diff options
Diffstat (limited to 'drivers/infiniband/hw/efa')
| -rw-r--r-- | drivers/infiniband/hw/efa/efa.h | 13 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 29 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_com.c | 5 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_com_cmd.c | 40 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_com_cmd.h | 19 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_main.c | 17 | ||||
| -rw-r--r-- | drivers/infiniband/hw/efa/efa_verbs.c | 370 |
7 files changed, 230 insertions, 263 deletions
diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h index 2283e432693e..aa7396a1588a 100644 --- a/drivers/infiniband/hw/efa/efa.h +++ b/drivers/infiniband/hw/efa/efa.h @@ -60,8 +60,6 @@ struct efa_dev { u64 mem_bar_len; u64 db_bar_addr; u64 db_bar_len; - u8 addr[EFA_GID_SIZE]; - u32 mtu; int admin_msix_vector_idx; struct efa_irq admin_irq; @@ -71,8 +69,6 @@ struct efa_dev { struct efa_ucontext { struct ib_ucontext ibucontext; - struct xarray mmap_xa; - u32 mmap_xa_page; u16 uarn; }; @@ -91,6 +87,7 @@ struct efa_cq { struct efa_ucontext *ucontext; dma_addr_t dma_addr; void *cpu_addr; + struct rdma_user_mmap_entry *mmap_entry; size_t size; u16 cq_idx; }; @@ -101,6 +98,13 @@ struct efa_qp { void *rq_cpu_addr; size_t rq_size; enum ib_qp_state state; + + /* Used for saving mmap_xa entries */ + struct rdma_user_mmap_entry *sq_db_mmap_entry; + struct rdma_user_mmap_entry *llq_desc_mmap_entry; + struct rdma_user_mmap_entry *rq_db_mmap_entry; + struct rdma_user_mmap_entry *rq_mmap_entry; + u32 qp_handle; u32 max_send_wr; u32 max_recv_wr; @@ -147,6 +151,7 @@ int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata); void efa_dealloc_ucontext(struct ib_ucontext *ibucontext); int efa_mmap(struct ib_ucontext *ibucontext, struct vm_area_struct *vma); +void efa_mmap_free(struct rdma_user_mmap_entry *rdma_entry); int efa_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, u32 flags, diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h index 2be0469d545f..e96bcb16bd2b 100644 --- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h +++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h @@ -362,9 +362,13 @@ struct efa_admin_reg_mr_cmd { /* * permissions - * 0 : local_write_enable - Write permissions: value - * of 1 needed for RQ buffers and for RDMA write - * 7:1 : reserved1 - remote access flags, etc + * 0 : local_write_enable - Local write permissions: + * must be set for RQ buffers and buffers posted for + * RDMA Read requests + * 1 : reserved1 - MBZ + * 2 : remote_read_enable - Remote read permissions: + * must be set to enable RDMA read from the region + * 7:3 : reserved2 - MBZ */ u8 permissions; @@ -558,6 +562,16 @@ struct efa_admin_feature_device_attr_desc { /* Indicates how many bits are used virtual address access */ u8 virt_addr_width; + + /* + * 0 : rdma_read - If set, RDMA Read is supported on + * TX queues + * 31:1 : reserved - MBZ + */ + u32 device_caps; + + /* Max RDMA transfer size in bytes */ + u32 max_rdma_size; }; struct efa_admin_feature_queue_attr_desc { @@ -604,6 +618,9 @@ struct efa_admin_feature_queue_attr_desc { /* The maximum size of LLQ in bytes */ u32 max_llq_size; + + /* Maximum number of SGEs for a single RDMA read WQE */ + u16 max_wr_rdma_sges; }; struct efa_admin_feature_aenq_desc { @@ -618,6 +635,7 @@ struct efa_admin_feature_network_attr_desc { /* Raw address data in network byte order */ u8 addr[16]; + /* max packet payload size in bytes */ u32 mtu; }; @@ -780,6 +798,8 @@ struct efa_admin_mmio_req_read_less_resp { #define EFA_ADMIN_REG_MR_CMD_MEM_ADDR_PHY_MODE_EN_SHIFT 7 #define EFA_ADMIN_REG_MR_CMD_MEM_ADDR_PHY_MODE_EN_MASK