aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox (follow)
AgeCommit message (Collapse)AuthorFilesLines
2016-11-14mlxsw: spectrum_router: Flush FIB tables during finiIdo Schimmel1-2/+12
Since commit b45f64d16d45 ("mlxsw: spectrum_router: Use FIB notifications instead of switchdev calls") we reflect to the device the entire FIB table and not only FIBs that point to netdevs created by the driver. During module removal, FIBs of the second type are removed following NETDEV_UNREGISTER events sent. The other FIBs are still present in both the driver's cache and the device's table. Fix this by iterating over all the FIB tables in the device and flush them. There's no need to take locks, as we're the only writer. Fixes: b45f64d16d45 ("mlxsw: spectrum_router: Use FIB notifications instead of switchdev calls") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-13mlxsw: spectrum_router: Correctly dump neighbour activityArkadi Sharshevsky1-1/+21
The device's neighbour table is periodically dumped in order to update the kernel about active neighbours. A single dump session may span multiple queries, until the response carries less records than requested or when a record (can contain up to four neighbour entries) is not full. Current code stops the session when the number of returned records is zero, which can result in infinite loop in case of high packet rate. Fix this by stopping the session according to the above logic. Fixes: c723c735fa6b ("mlxsw: spectrum_router: Periodically update the kernel's neigh table") Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com> Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-13mlxsw: spectrum: Fix refcount bug on span entriesYotam Gigi1-1/+3
When binding port to a newly created span entry, its refcount is initialized to zero even though it has a bound port. That leads to unexpected behaviour when the user tries to delete that port from the span entry. Fix this by initializing the reference count to 1. Also add a warning to put function. Fixes: 763b4b70afcd ("mlxsw: spectrum: Add support in matchall mirror TC offloading") Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-10mlxsw: spectrum_router: Ignore FIB notification events for non-init namespacesJiri Pirko1-0/+3
Since now, the table with same id in multiple netnamespaces were squashed to a single virtual router. That is not only incorrect, it also causes error messages when trying to use RALUE register to do double remove of FIB entries, like this one: mlxsw_spectrum 0000:03:00.0: EMAD reg access failed (tid=facb831c00007b20,reg_id=8013(ralue),type=write,status=7(bad parameter)) Since we don't allow ports to change namespaces (NETIF_F_NETNS_LOCAL), and the infrastructure is not yet prepared to handle netnamespaces, just ignore FIB notification events for non-init namespaces. That is clear to do since we don't need to offload them. Fixes: b45f64d16d45 ("mlxsw: spectrum_router: Use FIB notifications instead of switchdev calls") Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-10mlxsw: spectrum_router: Fix handling of neighbour structureJiri Pirko1-61/+34
__neigh_create function works in a different way than assumed. It passes "n" as a parameter to ndo_neigh_construct. But this "n" might be destroyed right away before __neigh_create() returns in case there is already another neighbour struct in the hashtable with the same dev and primary key. That is not expected by mlxsw_sp_router_neigh_construct() and the stored "n" points to freed memory, eventually leading to crash. Fix this by doing tight 1:1 coupling between neighbour struct and internal driver neigh_entry. That allows to narrow down the key in internal driver hashtable to do lookups by "n" only. Fixes: 6cf3c971dc84 ("mlxsw: spectrum_router: Add private neigh table") Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-09Revert "net/mlx4_en: Fix panic during reboot"Tariq Toukan1-1/+0
This reverts commit 9d2afba058722d40cc02f430229c91611c0e8d16. The original issue would possibly exist if an external module tried calling our "ethtool_ops" without checking if it still exists. The right way of solving it is by simply doing the check in the caller side. Currently, no action is required as there's no such use case. Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04net/mlx5: Fix invalid pointer reference when prof_sel parameter is invalidHuy Nguyen1-2/+3
When prof_sel is invalid, mlx5_core_warn is called but the mlx5_core_dev is not initialized yet. Solution is moving the prof_sel code after dev->pdev assignment Fixes: 2974ab6e8bd8 ('net/mlx5: Improve driver log messages') Signed-off-by: Huy Nguyen <huyn@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04net/mlx5: E-Switch, Set the actions for offloaded rules properlyOr Gerlitz1-1/+2
