diff options
Diffstat (limited to '')
| -rw-r--r-- | drivers/dma/idxd/Makefile | 2 | ||||
| -rw-r--r-- | drivers/dma/idxd/cdev.c | 289 | ||||
| -rw-r--r-- | drivers/dma/idxd/device.c | 739 | ||||
| -rw-r--r-- | drivers/dma/idxd/dma.c | 296 | ||||
| -rw-r--r-- | drivers/dma/idxd/idxd.h | 338 | ||||
| -rw-r--r-- | drivers/dma/idxd/init.c | 526 | ||||
| -rw-r--r-- | drivers/dma/idxd/irq.c | 277 | ||||
| -rw-r--r-- | drivers/dma/idxd/registers.h | 357 | ||||
| -rw-r--r-- | drivers/dma/idxd/submit.c | 95 | ||||
| -rw-r--r-- | drivers/dma/idxd/sysfs.c | 1668 |
10 files changed, 4587 insertions, 0 deletions
diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile new file mode 100644 index 000000000..8978b898d --- /dev/null +++ b/drivers/dma/idxd/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_INTEL_IDXD) += idxd.o +idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c new file mode 100644 index 000000000..ae65eb90a --- /dev/null +++ b/drivers/dma/idxd/cdev.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/sched/task.h> +#include <linux/intel-svm.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/cdev.h> +#include <linux/fs.h> +#include <linux/poll.h> +#include <uapi/linux/idxd.h> +#include "registers.h" +#include "idxd.h" + +struct idxd_cdev_context { + const char *name; + dev_t devt; + struct ida minor_ida; +}; + +/* + * ictx is an array based off of accelerator types. enum idxd_type + * is used as index + */ +static struct idxd_cdev_context ictx[IDXD_TYPE_MAX] = { + { .name = "dsa" }, +}; + +struct idxd_user_context { + struct idxd_wq *wq; + struct task_struct *task; + unsigned int flags; +}; + +static void idxd_cdev_dev_release(struct device *dev) +{ + struct idxd_cdev *idxd_cdev = container_of(dev, struct idxd_cdev, dev); + struct idxd_cdev_context *cdev_ctx; + struct idxd_wq *wq = idxd_cdev->wq; + + cdev_ctx = &ictx[wq->idxd->type]; + ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor); + kfree(idxd_cdev); +} + +static struct device_type idxd_cdev_device_type = { + .name = "idxd_cdev", + .release = idxd_cdev_dev_release, +}; + +static inline struct idxd_cdev *inode_idxd_cdev(struct inode *inode) +{ + struct cdev *cdev = inode->i_cdev; + + return container_of(cdev, struct idxd_cdev, cdev); +} + +static inline struct idxd_wq *inode_wq(struct inode *inode) +{ + struct idxd_cdev *idxd_cdev = inode_idxd_cdev(inode); + + return idxd_cdev->wq; +} + +static int idxd_cdev_open(struct inode *inode, struct file *filp) +{ + struct idxd_user_context *ctx; + struct idxd_device *idxd; + struct idxd_wq *wq; + struct device *dev; + int rc = 0; + + wq = inode_wq(inode); + idxd = wq->idxd; + dev = &idxd->pdev->dev; + + dev_dbg(dev, "%s called: %d\n", __func__, idxd_wq_refcount(wq)); + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + mutex_lock(&wq->wq_lock); + + if (idxd_wq_refcount(wq) > 0 && wq_dedicated(wq)) { + rc = -EBUSY; + goto failed; + } + + ctx->wq = wq; + filp->private_data = ctx; + idxd_wq_get(wq); + mutex_unlock(&wq->wq_lock); + return 0; + + failed: + mutex_unlock(&wq->wq_lock); + kfree(ctx); + return rc; +} + +static int idxd_cdev_release(struct inode *node, struct file *filep) +{ + struct idxd_user_context *ctx = filep->private_data; + struct idxd_wq *wq = ctx->wq; + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + + dev_dbg(dev, "%s called\n", __func__); + filep->private_data = NULL; + + /* Wait for in-flight operations to complete. */ + idxd_wq_drain(wq); + + kfree(ctx); + mutex_lock(&wq->wq_lock); + idxd_wq_put(wq); + mutex_unlock(&wq->wq_lock); + return 0; +} + +static int check_vma(struct idxd_wq *wq, struct vm_area_struct *vma, + const char *func) +{ + struct device *dev = &wq->idxd->pdev->dev; + + if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) { + dev_info_ratelimited(dev, + "%s: %s: mapping too large: %lu\n", + current->comm, func, + vma->vm_end - vma->vm_start); + return -EINVAL; + } + + return 0; +} + +static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct idxd_user_context *ctx = filp->private_data; + struct idxd_wq *wq = ctx->wq; + struct idxd_device *idxd = wq->idxd; + struct pci_dev *pdev = idxd->pdev; + phys_addr_t base = pci_resource_start(pdev, IDXD_WQ_BAR); + unsigned long pfn; + int rc; + + dev_dbg(&pdev->dev, "%s called\n", __func__); + rc = check_vma(wq, vma, __func__); + if (rc < 0) + return rc; + + vma->vm_flags |= VM_DONTCOPY; + pfn = (base + idxd_get_wq_portal_full_offset(wq->id, + IDXD_PORTAL_LIMITED)) >> PAGE_SHIFT; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vma->vm_private_data = ctx; + + return io_remap_pfn_range(vma, vma->vm_start, pfn, PAGE_SIZE, + vma->vm_page_prot); +} + +static __poll_t idxd_cdev_poll(struct file *filp, + struct poll_table_struct *wait) +{ + struct idxd_user_context *ctx = filp->private_data; + struct idxd_wq *wq = ctx->wq; + struct idxd_device *idxd = wq->idxd; + unsigned long flags; + __poll_t out = 0; + + poll_wait(filp, &wq->err_queue, wait); + spin_lock_irqsave(&idxd->dev_lock, flags); + if (idxd->sw_err.valid) + out = EPOLLIN | EPOLLRDNORM; + spin_unlock_irqrestore(&idxd->dev_lock, flags); + + return out; +} + +static const struct file_operations idxd_cdev_fops = { + .owner = THIS_MODULE, + .open = idxd_cdev_open, + .release = idxd_cdev_release, + .mmap = idxd_cdev_mmap, + .poll = idxd_cdev_poll, +}; + +int idxd_cdev_get_major(struct idxd_device *idxd) +{ + return MAJOR(ictx[idxd->type].devt); +} + +int idxd_wq_add_cdev(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct idxd_cdev *idxd_cdev; + struct cdev *cdev; + struct device *dev; + struct idxd_cdev_context *cdev_ctx; + int rc, minor; + + idxd_cdev = kzalloc(sizeof(*idxd_cdev), GFP_KERNEL); + if (!idxd_cdev) + return -ENOMEM; + + idxd_cdev->wq = wq; + cdev = &idxd_cdev->cdev; + dev = &idxd_cdev->dev; + cdev_ctx = &ictx[wq->idxd->type]; + minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL); + if (minor < 0) { + kfree(idxd_cdev); + return minor; + } + idxd_cdev->minor = minor; + + device_initialize(dev); + dev->parent = &wq->conf_dev; + dev->bus = idxd_get_bus_type(idxd); + dev->type = &idxd_cdev_device_type; + dev->devt = MKDEV(MAJOR(cdev_ctx->devt), minor); + + rc = dev_set_name(dev, "%s/wq%u.%u", idxd_get_dev_name(idxd), + idxd->id, wq->id); + if (rc < 0) + goto err; + + wq->idxd_cdev = idxd_cdev; + cdev_init(cdev, &idxd_cdev_fops); + rc = cdev_device_add(cdev, dev); + if (rc) { + dev_dbg(&wq->idxd->pdev->dev, "cdev_add failed: %d\n", rc); + goto err; + } + + return 0; + + err: + put_device(dev); + wq->idxd_cdev = NULL; + return rc; +} + +void idxd_wq_del_cdev(struct idxd_wq *wq) +{ + struct idxd_cdev *idxd_cdev; + struct idxd_cdev_context *cdev_ctx; + + cdev_ctx = &ictx[wq->idxd->type]; + idxd_cdev = wq->idxd_cdev; + wq->idxd_cdev = NULL; + cdev_device_del(&idxd_cdev->cdev, &idxd_cdev->dev); + put_device(&idxd_cdev->dev); +} + +int idxd_cdev_register(void) +{ + int rc, i; + + for (i = 0; i < IDXD_TYPE_MAX; i++) { + ida_init(&ictx[i].minor_ida); + rc = alloc_chrdev_region(&ictx[i].devt, 0, MINORMASK, + ictx[i].name); + if (rc) + goto err_free_chrdev_region; + } + + return 0; + +err_free_chrdev_region: + for (i--; i >= 0; i--) + unregister_chrdev_region(ictx[i].devt, MINORMASK); + + return rc; +} + +void idxd_cdev_remove(void) +{ + int i; + + for (i = 0; i < IDXD_TYPE_MAX; i++) { + unregister_chrdev_region(ictx[i].devt, MINORMASK); + ida_destroy(&ictx[i].minor_ida); + } +} diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c new file mode 100644 index 000000000..47aae5fe8 --- /dev/null +++ b/drivers/dma/idxd/device.c @@ -0,0 +1,739 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/dmaengine.h> +#include <linux/irq.h> +#include <linux/msi.h> +#include <uapi/linux/idxd.h> +#include "../dmaengine.h" +#include "idxd.h" +#include "registers.h" + +static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand, + u32 *status); + +/* Interrupt control bits */ +void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id) +{ + struct irq_data *data = irq_get_irq_data(idxd->msix_entries[vec_id].vector); + + pci_msi_mask_irq(data); +} + +void idxd_mask_msix_vectors(struct idxd_device *idxd) +{ + struct pci_dev *pdev = idxd->pdev; + int msixcnt = pci_msix_vec_count(pdev); + int i; + + for (i = 0; i < msixcnt; i++) + idxd_mask_msix_vector(idxd, i); +} + +void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id) +{ + struct irq_data *data = irq_get_irq_data(idxd->msix_entries[vec_id].vector); + + pci_msi_unmask_irq(data); +} + +void idxd_unmask_error_interrupts(struct idxd_device *idxd) +{ + union genctrl_reg genctrl; + + genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET); + genctrl.softerr_int_en = 1; + iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET); +} + +void idxd_mask_error_interrupts(struct idxd_device *idxd) +{ + union genctrl_reg genctrl; + + genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET); + genctrl.softerr_int_en = 0; + iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET); +} + +static void free_hw_descs(struct idxd_wq *wq) +{ + int i; + + for (i = 0; i < wq->num_descs; i++) + kfree(wq->hw_descs[i]); + + kfree(wq->hw_descs); +} + +static int alloc_hw_descs(struct idxd_wq *wq, int num) +{ + struct device *dev = &wq->idxd->pdev->dev; + int i; + int node = dev_to_node(dev); + + wq->hw_descs = kcalloc_node(num, sizeof(struct dsa_hw_desc *), + GFP_KERNEL, node); + if (!wq->hw_descs) + return -ENOMEM; + + for (i = 0; i < num; i++) { + wq->hw_descs[i] = kzalloc_node(sizeof(*wq->hw_descs[i]), + GFP_KERNEL, node); + if (!wq->hw_descs[i]) { + free_hw_descs(wq); + return -ENOMEM; + } + } + + return 0; +} + +static void free_descs(struct idxd_wq *wq) +{ + int i; + + for (i = 0; i < wq->num_descs; i++) + kfree(wq->descs[i]); + + kfree(wq->descs); +} + +static int alloc_descs(struct idxd_wq *wq, int num) +{ + struct device *dev = &wq->idxd->pdev->dev; + int i; + int node = dev_to_node(dev); + + wq->descs = kcalloc_node(num, sizeof(struct idxd_desc *), + GFP_KERNEL, node); + if (!wq->descs) + return -ENOMEM; + + for (i = 0; i < num; i++) { + wq->descs[i] = kzalloc_node(sizeof(*wq->descs[i]), + GFP_KERNEL, node); + if (!wq->descs[i]) { + free_descs(wq); + return -ENOMEM; + } + } + + return 0; +} + +/* WQ control bits */ +int idxd_wq_alloc_resources(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + int rc, num_descs, i; + + if (wq->type != IDXD_WQT_KERNEL) + return 0; + + wq->num_descs = wq->size; + num_descs = wq->size; + + rc = alloc_hw_descs(wq, num_descs); + if (rc < 0) + return rc; + + wq->compls_size = num_descs * sizeof(struct dsa_completion_record); + wq->compls = dma_alloc_coherent(dev, wq->compls_size, + &wq->compls_addr, GFP_KERNEL); + if (!wq->compls) { + rc = -ENOMEM; + goto fail_alloc_compls; + } + + rc = alloc_descs(wq, num_descs); + if (rc < 0) + goto fail_alloc_descs; + + rc = sbitmap_queue_init_node(&wq->sbq, num_descs, -1, false, GFP_KERNEL, + dev_to_node(dev)); + if (rc < 0) + goto fail_sbitmap_init; + + for (i = 0; i < num_descs; i++) { + struct idxd_desc *desc = wq->descs[i]; + + desc->hw = wq->hw_descs[i]; + desc->completion = &wq->compls[i]; + desc->compl_dma = wq->compls_addr + + sizeof(struct dsa_completion_record) * i; + desc->id = i; + desc->wq = wq; + desc->cpu = -1; + } + + return 0; + + fail_sbitmap_init: + free_descs(wq); + fail_alloc_descs: + dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); + fail_alloc_compls: + free_hw_descs(wq); + return rc; +} + +void idxd_wq_free_resources(struct idxd_wq *wq) +{ + struct device *dev = &wq->idxd->pdev->dev; + + if (wq->type != IDXD_WQT_KERNEL) + return; + + free_hw_descs(wq); + free_descs(wq); + dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); + sbitmap_queue_free(&wq->sbq); +} + +int idxd_wq_enable(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + u32 status; + + if (wq->state == IDXD_WQ_ENABLED) { + dev_dbg(dev, "WQ %d already enabled\n", wq->id); + return -ENXIO; + } + + idxd_cmd_exec(idxd, IDXD_CMD_ENABLE_WQ, wq->id, &status); + + if (status != IDXD_CMDSTS_SUCCESS && + status != IDXD_CMDSTS_ERR_WQ_ENABLED) { + dev_dbg(dev, "WQ enable failed: %#x\n", status); + return -ENXIO; + } + + wq->state = IDXD_WQ_ENABLED; + dev_dbg(dev, "WQ %d enabled\n", wq->id); + return 0; +} + +int idxd_wq_disable(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + u32 status, operand; + + dev_dbg(dev, "Disabling WQ %d\n", wq->id); + + if (wq->state != IDXD_WQ_ENABLED) { + dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state); + return 0; + } + + operand = BIT(wq->id % 16) | ((wq->id / 16) << 16); + idxd_cmd_exec(idxd, IDXD_CMD_DISABLE_WQ, operand, &status); + + if (status != IDXD_CMDSTS_SUCCESS) { + dev_dbg(dev, "WQ disable failed: %#x\n", status); + return -ENXIO; + } + + wq->state = IDXD_WQ_DISABLED; + dev_dbg(dev, "WQ %d