summaryrefslogtreecommitdiff
path: root/net/smc/smc_ib.c
AgeCommit message (Collapse)AuthorFilesLines
2023-04-06mm, treewide: redefine MAX_ORDER sanelyKirill A. Shutemov1-1/+1
MAX_ORDER currently defined as number of orders page allocator supports: user can ask buddy allocator for page order between 0 and MAX_ORDER-1. This definition is counter-intuitive and lead to number of bugs all over the kernel. Change the definition of MAX_ORDER to be inclusive: the range of orders user can ask from buddy allocator is 0..MAX_ORDER now. [kirill@shutemov.name: fix min() warning] Link: https://lkml.kernel.org/r/20230315153800.32wib3n5rickolvh@box [akpm@linux-foundation.org: fix another min_t warning] [kirill@shutemov.name: fixups per Zi Yan] Link: https://lkml.kernel.org/r/20230316232144.b7ic4cif4kjiabws@box.shutemov.name [akpm@linux-foundation.org: fix underlining in docs] Link: https://lore.kernel.org/oe-kbuild-all/202303191025.VRCTk6mP-lkp@intel.com/ Link: https://lkml.kernel.org/r/20230315113133.11326-11-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-18net/smc: Allow virtually contiguous sndbufs or RMBs for SMC-RWen Gu1-7/+8
On long-running enterprise production servers, high-order contiguous memory pages are usually very rare and in most cases we can only get fragmented pages. When replacing TCP with SMC-R in such production scenarios, attempting to allocate high-order physically contiguous sndbufs and RMBs may result in frequent memory compaction, which will cause unexpected hung issue and further stability risks. So this patch is aimed to allow SMC-R link group to use virtually contiguous sndbufs and RMBs to avoid potential issues mentioned above. Whether to use physically or virtually contiguous buffers can be set by sysctl smcr_buf_type. Note that using virtually contiguous buffers will bring an acceptable performance regression, which can be mainly divided into two parts: 1) regression in data path, which is brought by additional address translation of sndbuf by RNIC in Tx. But in general, translating address through MTT is fast. Taking 256KB sndbuf and RMB as an example, the comparisons in qperf latency and bandwidth test with physically and virtually contiguous buffers are as follows: - client: smc_run taskset -c <cpu> qperf <server> -oo msg_size:1:64K:*2\ -t 5 -vu tcp_{bw|lat} - server: smc_run taskset -c <cpu> qperf [latency] msgsize tcp smcr smcr-use-virt-buf 1 11.17 us 7.56 us 7.51 us (-0.67%) 2 10.65 us 7.74 us 7.56 us (-2.31%) 4 11.11 us 7.52 us 7.59 us ( 0.84%) 8 10.83 us 7.55 us 7.51 us (-0.48%) 16 11.21 us 7.46 us 7.51 us ( 0.71%) 32 10.65 us 7.53 us 7.58 us ( 0.61%) 64 10.95 us 7.74 us 7.80 us ( 0.76%) 128 11.14 us 7.83 us 7.87 us ( 0.47%) 256 10.97 us 7.94 us 7.92 us (-0.28%) 512 11.23 us 7.94 us 8.20 us ( 3.25%) 1024 11.60 us 8.12 us 8.20 us ( 0.96%) 2048 14.04 us 8.30 us 8.51 us ( 2.49%) 4096 16.88 us 9.13 us 9.07 us (-0.64%) 8192 22.50 us 10.56 us 11.22 us ( 6.26%) 16384 28.99 us 12.88 us 13.83 us ( 7.37%) 32768 40.13 us 16.76 us 16.95 us ( 1.16%) 65536 68.70 us 24.68 us 24.85 us ( 0.68%) [bandwidth] msgsize tcp smcr smcr-use-virt-buf 1 1.65 MB/s 1.59 MB/s 1.53 MB/s (-3.88%) 2 3.32 MB/s 3.17 MB/s 3.08 MB/s (-2.67%) 4 6.66 MB/s 6.33 MB/s 6.09 MB/s (-3.85%) 8 13.67 MB/s 13.45 MB/s 11.97 MB/s (-10.99%) 16 25.36 MB/s 27.15 MB/s 24.16 MB/s (-11.01%) 32 48.22 MB/s 54.24 MB/s 49.41 MB/s (-8.89%) 64 106.79 MB/s 107.32 MB/s 99.05 MB/s (-7.71%) 128 210.21 MB/s 202.46 MB/s 201.02 MB/s (-0.71%) 256 400.81 MB/s 416.81 MB/s 393.52 MB/s (-5.59%) 512 746.49 MB/s 834.12 MB/s 809.99 MB/s (-2.89%) 1024 1292.33 MB/s 1641.96 MB/s 1571.82 MB/s (-4.27%) 2048 2007.64 MB/s 2760.44 MB/s 2717.68 MB/s (-1.55%) 4096 2665.17 MB/s 4157.44 MB/s 4070.76 MB/s (-2.09%) 8192 3159.72 MB/s 4361.57 MB/s 4270.65 MB/s (-2.08%) 16384 4186.70 MB/s 4574.13 MB/s 4501.17 MB/s (-1.60%) 32768 4093.21 MB/s 4487.42 MB/s 4322.43 MB/s (-3.68%) 