From cd4fedf9cfe2d453148dce0f105a41725e5107a3 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 23 May 2012 21:02:07 +0530 Subject: RDMA/ocrdma: Correct queue free count math Correct queue free count math for SQ, RQ for all hardware type. Update user-kernel ABI interface. Signed-off-by: Parav Pandit Signed-off-by: Roland Dreier --- drivers/infiniband/hw/ocrdma/ocrdma.h | 1 - drivers/infiniband/hw/ocrdma/ocrdma_abi.h | 5 +---- drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 7 ------- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 5 ----- 4 files changed, 1 insertion(+), 17 deletions(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h index 85a69c95855..037f5cea85b 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma.h @@ -231,7 +231,6 @@ struct ocrdma_qp_hwq_info { u32 entry_size; u32 max_cnt; u32 max_wqe_idx; - u32 free_delta; u16 dbid; /* qid, where to ring the doorbell. */ u32 len; dma_addr_t pa; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h index a411a4e3193..517ab20b727 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h @@ -101,8 +101,6 @@ struct ocrdma_create_qp_uresp { u32 rsvd1; u32 num_wqe_allocated; u32 num_rqe_allocated; - u32 free_wqe_delta; - u32 free_rqe_delta; u32 db_sq_offset; u32 db_rq_offset; u32 db_shift; @@ -126,8 +124,7 @@ struct ocrdma_create_srq_uresp { u32 db_rq_offset; u32 db_shift; - u32 free_rqe_delta; - u32 rsvd2; + u64 rsvd2; u64 rsvd3; } __packed; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 9b204b1ba33..f26314fd5f6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1990,19 +1990,12 @@ static void ocrdma_get_create_qp_rsp(struct ocrdma_create_qp_rsp *rsp, max_wqe_allocated = 1 << max_wqe_allocated; max_rqe_allocated = 1 << ((u16)rsp->max_wqe_rqe); - if (qp->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) { - qp->sq.free_delta = 0; - qp->rq.free_delta = 1; - } else - qp->sq.free_delta = 1; - qp->sq.max_cnt = max_wqe_allocated; qp->sq.max_wqe_idx = max_wqe_allocated - 1; if (!attrs->srq) { qp->rq.max_cnt = max_rqe_allocated; qp->rq.max_wqe_idx = max_rqe_allocated - 1; - qp->rq.free_delta = 1; } } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index e9f74d1b48f..d16d172b6b6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -940,8 +940,6 @@ static int ocrdma_copy_qp_uresp(struct ocrdma_qp *qp, uresp.db_rq_offset = OCRDMA_DB_RQ_OFFSET; uresp.db_shift = 16; } - uresp.free_wqe_delta = qp->sq.free_delta; - uresp.free_rqe_delta = qp->rq.free_delta; if (qp->dpp_enabled) { uresp.dpp_credit = dpp_credit_lmt; @@ -1307,8 +1305,6 @@ static int ocrdma_hwq_free_cnt(struct ocrdma_qp_hwq_info *q) free_cnt = (q->max_cnt - q->head) + q->tail; else free_cnt = q->tail - q->head; - if (q->free_delta) - free_cnt -= q->free_delta; return free_cnt; } @@ -1501,7 +1497,6 @@ static int ocrdma_copy_srq_uresp(struct ocrdma_srq *srq, struct ib_udata *udata) (srq->pd->id * srq->dev->nic_info.db_page_size); uresp.db_page_size = srq->dev->nic_info.db_page_size; uresp.num_rqe_allocated = srq->rq.max_cnt; - uresp.free_rqe_delta = 1; if (srq->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) { uresp.db_rq_offset = OCRDMA_DB_GEN2_RQ1_OFFSET; uresp.db_shift = 24; -- cgit v1.2.3 From 804eaf29bac4148aa265bedc62182ed41a4c6120 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 23 May 2012 21:11:17 +0530 Subject: RDMA/ocrdma: Fix signaled event for SRQ_LIMIT_REACHED Signed-off-by: Parav Pandit Signed-off-by: Roland Dreier --- drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index f26314fd5f6..9343a152297 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -732,7 +732,7 @@ static void ocrdma_dispatch_ibevent(struct ocrdma_dev *dev, break; case OCRDMA_SRQ_LIMIT_EVENT: ib_evt.element.srq = &qp->srq->ibsrq; - ib_evt.event = IB_EVENT_QP_LAST_WQE_REACHED; + ib_evt.event = IB_EVENT_SRQ_LIMIT_REACHED; srq_event = 1; qp_event = 0; break; -- cgit v1.2.3 From 7ad5e449b96bd82f406ed4657a64c8f72a48896d Mon Sep 17 00:00:00 2001 From: Devendra Naga Date: Tue, 29 May 2012 12:51:47 +0530 Subject: RDMA/ocrdma: Remove unnecessary version.h includes "make versioncheck" shows: drivers/infiniband/hw/ocrdma/ocrdma_main.c: 29 linux/version.h not needed. drivers/infiniband/hw/ocrdma/ocrdma_verbs.h: 31 linux/version.h not needed. Signed-off-by: Devendra Naga Signed-off-by: Roland Dreier --- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 1 - drivers/infiniband/hw/ocrdma/ocrdma_verbs.h | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index a20d16eaae7..04fef3de6d7 