From 78b1beb0998437107ed144b341fbe1252188916b Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 24 Sep 2017 21:46:29 +0300 Subject: IB/core: Fix typo in the name of the tag-matching cap struct The tag matching functionality is implemented by mlx5 driver by extending XRQ, however this internal kernel information was exposed to user space applications with *xrq* name instead of *tm*. This patch renames *xrq* to *tm* to handle that. Fixes: 8d50505ada72 ("IB/uverbs: Expose XRQ capabilities") Signed-off-by: Leon Romanovsky Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- drivers/infiniband/core/uverbs_cmd.c | 14 +++++++------- drivers/infiniband/hw/mlx5/main.c | 10 +++++----- include/rdma/ib_verbs.h | 4 ++-- include/uapi/rdma/ib_user_verbs.h | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 4ab30d832ac5..52a2cf2d83aa 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3869,15 +3869,15 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, resp.raw_packet_caps = attr.raw_packet_caps; resp.response_length += sizeof(resp.raw_packet_caps); - if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps)) + if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps)) goto end; - resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size; - resp.xrq_caps.max_num_tags = attr.xrq_caps.max_num_tags; - resp.xrq_caps.max_ops = attr.xrq_caps.max_ops; - resp.xrq_caps.max_sge = attr.xrq_caps.max_sge; - resp.xrq_caps.flags = attr.xrq_caps.flags; - resp.response_length += sizeof(resp.xrq_caps); + resp.tm_caps.max_rndv_hdr_size = attr.tm_caps.max_rndv_hdr_size; + resp.tm_caps.max_num_tags = attr.tm_caps.max_num_tags; + resp.tm_caps.max_ops = attr.tm_caps.max_ops; + resp.tm_caps.max_sge = attr.tm_caps.max_sge; + resp.tm_caps.flags = attr.tm_caps.flags; + resp.response_length += sizeof(resp.tm_caps); end: err = ib_copy_to_udata(ucore, &resp, resp.response_length); return err; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 05fb4bdff6a0..d6fbad8f34aa 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -778,13 +778,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, } if (MLX5_CAP_GEN(mdev, tag_matching)) { - props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; - props->xrq_caps.max_num_tags = + props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; + props->tm_caps.max_num_tags = (1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1; - props->xrq_caps.flags = IB_TM_CAP_RC; - props->xrq_caps.max_ops = + props->tm_caps.flags = IB_TM_CAP_RC; + props->tm_caps.max_ops = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz); - props->xrq_caps.max_sge = MLX5_TM_MAX_SGE; + props->tm_caps.max_sge = MLX5_TM_MAX_SGE; } if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) { diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bdb1279a415b..bbb5f54db882 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -285,7 +285,7 @@ enum ib_tm_cap_flags { IB_TM_CAP_RC = 1 << 0, }; -struct ib_xrq_caps { +struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ @@ -358,7 +358,7 @@ struct ib_device_attr { struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ - struct ib_xrq_caps xrq_caps; + struct ib_tm_caps tm_caps; }; enum ib_mtu { diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 9a0b6479fe0c..d4e0b53bfc75 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -261,7 +261,7 @@ struct ib_uverbs_ex_query_device_resp { struct ib_uverbs_rss_caps rss_caps; __u32 max_wq_type_rq; __u32 raw_packet_caps; - struct ib_uverbs_tm_caps xrq_caps; + struct ib_uverbs_tm_caps tm_caps; }; struct ib_uverbs_query_port { -- cgit From 73827a605bbd7cebef4cfd1261e497246a82a0e7 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sun, 24 Sep 2017 21:46:30 +0300 Subject: IB/core: Fix qp_sec use after free access When security_ib_alloc_security fails, qp->qp_sec memory is freed. However ib_destroy_qp still tries to access this memory which result in kernel crash. So its initialized to NULL to avoid such access. Fixes: d291f1a65232 ("IB/core: Enforce PKey security on QPs") Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/core/security.