disabled\n", wq->id); + return 0; +} + +void idxd_wq_drain(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + u32 operand; + + if (wq->state != IDXD_WQ_ENABLED) { + dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state); + return; + } + + dev_dbg(dev, "Draining WQ %d\n", wq->id); + operand = BIT(wq->id % 16) | ((wq->id / 16) << 16); + idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_WQ, operand, NULL); +} + +void idxd_wq_reset(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + u32 operand; + + if (wq->state != IDXD_WQ_ENABLED) { + dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state); + return; + } + + operand = BIT(wq->id % 16) | ((wq->id / 16) << 16); + idxd_cmd_exec(idxd, IDXD_CMD_RESET_WQ, operand, NULL); + wq->state = IDXD_WQ_DISABLED; +} + +int idxd_wq_map_portal(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct pci_dev *pdev = idxd->pdev; + struct device *dev = &pdev->dev; + resource_size_t start; + + start = pci_resource_start(pdev, IDXD_WQ_BAR); + start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED); + + wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE); + if (!wq->dportal) + return -ENOMEM; + dev_dbg(dev, "wq %d portal mapped at %p\n", wq->id, wq->dportal); + + return 0; +} + +void idxd_wq_unmap_portal(struct idxd_wq *wq) +{ + struct device *dev = &wq->idxd->pdev->dev; + + devm_iounmap(dev, wq->dportal); +} + +void idxd_wq_disable_cleanup(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + + lockdep_assert_held(&idxd->dev_lock); + memset(wq->wqcfg, 0, idxd->wqcfg_size); + wq->type = IDXD_WQT_NONE; + wq->size = 0; + wq->group = NULL; + wq->threshold = 0; + wq->priority = 0; + clear_bit(WQ_FLAG_DEDICATED, &wq->flags); + memset(wq->name, 0, WQ_NAME_SIZE); +} + +/* Device control bits */ +static inline bool idxd_is_enabled(struct idxd_device *idxd) +{ + union gensts_reg gensts; + + gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); + + if (gensts.state == IDXD_DEVICE_STATE_ENABLED) + return true; + return false; +} + +static inline bool idxd_device_is_halted(struct idxd_device *idxd) +{ + union gensts_reg gensts; + + gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); + + return (gensts.state == IDXD_DEVICE_STATE_HALT); +} + +/* + * This is function is only used for reset during probe and will + * poll for completion. Once the device is setup with interrupts, + * all commands will be done via interrupt completion. + */ +int idxd_device_init_reset(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + union idxd_command_reg cmd; + unsigned long flags; + + if (idxd_device_is_halted(idxd)) { + dev_warn(&idxd->pdev->dev, "Device is HALTED!\n"); + return -ENXIO; + } + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = IDXD_CMD_RESET_DEVICE; + dev_dbg(dev, "%s: sending reset for init.\n", __func__); + spin_lock_irqsave(&idxd->dev_lock, flags); + iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET); + + while (ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET) & + IDXD_CMDSTS_ACTIVE) + cpu_relax(); + spin_unlock_irqrestore(&idxd->dev_lock, flags); + return 0; +} + +static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand, + u32 *status) +{ + union idxd_command_reg cmd; + DECLARE_COMPLETION_ONSTACK(done); + unsigned long flags; + + if (idxd_device_is_halted(idxd)) { + dev_warn(&idxd->pdev->dev, "Device is HALTED!\n"); + if (status) + *status = IDXD_CMDSTS_HW_ERR; + return; + } + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = cmd_code; + cmd.operand = operand; + cmd.int_req = 1; + + spin_lock_irqsave(&idxd->dev_lock, flags); + wait_event_lock_irq(idxd->cmd_waitq, + !test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags), + idxd->dev_lock); + + dev_dbg(&idxd->pdev->dev, "%s: sending cmd: %#x op: %#x\n", + __func__, cmd_code, operand); + + idxd->cmd_status = 0; + __set_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags); + idxd->cmd_done = &done; + iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET); + + /* + * After command submitted, release lock and go to sleep until + * the command completes via interrupt. + */ + spin_unlock_irqrestore(&idxd->dev_lock, flags); + wait_for_completion(&done); + spin_lock_irqsave(&idxd->dev_lock, flags); + if (status) { + *status = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET); + idxd->cmd_status = *status & GENMASK(7, 0); + } + + __clear_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags); + /* Wake up other pending commands */ + wake_up(&idxd->cmd_waitq); + spin_unlock_irqrestore(&idxd->dev_lock, flags); +} + +int idxd_device_enable(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + u32 status; + + if (idxd_is_enabled(idxd)) { + dev_dbg(dev, "Device already enabled\n"); + return -ENXIO; + } + + idxd_cmd_exec(idxd, IDXD_CMD_ENABLE_DEVICE, 0, &status); + + /* If the command is successful or if the device was enabled */ + if (status != IDXD_CMDSTS_SUCCESS && + status != IDXD_CMDSTS_ERR_DEV_ENABLED) { + dev_dbg(dev, "%s: err_code: %#x\n", __func__, status); + return -ENXIO; + } + + idxd->state = IDXD_DEV_ENABLED; + return 0; +} + +void idxd_device_wqs_clear_state(struct idxd_device *idxd) +{ + int i; + + lockdep_assert_held(&idxd->dev_lock); + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + if (wq->state == IDXD_WQ_ENABLED) { + idxd_wq_disable_cleanup(wq); + wq->state = IDXD_WQ_DISABLED; + } + } +} + +int idxd_device_disable(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + u32 status; + unsigned long flags; + + if (!idxd_is_enabled(idxd)) { + dev_dbg(dev, "Device is not enabled\n"); + return 0; + } + + idxd_cmd_exec(idxd, IDXD_CMD_DISABLE_DEVICE, 0, &status); + + /* If the command is successful or if the device was disabled */ + if (status != IDXD_CMDSTS_SUCCESS && + !(status & IDXD_CMDSTS_ERR_DIS_DEV_EN)) { + dev_dbg(dev, "%s: err_code: %#x\n", __func__, status); + return -ENXIO; + } + + spin_lock_irqsave(&idxd->dev_lock, flags); + idxd_device_wqs_clear_state(idxd); + idxd->state = IDXD_DEV_CONF_READY; + spin_unlock_irqrestore(&idxd->dev_lock, flags); + return 0; +} + +void idxd_device_reset(struct idxd_device *idxd) +{ + unsigned long flags; + + idxd_cmd_exec(idxd, IDXD_CMD_RESET_DEVICE, 0, NULL); + spin_lock_irqsave(&idxd->dev_lock, flags); + idxd_device_wqs_clear_state(idxd); + idxd->state = IDXD_DEV_CONF_READY; + spin_unlock_irqrestore(&idxd->dev_lock, flags); +} + +/* Device configuration bits */ +static void idxd_group_config_write(struct idxd_group *group) +{ + struct idxd_device *idxd = group->idxd; + struct device *dev = &idxd->pdev->dev; + int i; + u32 grpcfg_offset; + + dev_dbg(dev, "Writing group %d cfg registers\n", group->id); + + /* setup GRPWQCFG */ + for (i = 0; i < 4; i++) { + grpcfg_offset = idxd->grpcfg_offset + + group->id * 64 + i * sizeof(u64); + iowrite64(group->grpcfg.wqs[i], + idxd->reg_base + grpcfg_offset); + dev_dbg(dev, "GRPCFG wq[%d:%d: %#x]: %#llx\n", + group->id, i, grpcfg_offset, + ioread64(idxd->reg_base + grpcfg_offset)); + } + + /* setup GRPENGCFG */ + grpcfg_offset = idxd->grpcfg_offset + group->id * 64 + 32; + iowrite64(group->grpcfg.engines, idxd->reg_base + grpcfg_offset); + dev_dbg(dev, "GRPCFG engs[%d: %#x]: %#llx\n", group->id, + grpcfg_offset, ioread64(idxd->reg_base + grpcfg_offset)); + + /* setup GRPFLAGS */ + grpcfg_offset = idxd->grpcfg_offset + group->id * 64 + 40; + iowrite32(group->grpcfg.flags.bits, idxd->reg_base + grpcfg_offset); + dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n", + group->id, grpcfg_offset, + ioread32(idxd->reg_base + grpcfg_offset)); +} + +static int idxd_groups_config_write(struct idxd_device *idxd) + +{ + union gencfg_reg reg; + int i; + struct device *dev = &idxd->pdev->dev; + + /* Setup bandwidth token limit */ + if (idxd->token_limit) { + reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); + reg.token_limit = idxd->token_limit; + iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); + } + + dev_dbg(dev, "GENCFG(%#x): %#x\n", IDXD_GENCFG_OFFSET, + ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET)); + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *group = &idxd->groups[i]; + + idxd_group_config_write(group); + } + + return 0; +} + +static int idxd_wq_config_write(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + u32 wq_offset; + int i; + + if (!wq->group) + return 0; + + /* + * Instead of memset the entire shadow copy of WQCFG, copy from the hardware after + * wq reset. This will copy back the sticky values that are present on some devices. + */ + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); + wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset); + } + + /* byte 0-3 */ + wq->wqcfg->wq_size = wq->size; + + if (wq->size == 0) { + dev_warn(dev, "Incorrect work queue size: 0\n"); + return -EINVAL; + } + + /* bytes 4-7 */ + wq->wqcfg->wq_thresh = wq->threshold; + + /* byte 8-11 */ + wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL); + wq->wqcfg->mode = 1; + wq->wqcfg->priority = wq->priority; + + /* bytes 12-15 */ + wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); + wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size); + + dev_dbg(dev, "WQ %d CFGs\n", wq->id); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); + iowrite32(wq->wqcfg->bits[i], idxd->reg_base + wq_offset); + dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", + wq->id, i, wq_offset, + ioread32(idxd->reg_base + wq_offset)); + } + + return 0; +} + +static int idxd_wqs_config_write(struct idxd_device *idxd) +{ + int i, rc; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + rc = idxd_wq_config_write(wq); + if (rc < 0) + return rc; + } + + return 0; +} + +static void idxd_group_flags_setup(struct idxd_device *idxd) +{ + int i; + + /* TC-A 0 and TC-B 1 should be defaults */ + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *group = &idxd->groups[i]; + + if (group->tc_a == -1) + group->tc_a = group->grpcfg.flags.tc_a = 0; + else + group->grpcfg.flags.tc_a = group->tc_a; + if (group->tc_b == -1) + group->tc_b = group->grpcfg.flags.tc_b = 1; + else + group->grpcfg.flags.tc_b = group->tc_b; + group->grpcfg.flags.use_token_limit = group->use_token_limit; + group->grpcfg.flags.tokens_reserved = group->tokens_reserved; + if (group->tokens_allowed) + group->grpcfg.flags.tokens_allowed = + group->tokens_allowed; + else + group->grpcfg.flags.tokens_allowed = idxd->max_tokens; + } +} + +static int idxd_engines_setup(struct idxd_device *idxd) +{ + int i, engines = 0; + struct idxd_engine *eng; + struct idxd_group *group; + + for (i = 0; i < idxd->max_groups; i++) { + group = &idxd->groups[i]; + group->grpcfg.engines = 0; + } + + for (i = 0; i < idxd->max_engines; i++) { + eng = &idxd->engines[i]; + group = eng->group; + + if (!group) + continue; + + group->grpcfg.engines |= BIT(eng->id); + engines++; + } + + if (!engines) + return -EINVAL; + + return 0; +} + +static int idxd_wqs_setup(struct idxd_device *idxd) +{ + struct idxd_wq *wq; + struct idxd_group *group; + int i, j, configured = 0; + struct device *dev = &idxd->pdev->dev; + + for (i = 0; i < idxd->max_groups; i++) { + group = &idxd->groups[i]; + for (j = 0; j < 4; j++) + group->grpcfg.wqs[j] = 0; + } + + for (i = 0; i < idxd->max_wqs; i++) { + wq = &idxd->wqs[i]; + group = wq->group; + + if (!wq->group) + continue; + if (!wq->size) + continue; + + if (!wq_dedicated(wq)) { + dev_warn(dev, "No shared workqueue support.\n"); + return -EINVAL; + } + + group->grpcfg.wqs[wq->id / 64] |= BIT(wq->id % 64); + configured++; + } + + if (configured == 0) + return -EINVAL; + + return 0; +} + +int idxd_device_config(struct idxd_device *idxd) +{ + int rc; + + lockdep_assert_held(&idxd->dev_lock); + rc = idxd_wqs_setup(idxd); + if (rc < 0) + return rc; + + rc = idxd_engines_setup(idxd); + if (rc < 0) + return rc; + + idxd_group_flags_setup(idxd); + + rc = idxd_wqs_config_write(idxd); + if (rc < 0) + return rc; + + rc = idxd_groups_config_write(idxd); + if (rc < 0) + return rc; + + return 0; +} diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c new file mode 100644 index 000000000..09ad37bbd --- /dev/null +++ b/drivers/dma/idxd/dma.c @@ -0,0 +1,296 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/dmaengine.h> +#include <uapi/linux/idxd.h> +#include "../dmaengine.h" +#include "registers.h" +#include "idxd.h" + +static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c) +{ + struct idxd_dma_chan *idxd_chan; + + idxd_chan = container_of(c, struct idxd_dma_chan, chan); + return idxd_chan->wq; +} + +void idxd_dma_complete_txd(struct idxd_desc *desc, + enum idxd_complete_type comp_type) +{ + struct dma_async_tx_descriptor *tx; + struct dmaengine_result res; + int complete = 1; + + if (desc->completion->status == DSA_COMP_SUCCESS) + res.result = DMA_TRANS_NOERROR; + else if (desc->completion->status) + res.result = DMA_TRANS_WRITE_FAILED; + else if (comp_type == IDXD_COMPLETE_ABORT) + res.result = DMA_TRANS_ABORTED; + else + complete = 0; + + tx = &desc->txd; + if (complete && tx->cookie) { + dma_cookie_complete(tx); + dma_descriptor_unmap(tx); + dmaengine_desc_get_callback_invoke(tx, &res); + tx->callback = NULL; + tx->callback_result = NULL; + } +} + +static void op_flag_setup(unsigned long flags, u32 *desc_flags) +{ + *desc_flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR; + if (flags & DMA_PREP_INTERRUPT) + *desc_flags |= IDXD_OP_FLAG_RCI; +} + +static inline void set_completion_address(struct idxd_desc *desc, + u64 *compl_addr) +{ + *compl_addr = desc->compl_dma; +} + +static inline void idxd_prep_desc_common(struct idxd_wq *wq, + struct dsa_hw_desc *hw, char opcode, + u64 addr_f1, u64 addr_f2, u64 len, + u64 compl, u32 flags) +{ + struct idxd_device *idxd = wq->idxd; + + hw->flags = flags; + hw->opcode = opcode; + hw->src_addr = addr_f1; + hw->dst_addr = addr_f2; + hw->xfer_size = len; + hw->priv = !!