As for the current generation of the mlx5 HW (CX4/CX4-Lx) per flow vlan push/pop actions are emulated, we must not program them to the firmware. Fixes: f5f82476090f ('net/mlx5: E-Switch, Support VLAN actions in the offloads mode') Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Reported-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04net/mlx5e: Handle matching on vlan priority for offloaded TC rulesOr Gerlitz1-1/+4
We ignored the vlan priority in offloaded TC rules matching part, fix that. Fixes: 095b6cfd69ce ('net/mlx5e: Add TC vlan match parsing') Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Reported-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04net/mlx5e: Disallow changing name-space for VF representorsOr Gerlitz1-1/+1
VF reps should be altogether on the same NS as they were created. Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04net/mlx5e: Re-arrange XDP SQ/CQ creationSaeed Mahameed1-17/+15
In mlx5e_open_channel CQs must be created before napi is enabled. Here we move the XDP CQ creation to satisfy that fact. mlx5e_close_channel is already working according to the right order. Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04net/mlx5e: Fix XDP error path of mlx5e_open_channel()Saeed Mahameed1-1/+4
In case of mlx5e_open_rq fails the error handling will jump to label err_close_xdp_sq and will try to close the xdp_sq unconditionally. xdp_sq is valid only in case of XDP use cases, i.e priv->xdp_prog is not null. To fix this in this patch we test xdp_sq validity prior to closing it. In addition we now close the xdp_sq.cq as well. Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-01net/mlx5: Simplify a testChristophe Jaillet1-1/+1
'create_root_ns()' does not return an error pointer, so the test can be simplified to be more consistent. Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Acked-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-31mlxsw: spectrum: Fix incorrect reuse of MID entriesIdo Schimmel2-8/+8
In the device, a MID entry represents a group of local ports, which can later be bound to a MDB entry. The lookup of an existing MID entry is currently done using the provided MC MAC address and VID, from the Linux bridge. However, this can result in an incorrect reuse of the same MID index in different VLAN-unaware bridges (same IP MC group and VID 0). Fix this by performing the lookup based on FID instead of VID, which is unique across different bridges. Fixes: 3a49b4fde2a1 ("mlxsw: Adding layer 2 multicast support") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Acked-by: Elad Raz <eladr@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_en: Save slave ethtool stats commandTariq Toukan1-2/+3
Following the previous patch, as an optimization, the slave will not even bother sending the DUMP_ETH_STATS command over the comm channel. Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_en: Fix potential deadlock in port statistics flowJack Morgenstein3-16/+3
mlx4_en_DUMP_ETH_STATS took the *counter mutex* and then called the FW command, with WRAPPED attribute. As a result, the fw command is wrapped on the Hypervisor when it calls mlx4_en_DUMP_ETH_STATS. The FW command wrapper flow on the hypervisor takes the *slave_cmd_mutex* during processing. At the same time, a VF could be in the process of coming up, and could call mlx4_QUERY_FUNC_CAP. On the hypervisor, the command flow takes the *slave_cmd_mutex*, then executes mlx4_QUERY_FUNC_CAP_wrapper. mlx4_QUERY_FUNC_CAP wrapper calls mlx4_get_default_counter_index(), which takes the *counter mutex*. DEADLOCK. The fix is that the DUMP_ETH_STATS fw command should be called with the NATIVE attribute, so that on the hypervisor, this command does not enter the wrapper flow. Since the Hypervisor no longer goes through the wrapper code, we also simply return 0 in mlx4_DUMP_ETH_STATS_wrapper (i.e.the function succeeds, but the returned data will be all zeroes). No need to test if it is the Hypervisor going through the wrapper. Fixes: f9baff509f8a ("mlx4_core: Add "native" argument to mlx4_cmd ...") Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4: Fix firmware command timeout during interrupt testEugenia Emantayev2-35/+53
Currently interrupt test that is part of ethtool selftest runs the check over all interrupt vectors of the device. In mlx4_en package part of interrupt vectors are uninitialized since mlx4_ib doesn't exist. This causes NOP FW command to time out. Change logic to test current port interrupt vectors only. Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_core: Do not access comm channel if it has not yet been initializedJack Morgenstein1-0/+9
