ipc_irq_handler(struct ivpu_device *vdev) } } - if (!list_empty(&ipc->cb_msg_list)) - if (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_IPC)) - ivpu_err_ratelimited(vdev, "IRQ FIFO full\n"); + queue_work(system_wq, &vdev->irq_ipc_work); } -void ivpu_ipc_irq_thread_handler(struct ivpu_device *vdev) +void ivpu_ipc_irq_work_fn(struct work_struct *work) { + struct ivpu_device *vdev = container_of(work, struct ivpu_device, irq_ipc_work); struct ivpu_ipc_info *ipc = vdev->ipc; struct ivpu_ipc_rx_msg *rx_msg, *r; struct list_head cb_msg_list; diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h index b4dfb504679b..b524a1985b9d 100644 --- a/drivers/accel/ivpu/ivpu_ipc.h +++ b/drivers/accel/ivpu/ivpu_ipc.h @@ -90,7 +90,7 @@ void ivpu_ipc_disable(struct ivpu_device *vdev); void ivpu_ipc_reset(struct ivpu_device *vdev); void ivpu_ipc_irq_handler(struct ivpu_device *vdev); -void ivpu_ipc_irq_thread_handler(struct ivpu_device *vdev); +void ivpu_ipc_irq_work_fn(struct work_struct *work); void ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, u32 channel, ivpu_ipc_rx_callback_t callback); diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 7149312f16e1..fae8351aa330 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -8,6 +8,7 @@ #include <linux/bitfield.h> #include <linux/highmem.h> #include <linux/pci.h> +#include <linux/pm_runtime.h> #include <linux/module.h> #include <uapi/drm/ivpu_accel.h> @@ -17,6 +18,7 @@ #include "ivpu_ipc.h" #include "ivpu_job.h" #include "ivpu_jsm_msg.h" +#include "ivpu_mmu.h" #include "ivpu_pm.h" #include "ivpu_trace.h" #include "vpu_boot_api.h" @@ -83,23 +85,9 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv) if (!cmdq) return NULL; - ret = xa_alloc_cyclic(&vdev->db_xa, &cmdq->db_id, NULL, vdev->db_limit, &vdev->db_next, - GFP_KERNEL); - if (ret < 0) { - ivpu_err(vdev, "Failed to allocate doorbell id: %d\n", ret); - goto err_free_cmdq; - } - - ret = xa_alloc_cyclic(&file_priv->cmdq_xa, &cmdq->id, cmdq, file_priv->cmdq_limit, - &file_priv->cmdq_id_next, GFP_KERNEL); - if (ret < 0) { - ivpu_err(vdev, "Failed to allocate command queue id: %d\n", ret); - goto err_erase_db_xa; - } - cmdq->mem = ivpu_bo_create_global(vdev, SZ_4K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE); if (!cmdq->mem) - goto err_erase_cmdq_xa; + goto err_free_cmdq; ret = ivpu_preemption_buffers_create(vdev, file_priv, cmdq); if (ret) @@ -107,10 +95,6 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv) return cmdq; -err_erase_cmdq_xa: - xa_erase(&file_priv->cmdq_xa, cmdq->id); -err_erase_db_xa: - xa_erase(&vdev->db_xa, cmdq->db_id); err_free_cmdq: kfree(cmdq); return NULL; @@ -118,15 +102,44 @@ err_free_cmdq: static void ivpu_cmdq_free(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) { - if (!cmdq) - return; - ivpu_preemption_buffers_free(file_priv->vdev, file_priv, cmdq); ivpu_bo_free(cmdq->mem); - xa_erase(&file_priv->vdev->db_xa, cmdq->db_id); kfree(cmdq); } +static struct ivpu_cmdq *ivpu_cmdq_create(struct ivpu_file_priv *file_priv, u8 priority, + bool is_legacy) +{ + struct ivpu_device *vdev = file_priv->vdev; + struct ivpu_cmdq *cmdq = NULL; + int ret; + + lockdep_assert_held(&file_priv->lock); + + cmdq = ivpu_cmdq_alloc(file_priv); + if (!cmdq) { + ivpu_err(vdev, "Failed to allocate command queue\n"); + return NULL; + } + + cmdq->priority = priority; + cmdq->is_legacy = is_legacy; + + ret = xa_alloc_cyclic(&file_priv->cmdq_xa, &cmdq->id, cmdq, file_priv->cmdq_limit, + &file_priv->cmdq_id_next, GFP_KERNEL); + if (ret < 0) { + ivpu_err(vdev, "Failed to allocate command queue ID: %d\n", ret); + goto err_free_cmdq; + } + + ivpu_dbg(vdev, JOB, "Command queue %d created, ctx %d\n", cmdq->id, file_priv->ctx.id); + return cmdq; + +err_free_cmdq: + ivpu_cmdq_free(file_priv, cmdq); + return NULL; +} + static int ivpu_hws_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 engine, u8 priority) { @@ -152,6 +165,13 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq * struct ivpu_device *vdev = file_priv->vdev; int ret; + ret = xa_alloc_cyclic(&vdev->db_xa, &cmdq->db_id, NULL, vdev->db_limit, &vdev->db_next, + GFP_KERNEL); + if (ret < 0) { + ivpu_err(vdev, "Failed to allocate doorbell ID: %d\n", ret); + return ret; + } + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->id, cmdq->db_id, cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem)); @@ -160,41 +180,52 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq * cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem)); if (!ret) - ivpu_dbg(vdev, JOB, "DB %d registered to cmdq %d ctx %d\n", - cmdq->db_id, cmdq->id, file_priv->ctx.id); + ivpu_dbg(vdev, JOB, "DB %d registered to cmdq %d ctx %d priority %d\n", + cmdq->db_id, cmdq->id, file_priv->ctx.id, cmdq->priority); + else + xa_erase(&vdev->db_xa, cmdq->db_id); return ret; } -static int -ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u8 priority) +static void ivpu_cmdq_jobq_init(struct ivpu_device *vdev, struct vpu_job_queue *jobq) +{ + jobq->header.engine_idx = VPU_ENGINE_COMPUTE; + jobq->header.head = 0; + jobq->header.tail = 0; + + if (ivpu_test_mode & IVPU_TEST_MODE_TURBO) { + ivpu_dbg(vdev, JOB, "Turbo mode enabled"); + jobq->header.flags = VPU_JOB_QUEUE_FLAGS_TURBO_MODE; + } + + wmb(); /* Flush WC buffer for jobq->header */ +} + +static inline u32 ivpu_cmdq_get_entry_count(struct ivpu_cmdq *cmdq) +{ + size_t size = ivpu_bo_size(cmdq->mem) - sizeof(struct vpu_job_queue_header); + + return size / sizeof(struct vpu_job_queue_entry); +} + +static int ivpu_cmdq_register(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) { struct ivpu_device *vdev = file_priv->vdev; - struct vpu_job_queue_header *jobq_header; int ret; lockdep_assert_held(&file_priv->lock); - if (cmdq->db_registered) + if (cmdq->db_id) return 0; - cmdq->entry_count = (u32)((ivpu_bo_size(cmdq->mem) - sizeof(struct vpu_job_queue_header)) / - sizeof(struct vpu_job_queue_entry)); - + cmdq->entry_count = ivpu_cmdq_get_entry_count(cmdq); cmdq->jobq = (struct vpu_job_queue *)ivpu_bo_vaddr(cmdq->mem); - jobq_header = &cmdq->jobq->header; - jobq_header->engine_idx = VPU_ENGINE_COMPUTE; - jobq_header->head = 0; - jobq_header->tail = 0; - if (ivpu_test_mode & IVPU_TEST_MODE_TURBO) { - ivpu_dbg(vdev, JOB, "Turbo mode enabled"); - jobq_header->flags = VPU_JOB_QUEUE_FLAGS_TURBO_MODE; - } - wmb(); /* Flush WC buffer for jobq->header */ + ivpu_cmdq_jobq_init(vdev, cmdq->jobq); if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { - ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, priority); + ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, cmdq->priority); if (ret) return ret; } @@ -203,58 +234,83 @@ ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u8 prio if (ret) return ret; - cmdq->db_registered = true; - return 0; } -static int ivpu_cmdq_fini(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) +static int ivpu_cmdq_unregister(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) { struct ivpu_device *vdev = file_priv->vdev; int ret; lockdep_assert_held(&file_priv->lock); - if (!cmdq->db_registered) + if (!cmdq->db_id) return 0; - cmdq->db_registered = false; + ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id); + if (!ret) + ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id); if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); if (!ret) - ivpu_dbg(vdev, JOB, "Command queue %d destroyed\n", cmdq->id); + ivpu_dbg(vdev, JOB, "Command queue %d destroyed, ctx %d\n", + cmdq->id, file_priv->ctx.id); } - ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id); - if (!ret) - ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id); + xa_erase(&file_priv->vdev->db_xa, cmdq->db_id); + cmdq->db_id = 0; return 0; } -static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u8 priority) +static inline u8 ivpu_job_to_jsm_priority(u8 priority) +{ + if (priority == DRM_IVPU_JOB_PRIORITY_DEFAULT) + return VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL; + + return priority - 1; +} + +static void ivpu_cmdq_destroy(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) +{ + ivpu_cmdq_unregister(file_priv, cmdq); + xa_erase(&file_priv->cmdq_xa, cmdq->id); + ivpu_cmdq_free(file_priv, cmdq); +} + +static struct ivpu_cmdq *ivpu_cmdq_acquire_legacy(struct ivpu_file_priv *file_priv, u8 priority) { struct ivpu_cmdq *cmdq; - unsigned long cmdq_id; - int ret; + unsigned long id; lockdep_assert_held(&file_priv->lock); - xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) - if (cmdq->priority == priority) + xa_for_each(&file_priv->cmdq_xa, id, cmdq) + if (cmdq->is_legacy && cmdq->priority == priority) break; if (!cmdq) { - cmdq = ivpu_cmdq_alloc(file_priv); + cmdq = ivpu_cmdq_create(file_priv, priority, true); if (!cmdq) return NULL; - cmdq->priority = priority; } - ret = ivpu_cmdq_init(file_priv, cmdq, priority); - if (ret) + return cmdq; +} + +static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u32 cmdq_id) +{ + struct ivpu_device *vdev = file_priv->vdev; + struct ivpu_cmdq *cmdq; + + lockdep_assert_held(&file_priv->lock); + + cmdq = xa_load(&file_priv->cmdq_xa, cmdq_id); + if (!cmdq) { + ivpu_warn_ratelimited(vdev, "Failed to find command queue with ID: %u\n", cmdq_id); return NULL; + } return cmdq; } @@ -266,11 +322,8 @@ void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv) lockdep_assert_held(&file_priv->lock); - xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) { - xa_erase(&file_priv->cmdq_xa, cmdq_id); - ivpu_cmdq_fini(file_priv, cmdq); - ivpu_cmdq_free(file_priv, cmdq); - } + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) + ivpu_cmdq_destroy(file_priv, cmdq); } /* @@ -286,8 +339,10 @@ static void ivpu_cmdq_reset(struct ivpu_file_priv *file_priv) mutex_lock(&file_priv->lock); - xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) - cmdq->db_registered = false; + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) { + xa_erase(&file_priv->vdev->db_xa, cmdq->db_id); + cmdq->db_id = 0; + } mutex_unlock(&file_priv->lock); } @@ -305,25 +360,24 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev) mutex_unlock(&vdev->context_list_lock); } -static void ivpu_cmdq_fini_all(struct ivpu_file_priv *file_priv) -{ - struct ivpu_cmdq *cmdq; - unsigned long cmdq_id; - - xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) - ivpu_cmdq_fini(file_priv, cmdq); -} - void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv) { struct ivpu_device *vdev = file_priv->vdev; + struct ivpu_cmdq *cmdq; + unsigned long cmdq_id; lockdep_assert_held(&file_priv->lock); + ivpu_dbg(vdev, JOB, "Context ID: %u abort\n", file_priv->ctx.id); - ivpu_cmdq_fini_all(file_priv); + xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) + ivpu_cmdq_unregister(file_priv, cmdq); if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_OS) ivpu_jsm_context_release(vdev, file_priv->ctx.id); + + ivpu_mmu_disable_ssid_events(vdev, file_priv->ctx.id); + + file_priv->aborted = true; } static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job) @@ -416,8 +470,8 @@ static void ivpu_job_destroy(struct ivpu_job *job) struct ivpu_device *vdev = job->vdev; u32 i; - ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d engine %d", - job->job_id, job->file_priv->ctx.id, job->engine_idx); + ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d cmdq_id %u engine %d", + job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx); for (i = 0; i < job->bo_count; i++) if (job->bos[i]) @@ -462,16 +516,14 @@ static struct ivpu_job *ivpu_job_remove_from_submitted_jobs(struct ivpu_device * { struct ivpu_job *job; - xa_lock(&vdev->submitted_jobs_xa); - job = __xa_erase(&vdev->submitted_jobs_xa, job_id); + lockdep_assert_held(&vdev->submitted_jobs_lock); + job = xa_erase(&vdev->submitted_jobs_xa, job_id); if (xa_empty(&vdev->submitted_jobs_xa) && job) { vdev->busy_time = ktime_add(ktime_sub(ktime_get(), vdev->busy_start_ts), vdev->busy_time); } - xa_unlock(&vdev->submitted_jobs_xa); - return job; } @@ -479,6 +531,28 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 { struct ivpu_job *job; + lockdep_assert_held(&vdev->submitted_jobs_lock); + + job = xa_load(&vdev->submitted_jobs_xa, job_id); + if (!job) + return -ENOENT; + + if (job_status == VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW) { + guard(mutex)(&job->file_priv->lock); + + if (job->file_priv->has_mmu_faults) + return 0; + + /* + * Mark context as faulty and defer destruction of the job to jobs abort thread + * handler to synchronize between both faults and jobs returning context violation + * status and ensure both are handled in the same way + */ + job->file_priv->has_mmu_faults = true; + queue_work(system_wq, &vdev->context_abort_work); + return 0; + } + job = ivpu_job_remove_from_submitted_jobs(vdev, job_id); if (!job) return -ENOENT; @@ -490,13 +564,17 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 dma_fence_signal(job->done_fence); trace_job("done", job); - ivpu_dbg(vdev, JOB, "Job complete: id %3u ctx %2d engine %d status 0x%x\n", - job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status); + ivpu_dbg(vdev, JOB, "Job complete: id %3u ctx %2d cmdq_id %u engine %d status 0x%x\n", + job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx, job_status); ivpu_job_destroy(job); ivpu_stop_job_timeout_detection(vdev); ivpu_rpm_put(vdev); + + if (!xa_empty(&vdev->submitted_jobs_xa)) + ivpu_start_job_timeout_detection(vdev); + return 0; } @@ -505,11 +583,29 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev) struct ivpu_job *job; unsigned long id; + mutex_lock(&vdev->submitted_jobs_lock); + xa_for_each(&vdev->submitted_jobs_xa, id, job) ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED); + + mutex_unlock(&vdev->submitted_jobs_lock); +} + +void ivpu_cmdq_abort_all_jobs(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id) +{ + struct ivpu_job *job; + unsigned long id; + + mutex_lock(&vdev->submitted_jobs_lock); + + xa_for_each(&vdev->submitted_jobs_xa, id, job) + if (job->file_priv->ctx.id == ctx_id && job->cmdq_id == cmdq_id) + ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED); + + mutex_unlock(&vdev->submitted_jobs_lock); } -static int ivpu_job_submit(struct ivpu_job *job, u8 priority) +static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id) { struct ivpu_file_priv *file_priv = job->file_priv; struct ivpu_device *vdev = job->vdev; @@ -521,25 +617,35 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority) if (ret < 0) return ret; + mutex_lock(&vdev->submitted_jobs_lock); mutex_lock(&file_priv->lock); - cmdq = ivpu_cmdq_acquire(file_priv, priority); + if (cmdq_id == 0) + cmdq = ivpu_cmdq_acquire_legacy(file_priv, priority); + else + cmdq = ivpu_cmdq_acquire(file_priv, cmdq_id); if (!cmdq) { - ivpu_warn_ratelimited(vdev, "Failed to get job queue, ctx %d engine %d prio %d\n", - file_priv->ctx.id, job->engine_idx, priority); + ivpu_warn_ratelimited(vdev, "Failed to get job queue, ctx %d\n", file_priv->ctx.id); ret = -EINVAL; - goto err_unlock_file_priv; + goto err_unlock; + } + + ret = ivpu_cmdq_register(file_priv, cmdq); + if (ret) { + ivpu_err(vdev, "Failed to register command queue: %d\n", ret); + goto err_unlock; } - xa_lock(&vdev->submitted_jobs_xa); + job->cmdq_id = cmdq->id; + is_first_job = xa_empty(&vdev->submitted_jobs_xa); - ret = __xa_alloc_cyclic(&vdev->submitted_jobs_xa, &job->job_id, job, file_priv->job_limit, - &file_priv->job_id_next, GFP_KERNEL); + ret = xa_alloc_cyclic(&vdev->submitted_jobs_xa, &job->job_id, job, file_priv->job_limit, + &file_priv->job_id_next, GFP_KERNEL); if (ret < 0) { ivpu_dbg(vdev, JOB, "Too many active jobs in ctx %d\n", file_priv->ctx.id); ret = -EBUSY; - goto err_unlock_submitted_jobs_xa; + goto err_unlock; } ret = ivpu_cmdq_push_job(cmdq, job); @@ -558,25 +664,25 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority) } trace_job("submit", job); - ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d prio %d addr 0x%llx next %d\n", - job->job_id, file_priv->ctx.id, job->engine_idx, priority, + ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d cmdq_id %u engine %d prio %d addr 0x%llx next %d\n", + job->job_id, file_priv->ctx.id, cmdq->id, job->engine_idx, cmdq->priority, job->cmd_buf_vpu_addr, cmdq->jobq->header.tail); - xa_unlock(&vdev->submitted_jobs_xa); - mutex_unlock(&file_priv->lock); - if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) + if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) { ivpu_job_signal_and_destroy(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS); + } + + mutex_unlock(&vdev->submitted_jobs_lock); return 0; err_erase_xa: - __xa_erase(&vdev->submitted_jobs_xa, job->job_id); -err_unlock_submitted_jobs_xa: - xa_unlock(&vdev->submitted_jobs_xa); -err_unlock_file_priv: + xa_erase(&vdev->submitted_jobs_xa, job->job_id); +err_unlock: mutex_unlock(&file_priv->lock); + mutex_unlock(&vdev->submitted_jobs_lock); ivpu_rpm_put(vdev); return ret; } @@ -585,7 +691,7 @@ static int ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32 *buf_handles, u32 buf_count, u32 commands_offset) { - struct ivpu_file_priv *file_priv = file->driver_priv; + struct ivpu_file_priv *file_priv = job->file_priv; struct ivpu_device *vdev = file_priv->vdev; struct ww_acquire_ctx acquire_ctx; enum dma_resv_usage usage; @@ -647,49 +753,20 @@ unlock_reservations: return ret; } -static inline u8 ivpu_job_to_hws_priority(struct ivpu_file_priv *file_priv, u8 priority) +static int ivpu_submit(struct drm_file *file, struct ivpu_file_priv *file_priv, u32 cmdq_id, + u32 buffer_count, u32 engine, void __user *buffers_ptr, u32 cmds_offset, + u8 priority) { - if (priority == DRM_IVPU_JOB_PRIORITY_DEFAULT) - return DRM_IVPU_JOB_PRIORITY_NORMAL; - - return