65536 4057.14 MB/s 4735.61 MB/s 4555.17 MB/s (-3.81%) 2) regression in buffer initialization and destruction path, which is brought by additional MR operations of sndbufs. But thanks to link group buffer reuse mechanism, the impact of this kind of regression decreases as times of buffer reuse increases. Taking 256KB sndbuf and RMB as an example, latency of some key SMC-R buffer-related function obtained by bpftrace are as follows: Function Phys-bufs Virt-bufs smcr_new_buf_create() 67154 ns 79164 ns smc_ib_buf_map_sg() 525 ns 928 ns smc_ib_get_memory_region() 162294 ns 161191 ns smc_wr_reg_send() 9957 ns 9635 ns smc_ib_put_memory_region() 203548 ns 198374 ns smc_ib_buf_unmap_sg() 508 ns 1158 ns ------------ Test environment notes: 1. Above tests run on 2 VMs within the same Host. 2. The NIC is ConnectX-4Lx, using SRIOV and passing through 2 VFs to the each VM respectively. 3. VMs' vCPUs are binded to different physical CPUs, and the binded physical CPUs are isolated by `isolcpus=xxx` cmdline. 4. NICs' queue number are set to 1. Signed-off-by: Wen Gu <guwen@linux.alibaba.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-07-18net/smc: optimize for smc_sndbuf_sync_sg_for_device and smc_rmb_sync_sg_for_cpuGuangguan Wang1-0/+29
Some CPU, such as Xeon, can guarantee DMA cache coherency. So it is no need to use dma sync APIs to flush cache on such CPUs. In order to avoid calling dma sync APIs on the IO path, use the dma_need_sync to check whether smc_buf_desc needs dma sync when creating smc_buf_desc. Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-05-18net/smc: send cdc msg inline if qp has sufficient inline spaceGuangguan Wang1-0/+1
As cdc msg's length is 44B, cdc msgs can be sent inline in most rdma devices, which can help reducing sending latency. In my test environment, which are 2 VMs running on the same physical host and whose NICs(ConnectX-4Lx) are working on SR-IOV mode, qperf shows 0.4us-0.7us improvement in latency. Test command: server: smc_run taskset -c 1 qperf client: smc_run taskset -c 1 qperf <server ip> -oo \ msg_size:1:2K:*2 -t 30 -vu tcp_lat The results shown below: msgsize before after 1B 11.9 us 11.2 us (-0.7 us) 2B 11.7 us 11.2 us (-0.5 us) 4B 11.7 us 11.3 us (-0.4 us) 8B 11.6 us 11.2 us (-0.4 us) 16B 11.7 us 11.3 us (-0.4 us) 32B 11.7 us 11.3 us (-0.4 us) 64B 11.7 us 11.2 us (-0.5 us) 128B 11.6 us 11.2 us (-0.4 us) 256B 11.8 us 11.2 us (-0.6 us) 512B 11.8 us 11.4 us (-0.4 us) 1KB 11.9 us 11.4 us (-0.5 us) 2KB 12.1 us 11.5 us (-0.6 us) Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com> Reviewed-by: Tony Lu <tonylu@linux.alibaba.com> Tested-by: kernel test robot <lkp@intel.com> Acked-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-31Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-nextDavid S. Miller1-0/+2
Alexei Starovoitov says: ==================== pull-request: bpf-next 2021-12-30 The following pull-request contains BPF updates for your *net-next* tree. We've added 72 non-merge commits during the last 20 day(s) which contain a total of 223 files changed, 3510 insertions(+), 1591 deletions(-). The main changes are: 1) Automatic setrlimit in libbpf when bpf is memcg's in the kernel, from Andrii. 2) Beautify and de-verbose verifier logs, from Christy. 3) Composable verifier types, from Hao. 4) bpf_strncmp helper, from Hou. 5) bpf.h header dependency cleanup, from Jakub. 6) get_func_[arg|ret|arg_cnt] helpers, from Jiri. 7) Sleepable local storage, from KP. 8) Extend kfunc with PTR_TO_CTX, PTR_TO_MEM argument support, from Kumar. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2021-12-29net: Don't include filter.h from net/sock.hJakub Kicinski1-0/+2
