From 015d239ac0142ad0e26567fd890ef8d171f13709 Mon Sep 17 00:00:00 2001 From: Kenneth Lee Date: Tue, 11 Feb 2020 15:54:23 +0800 Subject: uacce: add uacce driver Uacce (Unified/User-space-access-intended Accelerator Framework) targets to provide Shared Virtual Addressing (SVA) between accelerators and processes. So accelerator can access any data structure of the main cpu. This differs from the data sharing between cpu and io device, which share only data content rather than address. Since unified address, hardware and user space of process can share the same virtual address in the communication. Uacce create a chrdev for every registration, the queue is allocated to the process when the chrdev is opened. Then the process can access the hardware resource by interact with the queue file. By mmap the queue file space to user space, the process can directly put requests to the hardware without syscall to the kernel space. The IOMMU core only tracks mm<->device bonds at the moment, because it only needs to handle IOTLB invalidation and PASID table entries. However uacce needs a finer granularity since multiple queues from the same device can be bound to an mm. When the mm exits, all bound queues must be stopped so that the IOMMU can safely clear the PASID table entry and reallocate the PASID. An intermediate struct uacce_mm links uacce devices and queues. Note that an mm may be bound to multiple devices but an uacce_mm structure only ever belongs to a single device, because we don't need anything more complex (if multiple devices are bound to one mm, then we'll create one uacce_mm for each bond). uacce_device --+-- uacce_mm --+-- uacce_queue | '-- uacce_queue | '-- uacce_mm --+-- uacce_queue +-- uacce_queue '-- uacce_queue Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jonathan Cameron Signed-off-by: Kenneth Lee Signed-off-by: Zaibo Xu Signed-off-by: Zhou Wang Signed-off-by: Jean-Philippe Brucker Signed-off-by: Zhangfei Gao Signed-off-by: Herbert Xu --- include/uapi/misc/uacce/uacce.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/uapi/misc/uacce/uacce.h (limited to 'include/uapi') diff --git a/include/uapi/misc/uacce/uacce.h b/include/uapi/misc/uacce/uacce.h new file mode 100644 index 000000000000..cc7185678f47 --- /dev/null +++ b/include/uapi/misc/uacce/uacce.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _UAPIUUACCE_H +#define _UAPIUUACCE_H + +#include +#include + +/* + * UACCE_CMD_START_Q: Start queue + */ +#define UACCE_CMD_START_Q _IO('W', 0) + +/* + * UACCE_CMD_PUT_Q: + * User actively stop queue and free queue resource immediately + * Optimization method since close fd may delay + */ +#define UACCE_CMD_PUT_Q _IO('W', 1) + +/* + * UACCE Device flags: + * UACCE_DEV_SVA: Shared Virtual Addresses + * Support PASID + * Support device page faults (PCI PRI or SMMU Stall) + */ +#define UACCE_DEV_SVA BIT(0) + +/** + * enum uacce_qfrt: queue file region type + * @UACCE_QFRT_MMIO: device mmio region + * @UACCE_QFRT_DUS: device user share region + */ +enum uacce_qfrt { + UACCE_QFRT_MMIO = 0, + UACCE_QFRT_DUS = 1, +}; + +#endif -- cgit v1.2.3 From 9e00df7156e45e42c695ffc596b4bf1328d00516 Mon Sep 17 00:00:00 2001 From: Zhangfei Gao Date: Tue, 11 Feb 2020 15:54:25 +0800 Subject: crypto: hisilicon - register zip engine to uacce Register qm to uacce framework for user crypto driver Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jonathan Cameron Signed-off-by: Zhangfei Gao Signed-off-by: Zhou Wang Signed-off-by: Herbert Xu --- drivers/crypto/hisilicon/qm.c | 239 +++++++++++++++++++++++++++++++- drivers/crypto/hisilicon/qm.h | 11 ++ drivers/crypto/hisilicon/zip/zip_main.c | 18 ++- include/uapi/misc/uacce/hisi_qm.h | 23 +++ 4 files changed, 283 insertions(+), 8 deletions(-) create mode 100644 include/uapi/misc/uacce/hisi_qm.h (limited to 'include/uapi') diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 79f84dc63a43..ad7146a0c577 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -9,6 +9,9 @@ #include #include #include +#include +#include +#include #include "qm.h" /* eq/aeq irq enable */ @@ -466,9 +469,14 @@ static void qm_cq_head_update(struct hisi_qp *qp) static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm) { - struct qm_cqe *cqe = qp->cqe + qp->qp_status.cq_head; + if (qp->event_cb) { + qp->event_cb(qp); + return; + } if (qp->req_cb) { + struct qm_cqe *cqe = qp->cqe + qp->qp_status.cq_head; + while (QM_CQE_PHASE(cqe) == qp->qp_status.cqc_phase) { dma_rmb(); qp->req_cb(qp, qp->sqe + qm->sqe_size * @@ -1273,7 +1281,7 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid) * @qp: The qp we want to start to run. * @arg: Accelerator specific argument. * - * After this function, qp can receive request from user. Return qp_id if + * After this function, qp can receive request from user. Return 0 if * successful, Return -EBUSY if failed. */ int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg) @@ -1318,7 +1326,7 @@ int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg) dev_dbg(dev, "queue %d started\n", qp_id); - return qp_id; + return 0; } EXPORT_SYMBOL_GPL(hisi_qm_start_qp); @@ -1399,6 +1407,214 @@ static void hisi_qm_cache_wb(struct hisi_qm *qm) } } +static void qm_qp_event_notifier(struct hisi_qp *qp) +{ + wake_up_interruptible(&qp->uacce_q->wait); +} + +static int hisi_qm_get_available_instances(struct uacce_device *uacce) +{ + int i, ret; + struct hisi_qm *qm = uacce->priv; + + read_lock(&qm->qps_lock); + for (i = 0, ret = 0; i < qm->qp_num; i++) + if (!qm->qp_array[i]) + ret++; + read_unlock(&qm->qps_lock); + + return ret; +} + +static int hisi_qm_uacce_get_queue(struct uacce_device *uacce, + unsigned long arg, + struct uacce_queue *q) +{ + struct hisi_qm *qm = uacce->priv; + struct hisi_qp *qp; + u8 alg_type = 0; + + qp = hisi_qm_create_qp(qm, alg_type); + if (IS_ERR(qp)) + return PTR_ERR(qp); + + q->priv = qp; + q->uacce = uacce; + qp->uacce_q = q; + qp->event_cb = qm_qp_event_notifier; + qp->pasid = arg; + + return 0; +} + +static void hisi_qm_uacce_put_queue(struct uacce_queue *q) +{ + struct hisi_qp *qp = q->priv; + + hisi_qm_cache_wb(qp->qm); + hisi_qm_release_qp(qp); +} + +/* map sq/cq/doorbell to user space */ +static int hisi_qm_uacce_mmap(struct uacce_queue *q, + struct vm_area_struct *vma, + struct uacce_qfile_region *qfr) +{ + struct hisi_qp *qp = q->priv; + struct hisi_qm *qm = qp->qm; + size_t sz = vma->vm_end - vma->vm_start; + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + unsigned long vm_pgoff; + int ret; + + switch (qfr->type) { + case UACCE_QFRT_MMIO: + if (qm->ver == QM_HW_V2) { + if (sz > PAGE_SIZE * (QM_DOORBELL_PAGE_NR + + QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE)) + return -EINVAL; + } else { + if (sz > PAGE_SIZE * QM_DOORBELL_PAGE_NR) + return -EINVAL; + } + + vma->vm_flags |= VM_IO; + + return remap_pfn_range(vma, vma->vm_start, + qm->phys_base >> PAGE_SHIFT, + sz, pgprot_noncached(vma->vm_page_prot)); + case UACCE_QFRT_DUS: + if (sz != qp->qdma.size) + return -EINVAL; + + /* + * dma_mmap_coherent() requires vm_pgoff as 0 + * restore vm_pfoff to initial value for mmap() + */ + vm_pgoff = vma->vm_pgoff; + vma->vm_pgoff = 0; + ret = dma_mmap_coherent(dev, vma, qp->qdma.va, + qp->qdma.dma, sz); + vma->vm_pgoff = vm_pgoff; + return ret; + + default: + return -EINVAL; + } +} + +static int hisi_qm_uacce_start_queue(struct uacce_queue *q) +{ + struct hisi_qp *qp = q->priv; + + return hisi_qm_start_qp(qp, qp->pasid); +} + +static void hisi_qm_uacce_stop_queue(struct uacce_queue *q) +{ + hisi_qm_stop_qp(q->priv); +} + +static int qm_set_sqctype(struct uacce_queue *q, u16 type) +{ + struct hisi_qm *qm = q->uacce->priv; + struct hisi_qp *qp = q->priv; + + write_lock(&qm->qps_lock); + qp->alg_type = type; + write_unlock(&qm->qps_lock); + + return 0; +} + +static long hisi_qm_uacce_ioctl(struct uacce_queue *q, unsigned int cmd, + unsigned long arg) +{ + struct hisi_qp *qp = q->priv; + struct hisi_qp_ctx qp_ctx; + + if (cmd == UACCE_CMD_QM_SET_QP_CTX) { + if (copy_from_user(&qp_ctx, (void __user *)arg, + sizeof(struct hisi_qp_ctx))) + return -EFAULT; + + if (qp_ctx.qc_type != 0 && qp_ctx.qc_type != 1) + return -EINVAL; + + qm_set_sqctype(q, qp_ctx.qc_type); + qp_ctx.id = qp->qp_id; + + if (copy_to_user((void __user *)arg, &qp_ctx, + sizeof(struct hisi_qp_ctx))) + return -EFAULT; + } else { + return -EINVAL; + } + + return 0; +} + +static const struct uacce_ops uacce_qm_ops = { + .get_available_instances = hisi_qm_get_available_instances, + .get_queue = hisi_qm_uacce_get_queue, + .put_queue = hisi_qm_uacce_put_queue, + .start_queue = hisi_qm_uacce_start_queue, + .stop_queue = hisi_qm_uacce_stop_queue, + .mmap = hisi_qm_uacce_mmap, + .ioctl = hisi_qm_uacce_ioctl, +}; + +static int qm_alloc_uacce(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct uacce_device *uacce; + unsigned long mmio_page_nr; + unsigned long dus_page_nr; + struct uacce_interface interface = { + .flags = UACCE_DEV_SVA, + .ops = &uacce_qm_ops, + }; + + strncpy(interface.name, pdev->driver->name, sizeof(interface.name)); + + uacce = uacce_alloc(&pdev->dev, &interface); + if (IS_ERR(uacce)) + return PTR_ERR(uacce); + + if (uacce->flags & UACCE_DEV_SVA) { + qm->use_sva = true; + } else { + /* only consider sva case */ + uacce_remove(uacce); + qm->uacce = NULL; + return -EINVAL; + } + + uacce->is_vf = pdev->is_virtfn; + uacce->priv = qm; + uacce->algs = qm->algs; + + if (qm->ver == QM_HW_V1) { + mmio_page_nr = QM_DOORBELL_PAGE_NR; + uacce->api_ver = HISI_QM_API_VER_BASE; + } else { + mmio_page_nr = QM_DOORBELL_PAGE_NR + + QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE; + uacce->api_ver = HISI_QM_API_VER2_BASE; + } + + dus_page_nr = (PAGE_SIZE - 1 + qm->sqe_size * QM_Q_DEPTH + + sizeof(struct qm_cqe) * QM_Q_DEPTH) >> PAGE_SHIFT; + + uacce->qf_pg_num[UACCE_QFRT_MMIO] = mmio_page_nr; + uacce->qf_pg_num[UACCE_QFRT_DUS] = dus_page_nr; + + qm->uacce = uacce; + + return 0; +} + /** * hisi_qm_get_free_qp_num() - Get free number of qp in qm. * @qm: The qm which want to get free qp. @@ -1441,10 +1657,14 @@ int hisi_qm_init(struct hisi_qm *qm) return -EINVAL; } + ret = qm_alloc_uacce(qm); + if (ret < 0) + dev_warn(&pdev->dev, "fail to alloc uacce (%d)\n", ret); + ret = pci_enable_device_mem(pdev); if (ret < 0) { dev_err(&pdev->dev, "Failed to enable device mem!