diff options
Diffstat (limited to 'drivers/accel')
24 files changed, 436 insertions, 304 deletions
diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile index cf9bf19dedb9..5c7911554c46 100644 --- a/drivers/accel/amdxdna/Makefile +++ b/drivers/accel/amdxdna/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only amdxdna-y := \ + aie.o \ aie2_ctx.o \ aie2_error.o \ aie2_message.o \ diff --git a/drivers/accel/amdxdna/aie.c b/drivers/accel/amdxdna/aie.c new file mode 100644 index 000000000000..4b3d4493128e --- /dev/null +++ b/drivers/accel/amdxdna/aie.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026, Advanced Micro Devices, Inc. + */ + +#include <linux/errno.h> + +#include "aie.h" +#include "amdxdna_mailbox_helper.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +void aie_dump_mgmt_chann_debug(struct aie_device *aie) +{ + struct amdxdna_dev *xdna = aie->xdna; + + XDNA_DBG(xdna, "i2x tail 0x%x", aie->mgmt_i2x.mb_tail_ptr_reg); + XDNA_DBG(xdna, "i2x head 0x%x", aie->mgmt_i2x.mb_head_ptr_reg); + XDNA_DBG(xdna, "i2x ringbuf 0x%x", aie->mgmt_i2x.rb_start_addr); + XDNA_DBG(xdna, "i2x rsize 0x%x", aie->mgmt_i2x.rb_size); + XDNA_DBG(xdna, "x2i tail 0x%x", aie->mgmt_x2i.mb_tail_ptr_reg); + XDNA_DBG(xdna, "x2i head 0x%x", aie->mgmt_x2i.mb_head_ptr_reg); + XDNA_DBG(xdna, "x2i ringbuf 0x%x", aie->mgmt_x2i.rb_start_addr); + XDNA_DBG(xdna, "x2i rsize 0x%x", aie->mgmt_x2i.rb_size); + XDNA_DBG(xdna, "x2i chann index 0x%x", aie->mgmt_chan_idx); + XDNA_DBG(xdna, "mailbox protocol major 0x%x", aie->mgmt_prot_major); + XDNA_DBG(xdna, "mailbox protocol minor 0x%x", aie->mgmt_prot_minor); +} + +void aie_destroy_chann(struct aie_device *aie, struct mailbox_channel **chann) +{ + struct amdxdna_dev *xdna = aie->xdna; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + if (!*chann) + return; + + xdna_mailbox_stop_channel(*chann); + xdna_mailbox_free_channel(*chann); + *chann = NULL; +} + +int aie_send_mgmt_msg_wait(struct aie_device *aie, struct xdna_mailbox_msg *msg) +{ + struct amdxdna_dev *xdna = aie->xdna; + struct xdna_notify *hdl = msg->handle; + int ret; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + if (!aie->mgmt_chann) + return -ENODEV; + + ret = xdna_send_msg_wait(xdna, aie->mgmt_chann, msg); + if (ret == -ETIME) + aie_destroy_chann(aie, &aie->mgmt_chann); + + if (!ret && *hdl->status) { + XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x", + msg->opcode, *hdl->data); + ret = -EINVAL; + } + + return ret; +} + +int aie_check_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor) +{ + const struct amdxdna_fw_feature_tbl *feature; + bool found = false; + + for (feature = aie->xdna->dev_info->fw_feature_tbl; + feature->major; feature++) { + if (feature->major != fw_major) + continue; + if (fw_minor < feature->min_minor) + continue; + if (feature->max_minor > 0 && fw_minor > feature->max_minor) + continue; + + aie->feature_mask |= feature->features; + + /* firmware version matches one of the driver support entry */ + found = true; + } + + return found ? 0 : -EOPNOTSUPP; +} diff --git a/drivers/accel/amdxdna/aie.h b/drivers/accel/amdxdna/aie.h new file mode 100644 index 000000000000..1bea14b79c7c --- /dev/null +++ b/drivers/accel/amdxdna/aie.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2026, Advanced Micro Devices, Inc. + */ +#ifndef _AIE_H_ +#define _AIE_H_ + +#include "amdxdna_pci_drv.h" +#include "amdxdna_mailbox.h" + +struct aie_device { + struct amdxdna_dev *xdna; + struct mailbox_channel *mgmt_chann; + 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; + unsigned long feature_mask; +}; + +#define DECLARE_AIE_MSG(name, op) \ + DECLARE_XDNA_MSG_COMMON(name, op, -1) +#define AIE_FEATURE_ON(aie, feature) test_bit(feature, &(aie)->feature_mask) + +void aie_dump_mgmt_chann_debug(struct aie_device *aie); +void aie_destroy_chann(struct aie_device *aie, struct mailbox_channel **chann); +int aie_send_mgmt_msg_wait(struct aie_device *aie, struct xdna_mailbox_msg *msg); +int aie_check_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor); + +#endif /* _AIE_H_ */ diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index eed3d0ec5413..a417b7d9ffac 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -270,17 +270,13 @@ aie2_sched_drvcmd_resp_handler(void *handle, void __iomem *data, size_t size) struct amdxdna_sched_job *job = handle; int ret = 0; - if (unlikely(!data)) - goto out; - - if (unlikely(size != sizeof(u32))) { + if (unlikely(!data || size != sizeof(u32))) { + job->drv_cmd->result = U32_MAX; ret = -EINVAL; - goto out; + } else { + job->drv_cmd->result = readl(data); } - job->drv_cmd->result = readl(data); - -out: aie2_sched_notify(job); return ret; } @@ -360,6 +356,7 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) ret = aie2_sync_bo(hwctx, job, aie2_sched_drvcmd_resp_handler); break; case ATTACH_DEBUG_BO: + case DETACH_DEBUG_BO: ret = aie2_config_debug_bo(hwctx, job, aie2_sched_drvcmd_resp_handler); break; default: @@ -515,7 +512,7 @@ static int aie2_alloc_resource(struct amdxdna_hwctx *hwctx) struct alloc_requests *xrs_req; int ret; - if (AIE2_FEATURE_ON(xdna->dev_handle, AIE2_TEMPORAL_ONLY)) { + if (AIE_FEATURE_ON(&xdna->dev_handle->aie, AIE2_TEMPORAL_ONLY)) { hwctx->num_unused_col = xdna->dev_handle->total_col - hwctx->num_col; hwctx->num_col = xdna->dev_handle->total_col; return aie2_create_context(xdna->dev_handle, hwctx); @@ -552,7 +549,7 @@ static void aie2_release_resource(struct amdxdna_hwctx *hwctx) struct amdxdna_dev *xdna = hwctx->client->xdna; int ret; - if (AIE2_FEATURE_ON(xdna->dev_handle, AIE2_TEMPORAL_ONLY)) { + if (AIE_FEATURE_ON(&xdna->dev_handle->aie, AIE2_TEMPORAL_ONLY)) { ret = aie2_destroy_context(xdna->dev_handle, hwctx); if (ret && ret != -ENODEV) XDNA_ERR(xdna, "Destroy temporal only context failed, ret %d", ret); @@ -818,7 +815,7 @@ static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size if (!hwctx->cus) return -ENOMEM; - ret = amdxdna_pm_resume_get_locked(xdna); + ret = amdxdna_pm_resume_get(xdna); if (ret) goto free_cus; @@ -893,6 +890,7 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl, aie2_cmd_wait(hwctx, seq); if (cmd.result) { XDNA_ERR(xdna, "Response failure 0x%x", cmd.result); + ret = -EINVAL; goto put_obj; } @@ -965,7 +963,7 @@ again: found = false; down_write(&xdna->notifier_lock); list_for_each_entry(mapp, &abo->mem.umap_list, node) { - if (mapp->invalid) { + if (mapp->invalid && kref_get_unless_zero(&mapp->refcnt)) { found = true; break; } @@ -976,11 +974,9 @@ again: up_write(&xdna->notifier_lock); return 0; } - kref_get(&mapp->refcnt); + up_write(&xdna->notifier_lock); - XDNA_DBG(xdna, "populate memory range %lx %lx", - mapp->vma->vm_start, mapp->vma->vm_end); mm = mapp->notifier.mm; if (!mmget_not_zero(mm)) { amdxdna_umap_put(mapp); diff --git a/drivers/accel/amdxdna/aie2_error.c b/drivers/accel/amdxdna/aie2_error.c index 58abb59b6153..70007b4363cd 100644 --- a/drivers/accel/amdxdna/aie2_error.c +++ b/drivers/accel/amdxdna/aie2_error.c @@ -249,12 +249,12 @@ static u32 aie2_error_backtrack(struct amdxdna_dev_hdl *ndev, void *err_info, u3 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", + XDNA_ERR(ndev->aie.