- 09 Jan, 2017 3 commits
-
-
Eli Cohen authored
Current check requests that new fields in struct mlx5_ib_alloc_ucontext_req_v2 that are not known to the driver be zero. This was introduced so new libraries passing additional information to the kernel through struct mlx5_ib_alloc_ucontext_req_v2 will be notified by old kernels that do not support their request by failing the operation. This schecme is problematic since it requires libmlx5 to issue the requests with descending input size for struct mlx5_ib_alloc_ucontext_req_v2. To avoid this, we require that new features that will obey the following rules: If the feature requires one or more fields in the response and the at least one of the fields can be encoded such that a zero value means the kernel ignored the request then this field will provide the indication to the library. If no response is required or if zero is a valid response, a new field should be added that indicates to the library whether its request was processed. Fixes: b368d7cb ('IB/mlx5: Add hca_core_clock_offset to udata in init_ucontext') Signed-off-by:
Eli Cohen <eli@mellanox.com> Reviewed-by:
Matan Barak <matanb@mellanox.com> Signed-off-by:
Leon Romanovsky <leon@kernel.org> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com>
-
Eli Cohen authored
Make use of the blue flame registers allocator at mlx5_ib. Since blue flame was not really supported we remove all the code that is related to blue flame and we let all consumers to use the same blue flame register. Once blue flame is supported we will add the code. As part of this patch we also move the definition of struct mlx5_bf to mlx5_ib.h as it is only used by mlx5_ib. Signed-off-by:
-
Eli Cohen authored
A reference to a UAR is required to generate CQ or EQ doorbells. Since CQ or EQ doorbells can all be generated using the same UAR area without any effect on performance, we are just getting a reference to any available UAR, If one is not available we allocate it but we don't waste the blue flame registers it can provide and we will use them for subsequent allocations. We get a reference to such UAR and put in mlx5_priv so any kernel consumer can make use of it. Signed-off-by:
-
- 08 Jan, 2017 5 commits
-
-
Eli Cohen authored
Here is an implementation of an allocator that allocates blue flame registers. A blue flame register is used for generating send doorbells. A blue flame register can be used to generate either a regular doorbell or a blue flame doorbell where the data to be sent is written to the device's I/O memory hence saving the need to read the data from memory. For blue flame kind of doorbells to succeed, the blue flame register need to be mapped as write combining. The user can specify what kind of send doorbells she wishes to use. If she requested write combining mapping but that failed, the allocator will fall back to non write combining mapping and will indicate that to the user. Subsequent patches in this series will make use of this allocator. Signed-off-by:
-
Eli Cohen authored
First the function retrieving the index of the first hi latency class blue flame register. High latency class bfregs are located right above medium latency class bfregs. Fixes: c1be5232 ('IB/mlx5: Fix micro UAR allocator') Signed-off-by:
-
Eli Cohen authored
This establishes a solid naming conventions for UARs. A UAR (User Access Region) can have size identical to a system page or can be fixed 4KB depending on a value queried by firmware. Each UAR always has 4 blue flame register which are used to post doorbell to send queue. In addition, a UAR has section used for posting doorbells to CQs or EQs. In this patch we change names to reflect this conventions. Signed-off-by:
-
Eli Cohen authored
Make sure order of cleanup is exactly the opposite of initialization. Fixes: 9603b61d ('mlx5: Move pci device handling from mlx5_ib to mlx5_core') Signed-off-by:
-
Eli Cohen authored
The logic was broken as it failed to update the response length for architectures with PAGE_SIZE larger than 4kB. As a result further extension of the ucontext response struct would fail. Fixes: d69e3bcf ('IB/mlx5: Mmap the HCA's core clock register to user-space') Signed-off-by:
-
- 02 Jan, 2017 27 commits
-
-
