From 809aa64ebff51eb170ee31a95f83b2d21efa32e2 Mon Sep 17 00:00:00 2001 From: Zhipeng Lu Date: Fri, 12 Jan 2024 16:55:23 +0800 Subject: IB/hfi1: Fix a memleak in init_credit_return When dma_alloc_coherent fails to allocate dd->cr_base[i].va, init_credit_return should deallocate dd->cr_base and dd->cr_base[i] that allocated before. Or those resources would be never freed and a memleak is triggered. Fixes: 7724105686e7 ("IB/hfi1: add driver files") Signed-off-by: Zhipeng Lu Link: https://lore.kernel.org/r/20240112085523.3731720-1-alexious@zju.edu.cn Acked-by: Dennis Dalessandro Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/pio.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 68c621ff59d0..5a91cbda4aee 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -2086,7 +2086,7 @@ int init_credit_return(struct hfi1_devdata *dd) "Unable to allocate credit return DMA range for NUMA %d\n", i); ret = -ENOMEM; - goto done; + goto free_cr_base; } } set_dev_node(&dd->pcidev->dev, dd->node); @@ -2094,6 +2094,10 @@ int init_credit_return(struct hfi1_devdata *dd) ret = 0; done: return ret; + +free_cr_base: + free_credit_return(dd); + goto done; } void free_credit_return(struct hfi1_devdata *dd) -- cgit v1.2.3 From 282fd66e2ef6e5d72b8fcd77efb2b282d2569464 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Mon, 22 Jan 2024 20:54:33 -0800 Subject: RDMA/bnxt_re: Avoid creating fence MR for newer adapters Limit the usage of fence MR to adapters older than Gen P5 products. Fixes: 1801d87b3598 ("RDMA/bnxt_re: Support new 5760X P7 devices") Signed-off-by: Kashyap Desai Signed-off-by: Bhargava Chenna Marreddy Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1705985677-15551-2-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers') diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 824349659d69..e1ea49263145 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -401,6 +401,10 @@ static void bnxt_re_create_fence_wqe(struct bnxt_re_pd *pd) struct bnxt_re_fence_data *fence = &pd->fence; struct ib_mr *ib_mr = &fence->mr->ib_mr; struct bnxt_qplib_swqe *wqe = &fence->bind_wqe; + struct bnxt_re_dev *rdev = pd->rdev; + + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; memset(wqe, 0, sizeof(*wqe)); wqe->type = BNXT_QPLIB_SWQE_TYPE_BIND_MW; @@ -455,6 +459,9 @@ static void bnxt_re_destroy_fence_mr(struct bnxt_re_pd *pd) struct device *dev = &rdev->en_dev->pdev->dev; struct bnxt_re_mr *mr = fence->mr; + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; + if (fence->mw) { bnxt_re_dealloc_mw(fence->mw); fence->mw = NULL; @@ -486,6 +493,9 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) struct ib_mw *mw; int rc; + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return 0; + dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES, DMA_BIDIRECTIONAL); rc = dma_mapping_error(dev, dma_addr); -- cgit v1.2.3 From 8fcbf0a55f71be7e562f10222abc9a34148189d0 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Mon, 22 Jan 2024 20:54:34 -0800 Subject: RDMA/bnxt_re: Remove a redundant check inside bnxt_re_vf_res_config After the cited commit, there is no possibility that this check can return true. Remove it. Fixes: a43c26fa2e6c ("RDMA/bnxt_re: Remove the sriov config callback") Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1705985677-15551-3-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/main.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index f022c922fae5..54b4d2f3a5d8 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -280,9 +280,6 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev) static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev) { - - if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags)) - return; rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev); if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { bnxt_re_set_resource_limits(rdev); -- cgit v1.2.3 From 8eaca6b5997bd8fd7039f2693e4ecf112823c816 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Mon, 22 Jan 2024 20:54:35 -0800 Subject: RDMA/bnxt_re: Fix unconditional fence for newer adapters Older adapters required an unconditional fence for non-wire memory operations. Newer adapters doesn't require this and therefore, disabling the unconditional fence. Fixes: 1801d87b3598 ("RDMA/bnxt_re: Support new 5760X P7 