In the Hypervisor, there are several FW commands which are invoked before the comm channel is initialized (in mlx4_multi_func_init). These include MOD_STAT_CONFIG, QUERY_DEV_CAP, INIT_HCA, and others. If any of these commands fails, say with a timeout, the Hypervisor driver enters the internal error reset flow. In this flow, the driver attempts to notify all slaves via the comm channel that an internal error has occurred. Since the comm channel has not yet been initialized (i.e., mapped via ioremap), this will cause dereferencing a NULL pointer. To fix this, do not access the comm channel in the internal error flow if it has not yet been initialized. Fixes: 55ad359225b2 ("net/mlx4_core: Enable device recovery flow with SRIOV") Fixes: ab9c17a009ee ("mlx4_core: Modify driver initialization flow to accommodate SRIOV for Ethernet") Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_en: Fix panic during rebootEugenia Emantayev1-0/+1
Fix a kernel panic that occurs as a result of an asynchronous event handled in roce_gid_mgmt: mlx4_en_get_drvinfo is called and accesses freed resources. This happens in a shutdown flow only, since pci device is destroyed while netdevice is still alive. Fixes: c27a02cd94d6 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC") Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_en: Process all completions in RX rings after port goes upErez Shitrit1-0/+7
Currently there is a race between incoming traffic and initialization flow. HW is able to receive the packets after INIT_PORT is done and unicast steering is configured. Before we set priv->port_up NAPI is not scheduled and receive queues become full. Therefore we never get new interrupts about the completions. This issue could happen if running heavy traffic during bringing port up. The resolution is to schedule NAPI once port_up is set. If receive queues were full this will process all cqes and release them. Fixes: c27a02cd94d6 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC") Signed-off-by: Erez Shitrit <erezsh@mellanox.com> Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_en: Resolve dividing by zero in 32-bit systemEugenia Emantayev1-1/+4
When doing roundup_pow_of_two for large enough number with bit 31, an overflow will occur and a value equal to 1 will be returned. In this case 1 will be subtracted from the return value and division by zero will be reached. Fixes: 31c128b66e5b ("net/mlx4_en: Choose time-stamping shift value according to HW frequency") Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_core: Change the default value of enable_qosMoshe Lazer1-2/+2
Change the default status of quality of service back to disabled, as it hurts performance in some cases. Fixes: 38438f7c7e8c ("net/mlx4: Set enhanced QoS support by default when ...") Signed-off-by: Moshe Lazer <moshel@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_core: Avoid setting ports to auto when only one port type is supportedMaor Gottlieb1-1/+9
When only one port type is supported, it should be read only. We reject changing requests, even to the auto sense mode. Fixes: 27bf91d6a0d5 ("mlx4_core: Add link type autosensing") Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moshe Shemesh <moshe@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx4_core: Fix the resource-type enum in res tracker to conform to FW specJack Morgenstein1-1/+2
The resource type enum in the resource tracker was incorrect. RES_EQ was put in the position of RES_NPORT_ID (a FC resource). Since the remaining resources maintain their current values, and RES_EQ is not passed from slaves to the hypervisor in any FW command, this change affects only the hypervisor. Therefore, there is no backwards-compatibility issue. Fixes: 623ed84b1f95 ("mlx4_core: initial header-file changes for SRIOV support") Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Moshe Shemesh <moshe@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29IB/mlx4: avoid a -Wmaybe-uninitialize warningArnd Bergmann1-2/+3
There is an old warning about mlx4_SW2HW_EQ_wrapper on x86: ethernet/mellanox/mlx4/resource_tracker.c: In function ‘mlx4_SW2HW_EQ_wrapper’: ethernet/mellanox/mlx4/resource_tracker.c:3071:10: error: ‘eq’ may be used uninitialized in this function [-Werror=maybe-uninitialized] The problem here is that gcc won't track the state of the variable across a spin_unlock. Moving the assignment out of the lock is safe here and avoids the warning. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Avoid passing dma address 0 to firmwareNoa Osherovich1-8/+18
Currently the firmware can't work with a page with dma address 0. Passing such an address to the firmware will cause the give_pages command to fail. To avoid this, in case we get a 0 dma address of a page from the dma engine, we avoid passing it to FW by remapping to get an address other than 0. Fixes: bf0bf77f6519 ('mlx5: Support communicating arbitrary host...') Signed-off-by: Noa Osherovich <noaos@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: PCI error recovery health care simulationMohamad Haj Yahia3-9/+55