David S. Miller authored
Saeed Mahameed says: ==================== Mellanox mlx5 core and ODP updates 2017-01-01 The following eleven patches mainly come from Artemy Kovalyov who expanded mlx5 on-demand-paging (ODP) support. In addition there are three cleanup patches which don't change any functionality, but are needed to align codebase prior accepting other patches. Memory region (MR) in IB can be huge and ODP (on-demand paging) technique allows to use unpinned memory, which can be consumed and released on demand. This allows to applications do not pin down the underlying physical pages of the address space, and save from them need to track the validity of the mappings. Rather, the HCA requests the latest translations from the OS when pages are not present, and the OS invalidates translations which are no longer valid due to either non-present pages or mapping changes. In existing ODP implementation applications is needed to register memory buffers for communication, though registered memory regions need not have valid mappings at registration time. This patch set performs the following steps to expand current ODP implementation: 1. It refactors UMR to support large regions, by introducing generic function to perform HCA translation table modifications. This function supports both atomic and process contexts and is not limited by number of modified entries. This function allows to enable reallocated memory regions of arbitrary size, so adding MR cache buckets to support up to 16GB MRs. 2. It changes page fault event format and refactor page faults logic together with addition of atomic support. 3. It prepares mlx5 core code to support implicit registration with simplified and relaxed semantics. Implicit ODP semantics allows to applications provide special memory key that represents their complete address space. Thus all IO accesses referencing to this key (with proper access rights associated with the key) wouldn't need not register any virtual address range. Thanks, Artemy, Ilya and Leon v1->v2: - Don't use 'inline' in .c files ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Artemy Kovalyov authored
Add "type" field to mlx5_core MKEY struct. Check whether page fault happens on MKEY corresponding to MR. Signed-off-by:
Artemy Kovalyov <artemyko@mellanox.com> Signed-off-by:
-
Artemy Kovalyov authored
Handle ODP atomic operations. When initiator of RDMA atomic operation use ODP MR to provide source data handle pagefault properly. Signed-off-by:
-
Artemy Kovalyov authored
* Update page fault event according to last specification. * Separate code path for page fault EQ, completion EQ and async EQ. * Move page fault handling work queue from mlx5_ib static variable into mlx5_core page fault EQ. * Allocate memory to store ODP event dynamically as the events arrive, since in atomic context - use mempool. * Make mlx5_ib page fault handler run in process context. Signed-off-by:
-
Artemy Kovalyov authored
Update PAGE_FAULT_RESUME command layout. Three bit fields describing page fault: rdma, rdma_write, req_res gave 8 possible combinations, while only a few were legal. Now they are interpreted as three-bit type field, where former legal combinations turns into corresponding types and unused were added as new types. Signed-off-by:
-
Artemy Kovalyov authored
In this change we turn mlx5_ib_update_mtt() into generic mlx5_ib_update_xlt() to perfrom HCA translation table modifiactions supporting both atomic and process contexts and not limited by number of modified entries. Using this function we increase preallocated MRs up to 16GB. Signed-off-by:
-
Artemy Kovalyov authored
Make use of extended UMR translation offset. Signed-off-by:
-
Artemy Kovalyov authored
* Update struct mlx5_wqe_umr_ctrl_seg. * Currenlty UMR send_flags aim only certain use cases: enabled/disable cached MR, modifying XLT for ODP. By making flags independent make UMR more flexible allowing arbitrary manipulations. * Since different UMR formats have different entry sizes UMR request should receive exact size of translation table update instead of number of entries. Rename field npages to xlt_size in struct mlx5_umr_wr and update relevant code accordingly. * Add support of length64 bit. Signed-off-by:
-
Artemy Kovalyov authored
This patch adds the following items to IFC file. 1. MLX5_MKC_ACCESS_MODE_KSM enum value for creating KSM memory keys. KSM access mode used when indirect MKey associated with fixed memory size entries. 2. null_mkey field that is used to indicate non-present KLM/KSM entries, where it causes the device to generate page fault event when trying to access it. 3. struct mlx5_ifc_cmd_hca_cap_bits capability bits indicating related value/field is supported: * fixed_buffer_size - MLX5_MKC_ACCESS_MODE_KSM * umr_extended_translation_offset - translation_offset_42_16 in UMR ctrl segment * null_mkey - null_mkey in QUERY_SPECIAL_CONTEXTS Signed-off-by: -
Binoy Jayan authored
Clean up the following common code (to post a list of work requests to the send queue of the specified QP) at various places and add a helper function 'mlx5_ib_post_send_wait' to implement the same. - Initialize 'mlx5_ib_umr_context' on stack - Assign "mlx5_umr_wr:wr:wr_cqe to umr_context.cqe - Acquire the semaphore - call ib_post_send with a single ib_send_wr - wait_for_completion() - Check for umr_context.status - Release the semaphore Signed-off-by:
Binoy Jayan <binoy.jayan@linaro.org> Signed-off-by:
-
Leon Romanovsky authored
The order of features exposed by private mlx5-abi.h file is CQE zipping, packet pacing and multi-packet WQE. The internal order implemented in mlx5_ib_query_device() is multi-packet WQE, CQE zipping and packet pacing. Such difference hurts code readability, so let's sync, while mlx5-abi.h (exposed to userspace) is the primary order. This commit doesn't change any functionality. Signed-off-by:
-
Max Gurtovoy authored
Fix offset for reserved fields. Fixes: 7486216b ("{net,IB}/mlx5: mlx5_ifc updates") Fixes: b4ff3a36 ("net/mlx5: Use offset based reserved field names in the IFC header file") Fixes: 7d5e1423 ("net/mlx5: Update mlx5_ifc hardware features") Signed-off-by:
Max Gurtovoy <maxg@mellanox.com> Reviewed-by:
-
David S. Miller authored
Merge tag 'wireless-drivers-next-for-davem-2017-01-02' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next Kalle Valo says: ==================== wireless-drivers-next patches for 4.11 The most notable change here is the inclusion of airtime fairness scheduling to ath9k. It prevents slow clients from hogging all the airtime and unfairly slowing down faster clients. Otherwise smaller changes and cleanup. Major changes: ath9k * cleanup eeprom endian handling * add airtime fairness scheduling ath10k * fix issues for new QCA9377 firmware version * support dev_coredump() for firmware crash dump * enable channel 169 on 5 GHz band ==================== Signed-off-by:
-
Niklas Cassel authored
For core revision 3.x Address-Aligned Beats is available in two registers. The DT property snps,aal was created for AAL in the DMA bus register, which is a read/write bit. The DT property snps,axi_all was created for AXI_AAL in the AXI bus mode register, which is a read only bit that reflects the value of AAL in the DMA bus register. Since the value of snps,axi_all is never used in the driver, and since the property was created for a bit that is read only, it should be safe to remove the property. Acked-by:
Giuseppe Cavallaro <peppe.cavallaro@st.com> Signed-off-by:
Niklas Cassel <niklas.cassel@axis.com> Signed-off-by:
-
David S. Miller authored
Yuval Mintz says: ==================== qed*: Driver updates The more interesting changes in this series include: - Restructuring of the qede files - qede_main.c has grown big and this series splits it into 3 parts [patches #2 and #3]. - Some significant changes in the API through which RSS indirection table gets configured [#8]. - Support for ndo_set_vf_trust() [#9] which would regulate which VFs are allowed to use promisc/multi-promisc mode. It also contains various minor changes to qed/qede, as well as non-functional changes [#1, #12] to complement other changes. ==================== Signed-off-by: -
Mintz, Yuval authored
Signed-off-by:
Yuval Mintz <Yuval.Mintz@cavium.com> Signed-off-by:
-
Ram Amrani authored
If qedr isn't part of the kernel then don't allocate RDMA resources for it in qed. Signed-off-by:
Ram Amrani <Ram.Amrani@cavium.com> Signed-off-by:
-
Mintz, Yuval authored