sock.h is pretty heavily used (5k objects rebuilt on x86 after it's touched). We can drop the include of filter.h from it and add a forward declaration of struct sk_filter instead. This decreases the number of rebuilt objects when bpf.h is touched from ~5k to ~1k. There's a lot of missing includes this was masking. Primarily in networking tho, this time. Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Marc Kleine-Budde <mkl@pengutronix.de> Acked-by: Florian Fainelli <f.fainelli@gmail.com> Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Link: https://lore.kernel.org/bpf/20211229004913.513372-1-kuba@kernel.org
2021-12-28net/smc: fix kernel panic caused by race of smc_sockDust Li1-2/+2
A crash occurs when smc_cdc_tx_handler() tries to access smc_sock but smc_release() has already freed it. [ 4570.695099] BUG: unable to handle page fault for address: 000000002eae9e88 [ 4570.696048] #PF: supervisor write access in kernel mode [ 4570.696728] #PF: error_code(0x0002) - not-present page [ 4570.697401] PGD 0 P4D 0 [ 4570.697716] Oops: 0002 [#1] PREEMPT SMP NOPTI [ 4570.698228] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.16.0-rc4+ #111 [ 4570.699013] Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 8c24b4c 04/0 [ 4570.699933] RIP: 0010:_raw_spin_lock+0x1a/0x30 <...> [ 4570.711446] Call Trace: [ 4570.711746] <IRQ> [ 4570.711992] smc_cdc_tx_handler+0x41/0xc0 [ 4570.712470] smc_wr_tx_tasklet_fn+0x213/0x560 [ 4570.712981] ? smc_cdc_tx_dismisser+0x10/0x10 [ 4570.713489] tasklet_action_common.isra.17+0x66/0x140 [ 4570.714083] __do_softirq+0x123/0x2f4 [ 4570.714521] irq_exit_rcu+0xc4/0xf0 [ 4570.714934] common_interrupt+0xba/0xe0 Though smc_cdc_tx_handler() checked the existence of smc connection, smc_release() may have already dismissed and released the smc socket before smc_cdc_tx_handler() further visits it. smc_cdc_tx_handler() |smc_release() if (!conn) | | |smc_cdc_tx_dismiss_slots() | smc_cdc_tx_dismisser() | |sock_put(&smc->sk) <- last sock_put, | smc_sock freed bh_lock_sock(&smc->sk) (panic) | To make sure we won't receive any CDC messages after we free the smc_sock, add a refcount on the smc_connection for inflight CDC message(posted to the QP but haven't received related CQE), and don't release the smc_connection until all the inflight CDC messages haven been done, for both success or failed ones. Using refcount on CDC messages brings another problem: when the link is going to be destroyed, smcr_link_clear() will reset the QP, which then remove all the pending CQEs related to the QP in the CQ. To make sure all the CQEs will always come back so the refcount on the smc_connection can always reach 0, smc_ib_modify_qp_reset() was replaced by smc_ib_modify_qp_error(). And remove the timeout in smc_wr_tx_wait_no_pending_sends() since we need to wait for all pending WQEs done, or we may encounter use-after- free when handling CQEs. For IB device removal routine, we need to wait for all the QPs on that device been destroyed before we can destroy CQs on the device, or the refcount on smc_connection won't reach 0 and smc_sock cannot be released. Fixes: 5f08318f617b ("smc: connection data control (CDC)") Reported-by: Wen Gu <guwen@linux.alibaba.com> Signed-off-by: Dust Li <dust.li@linux.alibaba.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16net/smc: stop links when their GID is removedKarsten Graul1-0/+53
With SMC-Rv2 the GID is an IP address that can be deleted from the device. When an IB_EVENT_GID_CHANGE event is provided then iterate over all active links and check if their GID is still defined. Otherwise stop the affected link. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16net/smc: add v2 support to the work request layerKarsten Graul1-1/+2
In the work request layer define one large v2 buffer for each link group that is used to transmit and receive large LLC control messages. Add the completion queue handling for this buffer. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16net/smc: retrieve v2 gid from IB deviceKarsten Graul1-13/+64