devices") Signed-off-by: Kashyap Desai Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1705985677-15551-4-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index e1ea49263145..fdb4fde1acbe 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2566,11 +2566,6 @@ static int bnxt_re_build_inv_wqe(const struct ib_send_wr *wr, wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV; wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey; - /* Need unconditional fence for local invalidate - * opcode to work as expected. - */ - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; - if (wr->send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; if (wr->send_flags & IB_SEND_SOLICITED) @@ -2593,12 +2588,6 @@ static int bnxt_re_build_reg_wqe(const struct ib_reg_wr *wr, wqe->frmr.levels = qplib_frpl->hwq.level; wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR; - /* Need unconditional fence for reg_mr - * opcode to function as expected. - */ - - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; - if (wr->wr.send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; @@ -2729,6 +2718,18 @@ bad: return rc; } +static void bnxt_re_legacy_set_uc_fence(struct bnxt_qplib_swqe *wqe) +{ + /* Need unconditional fence for non-wire memory opcode + * to work as expected. + */ + if (wqe->type == BNXT_QPLIB_SWQE_TYPE_LOCAL_INV || + wqe->type == BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR || + wqe->type == BNXT_QPLIB_SWQE_TYPE_REG_MR || + wqe->type == BNXT_QPLIB_SWQE_TYPE_BIND_MW) + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; +} + int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { @@ -2808,8 +2809,11 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, rc = -EINVAL; goto bad; } - if (!rc) + if (!rc) { + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_re_legacy_set_uc_fence(&wqe); rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe); + } bad: if (rc) { ibdev_err(&qp->rdev->ibdev, -- cgit v1.2.3 From 3687b450c5f32e80f179ce4b09e0454da1449eac Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Mon, 22 Jan 2024 20:54:36 -0800 Subject: RDMA/bnxt_re: Return error for SRQ resize SRQ resize is not supported in the driver. But driver is not returning error from bnxt_re_modify_srq() for SRQ resize. Fixes: 37cb11acf1f7 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters") Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1705985677-15551-5-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index fdb4fde1acbe..ce9c5bae83bf 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -1827,7 +1827,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, switch (srq_attr_mask) { case IB_SRQ_MAX_WR: /* SRQ resize is not supported */ - break; + return -EINVAL; case IB_SRQ_LIMIT: /* Change the SRQ threshold */ if (srq_attr->srq_limit > srq->qplib_srq.max_wqe) @@ -1842,13 +1842,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, /* On success, update the shadow */ srq->srq_limit = srq_attr->srq_limit; /* No need to Build and send response back to udata */ - break; + return 0; default: ibdev_err(&rdev->ibdev, "Unsupported srq_attr_mask 0x%x", srq_attr_mask); return -EINVAL; } - return 0; } int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr) -- cgit v1.2.3 From 80dde187f734cf9ccf988d5c2ef1a46b990660fd Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Mon, 22 Jan 2024 20:54:37 -0800 Subject: RDMA/bnxt_re: Add a missing check in bnxt_qplib_query_srq Before populating the response, driver has to check the status of HWRM command. Fixes: 37cb11acf1f7 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters") Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1705985677-15551-6-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index c98e04fe2ddd..439d0c7c5d0c 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -744,7 +744,8 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, &sbuf, sizeof(req), sizeof(resp), 0); rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); - srq->threshold = le16_to_cpu(sb->srq_limit); + if (!rc) + srq->threshold = le16_to_cpu(sb->srq_limit); dma_free_coherent(&rcfw->pdev->dev, sbuf.size, sbuf.sb, sbuf.dma_addr); -- cgit v1.2.3 From 4d5e86a56615cc387d21c629f9af8fb0e958d350 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 28 Jan 2024 11:29:11 +0200 Subject: RDMA/mlx5: Fix fortify source warning while accessing Eth segment ------------[ cut here ]------------ memcpy: detected field-spanning write (size 56) of single field "eseg->inline_hdr.start" at /var/lib/dkms/mlnx-ofed-kernel/5.8/build/drivers/infiniband/hw/mlx5/wr.c:131 (size 2) WARNING: CPU: 0 PID: 293779 at /var/lib/dkms/mlnx-ofed-kernel/5.8/build/drivers/infiniband/hw/mlx5/wr.c:131 mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] Modules linked in: 8021q garp mrp stp llc rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) ib_uverbs(OE) ib_core(OE) mlx5_core(OE) pci_hyperv_intf mlxdevm(OE) mlx_compat(OE) tls mlxfw(OE) psample nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables libcrc32c nfnetlink mst_pciconf(OE) knem(OE) vfio_pci vfio_pci_core vfio_iommu_type1 vfio iommufd irqbypass cuse nfsv3 nfs fscache netfs xfrm_user xfrm_algo ipmi_devintf ipmi_msghandler binfmt_misc crct10dif_pclmul crc32_pclmul polyval_clmulni polyval_generic ghash_clmulni_intel sha512_ssse3 snd_pcsp aesni_intel crypto_simd cryptd snd_pcm snd_timer joydev snd soundcore input_leds serio_raw evbug nfsd auth_rpcgss nfs_acl lockd grace sch_fq_codel sunrpc drm efi_pstore ip_tables x_tables autofs4 psmouse virtio_net net_failover failover floppy [last unloaded: mlx_compat(OE)] CPU: 0 PID: 293779 Comm: ssh Tainted: G OE 6.2.0-32-generic #32~22.04.1-Ubuntu Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] Code: 0c 01 00 a8 01 75 25 48 8b 75 a0 b9 02 00 00 00 48 c7 c2 10 5b fd c0 48 c7 c7 80 5b fd c0 c6 05 57 0c 03 00 01 e8 95 4d 93 da <0f> 0b 44 8b 4d b0 4c 8b 45 c8 48 8b 4d c0 e9 49 fb ff ff 41 0f b7 RSP: 0018:ffffb5b48478b570 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffb5b48478b628 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffb5b48478b5e8 R13: ffff963a3c609b5e R14: ffff9639c3fbd800 R15: ffffb5b480475a80 FS: 00007fc03b444c80(0000) GS:ffff963a3dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556f46bdf000 CR3: 0000000006ac6003 CR4: 00000000003706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? show_regs+0x72/0x90 ? mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] ? __warn+0x8d/0x160 ? mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] ? report_bug+0x1bb/0x1d0 ? handle_bug+0x46/0x90 ? exc_invalid_op+0x19/0x80 ? asm_exc_invalid_op+0x1b/0x20 ? mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] mlx5_ib_post_send_nodrain+0xb/0x20 [mlx5_ib] ipoib_send+0x2ec/0x770 [ib_ipoib] ipoib_start_xmit+0x5a0/0x770 [ib_ipoib] dev_hard_start_xmit+0x8e/0x1e0 ? validate_xmit_skb_list+0x4d/0x80 sch_direct_xmit+0x116/0x3a0 __dev_xmit_skb+0x1fd/0x580 __dev_queue_xmit+0x284/0x6b0 ? _raw_spin_unlock_irq+0xe/0x50 ? __flush_work.isra.0+0x20d/0x370 ? push_pseudo_header+0x17/0x40 [ib_ipoib] neigh_connected_output+0xcd/0x110 ip_finish_output2+0x179/0x480 ? __smp_call_single_queue+0x61/0xa0 __ip_finish_output+0xc3/0x190 ip_finish_output+0x2e/0xf0 ip_output+0x78/0x110 ? __pfx_ip_finish_output+0x10/0x10 ip_local_out+0x64/0x70 __ip_queue_xmit+0x18a/0x460 ip_queue_xmit+0x15/0x30 __tcp_transmit_skb+0x914/0x9c0 tcp_write_xmit+0x334/0x8d0 tcp_push_one+0x3c/0x60 tcp_sendmsg_locked+0x2e1/0xac0 tcp_sendmsg+0x2d/0x50 inet_sendmsg+0x43/0x90 sock_sendmsg+0x68/0x80 sock_write_iter+0x93/0x100 vfs_write+0x326/0x3c0 ksys_write+0xbd/0xf0 ? do_syscall_64+0x69/0x90 __x64_sys_write+0x19/0x30 do_syscall_64+0x59/0x90 ? do_user_addr_fault+0x1d0/0x640 ? exit_to_user_mode_prepare+0x3b/0xd0 ? irqentry_exit_to_user_mode+0x9/0x20 ? irqentry_exit+0x43/0x50 ? exc_page_fault+0x92/0x1b0 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7fc03ad14a37 Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 RSP: 002b:00007ffdf8697fe8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000008024 RCX: 00007fc03ad14a37 RDX: 0000000000008024 RSI: 0000556f46bd8270 RDI: 0000000000000003 RBP: 0000556f46bb1800 R08: 0000000000007fe3 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000002 R13: 0000556f46bc66b0 R14: 000000000000000a R15: 0000556f46bb2f50 ---[ end trace 0000000000000000 ]--- Link: https://lore.kernel.org/r/8228ad34bd1a25047586270f7b1fb4ddcd046282.1706433934.