BIT(7) #define EFA_ADMIN_REG_MR_CMD_LOCAL_WRITE_ENABLE_MASK BIT(0) +#define EFA_ADMIN_REG_MR_CMD_REMOTE_READ_ENABLE_SHIFT 2 +#define EFA_ADMIN_REG_MR_CMD_REMOTE_READ_ENABLE_MASK BIT(2) /* create_cq_cmd */ #define EFA_ADMIN_CREATE_CQ_CMD_INTERRUPT_MODE_ENABLED_SHIFT 5 @@ -791,4 +811,7 @@ struct efa_admin_mmio_req_read_less_resp { /* get_set_feature_common_desc */ #define EFA_ADMIN_GET_SET_FEATURE_COMMON_DESC_SELECT_MASK GENMASK(1, 0) +/* feature_device_attr_desc */ +#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK BIT(0) + #endif /* _EFA_ADMIN_CMDS_H_ */ diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c index 3c412bc5b94f..0778f4f7dccd 100644 --- a/drivers/infiniband/hw/efa/efa_com.c +++ b/drivers/infiniband/hw/efa/efa_com.c @@ -317,6 +317,7 @@ static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queu struct efa_admin_acq_entry *comp, size_t comp_size_in_bytes) { + struct efa_admin_aq_entry *aqe; struct efa_comp_ctx *comp_ctx; u16 queue_size_mask; u16 cmd_id; @@ -350,7 +351,9 @@ static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queu reinit_completion(&comp_ctx->wait_event); - memcpy(&aq->sq.entries[pi], cmd, cmd_size_in_bytes); + aqe = &aq->sq.entries[pi]; + memset(aqe, 0, sizeof(*aqe)); + memcpy(aqe, cmd, cmd_size_in_bytes); aq->sq.pc++; atomic64_inc(&aq->stats.submitted_cmd); diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c index c079f1332082..e20bd84a1014 100644 --- a/drivers/infiniband/hw/efa/efa_com_cmd.c +++ b/drivers/infiniband/hw/efa/efa_com_cmd.c @@ -230,8 +230,7 @@ int efa_com_register_mr(struct efa_com_dev *edev, mr_cmd.flags |= params->page_shift & EFA_ADMIN_REG_MR_CMD_PHYS_PAGE_SIZE_SHIFT_MASK; mr_cmd.iova = params->iova; - mr_cmd.permissions |= params->permissions & - EFA_ADMIN_REG_MR_CMD_LOCAL_WRITE_ENABLE_MASK; + mr_cmd.permissions = params->permissions; if (params->inline_pbl) { memcpy(mr_cmd.pbl.inline_pbl_array, @@ -423,28 +422,6 @@ static int efa_com_get_feature(struct efa_com_dev *edev, return efa_com_get_feature_ex(edev, get_resp, feature_id, 0, 0); } -int efa_com_get_network_attr(struct efa_com_dev *edev, - struct efa_com_get_network_attr_result *result) -{ - struct efa_admin_get_feature_resp resp; - int err; - - err = efa_com_get_feature(edev, &resp, - EFA_ADMIN_NETWORK_ATTR); - if (err) { - ibdev_err_ratelimited(edev->efa_dev, - "Failed to get network attributes %d\n", - err); - return err; - } - - memcpy(result->addr, resp.u.network_attr.addr, - sizeof(resp.u.network_attr.addr)); - result->mtu = resp.u.network_attr.mtu; - - return 0; -} - int efa_com_get_device_attr(struct efa_com_dev *edev, struct efa_com_get_device_attr_result *result) { @@ -467,6 +444,8 @@ int efa_com_get_device_attr(struct efa_com_dev *edev, result->phys_addr_width = resp.u.device_attr.phys_addr_width; result->virt_addr_width = resp.u.device_attr.virt_addr_width; result->db_bar = resp.u.device_attr.db_bar; + result->max_rdma_size = resp.u.device_attr.max_rdma_size; + result->device_caps = resp.u.device_attr.device_caps; if (result->admin_api_version < 1) { ibdev_err_ratelimited( @@ -500,6 +479,19 @@ int efa_com_get_device_attr(struct efa_com_dev *edev, result->max_ah = resp.u.queue_attr.max_ah; result->max_llq_size = resp.u.queue_attr.max_llq_size; result->sub_cqs_per_cq = resp.u.queue_attr.sub_cqs_per_cq; + result->max_wr_rdma_sge = resp.u.queue_attr.max_wr_rdma_sges; + + err = efa_com_get_feature(edev, &resp, EFA_ADMIN_NETWORK_ATTR); + if (err) { + ibdev_err_ratelimited(edev->efa_dev, + "Failed to get network attributes %d\n", + err); + return err; + } + + memcpy(result->addr, resp.u.network_attr.addr, + sizeof(resp.u.network_attr.addr)); + result->mtu = resp.u.network_attr.mtu; return 0; } diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h index 7f6c13052f49..31db5a0cbd5b 100644 --- a/drivers/infiniband/hw/efa/efa_com_cmd.h +++ b/drivers/infiniband/hw/efa/efa_com_cmd.h @@ -100,14 +100,11 @@ struct efa_com_destroy_ah_params { u16 pdn; }; -struct efa_com_get_network_attr_result { - u8 addr[EFA_GID_SIZE]; - u32 mtu; -}; - struct efa_com_get_device_attr_result { + u8 addr[EFA_GID_SIZE]; u64 page_size_cap; u64 max_mr_pages; + u32 mtu; u32 fw_version; u32 admin_api_version; u32 device_version; @@ -124,9 +121,12 @@ struct efa_com_get_device_attr_result { u32 max_pd; u32 max_ah; u32 max_llq_size; + u32 max_rdma_size; + u32 device_caps; u16 sub_cqs_per_cq; u16 max_sq_sge; u16 max_rq_sge; + u16 max_wr_rdma_sge; u8 db_bar; }; @@ -181,12 +181,7 @@ struct efa_com_reg_mr_params { * address mapping */ u8 page_shift; - /* - * permissions - * 0: local_write_enable - Write permissions: value of 1 needed - * for RQ buffers and for RDMA write:1: reserved1 - remote - * access flags, etc - */ + /* see permissions field of struct efa_admin_reg_mr_cmd */ u8 permissions; u8 inline_pbl; u8 indirect; @@ -271,8 +266,6 @@ int efa_com_create_ah(struct efa_com_dev *edev, struct efa_com_create_ah_result *result); int efa_com_destroy_ah(struct efa_com_dev *edev, struct efa_com_destroy_ah_params *params); -int efa_com_get_network_attr(struct efa_com_dev *edev, - struct efa_com_get_network_attr_result *result); int efa_com_get_device_attr(struct efa_com_dev *edev, struct efa_com_get_device_attr_result *result); int efa_com_get_hw_hints(struct efa_com_dev *edev, diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index 83858f7e83d0..faf3ff1bca2a 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -30,15 +30,6 @@ MODULE_DEVICE_TABLE(pci, efa_pci_tbl); (BIT(EFA_ADMIN_FATAL_ERROR) | BIT(EFA_ADMIN_WARNING) | \ BIT(EFA_ADMIN_NOTIFICATION) | BIT(EFA_ADMIN_KEEP_ALIVE)) -static void efa_update_network_attr(struct efa_dev *dev, - struct efa_com_get_network_attr_result *network_attr) -{ - memcpy(dev->addr, network_attr->addr, sizeof(network_attr->addr)); - dev->mtu = network_attr->mtu; - - dev_dbg(&dev->pdev->dev, "Full address %pI6\n", dev->addr); -} - /* This handler will called for unknown event group or unimplemented handlers */ static void unimplemented_aenq_handler(void *data, struct efa_admin_aenq_entry *aenq_e) @@ -217,6 +208,7 @@ static const struct ib_device_ops efa_dev_ops = { .get_link_layer = efa_port_link_layer, .get_port_immutable = efa_get_port_immutable, .mmap = efa_mmap, + .mmap_free = efa_mmap_free, .modify_qp = efa_modify_qp, .query_device = efa_query_device, .query_gid = efa_query_gid, @@ -233,7 +225,6 @@ static const struct ib_device_ops efa_dev_ops = { static int efa_ib_device_add(struct efa_dev *dev) { - struct efa_com_get_network_attr_result network_attr; struct efa_com_get_hw_hints_result hw_hints; struct pci_dev *pdev = dev->pdev; int err; @@ -249,12 +240,6 @@ static int efa_ib_device_add(struct efa_dev *dev) if (err) return err; - err = efa_com_get_network_attr(&dev->edev, &network_attr); - if (err) - goto err_release_doorbell_bar; - - efa_update_network_attr(dev, &network_attr); - err = efa_com_get_hw_hints(&dev->edev, &hw_hints); if (err) goto err_release_doorbell_bar; diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 4edae89e8e3c..c9d294caa27a 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -13,10 +13,6 @@ #include "efa.h" -#define EFA_MMAP_FLAG_SHIFT 56 -#define EFA_MMAP_PAGE_MASK GENMASK(EFA_MMAP_FLAG_SHIFT - 1, 0) -#define EFA_MMAP_INVALID U64_MAX - enum { EFA_MMAP_DMA_PAGE = 0, EFA_MMAP_IO_WC, @@ -27,20 +23,12 @@ enum { (BIT(EFA_ADMIN_FATAL_ERROR) | BIT(EFA_ADMIN_WARNING) | \ BIT(EFA_ADMIN_NOTIFICATION) | BIT(EFA_ADMIN_KEEP_ALIVE)) -struct efa_mmap_entry { - void *obj; +struct efa_user_mmap_entry { + struct rdma_user_mmap_entry rdma_entry; u64 address; - u64 length; - u32 mmap_page; u8 mmap_flag; }; -static inline u64 get_mmap_key(const struct efa_mmap_entry *efa) -{ - return ((u64)efa->mmap_flag << EFA_MMAP_FLAG_SHIFT) | - ((u64)efa->mmap_page << PAGE_SHIFT); -} - #define EFA_DEFINE_STATS(op) \ op(EFA_TX_BYTES, "tx_bytes") \ op(EFA_TX_PKTS, "tx_pkts") \ @@ -82,8 +70,6 @@ static const char *const efa_stats_names[] = { #define EFA_CHUNK_USED_SIZE \ ((EFA_PTRS_PER_CHUNK * EFA_CHUNK_PAYLOAD_PTR_SIZE) + EFA_CHUNK_PTR_SIZE) -#define EFA_SUPPORTED_ACCESS_FLAGS IB_ACCESS_LOCAL_WRITE - struct pbl_chunk { dma_addr_t dma_addr; u64 *buf; @@ -147,6 +133,17 @@ static inline struct efa_ah *to_eah(struct ib_ah *ibah) return container_of(ibah, struct efa_ah, ibah); } +static inline struct efa_user_mmap_entry * +to_emmap(struct rdma_user_mmap_entry *rdma_entry) +{ + return container_of(rdma_entry, struct efa_user_mmap_entry, rdma_entry); +} + +static inline bool is_rdma_read_cap(struct efa_dev *dev) +{ + return dev->dev_attr.device_caps & EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK; +} + #define field_avail(x, fld, sz) (offsetof(typeof(x), fld) + \ FIELD_SIZEOF(typeof(x), fld) <= (sz)) @@ -172,106 +169,6 @@ static void *efa_zalloc_mapped(struct efa_dev *dev, dma_addr_t *dma_addr, return addr; } -/* - * This is only called when the ucontext is destroyed and there can be no - * concurrent query via mmap or allocate on the xarray, thus we can be sure no - * other thread is using the entry pointer. We also know that all the BAR - * pages have either been zap'd or munmaped at this point. Normal pages are - * refcounted and will be freed at the proper time. - */ -static void mmap_entries_remove_free(struct efa_dev *dev, - struct efa_ucontext *ucontext) -{ - struct efa_mmap_entry *entry; - unsigned long mmap_page; - - xa_for_each(&ucontext->mmap_xa, mmap_page, entry) { - xa_erase(&ucontext->mmap_xa, mmap_page); - - ibdev_dbg( - &dev->ibdev, - "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n", - entry->obj, get_mmap_key(entry), entry->address, - entry->length); - if (entry->mmap_flag == EFA_MMAP_DMA_PAGE) - /* DMA mapping is already gone, now free the pages */ - free_pages_exact(phys_to_virt(entry->address), - entry->length); - kfree(entry); - } -} - -static struct efa_mmap_entry *mmap_entry_get(struct efa_dev *dev, - struct efa_ucontext *ucontext, - u64 key, u64 len) -{ - struct efa_mmap_entry *entry; - u64 mmap_page; - - mmap_page = (key & EFA_MMAP_PAGE_MASK) >> PAGE_SHIFT; - if (mmap_page > U32_MAX) - return NULL; - - entry = xa_load(&ucontext->mmap_xa, mmap_page); - if (!entry || get_mmap_key(entry) != key || entry->length != len) - return NULL; - - ibdev_dbg(&dev->ibdev, - "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n", - entry->obj, key, entry->address, entry->length); - - return entry; -} - -/* - * Note this locking scheme cannot support removal of entries, except during - * ucontext destruction when the core code guarentees no concurrency. - */ -static u64 mmap_entry_insert(struct efa_dev *dev, struct efa_ucontext *ucontext, - void *obj, u64 address, u64 length, u8 mmap_flag) -{ - struct efa_mmap_entry *entry; - u32 next_mmap_page; - int err; - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return EFA_MMAP_INVALID; - - entry->obj = obj; - entry->address = address; - entry->length = length; - entry->mmap_flag = mmap_flag; - - xa_lock(&ucontext->mmap_xa); - if (check_add_overflow(ucontext->mmap_xa_page, - (u32)(length >> PAGE_SHIFT), - &next_mmap_page)) - goto err_unlock; - - entry->mmap_page = ucontext->mmap_xa_page; - ucontext->mmap_xa_page = next_mmap_page; - err = __xa_insert(&ucontext->mmap_xa, entry->mmap_page, entry, - GFP_KERNEL); - if (err) - goto err_unlock; - - xa_unlock(&ucontext->mmap_xa); - - ibdev_dbg( - &dev->ibdev, - "mmap: obj[0x%p] addr[%#llx], len[%#llx], key[%#llx] inserted\n", - entry->obj, entry->address, entry->length, get_mmap_key(entry)); - - return get_mmap_key(entry); - -err_unlock: - xa_unlock(&ucontext->mmap_xa); - kfree(entry); - return EFA_MMAP_INVALID; - -} - int efa_query_device(struct ib_device *ibdev, struct ib_device_attr *props, struct ib_udata *udata) @@ -306,12 +203,17 @@ int efa_query_device(struct ib_device *ibdev, dev_attr->max_rq_depth); props->max_send_sge = dev_attr->max_sq_sge; props->max_recv_sge = dev_attr->max_rq_sge; + props->max_sge_rd = dev_attr->max_wr_rdma_sge; if (udata && udata->outlen) { resp.max_sq_sge = dev_attr->max_sq_sge; resp.max_rq_sge = dev_attr->max_rq_sge; resp.max_sq_wr = dev_attr->max_sq_depth; resp.max_rq_wr = dev_attr->max_rq_depth; + resp.max_rdma_size = dev_attr->max_rdma_size; + + if (is_rdma_read_cap(dev)) + resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_READ; err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen)); @@ -338,9 +240,9 @@ int efa_query_port(struct ib_device *ibdev, u8 port, props->pkey_tbl_len = 1; props->active_speed = IB_SPEED_EDR; props->active_width = IB_WIDTH_4X; - props->max_mtu = ib_mtu_int_to_enum(dev->mtu); - props->active_mtu = ib_mtu_int_to_enum(dev->mtu); - props->max_msg_sz = dev->mtu; + props->max_mtu = ib_mtu_int_to_enum(dev->dev_attr.mtu); + props->active_mtu = ib_mtu_int_to_enum(dev->dev_attr.mtu); + props->max_msg_sz = dev->dev_attr.mtu; props->max_vl_num = 1; return 0; @@ -401,7 +303,7 @@ int efa_query_gid(struct ib_device *ibdev, u8 port, int index, { struct efa_dev *dev = to_edev(ibdev); - memcpy(gid->raw, dev->addr, sizeof(dev->addr)); + memcpy(gid->raw, dev->dev_attr.addr, sizeof(dev->dev_attr.addr)); return 0; } @@ -485,8 +387,19 @@ static int efa_destroy_qp_handle(struct efa_dev *dev, u32 qp_handle) return efa_com_destroy_qp(&dev->edev, ¶ms); } +static void efa_qp_user_mmap_entries_remove(struct efa_ucontext *uctx, + struct efa_qp *qp) +{ + rdma_user_mmap_entry_remove(qp->rq_mmap_entry); + rdma_user_mmap_entry_remove(qp->rq_db_mmap_entry); + rdma_user_mmap_entry_remove(qp->llq_desc_mmap_entry); + rdma_user_mmap_entry_remove(qp->sq_db_mmap_entry); +} + int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) { + struct efa_ucontext *ucontext = rdma_udata_to_drv_context(udata, + struct efa_ucontext, ibucontext); struct efa_dev *dev = to_edev(ibqp->pd->device); struct efa_qp *qp = to_eqp(ibqp); int err; @@ -505,61 +418,101 @@ int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) DMA_TO_DEVICE); } + efa_qp_user_mmap_entries_remove(ucontext, qp); kfree(qp); return 0; } +static struct rdma_user_mmap_entry* +efa_user_mmap_entry_insert(struct ib_ucontext *ucontext, + u64 address, size_t length, + u8 mmap_flag, u64 *offset) +{ + struct efa_user_mmap_entry *entry = kzalloc(sizeof(*entry), GFP_KERNEL); + int err; + + if (!entry) + return NULL; + + entry->address = address; + entry->mmap_flag = mmap_flag; + + err = rdma_user_mmap_entry_insert(ucontext, &entry->rdma_entry, + length); + if (err) { + kfree(entry); + return NULL; + } + *offset = rdma_user_mmap_get_offset(&entry->rdma_entry); + + return &entry->rdma_entry; +} + static int qp_mmap_entries_setup(struct efa_qp *qp, struct efa_dev *dev, struct efa_ucontext *ucontext, struct efa_com_create_qp_params *params, struct