priority - 1; -} - -int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file) -{ - struct ivpu_file_priv *file_priv = file->driver_priv; struct ivpu_device *vdev = file_priv->vdev; - struct drm_ivpu_submit *params = data; struct ivpu_job *job; u32 *buf_handles; int idx, ret; - u8 priority; - - if (params->engine != DRM_IVPU_ENGINE_COMPUTE) - return -EINVAL; - if (params->priority > DRM_IVPU_JOB_PRIORITY_REALTIME) - return -EINVAL; - - if (params->buffer_count == 0 || params->buffer_count > JOB_MAX_BUFFER_COUNT) - return -EINVAL; - - if (!IS_ALIGNED(params->commands_offset, 8)) - return -EINVAL; - - if (!file_priv->ctx.id) - return -EINVAL; - - if (file_priv->has_mmu_faults) - return -EBADFD; - - buf_handles = kcalloc(params->buffer_count, sizeof(u32), GFP_KERNEL); + buf_handles = kcalloc(buffer_count, sizeof(u32), GFP_KERNEL); if (!buf_handles) return -ENOMEM; - ret = copy_from_user(buf_handles, - (void __user *)params->buffers_ptr, - params->buffer_count * sizeof(u32)); + ret = copy_from_user(buf_handles, buffers_ptr, buffer_count * sizeof(u32)); if (ret) { ret = -EFAULT; goto err_free_handles; @@ -700,27 +777,24 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_free_handles; } - ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n", - file_priv->ctx.id, params->buffer_count); + ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u cmdq_id %u buf_count %u\n", + file_priv->ctx.id, cmdq_id, buffer_count); - job = ivpu_job_create(file_priv, params->engine, params->buffer_count); + job = ivpu_job_create(file_priv, engine, buffer_count); if (!job) { ivpu_err(vdev, "Failed to create job\n"); ret = -ENOMEM; goto err_exit_dev; } - ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, params->buffer_count, - params->commands_offset); + ret = ivpu_job_prepare_bos_for_submit(file, job, buf_handles, buffer_count, cmds_offset); if (ret) { ivpu_err(vdev, "Failed to prepare job: %d\n", ret); goto err_destroy_job; } - priority = ivpu_job_to_hws_priority(file_priv, params->priority); - down_read(&vdev->pm->reset_lock); - ret = ivpu_job_submit(job, priority); + ret = ivpu_job_submit(job, priority, cmdq_id); up_read(&vdev->pm->reset_lock); if (ret) goto err_signal_fence; @@ -740,12 +814,137 @@ err_free_handles: return ret; } +int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct ivpu_file_priv *file_priv = file->driver_priv; + struct drm_ivpu_submit *args = data; + u8 priority; + + if (args->engine != DRM_IVPU_ENGINE_COMPUTE) + return -EINVAL; + + if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME) + return -EINVAL; + + if (args->buffer_count == 0 || args->buffer_count > JOB_MAX_BUFFER_COUNT) + return -EINVAL; + + if (!IS_ALIGNED(args->commands_offset, 8)) + return -EINVAL; + + if (!file_priv->ctx.id) + return -EINVAL; + + if (file_priv->has_mmu_faults) + return -EBADFD; + + priority = ivpu_job_to_jsm_priority(args->priority); + + return ivpu_submit(file, file_priv, 0, args->buffer_count, args->engine, + (void __user *)args->buffers_ptr, args->commands_offset, priority); +} + +int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct ivpu_file_priv *file_priv = file->driver_priv; + struct drm_ivpu_cmdq_submit *args = data; + + if (!ivpu_is_capable(file_priv->vdev, DRM_IVPU_CAP_MANAGE_CMDQ)) + return -ENODEV; + + if (args->cmdq_id < IVPU_CMDQ_MIN_ID || args->cmdq_id > IVPU_CMDQ_MAX_ID) + return -EINVAL; + + if (args->buffer_count == 0 || args->buffer_count > JOB_MAX_BUFFER_COUNT) + return -EINVAL; + + if (!IS_ALIGNED(args->commands_offset, 8)) + return -EINVAL; + + if (!file_priv->ctx.id) + return -EINVAL; + + if (file_priv->has_mmu_faults) + return -EBADFD; + + return ivpu_submit(file, file_priv, args->cmdq_id, args->buffer_count, VPU_ENGINE_COMPUTE, + (void __user *)args->buffers_ptr, args->commands_offset, 0); +} + +int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct ivpu_file_priv *file_priv = file->driver_priv; + struct ivpu_device *vdev = file_priv->vdev; + struct drm_ivpu_cmdq_create *args = data; + struct ivpu_cmdq *cmdq; + int ret; + + if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ)) + return -ENODEV; + + if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME) + return -EINVAL; + + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + + mutex_lock(&file_priv->lock); + + cmdq = ivpu_cmdq_create(file_priv, ivpu_job_to_jsm_priority(args->priority), false); + if (cmdq) + args->cmdq_id = cmdq->id; + + mutex_unlock(&file_priv->lock); + + ivpu_rpm_put(vdev); + + return cmdq ? 0 : -ENOMEM; +} + +int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct ivpu_file_priv *file_priv = file->driver_priv; + struct ivpu_device *vdev = file_priv->vdev; + struct drm_ivpu_cmdq_destroy *args = data; + struct ivpu_cmdq *cmdq; + u32 cmdq_id = 0; + int ret; + + if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ)) + return -ENODEV; + + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + + mutex_lock(&file_priv->lock); + + cmdq = xa_load(&file_priv->cmdq_xa, args->cmdq_id); + if (!cmdq || cmdq->is_legacy) { + ret = -ENOENT; + } else { + cmdq_id = cmdq->id; + ivpu_cmdq_destroy(file_priv, cmdq); + ret = 0; + } + + mutex_unlock(&file_priv->lock); + + /* Abort any pending jobs only if cmdq was destroyed */ + if (!ret) + ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id); + + ivpu_rpm_put(vdev); + + return ret; +} + static void ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg) { struct vpu_ipc_msg_payload_job_done *payload; - int ret; if (!jsm_msg) { ivpu_err(vdev, "IPC message has no JSM payload\n"); @@ -758,9 +957,10 @@ ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr, } payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload; - ret = ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status); - if (!ret && !xa_empty(&vdev->submitted_jobs_xa)) - ivpu_start_job_timeout_detection(vdev); + + mutex_lock(&vdev->submitted_jobs_lock); + ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status); + mutex_unlock(&vdev->submitted_jobs_lock); } void ivpu_job_done_consumer_init(struct ivpu_device *vdev) @@ -773,3 +973,57 @@ void ivpu_job_done_consumer_fini(struct ivpu_device *vdev) { ivpu_ipc_consumer_del(vdev, &vdev->job_done_consumer); } + +void ivpu_context_abort_work_fn(struct work_struct *work) +{ + struct ivpu_device *vdev = container_of(work, struct ivpu_device, context_abort_work); + struct ivpu_file_priv *file_priv; + struct ivpu_job *job; + unsigned long ctx_id; + unsigned long id; + + if (drm_WARN_ON(&vdev->drm, pm_runtime_get_if_active(vdev->drm.dev) <= 0)) + return; + + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) + if (ivpu_jsm_reset_engine(vdev, 0)) + return; + + mutex_lock(&vdev->context_list_lock); + xa_for_each(&vdev->context_xa, ctx_id, file_priv) { + if (!file_priv->has_mmu_faults || file_priv->aborted) + continue; + + mutex_lock(&file_priv->lock); + ivpu_context_abort_locked(file_priv); + mutex_unlock(&file_priv->lock); + } + mutex_unlock(&vdev->context_list_lock); + + /* + * We will not receive new MMU event interrupts until existing events are discarded + * however, we want to discard these events only after aborting the faulty context + * to avoid generating new faults from that context + */ + ivpu_mmu_discard_events(vdev); + + if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW) + goto runtime_put; + + if (ivpu_jsm_hws_resume_engine(vdev, 0)) + return; + /* + * In hardware scheduling mode NPU already has stopped processing jobs + * and won't send us any further notifications, thus we have to free job related resources + * and notify userspace + */ + mutex_lock(&vdev->submitted_jobs_lock); + xa_for_each(&vdev->submitted_jobs_xa, id, job) + if (job->file_priv->aborted) + ivpu_job_signal_and_destroy(vdev, job->job_id, DRM_IVPU_JOB_STATUS_ABORTED); + mutex_unlock(&vdev->submitted_jobs_lock); + +runtime_put: + pm_runtime_mark_last_busy(vdev->drm.dev); + pm_runtime_put_autosuspend(vdev->drm.dev); +} diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h index 8b19e3f8b4cf..2e301c2eea7b 100644 --- a/drivers/accel/ivpu/ivpu_job.h +++ b/drivers/accel/ivpu/ivpu_job.h @@ -30,8 +30,8 @@ struct ivpu_cmdq { u32 entry_count; u32 id; u32 db_id; - bool db_registered; u8 priority; + bool is_legacy; }; /** @@ -51,6 +51,7 @@ struct ivpu_job { struct ivpu_file_priv *file_priv; struct dma_fence *done_fence; u64 cmd_buf_vpu_addr; + u32 cmdq_id; u32 job_id; u32 engine_idx; size_t bo_count; @@ -58,14 +59,19 @@ struct ivpu_job { }; int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file); void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv); void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv); void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev); +void ivpu_cmdq_abort_all_jobs(struct ivpu_device *vdev, u32 ctx_id, u32 cmdq_id); void ivpu_job_done_consumer_init(struct