Currently multicast traffic wouldn't be routed internally to listener; Instead it would only be sent to network via the physical carrier. Signed-off-by:
-
Mintz, Yuval authored
Trusted VFs would be allowed to receive promiscuous and multicast promiscuous data. Signed-off-by:
-
Mintz, Yuval authored
A step toward having qede agnostic to the queue configurations in firmware/hardware - let the RSS indirections use queue handles instead of actual queue indices. Signed-off-by:
-
Mintz, Yuval authored
Signed-off-by:
-
Manish Chopra authored
When driver receives a recognized encapsulated packet it needs to set the skb->encapsulation field as well. Signed-off-by:
Manish Chopra <Manish.Chopra@cavium.com> Signed-off-by:
-
Mintz, Yuval authored
During Rx flow driver allocates a replacement buffer each time it consumes an Rx buffer. Failing to do so, it would consume the currently processed buffer and re-post it on the ring. As a result, the Rx ring is always completely full [from driver POV]. We now allow the Rx ring to shorten by doing the re-allocations at the end of the NAPI run. The only limitation is that we still want to make sure each time we reallocate that we'd still have sufficient elements in the Rx ring to guarantee that FW would be able to post additional data and trigger an interrupt. Signed-off-by:
-
Mintz, Yuval authored
Today qede requests contexts that would suffice for 64 'whole' combined queues [192 meant for 64 rx, tx and xdp tx queues], but registers netdev and limits the number of queues based on information received by qed. In turn, qed doesn't take context into account when informing qede how many queues it can support. This would lead to a configuration problem in case user tries configuring >64 combined queues to interface [or >96 in case xdp isn't enabled]. Since we don't have a mangement firware that actually provides so many interrupt lines to a single device we're currently safe but that's about to change soon. The new maximum is hence changed: - For RoCE devices, the limit would remain 64. - For non-RoCE devices, the limit might be higher [depending on the actual configuration of the device]. qed would start enforcing that limit in both scenarios. Signed-off-by: -
Mintz, Yuval authored
This takes the various filtering logic of the driver and moves them into their own dedicated file - qede_filter.c. Signed-off-by:
-
Mintz, Yuval authored
This adds a new file qede_fp.c and relocates the datapath-related logic into it [from qede_main.c]. Signed-off-by:
-
Mintz, Yuval authored
Since the submission of the qedr driver, there's inconsistency in the licensing of the various qed/qede files - some are GPLv2 and some are dual-license. Since qedr requires dual-license and it's dependent on both, we're updating the licensing of all qed/qede source files. Signed-off-by:
-
- 01 Jan, 2017 3 commits
-
-
Colin Ian King authored
trivial fix to spelling mistake in RT_TRACE message Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
Kalle Valo <kvalo@codeaurora.org>
-
Colin Ian King authored
trivial fix to spelling mistake of function name in wl1271_warning, should be dynamic_ps_timeout instead of dyanmic_ps_timeout. Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.gitKalle Valo authored
ath.git patches for 4.11. Major changes: ath9k * cleanup eeprom endian handling * add airtime fairness scheduling ath10k * fix issues for new QCA9377 firmware version * support dev_coredump() for firmware crash dump * enable channel 169 on 5 GHz band
-
- 30 Dec, 2016 2 commits
-
-
Thomas Preisner authored
In some cases the return value of a failing function is not being used and the function typhoon_init_one() returns another negative error code instead. Signed-off-by:
Thomas Preisner <thomas.preisner+linux@fau.de> Signed-off-by:
Milan Stephan <milan.stephan+linux@fau.de> Signed-off-by:
-
Thomas Preisner authored
In a few cases the err-variable is not set to a negative error code if a function call in typhoon_init_one() fails and thus 0 is returned instead. It may be better to set err to the appropriate negative error code before returning. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=188841Reported-by:
Pan Bian <bianpan2016@163.com> Signed-off-by:
-