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index 70ad19c4c73e..88bdafb297f5 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -432,8 +432,10 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) atomic_set(&qp->qp_sec->error_list_count, 0); init_completion(&qp->qp_sec->error_complete); ret = security_ib_alloc_security(&qp->qp_sec->security); - if (ret) + if (ret) { kfree(qp->qp_sec); + qp->qp_sec = NULL; + } return ret; } -- cgit From edd31551148c09608feee6b8756ad148d550ee3b Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sun, 24 Sep 2017 21:46:31 +0300 Subject: IB: Correct MR length field to be 64-bit The ib_mr->length represents the length of the MR in bytes as per the IBTA spec 1.3 section 11.2.10.3 (REGISTER PHYSICAL MEMORY REGION). Currently ib_mr->length field is defined as only 32-bits field. This might result into truncation and failed WRs of consumers who registers more than 4GB bytes memory regions and whose WRs accessing such MRs. This patch makes the length 64-bit to avoid such truncation. Cc: Sagi Grimberg Cc: Chuck Lever Cc: Faisal Latif Fixes: 4c67e2bfc8b7 ("IB/core: Introduce new fast registration API") Signed-off-by: Ilya Lesokhin Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/nes/nes_verbs.c | 4 ++-- drivers/infiniband/ulp/iser/iser_memory.c | 2 +- include/rdma/ib_verbs.h | 2 +- net/sunrpc/xprtrdma/frwr_ops.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index f0dc5f4aa177..442b9bdc0f03 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3232,7 +3232,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->ibmr.iova); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX, - mr->ibmr.length); + lower_32_bits(mr->ibmr.length)); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0); set_wqe_32bit_value(wqe->wqe_words, @@ -3274,7 +3274,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->npages * 8); nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, " - "length: %d, rkey: %0x, pgl_paddr: %llx, " + "length: %lld, rkey: %0x, pgl_paddr: %llx, " "page_list_len: %u, wqe_misc: %x\n", (unsigned long long) mr->ibmr.iova, mr->ibmr.length, diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 9c3e9ab53a41..322209d5ff58 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -154,7 +154,7 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec) { int i; - iser_err("page vec npages %d data length %d\n", + iser_err("page vec npages %d data length %lld\n", page_vec->npages, page_vec->fake_mr.length); for (i = 0; i < page_vec->npages; i++) iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bbb5f54db882..e8608b2dc844 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1739,7 +1739,7 @@ struct ib_mr { u32 lkey; u32 rkey; u64 iova; - u32 length; + u64 length; unsigned int page_size; bool need_inval; union { diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 5a936a6a31a3..df062e086bdb 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -401,7 +401,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (unlikely(n != mw->mw_nents)) goto out_mapmr_err; - dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n", + dprintk("RPC: %s: Using frmr %p to map %u segments (%llu bytes)\n", __func__, frmr, mw->mw_nents, mr->length); key = (u8)(mr->rkey & 0x000000FF); -- cgit From 9c6f42e9254150d2772242d9f8bd8d0b7b7431ff Mon Sep 17 00:00:00 2001 From: Shalom Lagziel Date: Sun, 24 Sep 2017 21:46:32 +0300 Subject: IB/ipoib: Fix sysfs Pkey create<->remove possible deadlock A possible ABBA lock can happen with RTNL and vlan_rwsem. For example: Flow A: Device Flush __ipoib_ib_dev_flush down_read(vlan_rwsem) // Lock A ipoib_flush_ah flush_workqueue(priv->wq) // Wait for completion A work on shared WQ (Mcast carrier) ipoib_mcast_carrier_on_task while (!rtnl_trylock()) // Wait for lock B Flow B: Sysfs PKEY delete ipoib_vlan_delete lock(RTNL) // Lock B down_write(vlan_rwsem) // Wait for lock A This can happen with PKEY creates as well. The solution is to release the RTNL lock in sysfs functions in case it is not possible to lock VLAN RW semaphore and reset the SYS call. Fixes: 69956d83267e ("IB/ipoib: Sync between remove_one to sysfs calls that use rtnl_lock") Signed-off-by: Shalom Lagziel Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 9927cd6b7082..e01c58edca15 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -141,14 +141,17 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); - if (!priv) { + if (!down_write_trylock(&ppriv->vlan_rwsem)) { rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - return -ENOMEM; + return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); + if (!priv) { + result = -ENOMEM; + goto out; + } /* * First ensure this isn't a duplicate. We check the parent device and @@ -175,7 +178,7 @@ out: rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - if (result) { + if (result && priv) { free_netdev(priv->dev); kfree(priv); } @@ -204,7 +207,12 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + if (!down_write_trylock(&ppriv->vlan_rwsem)) { + rtnl_unlock(); + mutex_unlock(&ppriv->sysfs_mutex); + return restart_syscall(); + } + list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) { if (priv->pkey == pkey && priv->child_type == IPOIB_LEGACY_CHILD) { -- cgit From 7c9d9662103ae1c11acc7bfc47d988466cff23cf Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Sun, 