In case that the kernel PCI error handlers are not called, we will trigger our own recovery flow. The health work will give priority to the kernel pci error handlers to recover the PCI by waiting for a small period, if the pci error handlers are not triggered the manual recovery flow will be executed. We don't save pci state in case of manual recovery because it will ruin the pci configuration space and we will lose dma sync. Fixes: 89d44f0a6c73 ('net/mlx5_core: Add pci error handlers to mlx5_core driver') Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Fix race between PCI error handlers and health workMohamad Haj Yahia2-5/+34
Currently there is a race between the health care work and the kernel pci error handlers because both of them detect the error, the first one to be called will do the error handling. There is a chance that health care will disable the pci after resuming pci slot. Also create a separate WQ because now we will have two types of health works, one for the error detection and one for the recovery. Fixes: 89d44f0a6c73 ('net/mlx5_core: Add pci error handlers to mlx5_core driver') Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Clear health sick bit when starting health pollMohamad Haj Yahia1-0/+1
The health sick status should be cleared when we start the health poll. This is crucial for driver reload (unload + load) in order to behave right in case of health issue. Fixes: fd76ee4da55a ('net/mlx5_core: Fix internal error detection conditions') Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Change the acl enable prototype to return statusMohamad Haj Yahia1-16/+34
The Ingress/Egress ACL enable function may fail and it should return status to its caller to avoid NULL pointer dereference. Fixes: f942380c1239 ('net/mlx5: E-Switch, Vport ingress/egress ACLs rules for spoofchk') Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5e: Unregister netdev before detaching itMohamad Haj Yahia2-1/+2
Detaching the netdev before unregistering it cause some netdev cleanup ndos to fail because they check presence of the netdev, so we need to unregister the netdev first. Fixes: 26e59d8077a3 ('net/mlx5e: Implement mlx5e interface attach/detach callbacks') Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5e: Choose best nearest LRO timeoutSaeed Mahameed2-3/+21
Instead of predicting the index of the wanted LRO timeout value from hardware capabilities, look for the nearest LRO timeout value. Fixes: 5c50368f3831 ('net/mlx5e: Light-weight netdev open/stop') Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Correctly initialize last use of flow countersPaul Blakey1-0/+1
Currently, last use timestamp is initialized to zero. This is not the expected value by higher layers such as when we do TC action offloading. To fix that, set it to the current time, e.g when the counter/rule is offloaded. This is the same behaviour of non-offloaded TC actions. Fixes: 43a335e055bb ('mlx5_core: Flow counters infrastructure') Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Fix autogroups groups num not decreasingPaul Blakey1-0/+3
Autogroups groups num is increased when creating a new flow group, but is never decreased. Now decreasing it when deleting a flow group. Fixes: f0d22d187473 ('net/mlx5_core: Introduce flow steering autogrouped flow table') Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Keep autogroups list orderedPaul Blakey1-3/+3
Finding a new autogroup range is done by going over a group list sorted by each group start index. The search is stopped after finding the first free range. Adding the newly created group to the list is wrongly added to the end of the list regardless of its start index as the parameter of where to insert it is ignored. This commit makes sure to use that unused parameter to insert it where requested. Fixes: f0d22d187473 ('net/mlx5_core: Introduce flow steering autogrouped flow table') Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29net/mlx5: Always Query HCA caps after setting themDaniel Jurgens1-6/+6
Always query the HCA caps after setting them to update the capablities data structures. Not doing so results in incorrect capabilities being reported including max_dc, max_qp and several others. Fixes: 59211bd3b632 ("net/mlx5: Split the load/unload flow into hardware and software flows") Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29{net, ib}/mlx5: Make cache line size determination at runtime.Daniel Jurgens1-5/+26
ARM 64B cache line systems have L1_CACHE_BYTES set to 128. cache_line_size() will return the correct size. Fixes: cf50b5efa2fe('net/mlx5_core/ib: New device capabilities handling.') Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-28mlxsw: spectrum_router: Compare only trees which are in use during tree getJiri Pirko1-1/+2
Only trees which are in use should be compared to requested prefix usage. Fixes: 53342023eed9 ("mlxsw: spectrum_router: Implement LPM trees management") Signed-off-by: Jiri Pirko <jiri@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-28mlxsw: spectrum_router: Save requested prefix bitlist when creating treeJiri Pirko1-0/+2