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/wr.c | 2 +- include/linux/mlx5/qp.h | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index df1d1b0a3ef7..9947feb7fb8a 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -78,7 +78,7 @@ static void set_eth_seg(const struct ib_send_wr *wr, struct mlx5_ib_qp *qp, */ copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start, left); - memcpy(eseg->inline_hdr.start, pdata, copysz); + memcpy(eseg->inline_hdr.data, pdata, copysz); stride = ALIGN(sizeof(struct mlx5_wqe_eth_seg) - sizeof(eseg->inline_hdr.start) + copysz, 16); *size += stride / 16; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index bd53cf4be7bd..f0e55bf3ec8b 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg { union { struct { __be16 sz; - u8 start[2]; + union { + u8 start[2]; + DECLARE_FLEX_ARRAY(u8, data); + }; } inline_hdr; struct { __be16 type; -- cgit v1.2.3 From 43fdbd140238d44e7e847232719fef7d20f9d326 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Sun, 28 Jan 2024 11:29:12 +0200 Subject: IB/mlx5: Don't expose debugfs entries for RRoCE general parameters if not supported debugfs entries for RRoCE general CC parameters must be exposed only when they are supported, otherwise when accessing them there may be a syndrome error in kernel log, for example: $ cat /sys/kernel/debug/mlx5/0000:08:00.1/cc_params/rtt_resp_dscp cat: '/sys/kernel/debug/mlx5/0000:08:00.1/cc_params/rtt_resp_dscp': Invalid argument $ dmesg mlx5_core 0000:08:00.1: mlx5_cmd_out_err:805:(pid 1253): QUERY_CONG_PARAMS(0x824) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x325a82), err(-22) Fixes: 66fb1d5df6ac ("IB/mlx5: Extend debug control for CC parameters") Reviewed-by: Edward Srouji Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/e7ade70bad52b7468bdb1de4d41d5fad70c8b71c.1706433934.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/cong.c | 6 ++++++ include/linux/mlx5/mlx5_ifc.h | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c index f87531318feb..a78a067e3ce7 100644 --- a/drivers/infiniband/hw/mlx5/cong.c +++ b/drivers/infiniband/hw/mlx5/cong.c @@ -458,6 +458,12 @@ void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num) dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev)); for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) { + if ((i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID || + i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP)) + if (!MLX5_CAP_GEN(mdev, roce) || + !MLX5_CAP_ROCE(mdev, roce_cc_general)) + continue; + dbg_cc_params->params[i].offset = i; dbg_cc_params->params[i].dev = dev; dbg_cc_params->params[i].port_num = port_num; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bf5320b28b8b..2c10350bd422 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1103,7 +1103,7 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x1]; + u8 roce_cc_general[0x1]; u8 qp_ooo_transmit_default[0x1]; u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; -- cgit v1.2.3 From be551ee1574280ef8afbf7c271212ac3e38933ef Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 28 Jan 2024 11:29:13 +0200 Subject: RDMA/mlx5: Relax DEVX access upon modify commands Relax DEVX access upon modify commands to be UVERBS_ACCESS_READ. The kernel doesn't need to protect what firmware protects, or what causes no damage to anyone but the user. As firmware needs to protect itself from parallel access to the same object, don't block parallel modify/query commands on the same object in the kernel side. This change will allow user space application to run parallel updates to different entries in the same bulk object. Tested-by: Tamar Mashiah Signed-off-by: Yishai Hadas Reviewed-by: Michael Guralnik Link: https://lore.kernel.org/r/7407d5ed35dc427c1097699e12b49c01e1073406.1706433934.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 869369cb5b5f..253fea374a72 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2949,7 +2949,7 @@ DECLARE_UVERBS_NAMED_METHOD( MLX5_IB_METHOD_DEVX_OBJ_MODIFY, UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_MODIFY_HANDLE, UVERBS_IDR_ANY_OBJECT, - UVERBS_ACCESS_WRITE, + UVERBS_ACCESS_READ, UA_MANDATORY), UVERBS_ATTR_PTR_IN( MLX5_IB_ATTR_DEVX_OBJ_MODIFY_CMD_IN, -- cgit v1.2.3 From bd97cea7b18a0a553773af806dfbfac27a7c4acb Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Wed, 31 Jan 2024 17:38:46 -0600 Subject: RDMA/irdma: Fix KASAN issue with tasklet KASAN testing revealed the following issue assocated with freeing an IRQ. [50006.466686] Call