efa_ibv_create_qp_resp *resp) { - /* - * Once an entry is inserted it might be mmapped, hence cannot be - * cleaned up until dealloc_ucontext. - */ - resp->sq_db_mmap_key = - mmap_entry_insert(dev, ucontext, qp, - dev->db_bar_addr + resp->sq_db_offset, - PAGE_SIZE, EFA_MMAP_IO_NC); - if (resp->sq_db_mmap_key == EFA_MMAP_INVALID) + size_t length; + u64 address; + + address = dev->db_bar_addr + resp->sq_db_offset; + qp->sq_db_mmap_entry = + efa_user_mmap_entry_insert(&ucontext->ibucontext, + address, + PAGE_SIZE, EFA_MMAP_IO_NC, + &resp->sq_db_mmap_key); + if (!qp->sq_db_mmap_entry) return -ENOMEM; resp->sq_db_offset &= ~PAGE_MASK; - resp->llq_desc_mmap_key = - mmap_entry_insert(dev, ucontext, qp, - dev->mem_bar_addr + resp->llq_desc_offset, - PAGE_ALIGN(params->sq_ring_size_in_bytes + - (resp->llq_desc_offset & ~PAGE_MASK)), - EFA_MMAP_IO_WC); - if (resp->llq_desc_mmap_key == EFA_MMAP_INVALID) - return -ENOMEM; + address = dev->mem_bar_addr + resp->llq_desc_offset; + length = PAGE_ALIGN(params->sq_ring_size_in_bytes + + (resp->llq_desc_offset & ~PAGE_MASK)); + + qp->llq_desc_mmap_entry = + efa_user_mmap_entry_insert(&ucontext->ibucontext, + address, length, + EFA_MMAP_IO_WC, + &resp->llq_desc_mmap_key); + if (!qp->llq_desc_mmap_entry) + goto err_remove_mmap; resp->llq_desc_offset &= ~PAGE_MASK; if (qp->rq_size) { - resp->rq_db_mmap_key = - mmap_entry_insert(dev, ucontext, qp, - dev->db_bar_addr + resp->rq_db_offset, - PAGE_SIZE, EFA_MMAP_IO_NC); - if (resp->rq_db_mmap_key == EFA_MMAP_INVALID) - return -ENOMEM; + address = dev->db_bar_addr + resp->rq_db_offset; + + qp->rq_db_mmap_entry = + efa_user_mmap_entry_insert(&ucontext->ibucontext, + address, PAGE_SIZE, + EFA_MMAP_IO_NC, + &resp->rq_db_mmap_key); + if (!qp->rq_db_mmap_entry) + goto err_remove_mmap; resp->rq_db_offset &= ~PAGE_MASK; - resp->rq_mmap_key = - mmap_entry_insert(dev, ucontext, qp, - virt_to_phys(qp->rq_cpu_addr), - qp->rq_size, EFA_MMAP_DMA_PAGE); - if (resp->rq_mmap_key == EFA_MMAP_INVALID) - return -ENOMEM; + address = virt_to_phys(qp->rq_cpu_addr); + qp->rq_mmap_entry = + efa_user_mmap_entry_insert(&ucontext->ibucontext, + address, qp->rq_size, + EFA_MMAP_DMA_PAGE, + &resp->rq_mmap_key); + if (!qp->rq_mmap_entry) + goto err_remove_mmap; resp->rq_mmap_size = qp->rq_size; } return 0; + +err_remove_mmap: + efa_qp_user_mmap_entries_remove(ucontext, qp); + + return -ENOMEM; } static int efa_qp_validate_cap(struct efa_dev *dev, @@ -634,7 +587,6 @@ struct ib_qp *efa_create_qp(struct ib_pd *ibpd, struct efa_dev *dev = to_edev(ibpd->device); struct efa_ibv_create_qp_resp resp = {}; struct efa_ibv_create_qp cmd = {}; - bool rq_entry_inserted = false; struct efa_ucontext *ucontext; struct efa_qp *qp; int err; @@ -742,7 +694,6 @@ struct ib_qp *efa_create_qp(struct ib_pd *ibpd, if (err) goto err_destroy_qp; - rq_entry_inserted = true; qp->qp_handle = create_qp_resp.qp_handle; qp->ibqp.qp_num = create_qp_resp.qp_num; qp->ibqp.qp_type = init_attr->qp_type; @@ -759,7 +710,7 @@ struct ib_qp *efa_create_qp(struct ib_pd *ibpd, ibdev_dbg(&dev->ibdev, "Failed to copy udata for qp[%u]\n", create_qp_resp.qp_num); - goto err_destroy_qp; + goto err_remove_mmap_entries; } } @@ -767,13 +718,16 @@ struct ib_qp *efa_create_qp(struct ib_pd *ibpd, return &qp->ibqp; +err_remove_mmap_entries: + efa_qp_user_mmap_entries_remove(ucontext, qp); err_destroy_qp: efa_destroy_qp_handle(dev, create_qp_resp.qp_handle); err_free_mapped: if (qp->rq_size) { dma_unmap_single(&dev->pdev->dev, qp->rq_dma_addr, qp->rq_size, DMA_TO_DEVICE); - if (!rq_entry_inserted) + + if (!qp->rq_mmap_entry) free_pages_exact(qp->rq_cpu_addr, qp->rq_size); } err_free_qp: @@ -897,16 +851,18 @@ void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) efa_destroy_cq_idx(dev, cq->cq_idx); dma_unmap_single(&dev->pdev->dev, cq->dma_addr, cq->size, DMA_FROM_DEVICE); + rdma_user_mmap_entry_remove(cq->mmap_entry); } static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq, struct efa_ibv_create_cq_resp *resp) { resp->q_mmap_size = cq->size; - resp->q_mmap_key = mmap_entry_insert(dev, cq->ucontext, cq, - virt_to_phys(cq->cpu_addr), - cq->size, EFA_MMAP_DMA_PAGE); - if (resp->q_mmap_key == EFA_MMAP_INVALID) + cq->mmap_entry = efa_user_mmap_entry_insert(&cq->ucontext->ibucontext, + virt_to_phys(cq->cpu_addr), + cq->size, EFA_MMAP_DMA_PAGE, + &resp->q_mmap_key); + if (!cq->mmap_entry) return -ENOMEM; return 0; @@ -924,7 +880,6 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct efa_dev *dev = to_edev(ibdev); struct efa_ibv_create_cq cmd = {}; struct efa_cq *cq = to_ecq(ibcq); - bool cq_entry_inserted = false; int entries = attr->cqe; int err; @@ -1013,15 +968,13 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, goto err_destroy_cq; } - cq_entry_inserted = true; - if (udata->outlen) { err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen)); if (err) { ibdev_dbg(ibdev, "Failed to copy udata for create_cq\n"); - goto err_destroy_cq; + goto err_remove_mmap; } } @@ -1030,13 +983,16 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, return 0; +err_remove_mmap: + rdma_user_mmap_entry_remove(cq->mmap_entry); err_destroy_cq: efa_destroy_cq_idx(dev, cq->cq_idx); err_free_mapped: dma_unmap_single(&dev->pdev->dev, cq->dma_addr, cq->size, DMA_FROM_DEVICE); - if (!cq_entry_inserted) + if (!cq->mmap_entry) free_pages_exact(cq->cpu_addr, cq->size); + err_out: atomic64_inc(&dev->stats.sw_stats.create_cq_err); return err; @@ -1396,6 +1352,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length, struct efa_com_reg_mr_params params = {}; struct efa_com_reg_mr_result result = {}; struct pbl_context pbl; + int supp_access_flags; unsigned int pg_sz; struct efa_mr *mr; int inline_size; @@ -1409,10 +1366,14 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length, goto err_out; } - if (access_flags & ~EFA_SUPPORTED_ACCESS_FLAGS) { + supp_access_flags = + IB_ACCESS_LOCAL_WRITE | + (is_rdma_read_cap(dev) ? IB_ACCESS_REMOTE_READ : 0); + + if (access_flags & ~supp_access_flags) { ibdev_dbg(&dev->ibdev, "Unsupported access flags[%#x], supported[%#x]\n", - access_flags, EFA_SUPPORTED_ACCESS_FLAGS); + access_flags, supp_access_flags); err = -EOPNOTSUPP; goto err_out; } @@ -1423,7 +1384,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length, goto err_out; } - mr->umem = ib_umem_get(udata, start, length, access_flags, 0); + mr->umem = ib_umem_get(udata, start, length, access_flags); if (IS_ERR(mr->umem)) { err = PTR_ERR(mr->umem); ibdev_dbg(&dev->ibdev, @@ -1434,7 +1395,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length, params.pd = to_epd(ibpd)->pdn; params.iova = virt_addr; params.mr_length_in_bytes = length; - params.permissions = access_flags & 0x1; + params.permissions = access_flags; pg_sz = ib_umem_find_best_pgsz(mr->umem, dev->dev_attr.page_size_cap, @@ -1556,7 +1517,6 @@ int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata) goto err_out; ucontext->uarn = result.uarn; - xa_init(&ucontext->mmap_xa); resp.cmds_supp_udata_mask |= EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE; resp.cmds_supp_udata_mask |= EFA_USER_CMDS_SUPP_UDATA_CREATE_AH; @@ -1585,38 +1545,56 @@ void efa_dealloc_ucontext(struct ib_ucontext *ibucontext) struct efa_ucontext *ucontext = to_eucontext(ibucontext); struct efa_dev *dev = to_edev(ibucontext->device); - mmap_entries_remove_free(dev, ucontext); efa_dealloc_uar(dev, ucontext->uarn); } +void