\n"); - return ret; + goto err_remove_uacce; } ret = pci_request_mem_regions(pdev, qm->dev_name); @@ -1453,8 +1673,9 @@ int hisi_qm_init(struct hisi_qm *qm) goto err_disable_pcidev; } - qm->io_base = ioremap(pci_resource_start(pdev, PCI_BAR_2), - pci_resource_len(qm->pdev, PCI_BAR_2)); + qm->phys_base = pci_resource_start(pdev, PCI_BAR_2); + qm->phys_size = pci_resource_len(qm->pdev, PCI_BAR_2); + qm->io_base = ioremap(qm->phys_base, qm->phys_size); if (!qm->io_base) { ret = -EIO; goto err_release_mem_regions; @@ -1497,6 +1718,9 @@ err_release_mem_regions: pci_release_mem_regions(pdev); err_disable_pcidev: pci_disable_device(pdev); +err_remove_uacce: + uacce_remove(qm->uacce); + qm->uacce = NULL; return ret; } @@ -1513,6 +1737,9 @@ void hisi_qm_uninit(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; struct device *dev = &pdev->dev; + uacce_remove(qm->uacce); + qm->uacce = NULL; + if (qm->use_dma_api && qm->qdma.va) { hisi_qm_cache_wb(qm); dma_free_coherent(dev, qm->qdma.size, diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h index cae26eabd849..1a4f208a9448 100644 --- a/drivers/crypto/hisilicon/qm.h +++ b/drivers/crypto/hisilicon/qm.h @@ -77,6 +77,9 @@ #define HISI_ACC_SGL_SGE_NR_MAX 255 +/* page number for queue file region */ +#define QM_DOORBELL_PAGE_NR 1 + enum qp_state { QP_STOP, }; @@ -180,7 +183,12 @@ struct hisi_qm { u32 error_mask; u32 msi_mask; + const char *algs; bool use_dma_api; + bool use_sva; + resource_size_t phys_base; + resource_size_t phys_size; + struct uacce_device *uacce; }; struct hisi_qp_status { @@ -210,10 +218,13 @@ struct hisi_qp { struct hisi_qp_ops *hw_ops; void *qp_ctx; void (*req_cb)(struct hisi_qp *qp, void *data); + void (*event_cb)(struct hisi_qp *qp); struct work_struct work; struct workqueue_struct *wq; struct hisi_qm *qm; + u16 pasid; + struct uacce_queue *uacce_q; }; int hisi_qm_init(struct hisi_qm *qm); diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 868e32c2d4e5..25a311248fb8 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "zip.h" #define PCI_DEVICE_ID_ZIP_PF 0xa250 @@ -354,8 +355,14 @@ static void hisi_zip_set_user_domain_and_cache(struct hisi_zip *hisi_zip) writel(AXUSER_BASE, base + HZIP_BD_RUSER_32_63); writel(AXUSER_BASE, base + HZIP_SGL_RUSER_32_63); writel(AXUSER_BASE, base + HZIP_BD_WUSER_32_63); - writel(AXUSER_BASE, base + HZIP_DATA_RUSER_32_63); - writel(AXUSER_BASE, base + HZIP_DATA_WUSER_32_63); + + if (hisi_zip->qm.use_sva) { + writel(AXUSER_BASE | AXUSER_SSV, base + HZIP_DATA_RUSER_32_63); + writel(AXUSER_BASE | AXUSER_SSV, base + HZIP_DATA_WUSER_32_63); + } else { + writel(AXUSER_BASE, base + HZIP_DATA_RUSER_32_63); + writel(AXUSER_BASE, base + HZIP_DATA_WUSER_32_63); + } /* let's open all compression/decompression cores */ writel(DECOMP_CHECK_ENABLE | ALL_COMP_DECOMP_EN, @@ -842,6 +849,7 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) qm->pdev = pdev; qm->ver = rev_id; + qm->algs = "zlib\ngzip"; qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? QM_HW_PF : @@ -885,6 +893,12 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) hisi_zip_add_to_list(hisi_zip); + if (qm->uacce) { + ret = uacce_register(qm->uacce); + if (ret) + goto err_qm_uninit; + } + if (qm->fun_type == QM_HW_PF && vfs_num > 0) { ret = hisi_zip_sriov_enable(pdev, vfs_num); if (ret < 0) diff --git a/include/uapi/misc/uacce/hisi_qm.h b/include/uapi/misc/uacce/hisi_qm.h new file mode 100644 index 000000000000..6435f0bcb556 --- /dev/null +++ b/include/uapi/misc/uacce/hisi_qm.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _UAPI_HISI_QM_H +#define _UAPI_HISI_QM_H + +#include + +/** + * struct hisi_qp_ctx - User data for hisi qp. + * @id: qp_index return to user space + * @qc_type: Accelerator algorithm type + */ +struct hisi_qp_ctx { + __u16 id; + __u16 qc_type; +}; + +#define HISI_QM_API_VER_BASE "hisi_qm_v1" +#define HISI_QM_API_VER2_BASE "hisi_qm_v2" + +/* UACCE_CMD_QM_SET_QP_CTX: Set qp algorithm type */ +#define UACCE_CMD_QM_SET_QP_CTX _IOWR('H', 10, struct hisi_qp_ctx) + +#endif -- cgit v1.2.3