In smc_ib.c, scan for RoCE devices that support UDP encapsulation. Find an eligible device and check that there is a route to the remote peer. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16net/smc: add SMC-Rv2 connection establishmentKarsten Graul1-0/+27
Send a CLC proposal message, and the remote side process this type of message and determine the target GID. Check for a valid route to this GID, and complete the connection establishment. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-05net: Remove redundant if statementsYajun Deng1-2/+1
The 'if (dev)' statement already move into dev_{put , hold}, so remove redundant if statements. Signed-off-by: Yajun Deng <yajun.deng@linux.dev> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-01-13net/smc: use memcpy instead of snprintf to avoid out of bounds readGuvenc Gulce1-3/+3
Using snprintf() to convert not null-terminated strings to null terminated strings may cause out of bounds read in the source string. Therefore use memcpy() and terminate the target string with a null afterwards. Fixes: a3db10efcc4c ("net/smc: Add support for obtaining SMCR device list") Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-17net/smc: fix access to parent of an ib deviceKarsten Graul1-13/+23
The parent of an ib device is used to retrieve the PCI device attributes. It turns out that there are possible cases when an ib device has no parent set in the device structure, which may lead to page faults when trying to access this memory. Fix that by checking the parent pointer and consolidate the pci device specific processing in a new function. Fixes: a3db10efcc4c ("net/smc: Add support for obtaining SMCR device list") Reported-by: syzbot+600fef7c414ee7e2d71b@syzkaller.appspotmail.com Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Link: https://lore.kernel.org/r/20201215091058.49354-2-kgraul@linux.ibm.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-02net/smc: Add support for obtaining SMCR device listGuvenc Gulce1-0/+156
Deliver SMCR device information via netlink based diagnostic interface. Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-02net/smc: Add diagnostic information to smc ib-deviceGuvenc Gulce1-0/+44
During smc ib-device creation, add network device ifindex to smc ib-device structure. Register for netdevice changes and update ib-device accordingly. This is needed for diagnostic purposes. Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-19net/smc: fix direct access to ib_gid_addr->ndev in smc_ib_determine_gid()Karsten Graul1-3/+3
Sparse complaints 3 times about: net/smc/smc_ib.c:203:52: warning: incorrect type in argument 1 (different address spaces) net/smc/smc_ib.c:203:52: expected struct net_device const *dev net/smc/smc_ib.c:203:52: got struct net_device [noderef] __rcu *const ndev Fix that by using the existing and validated ndev variable instead of accessing attr->ndev directly. Fixes: 5102eca9039b ("net/smc: Use rdma_read_gid_l2_fields to L2 fields") Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-07-20net/smc: protect smc ib device initializationKarsten Graul1-3/+13
Before an smc ib device is used the first time for an smc link it is lazily initialized. When there are 2 active link groups and a new ib device is brought online then it might happen that 2 link creations run in parallel and enter smc_ib_setup_per_ibdev(). Both allocate new send and receive completion queues on the device, but only one set of them keeps assigned and the other leaks. Fix that by protecting the setup and cleanup code using a mutex. Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Fixes: f3c1deddb21c ("net/smc: separate function for link initialization") Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-08net/smc: fix sleep bug in smc_pnet_find_roce_resource()Ursula Braun1-5/+6