efa_mmap_free(struct rdma_user_mmap_entry *rdma_entry) +{ + struct efa_user_mmap_entry *entry = to_emmap(rdma_entry); + + /* DMA mapping is already gone, now free the pages */ + if (entry->mmap_flag == EFA_MMAP_DMA_PAGE) + free_pages_exact(phys_to_virt(entry->address), + entry->rdma_entry.npages * PAGE_SIZE); + kfree(entry); +} + static int __efa_mmap(struct efa_dev *dev, struct efa_ucontext *ucontext, - struct vm_area_struct *vma, u64 key, u64 length) + struct vm_area_struct *vma) { - struct efa_mmap_entry *entry; + struct rdma_user_mmap_entry *rdma_entry; + struct efa_user_mmap_entry *entry; unsigned long va; + int err = 0; u64 pfn; - int err; - entry = mmap_entry_get(dev, ucontext, key, length); - if (!entry) { - ibdev_dbg(&dev->ibdev, "key[%#llx] does not have valid entry\n", - key); + rdma_entry = rdma_user_mmap_entry_get(&ucontext->ibucontext, vma); + if (!rdma_entry) { + ibdev_dbg(&dev->ibdev, + "pgoff[%#lx] does not have valid entry\n", + vma->vm_pgoff); return -EINVAL; } + entry = to_emmap(rdma_entry); ibdev_dbg(&dev->ibdev, - "Mapping address[%#llx], length[%#llx], mmap_flag[%d]\n", - entry->address, length, entry->mmap_flag); + "Mapping address[%#llx], length[%#zx], mmap_flag[%d]\n", + entry->address, rdma_entry->npages * PAGE_SIZE, + entry->mmap_flag); pfn = entry->address >> PAGE_SHIFT; switch (entry->mmap_flag) { case EFA_MMAP_IO_NC: - err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn, length, - pgprot_noncached(vma->vm_page_prot)); + err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn, + entry->rdma_entry.npages * PAGE_SIZE, + pgprot_noncached(vma->vm_page_prot), + rdma_entry); break; case EFA_MMAP_IO_WC: - err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn, length, - pgprot_writecombine(vma->vm_page_prot)); + err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn, + entry->rdma_entry.npages * PAGE_SIZE, + pgprot_writecombine(vma->vm_page_prot), + rdma_entry); break; case EFA_MMAP_DMA_PAGE: for (va = vma->vm_start; va < vma->vm_end; @@ -1633,12 +1611,13 @@ static int __efa_mmap(struct efa_dev *dev, struct efa_ucontext *ucontext, if (err) { ibdev_dbg( &dev->ibdev, - "Couldn't mmap address[%#llx] length[%#llx] mmap_flag[%d] err[%d]\n", - entry->address, length, entry->mmap_flag, err); - return err; + "Couldn't mmap address[%#llx] length[%#zx] mmap_flag[%d] err[%d]\n", + entry->address, rdma_entry->npages * PAGE_SIZE, + entry->mmap_flag, err); } - return 0; + rdma_user_mmap_entry_put(rdma_entry); + return err; } int efa_mmap(struct ib_ucontext *ibucontext, @@ -1646,26 +1625,13 @@ int efa_mmap(struct ib_ucontext *ibucontext, { struct efa_ucontext *ucontext = to_eucontext(ibucontext); struct efa_dev *dev = to_edev(ibucontext->device); - u64 length = vma->vm_end - vma->vm_start; - u64 key = vma->vm_pgoff << PAGE_SHIFT; + size_t length = vma->vm_end - vma->vm_start; ibdev_dbg(&dev->ibdev, - "start %#lx, end %#lx, length = %#llx, key = %#llx\n", - vma->vm_start, vma->vm_end, length, key); - - if (length % PAGE_SIZE != 0 || !(vma->vm_flags & VM_SHARED)) { - ibdev_dbg(&dev->ibdev, - "length[%#llx] is not page size aligned[%#lx] or VM_SHARED is not set [%#lx]\n", - length, PAGE_SIZE, vma->vm_flags); - return -EINVAL; - } - - if (vma->vm_flags & VM_EXEC) { - ibdev_dbg(&dev->ibdev, "Mapping executable pages is not permitted\n"); - return -EPERM; - } + "start %#lx, end %#lx, length = %#zx, pgoff = %#lx\n", + vma->vm_start, vma->vm_end, length, vma->vm_pgoff); - return __efa_mmap(dev, ucontext, vma, key, length); + return __efa_mmap(dev, ucontext, vma); } static int efa_ah_destroy(struct efa_dev *dev, struct efa_ah *ah) |