Trace: [50006.466691] [50006.489538] dump_stack+0x5c/0x80 [50006.493475] print_address_description.constprop.6+0x1a/0x150 [50006.499872] ? irdma_sc_process_ceq+0x483/0x790 [irdma] [50006.505742] ? irdma_sc_process_ceq+0x483/0x790 [irdma] [50006.511644] kasan_report.cold.11+0x7f/0x118 [50006.516572] ? irdma_sc_process_ceq+0x483/0x790 [irdma] [50006.522473] irdma_sc_process_ceq+0x483/0x790 [irdma] [50006.528232] irdma_process_ceq+0xb2/0x400 [irdma] [50006.533601] ? irdma_hw_flush_wqes_callback+0x370/0x370 [irdma] [50006.540298] irdma_ceq_dpc+0x44/0x100 [irdma] [50006.545306] tasklet_action_common.isra.14+0x148/0x2c0 [50006.551096] __do_softirq+0x1d0/0xaf8 [50006.555396] irq_exit_rcu+0x219/0x260 [50006.559670] irq_exit+0xa/0x20 [50006.563320] smp_apic_timer_interrupt+0x1bf/0x690 [50006.568645] apic_timer_interrupt+0xf/0x20 [50006.573341] The issue is that a tasklet could be pending on another core racing the delete of the irq. Fix by insuring any scheduled tasklet is killed after deleting the irq. Fixes: 44d9e52977a1 ("RDMA/irdma: Implement device initialization definitions") Signed-off-by: Mike Marciniszyn Signed-off-by: Shiraz Saleem Signed-off-by: Sindhu Devale Link: https://lore.kernel.org/r/20240131233849.400285-2-sindhu.devale@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/hw.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers') diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index bd4b2b896444..2f8d18d8be3b 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -570,6 +570,13 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf, dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx); irq_update_affinity_hint(msix_vec->irq, NULL); free_irq(msix_vec->irq, dev_id); + if (rf == dev_id) { + tasklet_kill(&rf->dpc_tasklet); + } else { + struct irdma_ceq *iwceq = (struct irdma_ceq *)dev_id; + + tasklet_kill(&iwceq->dpc_tasklet); + } } /** -- cgit v1.2.3 From ee107186bcfd25d7873258f3f75440e20f5e6416 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Wed, 31 Jan 2024 17:38:47 -0600 Subject: RDMA/irdma: Validate max_send_wr and max_recv_wr Validate that max_send_wr and max_recv_wr is within the supported range. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Change-Id: I2fc8b10292b641fddd20b36986a9dae90a93f4be Signed-off-by: Shiraz Saleem Signed-off-by: Sindhu Devale Link: https://lore.kernel.org/r/20240131233849.400285-3-sindhu.devale@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/verbs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index b5eb8d421988..cb828e3da478 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -839,7 +839,9 @@ static int irdma_validate_qp_attrs(struct ib_qp_init_attr *init_attr, if (init_attr->cap.max_inline_data > uk_attrs->max_hw_inline || init_attr->cap.max_send_sge > uk_attrs->max_hw_wq_frags || - init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags) + init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags || + init_attr->cap.max_send_wr > uk_attrs->max_hw_wq_quanta || + init_attr->cap.max_recv_wr > uk_attrs->max_hw_rq_quanta) return -EINVAL; if (rdma_protocol_roce(&iwdev->ibdev, 1)) { -- cgit v1.2.3 From 666047f3ece9f991774c1fe9b223139a9ef8908d Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Wed, 31 Jan 2024 17:38:48 -0600 Subject: RDMA/irdma: Set the CQ read threshold for GEN 1 The CQ shadow read threshold is currently not set for GEN 2. This could cause an invalid CQ overflow condition, so remove the GEN check that exclused GEN 1. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Sindhu Devale Link: https://lore.kernel.org/r/20240131233849.400285-4-sindhu.devale@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/verbs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index cb828e3da478..0b046c061742 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2186,9 +2186,8 @@ static int irdma_create_cq(struct ib_cq *ibcq, info.cq_base_pa = iwcq->kmem.pa; } - if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) - info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, - (u32)IRDMA_MAX_CQ_READ_THRESH); + info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, + (u32)IRDMA_MAX_CQ_READ_THRESH); if (irdma_sc_cq_init(cq, &info)) { ibdev_dbg(&iwdev->ibdev, "VERBS: init cq fail\n"); -- cgit v1.2.3 From 630bdb6f28ca9e5ff79e244030170ac788478332 Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Wed, 31 Jan 2024 17:38:49 -0600 Subject: RDMA/irdma: Add AE for too many RNRS Add IRDMA_AE_LLP_TOO_MANY_RNRS to the list of AE's processed as an abnormal asyncronous event. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Sindhu Devale Link: https://lore.kernel.org/r/20240131233849.400285-5-sindhu.devale@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/defs.h | 1 + drivers/infiniband/hw/irdma/hw.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h index 8fb752f2eda2..2cb4b96db721 100644 --- a/drivers/infiniband/hw/irdma/defs.h +++ b/drivers/infiniband/hw/irdma/defs.h @@ -346,6 +346,7 @@ enum irdma_cqp_op_type { #define IRDMA_AE_LLP_TOO_MANY_KEEPALIVE_RETRIES 0x050b #define IRDMA_AE_LLP_DOUBT_REACHABILITY 0x050c #define IRDMA_AE_LLP_CONNECTION_ESTABLISHED 0x050e +#define IRDMA_AE_LLP_TOO_MANY_RNRS 0x050f #define IRDMA_AE_RESOURCE_EXHAUSTION 0x0520 #define IRDMA_AE_RESET_SENT 0x0601 #define IRDMA_AE_TERMINATE_SENT 0x0602 diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 2f8d18d8be3b..ad50b77282f8 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -387,6 +387,7 @@ static void irdma_process_aeq(struct irdma_pci_f *rf) case IRDMA_AE_LLP_TOO_MANY_RETRIES: case IRDMA_AE_LCE_QP_CATASTROPHIC: case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC: + case IRDMA_AE_LLP_TOO_MANY_RNRS: case IRDMA_AE_LCE_CQ_CATASTROPHIC: case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG: default: -- cgit v1.2.3 From e6f57c6881916df39db7d95981a8ad2b9c3458d6 Mon Sep 17 00:00:00 2001 From: Daniel Vacek Date: Thu, 1 Feb 2024 09:10:08 +0100 Subject: IB/hfi1: Fix sdma.h tx->num_descs off-by-one error Unfortunately the commit `fd8958efe877` introduced another error causing the `descs` array to overflow. This reults in further crashes easily reproducible by `sendmsg` system call. [ 1080.836473] general protection fault, probably for non-canonical address 0x400300015528b00a: 0000 [#1] PREEMPT SMP PTI [ 1080.869326] RIP: 0010:hfi1_ipoib_build_ib_tx_headers.constprop.0+0xe1/0x2b0 [hfi1] -- [ 1080.974535] Call Trace: [ 1080.976990] [ 1081.021929] hfi1_ipoib_send_dma_common+0x7a/0x2e0 [hfi1] [ 1081.027364] hfi1_ipoib_send_dma_list+0x62/0x270 [hfi1] [ 1081.032633] hfi1_ipoib_send+0x112/0x300 [hfi1] [ 1081.042001] ipoib_start_xmit+0x2a9/0x2d0 [ib_ipoib] [ 1081.046978] dev_hard_start_xmit+0xc4/0x210 -- [ 1081.148347] __sys_sendmsg+0x59/0xa0 crash> ipoib_txreq 0xffff9cfeba229f00 struct ipoib_txreq { txreq = { list = { next = 0xffff9cfeba229f00, prev = 0xffff9cfeba229f00 }, descp = 0xffff9cfeba229f40, coalesce_buf = 0x0, wait = 0xffff9cfea4e69a48, complete = 0xffffffffc0fe0760 , packet_len = 0x46d, tlen = 0x0, num_desc = 0x0, desc_limit = 0x6, next_descq_idx = 0x45c, coalesce_idx = 0x0, flags = 0x0, descs = {{ qw = {0x8024000120dffb00, 0x4} # SDMA_DESC0_FIRST_DESC_FLAG (bit 63) }, { qw = { 0x3800014231b108, 0x4} }, { qw = { 0x310000e4ee0fcf0, 0x8} }, { qw = { 0x3000012e9f8000, 0x8} }, { qw = { 0x59000dfb9d0000, 0x8} }, { qw = { 0x78000e02e40000, 0x8} }} }, sdma_hdr = 0x400300015528b000, <<< invalid pointer in the tx request structure sdma_status = 0x0, SDMA_DESC0_LAST_DESC_FLAG (bit 62) complete = 0x0, priv = 0x0, txq = 0xffff9cfea4e69880, skb = 0xffff9d099809f400 } If an SDMA send consists of exactly 6 descriptors and requires dword padding (in the 7th descriptor), the sdma_txreq descriptor array is not properly expanded and the packet will overflow into the container structure. This results in a panic when the send completion runs. The exact panic varies depending on what elements of the container structure get corrupted. The fix is to use the correct expression in _pad_sdma_tx_descs() to test the need to expand the descriptor array. With this patch the crashes are no longer reproducible and the machine is stable. Fixes: fd8958efe877 ("IB/hfi1: Fix sdma.h tx->num_descs off-by-one errors") Cc: stable@vger.kernel.org Reported-by: Mats Kronberg Tested-by: Mats Kronberg Signed-off-by: Daniel Vacek Link: https://lore.kernel.org/r/20240201081009.1109442-1-neelx@redhat.