Tests showed this BUG: [572555.252867] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:935 [572555.252876] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 131031, name: smcapp [572555.252879] INFO: lockdep is turned off. [572555.252883] CPU: 1 PID: 131031 Comm: smcapp Tainted: G O 5.7.0-rc3uschi+ #356 [572555.252885] Hardware name: IBM 3906 M03 703 (LPAR) [572555.252887] Call Trace: [572555.252896] [<00000000ac364554>] show_stack+0x94/0xe8 [572555.252901] [<00000000aca1f400>] dump_stack+0xa0/0xe0 [572555.252906] [<00000000ac3c8c10>] ___might_sleep+0x260/0x280 [572555.252910] [<00000000acdc0c98>] __mutex_lock+0x48/0x940 [572555.252912] [<00000000acdc15c2>] mutex_lock_nested+0x32/0x40 [572555.252975] [<000003ff801762d0>] mlx5_lag_get_roce_netdev+0x30/0xc0 [mlx5_core] [572555.252996] [<000003ff801fb3aa>] mlx5_ib_get_netdev+0x3a/0xe0 [mlx5_ib] [572555.253007] [<000003ff80063848>] smc_pnet_find_roce_resource+0x1d8/0x310 [smc] [572555.253011] [<000003ff800602f0>] __smc_connect+0x1f0/0x3e0 [smc] [572555.253015] [<000003ff80060634>] smc_connect+0x154/0x190 [smc] [572555.253022] [<00000000acbed8d4>] __sys_connect+0x94/0xd0 [572555.253025] [<00000000acbef620>] __s390x_sys_socketcall+0x170/0x360 [572555.253028] [<00000000acdc6800>] system_call+0x298/0x2b8 [572555.253030] INFO: lockdep is turned off. Function smc_pnet_find_rdma_dev() might be called from smc_pnet_find_roce_resource(). It holds the smc_ib_devices list spinlock while calling infiniband op get_netdev(). At least for mlx5 the get_netdev operation wants mutex serialization, which conflicts with the smc_ib_devices spinlock. This patch switches the smc_ib_devices spinlock into a mutex to allow sleeping when calling get_netdev(). Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client") Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-06Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdmaLinus Torvalds1-8/+5
Pull rdma updates from Jason Gunthorpe: "A more active cycle than most of the recent past, with a few large, long discussed works this time. The RNBD block driver has been posted for nearly two years now, and flowing through RDMA due to it also introducing a new ULP. The removal of FMR has been a recurring discussion theme for a long time. And the usual smattering of features and bug fixes. Summary: - Various small driver bugs fixes in rxe, mlx5, hfi1, and efa - Continuing driver cleanups in bnxt_re, hns - Big cleanup of mlx5 QP creation flows - More consistent use of src port and flow label when LAG is used and a mlx5 implementation - Additional set of cleanups for IB CM - 'RNBD' network block driver and target. This is a network block RDMA device specific to ionos's cloud environment. It brings strong multipath and resiliency capabilities. - Accelerated IPoIB for HFI1 - QP/WQ/SRQ ioctl migration for uverbs, and support for multiple async fds - Support for exchanging the new IBTA defiend ECE data during RDMA CM exchanges - Removal of the very old and insecure FMR interface from all ULPs and drivers. FRWR should be preferred for at least a decade now" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (247 commits) RDMA/cm: Spurious WARNING triggered in cm_destroy_id() RDMA/mlx5: Return ECE DC support RDMA/mlx5: Don't rely on FW to set zeros in ECE response RDMA/mlx5: Return an error if copy_to_user fails IB/hfi1: Use free_netdev() in hfi1_netdev_free() RDMA/hns: Uninitialized variable in modify_qp_init_to_rtr() RDMA/core: Move and rename trace_cm_id_create() IB/hfi1: Fix hfi1_netdev_rx_init() error handling RDMA: Remove 'max_map_per_fmr' RDMA: Remove 'max_fmr' RDMA/core: Remove FMR device ops RDMA/rdmavt: Remove FMR memory registration RDMA/mthca: Remove FMR support for memory registration RDMA/mlx4: Remove FMR support for memory registration RDMA/i40iw: Remove FMR leftovers RDMA/bnxt_re: Remove FMR leftovers RDMA/mlx5: Remove FMR leftovers RDMA/core: Remove FMR pool API RDMA/rds: Remove FMR support for memory registration RDMA/srp: Remove support for FMR memory registration ...