ivpu_device *vdev); void ivpu_job_done_consumer_fini(struct ivpu_device *vdev); +void ivpu_context_abort_work_fn(struct work_struct *work); void ivpu_jobs_abort_all(struct ivpu_device *vdev); diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c index 30a40be76930..0256b2dfefc1 100644 --- a/drivers/accel/ivpu/ivpu_jsm_msg.c +++ b/drivers/accel/ivpu/ivpu_jsm_msg.c @@ -7,6 +7,8 @@ #include "ivpu_hw.h" #include "ivpu_ipc.h" #include "ivpu_jsm_msg.h" +#include "ivpu_pm.h" +#include "vpu_jsm_api.h" const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type) { @@ -162,8 +164,10 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 engine) ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_ENGINE_RESET_DONE, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); - if (ret) + if (ret) { ivpu_err_ratelimited(vdev, "Failed to reset engine %d: %d\n", engine, ret); + ivpu_pm_trigger_recovery(vdev, "Engine reset failed"); + } return ret; } @@ -353,8 +357,10 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine) ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); - if (ret) + if (ret) { ivpu_err_ratelimited(vdev, "Failed to resume engine %d: %d\n", engine, ret); + ivpu_pm_trigger_recovery(vdev, "Engine resume failed"); + } return ret; } @@ -407,26 +413,18 @@ int ivpu_jsm_hws_setup_priority_bands(struct ivpu_device *vdev) { struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP }; struct vpu_jsm_msg resp; + struct ivpu_hw_info *hw = vdev->hw; + struct vpu_ipc_msg_payload_hws_priority_band_setup *setup = + &req.payload.hws_priority_band_setup; int ret; - /* Idle */ - req.payload.hws_priority_band_setup.grace_period[0] = 0; - req.payload.hws_priority_band_setup.process_grace_period[0] = 50000; - req.payload.hws_priority_band_setup.process_quantum[0] = 160000; - /* Normal */ - req.payload.hws_priority_band_setup.grace_period[1] = 50000; - req.payload.hws_priority_band_setup.process_grace_period[1] = 50000; - req.payload.hws_priority_band_setup.process_quantum[1] = 300000; - /* Focus */ - req.payload.hws_priority_band_setup.grace_period[2] = 50000; - req.payload.hws_priority_band_setup.process_grace_period[2] = 50000; - req.payload.hws_priority_band_setup.process_quantum[2] = 200000; - /* Realtime */ - req.payload.hws_priority_band_setup.grace_period[3] = 0; - req.payload.hws_priority_band_setup.process_grace_period[3] = 50000; - req.payload.hws_priority_band_setup.process_quantum[3] = 200000; - - req.payload.hws_priority_band_setup.normal_band_percentage = 10; + for (int band = VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE; + band < VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT; band++) { + setup->grace_period[band] = hw->hws.grace_period[band]; + setup->process_grace_period[band] = hw->hws.process_grace_period[band]; + setup->process_quantum[band] = hw->hws.process_quantum[band]; + } + setup->normal_band_percentage = 10; ret = ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP_RSP, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index 26ef52fbb93e..5ea010568faa 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -20,6 +20,12 @@ #define IVPU_MMU_REG_CR0 0x00200020u #define IVPU_MMU_REG_CR0ACK 0x00200024u #define IVPU_MMU_REG_CR0ACK_VAL_MASK GENMASK(31, 0) +#define IVPU_MMU_REG_CR0_ATSCHK_MASK BIT(4) +#define IVPU_MMU_REG_CR0_CMDQEN_MASK BIT(3) +#define IVPU_MMU_REG_CR0_EVTQEN_MASK BIT(2) +#define IVPU_MMU_REG_CR0_PRIQEN_MASK BIT(1) +#define IVPU_MMU_REG_CR0_SMMUEN_MASK BIT(0) + #define IVPU_MMU_REG_CR1 0x00200028u #define IVPU_MMU_REG_CR2 0x0020002cu #define IVPU_MMU_REG_IRQ_CTRL 0x00200050u @@ -141,12 +147,6 @@ #define IVPU_MMU_IRQ_EVTQ_EN BIT(2) #define IVPU_MMU_IRQ_GERROR_EN BIT(0) -#define IVPU_MMU_CR0_ATSCHK BIT(4) -#define IVPU_MMU_CR0_CMDQEN BIT(3) -#define IVPU_MMU_CR0_EVTQEN BIT(2) -#define IVPU_MMU_CR0_PRIQEN BIT(1) -#define IVPU_MMU_CR0_SMMUEN BIT(0) - #define IVPU_MMU_CR1_TABLE_SH GENMASK(11, 10) #define IVPU_MMU_CR1_TABLE_OC GENMASK(9, 8) #define IVPU_MMU_CR1_TABLE_IC GENMASK(7, 6) @@ -596,7 +596,7 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev) REGV_WR32(IVPU_MMU_REG_CMDQ_PROD, 0); REGV_WR32(IVPU_MMU_REG_CMDQ_CONS, 0); - val = IVPU_MMU_CR0_CMDQEN; + val = REG_SET_FLD(IVPU_MMU_REG_CR0, CMDQEN, 0); ret = ivpu_mmu_reg_write_cr0(vdev, val); if (ret) return ret; @@ -617,12 +617,12 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev) REGV_WR32(IVPU_MMU_REG_EVTQ_PROD_SEC, 0); REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, 0); - val |= IVPU_MMU_CR0_EVTQEN; + val = REG_SET_FLD(IVPU_MMU_REG_CR0, EVTQEN, val); ret = ivpu_mmu_reg_write_cr0(vdev, val); if (ret) return ret; - val |= IVPU_MMU_CR0_ATSCHK; + val = REG_SET_FLD(IVPU_MMU_REG_CR0, ATSCHK, val); ret = ivpu_mmu_reg_write_cr0(vdev, val); if (ret) return ret; @@ -631,7 +631,7 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev) if (ret) return ret; - val |= IVPU_MMU_CR0_SMMUEN; + val = REG_SET_FLD(IVPU_MMU_REG_CR0, SMMUEN, val); return ivpu_mmu_reg_write_cr0(vdev, val); } @@ -725,8 +725,8 @@ static int ivpu_mmu_cdtab_entry_set(struct ivpu_device *vdev, u32 ssid, u64 cd_d cd[2] = 0; cd[3] = 0x0000000000007444; - /* For global context generate memory fault on VPU */ - if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID) + /* For global and reserved contexts generate memory fault on VPU */ + if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID || ssid == IVPU_RESERVED_CONTEXT_MMU_SSID) cd[0] |= IVPU_MMU_CD_0_A; if (valid) @@ -870,28 +870,107 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev) return evt; } +static int ivpu_mmu_evtq_set(struct ivpu_device *vdev, bool enable) +{ + u32 val = REGV_RD32(IVPU_MMU_REG_CR0); + + if (enable) + val = REG_SET_FLD(IVPU_MMU_REG_CR0, EVTQEN, val); + else + val = REG_CLR_FLD(IVPU_MMU_REG_CR0, EVTQEN, val); + REGV_WR32(IVPU_MMU_REG_CR0, val); + + return REGV_POLL_FLD(IVPU_MMU_REG_CR0ACK, VAL, val, IVPU_MMU_REG_TIMEOUT_US); +} + +static int ivpu_mmu_evtq_enable(struct ivpu_device *vdev) +{ + return ivpu_mmu_evtq_set(vdev, true); +} + +static int ivpu_mmu_evtq_disable(struct ivpu_device *vdev) +{ + return ivpu_mmu_evtq_set(vdev, false); +} + +void ivpu_mmu_discard_events(struct ivpu_device *vdev) +{ + struct ivpu_mmu_info *mmu = vdev->mmu; + + mutex_lock(&mmu->lock); + /* + * Disable event queue (stop MMU from updating the producer) + * to allow synchronization of consumer and producer indexes + */ + ivpu_mmu_evtq_disable(vdev); + + vdev->mmu->evtq.cons = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC); + REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons); + vdev->mmu->evtq.prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC); + + ivpu_mmu_evtq_enable(vdev); + + drm_WARN_ON_ONCE(&vdev->drm, vdev->mmu->evtq.cons != vdev->mmu->evtq.prod); + + mutex_unlock(&mmu->lock); +} + +int ivpu_mmu_disable_ssid_events(struct ivpu_device *vdev, u32 ssid) +{ + struct ivpu_mmu_info *mmu = vdev->mmu; + struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab; + u64 *entry; + u64 val; + + if (ssid > IVPU_MMU_CDTAB_ENT_COUNT) + return -EINVAL; + + mutex_lock(&mmu->lock); + + entry = cdtab->base + (ssid * IVPU_MMU_CDTAB_ENT_SIZE); + + val = READ_ONCE(entry[0]); + val &= ~IVPU_MMU_CD_0_R; + WRITE_ONCE(entry[0], val); + + if (!ivpu_is_force_snoop_enabled(vdev)) + clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE); + + ivpu_mmu_cmdq_write_cfgi_all(vdev); + ivpu_mmu_cmdq_sync(vdev); + + mutex_unlock(&mmu->lock); + + return 0; +} + void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev) { + struct ivpu_file_priv *file_priv; u32 *event; u32 ssid; ivpu_dbg(vdev, IRQ, "MMU event queue\n"); - while ((event = ivpu_mmu_get_event(vdev)) != NULL) { - ivpu_mmu_dump_event(vdev, event); - - ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, event[0]); - if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID) { + while ((event = ivpu_mmu_get_event(vdev))) { + ssid = FIELD_GET(IVPU_MMU_EVT_SSID_MASK, *event); + if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID || + ssid == IVPU_RESERVED_CONTEXT_MMU_SSID) { + ivpu_mmu_dump_event(vdev, event); ivpu_pm_trigger_recovery(vdev, "MMU event"); return; } - ivpu_mmu_user_context_mark_invalid(vdev, ssid); - REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons); + file_priv = xa_load(&vdev->context_xa, ssid); + if (file_priv) { + if (!READ_ONCE(file_priv->has_mmu_faults)) { + ivpu_mmu_dump_event(vdev, event); + WRITE_ONCE(file_priv->has_mmu_faults, true); + } + } } - if (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_MMU_EVTQ)) - ivpu_err_ratelimited(vdev, "IRQ FIFO full\n"); + queue_work(system_wq, &vdev->context_abort_work); } void ivpu_mmu_evtq_dump(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_mmu.h b/drivers/accel/ivpu/ivpu_mmu.h index 7afea9cd8731..1ce7529746ad 100644 --- a/drivers/accel/ivpu/ivpu_mmu.h +++ b/drivers/accel/ivpu/ivpu_mmu.h @@ -47,5 +47,7 @@ int ivpu_mmu_invalidate_tlb(struct ivpu_device *vdev, u16 ssid); void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev); void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev); void ivpu_mmu_evtq_dump(struct ivpu_device *vdev); +void ivpu_mmu_discard_events(struct ivpu_device *vdev); +int ivpu_mmu_disable_ssid_events(struct ivpu_device *vdev, u32 ssid); #endif /* __IVPU_MMU_H__ */ diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c index 0af614dfb6f9..f0267efa55aa 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.c +++ b/drivers/accel/ivpu/ivpu_mmu_context.c @@ -635,16 +635,3 @@ void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev) ivpu_mmu_cd_clear(vdev, vdev->rctx.id); ivpu_mmu_context_fini(vdev, &vdev->rctx); } - -void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid) -{ - struct ivpu_file_priv *file_priv; - - xa_lock(&vdev->context_xa); - - file_priv = xa_load(&vdev->context_xa, ssid); - if (file_priv) - file_priv->has_mmu_faults = true; - - xa_unlock(&vdev->context_xa); -} diff --git a/drivers/accel/ivpu/ivpu_mmu_context.h b/drivers/accel/ivpu/ivpu_mmu_context.h index 8042fc067062..f255310968cf 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.h +++ b/drivers/accel/ivpu/ivpu_mmu_context.h @@ -37,8 +37,6 @@ void ivpu_mmu_global_context_fini(struct ivpu_device *vdev); int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev); void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev); -void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid); - int ivpu_mmu_context_insert_node(struct ivpu_mmu_context *ctx, const struct ivpu_addr_range *range, u64 size, struct drm_mm_node *node); void ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *node); diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c index ffe7b10f8a76..2a043baf10ca 100644 --- a/drivers/accel/ivpu/ivpu_ms.c +++ b/drivers/accel/ivpu/ivpu_ms.c @@ -4,6 +4,7 @@ */ #include <drm/drm_file.h> +#include <linux/pm_runtime.h> #include "ivpu_drv.h" #include "ivpu_gem.h" @@ -44,6 +45,10 @@ int ivpu_ms_start_ioctl(struct drm_device *dev, void *data, struct drm_file *fil args->sampling_period_ns < MS_MIN_SAMPLE_PERIOD_NS) return -EINVAL; + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + mutex_lock(&file_priv->ms_lock); if (get_instance_by_mask(file_priv, args->metric_group_mask)) { @@ -96,6 +101,8 @@ err_free_ms: kfree(ms); unlock: mutex_unlock(&file_priv->ms_lock); + + ivpu_rpm_put(vdev); return ret; } @@ -160,6 +167,10 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file * if (!args->metric_group_mask) return -EINVAL; + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + mutex_lock(&file_priv->ms_lock); ms = get_instance_by_mask(file_priv, args->metric_group_mask); @@ -187,6 +198,7 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file * unlock: mutex_unlock(&file_priv->ms_lock); + ivpu_rpm_put(vdev); return ret; } @@ -204,11 +216,17 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file { struct ivpu_file_priv *file_priv = file->driver_priv; struct drm_ivpu_metric_streamer_stop *args = data; + struct ivpu_device *vdev = file_priv->vdev; struct ivpu_ms_instance *ms; + int ret; if (!args->metric_group_mask) return -EINVAL; + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + mutex_lock(&file_priv->ms_lock); ms = get_instance_by_mask(file_priv, args->metric_group_mask); @@ -217,6 +235,7 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file mutex_unlock(&file_priv->ms_lock); + ivpu_rpm_put(vdev); return ms ? 0 : -EINVAL; } @@ -281,6 +300,9 @@ unlock: void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv) { struct ivpu_ms_instance *ms, *tmp; + struct ivpu_device *vdev = file_priv->vdev; + + pm_runtime_get_sync(vdev->drm.dev); mutex_lock(&file_priv->ms_lock); @@ -293,6 +315,8 @@ void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv) free_instance(file_priv, ms); mutex_unlock(&file_priv->ms_lock); + + pm_runtime_put_autosuspend(vdev->drm.dev); } void ivpu_ms_cleanup_all(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 5060c5dd40d1..ac0e22454596 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -177,16 +177,11 @@ void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason) return; } - if (ivpu_is_fpga(vdev)) { - ivpu_err(vdev, "Recovery not available on FPGA\n"); - return; - } - /* Trigger recovery if it's not in progress */ if (atomic_cmpxchg(&vdev->pm->reset_pending, 0, 1) == 0) { ivpu_hw_diagnose_failure(vdev); ivpu_hw_irq_disable(vdev); /* Disable IRQ early to protect from IRQ storm */ - queue_work(system_long_wq, &vdev->pm->recovery_work); + queue_work(system_unbound_wq, &vdev->pm->recovery_work); } } @@ -433,16 +428,17 @@ int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent) active_us = (DCT_PERIOD_US * active_percent) / 100; inactive_us = DCT_PERIOD_US - active_us; + vdev->pm->dct_active_percent = active_percent; + + ivpu_dbg(vdev, PM, "DCT requested %u%% (D0: %uus, D0i2: %uus)\n", + active_percent, active_us, inactive_us); + ret = ivpu_jsm_dct_enable(vdev, active_us, inactive_us); if (ret) { ivpu_err_ratelimited(vdev, "Failed to enable DCT: %d\n", ret); return ret; } - vdev->pm->dct_active_percent = active_percent; - - ivpu_dbg(vdev, PM, "DCT set to %u%% (D0: %uus, D0i2: %uus)\n", - active_percent, active_us, inactive_us); return 0; } @@ -450,27 +446,29 @@ int ivpu_pm_dct_disable(struct ivpu_device *vdev) { int ret; + vdev->pm->dct_active_percent = 0; + + ivpu_dbg(vdev, PM, "DCT requested to be disabled\n"); + ret = ivpu_jsm_dct_disable(vdev); if (ret) { ivpu_err_ratelimited(vdev, "Failed to disable DCT: %d\n", ret); return ret; } - vdev->pm->dct_active_percent = 0; - - ivpu_dbg(vdev, PM, "DCT disabled\n"); return 0; } -void ivpu_pm_dct_irq_thread_handler(struct ivpu_device *vdev) +void ivpu_pm_irq_dct_work_fn(struct work_struct *work) { + struct ivpu_device *vdev = container_of(work, struct ivpu_device, irq_dct_work); bool enable; int ret; if (ivpu_hw_btrs_dct_get_request(vdev, &enable)) return; - if (vdev->pm->dct_active_percent) + if (enable) ret = ivpu_pm_dct_enable(vdev, DCT_DEFAULT_ACTIVE_PERCENT); else ret = ivpu_pm_dct_disable(vdev); diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h index b70efe6c36e4..89b264cc0e3e 100644 --- a/drivers/accel/ivpu/ivpu_pm.h +++ b/drivers/accel/ivpu/ivpu_pm.h @@ -45,6 +45,6 @@ void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev); int ivpu_pm_dct_init(struct ivpu_device *vdev); int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent); int ivpu_pm_dct_disable(struct ivpu_device *vdev); -void ivpu_pm_dct_irq_thread_handler(struct ivpu_device *vdev); +void ivpu_pm_irq_dct_work_fn(struct work_struct *work); #endif /* __IVPU_PM_H__ */ diff --git a/drivers/accel/ivpu/ivpu_sysfs.c b/drivers/accel/ivpu/ivpu_sysfs.c index 616477fc17fa..268ab7744a8b 100644 --- a/drivers/accel/ivpu/ivpu_sysfs.c +++ b/drivers/accel/ivpu/ivpu_sysfs.c @@ -1,17 +1,22 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2024 Intel Corporation + * Copyright (C) 2024-2025 Intel Corporation */ #include <linux/device.h> #include <linux/err.h> +#include <linux/pm_runtime.h> +#include <linux/units.h> #include "ivpu_drv.h" +#include "ivpu_gem.h" #include "ivpu_fw.h" #include "ivpu_hw.h" #include "ivpu_sysfs.h" -/* +/** + * DOC: npu_busy_time_us + * * npu_busy_time_us is the time that the device spent executing jobs. * The time is counted when and only when there are jobs submitted to firmware. * @@ -30,11 +35,12 @@ npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *b struct ivpu_device *vdev = to_ivpu_device(drm); ktime_t total, now = 0; - xa_lock(&vdev->submitted_jobs_xa); + mutex_lock(&vdev->submitted_jobs_lock); + total = vdev->busy_time; if (!xa_empty(&vdev->submitted_jobs_xa)) now = ktime_sub(ktime_get(), vdev->busy_start_ts); - xa_unlock(&vdev->submitted_jobs_xa); + mutex_unlock(&vdev->submitted_jobs_lock); return sysfs_emit(buf, "%lld\n", ktime_to_us(ktime_add(total, now))); } @@ -42,6 +48,30 @@ npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *b static DEVICE_ATTR_RO(npu_busy_time_us); /** + * DOC: npu_memory_utilization + * + * The npu_memory_utilization is used to report in bytes a current NPU memory utilization. + * + */ +static ssize_t +npu_memory_utilization_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct ivpu_device *vdev = to_ivpu_device(drm); + struct ivpu_bo *bo; + u64 total_npu_memory = 0; + + mutex_lock(&vdev->bo_list_lock); + list_for_each_entry(bo, &vdev->bo_list, bo_list_node) + total_npu_memory += bo->base.base.size; + mutex_unlock(&vdev->bo_list_lock); + + return sysfs_emit(buf, "%lld\n", total_npu_memory); +} + +static DEVICE_ATTR_RO(npu_memory_utilization); + +/** * DOC: sched_mode * * The sched_mode is used to report current NPU scheduling mode. @@ -62,9 +92,55 @@ sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf) static DEVICE_ATTR_RO(sched_mode); +/** + * DOC: npu_max_frequency + * + * The npu_max_frequency shows maximum frequency in MHz of the NPU's data + * processing unit + */ +static ssize_t +npu_max_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct ivpu_device *vdev = to_ivpu_device(drm); + u32 freq = ivpu_hw_dpu_max_freq_get(vdev); + + return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ); +} + +static DEVICE_ATTR_RO(npu_max_frequency_mhz); + +/** + * DOC: npu_current_frequency_mhz + * + * The npu_current_frequency_mhz shows current frequency in MHz of the NPU's + * data processing unit + */ +static ssize_t +npu_current_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct ivpu_device *vdev = to_ivpu_device(drm); + u32 freq = 0; + + /* Read frequency only if device is active, otherwise frequency is 0 */ + if (pm_runtime_get_if_active(vdev->drm.dev) > 0) { + freq = ivpu_hw_dpu_freq_get(vdev); + + pm_runtime_put_autosuspend(vdev->drm.dev); + } + + return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ); +} + +static DEVICE_ATTR_RO(npu_current_frequency_mhz); + static struct attribute *ivpu_dev_attrs[] = { &dev_attr_npu_busy_time_us.attr, + &dev_attr_npu_memory_utilization.attr, &dev_attr_sched_mode.attr, + &dev_attr_npu_max_frequency_mhz.attr, + &dev_attr_npu_current_frequency_mhz.attr, NULL, }; diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h index 908e68ea1c39..218468bbbcad 100644 --- a/drivers/accel/ivpu/vpu_boot_api.h +++ b/drivers/accel/ivpu/vpu_boot_api.h @@ -26,7 +26,7 @@ * Minor version changes when API backward compatibility is preserved. * Resets to 0 if Major version is incremented. */ -#define VPU_BOOT_API_VER_MINOR 26 +#define VPU_BOOT_API_VER_MINOR 28 /* * API header changed (field names, documentation, formatting) but API itself has not been changed @@ -76,8 +76,15 @@ struct vpu_firmware_header { * submission queue size and device capabilities. */ u32 preemption_buffer_2_size; + /* + * Maximum preemption buffer size that the FW can use: no need for the host + * driver to allocate more space than that specified by these fields. + * A value of 0 means no declared limit. + */ + u32 preemption_buffer_1_max_size; + u32 preemption_buffer_2_max_size; /* Space reserved for future preemption-related fields. */ - u32 preemption_reserved[6]; + u32 preemption_reserved[4]; /* FW image read only section start address, 4KB aligned */ u64 ro_section_start_address; /* FW image read only section size, 4KB aligned */ @@ -134,7 +141,7 @@ enum vpu_trace_destination { /* * Processor bit shifts (for loggable HW components). */ -#define VPU_TRACE_PROC_BIT_ARM 0 +#define VPU_TRACE_PROC_BIT_RESERVED 0 #define VPU_TRACE_PROC_BIT_LRT 1 #define VPU_TRACE_PROC_BIT_LNN 2 #define VPU_TRACE_PROC_BIT_SHV_0 3 diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h index 7215c144158c..4b6b2b3d2583 100644 --- a/drivers/accel/ivpu/vpu_jsm_api.h +++ b/drivers/accel/ivpu/vpu_jsm_api.h @@ -22,7 +22,7 @@ /* * Minor version changes when API backward compatibility is preserved. */ -#define VPU_JSM_API_VER_MINOR 25 +#define VPU_JSM_API_VER_MINOR 29 /* * API header changed (field names, documentation, formatting) but API itself has not been changed @@ -53,8 +53,7 @@ * Engine indexes. */ #define VPU_ENGINE_COMPUTE 0 -#define VPU_ENGINE_COPY 1 -#define VPU_ENGINE_NB 2 +#define VPU_ENGINE_NB 1 /* * VPU status values. @@ -126,11 +125,13 @@ enum { * When set, indicates that job queue uses native fences (as inline commands * in job queue). Such queues may also use legacy fences (as commands in batch buffers). * When cleared, indicates the job queue only uses legacy fences. - * NOTE: For queues using native fences, VPU expects that all jobs in the queue - * are immediately followed by an inline command object. This object is expected - * to be a fence signal command in most cases, but can also be a NOP in case the host - * does not need per-job fence signalling. Other inline commands objects can be - * inserted between "job and inline command" pairs. + * NOTES: + * 1. For queues using native fences, VPU expects that all jobs in the queue + * are immediately followed by an inline command object. This object is expected + * to be a fence signal command in most cases, but can also be a NOP in case the host + * does not need per-job fence signalling. Other inline commands objects can be + * inserted between "job and inline command" pairs. + * 2. Native fence queues are only supported on VPU 40xx onwards. */ VPU_JOB_QUEUE_FLAGS_USE_NATIVE_FENCE_MASK = (1 << 1U), @@ -275,6 +276,8 @@ struct vpu_inline_cmd { u64 value; /* User VA of the log buffer in which to add log entry on completion. */ u64 log_buffer_va; + /* NPU private data. */ + u64 npu_private_data; } fence; /* Other commands do not have a payload. */ /* Payload definition for future inline commands can be inserted here. */ @@ -791,12 +794,22 @@ struct vpu_jsm_metric_streamer_update { /** Metric group mask that identifies metric streamer instance. */ u64 metric_group_mask; /** - * Address and size of the buffer where the VPU will write metric data. If - * the buffer address is 0 or same as the currently used buffer the VPU will - * continue writing metric data to the current buffer. In this case the - * buffer size is ignored and the size of the current buffer is unchanged. - * If the address is non-zero and differs from the current buffer address the - * VPU will immediately switch data collection to the new buffer. + * Address and size of the buffer where the VPU will write metric data. + * This member dictates how the update operation should perform: + * 1. client needs information about the number of collected samples and the + * amount of data written to the current buffer + * 2. client wants to switch to a new buffer + * + * Case 1. is identified by the buffer address being 0 or the same as the + * currently used buffer address. In this case the buffer size is ignored and + * the size of the current buffer is unchanged. The VPU will return an update + * in the vpu_jsm_metric_streamer_done structure. The internal writing position + * into the buffer is not changed. + * + * Case 2. is identified by the address being non-zero and differs from the + * current buffer address. The VPU will immediately switch data collection to + * the new buffer. Then the VPU will return an update in the + * vpu_jsm_metric_streamer_done structure. */ u64 buffer_addr; u64 buffer_size; @@ -934,6 +947,7 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup { /* * Default quantum in 100ns units for scheduling across processes * within a priority band + * Minimum value supported by NPU is 1ms (10000 in 100ns units). */ u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS]; /* @@ -946,8 +960,10 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup { * in situations when it's starved by the focus band. */ u32 normal_band_percentage; - /* Reserved */ - u32 reserved_0; + /* + * TDR timeout value in milliseconds. Default value of 0 meaning no timeout. + */ + u32 tdr_timeout; }; /* @@ -1024,7 +1040,10 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties { s32 in_process_priority; /* Zero padding / Reserved */ u32 reserved_1; - /* Context quantum relative to other contexts of same priority in the same process */ + /* + * Context quantum relative to other contexts of same priority in the same process + * Minimum value supported by NPU is 1ms (10000 in 100ns units). + */ u64 context_quantum; /* Grace period when preempting context of the same priority within the same process */ u64 grace_period_same_priority; diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c index 8ab82e78dd94..13a14c6c6168 100644 --- a/drivers/accel/qaic/mhi_controller.c +++ b/drivers/accel/qaic/mhi_controller.c @@ -20,6 +20,11 @@ static unsigned int mhi_timeout_ms = 2000; /* 2 sec default */ module_param(mhi_timeout_ms, uint, 0600); MODULE_PARM_DESC(mhi_timeout_ms, "MHI controller timeout value"); +static const char *fw_image_paths[FAMILY_MAX] = { + [FAMILY_AIC100] = "qcom/aic100/sbl.bin", + [FAMILY_AIC200] = "qcom/aic200/sbl.bin", +}; + static const struct mhi_channel_config aic100_channels[] = { { .name = "QAIC_LOOPBACK", @@ -439,6 +444,297 @@ static const struct mhi_channel_config aic100_channels[] = { }, }; +static const struct mhi_channel_config aic200_channels[] = { + { + .name = "QAIC_LOOPBACK", + .num = 0, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_LOOPBACK", + .num = 1, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_SAHARA", + .num = 2, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_SBL, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_SAHARA", + .num = 3, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_SBL, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_SSR", + .num = 6, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_SSR", + .num = 7, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_CONTROL", + .num = 10, + .num_elements = 128, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_CONTROL", + .num = 11, + .num_elements = 128, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_LOGGING", + .num = 12, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_SBL, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_LOGGING", + .num = 13, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_SBL, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_STATUS", + .num = 14, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_STATUS", + .num = 15, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_TELEMETRY", + .num = 16, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_TELEMETRY", + .num = 17, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_TIMESYNC_PERIODIC", + .num = 22, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "QAIC_TIMESYNC_PERIODIC", + .num = 23, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "IPCR", + .num = 24, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_TO_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = false, + .wake_capable = false, + }, + { + .name = "IPCR", + .num = 25, + .num_elements = 32, + .local_elements = 0, + .event_ring = 0, + .dir = DMA_FROM_DEVICE, + .ee_mask = MHI_CH_EE_AMSS, + .pollcfg = 0, + .doorbell = MHI_DB_BRST_DISABLE, + .lpm_notify = false, + .offload_channel = false, + .doorbell_mode_switch = false, + .auto_queue = true, + .wake_capable = false, + }, +}; + static struct mhi_event_config aic100_events[] = { { .num_elements = 32, @@ -454,16 +750,44 @@ static struct mhi_event_config aic100_events[] = { }, }; -static struct mhi_controller_config aic100_config = { - .max_channels = 128, - .timeout_ms = 0, /* controlled by mhi_timeout */ - .buf_len = 0, - .num_channels = ARRAY_SIZE(aic100_channels), - .ch_cfg = aic100_channels, - .num_events = ARRAY_SIZE(aic100_events), - .event_cfg = aic100_events, - .use_bounce_buf = false, - .m2_no_db = false, +static struct mhi_event_config aic200_events[] = { + { + .num_elements = 32, + .irq_moderation_ms = 0, + .irq = 0, + .channel = U32_MAX, + .priority = 1, + .mode = MHI_DB_BRST_DISABLE, + .data_type = MHI_ER_CTRL, + .hardware_event = false, + .client_managed = false, + .offload_channel = false, + }, +}; + +static struct mhi_controller_config mhi_cntrl_configs[] = { + [FAMILY_AIC100] = { + .max_channels = 128, + .timeout_ms = 0, /* controlled by mhi_timeout */ + .buf_len = 0, + .num_channels = ARRAY_SIZE(aic100_channels), + .ch_cfg = aic100_channels, + .num_events = ARRAY_SIZE(aic100_events), + .event_cfg = aic100_events, + .use_bounce_buf = false, + .m2_no_db = false, + }, + [FAMILY_AIC200] = { + .max_channels = 128, + .timeout_ms = 0, /* controlled by mhi_timeout */ + .buf_len = 0, + .num_channels = ARRAY_SIZE(aic200_channels), + .ch_cfg = aic200_channels, + .num_events = ARRAY_SIZE(aic200_events), + .event_cfg = aic200_events, + .use_bounce_buf = false, + .m2_no_db = false, + }, }; static int mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 *out) @@ -545,8 +869,9 @@ static int mhi_reset_and_async_power_up(struct mhi_controller *mhi_cntrl) } struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, void __iomem *mhi_bar, - int mhi_irq, bool shared_msi) + int mhi_irq, bool shared_msi, int family) { + struct mhi_controller_config mhi_config = mhi_cntrl_configs[family]; struct mhi_controller *mhi_cntrl; int ret; @@ -581,11 +906,18 @@ struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, voi if (shared_msi) /* MSI shared with data path, no IRQF_NO_SUSPEND */ mhi_cntrl->irq_flags = IRQF_SHARED; - mhi_cntrl->fw_image = "qcom/aic100/sbl.bin"; + mhi_cntrl->fw_image = fw_image_paths[family]; + + if (family == FAMILY_AIC200) { + mhi_cntrl->name = "AIC200"; + mhi_cntrl->seg_len = SZ_512K; + } else { + mhi_cntrl->name = "AIC100"; + } /* use latest configured timeout */ - aic100_config.timeout_ms = mhi_timeout_ms; - ret = mhi_register_controller(mhi_cntrl, &aic100_config); + mhi_config.timeout_ms = mhi_timeout_ms; + ret = mhi_register_controller(mhi_cntrl, &mhi_config); if (ret) { pci_err(pci_dev, "mhi_register_controller failed %d\n", ret); return ERR_PTR(ret); diff --git a/drivers/accel/qaic/mhi_controller.h b/drivers/accel/qaic/mhi_controller.h index 500e7f4af2af..8939f6ae185e 100644 --- a/drivers/accel/qaic/mhi_controller.h +++ b/drivers/accel/qaic/mhi_controller.h @@ -8,7 +8,7 @@ #define MHICONTROLLERQAIC_H_ struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, void __iomem *mhi_bar, - int mhi_irq, bool shared_msi); + int mhi_irq, bool shared_msi, int family); void qaic_mhi_free_controller(struct mhi_controller *mhi_cntrl, bool link_up); void qaic_mhi_start_reset(struct mhi_controller *mhi_cntrl); void qaic_mhi_reset_done(struct mhi_controller *mhi_cntrl); diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h index 02561b6cecc6..0dbb8e32e4b9 100644 --- a/drivers/accel/qaic/qaic.h +++ b/drivers/accel/qaic/qaic.h @@ -32,6 +32,12 @@ #define to_accel_kdev(qddev) (to_drm(qddev)->accel->kdev) /* Return Linux device of accel node */ #define to_qaic_device(dev) (to_qaic_drm_device((dev))->qdev) +enum aic_families { + FAMILY_AIC100, + FAMILY_AIC200, + FAMILY_MAX, +}; + enum __packed dev_states { /* Device is offline or will be very soon */ QAIC_OFFLINE, @@ -113,10 +119,10 @@ struct qaic_device { struct pci_dev *pdev; /* Req. ID of request that will be queued next in MHI control device */ u32 next_seq_num; - /* Base address of bar 0 */ - void __iomem *bar_0; - /* Base address of bar 2 */ - void __iomem *bar_2; + /* Base address of the MHI bar */ + void __iomem *bar_mhi; + /* Base address of the DBCs bar */ + void __iomem *bar_dbc; /* Controller structure for MHI devices */ struct mhi_controller *mhi_cntrl; /* MHI control channel device */ diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index c20eb63750f5..43aba57b48f0 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -172,9 +172,10 @@ static void free_slice(struct kref *kref) static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_table **sgt_out, struct sg_table *sgt_in, u64 size, u64 offset) { - int total_len, len, nents, offf = 0, offl = 0; struct scatterlist *sg, *sgn, *sgf, *sgl; + unsigned int len, nents, offf, offl; struct sg_table *sgt; + size_t total_len; int ret, j; /* find out number of relevant nents needed for this mem */ @@ -182,6 +183,8 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl sgf = NULL; sgl = NULL; nents = 0; + offf = 0; + offl = 0; size = size ? size : PAGE_SIZE; for_each_sgtable_dma_sg(sgt_in, sg, j) { @@ -554,6 +557,7 @@ static bool invalid_sem(struct qaic_sem *sem) static int qaic_validate_req(struct qaic_device *qdev, struct qaic_attach_slice_entry *slice_ent, u32 count, u64 total_size) { + u64 total; int i; for (i = 0; i < count; i++) { @@ -563,7 +567,8 @@ static int qaic_validate_req(struct qaic_device *qdev, struct qaic_attach_slice_ invalid_sem(&slice_ent[i].sem2) || invalid_sem(&slice_ent[i].sem3)) return -EINVAL; - if (slice_ent[i].offset + slice_ent[i].size > total_size) + if (check_add_overflow(slice_ent[i].offset, slice_ent[i].size, &total) || + total > total_size) return -EINVAL; } diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index 4ddf89308ff5..3b415e2c9431 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -34,13 +34,46 @@ MODULE_IMPORT_NS("DMA_BUF"); -#define PCI_DEV_AIC080 0xa080 -#define PCI_DEV_AIC100 0xa100 +#define PCI_DEVICE_ID_QCOM_AIC080 0xa080 +#define PCI_DEVICE_ID_QCOM_AIC100 0xa100 +#define PCI_DEVICE_ID_QCOM_AIC200 0xa110 #define QAIC_NAME "qaic" #define QAIC_DESC "Qualcomm Cloud AI Accelerators" #define CNTL_MAJOR 5 #define CNTL_MINOR 0 +struct qaic_device_config { + /* Indicates the AIC family the device belongs to */ + int family; + /* A bitmask representing the available BARs */ + int bar_mask; + /* An index value used to identify the MHI controller BAR */ + unsigned int mhi_bar_idx; + /* An index value used to identify the DBCs BAR */ + unsigned int dbc_bar_idx; +}; + +static const struct qaic_device_config aic080_config = { + .family = FAMILY_AIC100, + .bar_mask = BIT(0) | BIT(2) | BIT(4), + .mhi_bar_idx = 0, + .dbc_bar_idx = 2, +}; + +static const struct qaic_device_config aic100_config = { + .family = FAMILY_AIC100, + .bar_mask = BIT(0) | BIT(2) | BIT(4), + .mhi_bar_idx = 0, + .dbc_bar_idx = 2, +}; + +static const struct qaic_device_config aic200_config = { + .family = FAMILY_AIC200, + .bar_mask = BIT(0) | BIT(1) | BIT(2) | BIT(4), + .mhi_bar_idx = 1, + .dbc_bar_idx = 2, +}; + bool datapath_polling; module_param(datapath_polling, bool, 0400); MODULE_PARM_DESC(datapath_polling, "Operate the datapath in polling mode"); @@ -208,7 +241,6 @@ static const struct drm_driver