Currently, the prefix bitlist is not saved for LPM trees, causing the compare to always fail which causes the tree to be destroyed and created for every inserted and removed FIB entry. So fix this by saving the bitlist as it should have been done from the very beginning. Fixes: 53342023eed9 ("mlxsw: spectrum_router: Implement LPM trees management") Signed-off-by: Jiri Pirko <jiri@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-20mlxsw: pci: Fix reset wait for SwitchX2Jiri Pirko1-2/+8
SwitchX2 firmware does not implement reset done yet. Moreover, when busy-polled for ready magic, that slows down firmware and reset takes longer than the defined timeout, causing initialization to fail. So restore the previous behaviour and just sleep in this case. Fixes: 233fa44bd67a ("mlxsw: pci: Implement reset done check") Signed-off-by: Jiri Pirko <jiri@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-20mlxsw: switchx2: Fix ethernet port initializationElad Raz1-0/+1
When creating an ethernet port fails, we must move the port to disable, otherwise putting the port in switch partition 0 (ETH) or 1 (IB) will always fails. Fixes: 31557f0f9755 ("mlxsw: Introduce Mellanox SwitchX-2 ASIC support") Signed-off-by: Elad Raz <eladr@mellanox.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-20mlxsw: spectrum_router: Make mlxsw_sp_router_fib4_del return void and remove warnJiri Pirko1-8/+5
The function return value is not checked anywhere. Also, the warning causes huge slowdown when removing large number of FIB entries which were not offloaded, because of ordering issue. Ido's preparing a patchset to fix the ordering issue, but that is definitelly not net tree material. Fixes: b45f64d16d45 ("mlxsw: spectrum_router: Use FIB notifications instead of switchdev calls") Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-20mlxsw: spectrum_router: Use correct tree index for bindingJiri Pirko1-1/+2
By a mistake, there is tree index 0 passed to RALTB. Should be MLXSW_SP_LPM_TREE_MIN. Fixes: b45f64d16d45 ("mlxsw: spectrum_router: Use FIB notifications instead of switchdev calls") Reported-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-14net/mlx4_en: fixup xdp tx irq to match rxBrenden Blanco1-1/+9
In cases where the number of tx rings is not a multiple of the number of rx rings, the tx completion event will be handled on a different core from the transmit and population of the ring. Races on the ring will lead to a double-free of the page, and possibly other corruption. The rings are initialized by default with a valid multiple of rings, based on the number of cpus, therefore an invalid configuration requires ethtool to change the ring layout. For instance 'ethtool -L eth0 rx 9 tx 8' will cause packets received on rx0, and XDP_TX'd to tx48, to be completed on cpu3 (48 % 9 == 3). Resolve this discrepancy by shifting the irq for the xdp tx queues to start again from 0, modulo rx_ring_num. Fixes: 9ecc2d86171a ("net/mlx4_en: add xdp forwarding and data write support") Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Brenden Blanco <bblanco@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-13net/mlx5: Add MLX5_ARRAY_SET64 to fix BUILD_BUG_ONTom Herbert1-2/+2
I am hitting this in mlx5: drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c: In function reclaim_pages_cmd.clone.0: drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:346: error: call to __compiletime_assert_346 declared with attribute error: BUILD_BUG_ON failed: __mlx5_bit_off(manage_pages_out, pas[i]) % 64 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c: In function give_pages: drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:291: error: call to __compiletime_assert_291 declared with attribute error: BUILD_BUG_ON failed: __mlx5_bit_off(manage_pages_in, pas[i]) % 64 Problem is that this is doing a BUILD_BUG_ON on a non-constant expression because of trying to take offset of pas[i] in the structure. Fix is to create MLX5_ARRAY_SET64 that takes an additional argument that is the field index to separate between BUILD_BUG_ON on the array constant field and the indexed field to assign the value to. There are two callers of MLX5_SET64 that are trying to get a variable offset, change those to call MLX5_ARRAY_SET64 passing 'pas' and 'i' as the arguments to use in the offset check and the indexed value assignment. Fixes: a533ed5e179cd ("net/mlx5: Pages management commands via mlx5 ifc") Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-09Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdmaLinus Torvalds1-3/+8