(wq->type == IDXD_WQT_KERNEL); + hw->completion_addr = compl; + + /* + * Descriptor completion vectors are 1-8 for MSIX. We will round + * robin through the 8 vectors. + */ + wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1; + hw->int_handle = wq->vec_ptr; +} + +static struct dma_async_tx_descriptor * +idxd_dma_prep_interrupt(struct dma_chan *c, unsigned long flags) +{ + struct idxd_wq *wq = to_idxd_wq(c); + u32 desc_flags; + struct idxd_desc *desc; + + if (wq->state != IDXD_WQ_ENABLED) + return NULL; + + op_flag_setup(flags, &desc_flags); + desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK); + if (IS_ERR(desc)) + return NULL; + + idxd_prep_desc_common(wq, desc->hw, DSA_OPCODE_NOOP, + 0, 0, 0, desc->compl_dma, desc_flags); + desc->txd.flags = flags; + return &desc->txd; +} + +static struct dma_async_tx_descriptor * +idxd_dma_submit_memcpy(struct dma_chan *c, dma_addr_t dma_dest, + dma_addr_t dma_src, size_t len, unsigned long flags) +{ + struct idxd_wq *wq = to_idxd_wq(c); + u32 desc_flags; + struct idxd_device *idxd = wq->idxd; + struct idxd_desc *desc; + + if (wq->state != IDXD_WQ_ENABLED) + return NULL; + + if (len > idxd->max_xfer_bytes) + return NULL; + + op_flag_setup(flags, &desc_flags); + desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK); + if (IS_ERR(desc)) + return NULL; + + idxd_prep_desc_common(wq, desc->hw, DSA_OPCODE_MEMMOVE, + dma_src, dma_dest, len, desc->compl_dma, + desc_flags); + + desc->txd.flags = flags; + + return &desc->txd; +} + +static int idxd_dma_alloc_chan_resources(struct dma_chan *chan) +{ + struct idxd_wq *wq = to_idxd_wq(chan); + struct device *dev = &wq->idxd->pdev->dev; + + idxd_wq_get(wq); + dev_dbg(dev, "%s: client_count: %d\n", __func__, + idxd_wq_refcount(wq)); + return 0; +} + +static void idxd_dma_free_chan_resources(struct dma_chan *chan) +{ + struct idxd_wq *wq = to_idxd_wq(chan); + struct device *dev = &wq->idxd->pdev->dev; + + idxd_wq_put(wq); + dev_dbg(dev, "%s: client_count: %d\n", __func__, + idxd_wq_refcount(wq)); +} + +static enum dma_status idxd_dma_tx_status(struct dma_chan *dma_chan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + return DMA_OUT_OF_ORDER; +} + +/* + * issue_pending() does not need to do anything since tx_submit() does the job + * already. + */ +static void idxd_dma_issue_pending(struct dma_chan *dma_chan) +{ +} + +static dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct dma_chan *c = tx->chan; + struct idxd_wq *wq = to_idxd_wq(c); + dma_cookie_t cookie; + int rc; + struct idxd_desc *desc = container_of(tx, struct idxd_desc, txd); + + cookie = dma_cookie_assign(tx); + + rc = idxd_submit_desc(wq, desc); + if (rc < 0) { + idxd_free_desc(wq, desc); + return rc; + } + + return cookie; +} + +static void idxd_dma_release(struct dma_device *device) +{ + struct idxd_dma_dev *idxd_dma = container_of(device, struct idxd_dma_dev, dma); + + kfree(idxd_dma); +} + +int idxd_register_dma_device(struct idxd_device *idxd) +{ + struct idxd_dma_dev *idxd_dma; + struct dma_device *dma; + struct device *dev = &idxd->pdev->dev; + int rc; + + idxd_dma = kzalloc_node(sizeof(*idxd_dma), GFP_KERNEL, dev_to_node(dev)); + if (!idxd_dma) + return -ENOMEM; + + dma = &idxd_dma->dma; + INIT_LIST_HEAD(&dma->channels); + dma->dev = dev; + + dma_cap_set(DMA_INTERRUPT, dma->cap_mask); + dma_cap_set(DMA_PRIVATE, dma->cap_mask); + dma_cap_set(DMA_COMPLETION_NO_ORDER, dma->cap_mask); + dma->device_release = idxd_dma_release; + + dma->device_prep_dma_interrupt = idxd_dma_prep_interrupt; + if (idxd->hw.opcap.bits[0] & IDXD_OPCAP_MEMMOVE) { + dma_cap_set(DMA_MEMCPY, dma->cap_mask); + dma->device_prep_dma_memcpy = idxd_dma_submit_memcpy; + } + + dma->device_tx_status = idxd_dma_tx_status; + dma->device_issue_pending = idxd_dma_issue_pending; + dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources; + dma->device_free_chan_resources = idxd_dma_free_chan_resources; + + rc = dma_async_device_register(dma); + if (rc < 0) { + kfree(idxd_dma); + return rc; + } + + idxd_dma->idxd = idxd; + /* + * This pointer is protected by the refs taken by the dma_chan. It will remain valid + * as long as there are outstanding channels. + */ + idxd->idxd_dma = idxd_dma; + return 0; +} + +void idxd_unregister_dma_device(struct idxd_device *idxd) +{ + dma_async_device_unregister(&idxd->idxd_dma->dma); +} + +int idxd_register_dma_channel(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct dma_device *dma = &idxd->idxd_dma->dma; + struct device *dev = &idxd->pdev->dev; + struct idxd_dma_chan *idxd_chan; + struct dma_chan *chan; + int rc, i; + + idxd_chan = kzalloc_node(sizeof(*idxd_chan), GFP_KERNEL, dev_to_node(dev)); + if (!idxd_chan) + return -ENOMEM; + + chan = &idxd_chan->chan; + chan->device = dma; + list_add_tail(&chan->device_node, &dma->channels); + + for (i = 0; i < wq->num_descs; i++) { + struct idxd_desc *desc = wq->descs[i]; + + dma_async_tx_descriptor_init(&desc->txd, chan); + desc->txd.tx_submit = idxd_dma_tx_submit; + } + + rc = dma_async_device_channel_register(dma, chan); + if (rc < 0) { + kfree(idxd_chan); + return rc; + } + + wq->idxd_chan = idxd_chan; + idxd_chan->wq = wq; + get_device(&wq->conf_dev); + + return 0; +} + +void idxd_unregister_dma_channel(struct idxd_wq *wq) +{ + struct idxd_dma_chan *idxd_chan = wq->idxd_chan; + struct dma_chan *chan = &idxd_chan->chan; + struct idxd_dma_dev *idxd_dma = wq->idxd->idxd_dma; + + dma_async_device_channel_unregister(&idxd_dma->dma, chan); + list_del(&chan->device_node); + kfree(wq->idxd_chan); + wq->idxd_chan = NULL; + put_device(&wq->conf_dev); +} diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h new file mode 100644 index 000000000..eef6996ec --- /dev/null +++ b/drivers/dma/idxd/idxd.h @@ -0,0 +1,338 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#ifndef _IDXD_H_ +#define _IDXD_H_ + +#include <linux/sbitmap.h> +#include <linux/dmaengine.h> +#include <linux/percpu-rwsem.h> +#include <linux/wait.h> +#include <linux/cdev.h> +#include "registers.h" + +#define IDXD_DRIVER_VERSION "1.00" + +extern struct kmem_cache *idxd_desc_pool; + +struct idxd_device; +struct idxd_wq; + +#define IDXD_REG_TIMEOUT 50 +#define IDXD_DRAIN_TIMEOUT 5000 + +enum idxd_type { + IDXD_TYPE_UNKNOWN = -1, + IDXD_TYPE_DSA = 0, + IDXD_TYPE_MAX +}; + +#define IDXD_NAME_SIZE 128 + +struct idxd_device_driver { + struct device_driver drv; +}; + +struct idxd_irq_entry { + struct idxd_device *idxd; + int id; + struct llist_head pending_llist; + struct list_head work_list; +}; + +struct idxd_group { + struct device conf_dev; + struct idxd_device *idxd; + struct grpcfg grpcfg; + int id; + int num_engines; + int num_wqs; + bool use_token_limit; + u8 tokens_allowed; + u8 tokens_reserved; + int tc_a; + int tc_b; +}; + +#define IDXD_MAX_PRIORITY 0xf + +enum idxd_wq_state { + IDXD_WQ_DISABLED = 0, + IDXD_WQ_ENABLED, +}; + +enum idxd_wq_flag { + WQ_FLAG_DEDICATED = 0, +}; + +enum idxd_wq_type { + IDXD_WQT_NONE = 0, + IDXD_WQT_KERNEL, + IDXD_WQT_USER, +}; + +struct idxd_cdev { + struct idxd_wq *wq; + struct cdev cdev; + struct device dev; + int minor; +}; + +#define IDXD_ALLOCATED_BATCH_SIZE 128U +#define WQ_NAME_SIZE 1024 +#define WQ_TYPE_SIZE 10 + +enum idxd_op_type { + IDXD_OP_BLOCK = 0, + IDXD_OP_NONBLOCK = 1, +}; + +enum idxd_complete_type { + IDXD_COMPLETE_NORMAL = 0, + IDXD_COMPLETE_ABORT, +}; + +struct idxd_dma_chan { + struct dma_chan chan; + struct idxd_wq *wq; +}; + +struct idxd_wq { + void __iomem *dportal; + struct device conf_dev; + struct idxd_cdev *idxd_cdev; + struct wait_queue_head err_queue; + struct idxd_device *idxd; + int id; + enum idxd_wq_type type; + struct idxd_group *group; + int client_count; + struct mutex wq_lock; /* mutex for workqueue */ + u32 size; + u32 threshold; + u32 priority; + enum idxd_wq_state state; + unsigned long flags; + union wqcfg *wqcfg; + u32 vec_ptr; /* interrupt steering */ + struct dsa_hw_desc **hw_descs; + int num_descs; + struct dsa_completion_record *compls; + dma_addr_t compls_addr; + int compls_size; + struct idxd_desc **descs; + struct sbitmap_queue sbq; + struct idxd_dma_chan *idxd_chan; + char name[WQ_NAME_SIZE + 1]; + u64 max_xfer_bytes; + u32 max_batch_size; +}; + +struct idxd_engine { + struct device conf_dev; + int id; + struct idxd_group *group; + struct idxd_device *idxd; +}; + +/* shadow registers */ +struct idxd_hw { + u32 version; + union gen_cap_reg gen_cap; + union wq_cap_reg wq_cap; + union group_cap_reg group_cap; + union engine_cap_reg engine_cap; + struct opcap opcap; +}; + +enum idxd_device_state { + IDXD_DEV_HALTED = -1, + IDXD_DEV_DISABLED = 0, + IDXD_DEV_CONF_READY, + IDXD_DEV_ENABLED, +}; + +enum idxd_device_flag { + IDXD_FLAG_CONFIGURABLE = 0, + IDXD_FLAG_CMD_RUNNING, +}; + +struct idxd_dma_dev { + struct idxd_device *idxd; + struct dma_device dma; +}; + +struct idxd_device { + enum idxd_type type; + struct device conf_dev; + struct list_head list; + struct idxd_hw hw; + enum idxd_device_state state; + unsigned long flags; + int id; + int major; + u8 cmd_status; + + struct pci_dev *pdev; + void __iomem *reg_base; + + spinlock_t dev_lock; /* spinlock for device */ + struct completion *cmd_done; + struct idxd_group *groups; + struct idxd_wq *wqs; + struct idxd_engine *engines; + + int num_groups; + + u32 msix_perm_offset; + u32 wqcfg_offset; + u32 grpcfg_offset; + u32 perfmon_offset; + + u64 max_xfer_bytes; + u32 max_batch_size; + int max_groups; + int max_engines; + int max_tokens; + int max_wqs; + int max_wq_size; + int token_limit; + int nr_tokens; /* non-reserved tokens */ + unsigned int wqcfg_size; + + union sw_err_reg sw_err; + wait_queue_head_t cmd_waitq; + struct msix_entry *msix_entries; + int num_wq_irqs; + struct idxd_irq_entry *irq_entries; + + struct idxd_dma_dev *idxd_dma; + struct workqueue_struct *wq; + struct work_struct work; +}; + +/* IDXD software descriptor */ +struct idxd_desc { + struct dsa_hw_desc *hw; + dma_addr_t desc_dma; + struct dsa_completion_record *completion; + dma_addr_t compl_dma; + struct dma_async_tx_descriptor txd; + struct llist_node llnode; + struct list_head list; + int id; + int cpu; + struct idxd_wq *wq; +}; + +#define confdev_to_idxd(dev) container_of(dev, struct idxd_device, conf_dev) +#define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev) + +extern struct bus_type dsa_bus_type; + +static inline bool wq_dedicated(struct idxd_wq *wq) +{ + return test_bit(WQ_FLAG_DEDICATED, &wq->flags); +} + +enum idxd_portal_prot { + IDXD_PORTAL_UNLIMITED = 0, + IDXD_PORTAL_LIMITED, +}; + +static inline int idxd_get_wq_portal_offset(enum idxd_portal_prot prot) +{ + return prot * 0x1000; +} + +static inline int idxd_get_wq_portal_full_offset(int wq_id, + enum idxd_portal_prot prot) +{ + return ((wq_id * 4) << PAGE_SHIFT) + idxd_get_wq_portal_offset(prot); +} + +static inline void idxd_set_type(struct idxd_device *idxd) +{ + struct pci_dev *pdev = idxd->pdev; + + if (pdev->device == PCI_DEVICE_ID_INTEL_DSA_SPR0) + idxd->type = IDXD_TYPE_DSA; + else + idxd->type = IDXD_TYPE_UNKNOWN; +} + +static inline void idxd_wq_get(struct idxd_wq *wq) +{ + wq->client_count++; +} + +static inline void idxd_wq_put(struct idxd_wq *wq) +{ + wq->client_count--; +} + +static inline int idxd_wq_refcount(struct idxd_wq *wq) +{ + return wq->client_count; +}; + +const char *idxd_get_dev_name(struct idxd_device *idxd); +int idxd_register_bus_type(void); +void idxd_unregister_bus_type(void); +int idxd_setup_sysfs(struct idxd_device *idxd); +void idxd_cleanup_sysfs(struct idxd_device *idxd); +int idxd_register_driver(void); +void idxd_unregister_driver(void); +struct bus_type *idxd_get_bus_type(struct idxd_device *idxd); + +/* device interrupt control */ +irqreturn_t idxd_irq_handler(int vec, void *data); +irqreturn_t idxd_misc_thread(int vec, void *data); +irqreturn_t idxd_wq_thread(int irq, void *data); +void idxd_mask_error_interrupts(struct idxd_device *idxd); +void idxd_unmask_error_interrupts(struct idxd_device *idxd); +void idxd_mask_msix_vectors(struct idxd_device *idxd); +void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id); +void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id); + +/* device control */ +int idxd_device_init_reset(struct idxd_device *idxd); +int idxd_device_enable(struct idxd_device *idxd); +int idxd_device_disable(struct idxd_device *idxd); +void idxd_device_reset(struct idxd_device *idxd); +void idxd_device_cleanup(struct idxd_device *idxd); +int idxd_device_config(struct idxd_device *idxd); +void idxd_device_wqs_clear_state(struct idxd_device *idxd); + +/* work queue control */ +int idxd_wq_alloc_resources(struct idxd_wq *wq); +void idxd_wq_free_resources(struct idxd_wq *wq); +int idxd_wq_enable(struct idxd_wq *wq); +int idxd_wq_disable(struct idxd_wq *wq); +void idxd_wq_drain(struct idxd_wq *wq); +void idxd_wq_reset(struct idxd_wq *wq); +int idxd_wq_map_portal(struct idxd_wq *wq); +void idxd_wq_unmap_portal(struct idxd_wq *wq); +void idxd_wq_disable_cleanup(struct idxd_wq *wq); + +/* submission */ +int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc); +struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype); +void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc); + +/* dmaengine */ +int idxd_register_dma_device(struct idxd_device *idxd); +void idxd_unregister_dma_device(struct idxd_device *idxd); +int idxd_register_dma_channel(struct idxd_wq *wq); +void idxd_unregister_dma_channel(struct idxd_wq *wq); +void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res); +void idxd_dma_complete_txd(struct idxd_desc *desc, + enum idxd_complete_type comp_type); + +/* cdev */ +int idxd_cdev_register(void); +void idxd_cdev_remove(void); +int idxd_cdev_get_major(struct idxd_device *idxd); +int idxd_wq_add_cdev(struct idxd_wq *wq); +void idxd_wq_del_cdev(struct idxd_wq *wq); + +#endif diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c new file mode 100644 index 000000000..048a23018 --- /dev/null +++ b/drivers/dma/idxd/init.c @@ -0,0 +1,526 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/workqueue.h> +#include <linux/aer.h> +#include <linux/fs.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/device.h> +#include <linux/idr.h> +#include <uapi/linux/idxd.h> +#include <linux/dmaengine.h> +#include "../dmaengine.h" +#include "registers.h" +#include "idxd.h" + +MODULE_VERSION(IDXD_DRIVER_VERSION); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Intel Corporation"); + +#define DRV_NAME "idxd" + +static struct idr idxd_idrs[IDXD_TYPE_MAX]; +static struct mutex idxd_idr_lock; + +static struct pci_device_id idxd_pci_tbl[] = { + /* DSA ver 1.0 platforms */ + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, idxd_pci_tbl); + +static char *idxd_name[] = { + "dsa", +}; + +const char *idxd_get_dev_name(struct idxd_device *idxd) +{ + return idxd_name[idxd->type]; +} + +static int idxd_setup_interrupts(struct idxd_device *idxd) +{ + struct pci_dev *pdev = idxd->pdev; + struct device *dev = &pdev->dev; + struct msix_entry *msix; + struct idxd_irq_entry *irq_entry; + int i, msixcnt; + int rc = 0; + + msixcnt = pci_msix_vec_count(pdev); + if (msixcnt < 0) { + dev_err(dev, "Not MSI-X interrupt capable.\n"); + goto err_no_irq; + } + + idxd->msix_entries = devm_kzalloc(dev, sizeof(struct msix_entry) * + msixcnt, GFP_KERNEL); + if (!idxd->msix_entries) { + rc = -ENOMEM; + goto err_no_irq; + } + + for (i = 0; i < msixcnt; i++) + idxd->msix_entries[i].entry = i; + + rc = pci_enable_msix_exact(pdev, idxd->msix_entries, msixcnt); + if (rc) { + dev_err(dev, "Failed enabling %d MSIX entries.\n", msixcnt); + goto err_no_irq; + } + dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt); + + /* + * We implement 1 completion list per MSI-X entry except for + * entry 0, which is for errors and others. + */ + idxd->irq_entries = devm_kcalloc(dev, msixcnt, + sizeof(struct idxd_irq_entry), + GFP_KERNEL); + if (!idxd->irq_entries) { + rc = -ENOMEM; + goto err_no_irq; + } + + for (i = 0; i < msixcnt; i++) { + idxd->irq_entries[i].id = i; + idxd->irq_entries[i].idxd = idxd; + } + + msix = &idxd->msix_entries[0]; + irq_entry = &idxd->irq_entries[0]; + rc = devm_request_threaded_irq(dev, msix->vector, idxd_irq_handler, + idxd_misc_thread, 0, "idxd-misc", + irq_entry); + if (rc < 0) { + dev_err(dev, "Failed to allocate misc interrupt.\n"); + goto err_no_irq; + } + + dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", + msix->vector); + + /* first MSI-X entry is not for wq interrupts */ + idxd->num_wq_irqs = msixcnt - 1; + + for (i = 1; i < msixcnt; i++) { + msix = &idxd->msix_entries[i]; + irq_entry = &idxd->irq_entries[i]; + + init_llist_head(&idxd->irq_entries[i].pending_llist); + INIT_LIST_HEAD(&idxd->irq_entries[i].work_list); + rc = devm_request_threaded_irq(dev, msix->vector, + idxd_irq_handler, + idxd_wq_thread, 0, + "idxd-portal", irq_entry); + if (rc < 0) { + dev_err(dev, "Failed to allocate irq %d.\n", + msix->vector); + goto err_no_irq; + } + dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", + i, msix->vector); + } + + idxd_unmask_error_interrupts(idxd); + + return 0; + + err_no_irq: + /* Disable error interrupt generation */ + idxd_mask_error_interrupts(idxd); + pci_disable_msix(pdev); + dev_err(dev, "No usable interrupts\n"); + return rc; +} + +static int idxd_setup_internals(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int i; + + init_waitqueue_head(&idxd->cmd_waitq); + idxd->groups = devm_kcalloc(dev, idxd->max_groups, + sizeof(struct idxd_group), GFP_KERNEL); + if (!idxd->groups) + return -ENOMEM; + + for (i = 0; i < idxd->max_groups; i++) { + idxd->groups[i].idxd = idxd; + idxd->groups[i].id = i; + idxd->groups[i].tc_a = -1; + idxd->groups[i].tc_b = -1; + } + + idxd->wqs = devm_kcalloc(dev, idxd->max_wqs, sizeof(struct idxd_wq), + GFP_KERNEL); + if (!idxd->wqs) + return -ENOMEM; + + idxd->engines = devm_kcalloc(dev, idxd->max_engines, + sizeof(struct idxd_engine), GFP_KERNEL); + if (!idxd->engines) + return -ENOMEM; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + wq->id = i; + wq->idxd = idxd; + mutex_init(&wq->wq_lock); + init_waitqueue_head(&wq->err_queue); + wq->max_xfer_bytes = idxd->max_xfer_bytes; + wq->max_batch_size = idxd->max_batch_size; + wq->wqcfg = devm_kzalloc(dev, idxd->wqcfg_size, GFP_KERNEL); + if (!wq->wqcfg) + return -ENOMEM; + } + + for (i = 0; i < idxd->max_engines; i++) { + idxd->engines[i].idxd = idxd; + idxd->engines[i].id = i; + } + + idxd->wq = create_workqueue(dev_name(dev)); + if (!idxd->wq) + return -ENOMEM; + + return 0; +} + +static void idxd_read_table_offsets(struct idxd_device *idxd) +{ + union offsets_reg offsets; + struct device *dev = &idxd->pdev->dev; + + offsets.bits[0] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET); + offsets.bits[1] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET + + sizeof(u64)); + idxd->grpcfg_offset = offsets.grpcfg * 0x100; + dev_dbg(dev, "IDXD Group Config Offset: %#x\n", idxd->grpcfg_offset); + idxd->wqcfg_offset = offsets.wqcfg * 0x100; + dev_dbg(dev, "IDXD Work Queue Config Offset: %#x\n", + idxd->wqcfg_offset); + idxd->msix_perm_offset = offsets.msix_perm * 0x100; + dev_dbg(dev, "IDXD MSIX Permission Offset: %#x\n", + idxd->msix_perm_offset); + idxd->perfmon_offset = offsets.perfmon * 0x100; + dev_dbg(dev, "IDXD Perfmon Offset: %#x\n", idxd->perfmon_offset); +} + +static void idxd_read_caps(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int i; + + /* reading generic capabilities */ + idxd->hw.gen_cap.bits = ioread64(idxd->reg_base + IDXD_GENCAP_OFFSET); + dev_dbg(dev, "gen_cap: %#llx\n", idxd->hw.gen_cap.bits); + idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift; + dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes); + idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift; + dev_dbg(dev, "max batch size: %u\n", idxd->max_batch_size); + if (idxd->hw.gen_cap.config_en) + set_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags); + + /* reading group capabilities */ + idxd->hw.group_cap.bits = + ioread64(idxd->reg_base + IDXD_GRPCAP_OFFSET); + dev_dbg(dev, "group_cap: %#llx\n", idxd->hw.group_cap.bits); + idxd->max_groups = idxd->hw.group_cap.num_groups; + dev_dbg(dev, "max groups: %u\n", idxd->max_groups); + idxd->max_tokens = idxd->hw.group_cap.total_tokens; + dev_dbg(dev, "max tokens: %u\n", idxd->max_tokens); + idxd->nr_tokens = idxd->max_tokens; + + /* read engine capabilities */ + idxd->hw.engine_cap.bits = + ioread64(idxd->reg_base + IDXD_ENGCAP_OFFSET); + dev_dbg(dev, "engine_cap: %#llx\n", idxd->hw.engine_cap.bits); + idxd->max_engines = idxd->hw.engine_cap.num_engines; + dev_dbg(dev, "max engines: %u\n", idxd->max_engines); + + /* read workqueue capabilities */ + idxd->hw.wq_cap.bits = ioread64(idxd->reg_base + IDXD_WQCAP_OFFSET); + dev_dbg(dev, "wq_cap: %#llx\n", idxd->hw.wq_cap.bits); + idxd->max_wq_size = idxd->hw.wq_cap.total_wq_size; + dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size); + idxd->max_wqs = idxd->hw.wq_cap.num_wqs; + dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs); + idxd->wqcfg_size = 1 << (idxd->hw.wq_cap.wqcfg_size + IDXD_WQCFG_MIN); + dev_dbg(dev, "wqcfg size: %u\n", idxd->wqcfg_size); + + /* reading operation capabilities */ + for (i = 0; i < 4; i++) { + idxd->hw.opcap.bits[i] = ioread64(idxd->reg_base + + IDXD_OPCAP_OFFSET + i * sizeof(u64)); + dev_dbg(dev, "opcap[%d]: %#llx\n", i, idxd->hw.opcap.bits[i]); + } +} + +static struct idxd_device *idxd_alloc(struct pci_dev *pdev, + void __iomem * const *iomap) +{ + struct device *dev = &pdev->dev; + struct idxd_device *idxd; + + idxd = devm_kzalloc(dev, sizeof(struct idxd_device), GFP_KERNEL); + if (!idxd) + return NULL; + + idxd->pdev = pdev; + idxd->reg_base = iomap[IDXD_MMIO_BAR]; + spin_lock_init(&idxd->dev_lock); + + return idxd; +} + +static int idxd_probe(struct idxd_device *idxd) +{ + struct pci_dev *pdev = idxd->pdev; + struct device *dev = &pdev->dev; + int rc; + + dev_dbg(dev, "%s entered and resetting device\n", __func__); + rc = idxd_device_init_reset(idxd); + if (rc < 0) + return rc; + + dev_dbg(dev, "IDXD reset complete\n"); + + idxd_read_caps(idxd); + idxd_read_table_offsets(idxd); + + rc = idxd_setup_internals(idxd); + if (rc) + goto err_setup; + + rc = idxd_setup_interrupts(idxd); + if (rc) + goto err_setup; + + dev_dbg(dev, "IDXD interrupt setup complete.\n"); + + mutex_lock(&idxd_idr_lock); + idxd->id = idr_alloc(&idxd_idrs[idxd->type], idxd, 0, 0, GFP_KERNEL); + mutex_unlock(&idxd_idr_lock); + if (idxd->id < 0) { + rc = -ENOMEM; + goto err_idr_fail; + } + + idxd->major = idxd_cdev_get_major(idxd); + + dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id); + return 0; + + err_idr_fail: + idxd_mask_error_interrupts(idxd); + idxd_mask_msix_vectors(idxd); + err_setup: + return rc; +} + +static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + void __iomem * const *iomap; + struct device *dev = &pdev->dev; + struct idxd_device *idxd; + int rc; + unsigned int mask; + + rc = pcim_enable_device(pdev); + if (rc) + return rc; + + dev_dbg(dev, "Mapping BARs\n"); + mask = (1 << IDXD_MMIO_BAR); + rc = pcim_iomap_regions(pdev, mask, DRV_NAME); + if (rc) + return rc; + + iomap = pcim_iomap_table(pdev); + if (!iomap) + return -ENOMEM; + + dev_dbg(dev, "Set DMA masks\n"); + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (rc) + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (rc) + return rc; + + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (rc) + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (rc) + return rc; + + dev_dbg(dev, "Alloc IDXD context\n"); + idxd = idxd_alloc(pdev, iomap); + if (!idxd) + return -ENOMEM; + + idxd_set_type(idxd); + + dev_dbg(dev, "Set PCI master\n"); + pci_set_master(pdev); + pci_set_drvdata(pdev, idxd); + + idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET); + rc = idxd_probe(idxd); + if (rc) { + dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n"); + return -ENODEV; + } + + rc = idxd_setup_sysfs(idxd); + if (rc) { + dev_err(dev, "IDXD sysfs setup failed\n"); + return -ENODEV; + } + + idxd->state = IDXD_DEV_CONF_READY; + + dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", + idxd->hw.version); + + return 0; +} + +static void idxd_flush_pending_llist(struct idxd_irq_entry *ie) +{ + struct idxd_desc *desc, *itr; + struct llist_node *head; + + head = llist_del_all(&ie->pending_llist); + if (!head) + return; + + llist_for_each_entry_safe(desc, itr, head, llnode) { + idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT); + idxd_free_desc(desc->wq, desc); + } +} + +static void idxd_flush_work_list(struct idxd_irq_entry *ie) +{ + struct idxd_desc *desc, *iter; + + list_for_each_entry_safe(desc, iter, &ie->work_list, list) { + list_del(&desc->list); + idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT); + idxd_free_desc(desc->wq, desc); + } +} + +static void idxd_shutdown(struct pci_dev *pdev) +{ + struct idxd_device *idxd = pci_get_drvdata(pdev); + int rc, i; + struct idxd_irq_entry *irq_entry; + int msixcnt = pci_msix_vec_count(pdev); + + rc = idxd_device_disable(idxd); + if (rc) + dev_err(&pdev->dev, "Disabling device failed\n"); + + dev_dbg(&pdev->dev, "%s called\n", __func__); + idxd_mask_msix_vectors(idxd); + idxd_mask_error_interrupts(idxd); + + for (i = 0; i < msixcnt; i++) { + irq_entry = &idxd->irq_entries[i]; + synchronize_irq(idxd->msix_entries[i].vector); + if (i == 0) + continue; + idxd_flush_pending_llist(irq_entry); + idxd_flush_work_list(irq_entry); + } + + destroy_workqueue(idxd->wq); +} + +static void idxd_remove(struct pci_dev *pdev) +{ + struct idxd_device *idxd = pci_get_drvdata(pdev); + + dev_dbg(&pdev->dev, "%s called\n", __func__); + idxd_cleanup_sysfs(idxd); + idxd_shutdown(pdev); + mutex_lock(&idxd_idr_lock); + idr_remove(&idxd_idrs[idxd->type], idxd->id); + mutex_unlock(&idxd_idr_lock); +} + +static struct pci_driver idxd_pci_driver = { + .name = DRV_NAME, + .id_table = idxd_pci_tbl, + .probe = idxd_pci_probe, + .remove = idxd_remove, + .shutdown = idxd_shutdown, +}; + +static int __init idxd_init_module(void) +{ + int err, i; + + /* + * If the CPU does not support write512, there's no point in + * enumerating the device. We can not utilize it. + */ + if (!boot_cpu_has(X86_FEATURE_MOVDIR64B)) { + pr_warn("idxd driver failed to load without MOVDIR64B.