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -26,7 +26,6 @@ *******************************************************************/ #include -#include #include #include #include diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h index e6483439f25..633f03d8027 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h @@ -28,7 +28,6 @@ #ifndef __OCRDMA_VERBS_H__ #define __OCRDMA_VERBS_H__ -#include int ocrdma_post_send(struct ib_qp *, struct ib_send_wr *, struct ib_send_wr **bad_wr); int ocrdma_post_recv(struct ib_qp *, struct ib_recv_wr *, -- cgit v1.2.3 From 71b43fd573a60972b2175df4927c4ee10d757004 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 17 May 2012 17:51:53 -0300 Subject: RDMA/cxgb4: Fix crash when peer address is 0.0.0.0 When using rping -c -a 0.0.0.0 with iw_cxgb4, the system crashes when rdma_connect() is called. ip_dev_find() will return NULL, but pdev is accessed anyway. Checking that pdev is NULL and returning -ENODEV prevents the system from crashing. Signed-off-by: Thadeu Lima de Souza Cascardo Acked-by: Steve Wise Signed-off-by: Roland Dreier --- drivers/infiniband/hw/cxgb4/cm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 55ab284e22f..b18870c455a 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1593,6 +1593,10 @@ static int import_ep(struct c4iw_ep *ep, __be32 peer_ip, struct dst_entry *dst, struct net_device *pdev; pdev = ip_dev_find(&init_net, peer_ip); + if (!pdev) { + err = -ENODEV; + goto out; + } ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t, n, pdev, 0); if (!ep->l2t) -- cgit v1.2.3 From 3aac6ff16a2097be668975fd51084df2e27e4999 Mon Sep 17 00:00:00 2001 From: Shlomo Pongratz Date: Thu, 24 May 2012 16:08:07 +0300 Subject: IB/mlx4: Fix EQ deallocation in legacy mode Commit e605b743f33d ("IB/mlx4: Increase the number of vectors (EQs) available for ULPs") didn't handle correctly the case where there aren't enough MSI-X vectors to increase the number of EQs, so only the legacy EQs are allocated. This results in an attempt to memset() to zero the EQ table which was never allocated and a kernel crash. Fix this by checking in the teardown flow if the table of EQs was ever allocated. Also remove some unneeded setting to zero of the EQ related fields in struct mlx4_ib_dev. Signed-off-by: Shlomo Pongratz Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/main.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ee1c577238f..8afea12c8d4 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1084,12 +1084,9 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) int total_eqs = 0; int i, j, eq; - /* Init eq table */ - ibdev->eq_table = NULL; - ibdev->eq_added = 0; - - /* Legacy mode? */ - if (dev->caps.comp_pool == 0) + /* Legacy mode or comp_pool is not large enough */ + if (dev->caps.comp_pool == 0 || + dev->caps.num_ports > dev->caps.comp_pool) return; eq_per_port = rounddown_pow_of_two(dev->caps.comp_pool/ @@ -1135,7 +1132,10 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) { int i; - int total_eqs; + + /* no additional eqs were added */ + if (!ibdev->eq_table) + return; /* Reset the advertised EQ number */ ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors; @@ -1148,12 +1148,7 @@ static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) mlx4_release_eq(dev, ibdev->eq_table[i]); } - total_eqs = dev->caps.num_comp_vectors + ibdev->eq_added; - memset(ibdev->eq_table, 0, total_eqs * sizeof(int)); kfree(ibdev->eq_table); - - ibdev->eq_table = NULL; - ibdev->eq_added = 0; } static void *mlx4_ib_add(struct mlx4_dev *dev) -- cgit v1.2.3 From edc4a67e15e34d2b3a2ab968625fd157751125d8 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Thu, 24 May 2012 16:08:09 +0300 Subject: mlx4_core: Fix setting VL_cap in mlx4_SET_PORT wrapper flow Commit 096335b3f983 ("mlx4_core: Allow dynamic MTU configuration for IB ports") modifies the port VL setting. This exposes a bug in mlx4_common_set_port(), where the VL cap value passed in (inside the command mailbox) is incorrectly zeroed-out: mlx4_SET_PORT modifies the VL_cap field (byte 3 of the mailbox). Since the SET_PORT command is paravirtualized on the master as well as on the slaves, mlx4_SET_PORT_wrapper() is invoked on the master. This calls mlx4_common_set_port() where mailbox byte 3 gets overwritten by code which should only set a single bit in that byte (for the reset qkey counter flag) -- but instead overwrites the entire byte. The result is that when running in SR-IOV mode, the VL_cap will be set to zero -- fix this. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/port.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 1fe2c7a8b40..a8fb52992c6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -697,10 +697,10 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, if (slave != dev->caps.function) memset(inbox->buf, 0, 256); if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) { - *(u8 *) inbox->buf = !!reset_qkey_viols << 6; + *(u8 *) inbox->buf |= !!reset_qkey_viols << 6; ((__be32 *) inbox->buf)[2] = agg_cap_mask; } else { - ((u8 *) inbox->buf)[3] = !!reset_qkey_viols; + ((u8 *) inbox->buf)[3] |= !!reset_qkey_viols; ((__be32 *) inbox->buf)[1] = agg_cap_mask; } -- cgit v1.2.3 From fc2d004419abebcfd740f46c32dd8201ce1b33c9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 24 May 2012 16:08:08 +0300 Subject: IB/mlx4: Fix max_wqe capacity reported from query device 1. Limit the max number of WQEs per QP reported when querying the device, so that ib_create_qp() will not fail for a QP size that the device claimed to support due to additional headroom WQEs being allocated. 2. Limit qp resources accepted for ib_create_qp() to the limits reported in ib_query_device(). In kernel space, make sure that the limits returned to the caller following qp creation also lie within the reported device limits. For userspace, report as before, and do adjustment in libmlx4 (so as not to break ABI). Signed-off-by: Jack Morgenstein Signed-off-by: Sagi Grimberg Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/infiniband/hw/mlx4/mlx4_ib.h | 8 ++++++++ drivers/infiniband/hw/mlx4/qp.c | 21 +++++++++++++++------ 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8afea12c8d4..3530c41fcd1 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -140,7 +140,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->max_mr_size = ~0ull; props->page_size_cap = dev->dev->caps.page_size_cap; props->max_qp = dev->dev->caps.num_qps - dev->dev->caps.reserved_qps; - props->max_qp_wr = dev->dev->caps.max_wqes; + props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; props->max_sge = min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); props->max_cq = dev->dev->caps.num_cqs - dev->dev->caps.reserved_cqs; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index e62297cc77c..ff36655d23d 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -44,6 +44,14 @@ #include #include +enum { + MLX4_IB_SQ_MIN_WQE_SHIFT = 6, + MLX4_IB_MAX_HEADROOM = 2048 +}; + +#define MLX4_IB_SQ_HEADROOM(shift) ((MLX4_IB_MAX_HEADROOM >> (shift)) + 1) +#define MLX4_IB_SQ_MAX_SPARE (MLX4_IB_SQ_HEADROOM(MLX4_IB_SQ_MIN_WQE_SHIFT)) + struct mlx4_ib_ucontext { struct ib_ucontext ibucontext; struct mlx4_uar uar; diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index ceb33327091..8d4ed24aef9 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -310,8 +310,8 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap, int is_user, int has_rq, struct mlx4_ib_qp *qp) { /* Sanity check RQ size before proceeding */ - if (cap->max_recv_wr > dev->dev->caps.max_wqes || - cap->max_recv_sge > dev->dev->caps.max_rq_sg) + if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE || + cap->max_recv_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg)) return -EINVAL; if (!has_rq) { @@ -329,8 +329,17 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap, qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg)); } - cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt; - cap->max_recv_sge = qp->rq.max_gs; + /* leave userspace return values as they were, so as not to break ABI */ + if (is_user) { + cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt; + cap->max_recv_sge = qp->rq.max_gs; + } else { + cap->max_recv_wr = qp->rq.max_post = + min(dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE, qp->rq.wqe_cnt); + cap->max_recv_sge = min(qp->rq.max_gs, + min(dev->dev->caps.max_sq_sg, + dev->dev->caps.max_rq_sg)); + } return 0; } @@ -341,8 +350,8 @@ static int set_kernel_sq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap, int s; /* Sanity check SQ size before proceeding */ - if (cap->max_send_wr > dev->dev->caps.max_wqes || - cap->max_send_sge > dev->dev->caps.max_sq_sg || + if (cap->max_send_wr > (dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE) || + cap->max_send_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg) || cap->max_inline_data + send_wqe_overhead(type, qp->flags) + sizeof (struct mlx4_wqe_inline_seg) > dev->dev->caps.max_sq_desc_sz) return -EINVAL; -- cgit v1.2.3