24 Sep 2017 21:46:33 +0300 Subject: IB/ipoib: Fix inconsistency with free_netdev and free_rdma_netdev Call free_rdma_netdev instead of free_netdev each time we want to release a netdevice. This call is also relevant for future freeing of offloaded child interfaces. This patch also adds a missing call for free netdevice when releasing a parent interface that has child interfaces using ipoib_remove_one. Fixes: cd565b4b51e5 ('IB/IPoIB: Support acceleration options callbacks') Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 15 +++++++++++---- drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 10 ++++++++-- 2 files changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index bac95b509a9b..dcc77014018d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2180,6 +2180,7 @@ static struct net_device *ipoib_add_port(const char *format, { struct ipoib_dev_priv *priv; struct ib_port_attr attr; + struct rdma_netdev *rn; int result = -ENOMEM; priv = ipoib_intf_alloc(hca, port, format); @@ -2279,7 +2280,8 @@ register_failed: ipoib_dev_cleanup(priv->dev); device_init_failed: - free_netdev(priv->dev); + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); alloc_mem_failed: @@ -2328,7 +2330,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) return; list_for_each_entry_safe(priv, tmp, dev_list, list) { - struct rdma_netdev *rn = netdev_priv(priv->dev); + struct rdma_netdev *parent_rn = netdev_priv(priv->dev); ib_unregister_event_handler(&priv->event_handler); flush_workqueue(ipoib_workqueue); @@ -2350,10 +2352,15 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) unregister_netdev(priv->dev); mutex_unlock(&priv->sysfs_mutex); - rn->free_rdma_netdev(priv->dev); + parent_rn->free_rdma_netdev(priv->dev); + + list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) { + struct rdma_netdev *child_rn; - list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) + child_rn = netdev_priv(cpriv->dev); + child_rn->free_rdma_netdev(cpriv->dev); kfree(cpriv); + } kfree(priv); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index e01c58edca15..55a9b71ed05a 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -179,7 +179,10 @@ out: mutex_unlock(&ppriv->sysfs_mutex); if (result && priv) { - free_netdev(priv->dev); + struct rdma_netdev *rn; + + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); } @@ -232,7 +235,10 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) mutex_unlock(&ppriv->sysfs_mutex); if (dev) { - free_netdev(dev); + struct rdma_netdev *rn; + + rn = netdev_priv(dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); return 0; } -- cgit From d67bc5d4e3e100d762c0f57ea67f28bc219698a6 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Sun, 24 Sep 2017 21:46:34 +0300 Subject: IB/mlx5: Simplify mlx5_ib_cont_pages The patch simplifies mlx5_ib_cont_pages and fixes the following issues in the original implementation: First issues is related to alignment of the PFNs. After the check base + p != PFN, the alignment of the PFN wasn't checked. So the PFN sequence 0, 1, 1, 2 would result in a page_shift of 13 even though the 3rd PFN is not 8KB aligned. This wasn't actually a bug because it was supported by all the existing mlx5 compatible device, but we don't want to require this support in all future devices. Another issue is because the inner loop didn't advance PFN so the test "if (base + p != pfn)" always failed for SGE with len > (1< Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mem.c | 47 +++++++++++++++------------------------- 1 file changed, 17 insertions(+), 30 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c index 914f212e7ef6..f3dbd75a0a96 100644 --- a/drivers/infiniband/hw/mlx5/mem.c +++ b/drivers/infiniband/hw/mlx5/mem.c @@ -50,13 +50,9 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, { unsigned long tmp; unsigned long m; - int i, k; - u64 base = 0; - int p = 0; - int skip; - int mask; - u64 len; - u64 pfn; + u64 base = ~0, p = 0; + u64 len, pfn; + int i = 0; struct scatterlist *sg; int entry; unsigned long page_shift = umem->page_shift; @@ -76,33 +72,24 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, m = find_first_bit(&tmp, BITS_PER_LONG); if (max_page_shift) m = min_t(unsigned long, max_page_shift - page_shift, m); - skip = 1 << m; - mask = skip - 1; - i = 0; + for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { len = sg_dma_len(sg) >> page_shift; pfn = sg_dma_address(sg) >> page_shift; - for (k = 0; k < len; k++) { - if (!