\n"); + return -ENODEV; + } + + pr_info("%s: Intel(R) Accelerator Devices Driver %s\n", + DRV_NAME, IDXD_DRIVER_VERSION); + + mutex_init(&idxd_idr_lock); + for (i = 0; i < IDXD_TYPE_MAX; i++) + idr_init(&idxd_idrs[i]); + + err = idxd_register_bus_type(); + if (err < 0) + return err; + + err = idxd_register_driver(); + if (err < 0) + goto err_idxd_driver_register; + + err = idxd_cdev_register(); + if (err) + goto err_cdev_register; + + err = pci_register_driver(&idxd_pci_driver); + if (err) + goto err_pci_register; + + return 0; + +err_pci_register: + idxd_cdev_remove(); +err_cdev_register: + idxd_unregister_driver(); +err_idxd_driver_register: + idxd_unregister_bus_type(); + return err; +} +module_init(idxd_init_module); + +static void __exit idxd_exit_module(void) +{ + idxd_unregister_driver(); + pci_unregister_driver(&idxd_pci_driver); + idxd_cdev_remove(); + idxd_unregister_bus_type(); +} +module_exit(idxd_exit_module); diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c new file mode 100644 index 000000000..fc9579180 --- /dev/null +++ b/drivers/dma/idxd/irq.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/dmaengine.h> +#include <uapi/linux/idxd.h> +#include "../dmaengine.h" +#include "idxd.h" +#include "registers.h" + +static void idxd_device_reinit(struct work_struct *work) +{ + struct idxd_device *idxd = container_of(work, struct idxd_device, work); + struct device *dev = &idxd->pdev->dev; + int rc, i; + + idxd_device_reset(idxd); + rc = idxd_device_config(idxd); + if (rc < 0) + goto out; + + rc = idxd_device_enable(idxd); + if (rc < 0) + goto out; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + if (wq->state == IDXD_WQ_ENABLED) { + rc = idxd_wq_enable(wq); + if (rc < 0) { + dev_warn(dev, "Unable to re-enable wq %s\n", + dev_name(&wq->conf_dev)); + } + } + } + + return; + + out: + idxd_device_wqs_clear_state(idxd); +} + +irqreturn_t idxd_irq_handler(int vec, void *data) +{ + struct idxd_irq_entry *irq_entry = data; + struct idxd_device *idxd = irq_entry->idxd; + + idxd_mask_msix_vector(idxd, irq_entry->id); + return IRQ_WAKE_THREAD; +} + +static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) +{ + struct device *dev = &idxd->pdev->dev; + union gensts_reg gensts; + u32 val = 0; + int i; + bool err = false; + + if (cause & IDXD_INTC_ERR) { + spin_lock_bh(&idxd->dev_lock); + for (i = 0; i < 4; i++) + idxd->sw_err.bits[i] = ioread64(idxd->reg_base + + IDXD_SWERR_OFFSET + i * sizeof(u64)); + + iowrite64(idxd->sw_err.bits[0] & IDXD_SWERR_ACK, + idxd->reg_base + IDXD_SWERR_OFFSET); + + if (idxd->sw_err.valid && idxd->sw_err.wq_idx_valid) { + int id = idxd->sw_err.wq_idx; + struct idxd_wq *wq = &idxd->wqs[id]; + + if (wq->type == IDXD_WQT_USER) + wake_up_interruptible(&wq->err_queue); + } else { + int i; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + if (wq->type == IDXD_WQT_USER) + wake_up_interruptible(&wq->err_queue); + } + } + + spin_unlock_bh(&idxd->dev_lock); + val |= IDXD_INTC_ERR; + + for (i = 0; i < 4; i++) + dev_warn(dev, "err[%d]: %#16.16llx\n", + i, idxd->sw_err.bits[i]); + err = true; + } + + if (cause & IDXD_INTC_CMD) { + val |= IDXD_INTC_CMD; + complete(idxd->cmd_done); + } + + if (cause & IDXD_INTC_OCCUPY) { + /* Driver does not utilize occupancy interrupt */ + val |= IDXD_INTC_OCCUPY; + } + + if (cause & IDXD_INTC_PERFMON_OVFL) { + /* + * Driver does not utilize perfmon counter overflow interrupt + * yet. + */ + val |= IDXD_INTC_PERFMON_OVFL; + } + + val ^= cause; + if (val) + dev_warn_once(dev, "Unexpected interrupt cause bits set: %#x\n", + val); + + if (!err) + return 0; + + gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); + if (gensts.state == IDXD_DEVICE_STATE_HALT) { + idxd->state = IDXD_DEV_HALTED; + if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) { + /* + * If we need a software reset, we will throw the work + * on a system workqueue in order to allow interrupts + * for the device command completions. + */ + INIT_WORK(&idxd->work, idxd_device_reinit); + queue_work(idxd->wq, &idxd->work); + } else { + spin_lock_bh(&idxd->dev_lock); + idxd_device_wqs_clear_state(idxd); + dev_err(&idxd->pdev->dev, + "idxd halted, need %s.\n", + gensts.reset_type == IDXD_DEVICE_RESET_FLR ? + "FLR" : "system reset"); + spin_unlock_bh(&idxd->dev_lock); + return -ENXIO; + } + } + + return 0; +} + +irqreturn_t idxd_misc_thread(int vec, void *data) +{ + struct idxd_irq_entry *irq_entry = data; + struct idxd_device *idxd = irq_entry->idxd; + int rc; + u32 cause; + + cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); + if (cause) + iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); + + while (cause) { + rc = process_misc_interrupts(idxd, cause); + if (rc < 0) + break; + cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); + if (cause) + iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); + } + + idxd_unmask_msix_vector(idxd, irq_entry->id); + return IRQ_HANDLED; +} + +static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry, + int *processed) +{ + struct idxd_desc *desc, *t; + struct llist_node *head; + int queued = 0; + + *processed = 0; + head = llist_del_all(&irq_entry->pending_llist); + if (!head) + return 0; + + llist_for_each_entry_safe(desc, t, head, llnode) { + if (desc->completion->status) { + idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL); + idxd_free_desc(desc->wq, desc); + (*processed)++; + } else { + list_add_tail(&desc->list, &irq_entry->work_list); + queued++; + } + } + + return queued; +} + +static int irq_process_work_list(struct idxd_irq_entry *irq_entry, + int *processed) +{ + struct list_head *node, *next; + int queued = 0; + + *processed = 0; + if (list_empty(&irq_entry->work_list)) + return 0; + + list_for_each_safe(node, next, &irq_entry->work_list) { + struct idxd_desc *desc = + container_of(node, struct idxd_desc, list); + + if (desc->completion->status) { + list_del(&desc->list); + /* process and callback */ + idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL); + idxd_free_desc(desc->wq, desc); + (*processed)++; + } else { + queued++; + } + } + + return queued; +} + +static int idxd_desc_process(struct idxd_irq_entry *irq_entry) +{ + int rc, processed, total = 0; + + /* + * There are two lists we are processing. The pending_llist is where + * submmiter adds all the submitted descriptor after sending it to + * the workqueue. It's a lockless singly linked list. The work_list + * is the common linux double linked list. We are in a scenario of + * multiple producers and a single consumer. The producers are all + * the kernel submitters of descriptors, and the consumer is the + * kernel irq handler thread for the msix vector when using threaded + * irq. To work with the restrictions of llist to remain lockless, + * we are doing the following steps: + * 1. Iterate through the work_list and process any completed + * descriptor. Delete the completed entries during iteration. + * 2. llist_del_all() from the pending list. + * 3. Iterate through the llist that was deleted from the pending list + * and process the completed entries. + * 4. If the entry is still waiting on hardware, list_add_tail() to + * the work_list. + * 5. Repeat until no more descriptors. + */ + do { + rc = irq_process_work_list(irq_entry, &processed); + total += processed; + if (rc != 0) + continue; + + rc = irq_process_pending_llist(irq_entry, &processed); + total += processed; + } while (rc != 0); + + return total; +} + +irqreturn_t idxd_wq_thread(int irq, void *data) +{ + struct idxd_irq_entry *irq_entry = data; + int processed; + + processed = idxd_desc_process(irq_entry); + idxd_unmask_msix_vector(irq_entry->idxd, irq_entry->id); + + if (processed == 0) + return IRQ_NONE; + + return IRQ_HANDLED; +} diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h new file mode 100644 index 000000000..54390334c --- /dev/null +++ b/drivers/dma/idxd/registers.h @@ -0,0 +1,357 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#ifndef _IDXD_REGISTERS_H_ +#define _IDXD_REGISTERS_H_ + +/* PCI Config */ +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 + +#define IDXD_MMIO_BAR 0 +#define IDXD_WQ_BAR 2 +#define IDXD_PORTAL_SIZE PAGE_SIZE + +/* MMIO Device BAR0 Registers */ +#define IDXD_VER_OFFSET 0x00 +#define IDXD_VER_MAJOR_MASK 0xf0 +#define IDXD_VER_MINOR_MASK 0x0f +#define GET_IDXD_VER_MAJOR(x) (((x) & IDXD_VER_MAJOR_MASK) >> 4) +#define GET_IDXD_VER_MINOR(x) ((x) & IDXD_VER_MINOR_MASK) + +union gen_cap_reg { + struct { + u64 block_on_fault:1; + u64 overlap_copy:1; + u64 cache_control_mem:1; + u64 cache_control_cache:1; + u64 rsvd:3; + u64 int_handle_req:1; + u64 dest_readback:1; + u64 drain_readback:1; + u64 rsvd2:6; + u64 max_xfer_shift:5; + u64 max_batch_shift:4; + u64 max_ims_mult:6; + u64 config_en:1; + u64 max_descs_per_engine:8; + u64 rsvd3:24; + }; + u64 bits; +} __packed; +#define IDXD_GENCAP_OFFSET 0x10 + +union wq_cap_reg { + struct { + u64 total_wq_size:16; + u64 num_wqs:8; + u64 wqcfg_size:4; + u64 rsvd:20; + u64 shared_mode:1; + u64 dedicated_mode:1; + u64 rsvd2:1; + u64 priority:1; + u64 occupancy:1; + u64 occupancy_int:1; + u64 rsvd3:10; + }; + u64 bits; +} __packed; +#define IDXD_WQCAP_OFFSET 0x20 +#define IDXD_WQCFG_MIN 5 + +union group_cap_reg { + struct { + u64 num_groups:8; + u64 total_tokens:8; + u64 token_en:1; + u64 token_limit:1; + u64 rsvd:46; + }; + u64 bits; +} __packed; +#define IDXD_GRPCAP_OFFSET 0x30 + +union engine_cap_reg { + struct { + u64 num_engines:8; + u64 rsvd:56; + }; + u64 bits; +} __packed; + +#define IDXD_ENGCAP_OFFSET 0x38 + +#define IDXD_OPCAP_NOOP 0x0001 +#define IDXD_OPCAP_BATCH 0x0002 +#define IDXD_OPCAP_MEMMOVE 0x0008 +struct opcap { + u64 bits[4]; +}; + +#define IDXD_OPCAP_OFFSET 0x40 + +#define IDXD_TABLE_OFFSET 0x60 +union offsets_reg { + struct { + u64 grpcfg:16; + u64 wqcfg:16; + u64 msix_perm:16; + u64 ims:16; + u64 perfmon:16; + u64 rsvd:48; + }; + u64 bits[2]; +} __packed; + +#define IDXD_GENCFG_OFFSET 0x80 +union gencfg_reg { + struct { + u32 token_limit:8; + u32 rsvd:4; + u32 user_int_en:1; + u32 rsvd2:19; + }; + u32 bits; +} __packed; + +#define IDXD_GENCTRL_OFFSET 0x88 +union genctrl_reg { + struct { + u32 softerr_int_en:1; + u32 rsvd:31; + }; + u32 bits; +} __packed; + +#define IDXD_GENSTATS_OFFSET 0x90 +union gensts_reg { + struct { + u32 state:2; + u32 reset_type:2; + u32 rsvd:28; + }; + u32 bits; +} __packed; + +enum idxd_device_status_state { + IDXD_DEVICE_STATE_DISABLED = 0, + IDXD_DEVICE_STATE_ENABLED, + IDXD_DEVICE_STATE_DRAIN, + IDXD_DEVICE_STATE_HALT, +}; + +enum idxd_device_reset_type { + IDXD_DEVICE_RESET_SOFTWARE = 0, + IDXD_DEVICE_RESET_FLR, + IDXD_DEVICE_RESET_WARM, + IDXD_DEVICE_RESET_COLD, +}; + +#define IDXD_INTCAUSE_OFFSET 0x98 +#define IDXD_INTC_ERR 0x01 +#define IDXD_INTC_CMD 0x02 +#define IDXD_INTC_OCCUPY 0x04 +#define IDXD_INTC_PERFMON_OVFL 0x08 + +#define IDXD_CMD_OFFSET 0xa0 +union idxd_command_reg { + struct { + u32 operand:20; + u32 cmd:5; + u32 rsvd:6; + u32 int_req:1; + }; + u32 bits; +} __packed; + +enum idxd_cmd { + IDXD_CMD_ENABLE_DEVICE = 