Pull main rdma updates from Doug Ledford: "This is the main pull request for the rdma stack this release. The code has been through 0day and I had it tagged for linux-next testing for a couple days. Summary: - updates to mlx5 - updates to mlx4 (two conflicts, both minor and easily resolved) - updates to iw_cxgb4 (one conflict, not so obvious to resolve, proper resolution is to keep the code in cxgb4_main.c as it is in Linus' tree as attach_uld was refactored and moved into cxgb4_uld.c) - improvements to uAPI (moved vendor specific API elements to uAPI area) - add hns-roce driver and hns and hns-roce ACPI reset support - conversion of all rdma code away from deprecated create_singlethread_workqueue - security improvement: remove unsafe ib_get_dma_mr (breaks lustre in staging)" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (75 commits) staging/lustre: Disable InfiniBand support iw_cxgb4: add fast-path for small REG_MR operations cxgb4: advertise support for FR_NSMR_TPTE_WR IB/core: correctly handle rdma_rw_init_mrs() failure IB/srp: Fix infinite loop when FMR sg[0].offset != 0 IB/srp: Remove an unused argument IB/core: Improve ib_map_mr_sg() documentation IB/mlx4: Fix possible vl/sl field mismatch in LRH header in QP1 packets IB/mthca: Move user vendor structures IB/nes: Move user vendor structures IB/ocrdma: Move user vendor structures IB/mlx4: Move user vendor structures IB/cxgb4: Move user vendor structures IB/cxgb3: Move user vendor structures IB/mlx5: Move and decouple user vendor structures IB/{core,hw}: Add constant for node_desc ipoib: Make ipoib_warn ratelimited IB/mlx4/alias_GUID: Remove deprecated create_singlethread_workqueue IB/ipoib_verbs: Remove deprecated create_singlethread_workqueue IB/ipoib: Remove deprecated create_singlethread_workqueue ...
2016-10-07IB/mlx4: Fix possible vl/sl field mismatch in LRH header in QP1 packetsJack Morgenstein1-4/+9
In MLX qp packets, the LRH (built by the driver) has both a VL field and an SL field. When building a QP1 packet, the VL field should reflect the SLtoVL mapping and not arbitrarily contain zero (as is done now). This bug causes credit problems in IB switches at high rates of QP1 packets. The fix is to cache the SL to VL mapping in the driver, and look up the VL mapped to the SL provided in the send request when sending QP1 packets. For FW versions which support generating a port_management_config_change event with subtype sl-to-vl-table-change, the driver uses that event to update its sl-to-vl mapping cache. Otherwise, the driver snoops incoming SMP mads to update the cache. There remains the case where the FW is running in secure-host mode (so no QP0 packets are delivered to the driver), and the FW does not generate the sl2vl mapping change event. To support this case, the driver updates (via querying the FW) its sl2vl mapping cache when running in secure-host mode when it receives either a Port Up event or a client-reregister event (where the port is still up, but there may have been an opensm failover). OpenSM modifies the sl2vl mapping before Port Up and Client-reregister events occur, so if there is a mapping change the driver's cache will be properly updated. Fixes: 225c7b1feef1 ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters") Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-04mlxsw: switchx2: Fix misuse of hard_header_lenYotam Gigi1-1/+1
In order to specify that the mlxsw switchx2 driver needs additional headroom for packets, there have been use of the hard_header_len field of the netdevice struct. This commit changes that to use needed_headroom instead, as this is the correct way to do that. Fixes: 31557f0f9755 ("mlxsw: Introduce Mellanox SwitchX-2 ASIC support") Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Acked-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-04mlxsw: spectrum: Fix misuse of hard_header_lenYotam Gigi1-1/+1
In order to specify that the mlxsw spectrum driver needs additional headroom for packets, there have been use of the hard_header_len field of the netdevice struct. This commit changes that to use needed_headroom instead, as this is the correct way to do that. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Acked-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-03mlxsw: spectrum_router: avoid potential uninitialized data usageArnd Bergmann1-3/+7
If fi->fib_nhs is zero, the router interface pointer is uninitialized, as shown by this warning: drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c: In function 'mlxsw_sp_router_fib_event': drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:1674:21: error: 'r' may be used uninitialized in this function [-Werror=maybe-uninitialized] drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:1643:23: note: 'r' was declared here This changes the loop so we handle the case the same way as finding no router interface pointer attached to one of the nexthops to ensure we always trap here instead of using uninitialized data. Fixes: b45f64d16d45 ("mlxsw: spectrum_router: Use FIB notifications instead of switchdev calls") Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.