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"); + XDNA_WARN(ndev->aie.xdna, "Invalid column number"); break; } @@ -294,7 +294,7 @@ static void aie2_error_worker(struct work_struct *err_work) e = container_of(err_work, struct async_event, work); - xdna = e->ndev->xdna; + xdna = e->ndev->aie.xdna; if (e->resp.status == MAX_AIE2_STATUS_CODE) return; @@ -329,7 +329,7 @@ static void aie2_error_worker(struct work_struct *err_work) void aie2_error_async_events_free(struct amdxdna_dev_hdl *ndev) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; struct async_events *events; events = ndev->async_events; @@ -344,7 +344,7 @@ void aie2_error_async_events_free(struct amdxdna_dev_hdl *ndev) int aie2_error_async_events_alloc(struct amdxdna_dev_hdl *ndev) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; u32 total_col = ndev->total_col; u32 total_size = ASYNC_BUF_SIZE * total_col; struct async_events *events; @@ -402,12 +402,15 @@ free_events: int aie2_get_array_async_error(struct amdxdna_dev_hdl *ndev, struct amdxdna_drm_get_array *args) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + if (!args->num_element) + return -EINVAL; + args->num_element = 1; - args->element_size = sizeof(ndev->last_async_err); + args->element_size = min(args->element_size, sizeof(ndev->last_async_err)); if (copy_to_user(u64_to_user_ptr(args->buffer), &ndev->last_async_err, args->element_size)) return -EFAULT; diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index a1c546c3e81c..302896806606 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -16,6 +16,7 @@ #include <linux/types.h> #include <linux/xarray.h> +#include "aie.h" #include "aie2_msg_priv.h" #include "aie2_pci.h" #include "amdxdna_ctx.h" @@ -24,38 +25,12 @@ #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) - #define EXEC_MSG_OPS(xdna) ((xdna)->dev_handle->exec_msg_ops) -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; - - ret = xdna_send_msg_wait(xdna, ndev->mgmt_chann, msg); - if (ret == -ETIME) - aie2_destroy_mgmt_chann(ndev); - - if (!ret && *hdl->status != AIE2_STATUS_SUCCESS) { - XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x", - msg->opcode, *hdl->data); - ret = -EINVAL; - } - - return ret; -} - void *aie2_alloc_msg_buffer(struct amdxdna_dev_hdl *ndev, u32 *size, dma_addr_t *dma_addr) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; void *vaddr; int order; @@ -79,7 +54,7 @@ void *aie2_alloc_msg_buffer(struct amdxdna_dev_hdl *ndev, u32 *size, void aie2_free_msg_buffer(struct amdxdna_dev_hdl *ndev, size_t size, void *cpu_addr, dma_addr_t dma_addr) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; if (amdxdna_iova_on(xdna)) { amdxdna_iommu_free(xdna, size, cpu_addr, dma_addr); @@ -91,12 +66,12 @@ void aie2_free_msg_buffer(struct amdxdna_dev_hdl *ndev, size_t size, int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev) { - DECLARE_AIE2_MSG(suspend, MSG_OP_SUSPEND); + DECLARE_AIE_MSG(suspend, MSG_OP_SUSPEND); int ret; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) { - XDNA_ERR(ndev->xdna, "Failed to suspend fw, ret %d", ret); + XDNA_ERR(ndev->aie.xdna, "Failed to suspend fw, ret %d", ret); return ret; } @@ -105,22 +80,22 @@ int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev) int aie2_resume_fw(struct amdxdna_dev_hdl *ndev) { - DECLARE_AIE2_MSG(suspend, MSG_OP_RESUME); + DECLARE_AIE_MSG(suspend, MSG_OP_RESUME); - return aie2_send_mgmt_msg_wait(ndev, &msg); + return aie_send_mgmt_msg_wait(&ndev->aie, &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); + DECLARE_AIE_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); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) { - XDNA_ERR(ndev->xdna, "Failed to set runtime config, ret %d", ret); + XDNA_ERR(ndev->aie.xdna, "Failed to set runtime config, ret %d", ret); return ret; } @@ -129,13 +104,13 @@ 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) { - DECLARE_AIE2_MSG(get_runtime_cfg, MSG_OP_GET_RUNTIME_CONFIG); + DECLARE_AIE_MSG(get_runtime_cfg, MSG_OP_GET_RUNTIME_CONFIG); int ret; req.type = type; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) { - XDNA_ERR(ndev->xdna, "Failed to get runtime config, ret %d", ret); + XDNA_ERR(ndev->aie.xdna, "Failed to get runtime config, ret %d", ret); return ret; } @@ -145,20 +120,20 @@ 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) { - DECLARE_AIE2_MSG(assign_mgmt_pasid, MSG_OP_ASSIGN_MGMT_PASID); + DECLARE_AIE_MSG(assign_mgmt_pasid, MSG_OP_ASSIGN_MGMT_PASID); req.pasid = pasid; - return aie2_send_mgmt_msg_wait(ndev, &msg); + return aie_send_mgmt_msg_wait(&ndev->aie, &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; + DECLARE_AIE_MSG(aie_version_info, MSG_OP_QUERY_AIE_VERSION); + struct amdxdna_dev *xdna = ndev->aie.xdna; int ret; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) return ret; @@ -173,10 +148,10 @@ int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *ver 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); + DECLARE_AIE_MSG(aie_tile_info, MSG_OP_QUERY_AIE_TILE_INFO); int ret; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) return ret; @@ -211,10 +186,10 @@ int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *m 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); + DECLARE_AIE_MSG(firmware_version, MSG_OP_GET_FIRMWARE_VERSION); int ret; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) return ret; @@ -228,12 +203,12 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, static int aie2_destroy_context_req(struct amdxdna_dev_hdl *ndev, u32 id) { - DECLARE_AIE2_MSG(destroy_ctx, MSG_OP_DESTROY_CONTEXT); - struct amdxdna_dev *xdna = ndev->xdna; + DECLARE_AIE_MSG(destroy_ctx, MSG_OP_DESTROY_CONTEXT); + struct amdxdna_dev *xdna = ndev->aie.xdna; int ret; req.context_id = id; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret && ret != -ENODEV) XDNA_WARN(xdna, "Destroy context failed, ret %d", ret); else if (ret == -ENODEV) @@ -245,7 +220,7 @@ static int aie2_destroy_context_req(struct amdxdna_dev_hdl *ndev, u32 id) static u32 aie2_get_context_priority(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx) { - if (!AIE2_FEATURE_ON(ndev, AIE2_PREEMPT)) + if (!AIE_FEATURE_ON(&ndev->aie, AIE2_PREEMPT)) return PRIORITY_HIGH; switch (hwctx->qos.priority) { @@ -264,8 +239,8 @@ static u32 aie2_get_context_priority(struct amdxdna_dev_hdl *ndev, 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; + DECLARE_AIE_MSG(create_ctx, MSG_OP_CREATE_CONTEXT); + struct amdxdna_dev *xdna = ndev->aie.xdna; struct xdna_mailbox_chann_res x2i; struct xdna_mailbox_chann_res i2x; struct cq_pair *cq_pair; @@ -280,7 +255,7 @@ int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwct req.pasid = amdxdna_pasid_on(hwctx->client) ? hwctx->client->pasid : 0; req.context_priority = aie2_get_context_priority(ndev, hwctx); - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) return ret; @@ -344,7 +319,7 @@ del_ctx_req: int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; int ret; if (!hwctx->priv->mbox_chann) @@ -363,14 +338,14 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc 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; + DECLARE_AIE_MSG(map_host_buffer, MSG_OP_MAP_HOST_BUFFER); + struct amdxdna_dev *xdna = ndev->aie.xdna; int ret; req.context_id = context_id; req.buf_addr = addr; req.buf_size = size; - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) return ret; @@ -392,14 +367,15 @@ static int amdxdna_hwctx_col_map(struct amdxdna_hwctx *hwctx, void *arg) 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; - u32 buf_sz = size, aie_bitmap = 0; + DECLARE_AIE_MSG(aie_column_info, MSG_OP_QUERY_COL_STATUS); + struct amdxdna_dev *xdna = ndev->aie.xdna; + u32 buf_sz, aie_bitmap = 0; struct amdxdna_client *client; dma_addr_t dma_addr; u8 *buff_addr; int ret; + buf_sz = ndev->metadata.cols * ndev->metadata.size; buff_addr = aie2_alloc_msg_buffer(ndev, &buf_sz, &dma_addr); if (IS_ERR(buff_addr)) return PTR_ERR(buff_addr); @@ -414,8 +390,8 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, 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); + drm_clflush_virt_range(buff_addr, req.dump_buff_size); /* device can access */ + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) { XDNA_ERR(xdna, "Error during NPU query, status %d", ret); goto fail; @@ -423,13 +399,14 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, XDNA_DBG(xdna, "Query NPU status completed"); - if (size < resp.size) { + if (buf_sz < resp.size) { ret = -EINVAL; - XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", size, resp.size); + XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", buf_sz, resp.size); goto fail; } - if (copy_to_user(buf, buff_addr, resp.size)) { + size = min(size, resp.size); + if (copy_to_user(buf, buff_addr, size)) { ret = -EFAULT; XDNA_ERR(xdna, "Failed to copy NPU status to user space"); goto fail; @@ -446,16 +423,17 @@ int aie2_query_telemetry(struct amdxdna_dev_hdl *ndev, char __user *buf, u32 size, struct amdxdna_drm_query_telemetry_header *header) { - DECLARE_AIE2_MSG(get_telemetry, MSG_OP_GET_TELEMETRY); - struct amdxdna_dev *xdna = ndev->xdna; + DECLARE_AIE_MSG(get_telemetry, MSG_OP_GET_TELEMETRY); + struct amdxdna_dev *xdna = ndev->aie.xdna; dma_addr_t dma_addr; - u32 buf_sz = size; + u32 buf_sz; u8 *addr; int ret; if (header->type >= MAX_TELEMETRY_TYPE) return -EINVAL; + buf_sz = min(size, SZ_4M); addr = aie2_alloc_msg_buffer(ndev, &buf_sz, &dma_addr); if (IS_ERR(addr)) return PTR_ERR(addr); @@ -464,20 +442,21 @@ int aie2_query_telemetry(struct amdxdna_dev_hdl *ndev, req.buf_size = buf_sz; req.type = header->type; - drm_clflush_virt_range(addr, size); /* device can access */ - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + drm_clflush_virt_range(addr, req.buf_size); /* device can access */ + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) { XDNA_ERR(xdna, "Query telemetry failed, status %d", ret); goto free_buf; } - if (size < resp.size) { + if (buf_sz < resp.size) { ret = -EINVAL; - XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", size, resp.size); + XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", buf_sz, resp.size); goto free_buf; } - if (copy_to_user(buf, addr, resp.size)) { + size = min(size, resp.size); + if (copy_to_user(buf, addr, size)) { ret = -EFAULT; XDNA_ERR(xdna, "Failed to copy telemetry to user space"); goto free_buf; @@ -506,8 +485,8 @@ int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, 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); + XDNA_DBG(ndev->aie.xdna, "Register addr 0x%llx size 0x%x", addr, size); + return xdna_mailbox_send_msg(ndev->aie.mgmt_chann, &msg, TX_TIMEOUT); } int aie2_config_cu(struct amdxdna_hwctx *hwctx, @@ -866,7 +845,6 @@ static int aie2_init_exec_req(void *req, struct amdxdna_gem_obj *cmd_abo, int ret; u32 op; - op = amdxdna_cmd_get_op(cmd_abo); switch (op) { case ERT_START_CU: @@ -915,12 +893,12 @@ aie2_cmdlist_fill_slot(void *slot, struct amdxdna_gem_obj *cmd_abo, ret = EXEC_MSG_OPS(xdna)->fill_dpu_slot(cmd_abo, slot, size); break; case ERT_START_NPU_PREEMPT: - if (!AIE2_FEATURE_ON(xdna->dev_handle, AIE2_PREEMPT)) + if (!AIE_FEATURE_ON(&xdna->dev_handle->aie, AIE2_PREEMPT)) return -EOPNOTSUPP; ret = EXEC_MSG_OPS(xdna)->fill_preempt_slot(cmd_abo, slot, size); break; case ERT_START_NPU_PREEMPT_ELF: - if (!AIE2_FEATURE_ON(xdna->dev_handle, AIE2_PREEMPT)) + if (!AIE_FEATURE_ON(&xdna->dev_handle->aie, AIE2_PREEMPT)) return -EOPNOTSUPP; ret = EXEC_MSG_OPS(xdna)->fill_elf_slot(cmd_abo, slot, size); break; @@ -935,26 +913,12 @@ aie2_cmdlist_fill_slot(void *slot, struct amdxdna_gem_obj *cmd_abo, void aie2_msg_init(struct amdxdna_dev_hdl *ndev) { - if (AIE2_FEATURE_ON(ndev, AIE2_NPU_COMMAND)) + if (AIE_FEATURE_ON(&ndev->aie, AIE2_NPU_COMMAND)) ndev->exec_msg_ops = &npu_exec_message_ops; else ndev->exec_msg_ops = &legacy_exec_message_ops; } -void aie2_destroy_mgmt_chann(struct amdxdna_dev_hdl *ndev) -{ - struct amdxdna_dev *xdna = ndev->xdna; - - drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); - - if (!ndev->mgmt_chann) - return; - - xdna_mailbox_stop_channel(ndev->mgmt_chann); - xdna_mailbox_free_channel(ndev->mgmt_chann); - ndev->mgmt_chann = NULL; -} - static inline struct amdxdna_gem_obj * aie2_cmdlist_get_cmd_buf(struct amdxdna_sched_job *job) { @@ -1199,14 +1163,14 @@ int aie2_config_debug_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job * int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id, struct app_health_report *report) { - DECLARE_AIE2_MSG(get_app_health, MSG_OP_GET_APP_HEALTH); - struct amdxdna_dev *xdna = ndev->xdna; + DECLARE_AIE_MSG(get_app_health, MSG_OP_GET_APP_HEALTH); + struct amdxdna_dev *xdna = ndev->aie.xdna; struct app_health_report *buf; dma_addr_t dma_addr; u32 buf_size; int ret; - if (!AIE2_FEATURE_ON(ndev, AIE2_APP_HEALTH)) { + if (!AIE_FEATURE_ON(&ndev->aie, AIE2_APP_HEALTH)) { XDNA_DBG(xdna, "App health feature not supported"); return -EOPNOTSUPP; } @@ -1222,8 +1186,8 @@ int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id, req.context_id = context_id; req.buf_size = buf_size; - drm_clflush_virt_range(buf, sizeof(*report)); - ret = aie2_send_mgmt_msg_wait(ndev, &msg); + drm_clflush_virt_range(buf, req.buf_size); + ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg); if (ret) { XDNA_ERR(xdna, "Get app health failed, ret %d status 0x%x", ret, resp.status); goto free_buf; diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h b/drivers/accel/amdxdna/aie2_msg_priv.h index f18e89a39e35..4a01d73209bb 100644 --- a/drivers/accel/amdxdna/aie2_msg_priv.h +++ b/drivers/accel/amdxdna/aie2_msg_priv.h @@ -460,7 +460,7 @@ struct fatal_error_info { __u32 exception_pc; /* Program Counter at the time of the exception */ __u32 app_module; /* Error module name */ __u32 task_index; /* Index of the task in which the error occurred */ - __u32 reserved[128]; + __u32 reserved[127]; }; struct app_health_report { diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 4500b9ccb02e..a7b923005ab7 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -60,45 +60,6 @@ struct mgmt_mbox_chann_info { __u32 rsvd[4]; }; -static int aie2_check_protocol(struct amdxdna_dev_hdl *ndev, u32 fw_major, u32 fw_minor) -{ - const struct aie2_fw_feature_tbl *feature; - bool found = false; - - for (feature = ndev->priv->fw_feature_tbl; feature->major; feature++) { - if (feature->major != fw_major) - continue; - if (fw_minor < feature->min_minor) - continue; - if (feature->max_minor > 0 && fw_minor > feature->max_minor) - continue; - - ndev->feature_mask |= feature->features; - - /* firmware version matches one of the driver support entry */ - found = true; - } - - return found ? 