1, + IDXD_CMD_DISABLE_DEVICE, + IDXD_CMD_DRAIN_ALL, + IDXD_CMD_ABORT_ALL, + IDXD_CMD_RESET_DEVICE, + IDXD_CMD_ENABLE_WQ, + IDXD_CMD_DISABLE_WQ, + IDXD_CMD_DRAIN_WQ, + IDXD_CMD_ABORT_WQ, + IDXD_CMD_RESET_WQ, + IDXD_CMD_DRAIN_PASID, + IDXD_CMD_ABORT_PASID, + IDXD_CMD_REQUEST_INT_HANDLE, +}; + +#define IDXD_CMDSTS_OFFSET 0xa8 +union cmdsts_reg { + struct { + u8 err; + u16 result; + u8 rsvd:7; + u8 active:1; + }; + u32 bits; +} __packed; +#define IDXD_CMDSTS_ACTIVE 0x80000000 + +enum idxd_cmdsts_err { + IDXD_CMDSTS_SUCCESS = 0, + IDXD_CMDSTS_INVAL_CMD, + IDXD_CMDSTS_INVAL_WQIDX, + IDXD_CMDSTS_HW_ERR, + /* enable device errors */ + IDXD_CMDSTS_ERR_DEV_ENABLED = 0x10, + IDXD_CMDSTS_ERR_CONFIG, + IDXD_CMDSTS_ERR_BUSMASTER_EN, + IDXD_CMDSTS_ERR_PASID_INVAL, + IDXD_CMDSTS_ERR_WQ_SIZE_ERANGE, + IDXD_CMDSTS_ERR_GRP_CONFIG, + IDXD_CMDSTS_ERR_GRP_CONFIG2, + IDXD_CMDSTS_ERR_GRP_CONFIG3, + IDXD_CMDSTS_ERR_GRP_CONFIG4, + /* enable wq errors */ + IDXD_CMDSTS_ERR_DEV_NOTEN = 0x20, + IDXD_CMDSTS_ERR_WQ_ENABLED, + IDXD_CMDSTS_ERR_WQ_SIZE, + IDXD_CMDSTS_ERR_WQ_PRIOR, + IDXD_CMDSTS_ERR_WQ_MODE, + IDXD_CMDSTS_ERR_BOF_EN, + IDXD_CMDSTS_ERR_PASID_EN, + IDXD_CMDSTS_ERR_MAX_BATCH_SIZE, + IDXD_CMDSTS_ERR_MAX_XFER_SIZE, + /* disable device errors */ + IDXD_CMDSTS_ERR_DIS_DEV_EN = 0x31, + /* disable WQ, drain WQ, abort WQ, reset WQ */ + IDXD_CMDSTS_ERR_DEV_NOT_EN, + /* request interrupt handle */ + IDXD_CMDSTS_ERR_INVAL_INT_IDX = 0x41, + IDXD_CMDSTS_ERR_NO_HANDLE, +}; + +#define IDXD_SWERR_OFFSET 0xc0 +#define IDXD_SWERR_VALID 0x00000001 +#define IDXD_SWERR_OVERFLOW 0x00000002 +#define IDXD_SWERR_ACK (IDXD_SWERR_VALID | IDXD_SWERR_OVERFLOW) +union sw_err_reg { + struct { + u64 valid:1; + u64 overflow:1; + u64 desc_valid:1; + u64 wq_idx_valid:1; + u64 batch:1; + u64 fault_rw:1; + u64 priv:1; + u64 rsvd:1; + u64 error:8; + u64 wq_idx:8; + u64 rsvd2:8; + u64 operation:8; + u64 pasid:20; + u64 rsvd3:4; + + u64 batch_idx:16; + u64 rsvd4:16; + u64 invalid_flags:32; + + u64 fault_addr; + + u64 rsvd5; + }; + u64 bits[4]; +} __packed; + +union msix_perm { + struct { + u32 rsvd:2; + u32 ignore:1; + u32 pasid_en:1; + u32 rsvd2:8; + u32 pasid:20; + }; + u32 bits; +} __packed; + +union group_flags { + struct { + u32 tc_a:3; + u32 tc_b:3; + u32 rsvd:1; + u32 use_token_limit:1; + u32 tokens_reserved:8; + u32 rsvd2:4; + u32 tokens_allowed:8; + u32 rsvd3:4; + }; + u32 bits; +} __packed; + +struct grpcfg { + u64 wqs[4]; + u64 engines; + union group_flags flags; +} __packed; + +union wqcfg { + struct { + /* bytes 0-3 */ + u16 wq_size; + u16 rsvd; + + /* bytes 4-7 */ + u16 wq_thresh; + u16 rsvd1; + + /* bytes 8-11 */ + u32 mode:1; /* shared or dedicated */ + u32 bof:1; /* block on fault */ + u32 rsvd2:2; + u32 priority:4; + u32 pasid:20; + u32 pasid_en:1; + u32 priv:1; + u32 rsvd3:2; + + /* bytes 12-15 */ + u32 max_xfer_shift:5; + u32 max_batch_shift:4; + u32 rsvd4:23; + + /* bytes 16-19 */ + u16 occupancy_inth; + u16 occupancy_table_sel:1; + u16 rsvd5:15; + + /* bytes 20-23 */ + u16 occupancy_limit; + u16 occupancy_int_en:1; + u16 rsvd6:15; + + /* bytes 24-27 */ + u16 occupancy; + u16 occupancy_int:1; + u16 rsvd7:12; + u16 mode_support:1; + u16 wq_state:2; + + /* bytes 28-31 */ + u32 rsvd8; + }; + u32 bits[8]; +} __packed; + +/* + * This macro calculates the offset into the WQCFG register + * idxd - struct idxd * + * n - wq id + * ofs - the index of the 32b dword for the config register + * + * The WQCFG register block is divided into groups per each wq. The n index + * allows us to move to the register group that's for that particular wq. + * Each register is 32bits. The ofs gives us the number of register to access. + */ +#define WQCFG_OFFSET(_idxd_dev, n, ofs) \ +({\ + typeof(_idxd_dev) __idxd_dev = (_idxd_dev); \ + (__idxd_dev)->wqcfg_offset + (n) * (__idxd_dev)->wqcfg_size + sizeof(u32) * (ofs); \ +}) + +#define WQCFG_STRIDES(_idxd_dev) ((_idxd_dev)->wqcfg_size / sizeof(u32)) + +#endif diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c new file mode 100644 index 000000000..0368c5490 --- /dev/null +++ b/drivers/dma/idxd/submit.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <uapi/linux/idxd.h> +#include "idxd.h" +#include "registers.h" + +static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu) +{ + struct idxd_desc *desc; + + desc = wq->descs[idx]; + memset(desc->hw, 0, sizeof(struct dsa_hw_desc)); + memset(desc->completion, 0, sizeof(struct dsa_completion_record)); + desc->cpu = cpu; + return desc; +} + +struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype) +{ + int cpu, idx; + struct idxd_device *idxd = wq->idxd; + DEFINE_SBQ_WAIT(wait); + struct sbq_wait_state *ws; + struct sbitmap_queue *sbq; + + if (idxd->state != IDXD_DEV_ENABLED) + return ERR_PTR(-EIO); + + sbq = &wq->sbq; + idx = sbitmap_queue_get(sbq, &cpu); + if (idx < 0) { + if (optype == IDXD_OP_NONBLOCK) + return ERR_PTR(-EAGAIN); + } else { + return __get_desc(wq, idx, cpu); + } + + ws = &sbq->ws[0]; + for (;;) { + sbitmap_prepare_to_wait(sbq, ws, &wait, TASK_INTERRUPTIBLE); + if (signal_pending_state(TASK_INTERRUPTIBLE, current)) + break; + idx = sbitmap_queue_get(sbq, &cpu); + if (idx >= 0) + break; + schedule(); + } + + sbitmap_finish_wait(sbq, ws, &wait); + if (idx < 0) + return ERR_PTR(-EAGAIN); + + return __get_desc(wq, idx, cpu); +} + +void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc) +{ + int cpu = desc->cpu; + + desc->cpu = -1; + sbitmap_queue_clear(&wq->sbq, desc->id, cpu); +} + +int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) +{ + struct idxd_device *idxd = wq->idxd; + int vec = desc->hw->int_handle; + void __iomem *portal; + + if (idxd->state != IDXD_DEV_ENABLED) + return -EIO; + + portal = wq->dportal; + /* + * The wmb() flushes writes to coherent DMA data before possibly + * triggering a DMA read. The wmb() is necessary even on UP because + * the recipient is a device. + */ + wmb(); + iosubmit_cmds512(portal, desc->hw, 1); + + /* + * Pending the descriptor to the lockless list for the irq_entry + * that we designated the descriptor to. + */ + if (desc->hw->flags & IDXD_OP_FLAG_RCI) + llist_add(&desc->llnode, + &idxd->irq_entries[vec].pending_llist); + + return 0; +} diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c new file mode 100644 index 000000000..51af0dfc3 --- /dev/null +++ b/drivers/dma/idxd/sysfs.c @@ -0,0 +1,1668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <uapi/linux/idxd.h> +#include "registers.h" +#include "idxd.h" + +static char *idxd_wq_type_names[] = { + [IDXD_WQT_NONE] = "none", + [IDXD_WQT_KERNEL] = "kernel", + [IDXD_WQT_USER] = "user", +}; + +static void idxd_conf_device_release(struct device *dev) +{ + dev_dbg(dev, "%s for %s\n", __func__, dev_name(dev)); +} + +static struct device_type idxd_group_device_type = { + .name = "group", + .release = idxd_conf_device_release, +}; + +static struct device_type idxd_wq_device_type = { + .name = "wq", + .release = idxd_conf_device_release, +}; + +static struct device_type idxd_engine_device_type = { + .name = "engine", + .release = idxd_conf_device_release, +}; + +static struct device_type dsa_device_type = { + .name = "dsa", + .release = idxd_conf_device_release, +}; + +static inline bool is_dsa_dev(struct device *dev) +{ + return dev ? dev->type == &dsa_device_type : false; +} + +static inline bool is_idxd_dev(struct device *dev) +{ + return is_dsa_dev(dev); +} + +static inline bool is_idxd_wq_dev(struct device *dev) +{ + return dev ? dev->type == &idxd_wq_device_type : false; +} + +static inline bool is_idxd_wq_dmaengine(struct idxd_wq *wq) +{ + if (wq->type == IDXD_WQT_KERNEL && + strcmp(wq->name, "dmaengine") == 0) + return true; + return false; +} + +static inline bool is_idxd_wq_cdev(struct idxd_wq *wq) +{ + return wq->type == IDXD_WQT_USER; +} + +static int idxd_config_bus_match(struct device *dev, + struct device_driver *drv) +{ + int matched = 0; + + if (is_idxd_dev(dev)) { + struct idxd_device *idxd = confdev_to_idxd(dev); + + if (idxd->state != IDXD_DEV_CONF_READY) + return 0; + matched = 1; + } else if (is_idxd_wq_dev(dev)) { + struct idxd_wq *wq = confdev_to_wq(dev); + struct idxd_device *idxd = wq->idxd; + + if (idxd->state < IDXD_DEV_CONF_READY) + return 0; + + if (wq->state != IDXD_WQ_DISABLED) { + dev_dbg(dev, "%s not disabled\n", dev_name(dev)); + return 0; + } + matched = 1; + } + + if (matched) + dev_dbg(dev, "%s matched\n", dev_name(dev)); + + return matched; +} + +static int idxd_config_bus_probe(struct device *dev) +{ + int rc; + unsigned long flags; + + dev_dbg(dev, "%s called\n", __func__); + + if (is_idxd_dev(dev)) { + struct idxd_device *idxd = confdev_to_idxd(dev); + + if (idxd->state != IDXD_DEV_CONF_READY) { + dev_warn(dev, "Device not ready for config\n"); + return -EBUSY; + } + + if (!try_module_get(THIS_MODULE)) + return -ENXIO; + + /* Perform IDXD configuration and enabling */ + spin_lock_irqsave(&idxd->dev_lock, flags); + rc = idxd_device_config(idxd); + spin_unlock_irqrestore(&idxd->dev_lock, flags); + if (rc < 0) { + module_put(THIS_MODULE); + dev_warn(dev, "Device config failed: %d\n", rc); + return rc; + } + + /* start device */ + rc = idxd_device_enable(idxd); + if (rc < 0) { + module_put(THIS_MODULE); + dev_warn(dev, "Device enable failed: %d\n", rc); + return rc; + } + + dev_info(dev, "Device %s enabled\n", dev_name(dev)); + + rc = idxd_register_dma_device(idxd); + if (rc < 0) { + module_put(THIS_MODULE); + dev_dbg(dev, "Failed to register dmaengine device\n"); + return rc; + } + return 0; + } else if (is_idxd_wq_dev(dev)) { + struct idxd_wq *wq = confdev_to_wq(dev); + struct idxd_device *idxd = wq->idxd; + + mutex_lock(&wq->wq_lock); + + if (idxd->state != IDXD_DEV_ENABLED) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "Enabling while device not enabled.\n"); + return -EPERM; + } + + if (wq->state != IDXD_WQ_DISABLED) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "WQ %d already enabled.\n", wq->id); + return -EBUSY; + } + + if (!wq->group) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "WQ not attached to group.\n"); + return -EINVAL; + } + + if (strlen(wq->name) == 0) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "WQ name not set.\n"); + return -EINVAL; + } + + rc = idxd_wq_alloc_resources(wq); + if (rc < 0) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "WQ resource alloc failed\n"); + return rc; + } + + spin_lock_irqsave(&idxd->dev_lock, flags); + rc = idxd_device_config(idxd); + spin_unlock_irqrestore(&idxd->dev_lock, flags); + if (rc < 0) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "Writing WQ %d config failed: %d\n", + wq->id, rc); + return rc; + } + + rc = idxd_wq_enable(wq); + if (rc < 0) { + mutex_unlock(&wq->wq_lock); + dev_warn(dev, "WQ %d enabling failed: %d\n", + wq->id, rc); + return rc; + } + + rc = idxd_wq_map_portal(wq); + if (rc < 0) { + dev_warn(dev, "wq portal mapping failed: %d\n", rc); + rc = idxd_wq_disable(wq); + if (rc < 0) + dev_warn(dev, "IDXD wq disable failed\n"); + mutex_unlock(&wq->wq_lock); + return rc; + } + + wq->client_count = 0; + + dev_info(dev, "wq %s enabled\n", dev_name(&wq->conf_dev)); + + if (is_idxd_wq_dmaengine(wq)) { + rc = idxd_register_dma_channel(wq); + if (rc < 0) { + dev_dbg(dev, "DMA channel register failed\n"); + mutex_unlock(&wq->wq_lock); + return rc; + } + } else if (is_idxd_wq_cdev(wq)) { + rc = idxd_wq_add_cdev(wq); + if (rc < 0) { + dev_dbg(dev, "Cdev creation failed\n"); + mutex_unlock(&wq->wq_lock); + return rc; + } + } + + mutex_unlock(&wq->wq_lock); + return 0; + } + + return -ENODEV; +} + +static void disable_wq(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + + mutex_lock(&wq->wq_lock); + dev_dbg(dev, "%s removing WQ %s\n", __func__, dev_name(&wq->conf_dev)); + if (wq->state == IDXD_WQ_DISABLED) { + mutex_unlock(&wq->wq_lock); + return; + } + + if (is_idxd_wq_dmaengine(wq)) + idxd_unregister_dma_channel(wq); + else if (is_idxd_wq_cdev(wq)) + idxd_wq_del_cdev(wq); + + if (idxd_wq_refcount(wq)) + dev_warn(dev, "Clients has claim on wq %d: %d\n", + wq->id, idxd_wq_refcount(wq)); + + idxd_wq_unmap_portal(wq); + + idxd_wq_drain(wq); + idxd_wq_reset(wq); + + idxd_wq_free_resources(wq); + wq->client_count = 0; + mutex_unlock(&wq->wq_lock); + + dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev)); +} + +static int idxd_config_bus_remove(struct device *dev) +{ + int rc; + + dev_dbg(dev, "%s called for %s\n", __func__, dev_name(dev)); + + /* disable workqueue here */ + if (is_idxd_wq_dev(dev)) { + struct idxd_wq *wq = confdev_to_wq(dev); + + disable_wq(wq); + } else if (is_idxd_dev(dev)) { + struct idxd_device *idxd = confdev_to_idxd(dev); + int i; + + dev_dbg(dev, "%s removing dev %s\n", __func__, + dev_name(&idxd->conf_dev)); + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + if (wq->state == IDXD_WQ_DISABLED) + continue; + dev_warn(dev, "Active wq %d on disable %s.