2020-05-06RDMA: Allow ib_client's to fail when add() is calledJason Gunthorpe1-6/+4
When a client is added it isn't allowed to fail, but all the client's have various failure paths within their add routines. This creates the very fringe condition where the client was added, failed during add and didn't set the client_data. The core code will then still call other client_data centric ops like remove(), rename(), get_nl_info(), and get_net_dev_by_params() with NULL client_data - which is confusing and unexpected. If the add() callback fails, then do not call any more client ops for the device, even remove. Remove all the now redundant checks for NULL client_data in ops callbacks. Update all the add() callbacks to return error codes appropriately. EOPNOTSUPP is used for cases where the ULP does not support the ib_device - eg because it only works with IB. Link: https://lore.kernel.org/r/20200421172440.387069-1-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Acked-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-05net/smc: log important pnetid and state change eventsKarsten Graul1-0/+11
Print to system log when SMC links are available or go down, link group state changes or pnetids are applied to and removed from devices. The log entries are triggered by either user configuration actions or adapter activation/deactivation events and are not expected to happen often. The entries help SMC users to keep track of the SMC link group status and to detect when actions are needed (like to add replacements for failed adapters). Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-02net/smc: add smcr_port_err() and smcr_link_down() processingKarsten Graul1-1/+1
Call smcr_port_err() when an IB event reports an inactive IB device. smcr_port_err() calls smcr_link_down() for all affected links. smcr_link_down() either triggers the local DELETE_LINK processing, or sends an DELETE_LINK LLC message to the SMC server to initiate the processing. The old handler function smc_port_terminate() is removed. Add helper smcr_link_down_cond() to take a link down conditionally, and smcr_link_down_cond_sched() to schedule the link_down processing to a work. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-02net/smc: add smcr_port_add() and smcr_link_up() processingKarsten Graul1-0/+1
Call smcr_port_add() when an IB event reports a new active IB device. smcr_port_add() will start a work which either triggers the local ADD_LINK processing, or send an ADD_LINK LLC message to the SMC server to initiate the processing. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-29net/smc: convert static link ID to dynamic referencesKarsten Graul1-29/+29
As a preparation for the support of multiple links remove the usage of a static link id (SMC_SINGLE_LINK) and allow dynamic link ids. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-29net/smc: rework pnet table to support SMC-R failoverKarsten Graul1-2/+3
The pnet table stored pnet ids in the smc device structures. When a device is going down its smc device structure is freed, and when the device is brought online again it no longer has a pnet id set. Rework the pnet table implementation to store the device name with their assigned pnet id and apply the pnet id to devices when they are registered. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-14RDMA: Remove a few extra calls to ib_get_client_data()Jason Gunthorpe1-2/+1
These four places already have easy access to the client data, just use that instead. Link: https://lore.kernel.org/r/0-v1-fae83f600b4a+68-less_get_client_data%25jgg@mellanox.com Acked-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-13Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netDavid S. Miller1-0/+1
Minor overlapping changes, nothing serious. Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-11net/smc: cancel event worker during device removalKarsten Graul1-0/+1
During IB device removal, cancel the event worker before the device structure is freed. Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client") Reported-by: syzbot+b297c6825752e7a07272@syzkaller.appspotmail.com Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Reviewed-by: Ursula Braun <ubraun@linux.ibm.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-28Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netDavid S. Miller1-0/+2
The mptcp conflict was overlapping additions. The SMC conflict was an additional and removal happening at the same time. Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-27net/smc: check for valid ib_client_dataKarsten Graul1-0/+2
In smc_ib_remove_dev() check if the provided ib device was actually initialized for SMC before. Reported-by: syzbot+84484ccebdd4e5451d91@syzkaller.appspotmail.com Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client") Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-27net/smc: improve peer ID in CLC decline for SMC-RHans Wippel1-1/+1
