From eeb8461e36c99fdf2d058751be924a2aab215005 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 28 Jan 2014 13:40:15 +0200 Subject: IB: Refactor umem to use linear SG table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch refactors the IB core umem code and vendor drivers to use a linear (chained) SG table instead of chunk list. With this change the relevant code becomes clearer—no need for nested loops to build and use umem. Signed-off-by: Shachar Raindel Signed-off-by: Yishai Hadas Signed-off-by: Roland Dreier --- drivers/infiniband/core/umem.c | 120 +++++++++++++++++++---------------------- 1 file changed, 56 insertions(+), 64 deletions(-) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index a8411232207..a3a2e9c1639 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -42,29 +42,29 @@ #include "uverbs.h" -#define IB_UMEM_MAX_PAGE_CHUNK \ - ((PAGE_SIZE - offsetof(struct ib_umem_chunk, page_list)) / \ - ((void *) &((struct ib_umem_chunk *) 0)->page_list[1] - \ - (void *) &((struct ib_umem_chunk *) 0)->page_list[0])) static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty) { - struct ib_umem_chunk *chunk, *tmp; + struct scatterlist *sg; + struct page *page; int i; - list_for_each_entry_safe(chunk, tmp, &umem->chunk_list, list) { - ib_dma_unmap_sg(dev, chunk->page_list, - chunk->nents, DMA_BIDIRECTIONAL); - for (i = 0; i < chunk->nents; ++i) { - struct page *page = sg_page(&chunk->page_list[i]); + if (umem->nmap > 0) + ib_dma_unmap_sg(dev, umem->sg_head.sgl, + umem->nmap, + DMA_BIDIRECTIONAL); - if (umem->writable && dirty) - set_page_dirty_lock(page); - put_page(page); - } + for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) { - kfree(chunk); + page = sg_page(sg); + if (umem->writable && dirty) + set_page_dirty_lock(page); + put_page(page); } + + sg_free_table(&umem->sg_head); + return; + } /** @@ -81,15 +81,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, struct ib_umem *umem; struct page **page_list; struct vm_area_struct **vma_list; - struct ib_umem_chunk *chunk; unsigned long locked; unsigned long lock_limit; unsigned long cur_base; unsigned long npages; int ret; - int off; int i; DEFINE_DMA_ATTRS(attrs); + struct scatterlist *sg, *sg_list_start; + int need_release = 0; if (dmasync) dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); @@ -97,7 +97,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, if (!can_do_mlock()) return ERR_PTR(-EPERM); - umem = kmalloc(sizeof *umem, GFP_KERNEL); + umem = kzalloc(sizeof *umem, GFP_KERNEL); if (!umem) return ERR_PTR(-ENOMEM); @@ -117,8 +117,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, /* We assume the memory is from hugetlb until proved otherwise */ umem->hugetlb = 1; - INIT_LIST_HEAD(&umem->chunk_list); - page_list = (struct page **) __get_free_page(GFP_KERNEL); if (!page_list) { kfree(umem); @@ -147,7 +145,18 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, cur_base = addr & PAGE_MASK; - ret = 0; + if (npages == 0) { + ret = -EINVAL; + goto out; + } + + ret = sg_alloc_table(&umem->sg_head, npages, GFP_KERNEL); + if (ret) + goto out; + + need_release = 1; + sg_list_start = umem->sg_head.sgl; + while (npages) { ret = get_user_pages(current, current->mm, cur_base, min_t(unsigned long, npages, @@ -157,54 +166,38 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, if (ret < 0) goto out; + umem->npages += ret; cur_base += ret * PAGE_SIZE; npages -= ret; - off = 0; - - while (ret) { - chunk = kmalloc(sizeof *chunk + sizeof (struct scatterlist) * - min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK), - GFP_KERNEL); - if (!chunk) { - ret = -ENOMEM; - goto out; - } - - chunk->nents = min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK); - sg_init_table(chunk->page_list, chunk->nents); - for (i = 0; i < chunk->nents; ++i) { - if (vma_list && - !is_vm_hugetlb_page(vma_list[i + off])) - umem->hugetlb = 0; - sg_set_page(&chunk->page_list[i], page_list[i + off], PAGE_SIZE, 