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/sdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 6e5ac2023328..b67d23b1f286 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -3158,7 +3158,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) { int rval = 0; - if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) { + if ((unlikely(tx->num_desc == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { __sdma_txclean(dd, tx); -- cgit v1.2.3 From fdfa083549de5d50ebf7f6811f33757781e838c0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Sun, 4 Feb 2024 16:42:07 -0800 Subject: RDMA/srpt: Support specifying the srpt_service_guid parameter Make loading ib_srpt with this parameter set work. The current behavior is that setting that parameter while loading the ib_srpt kernel module triggers the following kernel crash: BUG: kernel NULL pointer dereference, address: 0000000000000000 Call Trace: parse_one+0x18c/0x1d0 parse_args+0xe1/0x230 load_module+0x8de/0xa60 init_module_from_file+0x8b/0xd0 idempotent_init_module+0x181/0x240 __x64_sys_finit_module+0x5a/0xb0 do_syscall_64+0x5f/0xe0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 Cc: LiHonggang Reported-by: LiHonggang Fixes: a42d985bd5b2 ("ib_srpt: Initial SRP Target merge for v3.3-rc1") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240205004207.17031-1-bvanassche@acm.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/srpt/ib_srpt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 58f70cfec45a..d2dce6ce30a9 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444); MODULE_PARM_DESC(srpt_srq_size, "Shared receive queue (SRQ) size."); +static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp) +{ + return kstrtou64(buffer, 16, (u64 *)kp->arg); +} static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg); } -module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid, - 0444); +module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x, + &srpt_service_guid, 0444); MODULE_PARM_DESC(srpt_service_guid, "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA."); -- cgit v1.2.3 From 5ba4e6d5863c53e937f49932dee0ecb004c65928 Mon Sep 17 00:00:00 2001 From: Kamal Heib Date: Thu, 8 Feb 2024 17:36:28 -0500 Subject: RDMA/qedr: Fix qedr_create_user_qp error flow Avoid the following warning by making sure to free the allocated resources in case that qedr_init_user_queue() fail. -----------[ cut here ]----------- WARNING: CPU: 0 PID: 143192 at drivers/infiniband/core/rdma_core.c:874 uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] Modules linked in: tls target_core_user uio target_core_pscsi target_core_file target_core_iblock ib_srpt ib_srp scsi_transport_srp nfsd nfs_acl rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs 8021q garp mrp stp llc ext4 mbcache jbd2 opa_vnic ib_umad ib_ipoib sunrpc rdma_ucm ib_isert iscsi_target_mod target_core_mod ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm hfi1 intel_rapl_msr intel_rapl_common mgag200 qedr sb_edac drm_shmem_helper rdmavt x86_pkg_temp_thermal drm_kms_helper intel_powerclamp ib_uverbs coretemp i2c_algo_bit kvm_intel dell_wmi_descriptor ipmi_ssif sparse_keymap kvm ib_core rfkill syscopyarea sysfillrect video sysimgblt irqbypass ipmi_si ipmi_devintf fb_sys_fops rapl iTCO_wdt mxm_wmi iTCO_vendor_support intel_cstate pcspkr dcdbas intel_uncore ipmi_msghandler lpc_ich acpi_power_meter mei_me mei fuse drm xfs libcrc32c qede sd_mod ahci libahci t10_pi sg crct10dif_pclmul crc32_pclmul crc32c_intel qed libata tg3 ghash_clmulni_intel megaraid_sas crc8 wmi [last unloaded: ib_srpt] CPU: 0 PID: 143192 Comm: fi_rdm_tagged_p Kdump: loaded Not tainted 5.14.0-408.el9.x86_64 #1 Hardware name: Dell Inc. PowerEdge R430/03XKDV, BIOS 2.14.0 01/25/2022 RIP: 0010:uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] Code: 5d 41 5c 41 5d 41 5e e9 0f 26 1b dd 48 89 df e8 67 6a ff ff 49 8b 86 10 01 00 00 48 85 c0 74 9c 4c 89 e7 e8 83 c0 cb dd eb 92 <0f> 0b eb be 0f 0b be 04 00 00 00 48 89 df e8 8e f5 ff ff e9 6d ff RSP: 0018:ffffb7c6cadfbc60 EFLAGS: 00010286 RAX: ffff8f0889ee3f60 RBX: ffff8f088c1a5200 RCX: 00000000802a0016 RDX: 00000000802a0017 RSI: 0000000000000001 RDI: ffff8f0880042600 RBP: 0000000000000001 R08: 0000000000000001 R09: 0000000000000000 R10: ffff8f11fffd5000 R11: 0000000000039000 R12: ffff8f0d5b36cd80 R13: ffff8f088c1a5250 R14: ffff8f1206d91000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8f11d7c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000147069200e20 CR3: 