According to RFC 7609, all CLC messages contain a peer ID that consists of a unique instance ID and the MAC address of one of the host's RoCE devices. But if a SMC-R connection cannot be established, e.g., because no matching pnet table entry is found, the current implementation uses a zero value in the CLC decline message although the host's peer ID is set to a proper value. If no RoCE and no ISM device is usable for a connection, there is no LGR and the LGR check in smc_clc_send_decline() prevents that the peer ID is copied into the CLC decline message for both SMC-D and SMC-R. So, this patch modifies the check to also accept the case of no LGR. Also, only a valid peer ID is copied into the decline message. Signed-off-by: Hans Wippel <ndev@hwipl.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-27net/smc: rework peer ID handlingHans Wippel1-7/+12
This patch initializes the peer ID to a random instance ID and a zero MAC address. If a RoCE device is in the host, the MAC address part of the peer ID is overwritten with the respective address. Also, a function for checking if the peer ID is valid is added. A peer ID is considered valid if the MAC address part contains a non-zero MAC address. Signed-off-by: Hans Wippel <ndev@hwipl.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-18net/smc: reduce port_event schedulingUrsula Braun1-15/+29
IB event handlers schedule the port event worker for further processing of port state changes. This patch reduces the number of schedules to avoid duplicate processing of the same port change. Reviewed-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-16net/smc: introduce bookkeeping of SMCR link groupsUrsula Braun1-1/+3
If the smc module is unloaded return control from exit routine only, if all link groups are freed. If an IB device is thrown away return control from device removal only, if all link groups belonging to this device are freed. Counters for the total number of SMCR link groups and for the total number of SMCR links per IB device are introduced. smc module unloading continues only if the total number of SMCR link groups is zero. IB device removal continues only it the total number of SMCR links per IB device has decreased to zero. Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-15net/smc: immediate termination for SMCR link groupsUrsula Braun1-1/+2
If the SMC module is unloaded or an IB device is thrown away, the immediate link group freeing introduced for SMCD is exploited for SMCR as well. That means SMCR-specifics are added to smc_conn_kill(). Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-15net/smc: wait for tx completions before link freeingUrsula Braun1-1/+1
Make sure all pending work requests are completed before freeing a link. Dismiss tx pending slots already when terminating a link group to exploit termination shortcut in tx completion queue handler. And kill the completion queue tasklets after destroy of the completion queues, otherwise there is a time window for another tasklet schedule of an already killed tasklet. Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-10net/smc: no new connections on disappearing devicesUrsula Braun1-2/+13
Add a "going_away" indication to ISM devices and IB ports and avoid creation of new connections on such disappearing devices. And do not handle ISM events if ISM device is disappearing. Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
2019-05-03net/smc: Use rdma_read_gid_l2_fields to L2 fieldsParav Pandit1-8/+8
Use core provided API to fill the source MAC address and use rdma_read_gid_attr_ndev_rcu() to get stable netdev. This is preparation patch to allow gid attribute to become NULL when associated net device is removed. Signed-off-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-02-21net/smc: rework pnet tableHans Wippel1-1/+0
If a device does not have a pnetid, users can set a temporary pnetid for said device in the pnet table. This patch reworks the pnet table to make it more flexible. Multiple entries with the same pnetid but differing devices are now allowed. Additionally, the netlink interface now sends each mapping from pnetid to device separately to the user while maintaining the message format existing applications might expect. Also, the SMC data structure for ib devices already has a pnetid attribute. So, it is used to store the user defined pnetids. As a result, the pnet table entries are only used for netdevs. Signed-off-by: Hans Wippel <hwippel@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-12net/smc: check port_idx of ib eventKarsten Graul1-8/+16