0); - } - - chunk->nmap = ib_dma_map_sg_attrs(context->device, - &chunk->page_list[0], - chunk->nents, - DMA_BIDIRECTIONAL, - &attrs); - if (chunk->nmap <= 0) { - for (i = 0; i < chunk->nents; ++i) - put_page(sg_page(&chunk->page_list[i])); - kfree(chunk); - - ret = -ENOMEM; - goto out; - } - - ret -= chunk->nents; - off += chunk->nents; - list_add_tail(&chunk->list, &umem->chunk_list); + for_each_sg(sg_list_start, sg, ret, i) { + if (vma_list && !is_vm_hugetlb_page(vma_list[i])) + umem->hugetlb = 0; + + sg_set_page(sg, page_list[i], PAGE_SIZE, 0); } - ret = 0; + /* preparing for next loop */ + sg_list_start = sg; } + umem->nmap = ib_dma_map_sg_attrs(context->device, + umem->sg_head.sgl, + umem->npages, + DMA_BIDIRECTIONAL, + &attrs); + + if (umem->nmap <= 0) { + ret = -ENOMEM; + goto out; + } + + ret = 0; + out: if (ret < 0) { - __ib_umem_release(context->device, umem, 0); + if (need_release) + __ib_umem_release(context->device, umem, 0); kfree(umem); } else current->mm->pinned_vm = locked; @@ -278,17 +271,16 @@ EXPORT_SYMBOL(ib_umem_release); int ib_umem_page_count(struct ib_umem *umem) { - struct ib_umem_chunk *chunk; int shift; int i; int n; + struct scatterlist *sg; shift = ilog2(umem->page_size); n = 0; - list_for_each_entry(chunk, &umem->chunk_list, list) - for (i = 0; i < chunk->nmap; ++i) - n += sg_dma_len(&chunk->page_list[i]) >> shift; + for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) + n += sg_dma_len(sg) >> shift; return n; } -- cgit v1.2.3-70-g09d2 From 17cd3a2db825506c3e3bb9548ad20f67e2f8d0e7 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Sun, 23 Feb 2014 14:19:04 +0200 Subject: IB/core: Introduce protected memory regions This commit introduces verbs for creating/destoying memory regions which will allow new types of memory key operations such as protected memory registration. Indirect memory registration is registering several (one of more) pre-registered memory regions in a specific layout. The Indirect region may potentialy describe several regions and some repitition format between them. Protected Memory registration is registering a memory region with various data integrity attributes which will describe protection schemes that will be handled by the HCA in an offloaded manner. These memory regions will be applicable for a new REG_SIG_MR work request introduced later in this patchset. In the future these routines may replace or implement current memory regions creation routines existing today: - ib_reg_user_mr - ib_alloc_fast_reg_mr - ib_get_dma_mr - ib_dereg_mr Signed-off-by: Sagi Grimberg Signed-off-by: Roland Dreier --- drivers/infiniband/core/verbs.c | 39 +++++++++++++++++++++++++++++++++++++++ include/rdma/ib_verbs.h | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3ac79511543..ca8ce7d097e 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1169,6 +1169,45 @@ int ib_dereg_mr(struct ib_mr *mr) } EXPORT_SYMBOL(ib_dereg_mr); +struct ib_mr *ib_create_mr(struct ib_pd *pd, + struct ib_mr_init_attr *mr_init_attr) +{ + struct ib_mr *mr; + + if (!pd->device->create_mr) + return ERR_PTR(-ENOSYS); + + mr = pd->device->create_mr(pd, mr_init_attr); + + if (!IS_ERR(mr)) { + mr->device = pd->device; + mr->pd = pd; + mr->uobject = NULL; + atomic_inc(&pd->usecnt); + atomic_set(&mr->usecnt, 0); + } + + return mr; +} +EXPORT_SYMBOL(ib_create_mr); + +int ib_destroy_mr(struct ib_mr *mr) +{ + struct ib_pd *pd; + int ret; + + if (atomic_read(&mr->usecnt)) + return -EBUSY; + + pd = mr->pd; + ret = mr->device->destroy_mr(mr); + if (!ret) + atomic_dec(&pd->usecnt); + + return ret; +} +EXPORT_SYMBOL(ib_destroy_mr); + struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len) { struct ib_mr *mr; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 6793f32ccb5..cb12e6a4e55 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -461,6 +461,22 @@ int ib_rate_to_mult(enum ib_rate rate) __attribute_const__; */ int ib_rate_to_mbps(enum ib_rate rate) __attribute_const__; +enum