(i & mask)) { - tmp = (unsigned long)pfn; - m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG)); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } else { - if (base + p != pfn) { - tmp = (unsigned long)p; - m = find_first_bit(&tmp, BITS_PER_LONG); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } - } - p++; - i++; + if (base + p != pfn) { + /* If either the offset or the new + * base are unaligned update m + */ + tmp = (unsigned long)(pfn | p); + if (!IS_ALIGNED(tmp, 1 << m)) + m = find_first_bit(&tmp, BITS_PER_LONG); + + base = pfn; + p = 0; } + + p += len; + i += len; } if (i) { -- cgit From fbcd49838d9094ca45772356e7b33afe4b7c93e7 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Sun, 24 Sep 2017 21:46:35 +0300 Subject: IB/mlx5: Fix NULL deference on mlx5_ib_update_xlt failure mlx5_ib_reg_user_mr called mlx5_ib_dereg_mr in case of MR population failure. This resulted in a NULL dereference as ibmr->device wasn't initialized yet. We address this by adding an internal dereg_mr function that can handle partially initialized MRs, and fixing clean_mr to work on partially initialized MRs. Fixes: ff740aefecb9 ("IB/mlx5: Decouple MR allocation and population flows") Signed-off-by: Ilya Lesokhin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mr.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 0e2789d9bb4d..37bbc543847a 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -47,7 +47,8 @@ enum { #define MLX5_UMR_ALIGN 2048 -static int clean_mr(struct mlx5_ib_mr *mr); +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static int mr_cache_max_order(struct mlx5_ib_dev *dev); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); @@ -1270,8 +1271,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift, update_xlt_flags); + if (err) { - mlx5_ib_dereg_mr(&mr->ibmr); + dereg_mr(dev, mr); return ERR_PTR(err); } } @@ -1356,7 +1358,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, err = mr_umem_get(pd, addr, len, access_flags, &mr->umem, &npages, &page_shift, &ncont, &order); if (err < 0) { - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1410,7 +1412,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (err) { mlx5_ib_warn(dev, "Failed to rereg UMR\n"); ib_umem_release(mr->umem); - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1469,9 +1471,8 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr) } } -static int clean_mr(struct mlx5_ib_mr *mr) +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); int allocated_from_cache = mr->allocated_from_cache; int err; @@ -1507,10 +1508,8 @@ static int clean_mr(struct mlx5_ib_mr *mr) return 0; } -int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(ibmr->device); - struct mlx5_ib_mr *mr = to_mmr(ibmr); int npages = mr->npages; struct ib_umem *umem = mr->umem; @@ -1539,7 +1538,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) } #endif - clean_mr(mr); + clean_mr(dev, mr); if (umem) { ib_umem_release(umem); @@ -1549,6 +1548,14 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) return 0; } +int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +{ + struct mlx5_ib_dev *dev = to_mdev(ibmr->device); + struct mlx5_ib_mr *mr = to_mmr(ibmr); + + return dereg_mr(dev, mr); +} + struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg) -- cgit From df5efdd97029f2cff7e5c91ea1c9f2b94d009b0f Mon Sep 17 00:00:00 2001 From: Sebastian Sanchez Date: Tue, 26 Sep 2017 06:05:57 -0700 Subject: IB/hfi1: Turn off AOC TX after offline substates Offline.quietDuration was added in the 8051 firmware, and the driver only turns off the AOC transmitters when offline.quiet is reached. However, the AOC transmitters need to be turned off at the new state. Therefore, turn off the AOC transmitters at any offline substates including offline.quiet and offline.quietDuration, then recheck we reached offline.quiet to support backwards compatibility. Reviewed-by: Jakub Byczkowski Reviewed-by: Mike Marciniszyn Signed-off-by: Sebastian Sanchez Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 85 +++++++++++++++++++++++++++++---------- drivers/infiniband/hw/hfi1/chip.h | 1 + 2 files changed, 65 insertions(+), 21 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index b2ed4b9cda6e..1c810d65721a 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1066,6 +1066,8 @@ static int read_idle_sma(struct hfi1_devdata *dd, u64 *data); static int thermal_init(struct hfi1_devdata *dd); static void update_statusp(struct hfi1_pportdata *ppd, u32 state); +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs); static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, int msecs); static void log_state_transition(struct hfi1_pportdata *ppd, u32 state); @@ -10305,6 +10307,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) { struct hfi1_devdata *dd = ppd->dd; u32 previous_state; + int offline_state_ret; int ret; update_lcb_cache(dd); @@ -10326,28 +10329,11 