qaic_accel_driver = { .name = QAIC_NAME, .desc = QAIC_DESC, - .date = "20190618", .fops = &qaic_accel_fops, .open = qaic_open, @@ -353,7 +385,8 @@ void qaic_dev_reset_clean_local_state(struct qaic_device *qdev) release_dbc(qdev, i); } -static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_device_id *id) +static struct qaic_device *create_qdev(struct pci_dev *pdev, + const struct qaic_device_config *config) { struct device *dev = &pdev->dev; struct qaic_drm_device *qddev; @@ -366,12 +399,10 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de return NULL; qdev->dev_state = QAIC_OFFLINE; - if (id->device == PCI_DEV_AIC080 || id->device == PCI_DEV_AIC100) { - qdev->num_dbc = 16; - qdev->dbc = devm_kcalloc(dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL); - if (!qdev->dbc) - return NULL; - } + qdev->num_dbc = 16; + qdev->dbc = devm_kcalloc(dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL); + if (!qdev->dbc) + return NULL; qddev = devm_drm_dev_alloc(&pdev->dev, &qaic_accel_driver, struct qaic_drm_device, drm); if (IS_ERR(qddev)) @@ -427,17 +458,18 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de return qdev; } -static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev) +static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev, + const struct qaic_device_config *config) { int bars; int ret; - bars = pci_select_bars(pdev, IORESOURCE_MEM); + bars = pci_select_bars(pdev, IORESOURCE_MEM) & 0x3f; /* make sure the device has the expected BARs */ - if (bars != (BIT(0) | BIT(2) | BIT(4))) { - pci_dbg(pdev, "%s: expected BARs 0, 2, and 4 not found in device. Found 0x%x\n", - __func__, bars); + if (bars != config->bar_mask) { + pci_dbg(pdev, "%s: expected BARs %#x not found in device. Found %#x\n", + __func__, config->bar_mask, bars); return -EINVAL; } @@ -450,13 +482,13 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev) return ret; dma_set_max_seg_size(&pdev->dev, UINT_MAX); - qdev->bar_0 = devm_ioremap_resource(&pdev->dev, &pdev->resource[0]); - if (IS_ERR(qdev->bar_0)) - return PTR_ERR(qdev->bar_0); + qdev->bar_mhi = devm_ioremap_resource(&pdev->dev, &pdev->resource[config->mhi_bar_idx]); + if (IS_ERR(qdev->bar_mhi)) + return PTR_ERR(qdev->bar_mhi); - qdev->bar_2 = devm_ioremap_resource(&pdev->dev, &pdev->resource[2]); - if (IS_ERR(qdev->bar_2)) - return PTR_ERR(qdev->bar_2); + qdev->bar_dbc = devm_ioremap_resource(&pdev->dev, &pdev->resource[config->dbc_bar_idx]); + if (IS_ERR(qdev->bar_dbc)) + return PTR_ERR(qdev->bar_dbc); /* Managed release since we use pcim_enable_device above */ pci_set_master(pdev); @@ -466,14 +498,15 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev) static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev) { + int irq_count = qdev->num_dbc + 1; int mhi_irq; int ret; int i; /* Managed release since we use pcim_enable_device */ - ret = pci_alloc_irq_vectors(pdev, 32, 32, PCI_IRQ_MSI); + ret = pci_alloc_irq_vectors(pdev, irq_count, irq_count, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (ret == -ENOSPC) { - ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (ret < 0) return ret; @@ -486,7 +519,8 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev) * interrupted, it shouldn't race with itself. */ qdev->single_msi = true; - pci_info(pdev, "Allocating 32 MSIs failed, operating in 1 MSI mode. Performance may be impacted.\n"); + pci_info(pdev, "Allocating %d MSIs failed, operating in 1 MSI mode. Performance may be impacted.\n", + irq_count); } else if (ret < 0) { return ret; } @@ -516,21 +550,22 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev) static int qaic_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { + struct qaic_device_config *config = (struct qaic_device_config *)id->driver_data; struct qaic_device *qdev; int mhi_irq; int ret; int i; - qdev = create_qdev(pdev, id); + qdev = create_qdev(pdev, config); if (!qdev) return -ENOMEM; - ret = init_pci(qdev, pdev); + ret = init_pci(qdev, pdev, config); if (ret) return ret; for (i = 0; i < qdev->num_dbc; ++i) - qdev->dbc[i].dbc_base = qdev->bar_2 + QAIC_DBC_OFF(i); + qdev->dbc[i].dbc_base = qdev->bar_dbc + QAIC_DBC_OFF(i); mhi_irq = init_msi(qdev, pdev); if (mhi_irq < 0) @@ -540,8 +575,8 @@ static int qaic_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret; - qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_0, mhi_irq, - qdev->single_msi); + qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_mhi, mhi_irq, + qdev->single_msi, config->family); if (IS_ERR(qdev->mhi_cntrl)) { ret = PTR_ERR(qdev->mhi_cntrl); qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION); @@ -608,8 +643,9 @@ static struct mhi_driver qaic_mhi_driver = { }; static const struct pci_device_id qaic_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_QCOM, PCI_DEV_AIC080), }, - { PCI_DEVICE(PCI_VENDOR_ID_QCOM, PCI_DEV_AIC100), }, + { PCI_DEVICE_DATA(QCOM, AIC080, (kernel_ulong_t)&aic080_config), }, + { PCI_DEVICE_DATA(QCOM, AIC100, (kernel_ulong_t)&aic100_config), }, + { PCI_DEVICE_DATA(QCOM, AIC200, (kernel_ulong_t)&aic200_config), }, { } }; MODULE_DEVICE_TABLE(pci, qaic_ids); diff --git a/drivers/accel/qaic/qaic_timesync.c b/drivers/accel/qaic/qaic_timesync.c index 301f4462d51b..972833fabcfc 100644 --- a/drivers/accel/qaic/qaic_timesync.c +++ b/drivers/accel/qaic/qaic_timesync.c @@ -201,7 +201,7 @@ static int qaic_timesync_probe(struct mhi_device *mhi_dev, const struct mhi_devi goto free_sync_msg; /* Qtimer register pointer */ - mqtsdev->qtimer_addr = qdev->bar_0 + QTIMER_REG_OFFSET; + mqtsdev->qtimer_addr = qdev->bar_mhi + QTIMER_REG_OFFSET; timer_setup(timer, qaic_timesync_timer, 0); timer->expires = jiffies + msecs_to_jiffies(timesync_delay_ms); add_timer(timer); @@ -221,7 +221,7 @@ static void qaic_timesync_remove(struct mhi_device *mhi_dev) { struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev); - del_timer_sync(&mqtsdev->timer); + timer_delete_sync(&mqtsdev->timer); mhi_unprepare_from_transfer(mqtsdev->mhi_dev); kfree(mqtsdev->sync_msg); kfree(mqtsdev); diff --git a/drivers/accel/qaic/sahara.c b/drivers/accel/qaic/sahara.c index 6d772143d612..3ebcc1f7ff58 100644 --- a/drivers/accel/qaic/sahara.c +++ b/drivers/accel/qaic/sahara.c @@ -160,7 +160,7 @@ struct sahara_context { struct work_struct fw_work; struct work_struct dump_work; struct mhi_device *mhi_dev; - const char **image_table; + const char * const *image_table; u32 table_size; u32 active_image_id; const struct firmware *firmware; @@ -177,7 +177,7 @@ struct sahara_context { bool is_mem_dump_mode; }; -static const char *aic100_image_table[] = { +static const char * const aic100_image_table[] = { [1] = "qcom/aic100/fw1.bin", [2] = "qcom/aic100/fw2.bin", [4] = "qcom/aic100/fw4.bin", @@ -188,6 +188,34 @@ static const char *aic100_image_table[] = { [10] = "qcom/aic100/fw10.bin", }; +static const char * const aic200_image_table[] = { + [5] = "qcom/aic200/uefi.elf", + [12] = "qcom/aic200/aic200-nsp.bin", + [23] = "qcom/aic200/aop.mbn", + [32] = "qcom/aic200/tz.mbn", + [33] = "qcom/aic200/hypvm.mbn", + [39] = "qcom/aic200/aic200_abl.elf", + [40] = "qcom/aic200/apdp.mbn", + [41] = "qcom/aic200/devcfg.mbn", + [42] = "qcom/aic200/sec.elf", + [43] = "qcom/aic200/aic200-hlos.elf", + [49] = "qcom/aic200/shrm.elf", + [50] = "qcom/aic200/cpucp.elf", + [51] = "qcom/aic200/aop_devcfg.mbn", + [57] = "qcom/aic200/cpucp_dtbs.elf", + [62] = "qcom/aic200/uefi_dtbs.elf", + [63] = "qcom/aic200/xbl_ac_config.mbn", + [64] = "qcom/aic200/tz_ac_config.mbn", + [65] = "qcom/aic200/hyp_ac_config.mbn", + [66] = "qcom/aic200/pdp.elf", + [67] = "qcom/aic200/pdp_cdb.elf", + [68] = "qcom/aic200/sdi.mbn", + [69] = "qcom/aic200/dcd.mbn", + [73] = "qcom/aic200/gearvm.mbn", + [74] = "qcom/aic200/sti.bin", + [75] = "qcom/aic200/pvs.bin", +}; + static int sahara_find_image(struct sahara_context *context, u32 image_id) { int ret; @@ -748,8 +776,15 @@ static int sahara_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_ context->mhi_dev = mhi_dev; INIT_WORK(&context->fw_work, sahara_processing); INIT_WORK(&context->dump_work, sahara_dump_processing); - context->image_table = aic100_image_table; - context->table_size = ARRAY_SIZE(aic100_image_table); + + if (!strcmp(mhi_dev->mhi_cntrl->name, "AIC200")) { + context->image_table = aic200_image_table; + context->table_size = ARRAY_SIZE(aic200_image_table); + } else { + context->image_table = aic100_image_table; + context->table_size = ARRAY_SIZE(aic100_image_table); + } + context->active_image_id = SAHARA_IMAGE_ID_NONE; dev_set_drvdata(&mhi_dev->dev, context); @@ -772,8 +807,7 @@ static void sahara_mhi_remove(struct mhi_device *mhi_dev) cancel_work_sync(&context->fw_work); cancel_work_sync(&context->dump_work); - if (context->mem_dump) - vfree(context->mem_dump); + vfree(context->mem_dump); sahara_release_image(context); mhi_unprepare_from_transfer(mhi_dev); } |