ib_mr_create_flags { + IB_MR_SIGNATURE_EN = 1, +}; + +/** + * ib_mr_init_attr - Memory region init attributes passed to routine + * ib_create_mr. + * @max_reg_descriptors: max number of registration descriptors that + * may be used with registration work requests. + * @flags: MR creation flags bit mask. + */ +struct ib_mr_init_attr { + int max_reg_descriptors; + u32 flags; +}; + /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. @@ -1407,6 +1423,9 @@ struct ib_device { int (*query_mr)(struct ib_mr *mr, struct ib_mr_attr *mr_attr); int (*dereg_mr)(struct ib_mr *mr); + int (*destroy_mr)(struct ib_mr *mr); + struct ib_mr * (*create_mr)(struct ib_pd *pd, + struct ib_mr_init_attr *mr_init_attr); struct ib_mr * (*alloc_fast_reg_mr)(struct ib_pd *pd, int max_page_list_len); struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device, @@ -2250,6 +2269,25 @@ int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr); */ int ib_dereg_mr(struct ib_mr *mr); + +/** + * ib_create_mr - Allocates a memory region that may be used for + * signature handover operations. + * @pd: The protection domain associated with the region. + * @mr_init_attr: memory region init attributes. + */ +struct ib_mr *ib_create_mr(struct ib_pd *pd, + struct ib_mr_init_attr *mr_init_attr); + +/** + * ib_destroy_mr - Destroys a memory region that was created using + * ib_create_mr and removes it from HW translation tables. + * @mr: The memory region to destroy. + * + * This function can fail, if the memory region has memory windows bound to it. + */ +int ib_destroy_mr(struct ib_mr *mr); + /** * ib_alloc_fast_reg_mr - Allocates memory region usable with the * IB_WR_FAST_REG_MR send work request. -- cgit v1.2.3-70-g09d2 From 1b01d33560e78417334c2dc673bbfac6c644424c Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Sun, 23 Feb 2014 14:19:05 +0200 Subject: IB/core: Introduce signature verbs API Introduce a verbs interface for signature-related operations. A signature handover operation configures the layouts of data and protection attributes both in memory and wire domains. Signature operations are: - INSERT: Generate and insert protection information when handing over data from input space to output space. - validate and STRIP: Validate protection information and remove it when handing over data from input space to output space. - validate and PASS: Validate protection information and pass it when handing over data from input space to output space. Once the signature handover opration is done, the HCA will offload data integrity generation/validation while performing the actual data transfer. Additions: 1. HCA signature capabilities in device attributes Verbs provider supporting signature handover operations fills relevant fields in device attributes structure returned by ib_query_device. 2. QP creation flag IB_QP_CREATE_SIGNATURE_EN Creating a QP that will carry signature handover operations may require some special preparations from the verbs provider. So we add QP creation flag IB_QP_CREATE_SIGNATURE_EN to declare that the created QP may carry out signature handover operations. Expose signature support to verbs layer (no support for now). 3. New send work request IB_WR_REG_SIG_MR Signature handover work request. This WR will define the signature handover properties of the memory/wire domains as well as the domains layout. The purpose of this work request is to bind all the needed information for the signature operation: - data to be transferred: wr->sg_list (ib_sge). * The raw data, pre-registered to a single MR (normally, before signature, this MR would have been used directly for the data transfer) - data protection guards: sig_handover.prot (ib_sge). * The data protection buffer, pre-registered to a single MR, which contains the data integrity guards of the raw data blocks. Note that it may not always exist, only in cases where the user is interested in storing protection guards in memory. - signature operation attributes: sig_handover.sig_attrs. * Tells the HCA how to validate/generate the protection information. Once the work request is executed, the memory region that will describe the signature transaction will be the sig_mr. The application can now go ahead and send the sig_mr.rkey or use the sig_mr.lkey for data transfer. 