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) ppd->offline_disabled_reason = HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT); - /* - * Wait for offline transition. It can take a while for - * the link to go down. - */ - ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000); - if (ret < 0) - return ret; - - /* - * Now in charge of LCB - must be after the physical state is - * offline.quiet and before host_link_state is changed. - */ - set_host_lcb_access(dd); - write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ - - /* make sure the logical state is also down */ - ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); - if (ret) - force_logical_link_state_down(ppd); - - ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + offline_state_ret = wait_phys_link_offline_substates(ppd, 10000); + if (offline_state_ret < 0) + return offline_state_ret; + /* Disabling AOC transmitters */ if (ppd->port_type == PORT_TYPE_QSFP && ppd->qsfp_info.limiting_active && qsfp_mod_present(ppd)) { @@ -10364,6 +10350,30 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) } } + /* + * Wait for the offline.Quiet transition if it hasn't happened yet. It + * can take a while for the link to go down. + */ + if (offline_state_ret != PLS_OFFLINE_QUIET) { + ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000); + if (ret < 0) + return ret; + } + + /* + * Now in charge of LCB - must be after the physical state is + * offline.quiet and before host_link_state is changed. + */ + set_host_lcb_access(dd); + write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ + + /* make sure the logical state is also down */ + ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); + if (ret) + force_logical_link_state_down(ppd); + + ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + /* * The LNI has a mandatory wait time after the physical state * moves to Offline.Quiet. The wait time may be different @@ -12804,6 +12814,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state, return 0; } +/* + * wait_phys_link_offline_quiet_substates - wait for any offline substate + * @ppd: port device + * @msecs: the number of milliseconds to wait + * + * Wait up to msecs milliseconds for any offline physical link + * state change to occur. + * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT. + */ +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs) +{ + u32 read_state; + unsigned long timeout; + + timeout = jiffies + msecs_to_jiffies(msecs); + while (1) { + read_state = read_physical_state(ppd->dd); + if ((read_state & 0xF0) == PLS_OFFLINE) + break; + if (time_after(jiffies, timeout)) { + dd_dev_err(ppd->dd, + "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n", + read_state, msecs); + return -ETIMEDOUT; + } + usleep_range(1950, 2050); /* sleep 2ms-ish */ + } + + log_state_transition(ppd, read_state); + return read_state; +} + #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \ (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK) diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index b8345a60a0fb..461f937fe110 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -204,6 +204,7 @@ #define PLS_OFFLINE_READY_TO_QUIET_LT 0x92 #define PLS_OFFLINE_REPORT_FAILURE 0x93 #define PLS_OFFLINE_READY_TO_QUIET_BCC 0x94 +#define PLS_OFFLINE_QUIET_DURATION 0x95 #define PLS_POLLING 0x20 #define PLS_POLLING_QUIET 0x20 #define PLS_POLLING_ACTIVE 0x21 -- cgit From 30e10527bcce376114e627abb7fabfbe9bfee91e Mon Sep 17 00:00:00 2001 From: Sebastian Sanchez Date: Tue, 26 Sep 2017 06:06:03 -0700 Subject: IB/hfi1: Only reset QSFP after link up and turn off AOC TX QSFP reset enables AOC transmitters by default. They should be off before moving to high power mode to complete the setup. There is no need to reset the QSFP during LNI failure as it was reset at link down. Reviewed-by: Mike Marciniszyn Reviewed-by: Jakub Byczkowski Signed-off-by: Sebastian Sanchez Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 12 +++++++++++- drivers/infiniband/hw/hfi1/chip.h | 2 +- drivers/infiniband/hw/hfi1/platform.c | 4 +++- 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 1c810d65721a..27b75a8f5097 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -9415,7 +9415,7 @@ static void set_qsfp_int_n(struct hfi1_pportdata *ppd, u8 enable) write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask); } -void reset_qsfp(struct hfi1_pportdata *ppd) +int reset_qsfp(struct hfi1_pportdata *ppd) { struct hfi1_devdata *dd = ppd->dd; u64 mask, qsfp_mask; @@ -9445,6 +9445,13 @@ void reset_qsfp(struct hfi1_pportdata *ppd) * for alarms and warnings */ set_qsfp_int_n(ppd, 1); + + /* + * After the reset, AOC transmitters are enabled by