For robustness protect of higher port numbers than expected to avoid setting bits behind our port_event_mask. In case of an DEVICE_FATAL event all ports must be checked. The IB_EVENT_GID_CHANGE event is provided in the global event handler, so handle it there. And handle a QP_FATAL event instead of an DEVICE_FATAL event in the qp handler. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-02net/smc: use device link provided in qp_contextKarsten Graul1-3/+3
The device field of the IB event structure does not always point to the SMC IB device. Load the pointer from the qp_context which is always provided to smc_ib_qp_event_handler() in the priv field. And for qp events the affected port is given in the qp structure of the ibevent, derive it from there. Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-18RDMA/smc: Replace ib_query_gid with rdma_get_gid_attrJason Gunthorpe1-23/+25
All RDMA ULPs should be using rdma_get_gid_attr instead of ib_query_gid. Convert SMC to use the new API. In the process correct some confusion with gid_type - if attr->ndev is !NULL then gid_type can never be IB_GID_TYPE_IB by definition. IB_GID_TYPE_ROCE shares the same enum value and is probably what was intended here. Reviewed-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-08-16Merge branch 'linus/master' into rdma.git for-nextJason Gunthorpe1-63/+107
rdma.git merge resolution for the 4.19 merge window Conflicts: drivers/infiniband/core/rdma_core.c - Use the rdma code and revise with the new spelling for atomic_fetch_add_unless drivers/nvme/host/rdma.c - Replace max_sge with max_send_sge in new blk code drivers/nvme/target/rdma.c - Use the blk code and revise to use NULL for ib_post_recv when appropriate - Replace max_sge with max_recv_sge in new blk code net/rds/ib_send.c - Use the net code and revise to use NULL for ib_post_recv when appropriate Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-08-16Revert "net/smc: Replace ib_query_gid with rdma_get_gid_attr"Jason Gunthorpe1-14/+10
This reverts commit ddb457c6993babbcdd41fca638b870d2a2fc3941. The include rdma/ib_cache.h is kept, and we have to add a memset to the compat wrapper to avoid compiler warnings in gcc-7 This revert is done to avoid extensive merge conflicts with SMC changes in netdev during the 4.19 merge window. Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-07-26net/smc: use correct vlan gid of RoCE deviceUrsula Braun1-5/+36
SMC code uses the base gid for VLAN traffic. The gids exchanged in the CLC handshake and the gid index used for the QP have to switch from the base gid to the appropriate vlan gid. When searching for a matching IB device port for a certain vlan device, it does not make sense to return an IB device port, which is not enabled for the used vlan_id. Add another check whether a vlan gid exists for a certain IB device port. Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-23net/smc: add function to get link group from linkStefan Raspl1-2/+1
Replace a frequently used construct with a more readable variant, reducing the code. Also might come handy when we start to support more than a single per link group. Signed-off-by: Stefan Raspl <raspl@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-30net/smc: add pnetid supportUrsula Braun1-1/+5
s390 hardware supports the definition of a so-call Physical NETwork IDentifier (short PNETID) per network device port. These PNETIDS can be used to identify network devices that are attached to the same physical network (broadcast domain). On s390 try to use the PNETID of the ethernet device port used for initial connecting, and derive the IB device port used for SMC RDMA traffic. On platforms without PNETID support fall back to the existing solution of a configured pnet table. Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-30net/smc: determine port attributes independent from pnet tableUrsula Braun1-60/+70
For SMC it is important to know the current port state of RoCE devices. Monitoring port states has been triggered, when a RoCE device was added to the pnet table. To support future alternatives to the pnet table the monitoring of ports is made independent of the existence of a pnet table. It starts once the smc_ib_device is established. Due to this change smc_ib_remember_port_attr() is now a local function and shuffling its location and the location of its used functions makes any forward references obsolete. And the duplicate SMC_MAX_PORTS definition is removed. Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-18net/smc: Replace ib_query_gid with rdma_get_gid_attrParav Pandit1-10/+15
Push the copy of the gid_attr into the SMC code. This probably doesn't push it far enough, as it looks like the conn->lgr should potentially hold the reference for its lifetime. Signed-off-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>