0 : -EOPNOTSUPP; -} - -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; @@ -128,13 +89,13 @@ static int aie2_get_mgmt_chann_info(struct amdxdna_dev_hdl *ndev) 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); + XDNA_ERR(ndev->aie.xdna, "Invalid mbox magic 0x%x", info_regs.magic); ret = -EINVAL; goto done; } - i2x = &ndev->mgmt_i2x; - x2i = &ndev->mgmt_x2i; + i2x = &ndev->aie.mgmt_i2x; + x2i = &ndev->aie.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); @@ -146,14 +107,15 @@ static int aie2_get_mgmt_chann_info(struct amdxdna_dev_hdl *ndev) 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; + ndev->aie.mgmt_chan_idx = info_regs.msi_id; + ndev->aie.mgmt_prot_major = info_regs.prot_major; + ndev->aie.mgmt_prot_minor = info_regs.prot_minor; - ret = aie2_check_protocol(ndev, ndev->mgmt_prot_major, ndev->mgmt_prot_minor); + ret = aie_check_protocol(&ndev->aie, ndev->aie.mgmt_prot_major, + ndev->aie.mgmt_prot_minor); done: - aie2_dump_chann_info_debug(ndev); + aie_dump_mgmt_chann_debug(&ndev->aie); /* Must clear address at FW_ALIVE_OFF */ writel(0, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF)); @@ -173,13 +135,14 @@ int aie2_runtime_cfg(struct amdxdna_dev_hdl *ndev, continue; if (cfg->feature_mask && - bitmap_subset(&cfg->feature_mask, &ndev->feature_mask, AIE2_FEATURE_MAX)) + bitmap_subset(&cfg->feature_mask, &ndev->aie.feature_mask, + AIE2_FEATURE_MAX)) 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", + XDNA_ERR(ndev->aie.xdna, "Set type %d value %d failed", cfg->type, value); return ret; } @@ -194,13 +157,13 @@ static int aie2_xdna_reset(struct amdxdna_dev_hdl *ndev) ret = aie2_suspend_fw(ndev); if (ret) { - XDNA_ERR(ndev->xdna, "Suspend firmware failed"); + XDNA_ERR(ndev->aie.xdna, "Suspend firmware failed"); return ret; } ret = aie2_resume_fw(ndev); if (ret) { - XDNA_ERR(ndev->xdna, "Resume firmware failed"); + XDNA_ERR(ndev->aie.xdna, "Resume firmware failed"); return ret; } @@ -213,19 +176,19 @@ static int aie2_mgmt_fw_init(struct amdxdna_dev_hdl *ndev) ret = aie2_runtime_cfg(ndev, AIE2_RT_CFG_INIT, NULL); if (ret) { - XDNA_ERR(ndev->xdna, "Runtime config failed"); + XDNA_ERR(ndev->aie.xdna, "Runtime config failed"); return ret; } ret = aie2_assign_mgmt_pasid(ndev, 0); if (ret) { - XDNA_ERR(ndev->xdna, "Can not assign PASID"); + XDNA_ERR(ndev->aie.xdna, "Can not assign PASID"); return ret; } ret = aie2_xdna_reset(ndev); if (ret) { - XDNA_ERR(ndev->xdna, "Reset firmware failed"); + XDNA_ERR(ndev->aie.xdna, "Reset firmware failed"); return ret; } @@ -236,21 +199,21 @@ static int aie2_mgmt_fw_query(struct amdxdna_dev_hdl *ndev) { int ret; - ret = aie2_query_firmware_version(ndev, &ndev->xdna->fw_ver); + ret = aie2_query_firmware_version(ndev, &ndev->aie.xdna->fw_ver); if (ret) { - XDNA_ERR(ndev->xdna, "query firmware version failed"); + XDNA_ERR(ndev->aie.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"); + XDNA_ERR(ndev->aie.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"); + XDNA_ERR(ndev->aie.xdna, "Query AIE metadata failed"); return ret; } @@ -262,8 +225,8 @@ static int aie2_mgmt_fw_query(struct amdxdna_dev_hdl *ndev) 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"); + XDNA_ERR(ndev->aie.xdna, "Suspend_fw failed"); + XDNA_DBG(ndev->aie.xdna, "Firmware suspended"); } static int aie2_xrs_load(void *cb_arg, struct xrs_action_load *action) @@ -331,7 +294,7 @@ static void aie2_hw_stop(struct amdxdna_dev *xdna) aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, NULL); aie2_mgmt_fw_fini(ndev); - aie2_destroy_mgmt_chann(ndev); + aie_destroy_chann(&ndev->aie, &ndev->aie.mgmt_chann); drmm_kfree(&xdna->ddev, ndev->mbox); ndev->mbox = NULL; aie2_psp_stop(ndev->psp_hdl); @@ -374,8 +337,8 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) goto disable_dev; } - ndev->mgmt_chann = xdna_mailbox_alloc_channel(ndev->mbox); - if (!ndev->mgmt_chann) { + ndev->aie.mgmt_chann = xdna_mailbox_alloc_channel(ndev->mbox); + if (!ndev->aie.mgmt_chann) { XDNA_ERR(xdna, "failed to alloc channel"); ret = -ENODEV; goto disable_dev; @@ -399,17 +362,17 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) goto stop_psp; } - mgmt_mb_irq = pci_irq_vector(pdev, ndev->mgmt_chan_idx); + mgmt_mb_irq = pci_irq_vector(pdev, ndev->aie.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; - ret = xdna_mailbox_start_channel(ndev->mgmt_chann, - &ndev->mgmt_x2i, - &ndev->mgmt_i2x, + xdna_mailbox_intr_reg = ndev->aie.mgmt_i2x.mb_head_ptr_reg + 4; + ret = xdna_mailbox_start_channel(ndev->aie.mgmt_chann, + &ndev->aie.mgmt_x2i, + &ndev->aie.mgmt_i2x, xdna_mailbox_intr_reg, mgmt_mb_irq); if (ret) { @@ -448,14 +411,14 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) stop_fw: aie2_suspend_fw(ndev); - xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_stop_channel(ndev->aie.mgmt_chann); stop_psp: aie2_psp_stop(ndev->psp_hdl); fini_smu: aie2_smu_fini(ndev); free_channel: - xdna_mailbox_free_channel(ndev->mgmt_chann); - ndev->mgmt_chann = NULL; + xdna_mailbox_free_channel(ndev->aie.mgmt_chann); + ndev->aie.mgmt_chann = NULL; disable_dev: pci_disable_device(pdev); @@ -521,7 +484,7 @@ static int aie2_init(struct amdxdna_dev *xdna) return -ENOMEM; ndev->priv = xdna->dev_info->dev_priv; - ndev->xdna = xdna; + ndev->aie.xdna = xdna; for (i = 0; i < ARRAY_SIZE(npu_fw); i++) { fw_full_path = kasprintf(GFP_KERNEL, "%s%s", ndev->priv->fw_path, npu_fw[i]); @@ -644,23 +607,19 @@ static void aie2_fini(struct amdxdna_dev *xdna) 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_drm_query_aie_status status = {}; struct amdxdna_dev *xdna = client->xdna; struct amdxdna_dev_hdl *ndev; + u32 buf_sz; int ret; ndev = xdna->dev_handle; - if (copy_from_user(&status, u64_to_user_ptr(args->buffer), sizeof(status))) { + buf_sz = min(args->buffer_size, sizeof(status)); + if (copy_from_user(&status, u64_to_user_ptr(args->buffer), buf_sz)) { 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) { @@ -668,7 +627,7 @@ static int aie2_get_aie_status(struct amdxdna_client *client, return ret; } - if (copy_to_user(u64_to_user_ptr(args->buffer), &status, sizeof(status))) { + if (copy_to_user(u64_to_user_ptr(args->buffer), &status, buf_sz)) { XDNA_ERR(xdna, "Failed to copy AIE request info to user space"); return -EFAULT; } @@ -683,6 +642,7 @@ static int aie2_get_aie_metadata(struct amdxdna_client *client, struct amdxdna_dev *xdna = client->xdna; struct amdxdna_dev_hdl *ndev; int ret = 0; + u32 buf_sz; ndev = xdna->dev_handle; meta = kzalloc_obj(*meta); @@ -714,7 +674,8 @@ static int aie2_get_aie_metadata(struct amdxdna_client *client, 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))) + buf_sz = min(args->buffer_size, sizeof(*meta)); + if (copy_to_user(u64_to_user_ptr(args->buffer), meta, buf_sz)) ret = -EFAULT; kfree(meta); @@ -727,12 +688,14 @@ static int aie2_get_aie_version(struct amdxdna_client *client, struct amdxdna_drm_query_aie_version version; struct amdxdna_dev *xdna = client->xdna; struct amdxdna_dev_hdl *ndev; + u32 buf_sz; 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))) + buf_sz = min(args->buffer_size, sizeof(version)); + if (copy_to_user(u64_to_user_ptr(args->buffer), &version, buf_sz)) return -EFAULT; return 0; @@ -743,13 +706,15 @@ static int aie2_get_firmware_version(struct amdxdna_client *client, { struct amdxdna_drm_query_firmware_version version; struct amdxdna_dev *xdna = client->xdna; + u32 buf_sz; 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))) + buf_sz = min(args->buffer_size, sizeof(version)); + if (copy_to_user(u64_to_user_ptr(args->buffer), &version, buf_sz)) return -EFAULT; return 0; @@ -761,11 +726,13 @@ static int aie2_get_power_mode(struct amdxdna_client *client, struct amdxdna_drm_get_power_mode mode = {}; struct amdxdna_dev *xdna = client->xdna; struct amdxdna_dev_hdl *ndev; + u32 buf_sz; ndev = xdna->dev_handle; mode.power_mode = ndev->pw_mode; - if (copy_to_user(u64_to_user_ptr(args->buffer), &mode, sizeof(mode))) + buf_sz = min(args->buffer_size, sizeof(mode)); + if (copy_to_user(u64_to_user_ptr(args->buffer), &mode, buf_sz)) return -EFAULT; return 0; @@ -778,6 +745,7 @@ static int aie2_get_clock_metadata(struct amdxdna_client *client, struct amdxdna_dev *xdna = client->xdna; struct amdxdna_dev_hdl *ndev; int ret = 0; + u32 buf_sz; ndev = xdna->dev_handle; clock = kzalloc_obj(*clock); @@ -790,7 +758,8 @@ static int aie2_get_clock_metadata(struct amdxdna_client *client, 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))) + buf_sz = min(args->buffer_size, sizeof(*clock)); + if (copy_to_user(u64_to_user_ptr(args->buffer), clock, buf_sz)) ret = -EFAULT; kfree(clock); @@ -816,12 +785,14 @@ static int aie2_get_sensors(struct amdxdna_client *client, scnprintf(sensor.label, sizeof(sensor.label), "Total Power"); scnprintf(sensor.units, sizeof(sensor.units), "mW"); + if (args->buffer_size < sizeof(sensor)) + goto out; + if (copy_to_user(u64_to_user_ptr(args->buffer), &sensor, sizeof(sensor))) return -EFAULT; + args->buffer_size -= sizeof(sensor); sensors_count++; - if (args->buffer_size <= sensors_count * sizeof(sensor)) - goto out; for (i = 0; i < min_t(u32, ndev->total_col, 8); i++) { memset(&sensor, 0, sizeof(sensor)); @@ -831,13 +802,15 @@ static int aie2_get_sensors(struct amdxdna_client *client, scnprintf(sensor.label, sizeof(sensor.label), "Column %d Utilization", i); scnprintf(sensor.units, sizeof(sensor.units), "%%"); + if (args->buffer_size < sizeof(sensor)) + goto out; + if (copy_to_user(u64_to_user_ptr(args->buffer) + sensors_count * sizeof(sensor), &sensor, sizeof(sensor))) return -EFAULT; + args->buffer_size -= sizeof(sensor); sensors_count++; - if (args->buffer_size <= sensors_count * sizeof(sensor)) - goto out; } out: @@ -933,6 +906,7 @@ static int aie2_query_resource_info(struct amdxdna_client *client, const struct amdxdna_dev_priv *priv; struct amdxdna_dev_hdl *ndev; struct amdxdna_dev *xdna; + u32 buf_sz; xdna = client->xdna; ndev = xdna->dev_handle; @@ -944,7 +918,8 @@ static int aie2_query_resource_info(struct amdxdna_client *client, res_info.npu_tops_curr = ndev->curr_tops; res_info.npu_task_curr = ndev->hwctx_num; - if (copy_to_user(u64_to_user_ptr(args->buffer), &res_info, sizeof(res_info))) + buf_sz = min(args->buffer_size, sizeof(res_info)); + if (copy_to_user(u64_to_user_ptr(args->buffer), &res_info, buf_sz)) return -EFAULT; return 0; @@ -980,12 +955,7 @@ static int aie2_get_telemetry(struct amdxdna_client *client, XDNA_ERR(xdna, "Invalid buffer size"); return -EINVAL; } - telemetry_data_sz = args->buffer_size - header_sz; - if (telemetry_data_sz > SZ_4M) { - XDNA_ERR(xdna, "Buffer size is too big, %d", telemetry_data_sz); - return -EINVAL; - } header = kzalloc(header_sz, GFP_KERNEL); if (!header) @@ -1026,6 +996,7 @@ static int aie2_get_preempt_state(struct amdxdna_client *client, struct amdxdna_drm_attribute_state state = {}; struct amdxdna_dev *xdna = client->xdna; struct amdxdna_dev_hdl *ndev; + u32 buf_sz; ndev = xdna->dev_handle; if (args->param == DRM_AMDXDNA_GET_FORCE_PREEMPT_STATE) @@ -1033,7 +1004,8 @@ static int aie2_get_preempt_state(struct amdxdna_client *client, else if (args->param == DRM_AMDXDNA_GET_FRAME_BOUNDARY_PREEMPT_STATE) state.state = ndev->frame_boundary_preempt; - if (copy_to_user(u64_to_user_ptr(args->buffer), &state, sizeof(state))) + buf_sz = min(args->buffer_size, sizeof(state)); + if (copy_to_user(u64_to_user_ptr(args->buffer), &state, buf_sz)) return -EFAULT; return 0; diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index efcf4be035f0..90fb0aafaf40 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -10,6 +10,7 @@ #include <linux/limits.h> #include <linux/semaphore.h> +#include "aie.h" #include "aie2_msg_priv.h" #include "amdxdna_mailbox.h" @@ -20,7 +21,7 @@ #define AIE2_DEVM_BASE 0x4000000 #define AIE2_DEVM_SIZE SZ_64M -#define NDEV2PDEV(ndev) (to_pci_dev((ndev)->xdna->ddev.dev)) +#define NDEV2PDEV(ndev) (to_pci_dev((ndev)->aie.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) @@ -45,7 +46,7 @@ ({ \ typeof(ndev) _ndev = (ndev); \ ((_ndev)->priv->mbox_size) ? (_ndev)->priv->mbox_size : \ - pci_resource_len(NDEV2PDEV(_ndev), (_ndev)->xdna->dev_info->mbox_bar); \ + pci_resource_len(NDEV2PDEV(_ndev), (_ndev)->aie.xdna->dev_info->mbox_bar); \ }) #if IS_ENABLED(CONFIG_AMD_PMF) @@ -203,23 +204,16 @@ struct aie2_exec_msg_ops { }; struct amdxdna_dev_hdl { - struct amdxdna_dev *xdna; + struct aie_device aie; 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; - unsigned long feature_mask; struct aie2_exec_msg_ops *exec_msg_ops; /* power management and clock*/ @@ -237,7 +231,6 @@ struct amdxdna_dev_hdl { /* Mailbox and the management channel */ struct mailbox *mbox; - struct mailbox_channel *mgmt_chann; struct async_events *async_events; enum aie2_dev_status dev_status; @@ -266,21 +259,12 @@ enum aie2_fw_feature { AIE2_FEATURE_MAX }; -struct aie2_fw_feature_tbl { - u64 features; - u32 major; - u32 max_minor; - u32 min_minor; -}; - #define AIE2_ALL_FEATURES GENMASK_ULL(AIE2_FEATURE_MAX - 1, AIE2_NPU_COMMAND) -#define AIE2_FEATURE_ON(ndev, feature) test_bit(feature, &(ndev)->feature_mask) struct amdxdna_dev_priv { const char *fw_path; const struct rt_config *rt_config; const struct dpm_clk_freq *dpm_clk_tbl; - const struct aie2_fw_feature_tbl *fw_feature_tbl; #define COL_ALIGN_NONE 0 #define COL_ALIGN_NATURE 1 @@ -306,7 +290,7 @@ 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[]; -extern const struct aie2_fw_feature_tbl npu4_fw_feature_table[]; +extern const struct amdxdna_fw_feature_tbl npu4_fw_feature_table[]; /* aie2_smu.c */ int aie2_smu_init(struct amdxdna_dev_hdl *ndev); diff --git a/drivers/accel/amdxdna/aie2_pm.c b/drivers/accel/amdxdna/aie2_pm.c index 29bd4403a94d..5ec6728d04fd 100644 --- a/drivers/accel/amdxdna/aie2_pm.c +++ b/drivers/accel/amdxdna/aie2_pm.c @@ -31,14 +31,14 @@ int aie2_pm_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) { int ret; - ret = amdxdna_pm_resume_get_locked(ndev->xdna); + ret = amdxdna_pm_resume_get_locked(ndev->aie.xdna); if (ret) return ret; ret = ndev->priv->hw_ops.set_dpm(ndev, dpm_level); if (!ret) ndev->dpm_level = dpm_level; - amdxdna_pm_suspend_put(ndev->xdna); + amdxdna_pm_suspend_put(ndev->aie.xdna); return ret; } @@ -81,7 +81,7 @@ 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) { - struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_dev *xdna = ndev->aie.xdna; u32 clk_gating, dpm_level; int ret; diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/amdxdna/aie2_smu.c index d8c31924e501..727637dac3a8 100644 --- a/drivers/accel/amdxdna/aie2_smu.c +++ b/drivers/accel/amdxdna/aie2_smu.c @@ -46,7 +46,7 @@ static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd, 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); + XDNA_ERR(ndev->aie.xdna, "smu cmd %d timed out", reg_cmd); return ret; } @@ -54,7 +54,7 @@ static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd, *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); + XDNA_ERR(ndev->aie.xdna, "smu cmd %d failed, 0x%x", reg_cmd, resp); return -EINVAL; } @@ -69,7 +69,7 @@ int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) 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", + XDNA_ERR(ndev->aie.xdna, "Set npu clock to %d failed, ret %d\n", ndev->priv->dpm_clk_tbl[dpm_level].npuclk, ret); return ret; } @@ -78,7 +78,7 @@ int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) 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", + XDNA_ERR(ndev->aie.xdna, "Set h clock to %d failed, ret %d\n", ndev->priv->dpm_clk_tbl[dpm_level].hclk, ret); return ret; } @@ -87,7 +87,7 @@ int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) ndev->max_tops = 2 * ndev->total_col; ndev->curr_tops = ndev->max_tops * freq / 1028; - XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n", + XDNA_DBG(ndev->aie.xdna, "MP-NPU clock %d, H clock %d\n", ndev->npuclk_freq, ndev->hclk_freq); return 0; @@ -99,14 +99,14 @@ int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) 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 ", + XDNA_ERR(ndev->aie.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", + XDNA_ERR(ndev->aie.xdna, "Set soft dpm level %d failed, ret %d", dpm_level, ret); return ret; } @@ -116,7 +116,7 @@ int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) ndev->max_tops = NPU4_DPM_TOPS(ndev, ndev->max_dpm_level); ndev->curr_tops = NPU4_DPM_TOPS(ndev, dpm_level); - XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n", + XDNA_DBG(ndev->aie.xdna, "MP-NPU clock %d, H clock %d\n", ndev->npuclk_freq, ndev->hclk_freq); return 0; @@ -132,13 +132,13 @@ int aie2_smu_init(struct amdxdna_dev_hdl *ndev) */ ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_OFF, 0, NULL); if (ret) { - XDNA_ERR(ndev->xdna, "Access power failed, ret %d", ret); + XDNA_ERR(ndev->aie.xdna, "Access power failed, ret %d", ret); return ret; } ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_ON, 0, NULL); if (ret) { - XDNA_ERR(ndev->xdna, "Power on failed, ret %d", ret); + XDNA_ERR(ndev->aie.xdna, "Power on failed, ret %d", ret); return ret; } @@ -152,5 +152,5 @@ void aie2_smu_fini(struct amdxdna_dev_hdl *ndev) 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); + XDNA_ERR(ndev->aie.xdna, "Power off failed, ret %d", ret); } diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index ff6c3e8e5a15..5315466f137b 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -356,16 +356,25 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr return -EINVAL; } - guard(mutex)(&xdna->dev_lock); + ret = amdxdna_pm_resume_get(xdna); + if (ret) { + XDNA_ERR(xdna, "Resume failed, ret %d", ret); + goto free_buf; + } + + mutex_lock(&xdna->dev_lock); 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 free_buf; + goto unlock; } ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size); +unlock: + mutex_unlock(&xdna->dev_lock); + amdxdna_pm_suspend_put(xdna); free_buf: kfree(buf); return ret; @@ -386,16 +395,25 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client *client, u32 debug_bo_hdl) if (!gobj) return -EINVAL; + ret = amdxdna_pm_resume_get(xdna); + if (ret) { + XDNA_ERR(xdna, "Resume failed, ret %d", ret); + goto put_obj; + } + abo = to_xdna_obj(gobj); - guard(mutex)(&xdna->dev_lock); + mutex_lock(&xdna->dev_lock); hwctx = xa_load(&client->hwctx_xa, abo->assigned_hwctx); if (!hwctx) { ret = -EINVAL; - goto put_obj; + goto unlock; } ret = xdna->dev_info->ops->hwctx_sync_debug_bo(hwctx, debug_bo_hdl); +unlock: + mutex_unlock(&xdna->dev_lock); + amdxdna_pm_suspend_put(xdna); put_obj: drm_gem_object_put(gobj); return ret; @@ -478,6 +496,10 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, int ret, idx; XDNA_DBG(xdna, "Command BO hdl %d, Arg BO count %d", cmd_bo_hdl, arg_bo_cnt); + + if (!xdna->dev_info->ops->cmd_submit) + return -EOPNOTSUPP; + job = kzalloc_flex(*job, bos, arg_bo_cnt); if (!job) return -ENOMEM; @@ -491,6 +513,16 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, ret = -EINVAL; goto free_job; } + } else if (!drv_cmd) { + /* + * Only internal driver commands (drv_cmd != NULL) may omit a + * command BO. A user command submission with the invalid handle + * would leave job->cmd_bo NULL and later fault when the scheduler + * dereferences it in amdxdna_cmd_set_state(). + */ + XDNA_DBG(xdna, "Command BO handle required for user submission"); + ret = -EINVAL; + goto free_job; } ret = amdxdna_arg_bos_lookup(client, job, arg_bo_hdls, arg_bo_cnt); diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index 6e367ddb9e1b..cdf113dadc4d 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -200,7 +200,7 @@ static bool amdxdna_hmm_invalidate(struct mmu_interval_notifier *mni, xdna = to_xdna_dev(to_gobj(abo)->dev); XDNA_DBG(xdna, "Invalidating range 0x%lx, 0x%lx, type %d", - mapp->vma->vm_start, mapp->vma->vm_end, abo->type); + mapp->range.start, mapp->range.end, abo->type); if (!mmu_notifier_range_blockable(range)) return false; @@ -229,15 +229,23 @@ static const struct mmu_interval_notifier_ops amdxdna_hmm_ops = { .invalidate = amdxdna_hmm_invalidate, }; +static inline bool compare_range(struct amdxdna_umap *mapp, + struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + return (!mapp->unmapped && mapp->notifier.mm == mm && + mapp->range.start == start && mapp->range.end == end); +} + static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo, struct vm_area_struct *vma) { struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); struct amdxdna_umap *mapp; - down_read(&xdna->notifier_lock); + down_write(&xdna->notifier_lock); list_for_each_entry(mapp, &abo->mem.umap_list, node) { - if (!vma || mapp->vma == vma) { + if (!vma || compare_range(mapp, vma->vm_mm, vma->vm_start, vma->vm_end)) { if (!mapp->unmapped) { queue_work(xdna->notifier_wq, &mapp->hmm_unreg_work); mapp->unmapped = true; @@ -246,19 +254,16 @@ static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo, break; } } - up_read(&xdna->notifier_lock); + up_write(&xdna->notifier_lock); } static void amdxdna_umap_release(struct kref *ref) { struct amdxdna_umap *mapp = container_of(ref, struct amdxdna_umap, refcnt); struct amdxdna_gem_obj *abo = mapp->abo; - struct vm_area_struct *vma = mapp->vma; struct amdxdna_dev *xdna; mmu_interval_notifier_remove(&mapp->notifier); - if (is_import_bo(abo) && vma->vm_file && vma->vm_file->f_mapping) - mapping_clear_unevictable(vma->vm_file->f_mapping); xdna = to_xdna_dev(to_gobj(mapp->abo)->dev); down_write(&xdna->notifier_lock); @@ -291,12 +296,21 @@ static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, unsigned long len = vma->vm_end - vma->vm_start; unsigned long addr = vma->vm_start; struct amdxdna_umap *mapp; - u32 nr_pages; + unsigned long nr_pages; int ret; if (!xdna->dev_info->ops->hmm_invalidate) return 0; + down_read(&xdna->notifier_lock); + list_for_each_entry(mapp, &abo->mem.umap_list, node) { + if (compare_range(mapp, current->mm, addr, addr + len)) { + up_read(&xdna->notifier_lock); + return 0; + } + } + up_read(&xdna->notifier_lock); + mapp = kzalloc_obj(*mapp); if (!mapp) return -ENOMEM; @@ -322,13 +336,10 @@ static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, mapp->range.start = vma->vm_start; mapp->range.end = vma->vm_end; mapp->range.default_flags = HMM_PFN_REQ_FAULT; - mapp->vma = vma; mapp->abo = abo; kref_init(&mapp->refcnt); INIT_WORK(&mapp->hmm_unreg_work, amdxdna_hmm_unreg_work); - if (is_import_bo(abo) && vma->vm_file && vma->vm_file->f_mapping) - mapping_set_unevictable(vma->vm_file->f_mapping); down_write(&xdna->notifier_lock); if (list_empty(&abo->mem.umap_list)) @@ -469,6 +480,7 @@ static int amdxdna_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struc close_vma: vma->vm_ops->close(vma); + return ret; put_obj: drm_gem_object_put(gobj); return ret; @@ -1027,6 +1039,7 @@ int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm int amdxdna_drm_sync_bo_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_sync_bo *args = data; struct amdxdna_gem_obj *abo; @@ -1061,7 +1074,7 @@ int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, args->handle, args->offset, args->size); if (args->direction == SYNC_DIRECT_FROM_DEVICE) - ret = amdxdna_hwctx_sync_debug_bo(abo->client, args->handle); + ret = amdxdna_hwctx_sync_debug_bo(client, args->handle); put_obj: drm_gem_object_put(gobj); diff --git a/drivers/accel/amdxdna/amdxdna_gem.h b/drivers/accel/amdxdna/amdxdna_gem.h index 957305ccb485..10242f4a5ca9 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.h +++ b/drivers/accel/amdxdna/amdxdna_gem.h @@ -12,7 +12,6 @@ #include "amdxdna_pci_drv.h" struct amdxdna_umap { - struct vm_area_struct *vma; struct mmu_interval_notifier notifier; struct hmm_range range; struct work_struct hmm_unreg_work; diff --git a/drivers/accel/amdxdna/amdxdna_iommu.c b/drivers/accel/amdxdna/amdxdna_iommu.c index 4626434d4180..77443872beb2 100644 --- a/drivers/accel/amdxdna/amdxdna_iommu.c +++ b/drivers/accel/amdxdna/amdxdna_iommu.c @@ -4,6 +4,7 @@ */ #include <drm/amdxdna_accel.h> +#include <drm/drm_managed.h> #include <linux/iommu.h> #include <linux/iova.h> @@ -40,7 +41,7 @@ int amdxdna_iommu_map_bo(struct amdxdna_dev *xdna, struct amdxdna_gem_obj *abo) struct sg_table *sgt; dma_addr_t dma_addr; struct iova *iova; - size_t size; + ssize_t size; if (abo->type != AMDXDNA_BO_DEV_HEAP && abo->type != AMDXDNA_BO_SHMEM) return 0; @@ -65,7 +66,14 @@ int amdxdna_iommu_map_bo(struct amdxdna_dev *xdna, struct amdxdna_gem_obj *abo) size = iommu_map_sgtable(xdna->domain, dma_addr, sgt, IOMMU_READ | IOMMU_WRITE); + if (size < 0) { + XDNA_ERR(xdna, "iommu_map_sgtable failed: %zd", size); + __free_iova(&xdna->iovad, iova); + return size; + } + if (size < abo->mem.size) { + iommu_unmap(xdna->domain, dma_addr, size); __free_iova(&xdna->iovad, iova); return -ENXIO; } @@ -110,10 +118,12 @@ void *amdxdna_iommu_alloc(struct amdxdna_dev *xdna, size_t size, dma_addr_t *dma iova_align(&xdna->iovad, size), IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (ret) - goto free_iova; + goto free_cpu_addr; return cpu_addr; +free_cpu_addr: + free_pages((unsigned long)cpu_addr, get_order(size)); free_iova: __free_iova(&xdna->iovad, iova); return ERR_PTR(ret); @@ -127,10 +137,30 @@ void amdxdna_iommu_free(struct amdxdna_dev *xdna, size_t size, free_pages((unsigned long)cpu_addr, get_order(size)); } +static void amdxdna_cleanup_force_iova(struct drm_device *dev, void *res) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + + if (xdna->domain) { + iommu_detach_group(xdna->domain, xdna->group); + put_iova_domain(&xdna->iovad); + iova_cache_put(); + iommu_domain_free(xdna->domain); + } + + iommu_group_put(xdna->group); +} + +void amdxdna_iommu_fini(struct amdxdna_dev *xdna) +{ + if (xdna->group && !xdna->domain) + iommu_group_put(xdna->group); +} + int amdxdna_iommu_init(struct amdxdna_dev *xdna) { unsigned long order; - int ret; + int ret = 0; xdna->group = iommu_group_get(xdna->ddev.dev); if (!xdna->group || !force_iova) @@ -156,8 +186,14 @@ int amdxdna_iommu_init(struct amdxdna_dev *xdna) if (ret) goto put_iova; + ret = drmm_add_action(&xdna->ddev, amdxdna_cleanup_force_iova, NULL); + if (ret) + goto detach_group; + return 0; +detach_group: + iommu_detach_group(xdna->domain, xdna->group); put_iova: put_iova_domain(&xdna->iovad); iova_cache_put(); @@ -165,20 +201,8 @@ free_domain: iommu_domain_free(xdna->domain); put_group: iommu_group_put(xdna->group); + xdna->group = NULL; xdna->domain = NULL; return ret; } - -void amdxdna_iommu_fini(struct amdxdna_dev *xdna) -{ - if (xdna->domain) { - iommu_detach_group(xdna->domain, xdna->group); - put_iova_domain(&xdna->iovad); - iova_cache_put(); - iommu_domain_free(xdna->domain); - } - - if (xdna->group) - iommu_group_put(xdna->group); -} diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index e681a090752d..13c20bb3890c 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -485,6 +485,9 @@ free_chann: void xdna_mailbox_free_channel(struct mailbox_channel *mb_chann) { + if (!mb_chann) + return; + destroy_workqueue(mb_chann->work_q); kfree(mb_chann); } @@ -531,6 +534,9 @@ void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann) struct mailbox_msg *mb_msg; unsigned long msg_id; + if (!mb_chann) + return; + /* Disable an irq and wait. This might sleep. */ free_irq(mb_chann->msix_irq, mb_chann); @@ -538,7 +544,9 @@ void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann) drain_workqueue(mb_chann->work_q); /* We can clean up and release resources */ - xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg) + xa_for_each_start(&mb_chann->chan_xa, msg_id, mb_msg, mb_chann->next_msgid) + mailbox_release_msg(mb_chann, mb_msg); + xa_for_each_range(&mb_chann->chan_xa, msg_id, mb_msg, 0, mb_chann->next_msgid - 1) mailbox_release_msg(mb_chann, mb_msg); xa_destroy(&mb_chann->chan_xa); diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 0661749917d6..5e0bf565a1ae 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -66,6 +66,13 @@ struct amdxdna_dev_ops { int (*get_array)(struct amdxdna_client *client, struct amdxdna_drm_get_array *args); }; +struct amdxdna_fw_feature_tbl { + u64 features; + u32 major; + u32 max_minor; + u32 min_minor; +}; + /* * struct amdxdna_dev_info - Device hardware information * Record device static information, like reg, mbox, PSP, SMU bar index @@ -83,6 +90,7 @@ struct amdxdna_dev_info { size_t dev_mem_size; char *vbnv; const struct amdxdna_dev_priv *dev_priv; + const struct amdxdna_fw_feature_tbl *fw_feature_tbl; const struct amdxdna_dev_ops *ops; }; diff --git a/drivers/accel/amdxdna/amdxdna_ubuf.c b/drivers/accel/amdxdna/amdxdna_ubuf.c index 85390e3cc9f9..0e0cd69cd1fb 100644 --- a/drivers/accel/amdxdna/amdxdna_ubuf.c +++ b/drivers/accel/amdxdna/amdxdna_ubuf.c @@ -146,13 +146,17 @@ struct dma_buf *amdxdna_get_ubuf(struct drm_device *dev, ret = pin_user_pages_fast(va_ent[i].vaddr, npages, FOLL_WRITE | FOLL_LONGTERM, &ubuf->pages[start]); - if (ret < 0 || ret != npages) { - ret = -ENOMEM; + if (ret >= 0) { + start += ret; + if (ret != npages) { + XDNA_ERR(xdna, "Partially pinned pages %d/%u", ret, npages); + ret = -ENOMEM; + goto destroy_pages; + } + } else { XDNA_ERR(xdna, "Failed to pin pages ret %d", ret); goto destroy_pages; } - - start += ret; } exp_info.ops = &amdxdna_ubuf_dmabuf_ops; diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c index 1320e924e548..2ea7568a2e99 100644 --- a/drivers/accel/amdxdna/npu1_regs.c +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -65,7 +65,7 @@ const struct dpm_clk_freq npu1_dpm_clk_table[] = { { 0 } }; -static const struct aie2_fw_feature_tbl npu1_fw_feature_table[] = { +static const struct amdxdna_fw_feature_tbl npu1_fw_feature_table[] = { { .major = 5, .min_minor = 7 }, { .features = BIT_U64(AIE2_NPU_COMMAND), .major = 5, .min_minor = 8 }, { 0 } @@ -75,7 +75,6 @@ static const struct amdxdna_dev_priv npu1_dev_priv = { .fw_path = "amdnpu/1502_00/", .rt_config = npu1_default_rt_cfg, .dpm_clk_tbl = npu1_dpm_clk_table, - .fw_feature_tbl = npu1_fw_feature_table, .col_align = COL_ALIGN_NONE, .mbox_dev_addr = NPU1_MBOX_BAR_BASE, .mbox_size = 0, /* Use BAR size */ @@ -120,5 +119,6 @@ const struct amdxdna_dev_info dev_npu1_info = { .vbnv = "RyzenAI-npu1", .device_type = AMDXDNA_DEV_TYPE_KMQ, .dev_priv = &npu1_dev_priv, + .fw_feature_tbl = npu1_fw_feature_table, .ops = &aie2_ops, }; diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c index 619bff042e52..9689c56c83be 100644 --- a/drivers/accel/amdxdna/npu4_regs.c +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -88,7 +88,7 @@ const struct dpm_clk_freq npu4_dpm_clk_table[] = { { 0 } }; -const struct aie2_fw_feature_tbl npu4_fw_feature_table[] = { +const struct amdxdna_fw_feature_tbl npu4_fw_feature_table[] = { { .major = 6, .min_minor = 12 }, { .features = BIT_U64(AIE2_NPU_COMMAND), .major = 6, .min_minor = 15 }, { .features = BIT_U64(AIE2_PREEMPT), .major = 6, .min_minor = 12 }, @@ -102,7 +102,6 @@ static const struct amdxdna_dev_priv npu4_dev_priv = { .fw_path = "amdnpu/17f0_10/", .rt_config = npu4_default_rt_cfg, .dpm_clk_tbl = npu4_dpm_clk_table, - .fw_feature_tbl = npu4_fw_feature_table, .col_align = COL_ALIGN_NATURE, .mbox_dev_addr = NPU4_MBOX_BAR_BASE, .mbox_size = 0, /* Use BAR size */ @@ -147,5 +146,6 @@ const struct amdxdna_dev_info dev_npu4_info = { .vbnv = "RyzenAI-npu4", .device_type = AMDXDNA_DEV_TYPE_KMQ, .dev_priv = &npu4_dev_priv, + .fw_feature_tbl = npu4_fw_feature_table, .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 index c0ac5daf32ee..98ee8780f3f5 100644 --- a/drivers/accel/amdxdna/npu5_regs.c +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -66,7 +66,6 @@ static const struct amdxdna_dev_priv npu5_dev_priv = { .fw_path = "amdnpu/17f0_11/", .rt_config = npu4_default_rt_cfg, .dpm_clk_tbl = npu4_dpm_clk_table, - .fw_feature_tbl = npu4_fw_feature_table, .col_align = COL_ALIGN_NATURE, .mbox_dev_addr = NPU5_MBOX_BAR_BASE, .mbox_size = 0, /* Use BAR size */ @@ -111,5 +110,6 @@ const struct amdxdna_dev_info dev_npu5_info = { .vbnv = "RyzenAI-npu5", .device_type = AMDXDNA_DEV_TYPE_KMQ, .dev_priv = &npu5_dev_priv, + .fw_feature_tbl = npu4_fw_feature_table, .ops = &aie2_ops, }; diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/amdxdna/npu6_regs.c index ce591ed0d483..31400cca5ec4 100644 --- a/drivers/accel/amdxdna/npu6_regs.c +++ b/drivers/accel/amdxdna/npu6_regs.c @@ -66,7 +66,6 @@ static const struct amdxdna_dev_priv npu6_dev_priv = { .fw_path = "amdnpu/17f0_10/", .rt_config = npu4_default_rt_cfg, .dpm_clk_tbl = npu4_dpm_clk_table, - .fw_feature_tbl = npu4_fw_feature_table, .col_align = COL_ALIGN_NATURE, .mbox_dev_addr = NPU6_MBOX_BAR_BASE, .mbox_size = 0, /* Use BAR size */ @@ -112,5 +111,6 @@ const struct amdxdna_dev_info dev_npu6_info = { .vbnv = "RyzenAI-npu6", .device_type = AMDXDNA_DEV_TYPE_KMQ, .dev_priv = &npu6_dev_priv, + .fw_feature_tbl = npu4_fw_feature_table, .ops = &aie2_ops, }; diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c index 275baf844b56..716467aa3156 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.c +++ b/drivers/accel/ivpu/ivpu_fw_log.c @@ -43,6 +43,10 @@ static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *off ivpu_dbg(vdev, FW_BOOT, "Invalid header size 0x%x\n", log->header_size); return -EINVAL; } + if (log->size < log->header_size) { + ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); + return -EINVAL; + } if ((char *)log + log->size > (char *)ivpu_bo_vaddr(bo) + ivpu_bo_size(bo)) { ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); return -EINVAL; diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 521931d1f7fc..b24f31a8b567 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -208,9 +208,9 @@ static int ivpu_hws_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->id, priority); if (ret) - return ret; + ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); - return 0; + return ret; } static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) @@ -281,10 +281,10 @@ static int ivpu_cmdq_register(struct ivpu_file_priv *file_priv, struct ivpu_cmdq } ret = ivpu_register_db(file_priv, cmdq); - if (ret) - return ret; + if (ret && vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) + ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); - return 0; + return ret; } static int ivpu_cmdq_unregister(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) |