default. They need + * to be turned off to complete the QSFP setup before they can be + * enabled again. + */ + return set_qsfp_tx(ppd, 0); } static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd, @@ -10406,6 +10413,9 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) & (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) { /* went down while attempting link up */ check_lni_states(ppd); + + /* The QSFP doesn't need to be reset on LNI failure */ + ppd->qsfp_info.reset_needed = 0; } /* the active link width (downgrade) is 0 on link down */ diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index 461f937fe110..50b8645d0b87 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -723,7 +723,7 @@ void handle_link_downgrade(struct work_struct *work); void handle_link_bounce(struct work_struct *work); void handle_start_link(struct work_struct *work); void handle_sma_message(struct work_struct *work); -void reset_qsfp(struct hfi1_pportdata *ppd); +int reset_qsfp(struct hfi1_pportdata *ppd); void qsfp_event(struct work_struct *work); void start_freeze_handling(struct hfi1_pportdata *ppd, int flags); int send_idle_sma(struct hfi1_devdata *dd, u64 message); diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c index a8af96d2b1b0..d486355880cb 100644 --- a/drivers/infiniband/hw/hfi1/platform.c +++ b/drivers/infiniband/hw/hfi1/platform.c @@ -790,7 +790,9 @@ static int tune_active_qsfp(struct hfi1_pportdata *ppd, u32 *ptr_tx_preset, * reuse of stale settings established in our previous pass through. */ if (ppd->qsfp_info.reset_needed) { - reset_qsfp(ppd); + ret = reset_qsfp(ppd); + if (ret) + return ret; refresh_qsfp_cache(ppd, &ppd->qsfp_info); } else { ppd->qsfp_info.reset_needed = 1; -- cgit From 753b19afb19dd97d0767df5e8afb13faff605315 Mon Sep 17 00:00:00 2001 From: Jan Sokolowski Date: Tue, 26 Sep 2017 06:06:09 -0700 Subject: IB/hfi1: Check eeprom config partition validity Relying on a trailing magic value is incorrect. There are instances where this is not present as trailing magic value has a specific purpose which is not partition validation. Instead use the header magic value which is present in all variants of the platform configuration and is intended for validation. This is also used in other locations in the driver. Fixes: bc5214ee2922 (IB/hfi1: Handle missing magic values in config file) Reviewed-by: Jakub Byczkowski Signed-off-by: Jan Sokolowski Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/eprom.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c index d46b17107901..1613af1c58d9 100644 --- a/drivers/infiniband/hw/hfi1/eprom.c +++ b/drivers/infiniband/hw/hfi1/eprom.c @@ -204,7 +204,10 @@ done_asic: return ret; } -/* magic character sequence that trails an image */ +/* magic character sequence that begins an image */ +#define IMAGE_START_MAGIC "APO=" + +/* magic character sequence that might trail an image */ #define IMAGE_TRAIL_MAGIC "egamiAPO" /* EPROM file types */ @@ -250,6 +253,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, { void *buffer; void *p; + u32 length; int ret; buffer = kmalloc(P1_SIZE, GFP_KERNEL); @@ -262,15 +266,21 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, return ret; } - /* scan for image magic that may trail the actual data */ - p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); - if (!p) { + /* config partition is valid only if it starts with IMAGE_START_MAGIC */ + if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) { kfree(buffer); return -ENOENT; } + /* scan for image magic that may trail the actual data */ + p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); + if (p) + length = p - buffer; + else + length = P1_SIZE; + *data = buffer; - *size = p - buffer; + *size = length; return 0; } -- cgit From 09592af5fdd722615ebe435fb34308de26c74bcf Mon Sep 17 00:00:00 2001 From: Kamenee Arumugam Date: Tue, 26 Sep 2017 06:06:15 -0700 Subject: IB/hfi1: Return correct value in general interrupt handler The general interrupt handler returns IRQ_HANDLED whether an IRQ was handled or not. Determine if an IRQ was handled and return the correct value. Reviewed-by: Dennis Dalessandro Reviewed-by: Michael J. Ruhl Signed-off-by: Kamenee Arumugam Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 27b75a8f5097..0be42787759f 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -8240,6 +8240,7 @@ static irqreturn_t general_interrupt(int irq, void *data) u64 regs[CCE_NUM_INT_CSRS]; u32 bit; int i; + irqreturn_t handled = IRQ_NONE; this_cpu_inc(*dd->int_counter); @@ -8260,9 +8261,10 @@ static irqreturn_t general_interrupt(int irq, void *data) for_each_set_bit(bit, (unsigned long *)®s[0], CCE_NUM_INT_CSRS * 64) { is_interrupt(dd, bit); + handled = IRQ_HANDLED; } - return IRQ_HANDLED; + return handled; } static irqreturn_t sdma_interrupt(int irq, void *data) -- cgit From 612601d0013f03de9dc134809f242ba6da9ca252 Mon Sep 17 00:00:00 2001 From: Alex Estrin Date: Tue, 26 Sep 2017 06:06:22 -0700 Subject: Revert "IB/ipoib: Update broadcast object if PKey value was changed in index 0" commit 9a9b8112699d will cause core to fail UD QP from being destroyed on ipoib unload, therefore cause resources leakage. On pkey change event above patch modifies mgid before calling underlying driver to detach it from QP. Drivers' detach_mcast() will fail to find modified mgid it was never given to attach in a first place. Core qp->usecnt will never go down, so ib_destroy_qp() will fail. IPoIB driver actually does take care of new broadcast mgid based on new pkey by destroying an old mcast object in ipoib_mcast_dev_flush()) .... if (priv->broadcast) { rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree); list_add_tail(&priv->broadcast->list, &remove_list); priv->broadcast = NULL; } ... then in restarted ipoib_macst_join_task() creating a new broadcast mcast object, sending join request and on completion tells the driver to attach to reinitialized QP: ... if (!priv->broadcast) { ... broadcast = ipoib_mcast_alloc(dev, 0); ... memcpy(broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4, sizeof (union ib_gid)); priv->broadcast = broadcast; ... Fixes: 9a9b8112699d ("IB/ipoib: Update broadcast object if PKey value was changed in index 0") Cc: stable@vger.kernel.org Reviewed-by: Mike Marciniszyn Reviewed-by: Dennis Dalessandro Signed-off-by: Alex Estrin Signed-off-by: Dennis Dalessandro Reviewed-by: Feras Daoud Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 2e075377242e..6cd61638b441 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1000,19 +1000,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv) */ priv->dev->broadcast[8] = priv->pkey >> 8; priv->dev->broadcast[9] = priv->pkey & 0xff; - - /* - * Update the broadcast address in the priv->broadcast object, - * in case it already exists, otherwise no one will do that. - */ - if (priv->broadcast) { - spin_lock_irq(&priv->lock); - memcpy(priv->broadcast->mcmember.mgid.raw, - priv->dev->broadcast + 4, - sizeof(union ib_gid)); - spin_unlock_irq(&priv->lock); - } - return 0; } -- cgit From b8f42738acaddf67731c34935c0994e09a588ca7 Mon Sep 17 00:00:00 2001 From: "Michael J. Ruhl" Date: Tue, 26 Sep 2017 06:06:28 -0700 Subject: IB/hfi1: On error, fix use after free during user context setup During base context setup, if setup_base_ctxt() fails, the context is deallocated. This is incorrect because the context is referenced on return, to notify any waiting subcontext. If there are no subcontexts the pointer will be invalid. Reorganize the error path so that deallocate_ctxt() is called after all the possible subcontexts have been notified. Reviewed-by: Ira Weiny Signed-off-by: Michael J. Ruhl Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/file_ops.c | 41 +++++++++++++++++++---------------- 1 file changed, 22 insertions(+), 19 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 2bc89260235a..d9a1e9893136 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -930,15 +930,8 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) switch (ret) { case 0: ret = setup_base_ctxt(fd, uctxt); - if (uctxt->subctxt_cnt) { - /* - * Base context is done (successfully or not), notify - * anybody using a sub-context that is waiting for - * this completion. - */ - clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); - wake_up(&uctxt->wait); - } + if (ret) + deallocate_ctxt(uctxt); break; case 1: ret = complete_subctxt(fd); @@ -1305,25 +1298,25 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, /* Now allocate the RcvHdr queue and eager buffers. */ ret = hfi1_create_rcvhdrq(dd, uctxt); if (ret) - return ret; + goto done; ret = hfi1_setup_eagerbufs(uctxt); if (ret) - goto setup_failed; + goto done; /* If sub-contexts are enabled, do the appropriate setup */ if (uctxt->subctxt_cnt) ret = setup_subctxt(uctxt); if (ret) - goto setup_failed; + goto done; ret = hfi1_alloc_ctxt_rcv_groups(uctxt); if (ret) - goto setup_failed; + goto done; ret = init_user_ctxt(fd, uctxt); if (ret) - goto setup_failed; + goto done; user_init(uctxt); @@ -1331,12 +1324,22 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, fd->uctxt = uctxt; hfi1_rcd_get(uctxt); - return 0; +done: + if (uctxt->subctxt_cnt) { + /* + * On error, set the failed bit so sub-contexts will clean up + * correctly. + */ + if (ret) + set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); -setup_failed: - /* Set the failed bit so sub-context init can do