00000001c7210002 CR4: 00000000001706f0 Call Trace: ? show_trace_log_lvl+0x1c4/0x2df ? show_trace_log_lvl+0x1c4/0x2df ? ib_uverbs_close+0x1f/0xb0 [ib_uverbs] ? uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] ? __warn+0x81/0x110 ? uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] ? report_bug+0x10a/0x140 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] ib_uverbs_close+0x1f/0xb0 [ib_uverbs] __fput+0x94/0x250 task_work_run+0x5c/0x90 do_exit+0x270/0x4a0 do_group_exit+0x2d/0x90 get_signal+0x87c/0x8c0 arch_do_signal_or_restart+0x25/0x100 ? ib_uverbs_ioctl+0xc2/0x110 [ib_uverbs] exit_to_user_mode_loop+0x9c/0x130 exit_to_user_mode_prepare+0xb6/0x100 syscall_exit_to_user_mode+0x12/0x40 do_syscall_64+0x69/0x90 ? syscall_exit_work+0x103/0x130 ? syscall_exit_to_user_mode+0x22/0x40 ? do_syscall_64+0x69/0x90 ? syscall_exit_work+0x103/0x130 ? syscall_exit_to_user_mode+0x22/0x40 ? do_syscall_64+0x69/0x90 ? do_syscall_64+0x69/0x90 ? common_interrupt+0x43/0xa0 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x1470abe3ec6b Code: Unable to access opcode bytes at RIP 0x1470abe3ec41. RSP: 002b:00007fff13ce9108 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: fffffffffffffffc RBX: 00007fff13ce9218 RCX: 00001470abe3ec6b RDX: 00007fff13ce9200 RSI: 00000000c0181b01 RDI: 0000000000000004 RBP: 00007fff13ce91e0 R08: 0000558d9655da10 R09: 0000558d9655dd00 R10: 00007fff13ce95c0 R11: 0000000000000246 R12: 00007fff13ce9358 R13: 0000000000000013 R14: 0000558d9655db50 R15: 00007fff13ce9470 --[ end trace 888a9b92e04c5c97 ]-- Fixes: df15856132bc ("RDMA/qedr: restructure functions that create/destroy QPs") Signed-off-by: Kamal Heib Link: https://lore.kernel.org/r/20240208223628.2040841-1-kheib@redhat.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/qedr/verbs.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 7887a6786ed4..f118ce0a9a61 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1879,8 +1879,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev, /* RQ - read access only (0) */ rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr, ureq.rq_len, true, 0, alloc_and_init); - if (rc) + if (rc) { + ib_umem_release(qp->usq.umem); + qp->usq.umem = NULL; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + qedr_free_pbl(dev, &qp->usq.pbl_info, + qp->usq.pbl_tbl); + } else { + kfree(qp->usq.pbl_tbl); + } return rc; + } } memset(&in_params, 0, sizeof(in_params)); -- cgit v1.2.3 From eb5c7465c3240151cd42a55c7ace9da0026308a1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 13 Feb 2024 11:07:13 +0100 Subject: RDMA/srpt: fix function pointer cast warnings clang-16 notices that srpt_qp_event() gets called through an incompatible pointer here: drivers/infiniband/ulp/srpt/ib_srpt.c:1815:5: error: cast from 'void (*)(struct ib_event *, struct srpt_rdma_ch *)' to 'void (*)(struct ib_event *, void *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict] 1815 | = (void(*)(struct ib_event *, void*))srpt_qp_event; Change srpt_qp_event() to use the correct prototype and adjust the argument inside of it. Fixes: a42d985bd5b2 ("ib_srpt: Initial SRP Target merge for v3.3-rc1") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20240213100728.458348-1-arnd@kernel.org Reviewed-by: Bart Van Assche Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/srpt/ib_srpt.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index d2dce6ce30a9..040234c01be4 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -214,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s) /** * srpt_qp_event - QP event callback function * @event: Description of the event that occurred. - * @ch: SRPT RDMA channel. + * @ptr: SRPT RDMA channel. */ -static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) +static void srpt_qp_event(struct ib_event *event, void *ptr) { + struct srpt_rdma_ch *ch = ptr; + pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n", event->event, ch, ch->sess_name, ch->qp->qp_num, get_ch_state_name(ch->state)); @@ -1811,8 +1813,7 @@ retry: ch->cq_size = ch->rq_size + sq_size; qp_init->qp_context = (void *)ch; - qp_init->event_handler - = (void(*)(struct ib_event *, void*))srpt_qp_event; + qp_init->event_handler = srpt_qp_event; qp_init->send_cq = ch->cq; qp_init->recv_cq = ch->cq; qp_init->sq_sig_type = IB_SIGNAL_REQ_WR; -- cgit v1.2.3