4. New Verb ib_check_mr_status check_mr_status verb checks the status of the memory region post transaction. The first check that may be used is IB_MR_CHECK_SIG_STATUS, which will indicate if any signature errors are pending for a specific signature-enabled ib_mr. This verb is a lightwight check and is allowed to be taken from interrupt context. An application must call this verb after it is known that the actual data transfer has finished. Signed-off-by: Sagi Grimberg Signed-off-by: Roland Dreier --- drivers/infiniband/core/verbs.c | 8 +++ include/rdma/ib_verbs.h | 149 +++++++++++++++++++++++++++++++++++++++- 2 files changed, 156 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index ca8ce7d097e..92525f855d8 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1437,3 +1437,11 @@ int ib_destroy_flow(struct ib_flow *flow_id) return err; } EXPORT_SYMBOL(ib_destroy_flow); + +int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, + struct ib_mr_status *mr_status) +{ + return mr->device->check_mr_status ? + mr->device->check_mr_status(mr, check_mask, mr_status) : -ENOSYS; +} +EXPORT_SYMBOL(ib_check_mr_status); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index cb12e6a4e55..82ab5c1e760 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -122,7 +122,19 @@ enum ib_device_cap_flags { IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22), IB_DEVICE_MEM_WINDOW_TYPE_2A = (1<<23), IB_DEVICE_MEM_WINDOW_TYPE_2B = (1<<24), - IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29) + IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29), + IB_DEVICE_SIGNATURE_HANDOVER = (1<<30) +}; + +enum ib_signature_prot_cap { + IB_PROT_T10DIF_TYPE_1 = 1, + IB_PROT_T10DIF_TYPE_2 = 1 << 1, + IB_PROT_T10DIF_TYPE_3 = 1 << 2, +}; + +enum ib_signature_guard_cap { + IB_GUARD_T10DIF_CRC = 1, + IB_GUARD_T10DIF_CSUM = 1 << 1, }; enum ib_atomic_cap { @@ -172,6 +184,8 @@ struct ib_device_attr { unsigned int max_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; + int sig_prot_cap; + int sig_guard_cap; }; enum ib_mtu { @@ -477,6 +491,114 @@ struct ib_mr_init_attr { u32 flags; }; +enum ib_signature_type { + IB_SIG_TYPE_T10_DIF, +}; + +/** + * T10-DIF Signature types + * T10-DIF types are defined by SCSI + * specifications. + */ +enum ib_t10_dif_type { + IB_T10DIF_NONE, + IB_T10DIF_TYPE1, + IB_T10DIF_TYPE2, + IB_T10DIF_TYPE3 +}; + +/** + * Signature T10-DIF block-guard types + * IB_T10DIF_CRC: Corresponds to T10-PI mandated CRC checksum rules. + * IB_T10DIF_CSUM: Corresponds to IP checksum rules. + */ +enum ib_t10_dif_bg_type { + IB_T10DIF_CRC, + IB_T10DIF_CSUM +}; + +/** + * struct ib_t10_dif_domain - Parameters specific for T10-DIF + * domain. + * @type: T10-DIF type (0|1|2|3) + * @bg_type: T10-DIF block guard type (CRC|CSUM) + * @pi_interval: protection information interval. + * @bg: seed of guard computation. + * @app_tag: application tag of guard block + * @ref_tag: initial guard block reference tag. + * @type3_inc_reftag: T10-DIF type 3 does not state + * about the reference tag, it is the user + * choice to increment it or not. + */ +struct ib_t10_dif_domain { + enum ib_t10_dif_type type; + enum ib_t10_dif_bg_type bg_type; + u16 pi_interval; + u16 bg; + u16 app_tag; + u32 ref_tag; + bool type3_inc_reftag; +}; + +/** + * struct ib_sig_domain - Parameters for signature domain + * @sig_type: specific signauture type + * @sig: union of all signature domain attributes that may + * be used to set domain layout. + */ +struct ib_sig_domain { + enum ib_signature_type sig_type; + union { + struct ib_t10_dif_domain dif; + } sig; +}; + +/** + * struct ib_sig_attrs - Parameters for signature handover operation + * @check_mask: bitmask for signature byte check (8 bytes) + * @mem: memory domain layout desciptor. + * @wire: wire domain layout desciptor. + */ +struct ib_sig_attrs { + u8 check_mask; + struct ib_sig_domain mem; + struct ib_sig_domain wire; +}; + +enum ib_sig_err_type { + IB_SIG_BAD_GUARD, + IB_SIG_BAD_REFTAG, + IB_SIG_BAD_APPTAG, +}; + +/** + * struct ib_sig_err - signature error descriptor + */ +struct ib_sig_err { + enum ib_sig_err_type err_type; + u32 expected; + u32 actual; + u64 sig_err_offset; + u32 key; +}; + +enum ib_mr_status_check { + IB_MR_CHECK_SIG_STATUS = 1, +}; + +/** + * struct ib_mr_status - Memory region status container + * + * @fail_status: Bitmask of MR checks status. For each + * failed check a corresponding status bit is set. + * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS + * failure. + */ +struct ib_mr_status { + u32 fail_status; + struct ib_sig_err sig_err; +}; + /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. @@ -660,6 +782,7 @@ enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = 1 << 1, IB_QP_CREATE_NETIF_QP = 1 << 5, + IB_QP_CREATE_SIGNATURE_EN = 1 << 6, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, @@ -824,6 +947,7 @@ enum ib_wr_opcode { IB_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD, IB_WR_BIND_MW, + IB_WR_REG_SIG_MR, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ @@ -929,6 +1053,12 @@ struct ib_send_wr { u32 rkey; struct ib_mw_bind_info bind_info; } bind_mw; + struct { + struct ib_sig_attrs *sig_attrs; + struct ib_mr *sig_mr; + int access_flags; + struct ib_sge *prot; + } sig_handover; } wr; u32 xrc_remote_srq_num; /* XRC TGT QPs only */ }; @@ -1474,6 +1604,8 @@ struct ib_device { *flow_attr, int domain); int (*destroy_flow)(struct ib_flow *flow_id); + int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, + struct ib_mr_status *mr_status); struct ib_dma_mapping_ops *dma_ops; @@ -2473,4 +2605,19 @@ static inline int ib_check_mr_access(int flags) return 0; } +/** + * ib_check_mr_status: lightweight check of MR status. + * This routine may provide status checks on a selected + * ib_mr. first use is for signature status check. + * + * @mr: A memory region. + * @check_mask: Bitmask of which checks to perform from + * ib_mr_status_check enumeration. + * @mr_status: The container of relevant status checks. + * failed checks will be indicated in the status bitmask + * and the relevant info shall be in the error item. + */ +int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, + struct ib_mr_status *mr_status); + #endif /* IB_VERBS_H */ -- cgit v1.2.3-70-g09d2 From 2c34e68f426151bc6d16de6a187678f6693c0770 Mon Sep 17 00:00:00 2001 From: Yan Burman Date: Tue, 11 Mar 2014 14:41:47 +0200 Subject: IB/mad: Check and handle potential DMA mapping errors Running with DMA_API_DEBUG enabled and not checking for DMA mapping errors triggers a kernel stack trace with "DMA-API: device driver failed to check map error" message. Add these checks to the MAD module, both to be be more robust and also eliminate these false-positive stack traces. Signed-off-by: Yan Burman Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/infiniband/core/mad.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 4c837e66516..ab31f136d04 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -1022,12 +1022,21 @@ int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr) mad_send_wr->send_buf.mad, sge[0].length, DMA_TO_DEVICE); + if (unlikely(ib_dma_mapping_error(mad_agent->device, sge[0].addr))) + return -ENOMEM; + mad_send_wr->header_mapping = sge[0].addr; sge[1].addr = ib_dma_map_single(mad_agent->device, ib_get_payload(mad_send_wr), sge[1].length, DMA_TO_DEVICE); + if (unlikely(ib_dma_mapping_error(mad_agent->device, sge[1].addr))) { + ib_dma_unmap_single(mad_agent->device, + mad_send_wr->header_mapping, + sge[0].length, DMA_TO_DEVICE); + return -ENOMEM; + } mad_send_wr->payload_mapping = sge[1].addr; spin_lock_irqsave(&qp_info->send_queue.lock, flags); @@ -2590,6 +2599,11 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, sizeof *mad_priv - sizeof mad_priv->header, DMA_FROM_DEVICE); + if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device, + sg_list.addr))) { + ret = -ENOMEM; + break; + } mad_priv->header.mapping = sg_list.addr; recv_wr.wr_id = (unsigned long)&mad_priv->header.mad_list; mad_priv->header.mad_list.mad_queue = recv_queue; -- cgit v1.2.3-70-g09d2 From b2853fd6c2d0f383dbdf7427e263eb576a633867 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Thu, 27 Mar 2014 10:52:58 +0200 Subject: IB/core: Don't resolve passive side RoCE L2 address in CMA REQ handler The code that resolves the passive side source MAC within the rdma_cm connection request handler was both redundant and buggy, so remove it. It was redundant since later, when an RC QP is modified to RTR state, the resolution will take place in the ib_core module. It was buggy because this callback also deals with UD SIDR exchange, for which we incorrectly looked at the REQ member of the CM event and dereferenced a random value. Fixes: dd5f03beb4f7 ("IB/core: Ethernet L2 attributes in verbs/cm structures") Signed-off-by: Moni Shoua Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/infiniband/core/cm.c | 17 ----------------- drivers/infiniband/core/cma.c | 26 -------------------------- include/rdma/ib_cm.h | 1 - 3 files changed, 44 deletions(-) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 0601b9daf84..c3239170d8b 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -349,23 +349,6 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc, grh, &av->ah_attr); } -int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac) -{ - struct cm_id_private *cm_id_priv; - - cm_id_priv = container_of(id, struct cm_id_private, id); - - if (smac != NULL) - memcpy(cm_id_priv->av.smac, smac, sizeof(cm_id_priv->av.smac)); - - if (alt_smac != NULL) - memcpy(cm_id_priv->alt_av.smac, alt_smac, - sizeof(cm_id_priv->alt_av.smac)); - - return 0; -} -EXPORT_SYMBOL(ib_update_cm_av); - static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av) { struct cm_device *cm_dev; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 199958d9ddc..42c3058e6e9 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1284,15 +1284,6 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event; int offset, ret; - u8 smac[ETH_ALEN]; - u8 alt_smac[ETH_ALEN]; - u8 *psmac = smac; - u8 *palt_smac = alt_smac; - int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) == - RDMA_TRANSPORT_IB) && - (rdma_port_get_link_layer(cm_id->device, - ib_event->param.req_rcvd.port) == - IB_LINK_LAYER_ETHERNET)); listen_id = cm_id->context; if (!cma_check_req_qp_type(&listen_id->id, ib_event)) @@ -1336,28 +1327,11 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) ret = conn_id->id.event_handler(&conn_id->id, &event); if (ret) goto err3; - - if (is_iboe) { - if (ib_event->param.req_rcvd.primary_path != NULL) - rdma_addr_find_smac_by_sgid( - &ib_event->param.req_rcvd.primary_path->sgid, - psmac, NULL); - else - psmac = NULL; - if (ib_event->param.req_rcvd.alternate_path != NULL) - rdma_addr_find_smac_by_sgid( - &ib_event->param.req_rcvd.alternate_path->sgid, - palt_smac, NULL); - else - palt_smac = NULL; - } /* * Acquire mutex to prevent user executing rdma_destroy_id() * while we're accessing the cm_id. */ mutex_lock(&lock); - if (is_iboe) - ib_update_cm_av(cm_id, psmac, palt_smac); if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD)) ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h index f29e3a27c2c..0e3ff30647d 100644 --- a/include/rdma/ib_cm.h +++ b/include/rdma/ib_cm.h @@ -601,5 +601,4 @@ struct ib_cm_sidr_rep_param { int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id, struct ib_cm_sidr_rep_param *param); -int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac); #endif /* IB_CM_H */ -- cgit v1.2.3-70-g09d2