the right thing */ - set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); - deallocate_ctxt(uctxt); + /* + * Base context is done (successfully or not), notify anybody + * using a sub-context that is waiting for this completion. + */ + clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); + wake_up(&uctxt->wait); + } return ret; } -- cgit From 828bcbdc975fbcfb27946c33d4b1d1bfab70789b Mon Sep 17 00:00:00 2001 From: Harish Chegondi Date: Tue, 26 Sep 2017 06:06:34 -0700 Subject: IB/hfi1: Unsuccessful PCIe caps tuning should not fail driver load Failure to tune PCIe capabilities should not fail driver load. This can cause the driver load to fail on systems with any of the following: 1. HFI's parent is not root. Example: HFI card is behind a PCIe bridge. 2. HFI's parent is not PCI Express capable. In these situations, failure to tune PCIe capabilities should be logged in the system message logs but not cause the driver load to fail. This patch also ensures pcie capability word DevCtl is written only after a successful read and the capability tuning process continues even if read/write of the pcie capability word DevCtl fails. Fixes: c53df62c7a9a ("IB/hfi1: Check return values from PCI config API calls") Fixes: bf70a7757736 ("staging/rdma/hfi1: Enable WFR PCIe extended tags from the driver") Reviewed-by: Michael J. Ruhl Reviewed-by: Mike Marciniszyn Reviewed-by: Jakub Byczkowski Signed-off-by: Harish Chegondi Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/pcie.c | 50 ++++++++++++++++----------------------- 1 file changed, 21 insertions(+), 29 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 82447b7cdda1..09e50fd2a08f 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -68,7 +68,7 @@ /* * Code to adjust PCIe capabilities. */ -static int tune_pcie_caps(struct hfi1_devdata *); +static void tune_pcie_caps(struct hfi1_devdata *); /* * Do all the common PCIe setup and initialization. @@ -351,7 +351,7 @@ int pcie_speeds(struct hfi1_devdata *dd) */ int request_msix(struct hfi1_devdata *dd, u32 msireq) { - int nvec, ret; + int nvec; nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq, PCI_IRQ_MSIX | PCI_IRQ_LEGACY); @@ -360,12 +360,7 @@ int request_msix(struct hfi1_devdata *dd, u32 msireq) return nvec; } - ret = tune_pcie_caps(dd); - if (ret) { - dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret); - pci_free_irq_vectors(dd->pcidev); - return ret; - } + tune_pcie_caps(dd); /* check for legacy IRQ */ if (nvec == 1 && !dd->pcidev->msix_enabled) @@ -502,7 +497,7 @@ uint aspm_mode = ASPM_MODE_DISABLED; module_param_named(aspm, aspm_mode, uint, S_IRUGO); MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic"); -static int tune_pcie_caps(struct hfi1_devdata *dd) +static void tune_pcie_caps(struct hfi1_devdata *dd) { struct pci_dev *parent; u16 rc_mpss, rc_mps, ep_mpss, ep_mps; @@ -513,22 +508,14 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * Turn on extended tags in DevCtl in case the BIOS has turned it off * to improve WFR SDMA bandwidth */ - ret = pcie_capability_read_word(dd->pcidev, - PCI_EXP_DEVCTL, &ectl); - if (ret) { - dd_dev_err(dd, "Unable to read from PCI config\n"); - return ret; - } - - if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl); + if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { dd_dev_info(dd, "Enabling PCIe extended tags\n"); ectl |= PCI_EXP_DEVCTL_EXT_TAG; ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl); - if (ret) { - dd_dev_err(dd, "Unable to write to PCI config\n"); - return ret; - } + if (ret) + dd_dev_info(dd, "Unable to write to PCI config\n"); } /* Find out supported and configured values for parent (root) */ parent = dd->pcidev->bus->self; @@ -536,15 +523,22 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * The driver cannot perform the tuning if it does not have * access to the upstream component. */ - if (!parent) - return -EINVAL; + if (!parent) { + dd_dev_info(dd, "Parent not found\n"); + return; + } if (!pci_is_root_bus(parent->bus)) { dd_dev_info(dd, "Parent not root\n"); - return -EINVAL; + return; + } + if (!pci_is_pcie(parent)) { + dd_dev_info(dd, "Parent is not PCI Express capable\n"); + return; + } + if (!pci_is_pcie(dd->pcidev)) { + dd_dev_info(dd, "PCI device is not PCI Express capable\n"); + return; } - - if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev)) - return -EINVAL; rc_mpss = parent->pcie_mpss; rc_mps = ffs(pcie_get_mps(parent)) - 8; /* Find out supported and configured values for endpoint (us) */ @@ -590,8 +584,6 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) ep_mrrs = max_mrrs; pcie_set_readrq(dd->pcidev, ep_mrrs); } - - return 0; } /* End of PCIe capability tuning */ -- cgit