\n", i, + dev_name(&idxd->conf_dev)); + device_release_driver(&wq->conf_dev); + } + + idxd_unregister_dma_device(idxd); + rc = idxd_device_disable(idxd); + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + mutex_lock(&wq->wq_lock); + idxd_wq_disable_cleanup(wq); + mutex_unlock(&wq->wq_lock); + } + module_put(THIS_MODULE); + if (rc < 0) + dev_warn(dev, "Device disable failed\n"); + else + dev_info(dev, "Device %s disabled\n", dev_name(dev)); + + } + + return 0; +} + +static void idxd_config_bus_shutdown(struct device *dev) +{ + dev_dbg(dev, "%s called\n", __func__); +} + +struct bus_type dsa_bus_type = { + .name = "dsa", + .match = idxd_config_bus_match, + .probe = idxd_config_bus_probe, + .remove = idxd_config_bus_remove, + .shutdown = idxd_config_bus_shutdown, +}; + +static struct bus_type *idxd_bus_types[] = { + &dsa_bus_type +}; + +static struct idxd_device_driver dsa_drv = { + .drv = { + .name = "dsa", + .bus = &dsa_bus_type, + .owner = THIS_MODULE, + .mod_name = KBUILD_MODNAME, + }, +}; + +static struct idxd_device_driver *idxd_drvs[] = { + &dsa_drv +}; + +struct bus_type *idxd_get_bus_type(struct idxd_device *idxd) +{ + return idxd_bus_types[idxd->type]; +} + +static struct device_type *idxd_get_device_type(struct idxd_device *idxd) +{ + if (idxd->type == IDXD_TYPE_DSA) + return &dsa_device_type; + else + return NULL; +} + +/* IDXD generic driver setup */ +int idxd_register_driver(void) +{ + int i, rc; + + for (i = 0; i < IDXD_TYPE_MAX; i++) { + rc = driver_register(&idxd_drvs[i]->drv); + if (rc < 0) + goto drv_fail; + } + + return 0; + +drv_fail: + while (--i >= 0) + driver_unregister(&idxd_drvs[i]->drv); + return rc; +} + +void idxd_unregister_driver(void) +{ + int i; + + for (i = 0; i < IDXD_TYPE_MAX; i++) + driver_unregister(&idxd_drvs[i]->drv); +} + +/* IDXD engine attributes */ +static ssize_t engine_group_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_engine *engine = + container_of(dev, struct idxd_engine, conf_dev); + + if (engine->group) + return sprintf(buf, "%d\n", engine->group->id); + else + return sprintf(buf, "%d\n", -1); +} + +static ssize_t engine_group_id_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_engine *engine = + container_of(dev, struct idxd_engine, conf_dev); + struct idxd_device *idxd = engine->idxd; + long id; + int rc; + struct idxd_group *prevg; + + rc = kstrtol(buf, 10, &id); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (id > idxd->max_groups - 1 || id < -1) + return -EINVAL; + + if (id == -1) { + if (engine->group) { + engine->group->num_engines--; + engine->group = NULL; + } + return count; + } + + prevg = engine->group; + + if (prevg) + prevg->num_engines--; + engine->group = &idxd->groups[id]; + engine->group->num_engines++; + + return count; +} + +static struct device_attribute dev_attr_engine_group = + __ATTR(group_id, 0644, engine_group_id_show, + engine_group_id_store); + +static struct attribute *idxd_engine_attributes[] = { + &dev_attr_engine_group.attr, + NULL, +}; + +static const struct attribute_group idxd_engine_attribute_group = { + .attrs = idxd_engine_attributes, +}; + +static const struct attribute_group *idxd_engine_attribute_groups[] = { + &idxd_engine_attribute_group, + NULL, +}; + +/* Group attributes */ + +static void idxd_set_free_tokens(struct idxd_device *idxd) +{ + int i, tokens; + + for (i = 0, tokens = 0; i < idxd->max_groups; i++) { + struct idxd_group *g = &idxd->groups[i]; + + tokens += g->tokens_reserved; + } + + idxd->nr_tokens = idxd->max_tokens - tokens; +} + +static ssize_t group_tokens_reserved_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + + return sprintf(buf, "%u\n", group->tokens_reserved); +} + +static ssize_t group_tokens_reserved_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + struct idxd_device *idxd = group->idxd; + unsigned long val; + int rc; + + rc = kstrtoul(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (val > idxd->max_tokens) + return -EINVAL; + + if (val > idxd->nr_tokens + group->tokens_reserved) + return -EINVAL; + + group->tokens_reserved = val; + idxd_set_free_tokens(idxd); + return count; +} + +static struct device_attribute dev_attr_group_tokens_reserved = + __ATTR(tokens_reserved, 0644, group_tokens_reserved_show, + group_tokens_reserved_store); + +static ssize_t group_tokens_allowed_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + + return sprintf(buf, "%u\n", group->tokens_allowed); +} + +static ssize_t group_tokens_allowed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + struct idxd_device *idxd = group->idxd; + unsigned long val; + int rc; + + rc = kstrtoul(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (val < 4 * group->num_engines || + val > group->tokens_reserved + idxd->nr_tokens) + return -EINVAL; + + group->tokens_allowed = val; + return count; +} + +static struct device_attribute dev_attr_group_tokens_allowed = + __ATTR(tokens_allowed, 0644, group_tokens_allowed_show, + group_tokens_allowed_store); + +static ssize_t group_use_token_limit_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + + return sprintf(buf, "%u\n", group->use_token_limit); +} + +static ssize_t group_use_token_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + struct idxd_device *idxd = group->idxd; + unsigned long val; + int rc; + + rc = kstrtoul(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (idxd->token_limit == 0) + return -EPERM; + + group->use_token_limit = !!val; + return count; +} + +static struct device_attribute dev_attr_group_use_token_limit = + __ATTR(use_token_limit, 0644, group_use_token_limit_show, + group_use_token_limit_store); + +static ssize_t group_engines_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + int i, rc = 0; + char *tmp = buf; + struct idxd_device *idxd = group->idxd; + + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *engine = &idxd->engines[i]; + + if (!engine->group) + continue; + + if (engine->group->id == group->id) + rc += sprintf(tmp + rc, "engine%d.%d ", + idxd->id, engine->id); + } + + rc--; + rc += sprintf(tmp + rc, "\n"); + + return rc; +} + +static struct device_attribute dev_attr_group_engines = + __ATTR(engines, 0444, group_engines_show, NULL); + +static ssize_t group_work_queues_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + int i, rc = 0; + char *tmp = buf; + struct idxd_device *idxd = group->idxd; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + if (!wq->group) + continue; + + if (wq->group->id == group->id) + rc += sprintf(tmp + rc, "wq%d.%d ", + idxd->id, wq->id); + } + + rc--; + rc += sprintf(tmp + rc, "\n"); + + return rc; +} + +static struct device_attribute dev_attr_group_work_queues = + __ATTR(work_queues, 0444, group_work_queues_show, NULL); + +static ssize_t group_traffic_class_a_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + + return sprintf(buf, "%d\n", group->tc_a); +} + +static ssize_t group_traffic_class_a_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + struct idxd_device *idxd = group->idxd; + long val; + int rc; + + rc = kstrtol(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (val < 0 || val > 7) + return -EINVAL; + + group->tc_a = val; + return count; +} + +static struct device_attribute dev_attr_group_traffic_class_a = + __ATTR(traffic_class_a, 0644, group_traffic_class_a_show, + group_traffic_class_a_store); + +static ssize_t group_traffic_class_b_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + + return sprintf(buf, "%d\n", group->tc_b); +} + +static ssize_t group_traffic_class_b_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_group *group = + container_of(dev, struct idxd_group, conf_dev); + struct idxd_device *idxd = group->idxd; + long val; + int rc; + + rc = kstrtol(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (val < 0 || val > 7) + return -EINVAL; + + group->tc_b = val; + return count; +} + +static struct device_attribute dev_attr_group_traffic_class_b = + __ATTR(traffic_class_b, 0644, group_traffic_class_b_show, + group_traffic_class_b_store); + +static struct attribute *idxd_group_attributes[] = { + &dev_attr_group_work_queues.attr, + &dev_attr_group_engines.attr, + &dev_attr_group_use_token_limit.attr, + &dev_attr_group_tokens_allowed.attr, + &dev_attr_group_tokens_reserved.attr, + &dev_attr_group_traffic_class_a.attr, + &dev_attr_group_traffic_class_b.attr, + NULL, +}; + +static const struct attribute_group idxd_group_attribute_group = { + .attrs = idxd_group_attributes, +}; + +static const struct attribute_group *idxd_group_attribute_groups[] = { + &idxd_group_attribute_group, + NULL, +}; + +/* IDXD work queue attribs */ +static ssize_t wq_clients_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%d\n", wq->client_count); +} + +static struct device_attribute dev_attr_wq_clients = + __ATTR(clients, 0444, wq_clients_show, NULL); + +static ssize_t wq_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + switch (wq->state) { + case IDXD_WQ_DISABLED: + return sprintf(buf, "disabled\n"); + case IDXD_WQ_ENABLED: + return sprintf(buf, "enabled\n"); + } + + return sprintf(buf, "unknown\n"); +} + +static struct device_attribute dev_attr_wq_state = + __ATTR(state, 0444, wq_state_show, NULL); + +static ssize_t wq_group_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + if (wq->group) + return sprintf(buf, "%u\n", wq->group->id); + else + return sprintf(buf, "-1\n"); +} + +static ssize_t wq_group_id_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + struct idxd_device *idxd = wq->idxd; + long id; + int rc; + struct idxd_group *prevg, *group; + + rc = kstrtol(buf, 10, &id); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + if (id > idxd->max_groups - 1 || id < -1) + return -EINVAL; + + if (id == -1) { + if (wq->group) { + wq->group->num_wqs--; + wq->group = NULL; + } + return count; + } + + group = &idxd->groups[id]; + prevg = wq->group; + + if (prevg) + prevg->num_wqs--; + wq->group = group; + group->num_wqs++; + return count; +} + +static struct device_attribute dev_attr_wq_group_id = + __ATTR(group_id, 0644, wq_group_id_show, wq_group_id_store); + +static ssize_t wq_mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%s\n", + wq_dedicated(wq) ? "dedicated" : "shared"); +} + +static ssize_t wq_mode_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + struct idxd_device *idxd = wq->idxd; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + if (sysfs_streq(buf, "dedicated")) { + set_bit(WQ_FLAG_DEDICATED, &wq->flags); + wq->threshold = 0; + } else { + return -EINVAL; + } + + return count; +} + +static struct device_attribute dev_attr_wq_mode = + __ATTR(mode, 0644, wq_mode_show, wq_mode_store); + +static ssize_t wq_size_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%u\n", wq->size); +} + +static int total_claimed_wq_size(struct idxd_device *idxd) +{ + int i; + int wq_size = 0; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + wq_size += wq->size; + } + + return wq_size; +} + +static ssize_t wq_size_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + unsigned long size; + struct idxd_device *idxd = wq->idxd; + int rc; + + rc = kstrtoul(buf, 10, &size); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size) + return -EINVAL; + + wq->size = size; + return count; +} + +static struct device_attribute dev_attr_wq_size = + __ATTR(size, 0644, wq_size_show, wq_size_store); + +static ssize_t wq_priority_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%u\n", wq->priority); +} + +static ssize_t wq_priority_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + unsigned long prio; + struct idxd_device *idxd = wq->idxd; + int rc; + + rc = kstrtoul(buf, 10, &prio); + if (rc < 0) + return -EINVAL; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + if (prio > IDXD_MAX_PRIORITY) + return -EINVAL; + + wq->priority = prio; + return count; +} + +static struct device_attribute dev_attr_wq_priority = + __ATTR(priority, 0644, wq_priority_show, wq_priority_store); + +static ssize_t wq_type_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + switch (wq->type) { + case IDXD_WQT_KERNEL: + return sprintf(buf, "%s\n", + idxd_wq_type_names[IDXD_WQT_KERNEL]); + case IDXD_WQT_USER: + return sprintf(buf, "%s\n", + idxd_wq_type_names[IDXD_WQT_USER]); + case IDXD_WQT_NONE: + default: + return sprintf(buf, "%s\n", + idxd_wq_type_names[IDXD_WQT_NONE]); + } + + return -EINVAL; +} + +static ssize_t wq_type_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + enum idxd_wq_type old_type; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + old_type = wq->type; + if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_NONE])) + wq->type = IDXD_WQT_NONE; + else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_KERNEL])) + wq->type = IDXD_WQT_KERNEL; + else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_USER])) + wq->type = IDXD_WQT_USER; + else + return -EINVAL; + + /* If we are changing queue type, clear the name */ + if (wq->type != old_type) + memset(wq->name, 0, WQ_NAME_SIZE + 1); + + return count; +} + +static struct device_attribute dev_attr_wq_type = + __ATTR(type, 0644, wq_type_show, wq_type_store); + +static ssize_t wq_name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%s\n", wq->name); +} + +static ssize_t wq_name_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) == 0) + return -EINVAL; + + memset(wq->name, 0, WQ_NAME_SIZE + 1); + strncpy(wq->name, buf, WQ_NAME_SIZE); + strreplace(wq->name, '\n', '\0'); + return count; +} + +static struct device_attribute dev_attr_wq_name = + __ATTR(name, 0644, wq_name_show, wq_name_store); + +static ssize_t wq_cdev_minor_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + int minor = -1; + + mutex_lock(&wq->wq_lock); + if (wq->idxd_cdev) + minor = wq->idxd_cdev->minor; + mutex_unlock(&wq->wq_lock); + + if (minor == -1) + return -ENXIO; + return sysfs_emit(buf, "%d\n", minor); +} + +static struct device_attribute dev_attr_wq_cdev_minor = + __ATTR(cdev_minor, 0444, wq_cdev_minor_show, NULL); + +static int __get_sysfs_u64(const char *buf, u64 *val) +{ + int rc; + + rc = kstrtou64(buf, 0, val); + if (rc < 0) + return -EINVAL; + + if (*val == 0) + return -EINVAL; + + *val = roundup_pow_of_two(*val); + return 0; +} + +static ssize_t wq_max_transfer_size_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%llu\n", wq->max_xfer_bytes); +} + +static ssize_t wq_max_transfer_size_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + struct idxd_device *idxd = wq->idxd; + u64 xfer_size; + int rc; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + rc = __get_sysfs_u64(buf, &xfer_size); + if (rc < 0) + return rc; + + if (xfer_size > idxd->max_xfer_bytes) + return -EINVAL; + + wq->max_xfer_bytes = xfer_size; + + return count; +} + +static struct device_attribute dev_attr_wq_max_transfer_size = + __ATTR(max_transfer_size, 0644, + wq_max_transfer_size_show, wq_max_transfer_size_store); + +static ssize_t wq_max_batch_size_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + + return sprintf(buf, "%u\n", wq->max_batch_size); +} + +static ssize_t wq_max_batch_size_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev); + struct idxd_device *idxd = wq->idxd; + u64 batch_size; + int rc; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + rc = __get_sysfs_u64(buf, &batch_size); + if (rc < 0) + return rc; + + if (batch_size > idxd->max_batch_size) + return -EINVAL; + + wq->max_batch_size = (u32)batch_size; + + return count; +} + +static struct device_attribute dev_attr_wq_max_batch_size = + __ATTR(max_batch_size, 0644, wq_max_batch_size_show, wq_max_batch_size_store); + +static struct attribute *idxd_wq_attributes[] = { + &dev_attr_wq_clients.attr, + &dev_attr_wq_state.attr, + &dev_attr_wq_group_id.attr, + &dev_attr_wq_mode.attr, + &dev_attr_wq_size.attr, + &dev_attr_wq_priority.attr, + &dev_attr_wq_type.attr, + &dev_attr_wq_name.attr, + &dev_attr_wq_cdev_minor.attr, + &dev_attr_wq_max_transfer_size.attr, + &dev_attr_wq_max_batch_size.attr, + NULL, +}; + +static const struct attribute_group idxd_wq_attribute_group = { + .attrs = idxd_wq_attributes, +}; + +static const struct attribute_group *idxd_wq_attribute_groups[] = { + &idxd_wq_attribute_group, + NULL, +}; + +/* IDXD device attribs */ +static ssize_t version_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%#x\n", idxd->hw.version); +} +static DEVICE_ATTR_RO(version); + +static ssize_t max_work_queues_size_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->max_wq_size); +} +static DEVICE_ATTR_RO(max_work_queues_size); + +static ssize_t max_groups_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->max_groups); +} +static DEVICE_ATTR_RO(max_groups); + +static ssize_t max_work_queues_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->max_wqs); +} +static DEVICE_ATTR_RO(max_work_queues); + +static ssize_t max_engines_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->max_engines); +} +static DEVICE_ATTR_RO(max_engines); + +static ssize_t numa_node_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%d\n", dev_to_node(&idxd->pdev->dev)); +} +static DEVICE_ATTR_RO(numa_node); + +static ssize_t max_batch_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->max_batch_size); +} +static DEVICE_ATTR_RO(max_batch_size); + +static ssize_t max_transfer_size_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%llu\n", idxd->max_xfer_bytes); +} +static DEVICE_ATTR_RO(max_transfer_size); + +static ssize_t op_cap_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + int i, rc = 0; + + for (i = 0; i < 4; i++) + rc += sysfs_emit_at(buf, rc, "%#llx ", idxd->hw.opcap.bits[i]); + + rc--; + rc += sysfs_emit_at(buf, rc, "\n"); + return rc; +} +static DEVICE_ATTR_RO(op_cap); + +static ssize_t gen_cap_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%#llx\n", idxd->hw.gen_cap.bits); +} +static DEVICE_ATTR_RO(gen_cap); + +static ssize_t configurable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", + test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)); +} +static DEVICE_ATTR_RO(configurable); + +static ssize_t clients_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + unsigned long flags; + int count = 0, i; + + spin_lock_irqsave(&idxd->dev_lock, flags); + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + count += wq->client_count; + } + spin_unlock_irqrestore(&idxd->dev_lock, flags); + + return sprintf(buf, "%d\n", count); +} +static DEVICE_ATTR_RO(clients); + +static ssize_t state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + switch (idxd->state) { + case IDXD_DEV_DISABLED: + case IDXD_DEV_CONF_READY: + return sprintf(buf, "disabled\n"); + case IDXD_DEV_ENABLED: + return sprintf(buf, "enabled\n"); + case IDXD_DEV_HALTED: + return sprintf(buf, "halted\n"); + } + + return sprintf(buf, "unknown\n"); +} +static DEVICE_ATTR_RO(state); + +static ssize_t errors_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + int i, out = 0; + unsigned long flags; + + spin_lock_irqsave(&idxd->dev_lock, flags); + for (i = 0; i < 4; i++) + out += sprintf(buf + out, "%#018llx ", idxd->sw_err.bits[i]); + spin_unlock_irqrestore(&idxd->dev_lock, flags); + out--; + out += sprintf(buf + out, "\n"); + return out; +} +static DEVICE_ATTR_RO(errors); + +static ssize_t max_tokens_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->max_tokens); +} +static DEVICE_ATTR_RO(max_tokens); + +static ssize_t token_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->token_limit); +} + +static ssize_t token_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + unsigned long val; + int rc; + + rc = kstrtoul(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (!idxd->hw.group_cap.token_limit) + return -EPERM; + + if (val > idxd->hw.group_cap.total_tokens) + return -EINVAL; + + idxd->token_limit = val; + return count; +} +static DEVICE_ATTR_RW(token_limit); + +static ssize_t cdev_major_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = + container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%u\n", idxd->major); +} +static DEVICE_ATTR_RO(cdev_major); + +static ssize_t cmd_status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = container_of(dev, struct idxd_device, conf_dev); + + return sprintf(buf, "%#x\n", idxd->cmd_status); +} +static DEVICE_ATTR_RO(cmd_status); + +static struct attribute *idxd_device_attributes[] = { + &dev_attr_version.attr, + &dev_attr_max_groups.attr, + &dev_attr_max_work_queues.attr, + &dev_attr_max_work_queues_size.attr, + &dev_attr_max_engines.attr, + &dev_attr_numa_node.attr, + &dev_attr_max_batch_size.attr, + &dev_attr_max_transfer_size.attr, + &dev_attr_op_cap.attr, + &dev_attr_gen_cap.attr, + &dev_attr_configurable.attr, + &dev_attr_clients.attr, + &dev_attr_state.attr, + &dev_attr_errors.attr, + &dev_attr_max_tokens.attr, + &dev_attr_token_limit.attr, + &dev_attr_cdev_major.attr, + &dev_attr_cmd_status.attr, + NULL, +}; + +static const struct attribute_group idxd_device_attribute_group = { + .attrs = idxd_device_attributes, +}; + +static const struct attribute_group *idxd_attribute_groups[] = { + &idxd_device_attribute_group, + NULL, +}; + +static int idxd_setup_engine_sysfs(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int i, rc; + + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *engine = &idxd->engines[i]; + + engine->conf_dev.parent = &idxd->conf_dev; + dev_set_name(&engine->conf_dev, "engine%d.%d", + idxd->id, engine->id); + engine->conf_dev.bus = idxd_get_bus_type(idxd); + engine->conf_dev.groups = idxd_engine_attribute_groups; + engine->conf_dev.type = &idxd_engine_device_type; + dev_dbg(dev, "Engine device register: %s\n", + dev_name(&engine->conf_dev)); + rc = device_register(&engine->conf_dev); + if (rc < 0) { + put_device(&engine->conf_dev); + goto cleanup; + } + } + + return 0; + +cleanup: + while (i--) { + struct idxd_engine *engine = &idxd->engines[i]; + + device_unregister(&engine->conf_dev); + } + return rc; +} + +static int idxd_setup_group_sysfs(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int i, rc; + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *group = &idxd->groups[i]; + + group->conf_dev.parent = &idxd->conf_dev; + dev_set_name(&group->conf_dev, "group%d.%d", + idxd->id, group->id); + group->conf_dev.bus = idxd_get_bus_type(idxd); + group->conf_dev.groups = idxd_group_attribute_groups; + group->conf_dev.type = &idxd_group_device_type; + dev_dbg(dev, "Group device register: %s\n", + dev_name(&group->conf_dev)); + rc = device_register(&group->conf_dev); + if (rc < 0) { + put_device(&group->conf_dev); + goto cleanup; + } + } + + return 0; + +cleanup: + while (i--) { + struct idxd_group *group = &idxd->groups[i]; + + device_unregister(&group->conf_dev); + } + return rc; +} + +static int idxd_setup_wq_sysfs(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int i, rc; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + wq->conf_dev.parent = &idxd->conf_dev; + dev_set_name(&wq->conf_dev, "wq%d.%d", idxd->id, wq->id); + wq->conf_dev.bus = idxd_get_bus_type(idxd); + wq->conf_dev.groups = idxd_wq_attribute_groups; + wq->conf_dev.type = &idxd_wq_device_type; + dev_dbg(dev, "WQ device register: %s\n", + dev_name(&wq->conf_dev)); + rc = device_register(&wq->conf_dev); + if (rc < 0) { + put_device(&wq->conf_dev); + goto cleanup; + } + } + + return 0; + +cleanup: + while (i--) { + struct idxd_wq *wq = &idxd->wqs[i]; + + device_unregister(&wq->conf_dev); + } + return rc; +} + +static int idxd_setup_device_sysfs(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int rc; + char devname[IDXD_NAME_SIZE]; + + sprintf(devname, "%s%d", idxd_get_dev_name(idxd), idxd->id); + idxd->conf_dev.parent = dev; + dev_set_name(&idxd->conf_dev, "%s", devname); + idxd->conf_dev.bus = idxd_get_bus_type(idxd); + idxd->conf_dev.groups = idxd_attribute_groups; + idxd->conf_dev.type = idxd_get_device_type(idxd); + + dev_dbg(dev, "IDXD device register: %s\n", dev_name(&idxd->conf_dev)); + rc = device_register(&idxd->conf_dev); + if (rc < 0) { + put_device(&idxd->conf_dev); + return rc; + } + + return 0; +} + +int idxd_setup_sysfs(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + int rc; + + rc = idxd_setup_device_sysfs(idxd); + if (rc < 0) { + dev_dbg(dev, "Device sysfs registering failed: %d\n", rc); + return rc; + } + + rc = idxd_setup_wq_sysfs(idxd); + if (rc < 0) { + /* unregister conf dev */ + dev_dbg(dev, "Work Queue sysfs registering failed: %d\n", rc); + return rc; + } + + rc = idxd_setup_group_sysfs(idxd); + if (rc < 0) { + /* unregister conf dev */ + dev_dbg(dev, "Group sysfs registering failed: %d\n", rc); + return rc; + } + + rc = idxd_setup_engine_sysfs(idxd); + if (rc < 0) { + /* unregister conf dev */ + dev_dbg(dev, "Engine sysfs registering failed: %d\n", rc); + return rc; + } + + return 0; +} + +void idxd_cleanup_sysfs(struct idxd_device *idxd) +{ + int i; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = &idxd->wqs[i]; + + device_unregister(&wq->conf_dev); + } + + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *engine = &idxd->engines[i]; + + device_unregister(&engine->conf_dev); + } + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *group = &idxd->groups[i]; + + device_unregister(&group->conf_dev); + } + + device_unregister(&idxd->conf_dev); +} + +int idxd_register_bus_type(void) +{ + int i, rc; + + for (i = 0; i < IDXD_TYPE_MAX; i++) { + rc = bus_register(idxd_bus_types[i]); + if (rc < 0) + goto bus_err; + } + + return 0; + +bus_err: + while (--i >= 0) + bus_unregister(idxd_bus_types[i]); + return rc; +} + +void idxd_unregister_bus_type(void) +{ + int i; + + for (i = 0; i < IDXD_TYPE_MAX; i++) + bus_unregister(idxd_bus_types[i]); +} |